diff --git a/README.md b/README.md
index 80ee0ae2b01a96ab60dd97039764ed018ddcd8e2..248024822db84371dc4febe0f34f51fbf9c36e22 100644
--- a/README.md
+++ b/README.md
@@ -4,90 +4,6 @@ library_name: peft
 ## Training procedure
 
 
-The following `bitsandbytes` quantization config was used during training:
-- quant_method: bitsandbytes
-- load_in_8bit: True
-- load_in_4bit: False
-- llm_int8_threshold: 6.0
-- llm_int8_skip_modules: None
-- llm_int8_enable_fp32_cpu_offload: False
-- llm_int8_has_fp16_weight: False
-- bnb_4bit_quant_type: fp4
-- bnb_4bit_use_double_quant: False
-- bnb_4bit_compute_dtype: float32
-
-The following `bitsandbytes` quantization config was used during training:
-- quant_method: bitsandbytes
-- load_in_8bit: True
-- load_in_4bit: False
-- llm_int8_threshold: 6.0
-- llm_int8_skip_modules: None
-- llm_int8_enable_fp32_cpu_offload: False
-- llm_int8_has_fp16_weight: False
-- bnb_4bit_quant_type: fp4
-- bnb_4bit_use_double_quant: False
-- bnb_4bit_compute_dtype: float32
-
-The following `bitsandbytes` quantization config was used during training:
-- quant_method: bitsandbytes
-- load_in_8bit: True
-- load_in_4bit: False
-- llm_int8_threshold: 6.0
-- llm_int8_skip_modules: None
-- llm_int8_enable_fp32_cpu_offload: False
-- llm_int8_has_fp16_weight: False
-- bnb_4bit_quant_type: fp4
-- bnb_4bit_use_double_quant: False
-- bnb_4bit_compute_dtype: float32
-
-The following `bitsandbytes` quantization config was used during training:
-- quant_method: bitsandbytes
-- load_in_8bit: True
-- load_in_4bit: False
-- llm_int8_threshold: 6.0
-- llm_int8_skip_modules: None
-- llm_int8_enable_fp32_cpu_offload: False
-- llm_int8_has_fp16_weight: False
-- bnb_4bit_quant_type: fp4
-- bnb_4bit_use_double_quant: False
-- bnb_4bit_compute_dtype: float32
-
-The following `bitsandbytes` quantization config was used during training:
-- quant_method: bitsandbytes
-- load_in_8bit: True
-- load_in_4bit: False
-- llm_int8_threshold: 6.0
-- llm_int8_skip_modules: None
-- llm_int8_enable_fp32_cpu_offload: False
-- llm_int8_has_fp16_weight: False
-- bnb_4bit_quant_type: fp4
-- bnb_4bit_use_double_quant: False
-- bnb_4bit_compute_dtype: float32
-
-The following `bitsandbytes` quantization config was used during training:
-- quant_method: bitsandbytes
-- load_in_8bit: True
-- load_in_4bit: False
-- llm_int8_threshold: 6.0
-- llm_int8_skip_modules: None
-- llm_int8_enable_fp32_cpu_offload: False
-- llm_int8_has_fp16_weight: False
-- bnb_4bit_quant_type: fp4
-- bnb_4bit_use_double_quant: False
-- bnb_4bit_compute_dtype: float32
-
-The following `bitsandbytes` quantization config was used during training:
-- quant_method: bitsandbytes
-- load_in_8bit: True
-- load_in_4bit: False
-- llm_int8_threshold: 6.0
-- llm_int8_skip_modules: None
-- llm_int8_enable_fp32_cpu_offload: False
-- llm_int8_has_fp16_weight: False
-- bnb_4bit_quant_type: fp4
-- bnb_4bit_use_double_quant: False
-- bnb_4bit_compute_dtype: float32
-
 The following `bitsandbytes` quantization config was used during training:
 - quant_method: bitsandbytes
 - load_in_8bit: True
@@ -149,13 +65,6 @@ The following `bitsandbytes` quantization config was used during training:
 - bnb_4bit_compute_dtype: float32
 ### Framework versions
 
-- PEFT 0.6.0.dev0
-- PEFT 0.6.0.dev0
-- PEFT 0.6.0.dev0
-- PEFT 0.6.0.dev0
-- PEFT 0.6.0.dev0
-- PEFT 0.6.0.dev0
-- PEFT 0.6.0.dev0
 - PEFT 0.6.0.dev0
 - PEFT 0.6.0.dev0
 - PEFT 0.6.0.dev0
diff --git a/adapter_model.bin b/adapter_model.bin
index 769701ae943c9ac01dcd07f8a646624dea495446..91e98fe05a6d865275fa50fd4f2ae6e8c6a67cee 100644
--- a/adapter_model.bin
+++ b/adapter_model.bin
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab7d7332df354d85019ef8dbda22bf275f3e4612ebbe07ca7d3538dd755384e9
+oid sha256:e4ecd5f337c6a7563a7858b385415fc38ee7d3ebdd64f3cbdff82c605ba198cd
 size 39409357
diff --git a/checkpoint-100/README.md b/checkpoint-100/README.md
index 08371015f02382e6fcba318f4aaea54ae52cd3c4..80ee0ae2b01a96ab60dd97039764ed018ddcd8e2 100644
--- a/checkpoint-100/README.md
+++ b/checkpoint-100/README.md
@@ -4,6 +4,126 @@ library_name: peft
 ## Training procedure
 
 
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: True
+- load_in_4bit: False
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: True
+- load_in_4bit: False
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: True
+- load_in_4bit: False
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: True
+- load_in_4bit: False
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: True
+- load_in_4bit: False
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: True
+- load_in_4bit: False
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: True
+- load_in_4bit: False
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: True
+- load_in_4bit: False
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: True
+- load_in_4bit: False
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: True
+- load_in_4bit: False
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+
 The following `bitsandbytes` quantization config was used during training:
 - quant_method: bitsandbytes
 - load_in_8bit: True
@@ -29,6 +149,16 @@ The following `bitsandbytes` quantization config was used during training:
 - bnb_4bit_compute_dtype: float32
 ### Framework versions
 
+- PEFT 0.6.0.dev0
+- PEFT 0.6.0.dev0
+- PEFT 0.6.0.dev0
+- PEFT 0.6.0.dev0
+- PEFT 0.6.0.dev0
+- PEFT 0.6.0.dev0
+- PEFT 0.6.0.dev0
+- PEFT 0.6.0.dev0
+- PEFT 0.6.0.dev0
+- PEFT 0.6.0.dev0
 - PEFT 0.6.0.dev0
 
 - PEFT 0.6.0.dev0
diff --git a/checkpoint-100/adapter_model.bin b/checkpoint-100/adapter_model.bin
index 9cefddebe32057b0552baedbf3a139d5b5054704..769701ae943c9ac01dcd07f8a646624dea495446 100644
--- a/checkpoint-100/adapter_model.bin
+++ b/checkpoint-100/adapter_model.bin
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1494d9295feb24e846e9762b1b2118d8c5592c6b44f650b463565b33581b2bd
+oid sha256:ab7d7332df354d85019ef8dbda22bf275f3e4612ebbe07ca7d3538dd755384e9
 size 39409357
diff --git a/checkpoint-100/optimizer.pt b/checkpoint-100/optimizer.pt
index fac0f5f0b3493cc8e6ed7517e64a85da03a95adc..34032801bbe67857d30692ed9898878d063cb7e7 100644
--- a/checkpoint-100/optimizer.pt
+++ b/checkpoint-100/optimizer.pt
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0a5a340ededaf6a479a86b5f1d38b1ad96df10d24d2e3b600016733e406c965
+oid sha256:8e7ecf4519b7c7fe30096c1ce0de750678f8cf403d65a166a096e8155b6d1665
 size 78844421
diff --git a/checkpoint-100/rng_state.pth b/checkpoint-100/rng_state.pth
index 452f99ac534b9117d836494d73222e3d44e1523b..e8a62beafdd6e61c41abbc54c8b7428f4e3484c0 100644
--- a/checkpoint-100/rng_state.pth
+++ b/checkpoint-100/rng_state.pth
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6869750f95a25c4e970298a33adf90e2d7ab52680bf3317239bff1b10103235
+oid sha256:b2278a87cdf86c3f9219223c847f6b27f6b7f15b8226b617f38936e8ff2cbcde
 size 14575
diff --git a/checkpoint-100/scheduler.pt b/checkpoint-100/scheduler.pt
index 1e03fe8e3f8f657765fc796487ba79b428fc773d..bb6d23cefeb42e3de94cbbe62d4d34c67e305d59 100644
--- a/checkpoint-100/scheduler.pt
+++ b/checkpoint-100/scheduler.pt
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a58b95c1126bab491ac28f5f742cbad6d9169c46a57b0c332b4be7e7507c82f5
+oid sha256:02822a64d6ab3629baf2f69c5adf000658973be0bc2532154cc2534085175f34
 size 627
diff --git a/checkpoint-100/tokenizer.json b/checkpoint-100/tokenizer.json
index dbf002cafbd4818dcff2abc9156c088d681b4533..673c31abdeadf6576c3c754df86459e1ad64e207 100644
--- a/checkpoint-100/tokenizer.json
+++ b/checkpoint-100/tokenizer.json
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17a208233d2ee8d8c83b23bc214df737c44806a1919f444e89b31e586cd956ba
-size 14500471
+oid sha256:85b00d7db4df5df2e3f01cacc3feda246002a672f3356eec7f4b04a22eb0dfbe
+size 14500570
diff --git a/checkpoint-100/trainer_state.json b/checkpoint-100/trainer_state.json
index 522ea2d0c726e7f11042bb7fa90f062916630bba..5e07f9780764385efc69f7e354fe98c6a40d34a0 100644
--- a/checkpoint-100/trainer_state.json
+++ b/checkpoint-100/trainer_state.json
@@ -1,7 +1,7 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.0,
+  "epoch": 0.3429796355841372,
   "eval_steps": 500,
   "global_step": 100,
   "is_hyper_param_search": false,
@@ -9,611 +9,611 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.04,
-      "learning_rate": 0.0001996,
-      "loss": 2.4683,
+      "epoch": 0.0,
+      "learning_rate": 0.00019931271477663232,
+      "loss": 2.5587,
       "step": 1
     },
     {
-      "epoch": 0.08,
-      "learning_rate": 0.00019920000000000002,
-      "loss": 2.2023,
+      "epoch": 0.01,
+      "learning_rate": 0.0001986254295532646,
+      "loss": 2.3914,
       "step": 2
     },
     {
-      "epoch": 0.12,
-      "learning_rate": 0.0001988,
-      "loss": 2.3039,
+      "epoch": 0.01,
+      "learning_rate": 0.00019793814432989693,
+      "loss": 2.4218,
       "step": 3
     },
     {
-      "epoch": 0.16,
-      "learning_rate": 0.0001984,
-      "loss": 2.1855,
+      "epoch": 0.01,
+      "learning_rate": 0.00019725085910652924,
+      "loss": 2.3414,
       "step": 4
     },
     {
-      "epoch": 0.2,
-      "learning_rate": 0.00019800000000000002,
-      "loss": 2.328,
+      "epoch": 0.02,
+      "learning_rate": 0.0001965635738831615,
+      "loss": 2.2469,
       "step": 5
     },
     {
-      "epoch": 0.24,
-      "learning_rate": 0.0001976,
-      "loss": 2.3407,
+      "epoch": 0.02,
+      "learning_rate": 0.00019587628865979381,
+      "loss": 2.3241,
       "step": 6
     },
     {
-      "epoch": 0.28,
-      "learning_rate": 0.0001972,
-      "loss": 2.3432,
+      "epoch": 0.02,
+      "learning_rate": 0.00019518900343642613,
+      "loss": 2.3266,
       "step": 7
     },
     {
-      "epoch": 0.32,
-      "learning_rate": 0.0001968,
-      "loss": 2.2333,
+      "epoch": 0.03,
+      "learning_rate": 0.00019450171821305842,
+      "loss": 2.1856,
       "step": 8
     },
     {
-      "epoch": 0.36,
-      "learning_rate": 0.0001964,
-      "loss": 2.1761,
+      "epoch": 0.03,
+      "learning_rate": 0.00019381443298969073,
+      "loss": 2.3247,
       "step": 9
     },
     {
-      "epoch": 0.4,
-      "learning_rate": 0.000196,
-      "loss": 2.1473,
+      "epoch": 0.03,
+      "learning_rate": 0.00019312714776632305,
+      "loss": 2.3245,
       "step": 10
     },
     {
-      "epoch": 0.44,
-      "learning_rate": 0.0001956,
-      "loss": 2.2076,
+      "epoch": 0.04,
+      "learning_rate": 0.00019243986254295533,
+      "loss": 2.2591,
       "step": 11
     },
     {
-      "epoch": 0.48,
-      "learning_rate": 0.0001952,
-      "loss": 2.1925,
+      "epoch": 0.04,
+      "learning_rate": 0.00019175257731958765,
+      "loss": 2.1767,
       "step": 12
     },
     {
-      "epoch": 0.52,
-      "learning_rate": 0.0001948,
-      "loss": 2.1694,
+      "epoch": 0.04,
+      "learning_rate": 0.00019106529209621996,
+      "loss": 2.3478,
       "step": 13
     },
     {
-      "epoch": 0.56,
-      "learning_rate": 0.0001944,
-      "loss": 2.1056,
+      "epoch": 0.05,
+      "learning_rate": 0.00019037800687285222,
+      "loss": 2.3339,
       "step": 14
     },
     {
-      "epoch": 0.6,
-      "learning_rate": 0.000194,
-      "loss": 2.2426,
+      "epoch": 0.05,
+      "learning_rate": 0.00018969072164948454,
+      "loss": 2.234,
       "step": 15
     },
     {
-      "epoch": 0.64,
-      "learning_rate": 0.00019360000000000002,
-      "loss": 2.2635,
+      "epoch": 0.05,
+      "learning_rate": 0.00018900343642611685,
+      "loss": 2.2651,
       "step": 16
     },
     {
-      "epoch": 0.68,
-      "learning_rate": 0.0001932,
-      "loss": 2.251,
+      "epoch": 0.06,
+      "learning_rate": 0.00018831615120274914,
+      "loss": 2.1831,
       "step": 17
     },
     {
-      "epoch": 0.72,
-      "learning_rate": 0.0001928,
-      "loss": 2.224,
+      "epoch": 0.06,
+      "learning_rate": 0.00018762886597938145,
+      "loss": 2.216,
       "step": 18
     },
     {
-      "epoch": 0.76,
-      "learning_rate": 0.00019240000000000001,
-      "loss": 2.1848,
+      "epoch": 0.07,
+      "learning_rate": 0.00018694158075601377,
+      "loss": 2.1359,
       "step": 19
     },
     {
-      "epoch": 0.8,
-      "learning_rate": 0.000192,
-      "loss": 2.1341,
+      "epoch": 0.07,
+      "learning_rate": 0.00018625429553264605,
+      "loss": 2.1215,
       "step": 20
     },
     {
-      "epoch": 0.84,
-      "learning_rate": 0.0001916,
-      "loss": 2.126,
+      "epoch": 0.07,
+      "learning_rate": 0.00018556701030927837,
+      "loss": 2.2179,
       "step": 21
     },
     {
-      "epoch": 0.88,
-      "learning_rate": 0.0001912,
-      "loss": 2.0959,
+      "epoch": 0.08,
+      "learning_rate": 0.00018487972508591068,
+      "loss": 2.2598,
       "step": 22
     },
     {
-      "epoch": 0.92,
-      "learning_rate": 0.0001908,
-      "loss": 2.2446,
+      "epoch": 0.08,
+      "learning_rate": 0.00018419243986254294,
+      "loss": 2.1813,
       "step": 23
     },
     {
-      "epoch": 0.96,
-      "learning_rate": 0.0001904,
-      "loss": 1.9448,
+      "epoch": 0.08,
+      "learning_rate": 0.00018350515463917526,
+      "loss": 2.2006,
       "step": 24
     },
     {
-      "epoch": 1.0,
-      "learning_rate": 0.00019,
-      "loss": 2.0939,
+      "epoch": 0.09,
+      "learning_rate": 0.00018281786941580757,
+      "loss": 2.1564,
       "step": 25
     },
     {
-      "epoch": 1.04,
-      "learning_rate": 0.0001896,
-      "loss": 2.1247,
+      "epoch": 0.09,
+      "learning_rate": 0.00018213058419243986,
+      "loss": 2.2537,
       "step": 26
     },
     {
-      "epoch": 1.08,
-      "learning_rate": 0.0001892,
-      "loss": 1.9417,
+      "epoch": 0.09,
+      "learning_rate": 0.00018144329896907217,
+      "loss": 2.1975,
       "step": 27
     },
     {
-      "epoch": 1.12,
-      "learning_rate": 0.0001888,
-      "loss": 2.105,
+      "epoch": 0.1,
+      "learning_rate": 0.0001807560137457045,
+      "loss": 2.2566,
       "step": 28
     },
     {
-      "epoch": 1.16,
-      "learning_rate": 0.0001884,
-      "loss": 2.1595,
+      "epoch": 0.1,
+      "learning_rate": 0.00018006872852233677,
+      "loss": 2.1464,
       "step": 29
     },
     {
-      "epoch": 1.2,
-      "learning_rate": 0.000188,
-      "loss": 2.2009,
+      "epoch": 0.1,
+      "learning_rate": 0.0001793814432989691,
+      "loss": 2.1421,
       "step": 30
     },
     {
-      "epoch": 1.24,
-      "learning_rate": 0.0001876,
-      "loss": 2.0784,
+      "epoch": 0.11,
+      "learning_rate": 0.0001786941580756014,
+      "loss": 2.1276,
       "step": 31
     },
     {
-      "epoch": 1.28,
-      "learning_rate": 0.00018720000000000002,
-      "loss": 2.2173,
+      "epoch": 0.11,
+      "learning_rate": 0.00017800687285223366,
+      "loss": 2.0649,
       "step": 32
     },
     {
-      "epoch": 1.32,
-      "learning_rate": 0.00018680000000000001,
-      "loss": 2.1185,
+      "epoch": 0.11,
+      "learning_rate": 0.00017731958762886598,
+      "loss": 2.1835,
       "step": 33
     },
     {
-      "epoch": 1.36,
-      "learning_rate": 0.00018640000000000003,
-      "loss": 1.988,
+      "epoch": 0.12,
+      "learning_rate": 0.0001766323024054983,
+      "loss": 2.1711,
       "step": 34
     },
     {
-      "epoch": 1.4,
-      "learning_rate": 0.00018600000000000002,
-      "loss": 1.9493,
+      "epoch": 0.12,
+      "learning_rate": 0.00017594501718213058,
+      "loss": 2.2591,
       "step": 35
     },
     {
-      "epoch": 1.44,
-      "learning_rate": 0.0001856,
-      "loss": 1.9947,
+      "epoch": 0.12,
+      "learning_rate": 0.0001752577319587629,
+      "loss": 2.1471,
       "step": 36
     },
     {
-      "epoch": 1.48,
-      "learning_rate": 0.00018520000000000003,
-      "loss": 2.0506,
+      "epoch": 0.13,
+      "learning_rate": 0.0001745704467353952,
+      "loss": 2.0861,
       "step": 37
     },
     {
-      "epoch": 1.52,
-      "learning_rate": 0.00018480000000000002,
-      "loss": 2.0829,
+      "epoch": 0.13,
+      "learning_rate": 0.0001738831615120275,
+      "loss": 2.0702,
       "step": 38
     },
     {
-      "epoch": 1.56,
-      "learning_rate": 0.0001844,
-      "loss": 2.1455,
+      "epoch": 0.13,
+      "learning_rate": 0.0001731958762886598,
+      "loss": 2.1096,
       "step": 39
     },
     {
-      "epoch": 1.6,
-      "learning_rate": 0.00018400000000000003,
-      "loss": 2.0304,
+      "epoch": 0.14,
+      "learning_rate": 0.00017250859106529212,
+      "loss": 2.1062,
       "step": 40
     },
     {
-      "epoch": 1.64,
-      "learning_rate": 0.00018360000000000002,
-      "loss": 2.006,
+      "epoch": 0.14,
+      "learning_rate": 0.00017182130584192438,
+      "loss": 2.2545,
       "step": 41
     },
     {
-      "epoch": 1.68,
-      "learning_rate": 0.0001832,
-      "loss": 2.1759,
+      "epoch": 0.14,
+      "learning_rate": 0.0001711340206185567,
+      "loss": 2.1572,
       "step": 42
     },
     {
-      "epoch": 1.72,
-      "learning_rate": 0.00018280000000000003,
-      "loss": 2.0093,
+      "epoch": 0.15,
+      "learning_rate": 0.000170446735395189,
+      "loss": 2.0749,
       "step": 43
     },
     {
-      "epoch": 1.76,
-      "learning_rate": 0.00018240000000000002,
-      "loss": 2.0683,
+      "epoch": 0.15,
+      "learning_rate": 0.0001697594501718213,
+      "loss": 2.1922,
       "step": 44
     },
     {
-      "epoch": 1.8,
-      "learning_rate": 0.000182,
-      "loss": 2.1352,
+      "epoch": 0.15,
+      "learning_rate": 0.00016907216494845361,
+      "loss": 2.1915,
       "step": 45
     },
     {
-      "epoch": 1.84,
-      "learning_rate": 0.00018160000000000002,
-      "loss": 1.9736,
+      "epoch": 0.16,
+      "learning_rate": 0.00016838487972508593,
+      "loss": 2.1594,
       "step": 46
     },
     {
-      "epoch": 1.88,
-      "learning_rate": 0.0001812,
-      "loss": 1.9631,
+      "epoch": 0.16,
+      "learning_rate": 0.00016769759450171822,
+      "loss": 2.176,
       "step": 47
     },
     {
-      "epoch": 1.92,
-      "learning_rate": 0.0001808,
-      "loss": 2.1024,
+      "epoch": 0.16,
+      "learning_rate": 0.00016701030927835053,
+      "loss": 2.1223,
       "step": 48
     },
     {
-      "epoch": 1.96,
-      "learning_rate": 0.00018040000000000002,
-      "loss": 1.9895,
+      "epoch": 0.17,
+      "learning_rate": 0.00016632302405498285,
+      "loss": 2.1263,
       "step": 49
     },
     {
-      "epoch": 2.0,
-      "learning_rate": 0.00018,
-      "loss": 2.0067,
+      "epoch": 0.17,
+      "learning_rate": 0.00016563573883161513,
+      "loss": 2.0481,
       "step": 50
     },
     {
-      "epoch": 2.04,
-      "learning_rate": 0.0001796,
-      "loss": 2.0509,
+      "epoch": 0.17,
+      "learning_rate": 0.00016494845360824742,
+      "loss": 2.1043,
       "step": 51
     },
     {
-      "epoch": 2.08,
-      "learning_rate": 0.00017920000000000002,
-      "loss": 1.8795,
+      "epoch": 0.18,
+      "learning_rate": 0.00016426116838487973,
+      "loss": 2.1678,
       "step": 52
     },
     {
-      "epoch": 2.12,
-      "learning_rate": 0.0001788,
-      "loss": 2.0633,
+      "epoch": 0.18,
+      "learning_rate": 0.00016357388316151202,
+      "loss": 2.1602,
       "step": 53
     },
     {
-      "epoch": 2.16,
-      "learning_rate": 0.0001784,
-      "loss": 1.9998,
+      "epoch": 0.19,
+      "learning_rate": 0.00016288659793814434,
+      "loss": 2.1448,
       "step": 54
     },
     {
-      "epoch": 2.2,
-      "learning_rate": 0.00017800000000000002,
-      "loss": 2.0675,
+      "epoch": 0.19,
+      "learning_rate": 0.00016219931271477665,
+      "loss": 2.1536,
       "step": 55
     },
     {
-      "epoch": 2.24,
-      "learning_rate": 0.0001776,
-      "loss": 2.0129,
+      "epoch": 0.19,
+      "learning_rate": 0.00016151202749140894,
+      "loss": 2.0339,
       "step": 56
     },
     {
-      "epoch": 2.28,
-      "learning_rate": 0.0001772,
-      "loss": 1.9302,
+      "epoch": 0.2,
+      "learning_rate": 0.00016082474226804125,
+      "loss": 2.023,
       "step": 57
     },
     {
-      "epoch": 2.32,
-      "learning_rate": 0.00017680000000000001,
-      "loss": 2.0472,
+      "epoch": 0.2,
+      "learning_rate": 0.00016013745704467357,
+      "loss": 2.1407,
       "step": 58
     },
     {
-      "epoch": 2.36,
-      "learning_rate": 0.0001764,
-      "loss": 2.0031,
+      "epoch": 0.2,
+      "learning_rate": 0.00015945017182130585,
+      "loss": 2.1134,
       "step": 59
     },
     {
-      "epoch": 2.4,
-      "learning_rate": 0.00017600000000000002,
-      "loss": 2.0231,
+      "epoch": 0.21,
+      "learning_rate": 0.00015876288659793814,
+      "loss": 2.1652,
       "step": 60
     },
     {
-      "epoch": 2.44,
-      "learning_rate": 0.0001756,
-      "loss": 2.0192,
+      "epoch": 0.21,
+      "learning_rate": 0.00015807560137457046,
+      "loss": 2.0051,
       "step": 61
     },
     {
-      "epoch": 2.48,
-      "learning_rate": 0.0001752,
-      "loss": 2.1336,
+      "epoch": 0.21,
+      "learning_rate": 0.00015738831615120274,
+      "loss": 2.0604,
       "step": 62
     },
     {
-      "epoch": 2.52,
-      "learning_rate": 0.00017480000000000002,
-      "loss": 1.7753,
+      "epoch": 0.22,
+      "learning_rate": 0.00015670103092783506,
+      "loss": 2.1708,
       "step": 63
     },
     {
-      "epoch": 2.56,
-      "learning_rate": 0.0001744,
-      "loss": 2.0274,
+      "epoch": 0.22,
+      "learning_rate": 0.00015601374570446737,
+      "loss": 2.1106,
       "step": 64
     },
     {
-      "epoch": 2.6,
-      "learning_rate": 0.000174,
-      "loss": 1.8893,
+      "epoch": 0.22,
+      "learning_rate": 0.00015532646048109966,
+      "loss": 2.1445,
       "step": 65
     },
     {
-      "epoch": 2.64,
-      "learning_rate": 0.00017360000000000002,
-      "loss": 2.0341,
+      "epoch": 0.23,
+      "learning_rate": 0.00015463917525773197,
+      "loss": 2.0879,
       "step": 66
     },
     {
-      "epoch": 2.68,
-      "learning_rate": 0.0001732,
-      "loss": 2.1081,
+      "epoch": 0.23,
+      "learning_rate": 0.0001539518900343643,
+      "loss": 2.1498,
       "step": 67
     },
     {
-      "epoch": 2.72,
-      "learning_rate": 0.0001728,
-      "loss": 1.9463,
+      "epoch": 0.23,
+      "learning_rate": 0.00015326460481099657,
+      "loss": 2.0719,
       "step": 68
     },
     {
-      "epoch": 2.76,
-      "learning_rate": 0.00017240000000000002,
-      "loss": 2.0607,
+      "epoch": 0.24,
+      "learning_rate": 0.00015257731958762886,
+      "loss": 2.2167,
       "step": 69
     },
     {
-      "epoch": 2.8,
-      "learning_rate": 0.000172,
-      "loss": 1.9803,
+      "epoch": 0.24,
+      "learning_rate": 0.00015189003436426118,
+      "loss": 2.0811,
       "step": 70
     },
     {
-      "epoch": 2.84,
-      "learning_rate": 0.0001716,
-      "loss": 1.7663,
+      "epoch": 0.24,
+      "learning_rate": 0.00015120274914089346,
+      "loss": 2.1058,
       "step": 71
     },
     {
-      "epoch": 2.88,
-      "learning_rate": 0.00017120000000000001,
-      "loss": 2.1116,
+      "epoch": 0.25,
+      "learning_rate": 0.00015051546391752578,
+      "loss": 2.0392,
       "step": 72
     },
     {
-      "epoch": 2.92,
-      "learning_rate": 0.0001708,
-      "loss": 1.9039,
+      "epoch": 0.25,
+      "learning_rate": 0.0001498281786941581,
+      "loss": 2.0957,
       "step": 73
     },
     {
-      "epoch": 2.96,
-      "learning_rate": 0.0001704,
-      "loss": 2.049,
+      "epoch": 0.25,
+      "learning_rate": 0.00014914089347079038,
+      "loss": 1.9994,
       "step": 74
     },
     {
-      "epoch": 3.0,
-      "learning_rate": 0.00017,
-      "loss": 1.991,
+      "epoch": 0.26,
+      "learning_rate": 0.0001484536082474227,
+      "loss": 2.0464,
       "step": 75
     },
     {
-      "epoch": 3.04,
-      "learning_rate": 0.0001696,
-      "loss": 1.8755,
+      "epoch": 0.26,
+      "learning_rate": 0.000147766323024055,
+      "loss": 2.0417,
       "step": 76
     },
     {
-      "epoch": 3.08,
-      "learning_rate": 0.0001692,
-      "loss": 2.0367,
+      "epoch": 0.26,
+      "learning_rate": 0.0001470790378006873,
+      "loss": 2.105,
       "step": 77
     },
     {
-      "epoch": 3.12,
-      "learning_rate": 0.0001688,
-      "loss": 1.9959,
+      "epoch": 0.27,
+      "learning_rate": 0.00014639175257731958,
+      "loss": 2.1147,
       "step": 78
     },
     {
-      "epoch": 3.16,
-      "learning_rate": 0.0001684,
-      "loss": 1.8051,
+      "epoch": 0.27,
+      "learning_rate": 0.0001457044673539519,
+      "loss": 1.9964,
       "step": 79
     },
     {
-      "epoch": 3.2,
-      "learning_rate": 0.000168,
-      "loss": 2.0446,
+      "epoch": 0.27,
+      "learning_rate": 0.00014501718213058418,
+      "loss": 1.9723,
       "step": 80
     },
     {
-      "epoch": 3.24,
-      "learning_rate": 0.0001676,
-      "loss": 1.7873,
+      "epoch": 0.28,
+      "learning_rate": 0.0001443298969072165,
+      "loss": 2.0621,
       "step": 81
     },
     {
-      "epoch": 3.28,
-      "learning_rate": 0.0001672,
-      "loss": 1.9264,
+      "epoch": 0.28,
+      "learning_rate": 0.00014364261168384881,
+      "loss": 2.2703,
       "step": 82
     },
     {
-      "epoch": 3.32,
-      "learning_rate": 0.0001668,
-      "loss": 1.8595,
+      "epoch": 0.28,
+      "learning_rate": 0.0001429553264604811,
+      "loss": 2.0815,
       "step": 83
     },
     {
-      "epoch": 3.36,
-      "learning_rate": 0.0001664,
-      "loss": 1.9992,
+      "epoch": 0.29,
+      "learning_rate": 0.00014226804123711342,
+      "loss": 2.0774,
       "step": 84
     },
     {
-      "epoch": 3.4,
-      "learning_rate": 0.000166,
-      "loss": 1.8783,
+      "epoch": 0.29,
+      "learning_rate": 0.00014158075601374573,
+      "loss": 2.066,
       "step": 85
     },
     {
-      "epoch": 3.44,
-      "learning_rate": 0.0001656,
-      "loss": 2.0216,
+      "epoch": 0.29,
+      "learning_rate": 0.00014089347079037802,
+      "loss": 2.03,
       "step": 86
     },
     {
-      "epoch": 3.48,
-      "learning_rate": 0.0001652,
-      "loss": 1.947,
+      "epoch": 0.3,
+      "learning_rate": 0.0001402061855670103,
+      "loss": 2.1433,
       "step": 87
     },
     {
-      "epoch": 3.52,
-      "learning_rate": 0.0001648,
-      "loss": 1.9554,
+      "epoch": 0.3,
+      "learning_rate": 0.00013951890034364262,
+      "loss": 2.0811,
       "step": 88
     },
     {
-      "epoch": 3.56,
-      "learning_rate": 0.0001644,
-      "loss": 1.8563,
+      "epoch": 0.31,
+      "learning_rate": 0.0001388316151202749,
+      "loss": 1.9791,
       "step": 89
     },
     {
-      "epoch": 3.6,
-      "learning_rate": 0.000164,
-      "loss": 1.7795,
+      "epoch": 0.31,
+      "learning_rate": 0.00013814432989690722,
+      "loss": 2.0876,
       "step": 90
     },
     {
-      "epoch": 3.64,
-      "learning_rate": 0.0001636,
-      "loss": 1.9347,
+      "epoch": 0.31,
+      "learning_rate": 0.00013745704467353953,
+      "loss": 2.0314,
       "step": 91
     },
     {
-      "epoch": 3.68,
-      "learning_rate": 0.0001632,
-      "loss": 2.0078,
+      "epoch": 0.32,
+      "learning_rate": 0.00013676975945017182,
+      "loss": 1.9485,
       "step": 92
     },
     {
-      "epoch": 3.72,
-      "learning_rate": 0.0001628,
-      "loss": 1.9964,
+      "epoch": 0.32,
+      "learning_rate": 0.00013608247422680414,
+      "loss": 2.078,
       "step": 93
     },
     {
-      "epoch": 3.76,
-      "learning_rate": 0.00016240000000000002,
-      "loss": 1.9004,
+      "epoch": 0.32,
+      "learning_rate": 0.00013539518900343645,
+      "loss": 2.1251,
       "step": 94
     },
     {
-      "epoch": 3.8,
-      "learning_rate": 0.000162,
-      "loss": 1.9446,
+      "epoch": 0.33,
+      "learning_rate": 0.00013470790378006874,
+      "loss": 1.9736,
       "step": 95
     },
     {
-      "epoch": 3.84,
-      "learning_rate": 0.00016160000000000002,
-      "loss": 1.8857,
+      "epoch": 0.33,
+      "learning_rate": 0.00013402061855670103,
+      "loss": 2.0189,
       "step": 96
     },
     {
-      "epoch": 3.88,
-      "learning_rate": 0.00016120000000000002,
-      "loss": 1.8797,
+      "epoch": 0.33,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 2.0061,
       "step": 97
     },
     {
-      "epoch": 3.92,
-      "learning_rate": 0.0001608,
-      "loss": 1.7643,
+      "epoch": 0.34,
+      "learning_rate": 0.00013264604810996563,
+      "loss": 1.9595,
       "step": 98
     },
     {
-      "epoch": 3.96,
-      "learning_rate": 0.00016040000000000002,
-      "loss": 1.9724,
+      "epoch": 0.34,
+      "learning_rate": 0.00013195876288659794,
+      "loss": 1.9702,
       "step": 99
     },
     {
-      "epoch": 4.0,
-      "learning_rate": 0.00016,
-      "loss": 1.9058,
+      "epoch": 0.34,
+      "learning_rate": 0.00013127147766323026,
+      "loss": 2.0322,
       "step": 100
     }
   ],
   "logging_steps": 1,
-  "max_steps": 500,
-  "num_train_epochs": 20,
+  "max_steps": 291,
+  "num_train_epochs": 1,
   "save_steps": 100,
-  "total_flos": 3.406529677264896e+16,
+  "total_flos": 6.083398113601536e+16,
   "trial_name": null,
   "trial_params": null
 }
diff --git a/checkpoint-100/training_args.bin b/checkpoint-100/training_args.bin
index 4de6572a838c337c9990635a9406ebf46c0ec336..514bd8136ebdc96a275890c7b9b4df6ac072906c 100644
--- a/checkpoint-100/training_args.bin
+++ b/checkpoint-100/training_args.bin
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ef74b31950ae6c8955316bed48c343fb06cda0cb6a8a54ca46ca3cb681c8736
+oid sha256:7e3410eea0ea0eb09ca576511099334880accaab360c0279f3099c9e4d2e877a
 size 4027
diff --git a/checkpoint-200/README.md b/checkpoint-200/README.md
index 08371015f02382e6fcba318f4aaea54ae52cd3c4..876f20b74d7edd2433c53bf3037eb5a69dd2d328 100644
--- a/checkpoint-200/README.md
+++ b/checkpoint-200/README.md
@@ -4,6 +4,54 @@ library_name: peft
 ## Training procedure
 
 
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: True
+- load_in_4bit: False
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: True
+- load_in_4bit: False
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: True
+- load_in_4bit: False
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: True
+- load_in_4bit: False
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+
 The following `bitsandbytes` quantization config was used during training:
 - quant_method: bitsandbytes
 - load_in_8bit: True
@@ -29,6 +77,10 @@ The following `bitsandbytes` quantization config was used during training:
 - bnb_4bit_compute_dtype: float32
 ### Framework versions
 
+- PEFT 0.6.0.dev0
+- PEFT 0.6.0.dev0
+- PEFT 0.6.0.dev0
+- PEFT 0.6.0.dev0
 - PEFT 0.6.0.dev0
 
 - PEFT 0.6.0.dev0
diff --git a/checkpoint-200/adapter_model.bin b/checkpoint-200/adapter_model.bin
index ef1e30077687745ef49bd7f0dd6d052f39af2e4f..f37b103d9f11e64e1f3f3ccdfe0d80e5cd684300 100644
--- a/checkpoint-200/adapter_model.bin
+++ b/checkpoint-200/adapter_model.bin
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6eb0dcfb489eef093d9f20354ad4dbd76c3cacdee8012aaf3a92dc2a4267e697
+oid sha256:751fbae1398bb745f5e6d01f275966cedebe1e984b206292fb8476886cfd7027
 size 39409357
diff --git a/checkpoint-200/optimizer.pt b/checkpoint-200/optimizer.pt
index 3a352549f61b48d5ef8779874d4311cb8543ecf6..d738b6d76f95b9fc3edbf31110c82a541e289d1e 100644
--- a/checkpoint-200/optimizer.pt
+++ b/checkpoint-200/optimizer.pt
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5f31f7a2996c207ab778c7745622649ab7de438c906222dc8ef5f81d8c4ed10
+oid sha256:6d7f250b734db4b40976d1847121f325e5f8e4aa321a8357abe3dc127b5fc83a
 size 78844421
diff --git a/checkpoint-200/rng_state.pth b/checkpoint-200/rng_state.pth
index a0e229d77fa9bb9693355411d7e7ba7367c65223..e8a62beafdd6e61c41abbc54c8b7428f4e3484c0 100644
--- a/checkpoint-200/rng_state.pth
+++ b/checkpoint-200/rng_state.pth
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36fc71bd44bd7f04f2599c5dface64c517de1a7ab7bac3600f3f6470c6c72673
+oid sha256:b2278a87cdf86c3f9219223c847f6b27f6b7f15b8226b617f38936e8ff2cbcde
 size 14575
diff --git a/checkpoint-200/scheduler.pt b/checkpoint-200/scheduler.pt
index 40f3132372df114bd32a97767334e3e4ddd9e131..4d75c6ac674606680612e451dbc35eaa55daab52 100644
--- a/checkpoint-200/scheduler.pt
+++ b/checkpoint-200/scheduler.pt
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cf1ea83db88b65824ac70ed44968b05e8a83b81aa97e9d6a33c16e33168c1fe
+oid sha256:e683229dde9f79f059d3d1efb56203ba5ea68642c6ec20811bb7b486e3a6e3a2
 size 627
diff --git a/checkpoint-200/tokenizer.json b/checkpoint-200/tokenizer.json
index dbf002cafbd4818dcff2abc9156c088d681b4533..673c31abdeadf6576c3c754df86459e1ad64e207 100644
--- a/checkpoint-200/tokenizer.json
+++ b/checkpoint-200/tokenizer.json
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17a208233d2ee8d8c83b23bc214df737c44806a1919f444e89b31e586cd956ba
-size 14500471
+oid sha256:85b00d7db4df5df2e3f01cacc3feda246002a672f3356eec7f4b04a22eb0dfbe
+size 14500570
diff --git a/checkpoint-200/trainer_state.json b/checkpoint-200/trainer_state.json
index 93b4e50d2d23a116bf60296f900d7238745a0bf0..361e976614da9960ef805333a02262d0c4eb2739 100644
--- a/checkpoint-200/trainer_state.json
+++ b/checkpoint-200/trainer_state.json
@@ -1,7 +1,7 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 8.0,
+  "epoch": 0.6859592711682744,
   "eval_steps": 500,
   "global_step": 200,
   "is_hyper_param_search": false,
@@ -9,1211 +9,1211 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.04,
-      "learning_rate": 0.0001996,
-      "loss": 2.4683,
+      "epoch": 0.0,
+      "learning_rate": 0.00019931271477663232,
+      "loss": 2.5587,
       "step": 1
     },
     {
-      "epoch": 0.08,
-      "learning_rate": 0.00019920000000000002,
-      "loss": 2.2023,
+      "epoch": 0.01,
+      "learning_rate": 0.0001986254295532646,
+      "loss": 2.3914,
       "step": 2
     },
     {
-      "epoch": 0.12,
-      "learning_rate": 0.0001988,
-      "loss": 2.3039,
+      "epoch": 0.01,
+      "learning_rate": 0.00019793814432989693,
+      "loss": 2.4218,
       "step": 3
     },
     {
-      "epoch": 0.16,
-      "learning_rate": 0.0001984,
-      "loss": 2.1855,
+      "epoch": 0.01,
+      "learning_rate": 0.00019725085910652924,
+      "loss": 2.3414,
       "step": 4
     },
     {
-      "epoch": 0.2,
-      "learning_rate": 0.00019800000000000002,
-      "loss": 2.328,
+      "epoch": 0.02,
+      "learning_rate": 0.0001965635738831615,
+      "loss": 2.2469,
       "step": 5
     },
     {
-      "epoch": 0.24,
-      "learning_rate": 0.0001976,
-      "loss": 2.3407,
+      "epoch": 0.02,
+      "learning_rate": 0.00019587628865979381,
+      "loss": 2.3241,
       "step": 6
     },
     {
-      "epoch": 0.28,
-      "learning_rate": 0.0001972,
-      "loss": 2.3432,
+      "epoch": 0.02,
+      "learning_rate": 0.00019518900343642613,
+      "loss": 2.3266,
       "step": 7
     },
     {
-      "epoch": 0.32,
-      "learning_rate": 0.0001968,
-      "loss": 2.2333,
+      "epoch": 0.03,
+      "learning_rate": 0.00019450171821305842,
+      "loss": 2.1856,
       "step": 8
     },
     {
-      "epoch": 0.36,
-      "learning_rate": 0.0001964,
-      "loss": 2.1761,
+      "epoch": 0.03,
+      "learning_rate": 0.00019381443298969073,
+      "loss": 2.3247,
       "step": 9
     },
     {
-      "epoch": 0.4,
-      "learning_rate": 0.000196,
-      "loss": 2.1473,
+      "epoch": 0.03,
+      "learning_rate": 0.00019312714776632305,
+      "loss": 2.3245,
       "step": 10
     },
     {
-      "epoch": 0.44,
-      "learning_rate": 0.0001956,
-      "loss": 2.2076,
+      "epoch": 0.04,
+      "learning_rate": 0.00019243986254295533,
+      "loss": 2.2591,
       "step": 11
     },
     {
-      "epoch": 0.48,
-      "learning_rate": 0.0001952,
-      "loss": 2.1925,
+      "epoch": 0.04,
+      "learning_rate": 0.00019175257731958765,
+      "loss": 2.1767,
       "step": 12
     },
     {
-      "epoch": 0.52,
-      "learning_rate": 0.0001948,
-      "loss": 2.1694,
+      "epoch": 0.04,
+      "learning_rate": 0.00019106529209621996,
+      "loss": 2.3478,
       "step": 13
     },
     {
-      "epoch": 0.56,
-      "learning_rate": 0.0001944,
-      "loss": 2.1056,
+      "epoch": 0.05,
+      "learning_rate": 0.00019037800687285222,
+      "loss": 2.3339,
       "step": 14
     },
     {
-      "epoch": 0.6,
-      "learning_rate": 0.000194,
-      "loss": 2.2426,
+      "epoch": 0.05,
+      "learning_rate": 0.00018969072164948454,
+      "loss": 2.234,
       "step": 15
     },
     {
-      "epoch": 0.64,
-      "learning_rate": 0.00019360000000000002,
-      "loss": 2.2635,
+      "epoch": 0.05,
+      "learning_rate": 0.00018900343642611685,
+      "loss": 2.2651,
       "step": 16
     },
     {
-      "epoch": 0.68,
-      "learning_rate": 0.0001932,
-      "loss": 2.251,
+      "epoch": 0.06,
+      "learning_rate": 0.00018831615120274914,
+      "loss": 2.1831,
       "step": 17
     },
     {
-      "epoch": 0.72,
-      "learning_rate": 0.0001928,
-      "loss": 2.224,
+      "epoch": 0.06,
+      "learning_rate": 0.00018762886597938145,
+      "loss": 2.216,
       "step": 18
     },
     {
-      "epoch": 0.76,
-      "learning_rate": 0.00019240000000000001,
-      "loss": 2.1848,
+      "epoch": 0.07,
+      "learning_rate": 0.00018694158075601377,
+      "loss": 2.1359,
       "step": 19
     },
     {
-      "epoch": 0.8,
-      "learning_rate": 0.000192,
-      "loss": 2.1341,
+      "epoch": 0.07,
+      "learning_rate": 0.00018625429553264605,
+      "loss": 2.1215,
       "step": 20
     },
     {
-      "epoch": 0.84,
-      "learning_rate": 0.0001916,
-      "loss": 2.126,
+      "epoch": 0.07,
+      "learning_rate": 0.00018556701030927837,
+      "loss": 2.2179,
       "step": 21
     },
     {
-      "epoch": 0.88,
-      "learning_rate": 0.0001912,
-      "loss": 2.0959,
+      "epoch": 0.08,
+      "learning_rate": 0.00018487972508591068,
+      "loss": 2.2598,
       "step": 22
     },
     {
-      "epoch": 0.92,
-      "learning_rate": 0.0001908,
-      "loss": 2.2446,
+      "epoch": 0.08,
+      "learning_rate": 0.00018419243986254294,
+      "loss": 2.1813,
       "step": 23
     },
     {
-      "epoch": 0.96,
-      "learning_rate": 0.0001904,
-      "loss": 1.9448,
+      "epoch": 0.08,
+      "learning_rate": 0.00018350515463917526,
+      "loss": 2.2006,
       "step": 24
     },
     {
-      "epoch": 1.0,
-      "learning_rate": 0.00019,
-      "loss": 2.0939,
+      "epoch": 0.09,
+      "learning_rate": 0.00018281786941580757,
+      "loss": 2.1564,
       "step": 25
     },
     {
-      "epoch": 1.04,
-      "learning_rate": 0.0001896,
-      "loss": 2.1247,
+      "epoch": 0.09,
+      "learning_rate": 0.00018213058419243986,
+      "loss": 2.2537,
       "step": 26
     },
     {
-      "epoch": 1.08,
-      "learning_rate": 0.0001892,
-      "loss": 1.9417,
+      "epoch": 0.09,
+      "learning_rate": 0.00018144329896907217,
+      "loss": 2.1975,
       "step": 27
     },
     {
-      "epoch": 1.12,
-      "learning_rate": 0.0001888,
-      "loss": 2.105,
+      "epoch": 0.1,
+      "learning_rate": 0.0001807560137457045,
+      "loss": 2.2566,
       "step": 28
     },
     {
-      "epoch": 1.16,
-      "learning_rate": 0.0001884,
-      "loss": 2.1595,
+      "epoch": 0.1,
+      "learning_rate": 0.00018006872852233677,
+      "loss": 2.1464,
       "step": 29
     },
     {
-      "epoch": 1.2,
-      "learning_rate": 0.000188,
-      "loss": 2.2009,
+      "epoch": 0.1,
+      "learning_rate": 0.0001793814432989691,
+      "loss": 2.1421,
       "step": 30
     },
     {
-      "epoch": 1.24,
-      "learning_rate": 0.0001876,
-      "loss": 2.0784,
+      "epoch": 0.11,
+      "learning_rate": 0.0001786941580756014,
+      "loss": 2.1276,
       "step": 31
     },
     {
-      "epoch": 1.28,
-      "learning_rate": 0.00018720000000000002,
-      "loss": 2.2173,
+      "epoch": 0.11,
+      "learning_rate": 0.00017800687285223366,
+      "loss": 2.0649,
       "step": 32
     },
     {
-      "epoch": 1.32,
-      "learning_rate": 0.00018680000000000001,
-      "loss": 2.1185,
+      "epoch": 0.11,
+      "learning_rate": 0.00017731958762886598,
+      "loss": 2.1835,
       "step": 33
     },
     {
-      "epoch": 1.36,
-      "learning_rate": 0.00018640000000000003,
-      "loss": 1.988,
+      "epoch": 0.12,
+      "learning_rate": 0.0001766323024054983,
+      "loss": 2.1711,
       "step": 34
     },
     {
-      "epoch": 1.4,
-      "learning_rate": 0.00018600000000000002,
-      "loss": 1.9493,
+      "epoch": 0.12,
+      "learning_rate": 0.00017594501718213058,
+      "loss": 2.2591,
       "step": 35
     },
     {
-      "epoch": 1.44,
-      "learning_rate": 0.0001856,
-      "loss": 1.9947,
+      "epoch": 0.12,
+      "learning_rate": 0.0001752577319587629,
+      "loss": 2.1471,
       "step": 36
     },
     {
-      "epoch": 1.48,
-      "learning_rate": 0.00018520000000000003,
-      "loss": 2.0506,
+      "epoch": 0.13,
+      "learning_rate": 0.0001745704467353952,
+      "loss": 2.0861,
       "step": 37
     },
     {
-      "epoch": 1.52,
-      "learning_rate": 0.00018480000000000002,
-      "loss": 2.0829,
+      "epoch": 0.13,
+      "learning_rate": 0.0001738831615120275,
+      "loss": 2.0702,
       "step": 38
     },
     {
-      "epoch": 1.56,
-      "learning_rate": 0.0001844,
-      "loss": 2.1455,
+      "epoch": 0.13,
+      "learning_rate": 0.0001731958762886598,
+      "loss": 2.1096,
       "step": 39
     },
     {
-      "epoch": 1.6,
-      "learning_rate": 0.00018400000000000003,
-      "loss": 2.0304,
+      "epoch": 0.14,
+      "learning_rate": 0.00017250859106529212,
+      "loss": 2.1062,
       "step": 40
     },
     {
-      "epoch": 1.64,
-      "learning_rate": 0.00018360000000000002,
-      "loss": 2.006,
+      "epoch": 0.14,
+      "learning_rate": 0.00017182130584192438,
+      "loss": 2.2545,
       "step": 41
     },
     {
-      "epoch": 1.68,
-      "learning_rate": 0.0001832,
-      "loss": 2.1759,
+      "epoch": 0.14,
+      "learning_rate": 0.0001711340206185567,
+      "loss": 2.1572,
       "step": 42
     },
     {
-      "epoch": 1.72,
-      "learning_rate": 0.00018280000000000003,
-      "loss": 2.0093,
+      "epoch": 0.15,
+      "learning_rate": 0.000170446735395189,
+      "loss": 2.0749,
       "step": 43
     },
     {
-      "epoch": 1.76,
-      "learning_rate": 0.00018240000000000002,
-      "loss": 2.0683,
+      "epoch": 0.15,
+      "learning_rate": 0.0001697594501718213,
+      "loss": 2.1922,
       "step": 44
     },
     {
-      "epoch": 1.8,
-      "learning_rate": 0.000182,
-      "loss": 2.1352,
+      "epoch": 0.15,
+      "learning_rate": 0.00016907216494845361,
+      "loss": 2.1915,
       "step": 45
     },
     {
-      "epoch": 1.84,
-      "learning_rate": 0.00018160000000000002,
-      "loss": 1.9736,
+      "epoch": 0.16,
+      "learning_rate": 0.00016838487972508593,
+      "loss": 2.1594,
       "step": 46
     },
     {
-      "epoch": 1.88,
-      "learning_rate": 0.0001812,
-      "loss": 1.9631,
+      "epoch": 0.16,
+      "learning_rate": 0.00016769759450171822,
+      "loss": 2.176,
       "step": 47
     },
     {
-      "epoch": 1.92,
-      "learning_rate": 0.0001808,
-      "loss": 2.1024,
+      "epoch": 0.16,
+      "learning_rate": 0.00016701030927835053,
+      "loss": 2.1223,
       "step": 48
     },
     {
-      "epoch": 1.96,
-      "learning_rate": 0.00018040000000000002,
-      "loss": 1.9895,
+      "epoch": 0.17,
+      "learning_rate": 0.00016632302405498285,
+      "loss": 2.1263,
       "step": 49
     },
     {
-      "epoch": 2.0,
-      "learning_rate": 0.00018,
-      "loss": 2.0067,
+      "epoch": 0.17,
+      "learning_rate": 0.00016563573883161513,
+      "loss": 2.0481,
       "step": 50
     },
     {
-      "epoch": 2.04,
-      "learning_rate": 0.0001796,
-      "loss": 2.0509,
+      "epoch": 0.17,
+      "learning_rate": 0.00016494845360824742,
+      "loss": 2.1043,
       "step": 51
     },
     {
-      "epoch": 2.08,
-      "learning_rate": 0.00017920000000000002,
-      "loss": 1.8795,
+      "epoch": 0.18,
+      "learning_rate": 0.00016426116838487973,
+      "loss": 2.1678,
       "step": 52
     },
     {
-      "epoch": 2.12,
-      "learning_rate": 0.0001788,
-      "loss": 2.0633,
+      "epoch": 0.18,
+      "learning_rate": 0.00016357388316151202,
+      "loss": 2.1602,
       "step": 53
     },
     {
-      "epoch": 2.16,
-      "learning_rate": 0.0001784,
-      "loss": 1.9998,
+      "epoch": 0.19,
+      "learning_rate": 0.00016288659793814434,
+      "loss": 2.1448,
       "step": 54
     },
     {
-      "epoch": 2.2,
-      "learning_rate": 0.00017800000000000002,
-      "loss": 2.0675,
+      "epoch": 0.19,
+      "learning_rate": 0.00016219931271477665,
+      "loss": 2.1536,
       "step": 55
     },
     {
-      "epoch": 2.24,
-      "learning_rate": 0.0001776,
-      "loss": 2.0129,
+      "epoch": 0.19,
+      "learning_rate": 0.00016151202749140894,
+      "loss": 2.0339,
       "step": 56
     },
     {
-      "epoch": 2.28,
-      "learning_rate": 0.0001772,
-      "loss": 1.9302,
+      "epoch": 0.2,
+      "learning_rate": 0.00016082474226804125,
+      "loss": 2.023,
       "step": 57
     },
     {
-      "epoch": 2.32,
-      "learning_rate": 0.00017680000000000001,
-      "loss": 2.0472,
+      "epoch": 0.2,
+      "learning_rate": 0.00016013745704467357,
+      "loss": 2.1407,
       "step": 58
     },
     {
-      "epoch": 2.36,
-      "learning_rate": 0.0001764,
-      "loss": 2.0031,
+      "epoch": 0.2,
+      "learning_rate": 0.00015945017182130585,
+      "loss": 2.1134,
       "step": 59
     },
     {
-      "epoch": 2.4,
-      "learning_rate": 0.00017600000000000002,
-      "loss": 2.0231,
+      "epoch": 0.21,
+      "learning_rate": 0.00015876288659793814,
+      "loss": 2.1652,
       "step": 60
     },
     {
-      "epoch": 2.44,
-      "learning_rate": 0.0001756,
-      "loss": 2.0192,
+      "epoch": 0.21,
+      "learning_rate": 0.00015807560137457046,
+      "loss": 2.0051,
       "step": 61
     },
     {
-      "epoch": 2.48,
-      "learning_rate": 0.0001752,
-      "loss": 2.1336,
+      "epoch": 0.21,
+      "learning_rate": 0.00015738831615120274,
+      "loss": 2.0604,
       "step": 62
     },
     {
-      "epoch": 2.52,
-      "learning_rate": 0.00017480000000000002,
-      "loss": 1.7753,
+      "epoch": 0.22,
+      "learning_rate": 0.00015670103092783506,
+      "loss": 2.1708,
       "step": 63
     },
     {
-      "epoch": 2.56,
-      "learning_rate": 0.0001744,
-      "loss": 2.0274,
+      "epoch": 0.22,
+      "learning_rate": 0.00015601374570446737,
+      "loss": 2.1106,
       "step": 64
     },
     {
-      "epoch": 2.6,
-      "learning_rate": 0.000174,
-      "loss": 1.8893,
+      "epoch": 0.22,
+      "learning_rate": 0.00015532646048109966,
+      "loss": 2.1445,
       "step": 65
     },
     {
-      "epoch": 2.64,
-      "learning_rate": 0.00017360000000000002,
-      "loss": 2.0341,
+      "epoch": 0.23,
+      "learning_rate": 0.00015463917525773197,
+      "loss": 2.0879,
       "step": 66
     },
     {
-      "epoch": 2.68,
-      "learning_rate": 0.0001732,
-      "loss": 2.1081,
+      "epoch": 0.23,
+      "learning_rate": 0.0001539518900343643,
+      "loss": 2.1498,
       "step": 67
     },
     {
-      "epoch": 2.72,
-      "learning_rate": 0.0001728,
-      "loss": 1.9463,
+      "epoch": 0.23,
+      "learning_rate": 0.00015326460481099657,
+      "loss": 2.0719,
       "step": 68
     },
     {
-      "epoch": 2.76,
-      "learning_rate": 0.00017240000000000002,
-      "loss": 2.0607,
+      "epoch": 0.24,
+      "learning_rate": 0.00015257731958762886,
+      "loss": 2.2167,
       "step": 69
     },
     {
-      "epoch": 2.8,
-      "learning_rate": 0.000172,
-      "loss": 1.9803,
+      "epoch": 0.24,
+      "learning_rate": 0.00015189003436426118,
+      "loss": 2.0811,
       "step": 70
     },
     {
-      "epoch": 2.84,
-      "learning_rate": 0.0001716,
-      "loss": 1.7663,
+      "epoch": 0.24,
+      "learning_rate": 0.00015120274914089346,
+      "loss": 2.1058,
       "step": 71
     },
     {
-      "epoch": 2.88,
-      "learning_rate": 0.00017120000000000001,
-      "loss": 2.1116,
+      "epoch": 0.25,
+      "learning_rate": 0.00015051546391752578,
+      "loss": 2.0392,
       "step": 72
     },
     {
-      "epoch": 2.92,
-      "learning_rate": 0.0001708,
-      "loss": 1.9039,
+      "epoch": 0.25,
+      "learning_rate": 0.0001498281786941581,
+      "loss": 2.0957,
       "step": 73
     },
     {
-      "epoch": 2.96,
-      "learning_rate": 0.0001704,
-      "loss": 2.049,
+      "epoch": 0.25,
+      "learning_rate": 0.00014914089347079038,
+      "loss": 1.9994,
       "step": 74
     },
     {
-      "epoch": 3.0,
-      "learning_rate": 0.00017,
-      "loss": 1.991,
+      "epoch": 0.26,
+      "learning_rate": 0.0001484536082474227,
+      "loss": 2.0464,
       "step": 75
     },
     {
-      "epoch": 3.04,
-      "learning_rate": 0.0001696,
-      "loss": 1.8755,
+      "epoch": 0.26,
+      "learning_rate": 0.000147766323024055,
+      "loss": 2.0417,
       "step": 76
     },
     {
-      "epoch": 3.08,
-      "learning_rate": 0.0001692,
-      "loss": 2.0367,
+      "epoch": 0.26,
+      "learning_rate": 0.0001470790378006873,
+      "loss": 2.105,
       "step": 77
     },
     {
-      "epoch": 3.12,
-      "learning_rate": 0.0001688,
-      "loss": 1.9959,
+      "epoch": 0.27,
+      "learning_rate": 0.00014639175257731958,
+      "loss": 2.1147,
       "step": 78
     },
     {
-      "epoch": 3.16,
-      "learning_rate": 0.0001684,
-      "loss": 1.8051,
+      "epoch": 0.27,
+      "learning_rate": 0.0001457044673539519,
+      "loss": 1.9964,
       "step": 79
     },
     {
-      "epoch": 3.2,
-      "learning_rate": 0.000168,
-      "loss": 2.0446,
+      "epoch": 0.27,
+      "learning_rate": 0.00014501718213058418,
+      "loss": 1.9723,
       "step": 80
     },
     {
-      "epoch": 3.24,
-      "learning_rate": 0.0001676,
-      "loss": 1.7873,
+      "epoch": 0.28,
+      "learning_rate": 0.0001443298969072165,
+      "loss": 2.0621,
       "step": 81
     },
     {
-      "epoch": 3.28,
-      "learning_rate": 0.0001672,
-      "loss": 1.9264,
+      "epoch": 0.28,
+      "learning_rate": 0.00014364261168384881,
+      "loss": 2.2703,
       "step": 82
     },
     {
-      "epoch": 3.32,
-      "learning_rate": 0.0001668,
-      "loss": 1.8595,
+      "epoch": 0.28,
+      "learning_rate": 0.0001429553264604811,
+      "loss": 2.0815,
       "step": 83
     },
     {
-      "epoch": 3.36,
-      "learning_rate": 0.0001664,
-      "loss": 1.9992,
+      "epoch": 0.29,
+      "learning_rate": 0.00014226804123711342,
+      "loss": 2.0774,
       "step": 84
     },
     {
-      "epoch": 3.4,
-      "learning_rate": 0.000166,
-      "loss": 1.8783,
+      "epoch": 0.29,
+      "learning_rate": 0.00014158075601374573,
+      "loss": 2.066,
       "step": 85
     },
     {
-      "epoch": 3.44,
-      "learning_rate": 0.0001656,
-      "loss": 2.0216,
+      "epoch": 0.29,
+      "learning_rate": 0.00014089347079037802,
+      "loss": 2.03,
       "step": 86
     },
     {
-      "epoch": 3.48,
-      "learning_rate": 0.0001652,
-      "loss": 1.947,
+      "epoch": 0.3,
+      "learning_rate": 0.0001402061855670103,
+      "loss": 2.1433,
       "step": 87
     },
     {
-      "epoch": 3.52,
-      "learning_rate": 0.0001648,
-      "loss": 1.9554,
+      "epoch": 0.3,
+      "learning_rate": 0.00013951890034364262,
+      "loss": 2.0811,
       "step": 88
     },
     {
-      "epoch": 3.56,
-      "learning_rate": 0.0001644,
-      "loss": 1.8563,
+      "epoch": 0.31,
+      "learning_rate": 0.0001388316151202749,
+      "loss": 1.9791,
       "step": 89
     },
     {
-      "epoch": 3.6,
-      "learning_rate": 0.000164,
-      "loss": 1.7795,
+      "epoch": 0.31,
+      "learning_rate": 0.00013814432989690722,
+      "loss": 2.0876,
       "step": 90
     },
     {
-      "epoch": 3.64,
-      "learning_rate": 0.0001636,
-      "loss": 1.9347,
+      "epoch": 0.31,
+      "learning_rate": 0.00013745704467353953,
+      "loss": 2.0314,
       "step": 91
     },
     {
-      "epoch": 3.68,
-      "learning_rate": 0.0001632,
-      "loss": 2.0078,
+      "epoch": 0.32,
+      "learning_rate": 0.00013676975945017182,
+      "loss": 1.9485,
       "step": 92
     },
     {
-      "epoch": 3.72,
-      "learning_rate": 0.0001628,
-      "loss": 1.9964,
+      "epoch": 0.32,
+      "learning_rate": 0.00013608247422680414,
+      "loss": 2.078,
       "step": 93
     },
     {
-      "epoch": 3.76,
-      "learning_rate": 0.00016240000000000002,
-      "loss": 1.9004,
+      "epoch": 0.32,
+      "learning_rate": 0.00013539518900343645,
+      "loss": 2.1251,
       "step": 94
     },
     {
-      "epoch": 3.8,
-      "learning_rate": 0.000162,
-      "loss": 1.9446,
+      "epoch": 0.33,
+      "learning_rate": 0.00013470790378006874,
+      "loss": 1.9736,
       "step": 95
     },
     {
-      "epoch": 3.84,
-      "learning_rate": 0.00016160000000000002,
-      "loss": 1.8857,
+      "epoch": 0.33,
+      "learning_rate": 0.00013402061855670103,
+      "loss": 2.0189,
       "step": 96
     },
     {
-      "epoch": 3.88,
-      "learning_rate": 0.00016120000000000002,
-      "loss": 1.8797,
+      "epoch": 0.33,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 2.0061,
       "step": 97
     },
     {
-      "epoch": 3.92,
-      "learning_rate": 0.0001608,
-      "loss": 1.7643,
+      "epoch": 0.34,
+      "learning_rate": 0.00013264604810996563,
+      "loss": 1.9595,
       "step": 98
     },
     {
-      "epoch": 3.96,
-      "learning_rate": 0.00016040000000000002,
-      "loss": 1.9724,
+      "epoch": 0.34,
+      "learning_rate": 0.00013195876288659794,
+      "loss": 1.9702,
       "step": 99
     },
     {
-      "epoch": 4.0,
-      "learning_rate": 0.00016,
-      "loss": 1.9058,
+      "epoch": 0.34,
+      "learning_rate": 0.00013127147766323026,
+      "loss": 2.0322,
       "step": 100
     },
     {
-      "epoch": 4.04,
-      "learning_rate": 0.0001596,
-      "loss": 1.8663,
+      "epoch": 0.35,
+      "learning_rate": 0.00013058419243986254,
+      "loss": 2.0128,
       "step": 101
     },
     {
-      "epoch": 4.08,
-      "learning_rate": 0.00015920000000000002,
-      "loss": 1.8457,
+      "epoch": 0.35,
+      "learning_rate": 0.00012989690721649486,
+      "loss": 2.1276,
       "step": 102
     },
     {
-      "epoch": 4.12,
-      "learning_rate": 0.0001588,
-      "loss": 1.8394,
+      "epoch": 0.35,
+      "learning_rate": 0.00012920962199312717,
+      "loss": 2.0177,
       "step": 103
     },
     {
-      "epoch": 4.16,
-      "learning_rate": 0.00015840000000000003,
-      "loss": 1.8941,
+      "epoch": 0.36,
+      "learning_rate": 0.00012852233676975946,
+      "loss": 1.9366,
       "step": 104
     },
     {
-      "epoch": 4.2,
-      "learning_rate": 0.00015800000000000002,
-      "loss": 1.8601,
+      "epoch": 0.36,
+      "learning_rate": 0.00012783505154639175,
+      "loss": 2.0341,
       "step": 105
     },
     {
-      "epoch": 4.24,
-      "learning_rate": 0.0001576,
-      "loss": 1.7365,
+      "epoch": 0.36,
+      "learning_rate": 0.00012714776632302406,
+      "loss": 2.0251,
       "step": 106
     },
     {
-      "epoch": 4.28,
-      "learning_rate": 0.00015720000000000003,
-      "loss": 1.8809,
+      "epoch": 0.37,
+      "learning_rate": 0.00012646048109965635,
+      "loss": 1.9588,
       "step": 107
     },
     {
-      "epoch": 4.32,
-      "learning_rate": 0.00015680000000000002,
-      "loss": 2.0206,
+      "epoch": 0.37,
+      "learning_rate": 0.00012577319587628866,
+      "loss": 2.0445,
       "step": 108
     },
     {
-      "epoch": 4.36,
-      "learning_rate": 0.0001564,
-      "loss": 1.7776,
+      "epoch": 0.37,
+      "learning_rate": 0.00012508591065292098,
+      "loss": 1.8917,
       "step": 109
     },
     {
-      "epoch": 4.4,
-      "learning_rate": 0.00015600000000000002,
-      "loss": 1.9089,
+      "epoch": 0.38,
+      "learning_rate": 0.00012439862542955326,
+      "loss": 2.0385,
       "step": 110
     },
     {
-      "epoch": 4.44,
-      "learning_rate": 0.00015560000000000001,
-      "loss": 1.8464,
+      "epoch": 0.38,
+      "learning_rate": 0.00012371134020618558,
+      "loss": 2.0435,
       "step": 111
     },
     {
-      "epoch": 4.48,
-      "learning_rate": 0.0001552,
-      "loss": 1.7943,
+      "epoch": 0.38,
+      "learning_rate": 0.0001230240549828179,
+      "loss": 2.0666,
       "step": 112
     },
     {
-      "epoch": 4.52,
-      "learning_rate": 0.00015480000000000002,
-      "loss": 1.8081,
+      "epoch": 0.39,
+      "learning_rate": 0.00012233676975945018,
+      "loss": 1.9854,
       "step": 113
     },
     {
-      "epoch": 4.56,
-      "learning_rate": 0.0001544,
-      "loss": 1.734,
+      "epoch": 0.39,
+      "learning_rate": 0.00012164948453608247,
+      "loss": 1.9233,
       "step": 114
     },
     {
-      "epoch": 4.6,
-      "learning_rate": 0.000154,
-      "loss": 1.8379,
+      "epoch": 0.39,
+      "learning_rate": 0.00012096219931271477,
+      "loss": 1.985,
       "step": 115
     },
     {
-      "epoch": 4.64,
-      "learning_rate": 0.00015360000000000002,
-      "loss": 1.6841,
+      "epoch": 0.4,
+      "learning_rate": 0.00012027491408934708,
+      "loss": 2.0679,
       "step": 116
     },
     {
-      "epoch": 4.68,
-      "learning_rate": 0.0001532,
-      "loss": 1.8253,
+      "epoch": 0.4,
+      "learning_rate": 0.00011958762886597938,
+      "loss": 1.9717,
       "step": 117
     },
     {
-      "epoch": 4.72,
-      "learning_rate": 0.0001528,
-      "loss": 1.7607,
+      "epoch": 0.4,
+      "learning_rate": 0.00011890034364261168,
+      "loss": 1.9388,
       "step": 118
     },
     {
-      "epoch": 4.76,
-      "learning_rate": 0.00015240000000000002,
-      "loss": 1.8205,
+      "epoch": 0.41,
+      "learning_rate": 0.000118213058419244,
+      "loss": 1.9607,
       "step": 119
     },
     {
-      "epoch": 4.8,
-      "learning_rate": 0.000152,
-      "loss": 1.8443,
+      "epoch": 0.41,
+      "learning_rate": 0.0001175257731958763,
+      "loss": 1.9543,
       "step": 120
     },
     {
-      "epoch": 4.84,
-      "learning_rate": 0.0001516,
-      "loss": 1.8824,
+      "epoch": 0.42,
+      "learning_rate": 0.0001168384879725086,
+      "loss": 1.9925,
       "step": 121
     },
     {
-      "epoch": 4.88,
-      "learning_rate": 0.00015120000000000002,
-      "loss": 1.8369,
+      "epoch": 0.42,
+      "learning_rate": 0.00011615120274914091,
+      "loss": 1.9913,
       "step": 122
     },
     {
-      "epoch": 4.92,
-      "learning_rate": 0.0001508,
-      "loss": 1.8017,
+      "epoch": 0.42,
+      "learning_rate": 0.00011546391752577319,
+      "loss": 1.9857,
       "step": 123
     },
     {
-      "epoch": 4.96,
-      "learning_rate": 0.0001504,
-      "loss": 1.7858,
+      "epoch": 0.43,
+      "learning_rate": 0.00011477663230240549,
+      "loss": 2.0056,
       "step": 124
     },
     {
-      "epoch": 5.0,
-      "learning_rate": 0.00015000000000000001,
-      "loss": 1.8366,
+      "epoch": 0.43,
+      "learning_rate": 0.0001140893470790378,
+      "loss": 2.0133,
       "step": 125
     },
     {
-      "epoch": 5.04,
-      "learning_rate": 0.0001496,
-      "loss": 1.7353,
+      "epoch": 0.43,
+      "learning_rate": 0.0001134020618556701,
+      "loss": 1.8104,
       "step": 126
     },
     {
-      "epoch": 5.08,
-      "learning_rate": 0.0001492,
-      "loss": 1.6017,
+      "epoch": 0.44,
+      "learning_rate": 0.0001127147766323024,
+      "loss": 1.7946,
       "step": 127
     },
     {
-      "epoch": 5.12,
-      "learning_rate": 0.0001488,
-      "loss": 1.6645,
+      "epoch": 0.44,
+      "learning_rate": 0.00011202749140893472,
+      "loss": 1.8347,
       "step": 128
     },
     {
-      "epoch": 5.16,
-      "learning_rate": 0.0001484,
-      "loss": 1.8663,
+      "epoch": 0.44,
+      "learning_rate": 0.00011134020618556702,
+      "loss": 2.0342,
       "step": 129
     },
     {
-      "epoch": 5.2,
-      "learning_rate": 0.000148,
-      "loss": 1.7009,
+      "epoch": 0.45,
+      "learning_rate": 0.00011065292096219932,
+      "loss": 1.9425,
       "step": 130
     },
     {
-      "epoch": 5.24,
-      "learning_rate": 0.0001476,
-      "loss": 1.7371,
+      "epoch": 0.45,
+      "learning_rate": 0.00010996563573883164,
+      "loss": 1.9546,
       "step": 131
     },
     {
-      "epoch": 5.28,
-      "learning_rate": 0.0001472,
-      "loss": 1.8555,
+      "epoch": 0.45,
+      "learning_rate": 0.00010927835051546391,
+      "loss": 1.9694,
       "step": 132
     },
     {
-      "epoch": 5.32,
-      "learning_rate": 0.00014680000000000002,
-      "loss": 1.6373,
+      "epoch": 0.46,
+      "learning_rate": 0.00010859106529209621,
+      "loss": 1.936,
       "step": 133
     },
     {
-      "epoch": 5.36,
-      "learning_rate": 0.0001464,
-      "loss": 1.7211,
+      "epoch": 0.46,
+      "learning_rate": 0.00010790378006872852,
+      "loss": 2.0004,
       "step": 134
     },
     {
-      "epoch": 5.4,
-      "learning_rate": 0.000146,
-      "loss": 1.614,
+      "epoch": 0.46,
+      "learning_rate": 0.00010721649484536083,
+      "loss": 2.0462,
       "step": 135
     },
     {
-      "epoch": 5.44,
-      "learning_rate": 0.00014560000000000002,
-      "loss": 1.8736,
+      "epoch": 0.47,
+      "learning_rate": 0.00010652920962199313,
+      "loss": 1.9783,
       "step": 136
     },
     {
-      "epoch": 5.48,
-      "learning_rate": 0.0001452,
-      "loss": 1.7229,
+      "epoch": 0.47,
+      "learning_rate": 0.00010584192439862544,
+      "loss": 1.8628,
       "step": 137
     },
     {
-      "epoch": 5.52,
-      "learning_rate": 0.0001448,
-      "loss": 1.7315,
+      "epoch": 0.47,
+      "learning_rate": 0.00010515463917525774,
+      "loss": 1.9134,
       "step": 138
     },
     {
-      "epoch": 5.56,
-      "learning_rate": 0.0001444,
-      "loss": 1.7259,
+      "epoch": 0.48,
+      "learning_rate": 0.00010446735395189004,
+      "loss": 1.8846,
       "step": 139
     },
     {
-      "epoch": 5.6,
-      "learning_rate": 0.000144,
-      "loss": 1.7032,
+      "epoch": 0.48,
+      "learning_rate": 0.00010378006872852236,
+      "loss": 1.8119,
       "step": 140
     },
     {
-      "epoch": 5.64,
-      "learning_rate": 0.0001436,
-      "loss": 1.9237,
+      "epoch": 0.48,
+      "learning_rate": 0.00010309278350515463,
+      "loss": 1.9242,
       "step": 141
     },
     {
-      "epoch": 5.68,
-      "learning_rate": 0.0001432,
-      "loss": 1.7821,
+      "epoch": 0.49,
+      "learning_rate": 0.00010240549828178693,
+      "loss": 1.9292,
       "step": 142
     },
     {
-      "epoch": 5.72,
-      "learning_rate": 0.0001428,
-      "loss": 1.6081,
+      "epoch": 0.49,
+      "learning_rate": 0.00010171821305841925,
+      "loss": 1.9763,
       "step": 143
     },
     {
-      "epoch": 5.76,
-      "learning_rate": 0.0001424,
-      "loss": 1.7979,
+      "epoch": 0.49,
+      "learning_rate": 0.00010103092783505155,
+      "loss": 1.9023,
       "step": 144
     },
     {
-      "epoch": 5.8,
-      "learning_rate": 0.000142,
-      "loss": 1.6675,
+      "epoch": 0.5,
+      "learning_rate": 0.00010034364261168385,
+      "loss": 1.8064,
       "step": 145
     },
     {
-      "epoch": 5.84,
-      "learning_rate": 0.0001416,
-      "loss": 1.6758,
+      "epoch": 0.5,
+      "learning_rate": 9.965635738831616e-05,
+      "loss": 1.9646,
       "step": 146
     },
     {
-      "epoch": 5.88,
-      "learning_rate": 0.0001412,
-      "loss": 1.7783,
+      "epoch": 0.5,
+      "learning_rate": 9.896907216494846e-05,
+      "loss": 1.8234,
       "step": 147
     },
     {
-      "epoch": 5.92,
-      "learning_rate": 0.0001408,
-      "loss": 1.5935,
+      "epoch": 0.51,
+      "learning_rate": 9.828178694158075e-05,
+      "loss": 2.0289,
       "step": 148
     },
     {
-      "epoch": 5.96,
-      "learning_rate": 0.0001404,
-      "loss": 1.7372,
+      "epoch": 0.51,
+      "learning_rate": 9.759450171821306e-05,
+      "loss": 1.7698,
       "step": 149
     },
     {
-      "epoch": 6.0,
-      "learning_rate": 0.00014,
-      "loss": 1.6308,
+      "epoch": 0.51,
+      "learning_rate": 9.690721649484537e-05,
+      "loss": 1.9497,
       "step": 150
     },
     {
-      "epoch": 6.04,
-      "learning_rate": 0.0001396,
-      "loss": 1.5829,
+      "epoch": 0.52,
+      "learning_rate": 9.621993127147767e-05,
+      "loss": 1.9135,
       "step": 151
     },
     {
-      "epoch": 6.08,
-      "learning_rate": 0.0001392,
-      "loss": 1.6538,
+      "epoch": 0.52,
+      "learning_rate": 9.553264604810998e-05,
+      "loss": 1.7955,
       "step": 152
     },
     {
-      "epoch": 6.12,
-      "learning_rate": 0.00013879999999999999,
-      "loss": 1.7624,
+      "epoch": 0.52,
+      "learning_rate": 9.484536082474227e-05,
+      "loss": 1.9452,
       "step": 153
     },
     {
-      "epoch": 6.16,
-      "learning_rate": 0.0001384,
-      "loss": 1.4968,
+      "epoch": 0.53,
+      "learning_rate": 9.415807560137457e-05,
+      "loss": 1.9715,
       "step": 154
     },
     {
-      "epoch": 6.2,
-      "learning_rate": 0.000138,
-      "loss": 1.7305,
+      "epoch": 0.53,
+      "learning_rate": 9.347079037800688e-05,
+      "loss": 1.8546,
       "step": 155
     },
     {
-      "epoch": 6.24,
-      "learning_rate": 0.00013759999999999998,
-      "loss": 1.6536,
+      "epoch": 0.54,
+      "learning_rate": 9.278350515463918e-05,
+      "loss": 1.9756,
       "step": 156
     },
     {
-      "epoch": 6.28,
-      "learning_rate": 0.00013720000000000003,
-      "loss": 1.654,
+      "epoch": 0.54,
+      "learning_rate": 9.209621993127147e-05,
+      "loss": 2.0691,
       "step": 157
     },
     {
-      "epoch": 6.32,
-      "learning_rate": 0.00013680000000000002,
-      "loss": 1.7163,
+      "epoch": 0.54,
+      "learning_rate": 9.140893470790379e-05,
+      "loss": 1.8373,
       "step": 158
     },
     {
-      "epoch": 6.36,
-      "learning_rate": 0.0001364,
-      "loss": 1.6599,
+      "epoch": 0.55,
+      "learning_rate": 9.072164948453609e-05,
+      "loss": 1.7061,
       "step": 159
     },
     {
-      "epoch": 6.4,
-      "learning_rate": 0.00013600000000000003,
-      "loss": 1.5729,
+      "epoch": 0.55,
+      "learning_rate": 9.003436426116839e-05,
+      "loss": 1.9069,
       "step": 160
     },
     {
-      "epoch": 6.44,
-      "learning_rate": 0.00013560000000000002,
-      "loss": 1.5291,
+      "epoch": 0.55,
+      "learning_rate": 8.93470790378007e-05,
+      "loss": 1.8055,
       "step": 161
     },
     {
-      "epoch": 6.48,
-      "learning_rate": 0.0001352,
-      "loss": 1.5666,
+      "epoch": 0.56,
+      "learning_rate": 8.865979381443299e-05,
+      "loss": 1.8873,
       "step": 162
     },
     {
-      "epoch": 6.52,
-      "learning_rate": 0.00013480000000000002,
-      "loss": 1.7576,
+      "epoch": 0.56,
+      "learning_rate": 8.797250859106529e-05,
+      "loss": 1.8406,
       "step": 163
     },
     {
-      "epoch": 6.56,
-      "learning_rate": 0.00013440000000000001,
-      "loss": 1.4462,
+      "epoch": 0.56,
+      "learning_rate": 8.72852233676976e-05,
+      "loss": 1.9428,
       "step": 164
     },
     {
-      "epoch": 6.6,
-      "learning_rate": 0.000134,
-      "loss": 1.5659,
+      "epoch": 0.57,
+      "learning_rate": 8.65979381443299e-05,
+      "loss": 1.831,
       "step": 165
     },
     {
-      "epoch": 6.64,
-      "learning_rate": 0.00013360000000000002,
-      "loss": 1.6234,
+      "epoch": 0.57,
+      "learning_rate": 8.591065292096219e-05,
+      "loss": 1.8802,
       "step": 166
     },
     {
-      "epoch": 6.68,
-      "learning_rate": 0.0001332,
-      "loss": 1.5176,
+      "epoch": 0.57,
+      "learning_rate": 8.52233676975945e-05,
+      "loss": 1.8436,
       "step": 167
     },
     {
-      "epoch": 6.72,
-      "learning_rate": 0.0001328,
-      "loss": 1.667,
+      "epoch": 0.58,
+      "learning_rate": 8.453608247422681e-05,
+      "loss": 1.848,
       "step": 168
     },
     {
-      "epoch": 6.76,
-      "learning_rate": 0.00013240000000000002,
-      "loss": 1.6514,
+      "epoch": 0.58,
+      "learning_rate": 8.384879725085911e-05,
+      "loss": 1.9022,
       "step": 169
     },
     {
-      "epoch": 6.8,
-      "learning_rate": 0.000132,
-      "loss": 1.7179,
+      "epoch": 0.58,
+      "learning_rate": 8.316151202749142e-05,
+      "loss": 1.8015,
       "step": 170
     },
     {
-      "epoch": 6.84,
-      "learning_rate": 0.0001316,
-      "loss": 1.4373,
+      "epoch": 0.59,
+      "learning_rate": 8.247422680412371e-05,
+      "loss": 1.8204,
       "step": 171
     },
     {
-      "epoch": 6.88,
-      "learning_rate": 0.00013120000000000002,
-      "loss": 1.7044,
+      "epoch": 0.59,
+      "learning_rate": 8.178694158075601e-05,
+      "loss": 1.798,
       "step": 172
     },
     {
-      "epoch": 6.92,
-      "learning_rate": 0.0001308,
-      "loss": 1.5673,
+      "epoch": 0.59,
+      "learning_rate": 8.109965635738833e-05,
+      "loss": 1.8832,
       "step": 173
     },
     {
-      "epoch": 6.96,
-      "learning_rate": 0.0001304,
-      "loss": 1.6303,
+      "epoch": 0.6,
+      "learning_rate": 8.041237113402063e-05,
+      "loss": 1.8176,
       "step": 174
     },
     {
-      "epoch": 7.0,
-      "learning_rate": 0.00013000000000000002,
-      "loss": 1.4828,
+      "epoch": 0.6,
+      "learning_rate": 7.972508591065293e-05,
+      "loss": 1.9251,
       "step": 175
     },
     {
-      "epoch": 7.04,
-      "learning_rate": 0.0001296,
-      "loss": 1.6204,
+      "epoch": 0.6,
+      "learning_rate": 7.903780068728523e-05,
+      "loss": 1.7559,
       "step": 176
     },
     {
-      "epoch": 7.08,
-      "learning_rate": 0.00012920000000000002,
-      "loss": 1.4955,
+      "epoch": 0.61,
+      "learning_rate": 7.835051546391753e-05,
+      "loss": 1.805,
       "step": 177
     },
     {
-      "epoch": 7.12,
-      "learning_rate": 0.00012880000000000001,
-      "loss": 1.6109,
+      "epoch": 0.61,
+      "learning_rate": 7.766323024054983e-05,
+      "loss": 1.7995,
       "step": 178
     },
     {
-      "epoch": 7.16,
-      "learning_rate": 0.0001284,
-      "loss": 1.5318,
+      "epoch": 0.61,
+      "learning_rate": 7.697594501718214e-05,
+      "loss": 1.9055,
       "step": 179
     },
     {
-      "epoch": 7.2,
-      "learning_rate": 0.00012800000000000002,
-      "loss": 1.5702,
+      "epoch": 0.62,
+      "learning_rate": 7.628865979381443e-05,
+      "loss": 1.8654,
       "step": 180
     },
     {
-      "epoch": 7.24,
-      "learning_rate": 0.0001276,
-      "loss": 1.4598,
+      "epoch": 0.62,
+      "learning_rate": 7.560137457044673e-05,
+      "loss": 1.852,
       "step": 181
     },
     {
-      "epoch": 7.28,
-      "learning_rate": 0.0001272,
-      "loss": 1.6145,
+      "epoch": 0.62,
+      "learning_rate": 7.491408934707905e-05,
+      "loss": 1.9377,
       "step": 182
     },
     {
-      "epoch": 7.32,
-      "learning_rate": 0.00012680000000000002,
-      "loss": 1.3628,
+      "epoch": 0.63,
+      "learning_rate": 7.422680412371135e-05,
+      "loss": 1.8024,
       "step": 183
     },
     {
-      "epoch": 7.36,
-      "learning_rate": 0.0001264,
-      "loss": 1.4578,
+      "epoch": 0.63,
+      "learning_rate": 7.353951890034365e-05,
+      "loss": 1.7329,
       "step": 184
     },
     {
-      "epoch": 7.4,
-      "learning_rate": 0.000126,
-      "loss": 1.7094,
+      "epoch": 0.63,
+      "learning_rate": 7.285223367697595e-05,
+      "loss": 1.8203,
       "step": 185
     },
     {
-      "epoch": 7.44,
-      "learning_rate": 0.00012560000000000002,
-      "loss": 1.4376,
+      "epoch": 0.64,
+      "learning_rate": 7.216494845360825e-05,
+      "loss": 1.8223,
       "step": 186
     },
     {
-      "epoch": 7.48,
-      "learning_rate": 0.0001252,
-      "loss": 1.3393,
+      "epoch": 0.64,
+      "learning_rate": 7.147766323024055e-05,
+      "loss": 1.8506,
       "step": 187
     },
     {
-      "epoch": 7.52,
-      "learning_rate": 0.0001248,
-      "loss": 1.4273,
+      "epoch": 0.64,
+      "learning_rate": 7.079037800687286e-05,
+      "loss": 1.8169,
       "step": 188
     },
     {
-      "epoch": 7.56,
-      "learning_rate": 0.00012440000000000002,
-      "loss": 1.5506,
+      "epoch": 0.65,
+      "learning_rate": 7.010309278350515e-05,
+      "loss": 1.796,
       "step": 189
     },
     {
-      "epoch": 7.6,
-      "learning_rate": 0.000124,
-      "loss": 1.4774,
+      "epoch": 0.65,
+      "learning_rate": 6.941580756013745e-05,
+      "loss": 1.7975,
       "step": 190
     },
     {
-      "epoch": 7.64,
-      "learning_rate": 0.0001236,
-      "loss": 1.4632,
+      "epoch": 0.66,
+      "learning_rate": 6.872852233676977e-05,
+      "loss": 1.8774,
       "step": 191
     },
     {
-      "epoch": 7.68,
-      "learning_rate": 0.0001232,
-      "loss": 1.4568,
+      "epoch": 0.66,
+      "learning_rate": 6.804123711340207e-05,
+      "loss": 1.7822,
       "step": 192
     },
     {
-      "epoch": 7.72,
-      "learning_rate": 0.0001228,
-      "loss": 1.6106,
+      "epoch": 0.66,
+      "learning_rate": 6.735395189003437e-05,
+      "loss": 1.8542,
       "step": 193
     },
     {
-      "epoch": 7.76,
-      "learning_rate": 0.0001224,
-      "loss": 1.577,
+      "epoch": 0.67,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 1.8148,
       "step": 194
     },
     {
-      "epoch": 7.8,
-      "learning_rate": 0.000122,
-      "loss": 1.4805,
+      "epoch": 0.67,
+      "learning_rate": 6.597938144329897e-05,
+      "loss": 1.7446,
       "step": 195
     },
     {
-      "epoch": 7.84,
-      "learning_rate": 0.0001216,
-      "loss": 1.4546,
+      "epoch": 0.67,
+      "learning_rate": 6.529209621993127e-05,
+      "loss": 1.7477,
       "step": 196
     },
     {
-      "epoch": 7.88,
-      "learning_rate": 0.0001212,
-      "loss": 1.5164,
+      "epoch": 0.68,
+      "learning_rate": 6.460481099656359e-05,
+      "loss": 1.8121,
       "step": 197
     },
     {
-      "epoch": 7.92,
-      "learning_rate": 0.0001208,
-      "loss": 1.5061,
+      "epoch": 0.68,
+      "learning_rate": 6.391752577319587e-05,
+      "loss": 1.7289,
       "step": 198
     },
     {
-      "epoch": 7.96,
-      "learning_rate": 0.0001204,
-      "loss": 1.5312,
+      "epoch": 0.68,
+      "learning_rate": 6.323024054982817e-05,
+      "loss": 1.8006,
       "step": 199
     },
     {
-      "epoch": 8.0,
-      "learning_rate": 0.00012,
-      "loss": 1.4463,
+      "epoch": 0.69,
+      "learning_rate": 6.254295532646049e-05,
+      "loss": 1.7348,
       "step": 200
     }
   ],
   "logging_steps": 1,
-  "max_steps": 500,
-  "num_train_epochs": 20,
+  "max_steps": 291,
+  "num_train_epochs": 1,
   "save_steps": 100,
-  "total_flos": 6.816544875119616e+16,
+  "total_flos": 1.2148491200262144e+17,
   "trial_name": null,
   "trial_params": null
 }
diff --git a/checkpoint-200/training_args.bin b/checkpoint-200/training_args.bin
index 4de6572a838c337c9990635a9406ebf46c0ec336..514bd8136ebdc96a275890c7b9b4df6ac072906c 100644
--- a/checkpoint-200/training_args.bin
+++ b/checkpoint-200/training_args.bin
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ef74b31950ae6c8955316bed48c343fb06cda0cb6a8a54ca46ca3cb681c8736
+oid sha256:7e3410eea0ea0eb09ca576511099334880accaab360c0279f3099c9e4d2e877a
 size 4027
diff --git a/checkpoint-300/README.md b/checkpoint-300/README.md
index 08371015f02382e6fcba318f4aaea54ae52cd3c4..2f257a448caef1c59022426ad3ec9ba80acb3821 100644
--- a/checkpoint-300/README.md
+++ b/checkpoint-300/README.md
@@ -4,6 +4,30 @@ library_name: peft
 ## Training procedure
 
 
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: True
+- load_in_4bit: False
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: True
+- load_in_4bit: False
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+
 The following `bitsandbytes` quantization config was used during training:
 - quant_method: bitsandbytes
 - load_in_8bit: True
@@ -29,6 +53,8 @@ The following `bitsandbytes` quantization config was used during training:
 - bnb_4bit_compute_dtype: float32
 ### Framework versions
 
+- PEFT 0.6.0.dev0
+- PEFT 0.6.0.dev0
 - PEFT 0.6.0.dev0
 
 - PEFT 0.6.0.dev0
diff --git a/checkpoint-300/adapter_model.bin b/checkpoint-300/adapter_model.bin
index ec364bb05a02feac36e02fbed5b909ca903878d0..f32eee84dcfc362bb3dd9f9d9127291a2f42668f 100644
--- a/checkpoint-300/adapter_model.bin
+++ b/checkpoint-300/adapter_model.bin
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fced119b995138b5b4c9d37dd51211a238534b883b617216cadd221bc8ae36d
+oid sha256:b39b2ac3c3f75772f547048fda7ecb323076b9689db7d79915bba156dc508f2f
 size 39409357
diff --git a/checkpoint-300/optimizer.pt b/checkpoint-300/optimizer.pt
index 2e6a7d1c4e53d7609d642160c8fe43e397089790..3d79ee6144baeefb728bb603d5ca209014a1847b 100644
--- a/checkpoint-300/optimizer.pt
+++ b/checkpoint-300/optimizer.pt
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67fdec376938273ad2ba5e201ffaba7ad32265728524da3562b132b79fdf2ede
+oid sha256:c734ecaa394370ee4bcd94cc0b2ae016a26765122f3f76327b28c23f96a22732
 size 78844421
diff --git a/checkpoint-300/rng_state.pth b/checkpoint-300/rng_state.pth
index c4f6e431605a7da3e2efbdf0dc1fae0f500de983..b9111227e3b79b9bc3e2a642832c3e49e36216d4 100644
--- a/checkpoint-300/rng_state.pth
+++ b/checkpoint-300/rng_state.pth
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:370c3a07f37a8aae6ea141b54ca992b21699546baf7407eb587b6056f787333b
+oid sha256:972139d83957a9cf2600cb6eeca17287d7a5377c33a53500ae7e13fe830ad36b
 size 14575
diff --git a/checkpoint-300/scheduler.pt b/checkpoint-300/scheduler.pt
index 44bdad4dee332a8a72d1b7ed6d078cb796b00e47..ba7790505ccbdccc3664cac72a2743abf3f54ee6 100644
--- a/checkpoint-300/scheduler.pt
+++ b/checkpoint-300/scheduler.pt
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2bc1def4a9cb9244bae2e6cfff139bec4634b7353bf4cbc7d9c4c7018fdd400
+oid sha256:7d8dcaf05375bb59f736a94e8f8b03d33cdc87bc02411e6527a29996e0a68b3b
 size 627
diff --git a/checkpoint-300/tokenizer.json b/checkpoint-300/tokenizer.json
index dbf002cafbd4818dcff2abc9156c088d681b4533..673c31abdeadf6576c3c754df86459e1ad64e207 100644
--- a/checkpoint-300/tokenizer.json
+++ b/checkpoint-300/tokenizer.json
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17a208233d2ee8d8c83b23bc214df737c44806a1919f444e89b31e586cd956ba
-size 14500471
+oid sha256:85b00d7db4df5df2e3f01cacc3feda246002a672f3356eec7f4b04a22eb0dfbe
+size 14500570
diff --git a/checkpoint-300/trainer_state.json b/checkpoint-300/trainer_state.json
index bf13daeec8eb6cb2d11435b6be5bb180b795d1c8..bf5790647f2fda83e639ffc04ccde4b8937523ee 100644
--- a/checkpoint-300/trainer_state.json
+++ b/checkpoint-300/trainer_state.json
@@ -1,7 +1,7 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 12.0,
+  "epoch": 1.675977653631285,
   "eval_steps": 500,
   "global_step": 300,
   "is_hyper_param_search": false,
@@ -9,1811 +9,1811 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.04,
-      "learning_rate": 0.0001996,
-      "loss": 2.4683,
+      "epoch": 0.01,
+      "learning_rate": 0.00019972067039106145,
+      "loss": 2.6443,
       "step": 1
     },
     {
-      "epoch": 0.08,
-      "learning_rate": 0.00019920000000000002,
-      "loss": 2.2023,
+      "epoch": 0.01,
+      "learning_rate": 0.00019944134078212292,
+      "loss": 2.4104,
       "step": 2
     },
     {
-      "epoch": 0.12,
-      "learning_rate": 0.0001988,
-      "loss": 2.3039,
+      "epoch": 0.02,
+      "learning_rate": 0.00019916201117318435,
+      "loss": 2.4975,
       "step": 3
     },
     {
-      "epoch": 0.16,
-      "learning_rate": 0.0001984,
-      "loss": 2.1855,
+      "epoch": 0.02,
+      "learning_rate": 0.00019888268156424582,
+      "loss": 2.3513,
       "step": 4
     },
     {
-      "epoch": 0.2,
-      "learning_rate": 0.00019800000000000002,
-      "loss": 2.328,
+      "epoch": 0.03,
+      "learning_rate": 0.0001986033519553073,
+      "loss": 2.4274,
       "step": 5
     },
     {
-      "epoch": 0.24,
-      "learning_rate": 0.0001976,
-      "loss": 2.3407,
+      "epoch": 0.03,
+      "learning_rate": 0.00019832402234636873,
+      "loss": 2.3628,
       "step": 6
     },
     {
-      "epoch": 0.28,
-      "learning_rate": 0.0001972,
-      "loss": 2.3432,
+      "epoch": 0.04,
+      "learning_rate": 0.0001980446927374302,
+      "loss": 2.3567,
       "step": 7
     },
     {
-      "epoch": 0.32,
-      "learning_rate": 0.0001968,
-      "loss": 2.2333,
+      "epoch": 0.04,
+      "learning_rate": 0.00019776536312849163,
+      "loss": 2.4121,
       "step": 8
     },
     {
-      "epoch": 0.36,
-      "learning_rate": 0.0001964,
-      "loss": 2.1761,
+      "epoch": 0.05,
+      "learning_rate": 0.00019748603351955307,
+      "loss": 2.4033,
       "step": 9
     },
     {
-      "epoch": 0.4,
-      "learning_rate": 0.000196,
-      "loss": 2.1473,
+      "epoch": 0.06,
+      "learning_rate": 0.00019720670391061454,
+      "loss": 2.2805,
       "step": 10
     },
     {
-      "epoch": 0.44,
-      "learning_rate": 0.0001956,
-      "loss": 2.2076,
+      "epoch": 0.06,
+      "learning_rate": 0.00019692737430167598,
+      "loss": 2.2639,
       "step": 11
     },
     {
-      "epoch": 0.48,
-      "learning_rate": 0.0001952,
-      "loss": 2.1925,
+      "epoch": 0.07,
+      "learning_rate": 0.00019664804469273744,
+      "loss": 2.2724,
       "step": 12
     },
     {
-      "epoch": 0.52,
-      "learning_rate": 0.0001948,
-      "loss": 2.1694,
+      "epoch": 0.07,
+      "learning_rate": 0.00019636871508379888,
+      "loss": 2.332,
       "step": 13
     },
     {
-      "epoch": 0.56,
-      "learning_rate": 0.0001944,
-      "loss": 2.1056,
+      "epoch": 0.08,
+      "learning_rate": 0.00019608938547486035,
+      "loss": 2.2261,
       "step": 14
     },
     {
-      "epoch": 0.6,
-      "learning_rate": 0.000194,
-      "loss": 2.2426,
+      "epoch": 0.08,
+      "learning_rate": 0.00019581005586592182,
+      "loss": 2.2208,
       "step": 15
     },
     {
-      "epoch": 0.64,
-      "learning_rate": 0.00019360000000000002,
-      "loss": 2.2635,
+      "epoch": 0.09,
+      "learning_rate": 0.00019553072625698326,
+      "loss": 2.3351,
       "step": 16
     },
     {
-      "epoch": 0.68,
-      "learning_rate": 0.0001932,
-      "loss": 2.251,
+      "epoch": 0.09,
+      "learning_rate": 0.0001952513966480447,
+      "loss": 2.2475,
       "step": 17
     },
     {
-      "epoch": 0.72,
-      "learning_rate": 0.0001928,
-      "loss": 2.224,
+      "epoch": 0.1,
+      "learning_rate": 0.00019497206703910616,
+      "loss": 2.3283,
       "step": 18
     },
     {
-      "epoch": 0.76,
-      "learning_rate": 0.00019240000000000001,
-      "loss": 2.1848,
+      "epoch": 0.11,
+      "learning_rate": 0.0001946927374301676,
+      "loss": 2.1346,
       "step": 19
     },
     {
-      "epoch": 0.8,
-      "learning_rate": 0.000192,
-      "loss": 2.1341,
+      "epoch": 0.11,
+      "learning_rate": 0.00019441340782122907,
+      "loss": 2.131,
       "step": 20
     },
     {
-      "epoch": 0.84,
-      "learning_rate": 0.0001916,
-      "loss": 2.126,
+      "epoch": 0.12,
+      "learning_rate": 0.0001941340782122905,
+      "loss": 2.1718,
       "step": 21
     },
     {
-      "epoch": 0.88,
-      "learning_rate": 0.0001912,
-      "loss": 2.0959,
+      "epoch": 0.12,
+      "learning_rate": 0.00019385474860335195,
+      "loss": 2.2446,
       "step": 22
     },
     {
-      "epoch": 0.92,
-      "learning_rate": 0.0001908,
-      "loss": 2.2446,
+      "epoch": 0.13,
+      "learning_rate": 0.0001935754189944134,
+      "loss": 2.306,
       "step": 23
     },
     {
-      "epoch": 0.96,
-      "learning_rate": 0.0001904,
-      "loss": 1.9448,
+      "epoch": 0.13,
+      "learning_rate": 0.00019329608938547488,
+      "loss": 2.1908,
       "step": 24
     },
     {
-      "epoch": 1.0,
-      "learning_rate": 0.00019,
-      "loss": 2.0939,
+      "epoch": 0.14,
+      "learning_rate": 0.00019301675977653632,
+      "loss": 2.2844,
       "step": 25
     },
     {
-      "epoch": 1.04,
-      "learning_rate": 0.0001896,
-      "loss": 2.1247,
+      "epoch": 0.15,
+      "learning_rate": 0.00019273743016759779,
+      "loss": 2.2235,
       "step": 26
     },
     {
-      "epoch": 1.08,
-      "learning_rate": 0.0001892,
-      "loss": 1.9417,
+      "epoch": 0.15,
+      "learning_rate": 0.00019245810055865922,
+      "loss": 2.1842,
       "step": 27
     },
     {
-      "epoch": 1.12,
-      "learning_rate": 0.0001888,
-      "loss": 2.105,
+      "epoch": 0.16,
+      "learning_rate": 0.00019217877094972066,
+      "loss": 2.2675,
       "step": 28
     },
     {
-      "epoch": 1.16,
-      "learning_rate": 0.0001884,
-      "loss": 2.1595,
+      "epoch": 0.16,
+      "learning_rate": 0.00019189944134078213,
+      "loss": 2.2532,
       "step": 29
     },
     {
-      "epoch": 1.2,
-      "learning_rate": 0.000188,
-      "loss": 2.2009,
+      "epoch": 0.17,
+      "learning_rate": 0.00019162011173184357,
+      "loss": 2.1788,
       "step": 30
     },
     {
-      "epoch": 1.24,
-      "learning_rate": 0.0001876,
-      "loss": 2.0784,
+      "epoch": 0.17,
+      "learning_rate": 0.00019134078212290504,
+      "loss": 2.2494,
       "step": 31
     },
     {
-      "epoch": 1.28,
-      "learning_rate": 0.00018720000000000002,
-      "loss": 2.2173,
+      "epoch": 0.18,
+      "learning_rate": 0.0001910614525139665,
+      "loss": 2.1995,
       "step": 32
     },
     {
-      "epoch": 1.32,
-      "learning_rate": 0.00018680000000000001,
-      "loss": 2.1185,
+      "epoch": 0.18,
+      "learning_rate": 0.00019078212290502794,
+      "loss": 2.1451,
       "step": 33
     },
     {
-      "epoch": 1.36,
-      "learning_rate": 0.00018640000000000003,
-      "loss": 1.988,
+      "epoch": 0.19,
+      "learning_rate": 0.0001905027932960894,
+      "loss": 2.223,
       "step": 34
     },
     {
-      "epoch": 1.4,
-      "learning_rate": 0.00018600000000000002,
-      "loss": 1.9493,
+      "epoch": 0.2,
+      "learning_rate": 0.00019022346368715085,
+      "loss": 2.2854,
       "step": 35
     },
     {
-      "epoch": 1.44,
-      "learning_rate": 0.0001856,
-      "loss": 1.9947,
+      "epoch": 0.2,
+      "learning_rate": 0.0001899441340782123,
+      "loss": 2.2265,
       "step": 36
     },
     {
-      "epoch": 1.48,
-      "learning_rate": 0.00018520000000000003,
-      "loss": 2.0506,
+      "epoch": 0.21,
+      "learning_rate": 0.00018966480446927375,
+      "loss": 2.1214,
       "step": 37
     },
     {
-      "epoch": 1.52,
-      "learning_rate": 0.00018480000000000002,
-      "loss": 2.0829,
+      "epoch": 0.21,
+      "learning_rate": 0.0001893854748603352,
+      "loss": 2.1898,
       "step": 38
     },
     {
-      "epoch": 1.56,
-      "learning_rate": 0.0001844,
-      "loss": 2.1455,
+      "epoch": 0.22,
+      "learning_rate": 0.00018910614525139666,
+      "loss": 2.1974,
       "step": 39
     },
     {
-      "epoch": 1.6,
-      "learning_rate": 0.00018400000000000003,
-      "loss": 2.0304,
+      "epoch": 0.22,
+      "learning_rate": 0.0001888268156424581,
+      "loss": 2.2259,
       "step": 40
     },
     {
-      "epoch": 1.64,
-      "learning_rate": 0.00018360000000000002,
-      "loss": 2.006,
+      "epoch": 0.23,
+      "learning_rate": 0.00018854748603351957,
+      "loss": 2.2094,
       "step": 41
     },
     {
-      "epoch": 1.68,
-      "learning_rate": 0.0001832,
-      "loss": 2.1759,
+      "epoch": 0.23,
+      "learning_rate": 0.00018826815642458103,
+      "loss": 2.1731,
       "step": 42
     },
     {
-      "epoch": 1.72,
-      "learning_rate": 0.00018280000000000003,
-      "loss": 2.0093,
+      "epoch": 0.24,
+      "learning_rate": 0.00018798882681564247,
+      "loss": 2.2373,
       "step": 43
     },
     {
-      "epoch": 1.76,
-      "learning_rate": 0.00018240000000000002,
-      "loss": 2.0683,
+      "epoch": 0.25,
+      "learning_rate": 0.0001877094972067039,
+      "loss": 2.2295,
       "step": 44
     },
     {
-      "epoch": 1.8,
-      "learning_rate": 0.000182,
-      "loss": 2.1352,
+      "epoch": 0.25,
+      "learning_rate": 0.00018743016759776538,
+      "loss": 2.1947,
       "step": 45
     },
     {
-      "epoch": 1.84,
-      "learning_rate": 0.00018160000000000002,
-      "loss": 1.9736,
+      "epoch": 0.26,
+      "learning_rate": 0.00018715083798882682,
+      "loss": 2.2115,
       "step": 46
     },
     {
-      "epoch": 1.88,
-      "learning_rate": 0.0001812,
-      "loss": 1.9631,
+      "epoch": 0.26,
+      "learning_rate": 0.00018687150837988828,
+      "loss": 2.1224,
       "step": 47
     },
     {
-      "epoch": 1.92,
-      "learning_rate": 0.0001808,
-      "loss": 2.1024,
+      "epoch": 0.27,
+      "learning_rate": 0.00018659217877094972,
+      "loss": 2.2137,
       "step": 48
     },
     {
-      "epoch": 1.96,
-      "learning_rate": 0.00018040000000000002,
-      "loss": 1.9895,
+      "epoch": 0.27,
+      "learning_rate": 0.00018631284916201116,
+      "loss": 2.2338,
       "step": 49
     },
     {
-      "epoch": 2.0,
-      "learning_rate": 0.00018,
-      "loss": 2.0067,
+      "epoch": 0.28,
+      "learning_rate": 0.00018603351955307266,
+      "loss": 2.1298,
       "step": 50
     },
     {
-      "epoch": 2.04,
-      "learning_rate": 0.0001796,
-      "loss": 2.0509,
+      "epoch": 0.28,
+      "learning_rate": 0.0001857541899441341,
+      "loss": 2.0883,
       "step": 51
     },
     {
-      "epoch": 2.08,
-      "learning_rate": 0.00017920000000000002,
-      "loss": 1.8795,
+      "epoch": 0.29,
+      "learning_rate": 0.00018547486033519553,
+      "loss": 2.1216,
       "step": 52
     },
     {
-      "epoch": 2.12,
-      "learning_rate": 0.0001788,
-      "loss": 2.0633,
+      "epoch": 0.3,
+      "learning_rate": 0.000185195530726257,
+      "loss": 2.2112,
       "step": 53
     },
     {
-      "epoch": 2.16,
-      "learning_rate": 0.0001784,
-      "loss": 1.9998,
+      "epoch": 0.3,
+      "learning_rate": 0.00018491620111731844,
+      "loss": 2.1224,
       "step": 54
     },
     {
-      "epoch": 2.2,
-      "learning_rate": 0.00017800000000000002,
-      "loss": 2.0675,
+      "epoch": 0.31,
+      "learning_rate": 0.0001846368715083799,
+      "loss": 2.2375,
       "step": 55
     },
     {
-      "epoch": 2.24,
-      "learning_rate": 0.0001776,
-      "loss": 2.0129,
+      "epoch": 0.31,
+      "learning_rate": 0.00018435754189944135,
+      "loss": 2.2235,
       "step": 56
     },
     {
-      "epoch": 2.28,
-      "learning_rate": 0.0001772,
-      "loss": 1.9302,
+      "epoch": 0.32,
+      "learning_rate": 0.00018407821229050279,
+      "loss": 2.1682,
       "step": 57
     },
     {
-      "epoch": 2.32,
-      "learning_rate": 0.00017680000000000001,
-      "loss": 2.0472,
+      "epoch": 0.32,
+      "learning_rate": 0.00018379888268156425,
+      "loss": 2.2077,
       "step": 58
     },
     {
-      "epoch": 2.36,
-      "learning_rate": 0.0001764,
-      "loss": 2.0031,
+      "epoch": 0.33,
+      "learning_rate": 0.00018351955307262572,
+      "loss": 2.1596,
       "step": 59
     },
     {
-      "epoch": 2.4,
-      "learning_rate": 0.00017600000000000002,
-      "loss": 2.0231,
+      "epoch": 0.34,
+      "learning_rate": 0.00018324022346368716,
+      "loss": 2.1311,
       "step": 60
     },
     {
-      "epoch": 2.44,
-      "learning_rate": 0.0001756,
-      "loss": 2.0192,
+      "epoch": 0.34,
+      "learning_rate": 0.00018296089385474862,
+      "loss": 2.1333,
       "step": 61
     },
     {
-      "epoch": 2.48,
-      "learning_rate": 0.0001752,
-      "loss": 2.1336,
+      "epoch": 0.35,
+      "learning_rate": 0.00018268156424581006,
+      "loss": 2.0901,
       "step": 62
     },
     {
-      "epoch": 2.52,
-      "learning_rate": 0.00017480000000000002,
-      "loss": 1.7753,
+      "epoch": 0.35,
+      "learning_rate": 0.00018240223463687153,
+      "loss": 2.1971,
       "step": 63
     },
     {
-      "epoch": 2.56,
-      "learning_rate": 0.0001744,
-      "loss": 2.0274,
+      "epoch": 0.36,
+      "learning_rate": 0.00018212290502793297,
+      "loss": 2.2602,
       "step": 64
     },
     {
-      "epoch": 2.6,
-      "learning_rate": 0.000174,
-      "loss": 1.8893,
+      "epoch": 0.36,
+      "learning_rate": 0.0001818435754189944,
+      "loss": 2.2194,
       "step": 65
     },
     {
-      "epoch": 2.64,
-      "learning_rate": 0.00017360000000000002,
-      "loss": 2.0341,
+      "epoch": 0.37,
+      "learning_rate": 0.00018156424581005588,
+      "loss": 2.1218,
       "step": 66
     },
     {
-      "epoch": 2.68,
-      "learning_rate": 0.0001732,
-      "loss": 2.1081,
+      "epoch": 0.37,
+      "learning_rate": 0.00018128491620111731,
+      "loss": 2.2049,
       "step": 67
     },
     {
-      "epoch": 2.72,
-      "learning_rate": 0.0001728,
-      "loss": 1.9463,
+      "epoch": 0.38,
+      "learning_rate": 0.00018100558659217878,
+      "loss": 2.1521,
       "step": 68
     },
     {
-      "epoch": 2.76,
-      "learning_rate": 0.00017240000000000002,
-      "loss": 2.0607,
+      "epoch": 0.39,
+      "learning_rate": 0.00018072625698324025,
+      "loss": 2.112,
       "step": 69
     },
     {
-      "epoch": 2.8,
-      "learning_rate": 0.000172,
-      "loss": 1.9803,
+      "epoch": 0.39,
+      "learning_rate": 0.0001804469273743017,
+      "loss": 2.1906,
       "step": 70
     },
     {
-      "epoch": 2.84,
-      "learning_rate": 0.0001716,
-      "loss": 1.7663,
+      "epoch": 0.4,
+      "learning_rate": 0.00018016759776536313,
+      "loss": 2.1717,
       "step": 71
     },
     {
-      "epoch": 2.88,
-      "learning_rate": 0.00017120000000000001,
-      "loss": 2.1116,
+      "epoch": 0.4,
+      "learning_rate": 0.0001798882681564246,
+      "loss": 2.0712,
       "step": 72
     },
     {
-      "epoch": 2.92,
-      "learning_rate": 0.0001708,
-      "loss": 1.9039,
+      "epoch": 0.41,
+      "learning_rate": 0.00017960893854748603,
+      "loss": 2.141,
       "step": 73
     },
     {
-      "epoch": 2.96,
-      "learning_rate": 0.0001704,
-      "loss": 2.049,
+      "epoch": 0.41,
+      "learning_rate": 0.0001793296089385475,
+      "loss": 2.0656,
       "step": 74
     },
     {
-      "epoch": 3.0,
-      "learning_rate": 0.00017,
-      "loss": 1.991,
+      "epoch": 0.42,
+      "learning_rate": 0.00017905027932960894,
+      "loss": 2.1125,
       "step": 75
     },
     {
-      "epoch": 3.04,
-      "learning_rate": 0.0001696,
-      "loss": 1.8755,
+      "epoch": 0.42,
+      "learning_rate": 0.00017877094972067038,
+      "loss": 2.0869,
       "step": 76
     },
     {
-      "epoch": 3.08,
-      "learning_rate": 0.0001692,
-      "loss": 2.0367,
+      "epoch": 0.43,
+      "learning_rate": 0.00017849162011173187,
+      "loss": 2.2478,
       "step": 77
     },
     {
-      "epoch": 3.12,
-      "learning_rate": 0.0001688,
-      "loss": 1.9959,
+      "epoch": 0.44,
+      "learning_rate": 0.0001782122905027933,
+      "loss": 2.1535,
       "step": 78
     },
     {
-      "epoch": 3.16,
-      "learning_rate": 0.0001684,
-      "loss": 1.8051,
+      "epoch": 0.44,
+      "learning_rate": 0.00017793296089385475,
+      "loss": 2.1927,
       "step": 79
     },
     {
-      "epoch": 3.2,
-      "learning_rate": 0.000168,
-      "loss": 2.0446,
+      "epoch": 0.45,
+      "learning_rate": 0.00017765363128491622,
+      "loss": 2.1213,
       "step": 80
     },
     {
-      "epoch": 3.24,
-      "learning_rate": 0.0001676,
-      "loss": 1.7873,
+      "epoch": 0.45,
+      "learning_rate": 0.00017737430167597766,
+      "loss": 2.0981,
       "step": 81
     },
     {
-      "epoch": 3.28,
-      "learning_rate": 0.0001672,
-      "loss": 1.9264,
+      "epoch": 0.46,
+      "learning_rate": 0.00017709497206703912,
+      "loss": 2.1828,
       "step": 82
     },
     {
-      "epoch": 3.32,
-      "learning_rate": 0.0001668,
-      "loss": 1.8595,
+      "epoch": 0.46,
+      "learning_rate": 0.00017681564245810056,
+      "loss": 2.0562,
       "step": 83
     },
     {
-      "epoch": 3.36,
-      "learning_rate": 0.0001664,
-      "loss": 1.9992,
+      "epoch": 0.47,
+      "learning_rate": 0.000176536312849162,
+      "loss": 2.1334,
       "step": 84
     },
     {
-      "epoch": 3.4,
-      "learning_rate": 0.000166,
-      "loss": 1.8783,
+      "epoch": 0.47,
+      "learning_rate": 0.00017625698324022347,
+      "loss": 2.1225,
       "step": 85
     },
     {
-      "epoch": 3.44,
-      "learning_rate": 0.0001656,
-      "loss": 2.0216,
+      "epoch": 0.48,
+      "learning_rate": 0.00017597765363128493,
+      "loss": 2.2098,
       "step": 86
     },
     {
-      "epoch": 3.48,
-      "learning_rate": 0.0001652,
-      "loss": 1.947,
+      "epoch": 0.49,
+      "learning_rate": 0.00017569832402234637,
+      "loss": 2.1519,
       "step": 87
     },
     {
-      "epoch": 3.52,
-      "learning_rate": 0.0001648,
-      "loss": 1.9554,
+      "epoch": 0.49,
+      "learning_rate": 0.00017541899441340784,
+      "loss": 2.1132,
       "step": 88
     },
     {
-      "epoch": 3.56,
-      "learning_rate": 0.0001644,
-      "loss": 1.8563,
+      "epoch": 0.5,
+      "learning_rate": 0.00017513966480446928,
+      "loss": 2.0333,
       "step": 89
     },
     {
-      "epoch": 3.6,
-      "learning_rate": 0.000164,
-      "loss": 1.7795,
+      "epoch": 0.5,
+      "learning_rate": 0.00017486033519553075,
+      "loss": 2.2764,
       "step": 90
     },
     {
-      "epoch": 3.64,
-      "learning_rate": 0.0001636,
-      "loss": 1.9347,
+      "epoch": 0.51,
+      "learning_rate": 0.00017458100558659218,
+      "loss": 2.1838,
       "step": 91
     },
     {
-      "epoch": 3.68,
-      "learning_rate": 0.0001632,
-      "loss": 2.0078,
+      "epoch": 0.51,
+      "learning_rate": 0.00017430167597765362,
+      "loss": 2.1386,
       "step": 92
     },
     {
-      "epoch": 3.72,
-      "learning_rate": 0.0001628,
-      "loss": 1.9964,
+      "epoch": 0.52,
+      "learning_rate": 0.0001740223463687151,
+      "loss": 2.1034,
       "step": 93
     },
     {
-      "epoch": 3.76,
-      "learning_rate": 0.00016240000000000002,
-      "loss": 1.9004,
+      "epoch": 0.53,
+      "learning_rate": 0.00017374301675977656,
+      "loss": 2.0346,
       "step": 94
     },
     {
-      "epoch": 3.8,
-      "learning_rate": 0.000162,
-      "loss": 1.9446,
+      "epoch": 0.53,
+      "learning_rate": 0.000173463687150838,
+      "loss": 2.0274,
       "step": 95
     },
     {
-      "epoch": 3.84,
-      "learning_rate": 0.00016160000000000002,
-      "loss": 1.8857,
+      "epoch": 0.54,
+      "learning_rate": 0.00017318435754189946,
+      "loss": 2.1036,
       "step": 96
     },
     {
-      "epoch": 3.88,
-      "learning_rate": 0.00016120000000000002,
-      "loss": 1.8797,
+      "epoch": 0.54,
+      "learning_rate": 0.0001729050279329609,
+      "loss": 2.1208,
       "step": 97
     },
     {
-      "epoch": 3.92,
-      "learning_rate": 0.0001608,
-      "loss": 1.7643,
+      "epoch": 0.55,
+      "learning_rate": 0.00017262569832402237,
+      "loss": 2.0572,
       "step": 98
     },
     {
-      "epoch": 3.96,
-      "learning_rate": 0.00016040000000000002,
-      "loss": 1.9724,
+      "epoch": 0.55,
+      "learning_rate": 0.0001723463687150838,
+      "loss": 2.1702,
       "step": 99
     },
     {
-      "epoch": 4.0,
-      "learning_rate": 0.00016,
-      "loss": 1.9058,
+      "epoch": 0.56,
+      "learning_rate": 0.00017206703910614525,
+      "loss": 2.1302,
       "step": 100
     },
     {
-      "epoch": 4.04,
-      "learning_rate": 0.0001596,
-      "loss": 1.8663,
+      "epoch": 0.56,
+      "learning_rate": 0.0001717877094972067,
+      "loss": 2.0175,
       "step": 101
     },
     {
-      "epoch": 4.08,
-      "learning_rate": 0.00015920000000000002,
-      "loss": 1.8457,
+      "epoch": 0.57,
+      "learning_rate": 0.00017150837988826815,
+      "loss": 2.1006,
       "step": 102
     },
     {
-      "epoch": 4.12,
-      "learning_rate": 0.0001588,
-      "loss": 1.8394,
+      "epoch": 0.58,
+      "learning_rate": 0.00017122905027932962,
+      "loss": 2.0662,
       "step": 103
     },
     {
-      "epoch": 4.16,
-      "learning_rate": 0.00015840000000000003,
-      "loss": 1.8941,
+      "epoch": 0.58,
+      "learning_rate": 0.00017094972067039109,
+      "loss": 1.988,
       "step": 104
     },
     {
-      "epoch": 4.2,
-      "learning_rate": 0.00015800000000000002,
-      "loss": 1.8601,
+      "epoch": 0.59,
+      "learning_rate": 0.00017067039106145253,
+      "loss": 2.1008,
       "step": 105
     },
     {
-      "epoch": 4.24,
-      "learning_rate": 0.0001576,
-      "loss": 1.7365,
+      "epoch": 0.59,
+      "learning_rate": 0.00017039106145251396,
+      "loss": 2.1482,
       "step": 106
     },
     {
-      "epoch": 4.28,
-      "learning_rate": 0.00015720000000000003,
-      "loss": 1.8809,
+      "epoch": 0.6,
+      "learning_rate": 0.00017011173184357543,
+      "loss": 2.1052,
       "step": 107
     },
     {
-      "epoch": 4.32,
-      "learning_rate": 0.00015680000000000002,
-      "loss": 2.0206,
+      "epoch": 0.6,
+      "learning_rate": 0.00016983240223463687,
+      "loss": 2.0978,
       "step": 108
     },
     {
-      "epoch": 4.36,
-      "learning_rate": 0.0001564,
-      "loss": 1.7776,
+      "epoch": 0.61,
+      "learning_rate": 0.00016955307262569834,
+      "loss": 2.1303,
       "step": 109
     },
     {
-      "epoch": 4.4,
-      "learning_rate": 0.00015600000000000002,
-      "loss": 1.9089,
+      "epoch": 0.61,
+      "learning_rate": 0.00016927374301675978,
+      "loss": 2.0794,
       "step": 110
     },
     {
-      "epoch": 4.44,
-      "learning_rate": 0.00015560000000000001,
-      "loss": 1.8464,
+      "epoch": 0.62,
+      "learning_rate": 0.00016899441340782122,
+      "loss": 2.1059,
       "step": 111
     },
     {
-      "epoch": 4.48,
-      "learning_rate": 0.0001552,
-      "loss": 1.7943,
+      "epoch": 0.63,
+      "learning_rate": 0.0001687150837988827,
+      "loss": 1.9642,
       "step": 112
     },
     {
-      "epoch": 4.52,
-      "learning_rate": 0.00015480000000000002,
-      "loss": 1.8081,
+      "epoch": 0.63,
+      "learning_rate": 0.00016843575418994415,
+      "loss": 2.0415,
       "step": 113
     },
     {
-      "epoch": 4.56,
-      "learning_rate": 0.0001544,
-      "loss": 1.734,
+      "epoch": 0.64,
+      "learning_rate": 0.0001681564245810056,
+      "loss": 2.0795,
       "step": 114
     },
     {
-      "epoch": 4.6,
-      "learning_rate": 0.000154,
-      "loss": 1.8379,
+      "epoch": 0.64,
+      "learning_rate": 0.00016787709497206705,
+      "loss": 2.0238,
       "step": 115
     },
     {
-      "epoch": 4.64,
-      "learning_rate": 0.00015360000000000002,
-      "loss": 1.6841,
+      "epoch": 0.65,
+      "learning_rate": 0.0001675977653631285,
+      "loss": 2.078,
       "step": 116
     },
     {
-      "epoch": 4.68,
-      "learning_rate": 0.0001532,
-      "loss": 1.8253,
+      "epoch": 0.65,
+      "learning_rate": 0.00016731843575418996,
+      "loss": 2.1362,
       "step": 117
     },
     {
-      "epoch": 4.72,
-      "learning_rate": 0.0001528,
-      "loss": 1.7607,
+      "epoch": 0.66,
+      "learning_rate": 0.0001670391061452514,
+      "loss": 2.0552,
       "step": 118
     },
     {
-      "epoch": 4.76,
-      "learning_rate": 0.00015240000000000002,
-      "loss": 1.8205,
+      "epoch": 0.66,
+      "learning_rate": 0.00016675977653631284,
+      "loss": 2.213,
       "step": 119
     },
     {
-      "epoch": 4.8,
-      "learning_rate": 0.000152,
-      "loss": 1.8443,
+      "epoch": 0.67,
+      "learning_rate": 0.0001664804469273743,
+      "loss": 1.9999,
       "step": 120
     },
     {
-      "epoch": 4.84,
-      "learning_rate": 0.0001516,
-      "loss": 1.8824,
+      "epoch": 0.68,
+      "learning_rate": 0.00016620111731843577,
+      "loss": 2.06,
       "step": 121
     },
     {
-      "epoch": 4.88,
-      "learning_rate": 0.00015120000000000002,
-      "loss": 1.8369,
+      "epoch": 0.68,
+      "learning_rate": 0.0001659217877094972,
+      "loss": 2.0177,
       "step": 122
     },
     {
-      "epoch": 4.92,
-      "learning_rate": 0.0001508,
-      "loss": 1.8017,
+      "epoch": 0.69,
+      "learning_rate": 0.00016564245810055868,
+      "loss": 2.0504,
       "step": 123
     },
     {
-      "epoch": 4.96,
-      "learning_rate": 0.0001504,
-      "loss": 1.7858,
+      "epoch": 0.69,
+      "learning_rate": 0.00016536312849162012,
+      "loss": 2.0585,
       "step": 124
     },
     {
-      "epoch": 5.0,
-      "learning_rate": 0.00015000000000000001,
-      "loss": 1.8366,
+      "epoch": 0.7,
+      "learning_rate": 0.00016508379888268158,
+      "loss": 2.0273,
       "step": 125
     },
     {
-      "epoch": 5.04,
-      "learning_rate": 0.0001496,
-      "loss": 1.7353,
+      "epoch": 0.7,
+      "learning_rate": 0.00016480446927374302,
+      "loss": 2.0549,
       "step": 126
     },
     {
-      "epoch": 5.08,
-      "learning_rate": 0.0001492,
-      "loss": 1.6017,
+      "epoch": 0.71,
+      "learning_rate": 0.00016452513966480446,
+      "loss": 2.044,
       "step": 127
     },
     {
-      "epoch": 5.12,
-      "learning_rate": 0.0001488,
-      "loss": 1.6645,
+      "epoch": 0.72,
+      "learning_rate": 0.00016424581005586593,
+      "loss": 2.0731,
       "step": 128
     },
     {
-      "epoch": 5.16,
-      "learning_rate": 0.0001484,
-      "loss": 1.8663,
+      "epoch": 0.72,
+      "learning_rate": 0.00016396648044692737,
+      "loss": 2.0568,
       "step": 129
     },
     {
-      "epoch": 5.2,
-      "learning_rate": 0.000148,
-      "loss": 1.7009,
+      "epoch": 0.73,
+      "learning_rate": 0.00016368715083798883,
+      "loss": 2.007,
       "step": 130
     },
     {
-      "epoch": 5.24,
-      "learning_rate": 0.0001476,
-      "loss": 1.7371,
+      "epoch": 0.73,
+      "learning_rate": 0.0001634078212290503,
+      "loss": 2.0707,
       "step": 131
     },
     {
-      "epoch": 5.28,
-      "learning_rate": 0.0001472,
-      "loss": 1.8555,
+      "epoch": 0.74,
+      "learning_rate": 0.00016312849162011174,
+      "loss": 1.9793,
       "step": 132
     },
     {
-      "epoch": 5.32,
-      "learning_rate": 0.00014680000000000002,
-      "loss": 1.6373,
+      "epoch": 0.74,
+      "learning_rate": 0.0001628491620111732,
+      "loss": 2.1311,
       "step": 133
     },
     {
-      "epoch": 5.36,
-      "learning_rate": 0.0001464,
-      "loss": 1.7211,
+      "epoch": 0.75,
+      "learning_rate": 0.00016256983240223465,
+      "loss": 2.0016,
       "step": 134
     },
     {
-      "epoch": 5.4,
-      "learning_rate": 0.000146,
-      "loss": 1.614,
+      "epoch": 0.75,
+      "learning_rate": 0.00016229050279329609,
+      "loss": 1.9945,
       "step": 135
     },
     {
-      "epoch": 5.44,
-      "learning_rate": 0.00014560000000000002,
-      "loss": 1.8736,
+      "epoch": 0.76,
+      "learning_rate": 0.00016201117318435755,
+      "loss": 2.0186,
       "step": 136
     },
     {
-      "epoch": 5.48,
-      "learning_rate": 0.0001452,
-      "loss": 1.7229,
+      "epoch": 0.77,
+      "learning_rate": 0.000161731843575419,
+      "loss": 2.0971,
       "step": 137
     },
     {
-      "epoch": 5.52,
-      "learning_rate": 0.0001448,
-      "loss": 1.7315,
+      "epoch": 0.77,
+      "learning_rate": 0.00016145251396648046,
+      "loss": 2.0883,
       "step": 138
     },
     {
-      "epoch": 5.56,
-      "learning_rate": 0.0001444,
-      "loss": 1.7259,
+      "epoch": 0.78,
+      "learning_rate": 0.00016117318435754192,
+      "loss": 2.0803,
       "step": 139
     },
     {
-      "epoch": 5.6,
-      "learning_rate": 0.000144,
-      "loss": 1.7032,
+      "epoch": 0.78,
+      "learning_rate": 0.00016089385474860336,
+      "loss": 2.0617,
       "step": 140
     },
     {
-      "epoch": 5.64,
-      "learning_rate": 0.0001436,
-      "loss": 1.9237,
+      "epoch": 0.79,
+      "learning_rate": 0.00016061452513966483,
+      "loss": 2.1265,
       "step": 141
     },
     {
-      "epoch": 5.68,
-      "learning_rate": 0.0001432,
-      "loss": 1.7821,
+      "epoch": 0.79,
+      "learning_rate": 0.00016033519553072627,
+      "loss": 2.0151,
       "step": 142
     },
     {
-      "epoch": 5.72,
-      "learning_rate": 0.0001428,
-      "loss": 1.6081,
+      "epoch": 0.8,
+      "learning_rate": 0.0001600558659217877,
+      "loss": 1.996,
       "step": 143
     },
     {
-      "epoch": 5.76,
-      "learning_rate": 0.0001424,
-      "loss": 1.7979,
+      "epoch": 0.8,
+      "learning_rate": 0.00015977653631284918,
+      "loss": 2.0164,
       "step": 144
     },
     {
-      "epoch": 5.8,
-      "learning_rate": 0.000142,
-      "loss": 1.6675,
+      "epoch": 0.81,
+      "learning_rate": 0.00015949720670391061,
+      "loss": 2.0314,
       "step": 145
     },
     {
-      "epoch": 5.84,
-      "learning_rate": 0.0001416,
-      "loss": 1.6758,
+      "epoch": 0.82,
+      "learning_rate": 0.00015921787709497208,
+      "loss": 1.9501,
       "step": 146
     },
     {
-      "epoch": 5.88,
-      "learning_rate": 0.0001412,
-      "loss": 1.7783,
+      "epoch": 0.82,
+      "learning_rate": 0.00015893854748603352,
+      "loss": 2.087,
       "step": 147
     },
     {
-      "epoch": 5.92,
-      "learning_rate": 0.0001408,
-      "loss": 1.5935,
+      "epoch": 0.83,
+      "learning_rate": 0.000158659217877095,
+      "loss": 2.0262,
       "step": 148
     },
     {
-      "epoch": 5.96,
-      "learning_rate": 0.0001404,
-      "loss": 1.7372,
+      "epoch": 0.83,
+      "learning_rate": 0.00015837988826815643,
+      "loss": 2.0765,
       "step": 149
     },
     {
-      "epoch": 6.0,
-      "learning_rate": 0.00014,
-      "loss": 1.6308,
+      "epoch": 0.84,
+      "learning_rate": 0.0001581005586592179,
+      "loss": 2.105,
       "step": 150
     },
     {
-      "epoch": 6.04,
-      "learning_rate": 0.0001396,
-      "loss": 1.5829,
+      "epoch": 0.84,
+      "learning_rate": 0.00015782122905027933,
+      "loss": 1.9863,
       "step": 151
     },
     {
-      "epoch": 6.08,
-      "learning_rate": 0.0001392,
-      "loss": 1.6538,
+      "epoch": 0.85,
+      "learning_rate": 0.0001575418994413408,
+      "loss": 1.9873,
       "step": 152
     },
     {
-      "epoch": 6.12,
-      "learning_rate": 0.00013879999999999999,
-      "loss": 1.7624,
+      "epoch": 0.85,
+      "learning_rate": 0.00015726256983240224,
+      "loss": 2.0094,
       "step": 153
     },
     {
-      "epoch": 6.16,
-      "learning_rate": 0.0001384,
-      "loss": 1.4968,
+      "epoch": 0.86,
+      "learning_rate": 0.00015698324022346368,
+      "loss": 1.9141,
       "step": 154
     },
     {
-      "epoch": 6.2,
-      "learning_rate": 0.000138,
-      "loss": 1.7305,
+      "epoch": 0.87,
+      "learning_rate": 0.00015670391061452514,
+      "loss": 1.917,
       "step": 155
     },
     {
-      "epoch": 6.24,
-      "learning_rate": 0.00013759999999999998,
-      "loss": 1.6536,
+      "epoch": 0.87,
+      "learning_rate": 0.00015642458100558658,
+      "loss": 2.109,
       "step": 156
     },
     {
-      "epoch": 6.28,
-      "learning_rate": 0.00013720000000000003,
-      "loss": 1.654,
+      "epoch": 0.88,
+      "learning_rate": 0.00015614525139664805,
+      "loss": 1.9799,
       "step": 157
     },
     {
-      "epoch": 6.32,
-      "learning_rate": 0.00013680000000000002,
-      "loss": 1.7163,
+      "epoch": 0.88,
+      "learning_rate": 0.00015586592178770952,
+      "loss": 1.9571,
       "step": 158
     },
     {
-      "epoch": 6.36,
-      "learning_rate": 0.0001364,
-      "loss": 1.6599,
+      "epoch": 0.89,
+      "learning_rate": 0.00015558659217877096,
+      "loss": 1.9931,
       "step": 159
     },
     {
-      "epoch": 6.4,
-      "learning_rate": 0.00013600000000000003,
-      "loss": 1.5729,
+      "epoch": 0.89,
+      "learning_rate": 0.00015530726256983242,
+      "loss": 2.1004,
       "step": 160
     },
     {
-      "epoch": 6.44,
-      "learning_rate": 0.00013560000000000002,
-      "loss": 1.5291,
+      "epoch": 0.9,
+      "learning_rate": 0.00015502793296089386,
+      "loss": 2.0385,
       "step": 161
     },
     {
-      "epoch": 6.48,
-      "learning_rate": 0.0001352,
-      "loss": 1.5666,
+      "epoch": 0.91,
+      "learning_rate": 0.0001547486033519553,
+      "loss": 1.9751,
       "step": 162
     },
     {
-      "epoch": 6.52,
-      "learning_rate": 0.00013480000000000002,
-      "loss": 1.7576,
+      "epoch": 0.91,
+      "learning_rate": 0.00015446927374301677,
+      "loss": 2.0544,
       "step": 163
     },
     {
-      "epoch": 6.56,
-      "learning_rate": 0.00013440000000000001,
-      "loss": 1.4462,
+      "epoch": 0.92,
+      "learning_rate": 0.0001541899441340782,
+      "loss": 2.0069,
       "step": 164
     },
     {
-      "epoch": 6.6,
-      "learning_rate": 0.000134,
-      "loss": 1.5659,
+      "epoch": 0.92,
+      "learning_rate": 0.00015391061452513967,
+      "loss": 1.9576,
       "step": 165
     },
     {
-      "epoch": 6.64,
-      "learning_rate": 0.00013360000000000002,
-      "loss": 1.6234,
+      "epoch": 0.93,
+      "learning_rate": 0.00015363128491620114,
+      "loss": 1.8991,
       "step": 166
     },
     {
-      "epoch": 6.68,
-      "learning_rate": 0.0001332,
-      "loss": 1.5176,
+      "epoch": 0.93,
+      "learning_rate": 0.00015335195530726258,
+      "loss": 1.9336,
       "step": 167
     },
     {
-      "epoch": 6.72,
-      "learning_rate": 0.0001328,
-      "loss": 1.667,
+      "epoch": 0.94,
+      "learning_rate": 0.00015307262569832405,
+      "loss": 1.9736,
       "step": 168
     },
     {
-      "epoch": 6.76,
-      "learning_rate": 0.00013240000000000002,
-      "loss": 1.6514,
+      "epoch": 0.94,
+      "learning_rate": 0.00015279329608938548,
+      "loss": 1.9702,
       "step": 169
     },
     {
-      "epoch": 6.8,
-      "learning_rate": 0.000132,
-      "loss": 1.7179,
+      "epoch": 0.95,
+      "learning_rate": 0.00015251396648044692,
+      "loss": 1.9055,
       "step": 170
     },
     {
-      "epoch": 6.84,
-      "learning_rate": 0.0001316,
-      "loss": 1.4373,
+      "epoch": 0.96,
+      "learning_rate": 0.0001522346368715084,
+      "loss": 2.0503,
       "step": 171
     },
     {
-      "epoch": 6.88,
-      "learning_rate": 0.00013120000000000002,
-      "loss": 1.7044,
+      "epoch": 0.96,
+      "learning_rate": 0.00015195530726256983,
+      "loss": 2.0039,
       "step": 172
     },
     {
-      "epoch": 6.92,
-      "learning_rate": 0.0001308,
-      "loss": 1.5673,
+      "epoch": 0.97,
+      "learning_rate": 0.0001516759776536313,
+      "loss": 1.9406,
       "step": 173
     },
     {
-      "epoch": 6.96,
-      "learning_rate": 0.0001304,
-      "loss": 1.6303,
+      "epoch": 0.97,
+      "learning_rate": 0.00015139664804469274,
+      "loss": 2.0525,
       "step": 174
     },
     {
-      "epoch": 7.0,
-      "learning_rate": 0.00013000000000000002,
-      "loss": 1.4828,
+      "epoch": 0.98,
+      "learning_rate": 0.0001511173184357542,
+      "loss": 1.9234,
       "step": 175
     },
     {
-      "epoch": 7.04,
-      "learning_rate": 0.0001296,
-      "loss": 1.6204,
+      "epoch": 0.98,
+      "learning_rate": 0.00015083798882681567,
+      "loss": 1.8614,
       "step": 176
     },
     {
-      "epoch": 7.08,
-      "learning_rate": 0.00012920000000000002,
-      "loss": 1.4955,
+      "epoch": 0.99,
+      "learning_rate": 0.0001505586592178771,
+      "loss": 1.9616,
       "step": 177
     },
     {
-      "epoch": 7.12,
-      "learning_rate": 0.00012880000000000001,
-      "loss": 1.6109,
+      "epoch": 0.99,
+      "learning_rate": 0.00015027932960893855,
+      "loss": 1.9509,
       "step": 178
     },
     {
-      "epoch": 7.16,
-      "learning_rate": 0.0001284,
-      "loss": 1.5318,
+      "epoch": 1.0,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.9592,
       "step": 179
     },
     {
-      "epoch": 7.2,
-      "learning_rate": 0.00012800000000000002,
-      "loss": 1.5702,
+      "epoch": 1.01,
+      "learning_rate": 0.00014972067039106145,
+      "loss": 1.8991,
       "step": 180
     },
     {
-      "epoch": 7.24,
-      "learning_rate": 0.0001276,
-      "loss": 1.4598,
+      "epoch": 1.01,
+      "learning_rate": 0.00014944134078212292,
+      "loss": 1.9127,
       "step": 181
     },
     {
-      "epoch": 7.28,
-      "learning_rate": 0.0001272,
-      "loss": 1.6145,
+      "epoch": 1.02,
+      "learning_rate": 0.00014916201117318436,
+      "loss": 1.8982,
       "step": 182
     },
     {
-      "epoch": 7.32,
-      "learning_rate": 0.00012680000000000002,
-      "loss": 1.3628,
+      "epoch": 1.02,
+      "learning_rate": 0.0001488826815642458,
+      "loss": 1.9534,
       "step": 183
     },
     {
-      "epoch": 7.36,
-      "learning_rate": 0.0001264,
-      "loss": 1.4578,
+      "epoch": 1.03,
+      "learning_rate": 0.0001486033519553073,
+      "loss": 1.7794,
       "step": 184
     },
     {
-      "epoch": 7.4,
-      "learning_rate": 0.000126,
-      "loss": 1.7094,
+      "epoch": 1.03,
+      "learning_rate": 0.00014832402234636873,
+      "loss": 1.7958,
       "step": 185
     },
     {
-      "epoch": 7.44,
-      "learning_rate": 0.00012560000000000002,
-      "loss": 1.4376,
+      "epoch": 1.04,
+      "learning_rate": 0.00014804469273743017,
+      "loss": 1.8282,
       "step": 186
     },
     {
-      "epoch": 7.48,
-      "learning_rate": 0.0001252,
-      "loss": 1.3393,
+      "epoch": 1.04,
+      "learning_rate": 0.00014776536312849164,
+      "loss": 2.0423,
       "step": 187
     },
     {
-      "epoch": 7.52,
-      "learning_rate": 0.0001248,
-      "loss": 1.4273,
+      "epoch": 1.05,
+      "learning_rate": 0.00014748603351955308,
+      "loss": 1.9282,
       "step": 188
     },
     {
-      "epoch": 7.56,
-      "learning_rate": 0.00012440000000000002,
-      "loss": 1.5506,
+      "epoch": 1.06,
+      "learning_rate": 0.00014720670391061454,
+      "loss": 1.9072,
       "step": 189
     },
     {
-      "epoch": 7.6,
-      "learning_rate": 0.000124,
-      "loss": 1.4774,
+      "epoch": 1.06,
+      "learning_rate": 0.00014692737430167598,
+      "loss": 1.8665,
       "step": 190
     },
     {
-      "epoch": 7.64,
-      "learning_rate": 0.0001236,
-      "loss": 1.4632,
+      "epoch": 1.07,
+      "learning_rate": 0.00014664804469273742,
+      "loss": 1.9021,
       "step": 191
     },
     {
-      "epoch": 7.68,
-      "learning_rate": 0.0001232,
-      "loss": 1.4568,
+      "epoch": 1.07,
+      "learning_rate": 0.0001463687150837989,
+      "loss": 1.7308,
       "step": 192
     },
     {
-      "epoch": 7.72,
-      "learning_rate": 0.0001228,
-      "loss": 1.6106,
+      "epoch": 1.08,
+      "learning_rate": 0.00014608938547486035,
+      "loss": 1.9165,
       "step": 193
     },
     {
-      "epoch": 7.76,
-      "learning_rate": 0.0001224,
-      "loss": 1.577,
+      "epoch": 1.08,
+      "learning_rate": 0.0001458100558659218,
+      "loss": 1.842,
       "step": 194
     },
     {
-      "epoch": 7.8,
-      "learning_rate": 0.000122,
-      "loss": 1.4805,
+      "epoch": 1.09,
+      "learning_rate": 0.00014553072625698326,
+      "loss": 1.9128,
       "step": 195
     },
     {
-      "epoch": 7.84,
-      "learning_rate": 0.0001216,
-      "loss": 1.4546,
+      "epoch": 1.09,
+      "learning_rate": 0.0001452513966480447,
+      "loss": 1.8005,
       "step": 196
     },
     {
-      "epoch": 7.88,
-      "learning_rate": 0.0001212,
-      "loss": 1.5164,
+      "epoch": 1.1,
+      "learning_rate": 0.00014497206703910614,
+      "loss": 1.8547,
       "step": 197
     },
     {
-      "epoch": 7.92,
-      "learning_rate": 0.0001208,
-      "loss": 1.5061,
+      "epoch": 1.11,
+      "learning_rate": 0.0001446927374301676,
+      "loss": 1.9042,
       "step": 198
     },
     {
-      "epoch": 7.96,
-      "learning_rate": 0.0001204,
-      "loss": 1.5312,
+      "epoch": 1.11,
+      "learning_rate": 0.00014441340782122905,
+      "loss": 1.8609,
       "step": 199
     },
     {
-      "epoch": 8.0,
-      "learning_rate": 0.00012,
-      "loss": 1.4463,
+      "epoch": 1.12,
+      "learning_rate": 0.0001441340782122905,
+      "loss": 1.9591,
       "step": 200
     },
     {
-      "epoch": 8.04,
-      "learning_rate": 0.00011960000000000001,
-      "loss": 1.4207,
+      "epoch": 1.12,
+      "learning_rate": 0.00014385474860335195,
+      "loss": 1.8722,
       "step": 201
     },
     {
-      "epoch": 8.08,
-      "learning_rate": 0.0001192,
-      "loss": 1.4688,
+      "epoch": 1.13,
+      "learning_rate": 0.00014357541899441342,
+      "loss": 1.8535,
       "step": 202
     },
     {
-      "epoch": 8.12,
-      "learning_rate": 0.0001188,
-      "loss": 1.4445,
+      "epoch": 1.13,
+      "learning_rate": 0.00014329608938547488,
+      "loss": 1.8676,
       "step": 203
     },
     {
-      "epoch": 8.16,
-      "learning_rate": 0.0001184,
-      "loss": 1.4158,
+      "epoch": 1.14,
+      "learning_rate": 0.00014301675977653632,
+      "loss": 1.8976,
       "step": 204
     },
     {
-      "epoch": 8.2,
-      "learning_rate": 0.000118,
-      "loss": 1.3483,
+      "epoch": 1.15,
+      "learning_rate": 0.00014273743016759776,
+      "loss": 1.7723,
       "step": 205
     },
     {
-      "epoch": 8.24,
-      "learning_rate": 0.0001176,
-      "loss": 1.4117,
+      "epoch": 1.15,
+      "learning_rate": 0.00014245810055865923,
+      "loss": 1.8165,
       "step": 206
     },
     {
-      "epoch": 8.28,
-      "learning_rate": 0.0001172,
-      "loss": 1.4267,
+      "epoch": 1.16,
+      "learning_rate": 0.00014217877094972067,
+      "loss": 1.7811,
       "step": 207
     },
     {
-      "epoch": 8.32,
-      "learning_rate": 0.00011679999999999999,
-      "loss": 1.5547,
+      "epoch": 1.16,
+      "learning_rate": 0.00014189944134078214,
+      "loss": 1.908,
       "step": 208
     },
     {
-      "epoch": 8.36,
-      "learning_rate": 0.0001164,
-      "loss": 1.4883,
+      "epoch": 1.17,
+      "learning_rate": 0.00014162011173184357,
+      "loss": 1.7663,
       "step": 209
     },
     {
-      "epoch": 8.4,
-      "learning_rate": 0.000116,
-      "loss": 1.414,
+      "epoch": 1.17,
+      "learning_rate": 0.00014134078212290501,
+      "loss": 1.6779,
       "step": 210
     },
     {
-      "epoch": 8.44,
-      "learning_rate": 0.00011559999999999999,
-      "loss": 1.3254,
+      "epoch": 1.18,
+      "learning_rate": 0.0001410614525139665,
+      "loss": 1.9039,
       "step": 211
     },
     {
-      "epoch": 8.48,
-      "learning_rate": 0.0001152,
-      "loss": 1.22,
+      "epoch": 1.18,
+      "learning_rate": 0.00014078212290502795,
+      "loss": 1.8033,
       "step": 212
     },
     {
-      "epoch": 8.52,
-      "learning_rate": 0.0001148,
-      "loss": 1.3224,
+      "epoch": 1.19,
+      "learning_rate": 0.00014050279329608939,
+      "loss": 1.8251,
       "step": 213
     },
     {
-      "epoch": 8.56,
-      "learning_rate": 0.0001144,
-      "loss": 1.6158,
+      "epoch": 1.2,
+      "learning_rate": 0.00014022346368715085,
+      "loss": 1.8505,
       "step": 214
     },
     {
-      "epoch": 8.6,
-      "learning_rate": 0.00011399999999999999,
-      "loss": 1.2817,
+      "epoch": 1.2,
+      "learning_rate": 0.0001399441340782123,
+      "loss": 1.8147,
       "step": 215
     },
     {
-      "epoch": 8.64,
-      "learning_rate": 0.0001136,
-      "loss": 1.4077,
+      "epoch": 1.21,
+      "learning_rate": 0.00013966480446927376,
+      "loss": 1.8419,
       "step": 216
     },
     {
-      "epoch": 8.68,
-      "learning_rate": 0.0001132,
-      "loss": 1.5311,
+      "epoch": 1.21,
+      "learning_rate": 0.0001393854748603352,
+      "loss": 1.8401,
       "step": 217
     },
     {
-      "epoch": 8.72,
-      "learning_rate": 0.00011279999999999999,
-      "loss": 1.5289,
+      "epoch": 1.22,
+      "learning_rate": 0.00013910614525139664,
+      "loss": 1.8912,
       "step": 218
     },
     {
-      "epoch": 8.76,
-      "learning_rate": 0.00011240000000000002,
-      "loss": 1.4576,
+      "epoch": 1.22,
+      "learning_rate": 0.0001388268156424581,
+      "loss": 1.7548,
       "step": 219
     },
     {
-      "epoch": 8.8,
-      "learning_rate": 0.00011200000000000001,
-      "loss": 1.2063,
+      "epoch": 1.23,
+      "learning_rate": 0.00013854748603351957,
+      "loss": 1.8741,
       "step": 220
     },
     {
-      "epoch": 8.84,
-      "learning_rate": 0.00011160000000000002,
-      "loss": 1.3543,
+      "epoch": 1.23,
+      "learning_rate": 0.000138268156424581,
+      "loss": 1.9549,
       "step": 221
     },
     {
-      "epoch": 8.88,
-      "learning_rate": 0.00011120000000000002,
-      "loss": 1.4352,
+      "epoch": 1.24,
+      "learning_rate": 0.00013798882681564248,
+      "loss": 1.9093,
       "step": 222
     },
     {
-      "epoch": 8.92,
-      "learning_rate": 0.00011080000000000001,
-      "loss": 1.3058,
+      "epoch": 1.25,
+      "learning_rate": 0.00013770949720670392,
+      "loss": 1.7896,
       "step": 223
     },
     {
-      "epoch": 8.96,
-      "learning_rate": 0.00011040000000000001,
-      "loss": 1.3475,
+      "epoch": 1.25,
+      "learning_rate": 0.00013743016759776538,
+      "loss": 1.8491,
       "step": 224
     },
     {
-      "epoch": 9.0,
-      "learning_rate": 0.00011000000000000002,
-      "loss": 1.1293,
+      "epoch": 1.26,
+      "learning_rate": 0.00013715083798882682,
+      "loss": 1.7851,
       "step": 225
     },
     {
-      "epoch": 9.04,
-      "learning_rate": 0.00010960000000000001,
-      "loss": 1.1671,
+      "epoch": 1.26,
+      "learning_rate": 0.00013687150837988826,
+      "loss": 1.6992,
       "step": 226
     },
     {
-      "epoch": 9.08,
-      "learning_rate": 0.00010920000000000001,
-      "loss": 1.4726,
+      "epoch": 1.27,
+      "learning_rate": 0.00013659217877094973,
+      "loss": 1.9765,
       "step": 227
     },
     {
-      "epoch": 9.12,
-      "learning_rate": 0.00010880000000000002,
-      "loss": 1.3986,
+      "epoch": 1.27,
+      "learning_rate": 0.00013631284916201117,
+      "loss": 1.8179,
       "step": 228
     },
     {
-      "epoch": 9.16,
-      "learning_rate": 0.00010840000000000002,
-      "loss": 1.2731,
+      "epoch": 1.28,
+      "learning_rate": 0.00013603351955307263,
+      "loss": 1.8548,
       "step": 229
     },
     {
-      "epoch": 9.2,
-      "learning_rate": 0.00010800000000000001,
-      "loss": 1.2212,
+      "epoch": 1.28,
+      "learning_rate": 0.0001357541899441341,
+      "loss": 1.8843,
       "step": 230
     },
     {
-      "epoch": 9.24,
-      "learning_rate": 0.00010760000000000001,
-      "loss": 1.3067,
+      "epoch": 1.29,
+      "learning_rate": 0.00013547486033519554,
+      "loss": 1.9105,
       "step": 231
     },
     {
-      "epoch": 9.28,
-      "learning_rate": 0.00010720000000000002,
-      "loss": 1.278,
+      "epoch": 1.3,
+      "learning_rate": 0.00013519553072625698,
+      "loss": 1.8748,
       "step": 232
     },
     {
-      "epoch": 9.32,
-      "learning_rate": 0.00010680000000000001,
-      "loss": 1.4141,
+      "epoch": 1.3,
+      "learning_rate": 0.00013491620111731844,
+      "loss": 1.7976,
       "step": 233
     },
     {
-      "epoch": 9.36,
-      "learning_rate": 0.00010640000000000001,
-      "loss": 1.2885,
+      "epoch": 1.31,
+      "learning_rate": 0.00013463687150837988,
+      "loss": 1.7369,
       "step": 234
     },
     {
-      "epoch": 9.4,
-      "learning_rate": 0.00010600000000000002,
-      "loss": 1.466,
+      "epoch": 1.31,
+      "learning_rate": 0.00013435754189944135,
+      "loss": 1.7808,
       "step": 235
     },
     {
-      "epoch": 9.44,
-      "learning_rate": 0.0001056,
-      "loss": 1.2979,
+      "epoch": 1.32,
+      "learning_rate": 0.0001340782122905028,
+      "loss": 1.8385,
       "step": 236
     },
     {
-      "epoch": 9.48,
-      "learning_rate": 0.00010520000000000001,
-      "loss": 1.1622,
+      "epoch": 1.32,
+      "learning_rate": 0.00013379888268156423,
+      "loss": 1.8295,
       "step": 237
     },
     {
-      "epoch": 9.52,
-      "learning_rate": 0.00010480000000000001,
-      "loss": 1.2504,
+      "epoch": 1.33,
+      "learning_rate": 0.00013351955307262572,
+      "loss": 1.757,
       "step": 238
     },
     {
-      "epoch": 9.56,
-      "learning_rate": 0.0001044,
-      "loss": 1.228,
+      "epoch": 1.34,
+      "learning_rate": 0.00013324022346368716,
+      "loss": 1.7904,
       "step": 239
     },
     {
-      "epoch": 9.6,
-      "learning_rate": 0.00010400000000000001,
-      "loss": 1.3607,
+      "epoch": 1.34,
+      "learning_rate": 0.0001329608938547486,
+      "loss": 1.7632,
       "step": 240
     },
     {
-      "epoch": 9.64,
-      "learning_rate": 0.00010360000000000001,
-      "loss": 1.1921,
+      "epoch": 1.35,
+      "learning_rate": 0.00013268156424581007,
+      "loss": 1.7867,
       "step": 241
     },
     {
-      "epoch": 9.68,
-      "learning_rate": 0.0001032,
-      "loss": 1.2114,
+      "epoch": 1.35,
+      "learning_rate": 0.0001324022346368715,
+      "loss": 1.8259,
       "step": 242
     },
     {
-      "epoch": 9.72,
-      "learning_rate": 0.0001028,
-      "loss": 1.2385,
+      "epoch": 1.36,
+      "learning_rate": 0.00013212290502793297,
+      "loss": 1.6655,
       "step": 243
     },
     {
-      "epoch": 9.76,
-      "learning_rate": 0.00010240000000000001,
-      "loss": 1.3227,
+      "epoch": 1.36,
+      "learning_rate": 0.0001318435754189944,
+      "loss": 1.6848,
       "step": 244
     },
     {
-      "epoch": 9.8,
-      "learning_rate": 0.00010200000000000001,
-      "loss": 1.3935,
+      "epoch": 1.37,
+      "learning_rate": 0.00013156424581005585,
+      "loss": 1.7931,
       "step": 245
     },
     {
-      "epoch": 9.84,
-      "learning_rate": 0.0001016,
-      "loss": 1.2209,
+      "epoch": 1.37,
+      "learning_rate": 0.00013128491620111732,
+      "loss": 1.7868,
       "step": 246
     },
     {
-      "epoch": 9.88,
-      "learning_rate": 0.00010120000000000001,
-      "loss": 1.1541,
+      "epoch": 1.38,
+      "learning_rate": 0.00013100558659217879,
+      "loss": 1.7732,
       "step": 247
     },
     {
-      "epoch": 9.92,
-      "learning_rate": 0.00010080000000000001,
-      "loss": 1.4049,
+      "epoch": 1.39,
+      "learning_rate": 0.00013072625698324022,
+      "loss": 1.7851,
       "step": 248
     },
     {
-      "epoch": 9.96,
-      "learning_rate": 0.0001004,
-      "loss": 1.13,
+      "epoch": 1.39,
+      "learning_rate": 0.0001304469273743017,
+      "loss": 1.7406,
       "step": 249
     },
     {
-      "epoch": 10.0,
-      "learning_rate": 0.0001,
-      "loss": 1.3783,
+      "epoch": 1.4,
+      "learning_rate": 0.00013016759776536313,
+      "loss": 1.5853,
       "step": 250
     },
     {
-      "epoch": 10.04,
-      "learning_rate": 9.960000000000001e-05,
-      "loss": 1.3207,
+      "epoch": 1.4,
+      "learning_rate": 0.0001298882681564246,
+      "loss": 1.8271,
       "step": 251
     },
     {
-      "epoch": 10.08,
-      "learning_rate": 9.92e-05,
-      "loss": 1.2697,
+      "epoch": 1.41,
+      "learning_rate": 0.00012960893854748604,
+      "loss": 1.6054,
       "step": 252
     },
     {
-      "epoch": 10.12,
-      "learning_rate": 9.88e-05,
-      "loss": 1.091,
+      "epoch": 1.41,
+      "learning_rate": 0.00012932960893854748,
+      "loss": 1.6884,
       "step": 253
     },
     {
-      "epoch": 10.16,
-      "learning_rate": 9.84e-05,
-      "loss": 1.0463,
+      "epoch": 1.42,
+      "learning_rate": 0.00012905027932960894,
+      "loss": 1.7333,
       "step": 254
     },
     {
-      "epoch": 10.2,
-      "learning_rate": 9.8e-05,
-      "loss": 1.3686,
+      "epoch": 1.42,
+      "learning_rate": 0.00012877094972067038,
+      "loss": 1.803,
       "step": 255
     },
     {
-      "epoch": 10.24,
-      "learning_rate": 9.76e-05,
-      "loss": 1.3109,
+      "epoch": 1.43,
+      "learning_rate": 0.00012849162011173185,
+      "loss": 1.63,
       "step": 256
     },
     {
-      "epoch": 10.28,
-      "learning_rate": 9.72e-05,
-      "loss": 1.2338,
+      "epoch": 1.44,
+      "learning_rate": 0.00012821229050279331,
+      "loss": 1.8023,
       "step": 257
     },
     {
-      "epoch": 10.32,
-      "learning_rate": 9.680000000000001e-05,
-      "loss": 1.12,
+      "epoch": 1.44,
+      "learning_rate": 0.00012793296089385475,
+      "loss": 1.762,
       "step": 258
     },
     {
-      "epoch": 10.36,
-      "learning_rate": 9.64e-05,
-      "loss": 1.1864,
+      "epoch": 1.45,
+      "learning_rate": 0.00012765363128491622,
+      "loss": 1.7565,
       "step": 259
     },
     {
-      "epoch": 10.4,
-      "learning_rate": 9.6e-05,
-      "loss": 1.1062,
+      "epoch": 1.45,
+      "learning_rate": 0.00012737430167597766,
+      "loss": 1.5937,
       "step": 260
     },
     {
-      "epoch": 10.44,
-      "learning_rate": 9.56e-05,
-      "loss": 1.2924,
+      "epoch": 1.46,
+      "learning_rate": 0.0001270949720670391,
+      "loss": 1.7208,
       "step": 261
     },
     {
-      "epoch": 10.48,
-      "learning_rate": 9.52e-05,
-      "loss": 1.1931,
+      "epoch": 1.46,
+      "learning_rate": 0.00012681564245810057,
+      "loss": 1.8097,
       "step": 262
     },
     {
-      "epoch": 10.52,
-      "learning_rate": 9.48e-05,
-      "loss": 1.2366,
+      "epoch": 1.47,
+      "learning_rate": 0.000126536312849162,
+      "loss": 1.7042,
       "step": 263
     },
     {
-      "epoch": 10.56,
-      "learning_rate": 9.44e-05,
-      "loss": 1.1589,
+      "epoch": 1.47,
+      "learning_rate": 0.00012625698324022347,
+      "loss": 1.7892,
       "step": 264
     },
     {
-      "epoch": 10.6,
-      "learning_rate": 9.4e-05,
-      "loss": 1.1197,
+      "epoch": 1.48,
+      "learning_rate": 0.00012597765363128494,
+      "loss": 1.752,
       "step": 265
     },
     {
-      "epoch": 10.64,
-      "learning_rate": 9.360000000000001e-05,
-      "loss": 1.3072,
+      "epoch": 1.49,
+      "learning_rate": 0.00012569832402234638,
+      "loss": 1.7333,
       "step": 266
     },
     {
-      "epoch": 10.68,
-      "learning_rate": 9.320000000000002e-05,
-      "loss": 1.1173,
+      "epoch": 1.49,
+      "learning_rate": 0.00012541899441340784,
+      "loss": 1.7492,
       "step": 267
     },
     {
-      "epoch": 10.72,
-      "learning_rate": 9.28e-05,
-      "loss": 1.0378,
+      "epoch": 1.5,
+      "learning_rate": 0.00012513966480446928,
+      "loss": 1.818,
       "step": 268
     },
     {
-      "epoch": 10.76,
-      "learning_rate": 9.240000000000001e-05,
-      "loss": 1.1746,
+      "epoch": 1.5,
+      "learning_rate": 0.00012486033519553072,
+      "loss": 1.7146,
       "step": 269
     },
     {
-      "epoch": 10.8,
-      "learning_rate": 9.200000000000001e-05,
-      "loss": 1.1144,
+      "epoch": 1.51,
+      "learning_rate": 0.0001245810055865922,
+      "loss": 1.7958,
       "step": 270
     },
     {
-      "epoch": 10.84,
-      "learning_rate": 9.16e-05,
-      "loss": 1.1862,
+      "epoch": 1.51,
+      "learning_rate": 0.00012430167597765363,
+      "loss": 1.7212,
       "step": 271
     },
     {
-      "epoch": 10.88,
-      "learning_rate": 9.120000000000001e-05,
-      "loss": 1.0816,
+      "epoch": 1.52,
+      "learning_rate": 0.0001240223463687151,
+      "loss": 1.8835,
       "step": 272
     },
     {
-      "epoch": 10.92,
-      "learning_rate": 9.080000000000001e-05,
-      "loss": 1.2288,
+      "epoch": 1.53,
+      "learning_rate": 0.00012374301675977656,
+      "loss": 1.7486,
       "step": 273
     },
     {
-      "epoch": 10.96,
-      "learning_rate": 9.04e-05,
-      "loss": 1.3031,
+      "epoch": 1.53,
+      "learning_rate": 0.000123463687150838,
+      "loss": 1.8103,
       "step": 274
     },
     {
-      "epoch": 11.0,
-      "learning_rate": 9e-05,
-      "loss": 1.1646,
+      "epoch": 1.54,
+      "learning_rate": 0.00012318435754189944,
+      "loss": 1.7557,
       "step": 275
     },
     {
-      "epoch": 11.04,
-      "learning_rate": 8.960000000000001e-05,
-      "loss": 1.2088,
+      "epoch": 1.54,
+      "learning_rate": 0.0001229050279329609,
+      "loss": 1.6198,
       "step": 276
     },
     {
-      "epoch": 11.08,
-      "learning_rate": 8.92e-05,
-      "loss": 1.1465,
+      "epoch": 1.55,
+      "learning_rate": 0.00012262569832402235,
+      "loss": 1.6971,
       "step": 277
     },
     {
-      "epoch": 11.12,
-      "learning_rate": 8.88e-05,
-      "loss": 1.0313,
+      "epoch": 1.55,
+      "learning_rate": 0.0001223463687150838,
+      "loss": 1.668,
       "step": 278
     },
     {
-      "epoch": 11.16,
-      "learning_rate": 8.840000000000001e-05,
-      "loss": 0.9662,
+      "epoch": 1.56,
+      "learning_rate": 0.00012206703910614525,
+      "loss": 1.8795,
       "step": 279
     },
     {
-      "epoch": 11.2,
-      "learning_rate": 8.800000000000001e-05,
-      "loss": 1.051,
+      "epoch": 1.56,
+      "learning_rate": 0.0001217877094972067,
+      "loss": 1.6412,
       "step": 280
     },
     {
-      "epoch": 11.24,
-      "learning_rate": 8.76e-05,
-      "loss": 1.1708,
+      "epoch": 1.57,
+      "learning_rate": 0.00012150837988826816,
+      "loss": 1.7497,
       "step": 281
     },
     {
-      "epoch": 11.28,
-      "learning_rate": 8.72e-05,
-      "loss": 1.0236,
+      "epoch": 1.58,
+      "learning_rate": 0.00012122905027932962,
+      "loss": 1.5577,
       "step": 282
     },
     {
-      "epoch": 11.32,
-      "learning_rate": 8.680000000000001e-05,
-      "loss": 1.1359,
+      "epoch": 1.58,
+      "learning_rate": 0.00012094972067039108,
+      "loss": 1.8049,
       "step": 283
     },
     {
-      "epoch": 11.36,
-      "learning_rate": 8.64e-05,
-      "loss": 1.1398,
+      "epoch": 1.59,
+      "learning_rate": 0.00012067039106145253,
+      "loss": 1.6834,
       "step": 284
     },
     {
-      "epoch": 11.4,
-      "learning_rate": 8.6e-05,
-      "loss": 1.0213,
+      "epoch": 1.59,
+      "learning_rate": 0.00012039106145251397,
+      "loss": 1.7978,
       "step": 285
     },
     {
-      "epoch": 11.44,
-      "learning_rate": 8.560000000000001e-05,
-      "loss": 1.1788,
+      "epoch": 1.6,
+      "learning_rate": 0.00012011173184357542,
+      "loss": 1.6558,
       "step": 286
     },
     {
-      "epoch": 11.48,
-      "learning_rate": 8.52e-05,
-      "loss": 1.0387,
+      "epoch": 1.6,
+      "learning_rate": 0.00011983240223463687,
+      "loss": 1.7561,
       "step": 287
     },
     {
-      "epoch": 11.52,
-      "learning_rate": 8.48e-05,
-      "loss": 0.9476,
+      "epoch": 1.61,
+      "learning_rate": 0.00011955307262569833,
+      "loss": 1.6807,
       "step": 288
     },
     {
-      "epoch": 11.56,
-      "learning_rate": 8.44e-05,
-      "loss": 1.1954,
+      "epoch": 1.61,
+      "learning_rate": 0.00011927374301675978,
+      "loss": 1.6937,
       "step": 289
     },
     {
-      "epoch": 11.6,
-      "learning_rate": 8.4e-05,
-      "loss": 1.0309,
+      "epoch": 1.62,
+      "learning_rate": 0.00011899441340782122,
+      "loss": 1.6591,
       "step": 290
     },
     {
-      "epoch": 11.64,
-      "learning_rate": 8.36e-05,
-      "loss": 1.1321,
+      "epoch": 1.63,
+      "learning_rate": 0.0001187150837988827,
+      "loss": 1.6771,
       "step": 291
     },
     {
-      "epoch": 11.68,
-      "learning_rate": 8.32e-05,
-      "loss": 1.0914,
+      "epoch": 1.63,
+      "learning_rate": 0.00011843575418994415,
+      "loss": 1.7743,
       "step": 292
     },
     {
-      "epoch": 11.72,
-      "learning_rate": 8.28e-05,
-      "loss": 1.222,
+      "epoch": 1.64,
+      "learning_rate": 0.00011815642458100559,
+      "loss": 1.5857,
       "step": 293
     },
     {
-      "epoch": 11.76,
-      "learning_rate": 8.24e-05,
-      "loss": 1.0127,
+      "epoch": 1.64,
+      "learning_rate": 0.00011787709497206705,
+      "loss": 1.6999,
       "step": 294
     },
     {
-      "epoch": 11.8,
-      "learning_rate": 8.2e-05,
-      "loss": 1.1977,
+      "epoch": 1.65,
+      "learning_rate": 0.0001175977653631285,
+      "loss": 1.5661,
       "step": 295
     },
     {
-      "epoch": 11.84,
-      "learning_rate": 8.16e-05,
-      "loss": 1.122,
+      "epoch": 1.65,
+      "learning_rate": 0.00011731843575418995,
+      "loss": 1.7235,
       "step": 296
     },
     {
-      "epoch": 11.88,
-      "learning_rate": 8.120000000000001e-05,
-      "loss": 1.1543,
+      "epoch": 1.66,
+      "learning_rate": 0.0001170391061452514,
+      "loss": 1.607,
       "step": 297
     },
     {
-      "epoch": 11.92,
-      "learning_rate": 8.080000000000001e-05,
-      "loss": 1.1767,
+      "epoch": 1.66,
+      "learning_rate": 0.00011675977653631284,
+      "loss": 1.68,
       "step": 298
     },
     {
-      "epoch": 11.96,
-      "learning_rate": 8.04e-05,
-      "loss": 1.1341,
+      "epoch": 1.67,
+      "learning_rate": 0.0001164804469273743,
+      "loss": 1.6938,
       "step": 299
     },
     {
-      "epoch": 12.0,
-      "learning_rate": 8e-05,
-      "loss": 1.0107,
+      "epoch": 1.68,
+      "learning_rate": 0.00011620111731843578,
+      "loss": 1.6315,
       "step": 300
     }
   ],
   "logging_steps": 1,
-  "max_steps": 500,
-  "num_train_epochs": 20,
+  "max_steps": 716,
+  "num_train_epochs": 4,
   "save_steps": 100,
-  "total_flos": 1.0209241970264064e+17,
+  "total_flos": 1.5369996759656448e+17,
   "trial_name": null,
   "trial_params": null
 }
diff --git a/checkpoint-300/training_args.bin b/checkpoint-300/training_args.bin
index 4de6572a838c337c9990635a9406ebf46c0ec336..c8672c716e925d0028b4938db147703f58656ff7 100644
--- a/checkpoint-300/training_args.bin
+++ b/checkpoint-300/training_args.bin
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ef74b31950ae6c8955316bed48c343fb06cda0cb6a8a54ca46ca3cb681c8736
+oid sha256:188ae1c421cc0c6435d1f71d8d3423ac4abc7dba0e6fc2efcbc4dbe77c741317
 size 4027
diff --git a/checkpoint-400/README.md b/checkpoint-400/README.md
index 08371015f02382e6fcba318f4aaea54ae52cd3c4..2f257a448caef1c59022426ad3ec9ba80acb3821 100644
--- a/checkpoint-400/README.md
+++ b/checkpoint-400/README.md
@@ -4,6 +4,30 @@ library_name: peft
 ## Training procedure
 
 
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: True
+- load_in_4bit: False
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: True
+- load_in_4bit: False
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+
 The following `bitsandbytes` quantization config was used during training:
 - quant_method: bitsandbytes
 - load_in_8bit: True
@@ -29,6 +53,8 @@ The following `bitsandbytes` quantization config was used during training:
 - bnb_4bit_compute_dtype: float32
 ### Framework versions
 
+- PEFT 0.6.0.dev0
+- PEFT 0.6.0.dev0
 - PEFT 0.6.0.dev0
 
 - PEFT 0.6.0.dev0
diff --git a/checkpoint-400/adapter_model.bin b/checkpoint-400/adapter_model.bin
index c3e6363275595b219717dfc19f12692e62350c8f..1b6fe766ab6e3bde1e95c1168e8b27f515e22af0 100644
--- a/checkpoint-400/adapter_model.bin
+++ b/checkpoint-400/adapter_model.bin
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2314e06a7452fc12576ddd903f95a2753dfd474755a766d263b3d938b19d66f
+oid sha256:e7b701342ea311c1e25f0f6953505f048df3f56027dc5c764b95df4491bfde1c
 size 39409357
diff --git a/checkpoint-400/optimizer.pt b/checkpoint-400/optimizer.pt
index 17d28ff148a94bd700bad3627e4595256db5ea75..0119015704369e84c41214b2eda49f7eed10bbe8 100644
--- a/checkpoint-400/optimizer.pt
+++ b/checkpoint-400/optimizer.pt
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:744a5e62f698effd66997373bf91c530543a99d8828c460626ac0cd2032b7420
+oid sha256:da79792a601e6737b980ff24e453353405dce9a807a0964433ac96d5a97b84aa
 size 78844421
diff --git a/checkpoint-400/rng_state.pth b/checkpoint-400/rng_state.pth
index ce32862861da12da23bbb01ee9f59c5232cb111d..e0df6592e27bef84a4beb9293e7b49666a4d652e 100644
--- a/checkpoint-400/rng_state.pth
+++ b/checkpoint-400/rng_state.pth
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51f3c17c1e7ce128318be2166e96b6dda4d1ff79c8b44e6fb06488bf0bbfcf8d
+oid sha256:7508d4b8dd267de5cc58e972da25236687927651336a28f292c92f7f23951475
 size 14575
diff --git a/checkpoint-400/scheduler.pt b/checkpoint-400/scheduler.pt
index 74eed63b650e5eae737878728f47e3c4aaf6a0c3..b3ccbb3bd3df5add5130e76711d025db7007acb0 100644
--- a/checkpoint-400/scheduler.pt
+++ b/checkpoint-400/scheduler.pt
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9aafe6849dc1b38ea86a67ee0dd398e835f1054275ee4627209b6ffeca7902f
+oid sha256:04fdaf305b17644f9d215d28be45b77e6d0f8e4b5adc1c7045c50a61bd8f3c5b
 size 627
diff --git a/checkpoint-400/tokenizer.json b/checkpoint-400/tokenizer.json
index dbf002cafbd4818dcff2abc9156c088d681b4533..673c31abdeadf6576c3c754df86459e1ad64e207 100644
--- a/checkpoint-400/tokenizer.json
+++ b/checkpoint-400/tokenizer.json
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17a208233d2ee8d8c83b23bc214df737c44806a1919f444e89b31e586cd956ba
-size 14500471
+oid sha256:85b00d7db4df5df2e3f01cacc3feda246002a672f3356eec7f4b04a22eb0dfbe
+size 14500570
diff --git a/checkpoint-400/trainer_state.json b/checkpoint-400/trainer_state.json
index b6483d39779ceb63a8e9a7a661a5286d66760130..f60e92395bfa70b2808af040d92ac135cc2b0e93 100644
--- a/checkpoint-400/trainer_state.json
+++ b/checkpoint-400/trainer_state.json
@@ -1,7 +1,7 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 16.0,
+  "epoch": 2.2346368715083798,
   "eval_steps": 500,
   "global_step": 400,
   "is_hyper_param_search": false,
@@ -9,2411 +9,2411 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.04,
-      "learning_rate": 0.0001996,
-      "loss": 2.4683,
+      "epoch": 0.01,
+      "learning_rate": 0.00019972067039106145,
+      "loss": 2.6443,
       "step": 1
     },
     {
-      "epoch": 0.08,
-      "learning_rate": 0.00019920000000000002,
-      "loss": 2.2023,
+      "epoch": 0.01,
+      "learning_rate": 0.00019944134078212292,
+      "loss": 2.4104,
       "step": 2
     },
     {
-      "epoch": 0.12,
-      "learning_rate": 0.0001988,
-      "loss": 2.3039,
+      "epoch": 0.02,
+      "learning_rate": 0.00019916201117318435,
+      "loss": 2.4975,
       "step": 3
     },
     {
-      "epoch": 0.16,
-      "learning_rate": 0.0001984,
-      "loss": 2.1855,
+      "epoch": 0.02,
+      "learning_rate": 0.00019888268156424582,
+      "loss": 2.3513,
       "step": 4
     },
     {
-      "epoch": 0.2,
-      "learning_rate": 0.00019800000000000002,
-      "loss": 2.328,
+      "epoch": 0.03,
+      "learning_rate": 0.0001986033519553073,
+      "loss": 2.4274,
       "step": 5
     },
     {
-      "epoch": 0.24,
-      "learning_rate": 0.0001976,
-      "loss": 2.3407,
+      "epoch": 0.03,
+      "learning_rate": 0.00019832402234636873,
+      "loss": 2.3628,
       "step": 6
     },
     {
-      "epoch": 0.28,
-      "learning_rate": 0.0001972,
-      "loss": 2.3432,
+      "epoch": 0.04,
+      "learning_rate": 0.0001980446927374302,
+      "loss": 2.3567,
       "step": 7
     },
     {
-      "epoch": 0.32,
-      "learning_rate": 0.0001968,
-      "loss": 2.2333,
+      "epoch": 0.04,
+      "learning_rate": 0.00019776536312849163,
+      "loss": 2.4121,
       "step": 8
     },
     {
-      "epoch": 0.36,
-      "learning_rate": 0.0001964,
-      "loss": 2.1761,
+      "epoch": 0.05,
+      "learning_rate": 0.00019748603351955307,
+      "loss": 2.4033,
       "step": 9
     },
     {
-      "epoch": 0.4,
-      "learning_rate": 0.000196,
-      "loss": 2.1473,
+      "epoch": 0.06,
+      "learning_rate": 0.00019720670391061454,
+      "loss": 2.2805,
       "step": 10
     },
     {
-      "epoch": 0.44,
-      "learning_rate": 0.0001956,
-      "loss": 2.2076,
+      "epoch": 0.06,
+      "learning_rate": 0.00019692737430167598,
+      "loss": 2.2639,
       "step": 11
     },
     {
-      "epoch": 0.48,
-      "learning_rate": 0.0001952,
-      "loss": 2.1925,
+      "epoch": 0.07,
+      "learning_rate": 0.00019664804469273744,
+      "loss": 2.2724,
       "step": 12
     },
     {
-      "epoch": 0.52,
-      "learning_rate": 0.0001948,
-      "loss": 2.1694,
+      "epoch": 0.07,
+      "learning_rate": 0.00019636871508379888,
+      "loss": 2.332,
       "step": 13
     },
     {
-      "epoch": 0.56,
-      "learning_rate": 0.0001944,
-      "loss": 2.1056,
+      "epoch": 0.08,
+      "learning_rate": 0.00019608938547486035,
+      "loss": 2.2261,
       "step": 14
     },
     {
-      "epoch": 0.6,
-      "learning_rate": 0.000194,
-      "loss": 2.2426,
+      "epoch": 0.08,
+      "learning_rate": 0.00019581005586592182,
+      "loss": 2.2208,
       "step": 15
     },
     {
-      "epoch": 0.64,
-      "learning_rate": 0.00019360000000000002,
-      "loss": 2.2635,
+      "epoch": 0.09,
+      "learning_rate": 0.00019553072625698326,
+      "loss": 2.3351,
       "step": 16
     },
     {
-      "epoch": 0.68,
-      "learning_rate": 0.0001932,
-      "loss": 2.251,
+      "epoch": 0.09,
+      "learning_rate": 0.0001952513966480447,
+      "loss": 2.2475,
       "step": 17
     },
     {
-      "epoch": 0.72,
-      "learning_rate": 0.0001928,
-      "loss": 2.224,
+      "epoch": 0.1,
+      "learning_rate": 0.00019497206703910616,
+      "loss": 2.3283,
       "step": 18
     },
     {
-      "epoch": 0.76,
-      "learning_rate": 0.00019240000000000001,
-      "loss": 2.1848,
+      "epoch": 0.11,
+      "learning_rate": 0.0001946927374301676,
+      "loss": 2.1346,
       "step": 19
     },
     {
-      "epoch": 0.8,
-      "learning_rate": 0.000192,
-      "loss": 2.1341,
+      "epoch": 0.11,
+      "learning_rate": 0.00019441340782122907,
+      "loss": 2.131,
       "step": 20
     },
     {
-      "epoch": 0.84,
-      "learning_rate": 0.0001916,
-      "loss": 2.126,
+      "epoch": 0.12,
+      "learning_rate": 0.0001941340782122905,
+      "loss": 2.1718,
       "step": 21
     },
     {
-      "epoch": 0.88,
-      "learning_rate": 0.0001912,
-      "loss": 2.0959,
+      "epoch": 0.12,
+      "learning_rate": 0.00019385474860335195,
+      "loss": 2.2446,
       "step": 22
     },
     {
-      "epoch": 0.92,
-      "learning_rate": 0.0001908,
-      "loss": 2.2446,
+      "epoch": 0.13,
+      "learning_rate": 0.0001935754189944134,
+      "loss": 2.306,
       "step": 23
     },
     {
-      "epoch": 0.96,
-      "learning_rate": 0.0001904,
-      "loss": 1.9448,
+      "epoch": 0.13,
+      "learning_rate": 0.00019329608938547488,
+      "loss": 2.1908,
       "step": 24
     },
     {
-      "epoch": 1.0,
-      "learning_rate": 0.00019,
-      "loss": 2.0939,
+      "epoch": 0.14,
+      "learning_rate": 0.00019301675977653632,
+      "loss": 2.2844,
       "step": 25
     },
     {
-      "epoch": 1.04,
-      "learning_rate": 0.0001896,
-      "loss": 2.1247,
+      "epoch": 0.15,
+      "learning_rate": 0.00019273743016759779,
+      "loss": 2.2235,
       "step": 26
     },
     {
-      "epoch": 1.08,
-      "learning_rate": 0.0001892,
-      "loss": 1.9417,
+      "epoch": 0.15,
+      "learning_rate": 0.00019245810055865922,
+      "loss": 2.1842,
       "step": 27
     },
     {
-      "epoch": 1.12,
-      "learning_rate": 0.0001888,
-      "loss": 2.105,
+      "epoch": 0.16,
+      "learning_rate": 0.00019217877094972066,
+      "loss": 2.2675,
       "step": 28
     },
     {
-      "epoch": 1.16,
-      "learning_rate": 0.0001884,
-      "loss": 2.1595,
+      "epoch": 0.16,
+      "learning_rate": 0.00019189944134078213,
+      "loss": 2.2532,
       "step": 29
     },
     {
-      "epoch": 1.2,
-      "learning_rate": 0.000188,
-      "loss": 2.2009,
+      "epoch": 0.17,
+      "learning_rate": 0.00019162011173184357,
+      "loss": 2.1788,
       "step": 30
     },
     {
-      "epoch": 1.24,
-      "learning_rate": 0.0001876,
-      "loss": 2.0784,
+      "epoch": 0.17,
+      "learning_rate": 0.00019134078212290504,
+      "loss": 2.2494,
       "step": 31
     },
     {
-      "epoch": 1.28,
-      "learning_rate": 0.00018720000000000002,
-      "loss": 2.2173,
+      "epoch": 0.18,
+      "learning_rate": 0.0001910614525139665,
+      "loss": 2.1995,
       "step": 32
     },
     {
-      "epoch": 1.32,
-      "learning_rate": 0.00018680000000000001,
-      "loss": 2.1185,
+      "epoch": 0.18,
+      "learning_rate": 0.00019078212290502794,
+      "loss": 2.1451,
       "step": 33
     },
     {
-      "epoch": 1.36,
-      "learning_rate": 0.00018640000000000003,
-      "loss": 1.988,
+      "epoch": 0.19,
+      "learning_rate": 0.0001905027932960894,
+      "loss": 2.223,
       "step": 34
     },
     {
-      "epoch": 1.4,
-      "learning_rate": 0.00018600000000000002,
-      "loss": 1.9493,
+      "epoch": 0.2,
+      "learning_rate": 0.00019022346368715085,
+      "loss": 2.2854,
       "step": 35
     },
     {
-      "epoch": 1.44,
-      "learning_rate": 0.0001856,
-      "loss": 1.9947,
+      "epoch": 0.2,
+      "learning_rate": 0.0001899441340782123,
+      "loss": 2.2265,
       "step": 36
     },
     {
-      "epoch": 1.48,
-      "learning_rate": 0.00018520000000000003,
-      "loss": 2.0506,
+      "epoch": 0.21,
+      "learning_rate": 0.00018966480446927375,
+      "loss": 2.1214,
       "step": 37
     },
     {
-      "epoch": 1.52,
-      "learning_rate": 0.00018480000000000002,
-      "loss": 2.0829,
+      "epoch": 0.21,
+      "learning_rate": 0.0001893854748603352,
+      "loss": 2.1898,
       "step": 38
     },
     {
-      "epoch": 1.56,
-      "learning_rate": 0.0001844,
-      "loss": 2.1455,
+      "epoch": 0.22,
+      "learning_rate": 0.00018910614525139666,
+      "loss": 2.1974,
       "step": 39
     },
     {
-      "epoch": 1.6,
-      "learning_rate": 0.00018400000000000003,
-      "loss": 2.0304,
+      "epoch": 0.22,
+      "learning_rate": 0.0001888268156424581,
+      "loss": 2.2259,
       "step": 40
     },
     {
-      "epoch": 1.64,
-      "learning_rate": 0.00018360000000000002,
-      "loss": 2.006,
+      "epoch": 0.23,
+      "learning_rate": 0.00018854748603351957,
+      "loss": 2.2094,
       "step": 41
     },
     {
-      "epoch": 1.68,
-      "learning_rate": 0.0001832,
-      "loss": 2.1759,
+      "epoch": 0.23,
+      "learning_rate": 0.00018826815642458103,
+      "loss": 2.1731,
       "step": 42
     },
     {
-      "epoch": 1.72,
-      "learning_rate": 0.00018280000000000003,
-      "loss": 2.0093,
+      "epoch": 0.24,
+      "learning_rate": 0.00018798882681564247,
+      "loss": 2.2373,
       "step": 43
     },
     {
-      "epoch": 1.76,
-      "learning_rate": 0.00018240000000000002,
-      "loss": 2.0683,
+      "epoch": 0.25,
+      "learning_rate": 0.0001877094972067039,
+      "loss": 2.2295,
       "step": 44
     },
     {
-      "epoch": 1.8,
-      "learning_rate": 0.000182,
-      "loss": 2.1352,
+      "epoch": 0.25,
+      "learning_rate": 0.00018743016759776538,
+      "loss": 2.1947,
       "step": 45
     },
     {
-      "epoch": 1.84,
-      "learning_rate": 0.00018160000000000002,
-      "loss": 1.9736,
+      "epoch": 0.26,
+      "learning_rate": 0.00018715083798882682,
+      "loss": 2.2115,
       "step": 46
     },
     {
-      "epoch": 1.88,
-      "learning_rate": 0.0001812,
-      "loss": 1.9631,
+      "epoch": 0.26,
+      "learning_rate": 0.00018687150837988828,
+      "loss": 2.1224,
       "step": 47
     },
     {
-      "epoch": 1.92,
-      "learning_rate": 0.0001808,
-      "loss": 2.1024,
+      "epoch": 0.27,
+      "learning_rate": 0.00018659217877094972,
+      "loss": 2.2137,
       "step": 48
     },
     {
-      "epoch": 1.96,
-      "learning_rate": 0.00018040000000000002,
-      "loss": 1.9895,
+      "epoch": 0.27,
+      "learning_rate": 0.00018631284916201116,
+      "loss": 2.2338,
       "step": 49
     },
     {
-      "epoch": 2.0,
-      "learning_rate": 0.00018,
-      "loss": 2.0067,
+      "epoch": 0.28,
+      "learning_rate": 0.00018603351955307266,
+      "loss": 2.1298,
       "step": 50
     },
     {
-      "epoch": 2.04,
-      "learning_rate": 0.0001796,
-      "loss": 2.0509,
+      "epoch": 0.28,
+      "learning_rate": 0.0001857541899441341,
+      "loss": 2.0883,
       "step": 51
     },
     {
-      "epoch": 2.08,
-      "learning_rate": 0.00017920000000000002,
-      "loss": 1.8795,
+      "epoch": 0.29,
+      "learning_rate": 0.00018547486033519553,
+      "loss": 2.1216,
       "step": 52
     },
     {
-      "epoch": 2.12,
-      "learning_rate": 0.0001788,
-      "loss": 2.0633,
+      "epoch": 0.3,
+      "learning_rate": 0.000185195530726257,
+      "loss": 2.2112,
       "step": 53
     },
     {
-      "epoch": 2.16,
-      "learning_rate": 0.0001784,
-      "loss": 1.9998,
+      "epoch": 0.3,
+      "learning_rate": 0.00018491620111731844,
+      "loss": 2.1224,
       "step": 54
     },
     {
-      "epoch": 2.2,
-      "learning_rate": 0.00017800000000000002,
-      "loss": 2.0675,
+      "epoch": 0.31,
+      "learning_rate": 0.0001846368715083799,
+      "loss": 2.2375,
       "step": 55
     },
     {
-      "epoch": 2.24,
-      "learning_rate": 0.0001776,
-      "loss": 2.0129,
+      "epoch": 0.31,
+      "learning_rate": 0.00018435754189944135,
+      "loss": 2.2235,
       "step": 56
     },
     {
-      "epoch": 2.28,
-      "learning_rate": 0.0001772,
-      "loss": 1.9302,
+      "epoch": 0.32,
+      "learning_rate": 0.00018407821229050279,
+      "loss": 2.1682,
       "step": 57
     },
     {
-      "epoch": 2.32,
-      "learning_rate": 0.00017680000000000001,
-      "loss": 2.0472,
+      "epoch": 0.32,
+      "learning_rate": 0.00018379888268156425,
+      "loss": 2.2077,
       "step": 58
     },
     {
-      "epoch": 2.36,
-      "learning_rate": 0.0001764,
-      "loss": 2.0031,
+      "epoch": 0.33,
+      "learning_rate": 0.00018351955307262572,
+      "loss": 2.1596,
       "step": 59
     },
     {
-      "epoch": 2.4,
-      "learning_rate": 0.00017600000000000002,
-      "loss": 2.0231,
+      "epoch": 0.34,
+      "learning_rate": 0.00018324022346368716,
+      "loss": 2.1311,
       "step": 60
     },
     {
-      "epoch": 2.44,
-      "learning_rate": 0.0001756,
-      "loss": 2.0192,
+      "epoch": 0.34,
+      "learning_rate": 0.00018296089385474862,
+      "loss": 2.1333,
       "step": 61
     },
     {
-      "epoch": 2.48,
-      "learning_rate": 0.0001752,
-      "loss": 2.1336,
+      "epoch": 0.35,
+      "learning_rate": 0.00018268156424581006,
+      "loss": 2.0901,
       "step": 62
     },
     {
-      "epoch": 2.52,
-      "learning_rate": 0.00017480000000000002,
-      "loss": 1.7753,
+      "epoch": 0.35,
+      "learning_rate": 0.00018240223463687153,
+      "loss": 2.1971,
       "step": 63
     },
     {
-      "epoch": 2.56,
-      "learning_rate": 0.0001744,
-      "loss": 2.0274,
+      "epoch": 0.36,
+      "learning_rate": 0.00018212290502793297,
+      "loss": 2.2602,
       "step": 64
     },
     {
-      "epoch": 2.6,
-      "learning_rate": 0.000174,
-      "loss": 1.8893,
+      "epoch": 0.36,
+      "learning_rate": 0.0001818435754189944,
+      "loss": 2.2194,
       "step": 65
     },
     {
-      "epoch": 2.64,
-      "learning_rate": 0.00017360000000000002,
-      "loss": 2.0341,
+      "epoch": 0.37,
+      "learning_rate": 0.00018156424581005588,
+      "loss": 2.1218,
       "step": 66
     },
     {
-      "epoch": 2.68,
-      "learning_rate": 0.0001732,
-      "loss": 2.1081,
+      "epoch": 0.37,
+      "learning_rate": 0.00018128491620111731,
+      "loss": 2.2049,
       "step": 67
     },
     {
-      "epoch": 2.72,
-      "learning_rate": 0.0001728,
-      "loss": 1.9463,
+      "epoch": 0.38,
+      "learning_rate": 0.00018100558659217878,
+      "loss": 2.1521,
       "step": 68
     },
     {
-      "epoch": 2.76,
-      "learning_rate": 0.00017240000000000002,
-      "loss": 2.0607,
+      "epoch": 0.39,
+      "learning_rate": 0.00018072625698324025,
+      "loss": 2.112,
       "step": 69
     },
     {
-      "epoch": 2.8,
-      "learning_rate": 0.000172,
-      "loss": 1.9803,
+      "epoch": 0.39,
+      "learning_rate": 0.0001804469273743017,
+      "loss": 2.1906,
       "step": 70
     },
     {
-      "epoch": 2.84,
-      "learning_rate": 0.0001716,
-      "loss": 1.7663,
+      "epoch": 0.4,
+      "learning_rate": 0.00018016759776536313,
+      "loss": 2.1717,
       "step": 71
     },
     {
-      "epoch": 2.88,
-      "learning_rate": 0.00017120000000000001,
-      "loss": 2.1116,
+      "epoch": 0.4,
+      "learning_rate": 0.0001798882681564246,
+      "loss": 2.0712,
       "step": 72
     },
     {
-      "epoch": 2.92,
-      "learning_rate": 0.0001708,
-      "loss": 1.9039,
+      "epoch": 0.41,
+      "learning_rate": 0.00017960893854748603,
+      "loss": 2.141,
       "step": 73
     },
     {
-      "epoch": 2.96,
-      "learning_rate": 0.0001704,
-      "loss": 2.049,
+      "epoch": 0.41,
+      "learning_rate": 0.0001793296089385475,
+      "loss": 2.0656,
       "step": 74
     },
     {
-      "epoch": 3.0,
-      "learning_rate": 0.00017,
-      "loss": 1.991,
+      "epoch": 0.42,
+      "learning_rate": 0.00017905027932960894,
+      "loss": 2.1125,
       "step": 75
     },
     {
-      "epoch": 3.04,
-      "learning_rate": 0.0001696,
-      "loss": 1.8755,
+      "epoch": 0.42,
+      "learning_rate": 0.00017877094972067038,
+      "loss": 2.0869,
       "step": 76
     },
     {
-      "epoch": 3.08,
-      "learning_rate": 0.0001692,
-      "loss": 2.0367,
+      "epoch": 0.43,
+      "learning_rate": 0.00017849162011173187,
+      "loss": 2.2478,
       "step": 77
     },
     {
-      "epoch": 3.12,
-      "learning_rate": 0.0001688,
-      "loss": 1.9959,
+      "epoch": 0.44,
+      "learning_rate": 0.0001782122905027933,
+      "loss": 2.1535,
       "step": 78
     },
     {
-      "epoch": 3.16,
-      "learning_rate": 0.0001684,
-      "loss": 1.8051,
+      "epoch": 0.44,
+      "learning_rate": 0.00017793296089385475,
+      "loss": 2.1927,
       "step": 79
     },
     {
-      "epoch": 3.2,
-      "learning_rate": 0.000168,
-      "loss": 2.0446,
+      "epoch": 0.45,
+      "learning_rate": 0.00017765363128491622,
+      "loss": 2.1213,
       "step": 80
     },
     {
-      "epoch": 3.24,
-      "learning_rate": 0.0001676,
-      "loss": 1.7873,
+      "epoch": 0.45,
+      "learning_rate": 0.00017737430167597766,
+      "loss": 2.0981,
       "step": 81
     },
     {
-      "epoch": 3.28,
-      "learning_rate": 0.0001672,
-      "loss": 1.9264,
+      "epoch": 0.46,
+      "learning_rate": 0.00017709497206703912,
+      "loss": 2.1828,
       "step": 82
     },
     {
-      "epoch": 3.32,
-      "learning_rate": 0.0001668,
-      "loss": 1.8595,
+      "epoch": 0.46,
+      "learning_rate": 0.00017681564245810056,
+      "loss": 2.0562,
       "step": 83
     },
     {
-      "epoch": 3.36,
-      "learning_rate": 0.0001664,
-      "loss": 1.9992,
+      "epoch": 0.47,
+      "learning_rate": 0.000176536312849162,
+      "loss": 2.1334,
       "step": 84
     },
     {
-      "epoch": 3.4,
-      "learning_rate": 0.000166,
-      "loss": 1.8783,
+      "epoch": 0.47,
+      "learning_rate": 0.00017625698324022347,
+      "loss": 2.1225,
       "step": 85
     },
     {
-      "epoch": 3.44,
-      "learning_rate": 0.0001656,
-      "loss": 2.0216,
+      "epoch": 0.48,
+      "learning_rate": 0.00017597765363128493,
+      "loss": 2.2098,
       "step": 86
     },
     {
-      "epoch": 3.48,
-      "learning_rate": 0.0001652,
-      "loss": 1.947,
+      "epoch": 0.49,
+      "learning_rate": 0.00017569832402234637,
+      "loss": 2.1519,
       "step": 87
     },
     {
-      "epoch": 3.52,
-      "learning_rate": 0.0001648,
-      "loss": 1.9554,
+      "epoch": 0.49,
+      "learning_rate": 0.00017541899441340784,
+      "loss": 2.1132,
       "step": 88
     },
     {
-      "epoch": 3.56,
-      "learning_rate": 0.0001644,
-      "loss": 1.8563,
+      "epoch": 0.5,
+      "learning_rate": 0.00017513966480446928,
+      "loss": 2.0333,
       "step": 89
     },
     {
-      "epoch": 3.6,
-      "learning_rate": 0.000164,
-      "loss": 1.7795,
+      "epoch": 0.5,
+      "learning_rate": 0.00017486033519553075,
+      "loss": 2.2764,
       "step": 90
     },
     {
-      "epoch": 3.64,
-      "learning_rate": 0.0001636,
-      "loss": 1.9347,
+      "epoch": 0.51,
+      "learning_rate": 0.00017458100558659218,
+      "loss": 2.1838,
       "step": 91
     },
     {
-      "epoch": 3.68,
-      "learning_rate": 0.0001632,
-      "loss": 2.0078,
+      "epoch": 0.51,
+      "learning_rate": 0.00017430167597765362,
+      "loss": 2.1386,
       "step": 92
     },
     {
-      "epoch": 3.72,
-      "learning_rate": 0.0001628,
-      "loss": 1.9964,
+      "epoch": 0.52,
+      "learning_rate": 0.0001740223463687151,
+      "loss": 2.1034,
       "step": 93
     },
     {
-      "epoch": 3.76,
-      "learning_rate": 0.00016240000000000002,
-      "loss": 1.9004,
+      "epoch": 0.53,
+      "learning_rate": 0.00017374301675977656,
+      "loss": 2.0346,
       "step": 94
     },
     {
-      "epoch": 3.8,
-      "learning_rate": 0.000162,
-      "loss": 1.9446,
+      "epoch": 0.53,
+      "learning_rate": 0.000173463687150838,
+      "loss": 2.0274,
       "step": 95
     },
     {
-      "epoch": 3.84,
-      "learning_rate": 0.00016160000000000002,
-      "loss": 1.8857,
+      "epoch": 0.54,
+      "learning_rate": 0.00017318435754189946,
+      "loss": 2.1036,
       "step": 96
     },
     {
-      "epoch": 3.88,
-      "learning_rate": 0.00016120000000000002,
-      "loss": 1.8797,
+      "epoch": 0.54,
+      "learning_rate": 0.0001729050279329609,
+      "loss": 2.1208,
       "step": 97
     },
     {
-      "epoch": 3.92,
-      "learning_rate": 0.0001608,
-      "loss": 1.7643,
+      "epoch": 0.55,
+      "learning_rate": 0.00017262569832402237,
+      "loss": 2.0572,
       "step": 98
     },
     {
-      "epoch": 3.96,
-      "learning_rate": 0.00016040000000000002,
-      "loss": 1.9724,
+      "epoch": 0.55,
+      "learning_rate": 0.0001723463687150838,
+      "loss": 2.1702,
       "step": 99
     },
     {
-      "epoch": 4.0,
-      "learning_rate": 0.00016,
-      "loss": 1.9058,
+      "epoch": 0.56,
+      "learning_rate": 0.00017206703910614525,
+      "loss": 2.1302,
       "step": 100
     },
     {
-      "epoch": 4.04,
-      "learning_rate": 0.0001596,
-      "loss": 1.8663,
+      "epoch": 0.56,
+      "learning_rate": 0.0001717877094972067,
+      "loss": 2.0175,
       "step": 101
     },
     {
-      "epoch": 4.08,
-      "learning_rate": 0.00015920000000000002,
-      "loss": 1.8457,
+      "epoch": 0.57,
+      "learning_rate": 0.00017150837988826815,
+      "loss": 2.1006,
       "step": 102
     },
     {
-      "epoch": 4.12,
-      "learning_rate": 0.0001588,
-      "loss": 1.8394,
+      "epoch": 0.58,
+      "learning_rate": 0.00017122905027932962,
+      "loss": 2.0662,
       "step": 103
     },
     {
-      "epoch": 4.16,
-      "learning_rate": 0.00015840000000000003,
-      "loss": 1.8941,
+      "epoch": 0.58,
+      "learning_rate": 0.00017094972067039109,
+      "loss": 1.988,
       "step": 104
     },
     {
-      "epoch": 4.2,
-      "learning_rate": 0.00015800000000000002,
-      "loss": 1.8601,
+      "epoch": 0.59,
+      "learning_rate": 0.00017067039106145253,
+      "loss": 2.1008,
       "step": 105
     },
     {
-      "epoch": 4.24,
-      "learning_rate": 0.0001576,
-      "loss": 1.7365,
+      "epoch": 0.59,
+      "learning_rate": 0.00017039106145251396,
+      "loss": 2.1482,
       "step": 106
     },
     {
-      "epoch": 4.28,
-      "learning_rate": 0.00015720000000000003,
-      "loss": 1.8809,
+      "epoch": 0.6,
+      "learning_rate": 0.00017011173184357543,
+      "loss": 2.1052,
       "step": 107
     },
     {
-      "epoch": 4.32,
-      "learning_rate": 0.00015680000000000002,
-      "loss": 2.0206,
+      "epoch": 0.6,
+      "learning_rate": 0.00016983240223463687,
+      "loss": 2.0978,
       "step": 108
     },
     {
-      "epoch": 4.36,
-      "learning_rate": 0.0001564,
-      "loss": 1.7776,
+      "epoch": 0.61,
+      "learning_rate": 0.00016955307262569834,
+      "loss": 2.1303,
       "step": 109
     },
     {
-      "epoch": 4.4,
-      "learning_rate": 0.00015600000000000002,
-      "loss": 1.9089,
+      "epoch": 0.61,
+      "learning_rate": 0.00016927374301675978,
+      "loss": 2.0794,
       "step": 110
     },
     {
-      "epoch": 4.44,
-      "learning_rate": 0.00015560000000000001,
-      "loss": 1.8464,
+      "epoch": 0.62,
+      "learning_rate": 0.00016899441340782122,
+      "loss": 2.1059,
       "step": 111
     },
     {
-      "epoch": 4.48,
-      "learning_rate": 0.0001552,
-      "loss": 1.7943,
+      "epoch": 0.63,
+      "learning_rate": 0.0001687150837988827,
+      "loss": 1.9642,
       "step": 112
     },
     {
-      "epoch": 4.52,
-      "learning_rate": 0.00015480000000000002,
-      "loss": 1.8081,
+      "epoch": 0.63,
+      "learning_rate": 0.00016843575418994415,
+      "loss": 2.0415,
       "step": 113
     },
     {
-      "epoch": 4.56,
-      "learning_rate": 0.0001544,
-      "loss": 1.734,
+      "epoch": 0.64,
+      "learning_rate": 0.0001681564245810056,
+      "loss": 2.0795,
       "step": 114
     },
     {
-      "epoch": 4.6,
-      "learning_rate": 0.000154,
-      "loss": 1.8379,
+      "epoch": 0.64,
+      "learning_rate": 0.00016787709497206705,
+      "loss": 2.0238,
       "step": 115
     },
     {
-      "epoch": 4.64,
-      "learning_rate": 0.00015360000000000002,
-      "loss": 1.6841,
+      "epoch": 0.65,
+      "learning_rate": 0.0001675977653631285,
+      "loss": 2.078,
       "step": 116
     },
     {
-      "epoch": 4.68,
-      "learning_rate": 0.0001532,
-      "loss": 1.8253,
+      "epoch": 0.65,
+      "learning_rate": 0.00016731843575418996,
+      "loss": 2.1362,
       "step": 117
     },
     {
-      "epoch": 4.72,
-      "learning_rate": 0.0001528,
-      "loss": 1.7607,
+      "epoch": 0.66,
+      "learning_rate": 0.0001670391061452514,
+      "loss": 2.0552,
       "step": 118
     },
     {
-      "epoch": 4.76,
-      "learning_rate": 0.00015240000000000002,
-      "loss": 1.8205,
+      "epoch": 0.66,
+      "learning_rate": 0.00016675977653631284,
+      "loss": 2.213,
       "step": 119
     },
     {
-      "epoch": 4.8,
-      "learning_rate": 0.000152,
-      "loss": 1.8443,
+      "epoch": 0.67,
+      "learning_rate": 0.0001664804469273743,
+      "loss": 1.9999,
       "step": 120
     },
     {
-      "epoch": 4.84,
-      "learning_rate": 0.0001516,
-      "loss": 1.8824,
+      "epoch": 0.68,
+      "learning_rate": 0.00016620111731843577,
+      "loss": 2.06,
       "step": 121
     },
     {
-      "epoch": 4.88,
-      "learning_rate": 0.00015120000000000002,
-      "loss": 1.8369,
+      "epoch": 0.68,
+      "learning_rate": 0.0001659217877094972,
+      "loss": 2.0177,
       "step": 122
     },
     {
-      "epoch": 4.92,
-      "learning_rate": 0.0001508,
-      "loss": 1.8017,
+      "epoch": 0.69,
+      "learning_rate": 0.00016564245810055868,
+      "loss": 2.0504,
       "step": 123
     },
     {
-      "epoch": 4.96,
-      "learning_rate": 0.0001504,
-      "loss": 1.7858,
+      "epoch": 0.69,
+      "learning_rate": 0.00016536312849162012,
+      "loss": 2.0585,
       "step": 124
     },
     {
-      "epoch": 5.0,
-      "learning_rate": 0.00015000000000000001,
-      "loss": 1.8366,
+      "epoch": 0.7,
+      "learning_rate": 0.00016508379888268158,
+      "loss": 2.0273,
       "step": 125
     },
     {
-      "epoch": 5.04,
-      "learning_rate": 0.0001496,
-      "loss": 1.7353,
+      "epoch": 0.7,
+      "learning_rate": 0.00016480446927374302,
+      "loss": 2.0549,
       "step": 126
     },
     {
-      "epoch": 5.08,
-      "learning_rate": 0.0001492,
-      "loss": 1.6017,
+      "epoch": 0.71,
+      "learning_rate": 0.00016452513966480446,
+      "loss": 2.044,
       "step": 127
     },
     {
-      "epoch": 5.12,
-      "learning_rate": 0.0001488,
-      "loss": 1.6645,
+      "epoch": 0.72,
+      "learning_rate": 0.00016424581005586593,
+      "loss": 2.0731,
       "step": 128
     },
     {
-      "epoch": 5.16,
-      "learning_rate": 0.0001484,
-      "loss": 1.8663,
+      "epoch": 0.72,
+      "learning_rate": 0.00016396648044692737,
+      "loss": 2.0568,
       "step": 129
     },
     {
-      "epoch": 5.2,
-      "learning_rate": 0.000148,
-      "loss": 1.7009,
+      "epoch": 0.73,
+      "learning_rate": 0.00016368715083798883,
+      "loss": 2.007,
       "step": 130
     },
     {
-      "epoch": 5.24,
-      "learning_rate": 0.0001476,
-      "loss": 1.7371,
+      "epoch": 0.73,
+      "learning_rate": 0.0001634078212290503,
+      "loss": 2.0707,
       "step": 131
     },
     {
-      "epoch": 5.28,
-      "learning_rate": 0.0001472,
-      "loss": 1.8555,
+      "epoch": 0.74,
+      "learning_rate": 0.00016312849162011174,
+      "loss": 1.9793,
       "step": 132
     },
     {
-      "epoch": 5.32,
-      "learning_rate": 0.00014680000000000002,
-      "loss": 1.6373,
+      "epoch": 0.74,
+      "learning_rate": 0.0001628491620111732,
+      "loss": 2.1311,
       "step": 133
     },
     {
-      "epoch": 5.36,
-      "learning_rate": 0.0001464,
-      "loss": 1.7211,
+      "epoch": 0.75,
+      "learning_rate": 0.00016256983240223465,
+      "loss": 2.0016,
       "step": 134
     },
     {
-      "epoch": 5.4,
-      "learning_rate": 0.000146,
-      "loss": 1.614,
+      "epoch": 0.75,
+      "learning_rate": 0.00016229050279329609,
+      "loss": 1.9945,
       "step": 135
     },
     {
-      "epoch": 5.44,
-      "learning_rate": 0.00014560000000000002,
-      "loss": 1.8736,
+      "epoch": 0.76,
+      "learning_rate": 0.00016201117318435755,
+      "loss": 2.0186,
       "step": 136
     },
     {
-      "epoch": 5.48,
-      "learning_rate": 0.0001452,
-      "loss": 1.7229,
+      "epoch": 0.77,
+      "learning_rate": 0.000161731843575419,
+      "loss": 2.0971,
       "step": 137
     },
     {
-      "epoch": 5.52,
-      "learning_rate": 0.0001448,
-      "loss": 1.7315,
+      "epoch": 0.77,
+      "learning_rate": 0.00016145251396648046,
+      "loss": 2.0883,
       "step": 138
     },
     {
-      "epoch": 5.56,
-      "learning_rate": 0.0001444,
-      "loss": 1.7259,
+      "epoch": 0.78,
+      "learning_rate": 0.00016117318435754192,
+      "loss": 2.0803,
       "step": 139
     },
     {
-      "epoch": 5.6,
-      "learning_rate": 0.000144,
-      "loss": 1.7032,
+      "epoch": 0.78,
+      "learning_rate": 0.00016089385474860336,
+      "loss": 2.0617,
       "step": 140
     },
     {
-      "epoch": 5.64,
-      "learning_rate": 0.0001436,
-      "loss": 1.9237,
+      "epoch": 0.79,
+      "learning_rate": 0.00016061452513966483,
+      "loss": 2.1265,
       "step": 141
     },
     {
-      "epoch": 5.68,
-      "learning_rate": 0.0001432,
-      "loss": 1.7821,
+      "epoch": 0.79,
+      "learning_rate": 0.00016033519553072627,
+      "loss": 2.0151,
       "step": 142
     },
     {
-      "epoch": 5.72,
-      "learning_rate": 0.0001428,
-      "loss": 1.6081,
+      "epoch": 0.8,
+      "learning_rate": 0.0001600558659217877,
+      "loss": 1.996,
       "step": 143
     },
     {
-      "epoch": 5.76,
-      "learning_rate": 0.0001424,
-      "loss": 1.7979,
+      "epoch": 0.8,
+      "learning_rate": 0.00015977653631284918,
+      "loss": 2.0164,
       "step": 144
     },
     {
-      "epoch": 5.8,
-      "learning_rate": 0.000142,
-      "loss": 1.6675,
+      "epoch": 0.81,
+      "learning_rate": 0.00015949720670391061,
+      "loss": 2.0314,
       "step": 145
     },
     {
-      "epoch": 5.84,
-      "learning_rate": 0.0001416,
-      "loss": 1.6758,
+      "epoch": 0.82,
+      "learning_rate": 0.00015921787709497208,
+      "loss": 1.9501,
       "step": 146
     },
     {
-      "epoch": 5.88,
-      "learning_rate": 0.0001412,
-      "loss": 1.7783,
+      "epoch": 0.82,
+      "learning_rate": 0.00015893854748603352,
+      "loss": 2.087,
       "step": 147
     },
     {
-      "epoch": 5.92,
-      "learning_rate": 0.0001408,
-      "loss": 1.5935,
+      "epoch": 0.83,
+      "learning_rate": 0.000158659217877095,
+      "loss": 2.0262,
       "step": 148
     },
     {
-      "epoch": 5.96,
-      "learning_rate": 0.0001404,
-      "loss": 1.7372,
+      "epoch": 0.83,
+      "learning_rate": 0.00015837988826815643,
+      "loss": 2.0765,
       "step": 149
     },
     {
-      "epoch": 6.0,
-      "learning_rate": 0.00014,
-      "loss": 1.6308,
+      "epoch": 0.84,
+      "learning_rate": 0.0001581005586592179,
+      "loss": 2.105,
       "step": 150
     },
     {
-      "epoch": 6.04,
-      "learning_rate": 0.0001396,
-      "loss": 1.5829,
+      "epoch": 0.84,
+      "learning_rate": 0.00015782122905027933,
+      "loss": 1.9863,
       "step": 151
     },
     {
-      "epoch": 6.08,
-      "learning_rate": 0.0001392,
-      "loss": 1.6538,
+      "epoch": 0.85,
+      "learning_rate": 0.0001575418994413408,
+      "loss": 1.9873,
       "step": 152
     },
     {
-      "epoch": 6.12,
-      "learning_rate": 0.00013879999999999999,
-      "loss": 1.7624,
+      "epoch": 0.85,
+      "learning_rate": 0.00015726256983240224,
+      "loss": 2.0094,
       "step": 153
     },
     {
-      "epoch": 6.16,
-      "learning_rate": 0.0001384,
-      "loss": 1.4968,
+      "epoch": 0.86,
+      "learning_rate": 0.00015698324022346368,
+      "loss": 1.9141,
       "step": 154
     },
     {
-      "epoch": 6.2,
-      "learning_rate": 0.000138,
-      "loss": 1.7305,
+      "epoch": 0.87,
+      "learning_rate": 0.00015670391061452514,
+      "loss": 1.917,
       "step": 155
     },
     {
-      "epoch": 6.24,
-      "learning_rate": 0.00013759999999999998,
-      "loss": 1.6536,
+      "epoch": 0.87,
+      "learning_rate": 0.00015642458100558658,
+      "loss": 2.109,
       "step": 156
     },
     {
-      "epoch": 6.28,
-      "learning_rate": 0.00013720000000000003,
-      "loss": 1.654,
+      "epoch": 0.88,
+      "learning_rate": 0.00015614525139664805,
+      "loss": 1.9799,
       "step": 157
     },
     {
-      "epoch": 6.32,
-      "learning_rate": 0.00013680000000000002,
-      "loss": 1.7163,
+      "epoch": 0.88,
+      "learning_rate": 0.00015586592178770952,
+      "loss": 1.9571,
       "step": 158
     },
     {
-      "epoch": 6.36,
-      "learning_rate": 0.0001364,
-      "loss": 1.6599,
+      "epoch": 0.89,
+      "learning_rate": 0.00015558659217877096,
+      "loss": 1.9931,
       "step": 159
     },
     {
-      "epoch": 6.4,
-      "learning_rate": 0.00013600000000000003,
-      "loss": 1.5729,
+      "epoch": 0.89,
+      "learning_rate": 0.00015530726256983242,
+      "loss": 2.1004,
       "step": 160
     },
     {
-      "epoch": 6.44,
-      "learning_rate": 0.00013560000000000002,
-      "loss": 1.5291,
+      "epoch": 0.9,
+      "learning_rate": 0.00015502793296089386,
+      "loss": 2.0385,
       "step": 161
     },
     {
-      "epoch": 6.48,
-      "learning_rate": 0.0001352,
-      "loss": 1.5666,
+      "epoch": 0.91,
+      "learning_rate": 0.0001547486033519553,
+      "loss": 1.9751,
       "step": 162
     },
     {
-      "epoch": 6.52,
-      "learning_rate": 0.00013480000000000002,
-      "loss": 1.7576,
+      "epoch": 0.91,
+      "learning_rate": 0.00015446927374301677,
+      "loss": 2.0544,
       "step": 163
     },
     {
-      "epoch": 6.56,
-      "learning_rate": 0.00013440000000000001,
-      "loss": 1.4462,
+      "epoch": 0.92,
+      "learning_rate": 0.0001541899441340782,
+      "loss": 2.0069,
       "step": 164
     },
     {
-      "epoch": 6.6,
-      "learning_rate": 0.000134,
-      "loss": 1.5659,
+      "epoch": 0.92,
+      "learning_rate": 0.00015391061452513967,
+      "loss": 1.9576,
       "step": 165
     },
     {
-      "epoch": 6.64,
-      "learning_rate": 0.00013360000000000002,
-      "loss": 1.6234,
+      "epoch": 0.93,
+      "learning_rate": 0.00015363128491620114,
+      "loss": 1.8991,
       "step": 166
     },
     {
-      "epoch": 6.68,
-      "learning_rate": 0.0001332,
-      "loss": 1.5176,
+      "epoch": 0.93,
+      "learning_rate": 0.00015335195530726258,
+      "loss": 1.9336,
       "step": 167
     },
     {
-      "epoch": 6.72,
-      "learning_rate": 0.0001328,
-      "loss": 1.667,
+      "epoch": 0.94,
+      "learning_rate": 0.00015307262569832405,
+      "loss": 1.9736,
       "step": 168
     },
     {
-      "epoch": 6.76,
-      "learning_rate": 0.00013240000000000002,
-      "loss": 1.6514,
+      "epoch": 0.94,
+      "learning_rate": 0.00015279329608938548,
+      "loss": 1.9702,
       "step": 169
     },
     {
-      "epoch": 6.8,
-      "learning_rate": 0.000132,
-      "loss": 1.7179,
+      "epoch": 0.95,
+      "learning_rate": 0.00015251396648044692,
+      "loss": 1.9055,
       "step": 170
     },
     {
-      "epoch": 6.84,
-      "learning_rate": 0.0001316,
-      "loss": 1.4373,
+      "epoch": 0.96,
+      "learning_rate": 0.0001522346368715084,
+      "loss": 2.0503,
       "step": 171
     },
     {
-      "epoch": 6.88,
-      "learning_rate": 0.00013120000000000002,
-      "loss": 1.7044,
+      "epoch": 0.96,
+      "learning_rate": 0.00015195530726256983,
+      "loss": 2.0039,
       "step": 172
     },
     {
-      "epoch": 6.92,
-      "learning_rate": 0.0001308,
-      "loss": 1.5673,
+      "epoch": 0.97,
+      "learning_rate": 0.0001516759776536313,
+      "loss": 1.9406,
       "step": 173
     },
     {
-      "epoch": 6.96,
-      "learning_rate": 0.0001304,
-      "loss": 1.6303,
+      "epoch": 0.97,
+      "learning_rate": 0.00015139664804469274,
+      "loss": 2.0525,
       "step": 174
     },
     {
-      "epoch": 7.0,
-      "learning_rate": 0.00013000000000000002,
-      "loss": 1.4828,
+      "epoch": 0.98,
+      "learning_rate": 0.0001511173184357542,
+      "loss": 1.9234,
       "step": 175
     },
     {
-      "epoch": 7.04,
-      "learning_rate": 0.0001296,
-      "loss": 1.6204,
+      "epoch": 0.98,
+      "learning_rate": 0.00015083798882681567,
+      "loss": 1.8614,
       "step": 176
     },
     {
-      "epoch": 7.08,
-      "learning_rate": 0.00012920000000000002,
-      "loss": 1.4955,
+      "epoch": 0.99,
+      "learning_rate": 0.0001505586592178771,
+      "loss": 1.9616,
       "step": 177
     },
     {
-      "epoch": 7.12,
-      "learning_rate": 0.00012880000000000001,
-      "loss": 1.6109,
+      "epoch": 0.99,
+      "learning_rate": 0.00015027932960893855,
+      "loss": 1.9509,
       "step": 178
     },
     {
-      "epoch": 7.16,
-      "learning_rate": 0.0001284,
-      "loss": 1.5318,
+      "epoch": 1.0,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.9592,
       "step": 179
     },
     {
-      "epoch": 7.2,
-      "learning_rate": 0.00012800000000000002,
-      "loss": 1.5702,
+      "epoch": 1.01,
+      "learning_rate": 0.00014972067039106145,
+      "loss": 1.8991,
       "step": 180
     },
     {
-      "epoch": 7.24,
-      "learning_rate": 0.0001276,
-      "loss": 1.4598,
+      "epoch": 1.01,
+      "learning_rate": 0.00014944134078212292,
+      "loss": 1.9127,
       "step": 181
     },
     {
-      "epoch": 7.28,
-      "learning_rate": 0.0001272,
-      "loss": 1.6145,
+      "epoch": 1.02,
+      "learning_rate": 0.00014916201117318436,
+      "loss": 1.8982,
       "step": 182
     },
     {
-      "epoch": 7.32,
-      "learning_rate": 0.00012680000000000002,
-      "loss": 1.3628,
+      "epoch": 1.02,
+      "learning_rate": 0.0001488826815642458,
+      "loss": 1.9534,
       "step": 183
     },
     {
-      "epoch": 7.36,
-      "learning_rate": 0.0001264,
-      "loss": 1.4578,
+      "epoch": 1.03,
+      "learning_rate": 0.0001486033519553073,
+      "loss": 1.7794,
       "step": 184
     },
     {
-      "epoch": 7.4,
-      "learning_rate": 0.000126,
-      "loss": 1.7094,
+      "epoch": 1.03,
+      "learning_rate": 0.00014832402234636873,
+      "loss": 1.7958,
       "step": 185
     },
     {
-      "epoch": 7.44,
-      "learning_rate": 0.00012560000000000002,
-      "loss": 1.4376,
+      "epoch": 1.04,
+      "learning_rate": 0.00014804469273743017,
+      "loss": 1.8282,
       "step": 186
     },
     {
-      "epoch": 7.48,
-      "learning_rate": 0.0001252,
-      "loss": 1.3393,
+      "epoch": 1.04,
+      "learning_rate": 0.00014776536312849164,
+      "loss": 2.0423,
       "step": 187
     },
     {
-      "epoch": 7.52,
-      "learning_rate": 0.0001248,
-      "loss": 1.4273,
+      "epoch": 1.05,
+      "learning_rate": 0.00014748603351955308,
+      "loss": 1.9282,
       "step": 188
     },
     {
-      "epoch": 7.56,
-      "learning_rate": 0.00012440000000000002,
-      "loss": 1.5506,
+      "epoch": 1.06,
+      "learning_rate": 0.00014720670391061454,
+      "loss": 1.9072,
       "step": 189
     },
     {
-      "epoch": 7.6,
-      "learning_rate": 0.000124,
-      "loss": 1.4774,
+      "epoch": 1.06,
+      "learning_rate": 0.00014692737430167598,
+      "loss": 1.8665,
       "step": 190
     },
     {
-      "epoch": 7.64,
-      "learning_rate": 0.0001236,
-      "loss": 1.4632,
+      "epoch": 1.07,
+      "learning_rate": 0.00014664804469273742,
+      "loss": 1.9021,
       "step": 191
     },
     {
-      "epoch": 7.68,
-      "learning_rate": 0.0001232,
-      "loss": 1.4568,
+      "epoch": 1.07,
+      "learning_rate": 0.0001463687150837989,
+      "loss": 1.7308,
       "step": 192
     },
     {
-      "epoch": 7.72,
-      "learning_rate": 0.0001228,
-      "loss": 1.6106,
+      "epoch": 1.08,
+      "learning_rate": 0.00014608938547486035,
+      "loss": 1.9165,
       "step": 193
     },
     {
-      "epoch": 7.76,
-      "learning_rate": 0.0001224,
-      "loss": 1.577,
+      "epoch": 1.08,
+      "learning_rate": 0.0001458100558659218,
+      "loss": 1.842,
       "step": 194
     },
     {
-      "epoch": 7.8,
-      "learning_rate": 0.000122,
-      "loss": 1.4805,
+      "epoch": 1.09,
+      "learning_rate": 0.00014553072625698326,
+      "loss": 1.9128,
       "step": 195
     },
     {
-      "epoch": 7.84,
-      "learning_rate": 0.0001216,
-      "loss": 1.4546,
+      "epoch": 1.09,
+      "learning_rate": 0.0001452513966480447,
+      "loss": 1.8005,
       "step": 196
     },
     {
-      "epoch": 7.88,
-      "learning_rate": 0.0001212,
-      "loss": 1.5164,
+      "epoch": 1.1,
+      "learning_rate": 0.00014497206703910614,
+      "loss": 1.8547,
       "step": 197
     },
     {
-      "epoch": 7.92,
-      "learning_rate": 0.0001208,
-      "loss": 1.5061,
+      "epoch": 1.11,
+      "learning_rate": 0.0001446927374301676,
+      "loss": 1.9042,
       "step": 198
     },
     {
-      "epoch": 7.96,
-      "learning_rate": 0.0001204,
-      "loss": 1.5312,
+      "epoch": 1.11,
+      "learning_rate": 0.00014441340782122905,
+      "loss": 1.8609,
       "step": 199
     },
     {
-      "epoch": 8.0,
-      "learning_rate": 0.00012,
-      "loss": 1.4463,
+      "epoch": 1.12,
+      "learning_rate": 0.0001441340782122905,
+      "loss": 1.9591,
       "step": 200
     },
     {
-      "epoch": 8.04,
-      "learning_rate": 0.00011960000000000001,
-      "loss": 1.4207,
+      "epoch": 1.12,
+      "learning_rate": 0.00014385474860335195,
+      "loss": 1.8722,
       "step": 201
     },
     {
-      "epoch": 8.08,
-      "learning_rate": 0.0001192,
-      "loss": 1.4688,
+      "epoch": 1.13,
+      "learning_rate": 0.00014357541899441342,
+      "loss": 1.8535,
       "step": 202
     },
     {
-      "epoch": 8.12,
-      "learning_rate": 0.0001188,
-      "loss": 1.4445,
+      "epoch": 1.13,
+      "learning_rate": 0.00014329608938547488,
+      "loss": 1.8676,
       "step": 203
     },
     {
-      "epoch": 8.16,
-      "learning_rate": 0.0001184,
-      "loss": 1.4158,
+      "epoch": 1.14,
+      "learning_rate": 0.00014301675977653632,
+      "loss": 1.8976,
       "step": 204
     },
     {
-      "epoch": 8.2,
-      "learning_rate": 0.000118,
-      "loss": 1.3483,
+      "epoch": 1.15,
+      "learning_rate": 0.00014273743016759776,
+      "loss": 1.7723,
       "step": 205
     },
     {
-      "epoch": 8.24,
-      "learning_rate": 0.0001176,
-      "loss": 1.4117,
+      "epoch": 1.15,
+      "learning_rate": 0.00014245810055865923,
+      "loss": 1.8165,
       "step": 206
     },
     {
-      "epoch": 8.28,
-      "learning_rate": 0.0001172,
-      "loss": 1.4267,
+      "epoch": 1.16,
+      "learning_rate": 0.00014217877094972067,
+      "loss": 1.7811,
       "step": 207
     },
     {
-      "epoch": 8.32,
-      "learning_rate": 0.00011679999999999999,
-      "loss": 1.5547,
+      "epoch": 1.16,
+      "learning_rate": 0.00014189944134078214,
+      "loss": 1.908,
       "step": 208
     },
     {
-      "epoch": 8.36,
-      "learning_rate": 0.0001164,
-      "loss": 1.4883,
+      "epoch": 1.17,
+      "learning_rate": 0.00014162011173184357,
+      "loss": 1.7663,
       "step": 209
     },
     {
-      "epoch": 8.4,
-      "learning_rate": 0.000116,
-      "loss": 1.414,
+      "epoch": 1.17,
+      "learning_rate": 0.00014134078212290501,
+      "loss": 1.6779,
       "step": 210
     },
     {
-      "epoch": 8.44,
-      "learning_rate": 0.00011559999999999999,
-      "loss": 1.3254,
+      "epoch": 1.18,
+      "learning_rate": 0.0001410614525139665,
+      "loss": 1.9039,
       "step": 211
     },
     {
-      "epoch": 8.48,
-      "learning_rate": 0.0001152,
-      "loss": 1.22,
+      "epoch": 1.18,
+      "learning_rate": 0.00014078212290502795,
+      "loss": 1.8033,
       "step": 212
     },
     {
-      "epoch": 8.52,
-      "learning_rate": 0.0001148,
-      "loss": 1.3224,
+      "epoch": 1.19,
+      "learning_rate": 0.00014050279329608939,
+      "loss": 1.8251,
       "step": 213
     },
     {
-      "epoch": 8.56,
-      "learning_rate": 0.0001144,
-      "loss": 1.6158,
+      "epoch": 1.2,
+      "learning_rate": 0.00014022346368715085,
+      "loss": 1.8505,
       "step": 214
     },
     {
-      "epoch": 8.6,
-      "learning_rate": 0.00011399999999999999,
-      "loss": 1.2817,
+      "epoch": 1.2,
+      "learning_rate": 0.0001399441340782123,
+      "loss": 1.8147,
       "step": 215
     },
     {
-      "epoch": 8.64,
-      "learning_rate": 0.0001136,
-      "loss": 1.4077,
+      "epoch": 1.21,
+      "learning_rate": 0.00013966480446927376,
+      "loss": 1.8419,
       "step": 216
     },
     {
-      "epoch": 8.68,
-      "learning_rate": 0.0001132,
-      "loss": 1.5311,
+      "epoch": 1.21,
+      "learning_rate": 0.0001393854748603352,
+      "loss": 1.8401,
       "step": 217
     },
     {
-      "epoch": 8.72,
-      "learning_rate": 0.00011279999999999999,
-      "loss": 1.5289,
+      "epoch": 1.22,
+      "learning_rate": 0.00013910614525139664,
+      "loss": 1.8912,
       "step": 218
     },
     {
-      "epoch": 8.76,
-      "learning_rate": 0.00011240000000000002,
-      "loss": 1.4576,
+      "epoch": 1.22,
+      "learning_rate": 0.0001388268156424581,
+      "loss": 1.7548,
       "step": 219
     },
     {
-      "epoch": 8.8,
-      "learning_rate": 0.00011200000000000001,
-      "loss": 1.2063,
+      "epoch": 1.23,
+      "learning_rate": 0.00013854748603351957,
+      "loss": 1.8741,
       "step": 220
     },
     {
-      "epoch": 8.84,
-      "learning_rate": 0.00011160000000000002,
-      "loss": 1.3543,
+      "epoch": 1.23,
+      "learning_rate": 0.000138268156424581,
+      "loss": 1.9549,
       "step": 221
     },
     {
-      "epoch": 8.88,
-      "learning_rate": 0.00011120000000000002,
-      "loss": 1.4352,
+      "epoch": 1.24,
+      "learning_rate": 0.00013798882681564248,
+      "loss": 1.9093,
       "step": 222
     },
     {
-      "epoch": 8.92,
-      "learning_rate": 0.00011080000000000001,
-      "loss": 1.3058,
+      "epoch": 1.25,
+      "learning_rate": 0.00013770949720670392,
+      "loss": 1.7896,
       "step": 223
     },
     {
-      "epoch": 8.96,
-      "learning_rate": 0.00011040000000000001,
-      "loss": 1.3475,
+      "epoch": 1.25,
+      "learning_rate": 0.00013743016759776538,
+      "loss": 1.8491,
       "step": 224
     },
     {
-      "epoch": 9.0,
-      "learning_rate": 0.00011000000000000002,
-      "loss": 1.1293,
+      "epoch": 1.26,
+      "learning_rate": 0.00013715083798882682,
+      "loss": 1.7851,
       "step": 225
     },
     {
-      "epoch": 9.04,
-      "learning_rate": 0.00010960000000000001,
-      "loss": 1.1671,
+      "epoch": 1.26,
+      "learning_rate": 0.00013687150837988826,
+      "loss": 1.6992,
       "step": 226
     },
     {
-      "epoch": 9.08,
-      "learning_rate": 0.00010920000000000001,
-      "loss": 1.4726,
+      "epoch": 1.27,
+      "learning_rate": 0.00013659217877094973,
+      "loss": 1.9765,
       "step": 227
     },
     {
-      "epoch": 9.12,
-      "learning_rate": 0.00010880000000000002,
-      "loss": 1.3986,
+      "epoch": 1.27,
+      "learning_rate": 0.00013631284916201117,
+      "loss": 1.8179,
       "step": 228
     },
     {
-      "epoch": 9.16,
-      "learning_rate": 0.00010840000000000002,
-      "loss": 1.2731,
+      "epoch": 1.28,
+      "learning_rate": 0.00013603351955307263,
+      "loss": 1.8548,
       "step": 229
     },
     {
-      "epoch": 9.2,
-      "learning_rate": 0.00010800000000000001,
-      "loss": 1.2212,
+      "epoch": 1.28,
+      "learning_rate": 0.0001357541899441341,
+      "loss": 1.8843,
       "step": 230
     },
     {
-      "epoch": 9.24,
-      "learning_rate": 0.00010760000000000001,
-      "loss": 1.3067,
+      "epoch": 1.29,
+      "learning_rate": 0.00013547486033519554,
+      "loss": 1.9105,
       "step": 231
     },
     {
-      "epoch": 9.28,
-      "learning_rate": 0.00010720000000000002,
-      "loss": 1.278,
+      "epoch": 1.3,
+      "learning_rate": 0.00013519553072625698,
+      "loss": 1.8748,
       "step": 232
     },
     {
-      "epoch": 9.32,
-      "learning_rate": 0.00010680000000000001,
-      "loss": 1.4141,
+      "epoch": 1.3,
+      "learning_rate": 0.00013491620111731844,
+      "loss": 1.7976,
       "step": 233
     },
     {
-      "epoch": 9.36,
-      "learning_rate": 0.00010640000000000001,
-      "loss": 1.2885,
+      "epoch": 1.31,
+      "learning_rate": 0.00013463687150837988,
+      "loss": 1.7369,
       "step": 234
     },
     {
-      "epoch": 9.4,
-      "learning_rate": 0.00010600000000000002,
-      "loss": 1.466,
+      "epoch": 1.31,
+      "learning_rate": 0.00013435754189944135,
+      "loss": 1.7808,
       "step": 235
     },
     {
-      "epoch": 9.44,
-      "learning_rate": 0.0001056,
-      "loss": 1.2979,
+      "epoch": 1.32,
+      "learning_rate": 0.0001340782122905028,
+      "loss": 1.8385,
       "step": 236
     },
     {
-      "epoch": 9.48,
-      "learning_rate": 0.00010520000000000001,
-      "loss": 1.1622,
+      "epoch": 1.32,
+      "learning_rate": 0.00013379888268156423,
+      "loss": 1.8295,
       "step": 237
     },
     {
-      "epoch": 9.52,
-      "learning_rate": 0.00010480000000000001,
-      "loss": 1.2504,
+      "epoch": 1.33,
+      "learning_rate": 0.00013351955307262572,
+      "loss": 1.757,
       "step": 238
     },
     {
-      "epoch": 9.56,
-      "learning_rate": 0.0001044,
-      "loss": 1.228,
+      "epoch": 1.34,
+      "learning_rate": 0.00013324022346368716,
+      "loss": 1.7904,
       "step": 239
     },
     {
-      "epoch": 9.6,
-      "learning_rate": 0.00010400000000000001,
-      "loss": 1.3607,
+      "epoch": 1.34,
+      "learning_rate": 0.0001329608938547486,
+      "loss": 1.7632,
       "step": 240
     },
     {
-      "epoch": 9.64,
-      "learning_rate": 0.00010360000000000001,
-      "loss": 1.1921,
+      "epoch": 1.35,
+      "learning_rate": 0.00013268156424581007,
+      "loss": 1.7867,
       "step": 241
     },
     {
-      "epoch": 9.68,
-      "learning_rate": 0.0001032,
-      "loss": 1.2114,
+      "epoch": 1.35,
+      "learning_rate": 0.0001324022346368715,
+      "loss": 1.8259,
       "step": 242
     },
     {
-      "epoch": 9.72,
-      "learning_rate": 0.0001028,
-      "loss": 1.2385,
+      "epoch": 1.36,
+      "learning_rate": 0.00013212290502793297,
+      "loss": 1.6655,
       "step": 243
     },
     {
-      "epoch": 9.76,
-      "learning_rate": 0.00010240000000000001,
-      "loss": 1.3227,
+      "epoch": 1.36,
+      "learning_rate": 0.0001318435754189944,
+      "loss": 1.6848,
       "step": 244
     },
     {
-      "epoch": 9.8,
-      "learning_rate": 0.00010200000000000001,
-      "loss": 1.3935,
+      "epoch": 1.37,
+      "learning_rate": 0.00013156424581005585,
+      "loss": 1.7931,
       "step": 245
     },
     {
-      "epoch": 9.84,
-      "learning_rate": 0.0001016,
-      "loss": 1.2209,
+      "epoch": 1.37,
+      "learning_rate": 0.00013128491620111732,
+      "loss": 1.7868,
       "step": 246
     },
     {
-      "epoch": 9.88,
-      "learning_rate": 0.00010120000000000001,
-      "loss": 1.1541,
+      "epoch": 1.38,
+      "learning_rate": 0.00013100558659217879,
+      "loss": 1.7732,
       "step": 247
     },
     {
-      "epoch": 9.92,
-      "learning_rate": 0.00010080000000000001,
-      "loss": 1.4049,
+      "epoch": 1.39,
+      "learning_rate": 0.00013072625698324022,
+      "loss": 1.7851,
       "step": 248
     },
     {
-      "epoch": 9.96,
-      "learning_rate": 0.0001004,
-      "loss": 1.13,
+      "epoch": 1.39,
+      "learning_rate": 0.0001304469273743017,
+      "loss": 1.7406,
       "step": 249
     },
     {
-      "epoch": 10.0,
-      "learning_rate": 0.0001,
-      "loss": 1.3783,
+      "epoch": 1.4,
+      "learning_rate": 0.00013016759776536313,
+      "loss": 1.5853,
       "step": 250
     },
     {
-      "epoch": 10.04,
-      "learning_rate": 9.960000000000001e-05,
-      "loss": 1.3207,
+      "epoch": 1.4,
+      "learning_rate": 0.0001298882681564246,
+      "loss": 1.8271,
       "step": 251
     },
     {
-      "epoch": 10.08,
-      "learning_rate": 9.92e-05,
-      "loss": 1.2697,
+      "epoch": 1.41,
+      "learning_rate": 0.00012960893854748604,
+      "loss": 1.6054,
       "step": 252
     },
     {
-      "epoch": 10.12,
-      "learning_rate": 9.88e-05,
-      "loss": 1.091,
+      "epoch": 1.41,
+      "learning_rate": 0.00012932960893854748,
+      "loss": 1.6884,
       "step": 253
     },
     {
-      "epoch": 10.16,
-      "learning_rate": 9.84e-05,
-      "loss": 1.0463,
+      "epoch": 1.42,
+      "learning_rate": 0.00012905027932960894,
+      "loss": 1.7333,
       "step": 254
     },
     {
-      "epoch": 10.2,
-      "learning_rate": 9.8e-05,
-      "loss": 1.3686,
+      "epoch": 1.42,
+      "learning_rate": 0.00012877094972067038,
+      "loss": 1.803,
       "step": 255
     },
     {
-      "epoch": 10.24,
-      "learning_rate": 9.76e-05,
-      "loss": 1.3109,
+      "epoch": 1.43,
+      "learning_rate": 0.00012849162011173185,
+      "loss": 1.63,
       "step": 256
     },
     {
-      "epoch": 10.28,
-      "learning_rate": 9.72e-05,
-      "loss": 1.2338,
+      "epoch": 1.44,
+      "learning_rate": 0.00012821229050279331,
+      "loss": 1.8023,
       "step": 257
     },
     {
-      "epoch": 10.32,
-      "learning_rate": 9.680000000000001e-05,
-      "loss": 1.12,
+      "epoch": 1.44,
+      "learning_rate": 0.00012793296089385475,
+      "loss": 1.762,
       "step": 258
     },
     {
-      "epoch": 10.36,
-      "learning_rate": 9.64e-05,
-      "loss": 1.1864,
+      "epoch": 1.45,
+      "learning_rate": 0.00012765363128491622,
+      "loss": 1.7565,
       "step": 259
     },
     {
-      "epoch": 10.4,
-      "learning_rate": 9.6e-05,
-      "loss": 1.1062,
+      "epoch": 1.45,
+      "learning_rate": 0.00012737430167597766,
+      "loss": 1.5937,
       "step": 260
     },
     {
-      "epoch": 10.44,
-      "learning_rate": 9.56e-05,
-      "loss": 1.2924,
+      "epoch": 1.46,
+      "learning_rate": 0.0001270949720670391,
+      "loss": 1.7208,
       "step": 261
     },
     {
-      "epoch": 10.48,
-      "learning_rate": 9.52e-05,
-      "loss": 1.1931,
+      "epoch": 1.46,
+      "learning_rate": 0.00012681564245810057,
+      "loss": 1.8097,
       "step": 262
     },
     {
-      "epoch": 10.52,
-      "learning_rate": 9.48e-05,
-      "loss": 1.2366,
+      "epoch": 1.47,
+      "learning_rate": 0.000126536312849162,
+      "loss": 1.7042,
       "step": 263
     },
     {
-      "epoch": 10.56,
-      "learning_rate": 9.44e-05,
-      "loss": 1.1589,
+      "epoch": 1.47,
+      "learning_rate": 0.00012625698324022347,
+      "loss": 1.7892,
       "step": 264
     },
     {
-      "epoch": 10.6,
-      "learning_rate": 9.4e-05,
-      "loss": 1.1197,
+      "epoch": 1.48,
+      "learning_rate": 0.00012597765363128494,
+      "loss": 1.752,
       "step": 265
     },
     {
-      "epoch": 10.64,
-      "learning_rate": 9.360000000000001e-05,
-      "loss": 1.3072,
+      "epoch": 1.49,
+      "learning_rate": 0.00012569832402234638,
+      "loss": 1.7333,
       "step": 266
     },
     {
-      "epoch": 10.68,
-      "learning_rate": 9.320000000000002e-05,
-      "loss": 1.1173,
+      "epoch": 1.49,
+      "learning_rate": 0.00012541899441340784,
+      "loss": 1.7492,
       "step": 267
     },
     {
-      "epoch": 10.72,
-      "learning_rate": 9.28e-05,
-      "loss": 1.0378,
+      "epoch": 1.5,
+      "learning_rate": 0.00012513966480446928,
+      "loss": 1.818,
       "step": 268
     },
     {
-      "epoch": 10.76,
-      "learning_rate": 9.240000000000001e-05,
-      "loss": 1.1746,
+      "epoch": 1.5,
+      "learning_rate": 0.00012486033519553072,
+      "loss": 1.7146,
       "step": 269
     },
     {
-      "epoch": 10.8,
-      "learning_rate": 9.200000000000001e-05,
-      "loss": 1.1144,
+      "epoch": 1.51,
+      "learning_rate": 0.0001245810055865922,
+      "loss": 1.7958,
       "step": 270
     },
     {
-      "epoch": 10.84,
-      "learning_rate": 9.16e-05,
-      "loss": 1.1862,
+      "epoch": 1.51,
+      "learning_rate": 0.00012430167597765363,
+      "loss": 1.7212,
       "step": 271
     },
     {
-      "epoch": 10.88,
-      "learning_rate": 9.120000000000001e-05,
-      "loss": 1.0816,
+      "epoch": 1.52,
+      "learning_rate": 0.0001240223463687151,
+      "loss": 1.8835,
       "step": 272
     },
     {
-      "epoch": 10.92,
-      "learning_rate": 9.080000000000001e-05,
-      "loss": 1.2288,
+      "epoch": 1.53,
+      "learning_rate": 0.00012374301675977656,
+      "loss": 1.7486,
       "step": 273
     },
     {
-      "epoch": 10.96,
-      "learning_rate": 9.04e-05,
-      "loss": 1.3031,
+      "epoch": 1.53,
+      "learning_rate": 0.000123463687150838,
+      "loss": 1.8103,
       "step": 274
     },
     {
-      "epoch": 11.0,
-      "learning_rate": 9e-05,
-      "loss": 1.1646,
+      "epoch": 1.54,
+      "learning_rate": 0.00012318435754189944,
+      "loss": 1.7557,
       "step": 275
     },
     {
-      "epoch": 11.04,
-      "learning_rate": 8.960000000000001e-05,
-      "loss": 1.2088,
+      "epoch": 1.54,
+      "learning_rate": 0.0001229050279329609,
+      "loss": 1.6198,
       "step": 276
     },
     {
-      "epoch": 11.08,
-      "learning_rate": 8.92e-05,
-      "loss": 1.1465,
+      "epoch": 1.55,
+      "learning_rate": 0.00012262569832402235,
+      "loss": 1.6971,
       "step": 277
     },
     {
-      "epoch": 11.12,
-      "learning_rate": 8.88e-05,
-      "loss": 1.0313,
+      "epoch": 1.55,
+      "learning_rate": 0.0001223463687150838,
+      "loss": 1.668,
       "step": 278
     },
     {
-      "epoch": 11.16,
-      "learning_rate": 8.840000000000001e-05,
-      "loss": 0.9662,
+      "epoch": 1.56,
+      "learning_rate": 0.00012206703910614525,
+      "loss": 1.8795,
       "step": 279
     },
     {
-      "epoch": 11.2,
-      "learning_rate": 8.800000000000001e-05,
-      "loss": 1.051,
+      "epoch": 1.56,
+      "learning_rate": 0.0001217877094972067,
+      "loss": 1.6412,
       "step": 280
     },
     {
-      "epoch": 11.24,
-      "learning_rate": 8.76e-05,
-      "loss": 1.1708,
+      "epoch": 1.57,
+      "learning_rate": 0.00012150837988826816,
+      "loss": 1.7497,
       "step": 281
     },
     {
-      "epoch": 11.28,
-      "learning_rate": 8.72e-05,
-      "loss": 1.0236,
+      "epoch": 1.58,
+      "learning_rate": 0.00012122905027932962,
+      "loss": 1.5577,
       "step": 282
     },
     {
-      "epoch": 11.32,
-      "learning_rate": 8.680000000000001e-05,
-      "loss": 1.1359,
+      "epoch": 1.58,
+      "learning_rate": 0.00012094972067039108,
+      "loss": 1.8049,
       "step": 283
     },
     {
-      "epoch": 11.36,
-      "learning_rate": 8.64e-05,
-      "loss": 1.1398,
+      "epoch": 1.59,
+      "learning_rate": 0.00012067039106145253,
+      "loss": 1.6834,
       "step": 284
     },
     {
-      "epoch": 11.4,
-      "learning_rate": 8.6e-05,
-      "loss": 1.0213,
+      "epoch": 1.59,
+      "learning_rate": 0.00012039106145251397,
+      "loss": 1.7978,
       "step": 285
     },
     {
-      "epoch": 11.44,
-      "learning_rate": 8.560000000000001e-05,
-      "loss": 1.1788,
+      "epoch": 1.6,
+      "learning_rate": 0.00012011173184357542,
+      "loss": 1.6558,
       "step": 286
     },
     {
-      "epoch": 11.48,
-      "learning_rate": 8.52e-05,
-      "loss": 1.0387,
+      "epoch": 1.6,
+      "learning_rate": 0.00011983240223463687,
+      "loss": 1.7561,
       "step": 287
     },
     {
-      "epoch": 11.52,
-      "learning_rate": 8.48e-05,
-      "loss": 0.9476,
+      "epoch": 1.61,
+      "learning_rate": 0.00011955307262569833,
+      "loss": 1.6807,
       "step": 288
     },
     {
-      "epoch": 11.56,
-      "learning_rate": 8.44e-05,
-      "loss": 1.1954,
+      "epoch": 1.61,
+      "learning_rate": 0.00011927374301675978,
+      "loss": 1.6937,
       "step": 289
     },
     {
-      "epoch": 11.6,
-      "learning_rate": 8.4e-05,
-      "loss": 1.0309,
+      "epoch": 1.62,
+      "learning_rate": 0.00011899441340782122,
+      "loss": 1.6591,
       "step": 290
     },
     {
-      "epoch": 11.64,
-      "learning_rate": 8.36e-05,
-      "loss": 1.1321,
+      "epoch": 1.63,
+      "learning_rate": 0.0001187150837988827,
+      "loss": 1.6771,
       "step": 291
     },
     {
-      "epoch": 11.68,
-      "learning_rate": 8.32e-05,
-      "loss": 1.0914,
+      "epoch": 1.63,
+      "learning_rate": 0.00011843575418994415,
+      "loss": 1.7743,
       "step": 292
     },
     {
-      "epoch": 11.72,
-      "learning_rate": 8.28e-05,
-      "loss": 1.222,
+      "epoch": 1.64,
+      "learning_rate": 0.00011815642458100559,
+      "loss": 1.5857,
       "step": 293
     },
     {
-      "epoch": 11.76,
-      "learning_rate": 8.24e-05,
-      "loss": 1.0127,
+      "epoch": 1.64,
+      "learning_rate": 0.00011787709497206705,
+      "loss": 1.6999,
       "step": 294
     },
     {
-      "epoch": 11.8,
-      "learning_rate": 8.2e-05,
-      "loss": 1.1977,
+      "epoch": 1.65,
+      "learning_rate": 0.0001175977653631285,
+      "loss": 1.5661,
       "step": 295
     },
     {
-      "epoch": 11.84,
-      "learning_rate": 8.16e-05,
-      "loss": 1.122,
+      "epoch": 1.65,
+      "learning_rate": 0.00011731843575418995,
+      "loss": 1.7235,
       "step": 296
     },
     {
-      "epoch": 11.88,
-      "learning_rate": 8.120000000000001e-05,
-      "loss": 1.1543,
+      "epoch": 1.66,
+      "learning_rate": 0.0001170391061452514,
+      "loss": 1.607,
       "step": 297
     },
     {
-      "epoch": 11.92,
-      "learning_rate": 8.080000000000001e-05,
-      "loss": 1.1767,
+      "epoch": 1.66,
+      "learning_rate": 0.00011675977653631284,
+      "loss": 1.68,
       "step": 298
     },
     {
-      "epoch": 11.96,
-      "learning_rate": 8.04e-05,
-      "loss": 1.1341,
+      "epoch": 1.67,
+      "learning_rate": 0.0001164804469273743,
+      "loss": 1.6938,
       "step": 299
     },
     {
-      "epoch": 12.0,
-      "learning_rate": 8e-05,
-      "loss": 1.0107,
+      "epoch": 1.68,
+      "learning_rate": 0.00011620111731843578,
+      "loss": 1.6315,
       "step": 300
     },
     {
-      "epoch": 12.04,
-      "learning_rate": 7.960000000000001e-05,
-      "loss": 1.1455,
+      "epoch": 1.68,
+      "learning_rate": 0.00011592178770949722,
+      "loss": 1.6802,
       "step": 301
     },
     {
-      "epoch": 12.08,
-      "learning_rate": 7.920000000000001e-05,
-      "loss": 1.0091,
+      "epoch": 1.69,
+      "learning_rate": 0.00011564245810055867,
+      "loss": 1.7174,
       "step": 302
     },
     {
-      "epoch": 12.12,
-      "learning_rate": 7.88e-05,
-      "loss": 0.9888,
+      "epoch": 1.69,
+      "learning_rate": 0.00011536312849162012,
+      "loss": 1.5212,
       "step": 303
     },
     {
-      "epoch": 12.16,
-      "learning_rate": 7.840000000000001e-05,
-      "loss": 0.9894,
+      "epoch": 1.7,
+      "learning_rate": 0.00011508379888268157,
+      "loss": 1.5808,
       "step": 304
     },
     {
-      "epoch": 12.2,
-      "learning_rate": 7.800000000000001e-05,
-      "loss": 1.0095,
+      "epoch": 1.7,
+      "learning_rate": 0.00011480446927374303,
+      "loss": 1.6152,
       "step": 305
     },
     {
-      "epoch": 12.24,
-      "learning_rate": 7.76e-05,
-      "loss": 1.1163,
+      "epoch": 1.71,
+      "learning_rate": 0.00011452513966480447,
+      "loss": 1.5435,
       "step": 306
     },
     {
-      "epoch": 12.28,
-      "learning_rate": 7.72e-05,
-      "loss": 1.0345,
+      "epoch": 1.72,
+      "learning_rate": 0.00011424581005586592,
+      "loss": 1.6603,
       "step": 307
     },
     {
-      "epoch": 12.32,
-      "learning_rate": 7.680000000000001e-05,
-      "loss": 0.9662,
+      "epoch": 1.72,
+      "learning_rate": 0.00011396648044692737,
+      "loss": 1.685,
       "step": 308
     },
     {
-      "epoch": 12.36,
-      "learning_rate": 7.64e-05,
-      "loss": 0.9064,
+      "epoch": 1.73,
+      "learning_rate": 0.00011368715083798884,
+      "loss": 1.6002,
       "step": 309
     },
     {
-      "epoch": 12.4,
-      "learning_rate": 7.6e-05,
-      "loss": 0.9448,
+      "epoch": 1.73,
+      "learning_rate": 0.00011340782122905029,
+      "loss": 1.6046,
       "step": 310
     },
     {
-      "epoch": 12.44,
-      "learning_rate": 7.560000000000001e-05,
-      "loss": 0.9509,
+      "epoch": 1.74,
+      "learning_rate": 0.00011312849162011174,
+      "loss": 1.5969,
       "step": 311
     },
     {
-      "epoch": 12.48,
-      "learning_rate": 7.52e-05,
-      "loss": 1.123,
+      "epoch": 1.74,
+      "learning_rate": 0.0001128491620111732,
+      "loss": 1.5845,
       "step": 312
     },
     {
-      "epoch": 12.52,
-      "learning_rate": 7.48e-05,
-      "loss": 1.1011,
+      "epoch": 1.75,
+      "learning_rate": 0.00011256983240223464,
+      "loss": 1.8183,
       "step": 313
     },
     {
-      "epoch": 12.56,
-      "learning_rate": 7.44e-05,
-      "loss": 0.9398,
+      "epoch": 1.75,
+      "learning_rate": 0.00011229050279329609,
+      "loss": 1.6953,
       "step": 314
     },
     {
-      "epoch": 12.6,
-      "learning_rate": 7.4e-05,
-      "loss": 1.0498,
+      "epoch": 1.76,
+      "learning_rate": 0.00011201117318435754,
+      "loss": 1.7787,
       "step": 315
     },
     {
-      "epoch": 12.64,
-      "learning_rate": 7.36e-05,
-      "loss": 1.0442,
+      "epoch": 1.77,
+      "learning_rate": 0.000111731843575419,
+      "loss": 1.6422,
       "step": 316
     },
     {
-      "epoch": 12.68,
-      "learning_rate": 7.32e-05,
-      "loss": 0.9599,
+      "epoch": 1.77,
+      "learning_rate": 0.00011145251396648045,
+      "loss": 1.7034,
       "step": 317
     },
     {
-      "epoch": 12.72,
-      "learning_rate": 7.280000000000001e-05,
-      "loss": 0.8778,
+      "epoch": 1.78,
+      "learning_rate": 0.00011117318435754192,
+      "loss": 1.7301,
       "step": 318
     },
     {
-      "epoch": 12.76,
-      "learning_rate": 7.24e-05,
-      "loss": 0.8727,
+      "epoch": 1.78,
+      "learning_rate": 0.00011089385474860337,
+      "loss": 1.7084,
       "step": 319
     },
     {
-      "epoch": 12.8,
-      "learning_rate": 7.2e-05,
-      "loss": 1.0189,
+      "epoch": 1.79,
+      "learning_rate": 0.00011061452513966482,
+      "loss": 1.772,
       "step": 320
     },
     {
-      "epoch": 12.84,
-      "learning_rate": 7.16e-05,
-      "loss": 1.0543,
+      "epoch": 1.79,
+      "learning_rate": 0.00011033519553072626,
+      "loss": 1.5733,
       "step": 321
     },
     {
-      "epoch": 12.88,
-      "learning_rate": 7.12e-05,
-      "loss": 1.1282,
+      "epoch": 1.8,
+      "learning_rate": 0.00011005586592178771,
+      "loss": 1.6423,
       "step": 322
     },
     {
-      "epoch": 12.92,
-      "learning_rate": 7.08e-05,
-      "loss": 1.1018,
+      "epoch": 1.8,
+      "learning_rate": 0.00010977653631284917,
+      "loss": 1.5809,
       "step": 323
     },
     {
-      "epoch": 12.96,
-      "learning_rate": 7.04e-05,
-      "loss": 1.1827,
+      "epoch": 1.81,
+      "learning_rate": 0.00010949720670391062,
+      "loss": 1.6781,
       "step": 324
     },
     {
-      "epoch": 13.0,
-      "learning_rate": 7e-05,
-      "loss": 1.108,
+      "epoch": 1.82,
+      "learning_rate": 0.00010921787709497207,
+      "loss": 1.6788,
       "step": 325
     },
     {
-      "epoch": 13.04,
-      "learning_rate": 6.96e-05,
-      "loss": 0.9618,
+      "epoch": 1.82,
+      "learning_rate": 0.00010893854748603351,
+      "loss": 1.6346,
       "step": 326
     },
     {
-      "epoch": 13.08,
-      "learning_rate": 6.92e-05,
-      "loss": 1.0666,
+      "epoch": 1.83,
+      "learning_rate": 0.00010865921787709499,
+      "loss": 1.6634,
       "step": 327
     },
     {
-      "epoch": 13.12,
-      "learning_rate": 6.879999999999999e-05,
-      "loss": 0.9973,
+      "epoch": 1.83,
+      "learning_rate": 0.00010837988826815643,
+      "loss": 1.7561,
       "step": 328
     },
     {
-      "epoch": 13.16,
-      "learning_rate": 6.840000000000001e-05,
-      "loss": 1.0103,
+      "epoch": 1.84,
+      "learning_rate": 0.00010810055865921788,
+      "loss": 1.66,
       "step": 329
     },
     {
-      "epoch": 13.2,
-      "learning_rate": 6.800000000000001e-05,
-      "loss": 0.9974,
+      "epoch": 1.84,
+      "learning_rate": 0.00010782122905027934,
+      "loss": 1.7298,
       "step": 330
     },
     {
-      "epoch": 13.24,
-      "learning_rate": 6.76e-05,
-      "loss": 1.2283,
+      "epoch": 1.85,
+      "learning_rate": 0.00010754189944134079,
+      "loss": 1.6893,
       "step": 331
     },
     {
-      "epoch": 13.28,
-      "learning_rate": 6.720000000000001e-05,
-      "loss": 0.7485,
+      "epoch": 1.85,
+      "learning_rate": 0.00010726256983240224,
+      "loss": 1.7631,
       "step": 332
     },
     {
-      "epoch": 13.32,
-      "learning_rate": 6.680000000000001e-05,
-      "loss": 0.8072,
+      "epoch": 1.86,
+      "learning_rate": 0.00010698324022346368,
+      "loss": 1.6633,
       "step": 333
     },
     {
-      "epoch": 13.36,
-      "learning_rate": 6.64e-05,
-      "loss": 1.1106,
+      "epoch": 1.87,
+      "learning_rate": 0.00010670391061452513,
+      "loss": 1.5388,
       "step": 334
     },
     {
-      "epoch": 13.4,
-      "learning_rate": 6.6e-05,
-      "loss": 0.8216,
+      "epoch": 1.87,
+      "learning_rate": 0.00010642458100558659,
+      "loss": 1.6718,
       "step": 335
     },
     {
-      "epoch": 13.44,
-      "learning_rate": 6.560000000000001e-05,
-      "loss": 0.959,
+      "epoch": 1.88,
+      "learning_rate": 0.00010614525139664805,
+      "loss": 1.5536,
       "step": 336
     },
     {
-      "epoch": 13.48,
-      "learning_rate": 6.52e-05,
-      "loss": 1.0767,
+      "epoch": 1.88,
+      "learning_rate": 0.00010586592178770951,
+      "loss": 1.6483,
       "step": 337
     },
     {
-      "epoch": 13.52,
-      "learning_rate": 6.48e-05,
-      "loss": 1.0395,
+      "epoch": 1.89,
+      "learning_rate": 0.00010558659217877096,
+      "loss": 1.5774,
       "step": 338
     },
     {
-      "epoch": 13.56,
-      "learning_rate": 6.440000000000001e-05,
-      "loss": 0.9102,
+      "epoch": 1.89,
+      "learning_rate": 0.00010530726256983241,
+      "loss": 1.6366,
       "step": 339
     },
     {
-      "epoch": 13.6,
-      "learning_rate": 6.400000000000001e-05,
-      "loss": 0.8875,
+      "epoch": 1.9,
+      "learning_rate": 0.00010502793296089387,
+      "loss": 1.5567,
       "step": 340
     },
     {
-      "epoch": 13.64,
-      "learning_rate": 6.36e-05,
-      "loss": 1.0005,
+      "epoch": 1.91,
+      "learning_rate": 0.0001047486033519553,
+      "loss": 1.5323,
       "step": 341
     },
     {
-      "epoch": 13.68,
-      "learning_rate": 6.32e-05,
-      "loss": 0.9208,
+      "epoch": 1.91,
+      "learning_rate": 0.00010446927374301676,
+      "loss": 1.4608,
       "step": 342
     },
     {
-      "epoch": 13.72,
-      "learning_rate": 6.280000000000001e-05,
-      "loss": 0.8943,
+      "epoch": 1.92,
+      "learning_rate": 0.00010418994413407821,
+      "loss": 1.5933,
       "step": 343
     },
     {
-      "epoch": 13.76,
-      "learning_rate": 6.24e-05,
-      "loss": 0.8441,
+      "epoch": 1.92,
+      "learning_rate": 0.00010391061452513966,
+      "loss": 1.6625,
       "step": 344
     },
     {
-      "epoch": 13.8,
-      "learning_rate": 6.2e-05,
-      "loss": 0.9953,
+      "epoch": 1.93,
+      "learning_rate": 0.00010363128491620113,
+      "loss": 1.7236,
       "step": 345
     },
     {
-      "epoch": 13.84,
-      "learning_rate": 6.16e-05,
-      "loss": 0.796,
+      "epoch": 1.93,
+      "learning_rate": 0.00010335195530726258,
+      "loss": 1.759,
       "step": 346
     },
     {
-      "epoch": 13.88,
-      "learning_rate": 6.12e-05,
-      "loss": 1.0745,
+      "epoch": 1.94,
+      "learning_rate": 0.00010307262569832404,
+      "loss": 1.7248,
       "step": 347
     },
     {
-      "epoch": 13.92,
-      "learning_rate": 6.08e-05,
-      "loss": 0.9898,
+      "epoch": 1.94,
+      "learning_rate": 0.00010279329608938548,
+      "loss": 1.5144,
       "step": 348
     },
     {
-      "epoch": 13.96,
-      "learning_rate": 6.04e-05,
-      "loss": 0.9559,
+      "epoch": 1.95,
+      "learning_rate": 0.00010251396648044693,
+      "loss": 1.6905,
       "step": 349
     },
     {
-      "epoch": 14.0,
-      "learning_rate": 6e-05,
-      "loss": 0.8236,
+      "epoch": 1.96,
+      "learning_rate": 0.00010223463687150838,
+      "loss": 1.6119,
       "step": 350
     },
     {
-      "epoch": 14.04,
-      "learning_rate": 5.96e-05,
-      "loss": 0.7318,
+      "epoch": 1.96,
+      "learning_rate": 0.00010195530726256983,
+      "loss": 1.5464,
       "step": 351
     },
     {
-      "epoch": 14.08,
-      "learning_rate": 5.92e-05,
-      "loss": 0.8994,
+      "epoch": 1.97,
+      "learning_rate": 0.00010167597765363129,
+      "loss": 1.6901,
       "step": 352
     },
     {
-      "epoch": 14.12,
-      "learning_rate": 5.88e-05,
-      "loss": 0.9707,
+      "epoch": 1.97,
+      "learning_rate": 0.00010139664804469273,
+      "loss": 1.3511,
       "step": 353
     },
     {
-      "epoch": 14.16,
-      "learning_rate": 5.8399999999999997e-05,
-      "loss": 0.806,
+      "epoch": 1.98,
+      "learning_rate": 0.0001011173184357542,
+      "loss": 1.5434,
       "step": 354
     },
     {
-      "epoch": 14.2,
-      "learning_rate": 5.8e-05,
-      "loss": 1.0525,
+      "epoch": 1.98,
+      "learning_rate": 0.00010083798882681566,
+      "loss": 1.5891,
       "step": 355
     },
     {
-      "epoch": 14.24,
-      "learning_rate": 5.76e-05,
-      "loss": 0.7589,
+      "epoch": 1.99,
+      "learning_rate": 0.0001005586592178771,
+      "loss": 1.6658,
       "step": 356
     },
     {
-      "epoch": 14.28,
-      "learning_rate": 5.72e-05,
-      "loss": 0.7703,
+      "epoch": 1.99,
+      "learning_rate": 0.00010027932960893855,
+      "loss": 1.5657,
       "step": 357
     },
     {
-      "epoch": 14.32,
-      "learning_rate": 5.68e-05,
-      "loss": 0.9869,
+      "epoch": 2.0,
+      "learning_rate": 0.0001,
+      "loss": 1.7005,
       "step": 358
     },
     {
-      "epoch": 14.36,
-      "learning_rate": 5.6399999999999995e-05,
-      "loss": 0.9673,
+      "epoch": 2.01,
+      "learning_rate": 9.972067039106146e-05,
+      "loss": 1.4202,
       "step": 359
     },
     {
-      "epoch": 14.4,
-      "learning_rate": 5.6000000000000006e-05,
-      "loss": 0.9913,
+      "epoch": 2.01,
+      "learning_rate": 9.944134078212291e-05,
+      "loss": 1.5262,
       "step": 360
     },
     {
-      "epoch": 14.44,
-      "learning_rate": 5.560000000000001e-05,
-      "loss": 1.0219,
+      "epoch": 2.02,
+      "learning_rate": 9.916201117318436e-05,
+      "loss": 1.6323,
       "step": 361
     },
     {
-      "epoch": 14.48,
-      "learning_rate": 5.520000000000001e-05,
-      "loss": 0.8672,
+      "epoch": 2.02,
+      "learning_rate": 9.888268156424582e-05,
+      "loss": 1.5521,
       "step": 362
     },
     {
-      "epoch": 14.52,
-      "learning_rate": 5.4800000000000004e-05,
-      "loss": 1.0464,
+      "epoch": 2.03,
+      "learning_rate": 9.860335195530727e-05,
+      "loss": 1.5762,
       "step": 363
     },
     {
-      "epoch": 14.56,
-      "learning_rate": 5.440000000000001e-05,
-      "loss": 1.0109,
+      "epoch": 2.03,
+      "learning_rate": 9.832402234636872e-05,
+      "loss": 1.613,
       "step": 364
     },
     {
-      "epoch": 14.6,
-      "learning_rate": 5.4000000000000005e-05,
-      "loss": 0.9913,
+      "epoch": 2.04,
+      "learning_rate": 9.804469273743018e-05,
+      "loss": 1.4231,
       "step": 365
     },
     {
-      "epoch": 14.64,
-      "learning_rate": 5.360000000000001e-05,
-      "loss": 0.779,
+      "epoch": 2.04,
+      "learning_rate": 9.776536312849163e-05,
+      "loss": 1.5706,
       "step": 366
     },
     {
-      "epoch": 14.68,
-      "learning_rate": 5.3200000000000006e-05,
-      "loss": 0.8675,
+      "epoch": 2.05,
+      "learning_rate": 9.748603351955308e-05,
+      "loss": 1.5245,
       "step": 367
     },
     {
-      "epoch": 14.72,
-      "learning_rate": 5.28e-05,
-      "loss": 0.987,
+      "epoch": 2.06,
+      "learning_rate": 9.720670391061453e-05,
+      "loss": 1.4771,
       "step": 368
     },
     {
-      "epoch": 14.76,
-      "learning_rate": 5.2400000000000007e-05,
-      "loss": 0.741,
+      "epoch": 2.06,
+      "learning_rate": 9.692737430167597e-05,
+      "loss": 1.596,
       "step": 369
     },
     {
-      "epoch": 14.8,
-      "learning_rate": 5.2000000000000004e-05,
-      "loss": 0.9585,
+      "epoch": 2.07,
+      "learning_rate": 9.664804469273744e-05,
+      "loss": 1.537,
       "step": 370
     },
     {
-      "epoch": 14.84,
-      "learning_rate": 5.16e-05,
-      "loss": 0.8977,
+      "epoch": 2.07,
+      "learning_rate": 9.636871508379889e-05,
+      "loss": 1.4276,
       "step": 371
     },
     {
-      "epoch": 14.88,
-      "learning_rate": 5.1200000000000004e-05,
-      "loss": 0.7836,
+      "epoch": 2.08,
+      "learning_rate": 9.608938547486033e-05,
+      "loss": 1.4746,
       "step": 372
     },
     {
-      "epoch": 14.92,
-      "learning_rate": 5.08e-05,
-      "loss": 0.8461,
+      "epoch": 2.08,
+      "learning_rate": 9.581005586592178e-05,
+      "loss": 1.4374,
       "step": 373
     },
     {
-      "epoch": 14.96,
-      "learning_rate": 5.0400000000000005e-05,
-      "loss": 0.7531,
+      "epoch": 2.09,
+      "learning_rate": 9.553072625698325e-05,
+      "loss": 1.4704,
       "step": 374
     },
     {
-      "epoch": 15.0,
-      "learning_rate": 5e-05,
-      "loss": 0.8906,
+      "epoch": 2.09,
+      "learning_rate": 9.52513966480447e-05,
+      "loss": 1.5997,
       "step": 375
     },
     {
-      "epoch": 15.04,
-      "learning_rate": 4.96e-05,
-      "loss": 0.8793,
+      "epoch": 2.1,
+      "learning_rate": 9.497206703910614e-05,
+      "loss": 1.5034,
       "step": 376
     },
     {
-      "epoch": 15.08,
-      "learning_rate": 4.92e-05,
-      "loss": 0.8596,
+      "epoch": 2.11,
+      "learning_rate": 9.46927374301676e-05,
+      "loss": 1.6392,
       "step": 377
     },
     {
-      "epoch": 15.12,
-      "learning_rate": 4.88e-05,
-      "loss": 0.7947,
+      "epoch": 2.11,
+      "learning_rate": 9.441340782122905e-05,
+      "loss": 1.5611,
       "step": 378
     },
     {
-      "epoch": 15.16,
-      "learning_rate": 4.8400000000000004e-05,
-      "loss": 0.7976,
+      "epoch": 2.12,
+      "learning_rate": 9.413407821229052e-05,
+      "loss": 1.3384,
       "step": 379
     },
     {
-      "epoch": 15.2,
-      "learning_rate": 4.8e-05,
-      "loss": 0.9037,
+      "epoch": 2.12,
+      "learning_rate": 9.385474860335196e-05,
+      "loss": 1.5732,
       "step": 380
     },
     {
-      "epoch": 15.24,
-      "learning_rate": 4.76e-05,
-      "loss": 0.9863,
+      "epoch": 2.13,
+      "learning_rate": 9.357541899441341e-05,
+      "loss": 1.3874,
       "step": 381
     },
     {
-      "epoch": 15.28,
-      "learning_rate": 4.72e-05,
-      "loss": 0.7735,
+      "epoch": 2.13,
+      "learning_rate": 9.329608938547486e-05,
+      "loss": 1.4139,
       "step": 382
     },
     {
-      "epoch": 15.32,
-      "learning_rate": 4.6800000000000006e-05,
-      "loss": 0.6723,
+      "epoch": 2.14,
+      "learning_rate": 9.301675977653633e-05,
+      "loss": 1.5195,
       "step": 383
     },
     {
-      "epoch": 15.36,
-      "learning_rate": 4.64e-05,
-      "loss": 0.7002,
+      "epoch": 2.15,
+      "learning_rate": 9.273743016759777e-05,
+      "loss": 1.4371,
       "step": 384
     },
     {
-      "epoch": 15.4,
-      "learning_rate": 4.600000000000001e-05,
-      "loss": 0.9479,
+      "epoch": 2.15,
+      "learning_rate": 9.245810055865922e-05,
+      "loss": 1.4411,
       "step": 385
     },
     {
-      "epoch": 15.44,
-      "learning_rate": 4.5600000000000004e-05,
-      "loss": 0.8159,
+      "epoch": 2.16,
+      "learning_rate": 9.217877094972067e-05,
+      "loss": 1.5214,
       "step": 386
     },
     {
-      "epoch": 15.48,
-      "learning_rate": 4.52e-05,
-      "loss": 0.7954,
+      "epoch": 2.16,
+      "learning_rate": 9.189944134078213e-05,
+      "loss": 1.4971,
       "step": 387
     },
     {
-      "epoch": 15.52,
-      "learning_rate": 4.4800000000000005e-05,
-      "loss": 0.8016,
+      "epoch": 2.17,
+      "learning_rate": 9.162011173184358e-05,
+      "loss": 1.3453,
       "step": 388
     },
     {
-      "epoch": 15.56,
-      "learning_rate": 4.44e-05,
-      "loss": 0.7995,
+      "epoch": 2.17,
+      "learning_rate": 9.134078212290503e-05,
+      "loss": 1.394,
       "step": 389
     },
     {
-      "epoch": 15.6,
-      "learning_rate": 4.4000000000000006e-05,
-      "loss": 0.8243,
+      "epoch": 2.18,
+      "learning_rate": 9.106145251396648e-05,
+      "loss": 1.5058,
       "step": 390
     },
     {
-      "epoch": 15.64,
-      "learning_rate": 4.36e-05,
-      "loss": 0.8335,
+      "epoch": 2.18,
+      "learning_rate": 9.078212290502794e-05,
+      "loss": 1.4855,
       "step": 391
     },
     {
-      "epoch": 15.68,
-      "learning_rate": 4.32e-05,
-      "loss": 1.001,
+      "epoch": 2.19,
+      "learning_rate": 9.050279329608939e-05,
+      "loss": 1.4647,
       "step": 392
     },
     {
-      "epoch": 15.72,
-      "learning_rate": 4.2800000000000004e-05,
-      "loss": 0.9385,
+      "epoch": 2.2,
+      "learning_rate": 9.022346368715084e-05,
+      "loss": 1.3435,
       "step": 393
     },
     {
-      "epoch": 15.76,
-      "learning_rate": 4.24e-05,
-      "loss": 0.8796,
+      "epoch": 2.2,
+      "learning_rate": 8.99441340782123e-05,
+      "loss": 1.5815,
       "step": 394
     },
     {
-      "epoch": 15.8,
-      "learning_rate": 4.2e-05,
-      "loss": 0.98,
+      "epoch": 2.21,
+      "learning_rate": 8.966480446927375e-05,
+      "loss": 1.4742,
       "step": 395
     },
     {
-      "epoch": 15.84,
-      "learning_rate": 4.16e-05,
-      "loss": 0.7547,
+      "epoch": 2.21,
+      "learning_rate": 8.938547486033519e-05,
+      "loss": 1.5389,
       "step": 396
     },
     {
-      "epoch": 15.88,
-      "learning_rate": 4.12e-05,
-      "loss": 0.7943,
+      "epoch": 2.22,
+      "learning_rate": 8.910614525139666e-05,
+      "loss": 1.384,
       "step": 397
     },
     {
-      "epoch": 15.92,
-      "learning_rate": 4.08e-05,
-      "loss": 0.8135,
+      "epoch": 2.22,
+      "learning_rate": 8.882681564245811e-05,
+      "loss": 1.3967,
       "step": 398
     },
     {
-      "epoch": 15.96,
-      "learning_rate": 4.0400000000000006e-05,
-      "loss": 0.87,
+      "epoch": 2.23,
+      "learning_rate": 8.854748603351956e-05,
+      "loss": 1.442,
       "step": 399
     },
     {
-      "epoch": 16.0,
-      "learning_rate": 4e-05,
-      "loss": 0.8818,
+      "epoch": 2.23,
+      "learning_rate": 8.8268156424581e-05,
+      "loss": 1.396,
       "step": 400
     }
   ],
   "logging_steps": 1,
-  "max_steps": 500,
-  "num_train_epochs": 20,
+  "max_steps": 716,
+  "num_train_epochs": 4,
   "save_steps": 100,
-  "total_flos": 1.361597073887232e+17,
+  "total_flos": 2.056923590572032e+17,
   "trial_name": null,
   "trial_params": null
 }
diff --git a/checkpoint-400/training_args.bin b/checkpoint-400/training_args.bin
index 4de6572a838c337c9990635a9406ebf46c0ec336..c8672c716e925d0028b4938db147703f58656ff7 100644
--- a/checkpoint-400/training_args.bin
+++ b/checkpoint-400/training_args.bin
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ef74b31950ae6c8955316bed48c343fb06cda0cb6a8a54ca46ca3cb681c8736
+oid sha256:188ae1c421cc0c6435d1f71d8d3423ac4abc7dba0e6fc2efcbc4dbe77c741317
 size 4027
diff --git a/checkpoint-500/README.md b/checkpoint-500/README.md
index 08371015f02382e6fcba318f4aaea54ae52cd3c4..2f257a448caef1c59022426ad3ec9ba80acb3821 100644
--- a/checkpoint-500/README.md
+++ b/checkpoint-500/README.md
@@ -4,6 +4,30 @@ library_name: peft
 ## Training procedure
 
 
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: True
+- load_in_4bit: False
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: True
+- load_in_4bit: False
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+
 The following `bitsandbytes` quantization config was used during training:
 - quant_method: bitsandbytes
 - load_in_8bit: True
@@ -29,6 +53,8 @@ The following `bitsandbytes` quantization config was used during training:
 - bnb_4bit_compute_dtype: float32
 ### Framework versions
 
+- PEFT 0.6.0.dev0
+- PEFT 0.6.0.dev0
 - PEFT 0.6.0.dev0
 
 - PEFT 0.6.0.dev0
diff --git a/checkpoint-500/adapter_model.bin b/checkpoint-500/adapter_model.bin
index c591858f8c3078c2a2cb20f492f65b893f93f7e6..6198683070fc9df0fa08204fb385a9c9cf4fb8a2 100644
--- a/checkpoint-500/adapter_model.bin
+++ b/checkpoint-500/adapter_model.bin
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a125cc125172a0c45ae8a435cdae72b0c657f9b899e914953f9df21478011a8
+oid sha256:fbc5f8a93e505087cecc049ff476019df96de3cba21db5d67029ade06c844216
 size 39409357
diff --git a/checkpoint-500/optimizer.pt b/checkpoint-500/optimizer.pt
index 77340f17ffa5f66b1643f14304ad12b7af091dbc..dec2baaffc2c1b79896eb5f10b68cc8630ce5592 100644
--- a/checkpoint-500/optimizer.pt
+++ b/checkpoint-500/optimizer.pt
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20490071892c8d3160a456d6e86f6905a6d5f8dfd4a5099f884f3c570dfd5be2
+oid sha256:cbab141106d84467be5a7a978a93b8492dd00bcc4a497115fb4124bf8beaa046
 size 78844421
diff --git a/checkpoint-500/rng_state.pth b/checkpoint-500/rng_state.pth
index b10130f910d9e6a0f56a41b5d4b3e6c851381a72..e0df6592e27bef84a4beb9293e7b49666a4d652e 100644
--- a/checkpoint-500/rng_state.pth
+++ b/checkpoint-500/rng_state.pth
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3464e9c253485ee0e45ad721cb8a719f3a43712377f5b9e04d190fe903bbfbe
+oid sha256:7508d4b8dd267de5cc58e972da25236687927651336a28f292c92f7f23951475
 size 14575
diff --git a/checkpoint-500/scheduler.pt b/checkpoint-500/scheduler.pt
index b29b9b24abffbaf84031523df986bd3982387246..53ba5c95b7d8f86bbe40d20004a07e2e74748d22 100644
--- a/checkpoint-500/scheduler.pt
+++ b/checkpoint-500/scheduler.pt
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:becc6ce1d910c1484b60d785c856d3d18b0420d3e43c97ef16af3312337b9491
+oid sha256:b841ff782e5772fca220707441f952d8fcec6aefcd65e69bf2fe08db08edfce1
 size 627
diff --git a/checkpoint-500/tokenizer.json b/checkpoint-500/tokenizer.json
index dbf002cafbd4818dcff2abc9156c088d681b4533..673c31abdeadf6576c3c754df86459e1ad64e207 100644
--- a/checkpoint-500/tokenizer.json
+++ b/checkpoint-500/tokenizer.json
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17a208233d2ee8d8c83b23bc214df737c44806a1919f444e89b31e586cd956ba
-size 14500471
+oid sha256:85b00d7db4df5df2e3f01cacc3feda246002a672f3356eec7f4b04a22eb0dfbe
+size 14500570
diff --git a/checkpoint-500/trainer_state.json b/checkpoint-500/trainer_state.json
index 581f1e94b337ced6715385f7977bf3cafe178e58..121cade410f9ee4e2a798857772481a6700d2a71 100644
--- a/checkpoint-500/trainer_state.json
+++ b/checkpoint-500/trainer_state.json
@@ -1,7 +1,7 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 20.0,
+  "epoch": 2.793296089385475,
   "eval_steps": 500,
   "global_step": 500,
   "is_hyper_param_search": false,
@@ -9,3011 +9,3011 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.04,
-      "learning_rate": 0.0001996,
-      "loss": 2.4683,
+      "epoch": 0.01,
+      "learning_rate": 0.00019972067039106145,
+      "loss": 2.6443,
       "step": 1
     },
     {
-      "epoch": 0.08,
-      "learning_rate": 0.00019920000000000002,
-      "loss": 2.2023,
+      "epoch": 0.01,
+      "learning_rate": 0.00019944134078212292,
+      "loss": 2.4104,
       "step": 2
     },
     {
-      "epoch": 0.12,
-      "learning_rate": 0.0001988,
-      "loss": 2.3039,
+      "epoch": 0.02,
+      "learning_rate": 0.00019916201117318435,
+      "loss": 2.4975,
       "step": 3
     },
     {
-      "epoch": 0.16,
-      "learning_rate": 0.0001984,
-      "loss": 2.1855,
+      "epoch": 0.02,
+      "learning_rate": 0.00019888268156424582,
+      "loss": 2.3513,
       "step": 4
     },
     {
-      "epoch": 0.2,
-      "learning_rate": 0.00019800000000000002,
-      "loss": 2.328,
+      "epoch": 0.03,
+      "learning_rate": 0.0001986033519553073,
+      "loss": 2.4274,
       "step": 5
     },
     {
-      "epoch": 0.24,
-      "learning_rate": 0.0001976,
-      "loss": 2.3407,
+      "epoch": 0.03,
+      "learning_rate": 0.00019832402234636873,
+      "loss": 2.3628,
       "step": 6
     },
     {
-      "epoch": 0.28,
-      "learning_rate": 0.0001972,
-      "loss": 2.3432,
+      "epoch": 0.04,
+      "learning_rate": 0.0001980446927374302,
+      "loss": 2.3567,
       "step": 7
     },
     {
-      "epoch": 0.32,
-      "learning_rate": 0.0001968,
-      "loss": 2.2333,
+      "epoch": 0.04,
+      "learning_rate": 0.00019776536312849163,
+      "loss": 2.4121,
       "step": 8
     },
     {
-      "epoch": 0.36,
-      "learning_rate": 0.0001964,
-      "loss": 2.1761,
+      "epoch": 0.05,
+      "learning_rate": 0.00019748603351955307,
+      "loss": 2.4033,
       "step": 9
     },
     {
-      "epoch": 0.4,
-      "learning_rate": 0.000196,
-      "loss": 2.1473,
+      "epoch": 0.06,
+      "learning_rate": 0.00019720670391061454,
+      "loss": 2.2805,
       "step": 10
     },
     {
-      "epoch": 0.44,
-      "learning_rate": 0.0001956,
-      "loss": 2.2076,
+      "epoch": 0.06,
+      "learning_rate": 0.00019692737430167598,
+      "loss": 2.2639,
       "step": 11
     },
     {
-      "epoch": 0.48,
-      "learning_rate": 0.0001952,
-      "loss": 2.1925,
+      "epoch": 0.07,
+      "learning_rate": 0.00019664804469273744,
+      "loss": 2.2724,
       "step": 12
     },
     {
-      "epoch": 0.52,
-      "learning_rate": 0.0001948,
-      "loss": 2.1694,
+      "epoch": 0.07,
+      "learning_rate": 0.00019636871508379888,
+      "loss": 2.332,
       "step": 13
     },
     {
-      "epoch": 0.56,
-      "learning_rate": 0.0001944,
-      "loss": 2.1056,
+      "epoch": 0.08,
+      "learning_rate": 0.00019608938547486035,
+      "loss": 2.2261,
       "step": 14
     },
     {
-      "epoch": 0.6,
-      "learning_rate": 0.000194,
-      "loss": 2.2426,
+      "epoch": 0.08,
+      "learning_rate": 0.00019581005586592182,
+      "loss": 2.2208,
       "step": 15
     },
     {
-      "epoch": 0.64,
-      "learning_rate": 0.00019360000000000002,
-      "loss": 2.2635,
+      "epoch": 0.09,
+      "learning_rate": 0.00019553072625698326,
+      "loss": 2.3351,
       "step": 16
     },
     {
-      "epoch": 0.68,
-      "learning_rate": 0.0001932,
-      "loss": 2.251,
+      "epoch": 0.09,
+      "learning_rate": 0.0001952513966480447,
+      "loss": 2.2475,
       "step": 17
     },
     {
-      "epoch": 0.72,
-      "learning_rate": 0.0001928,
-      "loss": 2.224,
+      "epoch": 0.1,
+      "learning_rate": 0.00019497206703910616,
+      "loss": 2.3283,
       "step": 18
     },
     {
-      "epoch": 0.76,
-      "learning_rate": 0.00019240000000000001,
-      "loss": 2.1848,
+      "epoch": 0.11,
+      "learning_rate": 0.0001946927374301676,
+      "loss": 2.1346,
       "step": 19
     },
     {
-      "epoch": 0.8,
-      "learning_rate": 0.000192,
-      "loss": 2.1341,
+      "epoch": 0.11,
+      "learning_rate": 0.00019441340782122907,
+      "loss": 2.131,
       "step": 20
     },
     {
-      "epoch": 0.84,
-      "learning_rate": 0.0001916,
-      "loss": 2.126,
+      "epoch": 0.12,
+      "learning_rate": 0.0001941340782122905,
+      "loss": 2.1718,
       "step": 21
     },
     {
-      "epoch": 0.88,
-      "learning_rate": 0.0001912,
-      "loss": 2.0959,
+      "epoch": 0.12,
+      "learning_rate": 0.00019385474860335195,
+      "loss": 2.2446,
       "step": 22
     },
     {
-      "epoch": 0.92,
-      "learning_rate": 0.0001908,
-      "loss": 2.2446,
+      "epoch": 0.13,
+      "learning_rate": 0.0001935754189944134,
+      "loss": 2.306,
       "step": 23
     },
     {
-      "epoch": 0.96,
-      "learning_rate": 0.0001904,
-      "loss": 1.9448,
+      "epoch": 0.13,
+      "learning_rate": 0.00019329608938547488,
+      "loss": 2.1908,
       "step": 24
     },
     {
-      "epoch": 1.0,
-      "learning_rate": 0.00019,
-      "loss": 2.0939,
+      "epoch": 0.14,
+      "learning_rate": 0.00019301675977653632,
+      "loss": 2.2844,
       "step": 25
     },
     {
-      "epoch": 1.04,
-      "learning_rate": 0.0001896,
-      "loss": 2.1247,
+      "epoch": 0.15,
+      "learning_rate": 0.00019273743016759779,
+      "loss": 2.2235,
       "step": 26
     },
     {
-      "epoch": 1.08,
-      "learning_rate": 0.0001892,
-      "loss": 1.9417,
+      "epoch": 0.15,
+      "learning_rate": 0.00019245810055865922,
+      "loss": 2.1842,
       "step": 27
     },
     {
-      "epoch": 1.12,
-      "learning_rate": 0.0001888,
-      "loss": 2.105,
+      "epoch": 0.16,
+      "learning_rate": 0.00019217877094972066,
+      "loss": 2.2675,
       "step": 28
     },
     {
-      "epoch": 1.16,
-      "learning_rate": 0.0001884,
-      "loss": 2.1595,
+      "epoch": 0.16,
+      "learning_rate": 0.00019189944134078213,
+      "loss": 2.2532,
       "step": 29
     },
     {
-      "epoch": 1.2,
-      "learning_rate": 0.000188,
-      "loss": 2.2009,
+      "epoch": 0.17,
+      "learning_rate": 0.00019162011173184357,
+      "loss": 2.1788,
       "step": 30
     },
     {
-      "epoch": 1.24,
-      "learning_rate": 0.0001876,
-      "loss": 2.0784,
+      "epoch": 0.17,
+      "learning_rate": 0.00019134078212290504,
+      "loss": 2.2494,
       "step": 31
     },
     {
-      "epoch": 1.28,
-      "learning_rate": 0.00018720000000000002,
-      "loss": 2.2173,
+      "epoch": 0.18,
+      "learning_rate": 0.0001910614525139665,
+      "loss": 2.1995,
       "step": 32
     },
     {
-      "epoch": 1.32,
-      "learning_rate": 0.00018680000000000001,
-      "loss": 2.1185,
+      "epoch": 0.18,
+      "learning_rate": 0.00019078212290502794,
+      "loss": 2.1451,
       "step": 33
     },
     {
-      "epoch": 1.36,
-      "learning_rate": 0.00018640000000000003,
-      "loss": 1.988,
+      "epoch": 0.19,
+      "learning_rate": 0.0001905027932960894,
+      "loss": 2.223,
       "step": 34
     },
     {
-      "epoch": 1.4,
-      "learning_rate": 0.00018600000000000002,
-      "loss": 1.9493,
+      "epoch": 0.2,
+      "learning_rate": 0.00019022346368715085,
+      "loss": 2.2854,
       "step": 35
     },
     {
-      "epoch": 1.44,
-      "learning_rate": 0.0001856,
-      "loss": 1.9947,
+      "epoch": 0.2,
+      "learning_rate": 0.0001899441340782123,
+      "loss": 2.2265,
       "step": 36
     },
     {
-      "epoch": 1.48,
-      "learning_rate": 0.00018520000000000003,
-      "loss": 2.0506,
+      "epoch": 0.21,
+      "learning_rate": 0.00018966480446927375,
+      "loss": 2.1214,
       "step": 37
     },
     {
-      "epoch": 1.52,
-      "learning_rate": 0.00018480000000000002,
-      "loss": 2.0829,
+      "epoch": 0.21,
+      "learning_rate": 0.0001893854748603352,
+      "loss": 2.1898,
       "step": 38
     },
     {
-      "epoch": 1.56,
-      "learning_rate": 0.0001844,
-      "loss": 2.1455,
+      "epoch": 0.22,
+      "learning_rate": 0.00018910614525139666,
+      "loss": 2.1974,
       "step": 39
     },
     {
-      "epoch": 1.6,
-      "learning_rate": 0.00018400000000000003,
-      "loss": 2.0304,
+      "epoch": 0.22,
+      "learning_rate": 0.0001888268156424581,
+      "loss": 2.2259,
       "step": 40
     },
     {
-      "epoch": 1.64,
-      "learning_rate": 0.00018360000000000002,
-      "loss": 2.006,
+      "epoch": 0.23,
+      "learning_rate": 0.00018854748603351957,
+      "loss": 2.2094,
       "step": 41
     },
     {
-      "epoch": 1.68,
-      "learning_rate": 0.0001832,
-      "loss": 2.1759,
+      "epoch": 0.23,
+      "learning_rate": 0.00018826815642458103,
+      "loss": 2.1731,
       "step": 42
     },
     {
-      "epoch": 1.72,
-      "learning_rate": 0.00018280000000000003,
-      "loss": 2.0093,
+      "epoch": 0.24,
+      "learning_rate": 0.00018798882681564247,
+      "loss": 2.2373,
       "step": 43
     },
     {
-      "epoch": 1.76,
-      "learning_rate": 0.00018240000000000002,
-      "loss": 2.0683,
+      "epoch": 0.25,
+      "learning_rate": 0.0001877094972067039,
+      "loss": 2.2295,
       "step": 44
     },
     {
-      "epoch": 1.8,
-      "learning_rate": 0.000182,
-      "loss": 2.1352,
+      "epoch": 0.25,
+      "learning_rate": 0.00018743016759776538,
+      "loss": 2.1947,
       "step": 45
     },
     {
-      "epoch": 1.84,
-      "learning_rate": 0.00018160000000000002,
-      "loss": 1.9736,
+      "epoch": 0.26,
+      "learning_rate": 0.00018715083798882682,
+      "loss": 2.2115,
       "step": 46
     },
     {
-      "epoch": 1.88,
-      "learning_rate": 0.0001812,
-      "loss": 1.9631,
+      "epoch": 0.26,
+      "learning_rate": 0.00018687150837988828,
+      "loss": 2.1224,
       "step": 47
     },
     {
-      "epoch": 1.92,
-      "learning_rate": 0.0001808,
-      "loss": 2.1024,
+      "epoch": 0.27,
+      "learning_rate": 0.00018659217877094972,
+      "loss": 2.2137,
       "step": 48
     },
     {
-      "epoch": 1.96,
-      "learning_rate": 0.00018040000000000002,
-      "loss": 1.9895,
+      "epoch": 0.27,
+      "learning_rate": 0.00018631284916201116,
+      "loss": 2.2338,
       "step": 49
     },
     {
-      "epoch": 2.0,
-      "learning_rate": 0.00018,
-      "loss": 2.0067,
+      "epoch": 0.28,
+      "learning_rate": 0.00018603351955307266,
+      "loss": 2.1298,
       "step": 50
     },
     {
-      "epoch": 2.04,
-      "learning_rate": 0.0001796,
-      "loss": 2.0509,
+      "epoch": 0.28,
+      "learning_rate": 0.0001857541899441341,
+      "loss": 2.0883,
       "step": 51
     },
     {
-      "epoch": 2.08,
-      "learning_rate": 0.00017920000000000002,
-      "loss": 1.8795,
+      "epoch": 0.29,
+      "learning_rate": 0.00018547486033519553,
+      "loss": 2.1216,
       "step": 52
     },
     {
-      "epoch": 2.12,
-      "learning_rate": 0.0001788,
-      "loss": 2.0633,
+      "epoch": 0.3,
+      "learning_rate": 0.000185195530726257,
+      "loss": 2.2112,
       "step": 53
     },
     {
-      "epoch": 2.16,
-      "learning_rate": 0.0001784,
-      "loss": 1.9998,
+      "epoch": 0.3,
+      "learning_rate": 0.00018491620111731844,
+      "loss": 2.1224,
       "step": 54
     },
     {
-      "epoch": 2.2,
-      "learning_rate": 0.00017800000000000002,
-      "loss": 2.0675,
+      "epoch": 0.31,
+      "learning_rate": 0.0001846368715083799,
+      "loss": 2.2375,
       "step": 55
     },
     {
-      "epoch": 2.24,
-      "learning_rate": 0.0001776,
-      "loss": 2.0129,
+      "epoch": 0.31,
+      "learning_rate": 0.00018435754189944135,
+      "loss": 2.2235,
       "step": 56
     },
     {
-      "epoch": 2.28,
-      "learning_rate": 0.0001772,
-      "loss": 1.9302,
+      "epoch": 0.32,
+      "learning_rate": 0.00018407821229050279,
+      "loss": 2.1682,
       "step": 57
     },
     {
-      "epoch": 2.32,
-      "learning_rate": 0.00017680000000000001,
-      "loss": 2.0472,
+      "epoch": 0.32,
+      "learning_rate": 0.00018379888268156425,
+      "loss": 2.2077,
       "step": 58
     },
     {
-      "epoch": 2.36,
-      "learning_rate": 0.0001764,
-      "loss": 2.0031,
+      "epoch": 0.33,
+      "learning_rate": 0.00018351955307262572,
+      "loss": 2.1596,
       "step": 59
     },
     {
-      "epoch": 2.4,
-      "learning_rate": 0.00017600000000000002,
-      "loss": 2.0231,
+      "epoch": 0.34,
+      "learning_rate": 0.00018324022346368716,
+      "loss": 2.1311,
       "step": 60
     },
     {
-      "epoch": 2.44,
-      "learning_rate": 0.0001756,
-      "loss": 2.0192,
+      "epoch": 0.34,
+      "learning_rate": 0.00018296089385474862,
+      "loss": 2.1333,
       "step": 61
     },
     {
-      "epoch": 2.48,
-      "learning_rate": 0.0001752,
-      "loss": 2.1336,
+      "epoch": 0.35,
+      "learning_rate": 0.00018268156424581006,
+      "loss": 2.0901,
       "step": 62
     },
     {
-      "epoch": 2.52,
-      "learning_rate": 0.00017480000000000002,
-      "loss": 1.7753,
+      "epoch": 0.35,
+      "learning_rate": 0.00018240223463687153,
+      "loss": 2.1971,
       "step": 63
     },
     {
-      "epoch": 2.56,
-      "learning_rate": 0.0001744,
-      "loss": 2.0274,
+      "epoch": 0.36,
+      "learning_rate": 0.00018212290502793297,
+      "loss": 2.2602,
       "step": 64
     },
     {
-      "epoch": 2.6,
-      "learning_rate": 0.000174,
-      "loss": 1.8893,
+      "epoch": 0.36,
+      "learning_rate": 0.0001818435754189944,
+      "loss": 2.2194,
       "step": 65
     },
     {
-      "epoch": 2.64,
-      "learning_rate": 0.00017360000000000002,
-      "loss": 2.0341,
+      "epoch": 0.37,
+      "learning_rate": 0.00018156424581005588,
+      "loss": 2.1218,
       "step": 66
     },
     {
-      "epoch": 2.68,
-      "learning_rate": 0.0001732,
-      "loss": 2.1081,
+      "epoch": 0.37,
+      "learning_rate": 0.00018128491620111731,
+      "loss": 2.2049,
       "step": 67
     },
     {
-      "epoch": 2.72,
-      "learning_rate": 0.0001728,
-      "loss": 1.9463,
+      "epoch": 0.38,
+      "learning_rate": 0.00018100558659217878,
+      "loss": 2.1521,
       "step": 68
     },
     {
-      "epoch": 2.76,
-      "learning_rate": 0.00017240000000000002,
-      "loss": 2.0607,
+      "epoch": 0.39,
+      "learning_rate": 0.00018072625698324025,
+      "loss": 2.112,
       "step": 69
     },
     {
-      "epoch": 2.8,
-      "learning_rate": 0.000172,
-      "loss": 1.9803,
+      "epoch": 0.39,
+      "learning_rate": 0.0001804469273743017,
+      "loss": 2.1906,
       "step": 70
     },
     {
-      "epoch": 2.84,
-      "learning_rate": 0.0001716,
-      "loss": 1.7663,
+      "epoch": 0.4,
+      "learning_rate": 0.00018016759776536313,
+      "loss": 2.1717,
       "step": 71
     },
     {
-      "epoch": 2.88,
-      "learning_rate": 0.00017120000000000001,
-      "loss": 2.1116,
+      "epoch": 0.4,
+      "learning_rate": 0.0001798882681564246,
+      "loss": 2.0712,
       "step": 72
     },
     {
-      "epoch": 2.92,
-      "learning_rate": 0.0001708,
-      "loss": 1.9039,
+      "epoch": 0.41,
+      "learning_rate": 0.00017960893854748603,
+      "loss": 2.141,
       "step": 73
     },
     {
-      "epoch": 2.96,
-      "learning_rate": 0.0001704,
-      "loss": 2.049,
+      "epoch": 0.41,
+      "learning_rate": 0.0001793296089385475,
+      "loss": 2.0656,
       "step": 74
     },
     {
-      "epoch": 3.0,
-      "learning_rate": 0.00017,
-      "loss": 1.991,
+      "epoch": 0.42,
+      "learning_rate": 0.00017905027932960894,
+      "loss": 2.1125,
       "step": 75
     },
     {
-      "epoch": 3.04,
-      "learning_rate": 0.0001696,
-      "loss": 1.8755,
+      "epoch": 0.42,
+      "learning_rate": 0.00017877094972067038,
+      "loss": 2.0869,
       "step": 76
     },
     {
-      "epoch": 3.08,
-      "learning_rate": 0.0001692,
-      "loss": 2.0367,
+      "epoch": 0.43,
+      "learning_rate": 0.00017849162011173187,
+      "loss": 2.2478,
       "step": 77
     },
     {
-      "epoch": 3.12,
-      "learning_rate": 0.0001688,
-      "loss": 1.9959,
+      "epoch": 0.44,
+      "learning_rate": 0.0001782122905027933,
+      "loss": 2.1535,
       "step": 78
     },
     {
-      "epoch": 3.16,
-      "learning_rate": 0.0001684,
-      "loss": 1.8051,
+      "epoch": 0.44,
+      "learning_rate": 0.00017793296089385475,
+      "loss": 2.1927,
       "step": 79
     },
     {
-      "epoch": 3.2,
-      "learning_rate": 0.000168,
-      "loss": 2.0446,
+      "epoch": 0.45,
+      "learning_rate": 0.00017765363128491622,
+      "loss": 2.1213,
       "step": 80
     },
     {
-      "epoch": 3.24,
-      "learning_rate": 0.0001676,
-      "loss": 1.7873,
+      "epoch": 0.45,
+      "learning_rate": 0.00017737430167597766,
+      "loss": 2.0981,
       "step": 81
     },
     {
-      "epoch": 3.28,
-      "learning_rate": 0.0001672,
-      "loss": 1.9264,
+      "epoch": 0.46,
+      "learning_rate": 0.00017709497206703912,
+      "loss": 2.1828,
       "step": 82
     },
     {
-      "epoch": 3.32,
-      "learning_rate": 0.0001668,
-      "loss": 1.8595,
+      "epoch": 0.46,
+      "learning_rate": 0.00017681564245810056,
+      "loss": 2.0562,
       "step": 83
     },
     {
-      "epoch": 3.36,
-      "learning_rate": 0.0001664,
-      "loss": 1.9992,
+      "epoch": 0.47,
+      "learning_rate": 0.000176536312849162,
+      "loss": 2.1334,
       "step": 84
     },
     {
-      "epoch": 3.4,
-      "learning_rate": 0.000166,
-      "loss": 1.8783,
+      "epoch": 0.47,
+      "learning_rate": 0.00017625698324022347,
+      "loss": 2.1225,
       "step": 85
     },
     {
-      "epoch": 3.44,
-      "learning_rate": 0.0001656,
-      "loss": 2.0216,
+      "epoch": 0.48,
+      "learning_rate": 0.00017597765363128493,
+      "loss": 2.2098,
       "step": 86
     },
     {
-      "epoch": 3.48,
-      "learning_rate": 0.0001652,
-      "loss": 1.947,
+      "epoch": 0.49,
+      "learning_rate": 0.00017569832402234637,
+      "loss": 2.1519,
       "step": 87
     },
     {
-      "epoch": 3.52,
-      "learning_rate": 0.0001648,
-      "loss": 1.9554,
+      "epoch": 0.49,
+      "learning_rate": 0.00017541899441340784,
+      "loss": 2.1132,
       "step": 88
     },
     {
-      "epoch": 3.56,
-      "learning_rate": 0.0001644,
-      "loss": 1.8563,
+      "epoch": 0.5,
+      "learning_rate": 0.00017513966480446928,
+      "loss": 2.0333,
       "step": 89
     },
     {
-      "epoch": 3.6,
-      "learning_rate": 0.000164,
-      "loss": 1.7795,
+      "epoch": 0.5,
+      "learning_rate": 0.00017486033519553075,
+      "loss": 2.2764,
       "step": 90
     },
     {
-      "epoch": 3.64,
-      "learning_rate": 0.0001636,
-      "loss": 1.9347,
+      "epoch": 0.51,
+      "learning_rate": 0.00017458100558659218,
+      "loss": 2.1838,
       "step": 91
     },
     {
-      "epoch": 3.68,
-      "learning_rate": 0.0001632,
-      "loss": 2.0078,
+      "epoch": 0.51,
+      "learning_rate": 0.00017430167597765362,
+      "loss": 2.1386,
       "step": 92
     },
     {
-      "epoch": 3.72,
-      "learning_rate": 0.0001628,
-      "loss": 1.9964,
+      "epoch": 0.52,
+      "learning_rate": 0.0001740223463687151,
+      "loss": 2.1034,
       "step": 93
     },
     {
-      "epoch": 3.76,
-      "learning_rate": 0.00016240000000000002,
-      "loss": 1.9004,
+      "epoch": 0.53,
+      "learning_rate": 0.00017374301675977656,
+      "loss": 2.0346,
       "step": 94
     },
     {
-      "epoch": 3.8,
-      "learning_rate": 0.000162,
-      "loss": 1.9446,
+      "epoch": 0.53,
+      "learning_rate": 0.000173463687150838,
+      "loss": 2.0274,
       "step": 95
     },
     {
-      "epoch": 3.84,
-      "learning_rate": 0.00016160000000000002,
-      "loss": 1.8857,
+      "epoch": 0.54,
+      "learning_rate": 0.00017318435754189946,
+      "loss": 2.1036,
       "step": 96
     },
     {
-      "epoch": 3.88,
-      "learning_rate": 0.00016120000000000002,
-      "loss": 1.8797,
+      "epoch": 0.54,
+      "learning_rate": 0.0001729050279329609,
+      "loss": 2.1208,
       "step": 97
     },
     {
-      "epoch": 3.92,
-      "learning_rate": 0.0001608,
-      "loss": 1.7643,
+      "epoch": 0.55,
+      "learning_rate": 0.00017262569832402237,
+      "loss": 2.0572,
       "step": 98
     },
     {
-      "epoch": 3.96,
-      "learning_rate": 0.00016040000000000002,
-      "loss": 1.9724,
+      "epoch": 0.55,
+      "learning_rate": 0.0001723463687150838,
+      "loss": 2.1702,
       "step": 99
     },
     {
-      "epoch": 4.0,
-      "learning_rate": 0.00016,
-      "loss": 1.9058,
+      "epoch": 0.56,
+      "learning_rate": 0.00017206703910614525,
+      "loss": 2.1302,
       "step": 100
     },
     {
-      "epoch": 4.04,
-      "learning_rate": 0.0001596,
-      "loss": 1.8663,
+      "epoch": 0.56,
+      "learning_rate": 0.0001717877094972067,
+      "loss": 2.0175,
       "step": 101
     },
     {
-      "epoch": 4.08,
-      "learning_rate": 0.00015920000000000002,
-      "loss": 1.8457,
+      "epoch": 0.57,
+      "learning_rate": 0.00017150837988826815,
+      "loss": 2.1006,
       "step": 102
     },
     {
-      "epoch": 4.12,
-      "learning_rate": 0.0001588,
-      "loss": 1.8394,
+      "epoch": 0.58,
+      "learning_rate": 0.00017122905027932962,
+      "loss": 2.0662,
       "step": 103
     },
     {
-      "epoch": 4.16,
-      "learning_rate": 0.00015840000000000003,
-      "loss": 1.8941,
+      "epoch": 0.58,
+      "learning_rate": 0.00017094972067039109,
+      "loss": 1.988,
       "step": 104
     },
     {
-      "epoch": 4.2,
-      "learning_rate": 0.00015800000000000002,
-      "loss": 1.8601,
+      "epoch": 0.59,
+      "learning_rate": 0.00017067039106145253,
+      "loss": 2.1008,
       "step": 105
     },
     {
-      "epoch": 4.24,
-      "learning_rate": 0.0001576,
-      "loss": 1.7365,
+      "epoch": 0.59,
+      "learning_rate": 0.00017039106145251396,
+      "loss": 2.1482,
       "step": 106
     },
     {
-      "epoch": 4.28,
-      "learning_rate": 0.00015720000000000003,
-      "loss": 1.8809,
+      "epoch": 0.6,
+      "learning_rate": 0.00017011173184357543,
+      "loss": 2.1052,
       "step": 107
     },
     {
-      "epoch": 4.32,
-      "learning_rate": 0.00015680000000000002,
-      "loss": 2.0206,
+      "epoch": 0.6,
+      "learning_rate": 0.00016983240223463687,
+      "loss": 2.0978,
       "step": 108
     },
     {
-      "epoch": 4.36,
-      "learning_rate": 0.0001564,
-      "loss": 1.7776,
+      "epoch": 0.61,
+      "learning_rate": 0.00016955307262569834,
+      "loss": 2.1303,
       "step": 109
     },
     {
-      "epoch": 4.4,
-      "learning_rate": 0.00015600000000000002,
-      "loss": 1.9089,
+      "epoch": 0.61,
+      "learning_rate": 0.00016927374301675978,
+      "loss": 2.0794,
       "step": 110
     },
     {
-      "epoch": 4.44,
-      "learning_rate": 0.00015560000000000001,
-      "loss": 1.8464,
+      "epoch": 0.62,
+      "learning_rate": 0.00016899441340782122,
+      "loss": 2.1059,
       "step": 111
     },
     {
-      "epoch": 4.48,
-      "learning_rate": 0.0001552,
-      "loss": 1.7943,
+      "epoch": 0.63,
+      "learning_rate": 0.0001687150837988827,
+      "loss": 1.9642,
       "step": 112
     },
     {
-      "epoch": 4.52,
-      "learning_rate": 0.00015480000000000002,
-      "loss": 1.8081,
+      "epoch": 0.63,
+      "learning_rate": 0.00016843575418994415,
+      "loss": 2.0415,
       "step": 113
     },
     {
-      "epoch": 4.56,
-      "learning_rate": 0.0001544,
-      "loss": 1.734,
+      "epoch": 0.64,
+      "learning_rate": 0.0001681564245810056,
+      "loss": 2.0795,
       "step": 114
     },
     {
-      "epoch": 4.6,
-      "learning_rate": 0.000154,
-      "loss": 1.8379,
+      "epoch": 0.64,
+      "learning_rate": 0.00016787709497206705,
+      "loss": 2.0238,
       "step": 115
     },
     {
-      "epoch": 4.64,
-      "learning_rate": 0.00015360000000000002,
-      "loss": 1.6841,
+      "epoch": 0.65,
+      "learning_rate": 0.0001675977653631285,
+      "loss": 2.078,
       "step": 116
     },
     {
-      "epoch": 4.68,
-      "learning_rate": 0.0001532,
-      "loss": 1.8253,
+      "epoch": 0.65,
+      "learning_rate": 0.00016731843575418996,
+      "loss": 2.1362,
       "step": 117
     },
     {
-      "epoch": 4.72,
-      "learning_rate": 0.0001528,
-      "loss": 1.7607,
+      "epoch": 0.66,
+      "learning_rate": 0.0001670391061452514,
+      "loss": 2.0552,
       "step": 118
     },
     {
-      "epoch": 4.76,
-      "learning_rate": 0.00015240000000000002,
-      "loss": 1.8205,
+      "epoch": 0.66,
+      "learning_rate": 0.00016675977653631284,
+      "loss": 2.213,
       "step": 119
     },
     {
-      "epoch": 4.8,
-      "learning_rate": 0.000152,
-      "loss": 1.8443,
+      "epoch": 0.67,
+      "learning_rate": 0.0001664804469273743,
+      "loss": 1.9999,
       "step": 120
     },
     {
-      "epoch": 4.84,
-      "learning_rate": 0.0001516,
-      "loss": 1.8824,
+      "epoch": 0.68,
+      "learning_rate": 0.00016620111731843577,
+      "loss": 2.06,
       "step": 121
     },
     {
-      "epoch": 4.88,
-      "learning_rate": 0.00015120000000000002,
-      "loss": 1.8369,
+      "epoch": 0.68,
+      "learning_rate": 0.0001659217877094972,
+      "loss": 2.0177,
       "step": 122
     },
     {
-      "epoch": 4.92,
-      "learning_rate": 0.0001508,
-      "loss": 1.8017,
+      "epoch": 0.69,
+      "learning_rate": 0.00016564245810055868,
+      "loss": 2.0504,
       "step": 123
     },
     {
-      "epoch": 4.96,
-      "learning_rate": 0.0001504,
-      "loss": 1.7858,
+      "epoch": 0.69,
+      "learning_rate": 0.00016536312849162012,
+      "loss": 2.0585,
       "step": 124
     },
     {
-      "epoch": 5.0,
-      "learning_rate": 0.00015000000000000001,
-      "loss": 1.8366,
+      "epoch": 0.7,
+      "learning_rate": 0.00016508379888268158,
+      "loss": 2.0273,
       "step": 125
     },
     {
-      "epoch": 5.04,
-      "learning_rate": 0.0001496,
-      "loss": 1.7353,
+      "epoch": 0.7,
+      "learning_rate": 0.00016480446927374302,
+      "loss": 2.0549,
       "step": 126
     },
     {
-      "epoch": 5.08,
-      "learning_rate": 0.0001492,
-      "loss": 1.6017,
+      "epoch": 0.71,
+      "learning_rate": 0.00016452513966480446,
+      "loss": 2.044,
       "step": 127
     },
     {
-      "epoch": 5.12,
-      "learning_rate": 0.0001488,
-      "loss": 1.6645,
+      "epoch": 0.72,
+      "learning_rate": 0.00016424581005586593,
+      "loss": 2.0731,
       "step": 128
     },
     {
-      "epoch": 5.16,
-      "learning_rate": 0.0001484,
-      "loss": 1.8663,
+      "epoch": 0.72,
+      "learning_rate": 0.00016396648044692737,
+      "loss": 2.0568,
       "step": 129
     },
     {
-      "epoch": 5.2,
-      "learning_rate": 0.000148,
-      "loss": 1.7009,
+      "epoch": 0.73,
+      "learning_rate": 0.00016368715083798883,
+      "loss": 2.007,
       "step": 130
     },
     {
-      "epoch": 5.24,
-      "learning_rate": 0.0001476,
-      "loss": 1.7371,
+      "epoch": 0.73,
+      "learning_rate": 0.0001634078212290503,
+      "loss": 2.0707,
       "step": 131
     },
     {
-      "epoch": 5.28,
-      "learning_rate": 0.0001472,
-      "loss": 1.8555,
+      "epoch": 0.74,
+      "learning_rate": 0.00016312849162011174,
+      "loss": 1.9793,
       "step": 132
     },
     {
-      "epoch": 5.32,
-      "learning_rate": 0.00014680000000000002,
-      "loss": 1.6373,
+      "epoch": 0.74,
+      "learning_rate": 0.0001628491620111732,
+      "loss": 2.1311,
       "step": 133
     },
     {
-      "epoch": 5.36,
-      "learning_rate": 0.0001464,
-      "loss": 1.7211,
+      "epoch": 0.75,
+      "learning_rate": 0.00016256983240223465,
+      "loss": 2.0016,
       "step": 134
     },
     {
-      "epoch": 5.4,
-      "learning_rate": 0.000146,
-      "loss": 1.614,
+      "epoch": 0.75,
+      "learning_rate": 0.00016229050279329609,
+      "loss": 1.9945,
       "step": 135
     },
     {
-      "epoch": 5.44,
-      "learning_rate": 0.00014560000000000002,
-      "loss": 1.8736,
+      "epoch": 0.76,
+      "learning_rate": 0.00016201117318435755,
+      "loss": 2.0186,
       "step": 136
     },
     {
-      "epoch": 5.48,
-      "learning_rate": 0.0001452,
-      "loss": 1.7229,
+      "epoch": 0.77,
+      "learning_rate": 0.000161731843575419,
+      "loss": 2.0971,
       "step": 137
     },
     {
-      "epoch": 5.52,
-      "learning_rate": 0.0001448,
-      "loss": 1.7315,
+      "epoch": 0.77,
+      "learning_rate": 0.00016145251396648046,
+      "loss": 2.0883,
       "step": 138
     },
     {
-      "epoch": 5.56,
-      "learning_rate": 0.0001444,
-      "loss": 1.7259,
+      "epoch": 0.78,
+      "learning_rate": 0.00016117318435754192,
+      "loss": 2.0803,
       "step": 139
     },
     {
-      "epoch": 5.6,
-      "learning_rate": 0.000144,
-      "loss": 1.7032,
+      "epoch": 0.78,
+      "learning_rate": 0.00016089385474860336,
+      "loss": 2.0617,
       "step": 140
     },
     {
-      "epoch": 5.64,
-      "learning_rate": 0.0001436,
-      "loss": 1.9237,
+      "epoch": 0.79,
+      "learning_rate": 0.00016061452513966483,
+      "loss": 2.1265,
       "step": 141
     },
     {
-      "epoch": 5.68,
-      "learning_rate": 0.0001432,
-      "loss": 1.7821,
+      "epoch": 0.79,
+      "learning_rate": 0.00016033519553072627,
+      "loss": 2.0151,
       "step": 142
     },
     {
-      "epoch": 5.72,
-      "learning_rate": 0.0001428,
-      "loss": 1.6081,
+      "epoch": 0.8,
+      "learning_rate": 0.0001600558659217877,
+      "loss": 1.996,
       "step": 143
     },
     {
-      "epoch": 5.76,
-      "learning_rate": 0.0001424,
-      "loss": 1.7979,
+      "epoch": 0.8,
+      "learning_rate": 0.00015977653631284918,
+      "loss": 2.0164,
       "step": 144
     },
     {
-      "epoch": 5.8,
-      "learning_rate": 0.000142,
-      "loss": 1.6675,
+      "epoch": 0.81,
+      "learning_rate": 0.00015949720670391061,
+      "loss": 2.0314,
       "step": 145
     },
     {
-      "epoch": 5.84,
-      "learning_rate": 0.0001416,
-      "loss": 1.6758,
+      "epoch": 0.82,
+      "learning_rate": 0.00015921787709497208,
+      "loss": 1.9501,
       "step": 146
     },
     {
-      "epoch": 5.88,
-      "learning_rate": 0.0001412,
-      "loss": 1.7783,
+      "epoch": 0.82,
+      "learning_rate": 0.00015893854748603352,
+      "loss": 2.087,
       "step": 147
     },
     {
-      "epoch": 5.92,
-      "learning_rate": 0.0001408,
-      "loss": 1.5935,
+      "epoch": 0.83,
+      "learning_rate": 0.000158659217877095,
+      "loss": 2.0262,
       "step": 148
     },
     {
-      "epoch": 5.96,
-      "learning_rate": 0.0001404,
-      "loss": 1.7372,
+      "epoch": 0.83,
+      "learning_rate": 0.00015837988826815643,
+      "loss": 2.0765,
       "step": 149
     },
     {
-      "epoch": 6.0,
-      "learning_rate": 0.00014,
-      "loss": 1.6308,
+      "epoch": 0.84,
+      "learning_rate": 0.0001581005586592179,
+      "loss": 2.105,
       "step": 150
     },
     {
-      "epoch": 6.04,
-      "learning_rate": 0.0001396,
-      "loss": 1.5829,
+      "epoch": 0.84,
+      "learning_rate": 0.00015782122905027933,
+      "loss": 1.9863,
       "step": 151
     },
     {
-      "epoch": 6.08,
-      "learning_rate": 0.0001392,
-      "loss": 1.6538,
+      "epoch": 0.85,
+      "learning_rate": 0.0001575418994413408,
+      "loss": 1.9873,
       "step": 152
     },
     {
-      "epoch": 6.12,
-      "learning_rate": 0.00013879999999999999,
-      "loss": 1.7624,
+      "epoch": 0.85,
+      "learning_rate": 0.00015726256983240224,
+      "loss": 2.0094,
       "step": 153
     },
     {
-      "epoch": 6.16,
-      "learning_rate": 0.0001384,
-      "loss": 1.4968,
+      "epoch": 0.86,
+      "learning_rate": 0.00015698324022346368,
+      "loss": 1.9141,
       "step": 154
     },
     {
-      "epoch": 6.2,
-      "learning_rate": 0.000138,
-      "loss": 1.7305,
+      "epoch": 0.87,
+      "learning_rate": 0.00015670391061452514,
+      "loss": 1.917,
       "step": 155
     },
     {
-      "epoch": 6.24,
-      "learning_rate": 0.00013759999999999998,
-      "loss": 1.6536,
+      "epoch": 0.87,
+      "learning_rate": 0.00015642458100558658,
+      "loss": 2.109,
       "step": 156
     },
     {
-      "epoch": 6.28,
-      "learning_rate": 0.00013720000000000003,
-      "loss": 1.654,
+      "epoch": 0.88,
+      "learning_rate": 0.00015614525139664805,
+      "loss": 1.9799,
       "step": 157
     },
     {
-      "epoch": 6.32,
-      "learning_rate": 0.00013680000000000002,
-      "loss": 1.7163,
+      "epoch": 0.88,
+      "learning_rate": 0.00015586592178770952,
+      "loss": 1.9571,
       "step": 158
     },
     {
-      "epoch": 6.36,
-      "learning_rate": 0.0001364,
-      "loss": 1.6599,
+      "epoch": 0.89,
+      "learning_rate": 0.00015558659217877096,
+      "loss": 1.9931,
       "step": 159
     },
     {
-      "epoch": 6.4,
-      "learning_rate": 0.00013600000000000003,
-      "loss": 1.5729,
+      "epoch": 0.89,
+      "learning_rate": 0.00015530726256983242,
+      "loss": 2.1004,
       "step": 160
     },
     {
-      "epoch": 6.44,
-      "learning_rate": 0.00013560000000000002,
-      "loss": 1.5291,
+      "epoch": 0.9,
+      "learning_rate": 0.00015502793296089386,
+      "loss": 2.0385,
       "step": 161
     },
     {
-      "epoch": 6.48,
-      "learning_rate": 0.0001352,
-      "loss": 1.5666,
+      "epoch": 0.91,
+      "learning_rate": 0.0001547486033519553,
+      "loss": 1.9751,
       "step": 162
     },
     {
-      "epoch": 6.52,
-      "learning_rate": 0.00013480000000000002,
-      "loss": 1.7576,
+      "epoch": 0.91,
+      "learning_rate": 0.00015446927374301677,
+      "loss": 2.0544,
       "step": 163
     },
     {
-      "epoch": 6.56,
-      "learning_rate": 0.00013440000000000001,
-      "loss": 1.4462,
+      "epoch": 0.92,
+      "learning_rate": 0.0001541899441340782,
+      "loss": 2.0069,
       "step": 164
     },
     {
-      "epoch": 6.6,
-      "learning_rate": 0.000134,
-      "loss": 1.5659,
+      "epoch": 0.92,
+      "learning_rate": 0.00015391061452513967,
+      "loss": 1.9576,
       "step": 165
     },
     {
-      "epoch": 6.64,
-      "learning_rate": 0.00013360000000000002,
-      "loss": 1.6234,
+      "epoch": 0.93,
+      "learning_rate": 0.00015363128491620114,
+      "loss": 1.8991,
       "step": 166
     },
     {
-      "epoch": 6.68,
-      "learning_rate": 0.0001332,
-      "loss": 1.5176,
+      "epoch": 0.93,
+      "learning_rate": 0.00015335195530726258,
+      "loss": 1.9336,
       "step": 167
     },
     {
-      "epoch": 6.72,
-      "learning_rate": 0.0001328,
-      "loss": 1.667,
+      "epoch": 0.94,
+      "learning_rate": 0.00015307262569832405,
+      "loss": 1.9736,
       "step": 168
     },
     {
-      "epoch": 6.76,
-      "learning_rate": 0.00013240000000000002,
-      "loss": 1.6514,
+      "epoch": 0.94,
+      "learning_rate": 0.00015279329608938548,
+      "loss": 1.9702,
       "step": 169
     },
     {
-      "epoch": 6.8,
-      "learning_rate": 0.000132,
-      "loss": 1.7179,
+      "epoch": 0.95,
+      "learning_rate": 0.00015251396648044692,
+      "loss": 1.9055,
       "step": 170
     },
     {
-      "epoch": 6.84,
-      "learning_rate": 0.0001316,
-      "loss": 1.4373,
+      "epoch": 0.96,
+      "learning_rate": 0.0001522346368715084,
+      "loss": 2.0503,
       "step": 171
     },
     {
-      "epoch": 6.88,
-      "learning_rate": 0.00013120000000000002,
-      "loss": 1.7044,
+      "epoch": 0.96,
+      "learning_rate": 0.00015195530726256983,
+      "loss": 2.0039,
       "step": 172
     },
     {
-      "epoch": 6.92,
-      "learning_rate": 0.0001308,
-      "loss": 1.5673,
+      "epoch": 0.97,
+      "learning_rate": 0.0001516759776536313,
+      "loss": 1.9406,
       "step": 173
     },
     {
-      "epoch": 6.96,
-      "learning_rate": 0.0001304,
-      "loss": 1.6303,
+      "epoch": 0.97,
+      "learning_rate": 0.00015139664804469274,
+      "loss": 2.0525,
       "step": 174
     },
     {
-      "epoch": 7.0,
-      "learning_rate": 0.00013000000000000002,
-      "loss": 1.4828,
+      "epoch": 0.98,
+      "learning_rate": 0.0001511173184357542,
+      "loss": 1.9234,
       "step": 175
     },
     {
-      "epoch": 7.04,
-      "learning_rate": 0.0001296,
-      "loss": 1.6204,
+      "epoch": 0.98,
+      "learning_rate": 0.00015083798882681567,
+      "loss": 1.8614,
       "step": 176
     },
     {
-      "epoch": 7.08,
-      "learning_rate": 0.00012920000000000002,
-      "loss": 1.4955,
+      "epoch": 0.99,
+      "learning_rate": 0.0001505586592178771,
+      "loss": 1.9616,
       "step": 177
     },
     {
-      "epoch": 7.12,
-      "learning_rate": 0.00012880000000000001,
-      "loss": 1.6109,
+      "epoch": 0.99,
+      "learning_rate": 0.00015027932960893855,
+      "loss": 1.9509,
       "step": 178
     },
     {
-      "epoch": 7.16,
-      "learning_rate": 0.0001284,
-      "loss": 1.5318,
+      "epoch": 1.0,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.9592,
       "step": 179
     },
     {
-      "epoch": 7.2,
-      "learning_rate": 0.00012800000000000002,
-      "loss": 1.5702,
+      "epoch": 1.01,
+      "learning_rate": 0.00014972067039106145,
+      "loss": 1.8991,
       "step": 180
     },
     {
-      "epoch": 7.24,
-      "learning_rate": 0.0001276,
-      "loss": 1.4598,
+      "epoch": 1.01,
+      "learning_rate": 0.00014944134078212292,
+      "loss": 1.9127,
       "step": 181
     },
     {
-      "epoch": 7.28,
-      "learning_rate": 0.0001272,
-      "loss": 1.6145,
+      "epoch": 1.02,
+      "learning_rate": 0.00014916201117318436,
+      "loss": 1.8982,
       "step": 182
     },
     {
-      "epoch": 7.32,
-      "learning_rate": 0.00012680000000000002,
-      "loss": 1.3628,
+      "epoch": 1.02,
+      "learning_rate": 0.0001488826815642458,
+      "loss": 1.9534,
       "step": 183
     },
     {
-      "epoch": 7.36,
-      "learning_rate": 0.0001264,
-      "loss": 1.4578,
+      "epoch": 1.03,
+      "learning_rate": 0.0001486033519553073,
+      "loss": 1.7794,
       "step": 184
     },
     {
-      "epoch": 7.4,
-      "learning_rate": 0.000126,
-      "loss": 1.7094,
+      "epoch": 1.03,
+      "learning_rate": 0.00014832402234636873,
+      "loss": 1.7958,
       "step": 185
     },
     {
-      "epoch": 7.44,
-      "learning_rate": 0.00012560000000000002,
-      "loss": 1.4376,
+      "epoch": 1.04,
+      "learning_rate": 0.00014804469273743017,
+      "loss": 1.8282,
       "step": 186
     },
     {
-      "epoch": 7.48,
-      "learning_rate": 0.0001252,
-      "loss": 1.3393,
+      "epoch": 1.04,
+      "learning_rate": 0.00014776536312849164,
+      "loss": 2.0423,
       "step": 187
     },
     {
-      "epoch": 7.52,
-      "learning_rate": 0.0001248,
-      "loss": 1.4273,
+      "epoch": 1.05,
+      "learning_rate": 0.00014748603351955308,
+      "loss": 1.9282,
       "step": 188
     },
     {
-      "epoch": 7.56,
-      "learning_rate": 0.00012440000000000002,
-      "loss": 1.5506,
+      "epoch": 1.06,
+      "learning_rate": 0.00014720670391061454,
+      "loss": 1.9072,
       "step": 189
     },
     {
-      "epoch": 7.6,
-      "learning_rate": 0.000124,
-      "loss": 1.4774,
+      "epoch": 1.06,
+      "learning_rate": 0.00014692737430167598,
+      "loss": 1.8665,
       "step": 190
     },
     {
-      "epoch": 7.64,
-      "learning_rate": 0.0001236,
-      "loss": 1.4632,
+      "epoch": 1.07,
+      "learning_rate": 0.00014664804469273742,
+      "loss": 1.9021,
       "step": 191
     },
     {
-      "epoch": 7.68,
-      "learning_rate": 0.0001232,
-      "loss": 1.4568,
+      "epoch": 1.07,
+      "learning_rate": 0.0001463687150837989,
+      "loss": 1.7308,
       "step": 192
     },
     {
-      "epoch": 7.72,
-      "learning_rate": 0.0001228,
-      "loss": 1.6106,
+      "epoch": 1.08,
+      "learning_rate": 0.00014608938547486035,
+      "loss": 1.9165,
       "step": 193
     },
     {
-      "epoch": 7.76,
-      "learning_rate": 0.0001224,
-      "loss": 1.577,
+      "epoch": 1.08,
+      "learning_rate": 0.0001458100558659218,
+      "loss": 1.842,
       "step": 194
     },
     {
-      "epoch": 7.8,
-      "learning_rate": 0.000122,
-      "loss": 1.4805,
+      "epoch": 1.09,
+      "learning_rate": 0.00014553072625698326,
+      "loss": 1.9128,
       "step": 195
     },
     {
-      "epoch": 7.84,
-      "learning_rate": 0.0001216,
-      "loss": 1.4546,
+      "epoch": 1.09,
+      "learning_rate": 0.0001452513966480447,
+      "loss": 1.8005,
       "step": 196
     },
     {
-      "epoch": 7.88,
-      "learning_rate": 0.0001212,
-      "loss": 1.5164,
+      "epoch": 1.1,
+      "learning_rate": 0.00014497206703910614,
+      "loss": 1.8547,
       "step": 197
     },
     {
-      "epoch": 7.92,
-      "learning_rate": 0.0001208,
-      "loss": 1.5061,
+      "epoch": 1.11,
+      "learning_rate": 0.0001446927374301676,
+      "loss": 1.9042,
       "step": 198
     },
     {
-      "epoch": 7.96,
-      "learning_rate": 0.0001204,
-      "loss": 1.5312,
+      "epoch": 1.11,
+      "learning_rate": 0.00014441340782122905,
+      "loss": 1.8609,
       "step": 199
     },
     {
-      "epoch": 8.0,
-      "learning_rate": 0.00012,
-      "loss": 1.4463,
+      "epoch": 1.12,
+      "learning_rate": 0.0001441340782122905,
+      "loss": 1.9591,
       "step": 200
     },
     {
-      "epoch": 8.04,
-      "learning_rate": 0.00011960000000000001,
-      "loss": 1.4207,
+      "epoch": 1.12,
+      "learning_rate": 0.00014385474860335195,
+      "loss": 1.8722,
       "step": 201
     },
     {
-      "epoch": 8.08,
-      "learning_rate": 0.0001192,
-      "loss": 1.4688,
+      "epoch": 1.13,
+      "learning_rate": 0.00014357541899441342,
+      "loss": 1.8535,
       "step": 202
     },
     {
-      "epoch": 8.12,
-      "learning_rate": 0.0001188,
-      "loss": 1.4445,
+      "epoch": 1.13,
+      "learning_rate": 0.00014329608938547488,
+      "loss": 1.8676,
       "step": 203
     },
     {
-      "epoch": 8.16,
-      "learning_rate": 0.0001184,
-      "loss": 1.4158,
+      "epoch": 1.14,
+      "learning_rate": 0.00014301675977653632,
+      "loss": 1.8976,
       "step": 204
     },
     {
-      "epoch": 8.2,
-      "learning_rate": 0.000118,
-      "loss": 1.3483,
+      "epoch": 1.15,
+      "learning_rate": 0.00014273743016759776,
+      "loss": 1.7723,
       "step": 205
     },
     {
-      "epoch": 8.24,
-      "learning_rate": 0.0001176,
-      "loss": 1.4117,
+      "epoch": 1.15,
+      "learning_rate": 0.00014245810055865923,
+      "loss": 1.8165,
       "step": 206
     },
     {
-      "epoch": 8.28,
-      "learning_rate": 0.0001172,
-      "loss": 1.4267,
+      "epoch": 1.16,
+      "learning_rate": 0.00014217877094972067,
+      "loss": 1.7811,
       "step": 207
     },
     {
-      "epoch": 8.32,
-      "learning_rate": 0.00011679999999999999,
-      "loss": 1.5547,
+      "epoch": 1.16,
+      "learning_rate": 0.00014189944134078214,
+      "loss": 1.908,
       "step": 208
     },
     {
-      "epoch": 8.36,
-      "learning_rate": 0.0001164,
-      "loss": 1.4883,
+      "epoch": 1.17,
+      "learning_rate": 0.00014162011173184357,
+      "loss": 1.7663,
       "step": 209
     },
     {
-      "epoch": 8.4,
-      "learning_rate": 0.000116,
-      "loss": 1.414,
+      "epoch": 1.17,
+      "learning_rate": 0.00014134078212290501,
+      "loss": 1.6779,
       "step": 210
     },
     {
-      "epoch": 8.44,
-      "learning_rate": 0.00011559999999999999,
-      "loss": 1.3254,
+      "epoch": 1.18,
+      "learning_rate": 0.0001410614525139665,
+      "loss": 1.9039,
       "step": 211
     },
     {
-      "epoch": 8.48,
-      "learning_rate": 0.0001152,
-      "loss": 1.22,
+      "epoch": 1.18,
+      "learning_rate": 0.00014078212290502795,
+      "loss": 1.8033,
       "step": 212
     },
     {
-      "epoch": 8.52,
-      "learning_rate": 0.0001148,
-      "loss": 1.3224,
+      "epoch": 1.19,
+      "learning_rate": 0.00014050279329608939,
+      "loss": 1.8251,
       "step": 213
     },
     {
-      "epoch": 8.56,
-      "learning_rate": 0.0001144,
-      "loss": 1.6158,
+      "epoch": 1.2,
+      "learning_rate": 0.00014022346368715085,
+      "loss": 1.8505,
       "step": 214
     },
     {
-      "epoch": 8.6,
-      "learning_rate": 0.00011399999999999999,
-      "loss": 1.2817,
+      "epoch": 1.2,
+      "learning_rate": 0.0001399441340782123,
+      "loss": 1.8147,
       "step": 215
     },
     {
-      "epoch": 8.64,
-      "learning_rate": 0.0001136,
-      "loss": 1.4077,
+      "epoch": 1.21,
+      "learning_rate": 0.00013966480446927376,
+      "loss": 1.8419,
       "step": 216
     },
     {
-      "epoch": 8.68,
-      "learning_rate": 0.0001132,
-      "loss": 1.5311,
+      "epoch": 1.21,
+      "learning_rate": 0.0001393854748603352,
+      "loss": 1.8401,
       "step": 217
     },
     {
-      "epoch": 8.72,
-      "learning_rate": 0.00011279999999999999,
-      "loss": 1.5289,
+      "epoch": 1.22,
+      "learning_rate": 0.00013910614525139664,
+      "loss": 1.8912,
       "step": 218
     },
     {
-      "epoch": 8.76,
-      "learning_rate": 0.00011240000000000002,
-      "loss": 1.4576,
+      "epoch": 1.22,
+      "learning_rate": 0.0001388268156424581,
+      "loss": 1.7548,
       "step": 219
     },
     {
-      "epoch": 8.8,
-      "learning_rate": 0.00011200000000000001,
-      "loss": 1.2063,
+      "epoch": 1.23,
+      "learning_rate": 0.00013854748603351957,
+      "loss": 1.8741,
       "step": 220
     },
     {
-      "epoch": 8.84,
-      "learning_rate": 0.00011160000000000002,
-      "loss": 1.3543,
+      "epoch": 1.23,
+      "learning_rate": 0.000138268156424581,
+      "loss": 1.9549,
       "step": 221
     },
     {
-      "epoch": 8.88,
-      "learning_rate": 0.00011120000000000002,
-      "loss": 1.4352,
+      "epoch": 1.24,
+      "learning_rate": 0.00013798882681564248,
+      "loss": 1.9093,
       "step": 222
     },
     {
-      "epoch": 8.92,
-      "learning_rate": 0.00011080000000000001,
-      "loss": 1.3058,
+      "epoch": 1.25,
+      "learning_rate": 0.00013770949720670392,
+      "loss": 1.7896,
       "step": 223
     },
     {
-      "epoch": 8.96,
-      "learning_rate": 0.00011040000000000001,
-      "loss": 1.3475,
+      "epoch": 1.25,
+      "learning_rate": 0.00013743016759776538,
+      "loss": 1.8491,
       "step": 224
     },
     {
-      "epoch": 9.0,
-      "learning_rate": 0.00011000000000000002,
-      "loss": 1.1293,
+      "epoch": 1.26,
+      "learning_rate": 0.00013715083798882682,
+      "loss": 1.7851,
       "step": 225
     },
     {
-      "epoch": 9.04,
-      "learning_rate": 0.00010960000000000001,
-      "loss": 1.1671,
+      "epoch": 1.26,
+      "learning_rate": 0.00013687150837988826,
+      "loss": 1.6992,
       "step": 226
     },
     {
-      "epoch": 9.08,
-      "learning_rate": 0.00010920000000000001,
-      "loss": 1.4726,
+      "epoch": 1.27,
+      "learning_rate": 0.00013659217877094973,
+      "loss": 1.9765,
       "step": 227
     },
     {
-      "epoch": 9.12,
-      "learning_rate": 0.00010880000000000002,
-      "loss": 1.3986,
+      "epoch": 1.27,
+      "learning_rate": 0.00013631284916201117,
+      "loss": 1.8179,
       "step": 228
     },
     {
-      "epoch": 9.16,
-      "learning_rate": 0.00010840000000000002,
-      "loss": 1.2731,
+      "epoch": 1.28,
+      "learning_rate": 0.00013603351955307263,
+      "loss": 1.8548,
       "step": 229
     },
     {
-      "epoch": 9.2,
-      "learning_rate": 0.00010800000000000001,
-      "loss": 1.2212,
+      "epoch": 1.28,
+      "learning_rate": 0.0001357541899441341,
+      "loss": 1.8843,
       "step": 230
     },
     {
-      "epoch": 9.24,
-      "learning_rate": 0.00010760000000000001,
-      "loss": 1.3067,
+      "epoch": 1.29,
+      "learning_rate": 0.00013547486033519554,
+      "loss": 1.9105,
       "step": 231
     },
     {
-      "epoch": 9.28,
-      "learning_rate": 0.00010720000000000002,
-      "loss": 1.278,
+      "epoch": 1.3,
+      "learning_rate": 0.00013519553072625698,
+      "loss": 1.8748,
       "step": 232
     },
     {
-      "epoch": 9.32,
-      "learning_rate": 0.00010680000000000001,
-      "loss": 1.4141,
+      "epoch": 1.3,
+      "learning_rate": 0.00013491620111731844,
+      "loss": 1.7976,
       "step": 233
     },
     {
-      "epoch": 9.36,
-      "learning_rate": 0.00010640000000000001,
-      "loss": 1.2885,
+      "epoch": 1.31,
+      "learning_rate": 0.00013463687150837988,
+      "loss": 1.7369,
       "step": 234
     },
     {
-      "epoch": 9.4,
-      "learning_rate": 0.00010600000000000002,
-      "loss": 1.466,
+      "epoch": 1.31,
+      "learning_rate": 0.00013435754189944135,
+      "loss": 1.7808,
       "step": 235
     },
     {
-      "epoch": 9.44,
-      "learning_rate": 0.0001056,
-      "loss": 1.2979,
+      "epoch": 1.32,
+      "learning_rate": 0.0001340782122905028,
+      "loss": 1.8385,
       "step": 236
     },
     {
-      "epoch": 9.48,
-      "learning_rate": 0.00010520000000000001,
-      "loss": 1.1622,
+      "epoch": 1.32,
+      "learning_rate": 0.00013379888268156423,
+      "loss": 1.8295,
       "step": 237
     },
     {
-      "epoch": 9.52,
-      "learning_rate": 0.00010480000000000001,
-      "loss": 1.2504,
+      "epoch": 1.33,
+      "learning_rate": 0.00013351955307262572,
+      "loss": 1.757,
       "step": 238
     },
     {
-      "epoch": 9.56,
-      "learning_rate": 0.0001044,
-      "loss": 1.228,
+      "epoch": 1.34,
+      "learning_rate": 0.00013324022346368716,
+      "loss": 1.7904,
       "step": 239
     },
     {
-      "epoch": 9.6,
-      "learning_rate": 0.00010400000000000001,
-      "loss": 1.3607,
+      "epoch": 1.34,
+      "learning_rate": 0.0001329608938547486,
+      "loss": 1.7632,
       "step": 240
     },
     {
-      "epoch": 9.64,
-      "learning_rate": 0.00010360000000000001,
-      "loss": 1.1921,
+      "epoch": 1.35,
+      "learning_rate": 0.00013268156424581007,
+      "loss": 1.7867,
       "step": 241
     },
     {
-      "epoch": 9.68,
-      "learning_rate": 0.0001032,
-      "loss": 1.2114,
+      "epoch": 1.35,
+      "learning_rate": 0.0001324022346368715,
+      "loss": 1.8259,
       "step": 242
     },
     {
-      "epoch": 9.72,
-      "learning_rate": 0.0001028,
-      "loss": 1.2385,
+      "epoch": 1.36,
+      "learning_rate": 0.00013212290502793297,
+      "loss": 1.6655,
       "step": 243
     },
     {
-      "epoch": 9.76,
-      "learning_rate": 0.00010240000000000001,
-      "loss": 1.3227,
+      "epoch": 1.36,
+      "learning_rate": 0.0001318435754189944,
+      "loss": 1.6848,
       "step": 244
     },
     {
-      "epoch": 9.8,
-      "learning_rate": 0.00010200000000000001,
-      "loss": 1.3935,
+      "epoch": 1.37,
+      "learning_rate": 0.00013156424581005585,
+      "loss": 1.7931,
       "step": 245
     },
     {
-      "epoch": 9.84,
-      "learning_rate": 0.0001016,
-      "loss": 1.2209,
+      "epoch": 1.37,
+      "learning_rate": 0.00013128491620111732,
+      "loss": 1.7868,
       "step": 246
     },
     {
-      "epoch": 9.88,
-      "learning_rate": 0.00010120000000000001,
-      "loss": 1.1541,
+      "epoch": 1.38,
+      "learning_rate": 0.00013100558659217879,
+      "loss": 1.7732,
       "step": 247
     },
     {
-      "epoch": 9.92,
-      "learning_rate": 0.00010080000000000001,
-      "loss": 1.4049,
+      "epoch": 1.39,
+      "learning_rate": 0.00013072625698324022,
+      "loss": 1.7851,
       "step": 248
     },
     {
-      "epoch": 9.96,
-      "learning_rate": 0.0001004,
-      "loss": 1.13,
+      "epoch": 1.39,
+      "learning_rate": 0.0001304469273743017,
+      "loss": 1.7406,
       "step": 249
     },
     {
-      "epoch": 10.0,
-      "learning_rate": 0.0001,
-      "loss": 1.3783,
+      "epoch": 1.4,
+      "learning_rate": 0.00013016759776536313,
+      "loss": 1.5853,
       "step": 250
     },
     {
-      "epoch": 10.04,
-      "learning_rate": 9.960000000000001e-05,
-      "loss": 1.3207,
+      "epoch": 1.4,
+      "learning_rate": 0.0001298882681564246,
+      "loss": 1.8271,
       "step": 251
     },
     {
-      "epoch": 10.08,
-      "learning_rate": 9.92e-05,
-      "loss": 1.2697,
+      "epoch": 1.41,
+      "learning_rate": 0.00012960893854748604,
+      "loss": 1.6054,
       "step": 252
     },
     {
-      "epoch": 10.12,
-      "learning_rate": 9.88e-05,
-      "loss": 1.091,
+      "epoch": 1.41,
+      "learning_rate": 0.00012932960893854748,
+      "loss": 1.6884,
       "step": 253
     },
     {
-      "epoch": 10.16,
-      "learning_rate": 9.84e-05,
-      "loss": 1.0463,
+      "epoch": 1.42,
+      "learning_rate": 0.00012905027932960894,
+      "loss": 1.7333,
       "step": 254
     },
     {
-      "epoch": 10.2,
-      "learning_rate": 9.8e-05,
-      "loss": 1.3686,
+      "epoch": 1.42,
+      "learning_rate": 0.00012877094972067038,
+      "loss": 1.803,
       "step": 255
     },
     {
-      "epoch": 10.24,
-      "learning_rate": 9.76e-05,
-      "loss": 1.3109,
+      "epoch": 1.43,
+      "learning_rate": 0.00012849162011173185,
+      "loss": 1.63,
       "step": 256
     },
     {
-      "epoch": 10.28,
-      "learning_rate": 9.72e-05,
-      "loss": 1.2338,
+      "epoch": 1.44,
+      "learning_rate": 0.00012821229050279331,
+      "loss": 1.8023,
       "step": 257
     },
     {
-      "epoch": 10.32,
-      "learning_rate": 9.680000000000001e-05,
-      "loss": 1.12,
+      "epoch": 1.44,
+      "learning_rate": 0.00012793296089385475,
+      "loss": 1.762,
       "step": 258
     },
     {
-      "epoch": 10.36,
-      "learning_rate": 9.64e-05,
-      "loss": 1.1864,
+      "epoch": 1.45,
+      "learning_rate": 0.00012765363128491622,
+      "loss": 1.7565,
       "step": 259
     },
     {
-      "epoch": 10.4,
-      "learning_rate": 9.6e-05,
-      "loss": 1.1062,
+      "epoch": 1.45,
+      "learning_rate": 0.00012737430167597766,
+      "loss": 1.5937,
       "step": 260
     },
     {
-      "epoch": 10.44,
-      "learning_rate": 9.56e-05,
-      "loss": 1.2924,
+      "epoch": 1.46,
+      "learning_rate": 0.0001270949720670391,
+      "loss": 1.7208,
       "step": 261
     },
     {
-      "epoch": 10.48,
-      "learning_rate": 9.52e-05,
-      "loss": 1.1931,
+      "epoch": 1.46,
+      "learning_rate": 0.00012681564245810057,
+      "loss": 1.8097,
       "step": 262
     },
     {
-      "epoch": 10.52,
-      "learning_rate": 9.48e-05,
-      "loss": 1.2366,
+      "epoch": 1.47,
+      "learning_rate": 0.000126536312849162,
+      "loss": 1.7042,
       "step": 263
     },
     {
-      "epoch": 10.56,
-      "learning_rate": 9.44e-05,
-      "loss": 1.1589,
+      "epoch": 1.47,
+      "learning_rate": 0.00012625698324022347,
+      "loss": 1.7892,
       "step": 264
     },
     {
-      "epoch": 10.6,
-      "learning_rate": 9.4e-05,
-      "loss": 1.1197,
+      "epoch": 1.48,
+      "learning_rate": 0.00012597765363128494,
+      "loss": 1.752,
       "step": 265
     },
     {
-      "epoch": 10.64,
-      "learning_rate": 9.360000000000001e-05,
-      "loss": 1.3072,
+      "epoch": 1.49,
+      "learning_rate": 0.00012569832402234638,
+      "loss": 1.7333,
       "step": 266
     },
     {
-      "epoch": 10.68,
-      "learning_rate": 9.320000000000002e-05,
-      "loss": 1.1173,
+      "epoch": 1.49,
+      "learning_rate": 0.00012541899441340784,
+      "loss": 1.7492,
       "step": 267
     },
     {
-      "epoch": 10.72,
-      "learning_rate": 9.28e-05,
-      "loss": 1.0378,
+      "epoch": 1.5,
+      "learning_rate": 0.00012513966480446928,
+      "loss": 1.818,
       "step": 268
     },
     {
-      "epoch": 10.76,
-      "learning_rate": 9.240000000000001e-05,
-      "loss": 1.1746,
+      "epoch": 1.5,
+      "learning_rate": 0.00012486033519553072,
+      "loss": 1.7146,
       "step": 269
     },
     {
-      "epoch": 10.8,
-      "learning_rate": 9.200000000000001e-05,
-      "loss": 1.1144,
+      "epoch": 1.51,
+      "learning_rate": 0.0001245810055865922,
+      "loss": 1.7958,
       "step": 270
     },
     {
-      "epoch": 10.84,
-      "learning_rate": 9.16e-05,
-      "loss": 1.1862,
+      "epoch": 1.51,
+      "learning_rate": 0.00012430167597765363,
+      "loss": 1.7212,
       "step": 271
     },
     {
-      "epoch": 10.88,
-      "learning_rate": 9.120000000000001e-05,
-      "loss": 1.0816,
+      "epoch": 1.52,
+      "learning_rate": 0.0001240223463687151,
+      "loss": 1.8835,
       "step": 272
     },
     {
-      "epoch": 10.92,
-      "learning_rate": 9.080000000000001e-05,
-      "loss": 1.2288,
+      "epoch": 1.53,
+      "learning_rate": 0.00012374301675977656,
+      "loss": 1.7486,
       "step": 273
     },
     {
-      "epoch": 10.96,
-      "learning_rate": 9.04e-05,
-      "loss": 1.3031,
+      "epoch": 1.53,
+      "learning_rate": 0.000123463687150838,
+      "loss": 1.8103,
       "step": 274
     },
     {
-      "epoch": 11.0,
-      "learning_rate": 9e-05,
-      "loss": 1.1646,
+      "epoch": 1.54,
+      "learning_rate": 0.00012318435754189944,
+      "loss": 1.7557,
       "step": 275
     },
     {
-      "epoch": 11.04,
-      "learning_rate": 8.960000000000001e-05,
-      "loss": 1.2088,
+      "epoch": 1.54,
+      "learning_rate": 0.0001229050279329609,
+      "loss": 1.6198,
       "step": 276
     },
     {
-      "epoch": 11.08,
-      "learning_rate": 8.92e-05,
-      "loss": 1.1465,
+      "epoch": 1.55,
+      "learning_rate": 0.00012262569832402235,
+      "loss": 1.6971,
       "step": 277
     },
     {
-      "epoch": 11.12,
-      "learning_rate": 8.88e-05,
-      "loss": 1.0313,
+      "epoch": 1.55,
+      "learning_rate": 0.0001223463687150838,
+      "loss": 1.668,
       "step": 278
     },
     {
-      "epoch": 11.16,
-      "learning_rate": 8.840000000000001e-05,
-      "loss": 0.9662,
+      "epoch": 1.56,
+      "learning_rate": 0.00012206703910614525,
+      "loss": 1.8795,
       "step": 279
     },
     {
-      "epoch": 11.2,
-      "learning_rate": 8.800000000000001e-05,
-      "loss": 1.051,
+      "epoch": 1.56,
+      "learning_rate": 0.0001217877094972067,
+      "loss": 1.6412,
       "step": 280
     },
     {
-      "epoch": 11.24,
-      "learning_rate": 8.76e-05,
-      "loss": 1.1708,
+      "epoch": 1.57,
+      "learning_rate": 0.00012150837988826816,
+      "loss": 1.7497,
       "step": 281
     },
     {
-      "epoch": 11.28,
-      "learning_rate": 8.72e-05,
-      "loss": 1.0236,
+      "epoch": 1.58,
+      "learning_rate": 0.00012122905027932962,
+      "loss": 1.5577,
       "step": 282
     },
     {
-      "epoch": 11.32,
-      "learning_rate": 8.680000000000001e-05,
-      "loss": 1.1359,
+      "epoch": 1.58,
+      "learning_rate": 0.00012094972067039108,
+      "loss": 1.8049,
       "step": 283
     },
     {
-      "epoch": 11.36,
-      "learning_rate": 8.64e-05,
-      "loss": 1.1398,
+      "epoch": 1.59,
+      "learning_rate": 0.00012067039106145253,
+      "loss": 1.6834,
       "step": 284
     },
     {
-      "epoch": 11.4,
-      "learning_rate": 8.6e-05,
-      "loss": 1.0213,
+      "epoch": 1.59,
+      "learning_rate": 0.00012039106145251397,
+      "loss": 1.7978,
       "step": 285
     },
     {
-      "epoch": 11.44,
-      "learning_rate": 8.560000000000001e-05,
-      "loss": 1.1788,
+      "epoch": 1.6,
+      "learning_rate": 0.00012011173184357542,
+      "loss": 1.6558,
       "step": 286
     },
     {
-      "epoch": 11.48,
-      "learning_rate": 8.52e-05,
-      "loss": 1.0387,
+      "epoch": 1.6,
+      "learning_rate": 0.00011983240223463687,
+      "loss": 1.7561,
       "step": 287
     },
     {
-      "epoch": 11.52,
-      "learning_rate": 8.48e-05,
-      "loss": 0.9476,
+      "epoch": 1.61,
+      "learning_rate": 0.00011955307262569833,
+      "loss": 1.6807,
       "step": 288
     },
     {
-      "epoch": 11.56,
-      "learning_rate": 8.44e-05,
-      "loss": 1.1954,
+      "epoch": 1.61,
+      "learning_rate": 0.00011927374301675978,
+      "loss": 1.6937,
       "step": 289
     },
     {
-      "epoch": 11.6,
-      "learning_rate": 8.4e-05,
-      "loss": 1.0309,
+      "epoch": 1.62,
+      "learning_rate": 0.00011899441340782122,
+      "loss": 1.6591,
       "step": 290
     },
     {
-      "epoch": 11.64,
-      "learning_rate": 8.36e-05,
-      "loss": 1.1321,
+      "epoch": 1.63,
+      "learning_rate": 0.0001187150837988827,
+      "loss": 1.6771,
       "step": 291
     },
     {
-      "epoch": 11.68,
-      "learning_rate": 8.32e-05,
-      "loss": 1.0914,
+      "epoch": 1.63,
+      "learning_rate": 0.00011843575418994415,
+      "loss": 1.7743,
       "step": 292
     },
     {
-      "epoch": 11.72,
-      "learning_rate": 8.28e-05,
-      "loss": 1.222,
+      "epoch": 1.64,
+      "learning_rate": 0.00011815642458100559,
+      "loss": 1.5857,
       "step": 293
     },
     {
-      "epoch": 11.76,
-      "learning_rate": 8.24e-05,
-      "loss": 1.0127,
+      "epoch": 1.64,
+      "learning_rate": 0.00011787709497206705,
+      "loss": 1.6999,
       "step": 294
     },
     {
-      "epoch": 11.8,
-      "learning_rate": 8.2e-05,
-      "loss": 1.1977,
+      "epoch": 1.65,
+      "learning_rate": 0.0001175977653631285,
+      "loss": 1.5661,
       "step": 295
     },
     {
-      "epoch": 11.84,
-      "learning_rate": 8.16e-05,
-      "loss": 1.122,
+      "epoch": 1.65,
+      "learning_rate": 0.00011731843575418995,
+      "loss": 1.7235,
       "step": 296
     },
     {
-      "epoch": 11.88,
-      "learning_rate": 8.120000000000001e-05,
-      "loss": 1.1543,
+      "epoch": 1.66,
+      "learning_rate": 0.0001170391061452514,
+      "loss": 1.607,
       "step": 297
     },
     {
-      "epoch": 11.92,
-      "learning_rate": 8.080000000000001e-05,
-      "loss": 1.1767,
+      "epoch": 1.66,
+      "learning_rate": 0.00011675977653631284,
+      "loss": 1.68,
       "step": 298
     },
     {
-      "epoch": 11.96,
-      "learning_rate": 8.04e-05,
-      "loss": 1.1341,
+      "epoch": 1.67,
+      "learning_rate": 0.0001164804469273743,
+      "loss": 1.6938,
       "step": 299
     },
     {
-      "epoch": 12.0,
-      "learning_rate": 8e-05,
-      "loss": 1.0107,
+      "epoch": 1.68,
+      "learning_rate": 0.00011620111731843578,
+      "loss": 1.6315,
       "step": 300
     },
     {
-      "epoch": 12.04,
-      "learning_rate": 7.960000000000001e-05,
-      "loss": 1.1455,
+      "epoch": 1.68,
+      "learning_rate": 0.00011592178770949722,
+      "loss": 1.6802,
       "step": 301
     },
     {
-      "epoch": 12.08,
-      "learning_rate": 7.920000000000001e-05,
-      "loss": 1.0091,
+      "epoch": 1.69,
+      "learning_rate": 0.00011564245810055867,
+      "loss": 1.7174,
       "step": 302
     },
     {
-      "epoch": 12.12,
-      "learning_rate": 7.88e-05,
-      "loss": 0.9888,
+      "epoch": 1.69,
+      "learning_rate": 0.00011536312849162012,
+      "loss": 1.5212,
       "step": 303
     },
     {
-      "epoch": 12.16,
-      "learning_rate": 7.840000000000001e-05,
-      "loss": 0.9894,
+      "epoch": 1.7,
+      "learning_rate": 0.00011508379888268157,
+      "loss": 1.5808,
       "step": 304
     },
     {
-      "epoch": 12.2,
-      "learning_rate": 7.800000000000001e-05,
-      "loss": 1.0095,
+      "epoch": 1.7,
+      "learning_rate": 0.00011480446927374303,
+      "loss": 1.6152,
       "step": 305
     },
     {
-      "epoch": 12.24,
-      "learning_rate": 7.76e-05,
-      "loss": 1.1163,
+      "epoch": 1.71,
+      "learning_rate": 0.00011452513966480447,
+      "loss": 1.5435,
       "step": 306
     },
     {
-      "epoch": 12.28,
-      "learning_rate": 7.72e-05,
-      "loss": 1.0345,
+      "epoch": 1.72,
+      "learning_rate": 0.00011424581005586592,
+      "loss": 1.6603,
       "step": 307
     },
     {
-      "epoch": 12.32,
-      "learning_rate": 7.680000000000001e-05,
-      "loss": 0.9662,
+      "epoch": 1.72,
+      "learning_rate": 0.00011396648044692737,
+      "loss": 1.685,
       "step": 308
     },
     {
-      "epoch": 12.36,
-      "learning_rate": 7.64e-05,
-      "loss": 0.9064,
+      "epoch": 1.73,
+      "learning_rate": 0.00011368715083798884,
+      "loss": 1.6002,
       "step": 309
     },
     {
-      "epoch": 12.4,
-      "learning_rate": 7.6e-05,
-      "loss": 0.9448,
+      "epoch": 1.73,
+      "learning_rate": 0.00011340782122905029,
+      "loss": 1.6046,
       "step": 310
     },
     {
-      "epoch": 12.44,
-      "learning_rate": 7.560000000000001e-05,
-      "loss": 0.9509,
+      "epoch": 1.74,
+      "learning_rate": 0.00011312849162011174,
+      "loss": 1.5969,
       "step": 311
     },
     {
-      "epoch": 12.48,
-      "learning_rate": 7.52e-05,
-      "loss": 1.123,
+      "epoch": 1.74,
+      "learning_rate": 0.0001128491620111732,
+      "loss": 1.5845,
       "step": 312
     },
     {
-      "epoch": 12.52,
-      "learning_rate": 7.48e-05,
-      "loss": 1.1011,
+      "epoch": 1.75,
+      "learning_rate": 0.00011256983240223464,
+      "loss": 1.8183,
       "step": 313
     },
     {
-      "epoch": 12.56,
-      "learning_rate": 7.44e-05,
-      "loss": 0.9398,
+      "epoch": 1.75,
+      "learning_rate": 0.00011229050279329609,
+      "loss": 1.6953,
       "step": 314
     },
     {
-      "epoch": 12.6,
-      "learning_rate": 7.4e-05,
-      "loss": 1.0498,
+      "epoch": 1.76,
+      "learning_rate": 0.00011201117318435754,
+      "loss": 1.7787,
       "step": 315
     },
     {
-      "epoch": 12.64,
-      "learning_rate": 7.36e-05,
-      "loss": 1.0442,
+      "epoch": 1.77,
+      "learning_rate": 0.000111731843575419,
+      "loss": 1.6422,
       "step": 316
     },
     {
-      "epoch": 12.68,
-      "learning_rate": 7.32e-05,
-      "loss": 0.9599,
+      "epoch": 1.77,
+      "learning_rate": 0.00011145251396648045,
+      "loss": 1.7034,
       "step": 317
     },
     {
-      "epoch": 12.72,
-      "learning_rate": 7.280000000000001e-05,
-      "loss": 0.8778,
+      "epoch": 1.78,
+      "learning_rate": 0.00011117318435754192,
+      "loss": 1.7301,
       "step": 318
     },
     {
-      "epoch": 12.76,
-      "learning_rate": 7.24e-05,
-      "loss": 0.8727,
+      "epoch": 1.78,
+      "learning_rate": 0.00011089385474860337,
+      "loss": 1.7084,
       "step": 319
     },
     {
-      "epoch": 12.8,
-      "learning_rate": 7.2e-05,
-      "loss": 1.0189,
+      "epoch": 1.79,
+      "learning_rate": 0.00011061452513966482,
+      "loss": 1.772,
       "step": 320
     },
     {
-      "epoch": 12.84,
-      "learning_rate": 7.16e-05,
-      "loss": 1.0543,
+      "epoch": 1.79,
+      "learning_rate": 0.00011033519553072626,
+      "loss": 1.5733,
       "step": 321
     },
     {
-      "epoch": 12.88,
-      "learning_rate": 7.12e-05,
-      "loss": 1.1282,
+      "epoch": 1.8,
+      "learning_rate": 0.00011005586592178771,
+      "loss": 1.6423,
       "step": 322
     },
     {
-      "epoch": 12.92,
-      "learning_rate": 7.08e-05,
-      "loss": 1.1018,
+      "epoch": 1.8,
+      "learning_rate": 0.00010977653631284917,
+      "loss": 1.5809,
       "step": 323
     },
     {
-      "epoch": 12.96,
-      "learning_rate": 7.04e-05,
-      "loss": 1.1827,
+      "epoch": 1.81,
+      "learning_rate": 0.00010949720670391062,
+      "loss": 1.6781,
       "step": 324
     },
     {
-      "epoch": 13.0,
-      "learning_rate": 7e-05,
-      "loss": 1.108,
+      "epoch": 1.82,
+      "learning_rate": 0.00010921787709497207,
+      "loss": 1.6788,
       "step": 325
     },
     {
-      "epoch": 13.04,
-      "learning_rate": 6.96e-05,
-      "loss": 0.9618,
+      "epoch": 1.82,
+      "learning_rate": 0.00010893854748603351,
+      "loss": 1.6346,
       "step": 326
     },
     {
-      "epoch": 13.08,
-      "learning_rate": 6.92e-05,
-      "loss": 1.0666,
+      "epoch": 1.83,
+      "learning_rate": 0.00010865921787709499,
+      "loss": 1.6634,
       "step": 327
     },
     {
-      "epoch": 13.12,
-      "learning_rate": 6.879999999999999e-05,
-      "loss": 0.9973,
+      "epoch": 1.83,
+      "learning_rate": 0.00010837988826815643,
+      "loss": 1.7561,
       "step": 328
     },
     {
-      "epoch": 13.16,
-      "learning_rate": 6.840000000000001e-05,
-      "loss": 1.0103,
+      "epoch": 1.84,
+      "learning_rate": 0.00010810055865921788,
+      "loss": 1.66,
       "step": 329
     },
     {
-      "epoch": 13.2,
-      "learning_rate": 6.800000000000001e-05,
-      "loss": 0.9974,
+      "epoch": 1.84,
+      "learning_rate": 0.00010782122905027934,
+      "loss": 1.7298,
       "step": 330
     },
     {
-      "epoch": 13.24,
-      "learning_rate": 6.76e-05,
-      "loss": 1.2283,
+      "epoch": 1.85,
+      "learning_rate": 0.00010754189944134079,
+      "loss": 1.6893,
       "step": 331
     },
     {
-      "epoch": 13.28,
-      "learning_rate": 6.720000000000001e-05,
-      "loss": 0.7485,
+      "epoch": 1.85,
+      "learning_rate": 0.00010726256983240224,
+      "loss": 1.7631,
       "step": 332
     },
     {
-      "epoch": 13.32,
-      "learning_rate": 6.680000000000001e-05,
-      "loss": 0.8072,
+      "epoch": 1.86,
+      "learning_rate": 0.00010698324022346368,
+      "loss": 1.6633,
       "step": 333
     },
     {
-      "epoch": 13.36,
-      "learning_rate": 6.64e-05,
-      "loss": 1.1106,
+      "epoch": 1.87,
+      "learning_rate": 0.00010670391061452513,
+      "loss": 1.5388,
       "step": 334
     },
     {
-      "epoch": 13.4,
-      "learning_rate": 6.6e-05,
-      "loss": 0.8216,
+      "epoch": 1.87,
+      "learning_rate": 0.00010642458100558659,
+      "loss": 1.6718,
       "step": 335
     },
     {
-      "epoch": 13.44,
-      "learning_rate": 6.560000000000001e-05,
-      "loss": 0.959,
+      "epoch": 1.88,
+      "learning_rate": 0.00010614525139664805,
+      "loss": 1.5536,
       "step": 336
     },
     {
-      "epoch": 13.48,
-      "learning_rate": 6.52e-05,
-      "loss": 1.0767,
+      "epoch": 1.88,
+      "learning_rate": 0.00010586592178770951,
+      "loss": 1.6483,
       "step": 337
     },
     {
-      "epoch": 13.52,
-      "learning_rate": 6.48e-05,
-      "loss": 1.0395,
+      "epoch": 1.89,
+      "learning_rate": 0.00010558659217877096,
+      "loss": 1.5774,
       "step": 338
     },
     {
-      "epoch": 13.56,
-      "learning_rate": 6.440000000000001e-05,
-      "loss": 0.9102,
+      "epoch": 1.89,
+      "learning_rate": 0.00010530726256983241,
+      "loss": 1.6366,
       "step": 339
     },
     {
-      "epoch": 13.6,
-      "learning_rate": 6.400000000000001e-05,
-      "loss": 0.8875,
+      "epoch": 1.9,
+      "learning_rate": 0.00010502793296089387,
+      "loss": 1.5567,
       "step": 340
     },
     {
-      "epoch": 13.64,
-      "learning_rate": 6.36e-05,
-      "loss": 1.0005,
+      "epoch": 1.91,
+      "learning_rate": 0.0001047486033519553,
+      "loss": 1.5323,
       "step": 341
     },
     {
-      "epoch": 13.68,
-      "learning_rate": 6.32e-05,
-      "loss": 0.9208,
+      "epoch": 1.91,
+      "learning_rate": 0.00010446927374301676,
+      "loss": 1.4608,
       "step": 342
     },
     {
-      "epoch": 13.72,
-      "learning_rate": 6.280000000000001e-05,
-      "loss": 0.8943,
+      "epoch": 1.92,
+      "learning_rate": 0.00010418994413407821,
+      "loss": 1.5933,
       "step": 343
     },
     {
-      "epoch": 13.76,
-      "learning_rate": 6.24e-05,
-      "loss": 0.8441,
+      "epoch": 1.92,
+      "learning_rate": 0.00010391061452513966,
+      "loss": 1.6625,
       "step": 344
     },
     {
-      "epoch": 13.8,
-      "learning_rate": 6.2e-05,
-      "loss": 0.9953,
+      "epoch": 1.93,
+      "learning_rate": 0.00010363128491620113,
+      "loss": 1.7236,
       "step": 345
     },
     {
-      "epoch": 13.84,
-      "learning_rate": 6.16e-05,
-      "loss": 0.796,
+      "epoch": 1.93,
+      "learning_rate": 0.00010335195530726258,
+      "loss": 1.759,
       "step": 346
     },
     {
-      "epoch": 13.88,
-      "learning_rate": 6.12e-05,
-      "loss": 1.0745,
+      "epoch": 1.94,
+      "learning_rate": 0.00010307262569832404,
+      "loss": 1.7248,
       "step": 347
     },
     {
-      "epoch": 13.92,
-      "learning_rate": 6.08e-05,
-      "loss": 0.9898,
+      "epoch": 1.94,
+      "learning_rate": 0.00010279329608938548,
+      "loss": 1.5144,
       "step": 348
     },
     {
-      "epoch": 13.96,
-      "learning_rate": 6.04e-05,
-      "loss": 0.9559,
+      "epoch": 1.95,
+      "learning_rate": 0.00010251396648044693,
+      "loss": 1.6905,
       "step": 349
     },
     {
-      "epoch": 14.0,
-      "learning_rate": 6e-05,
-      "loss": 0.8236,
+      "epoch": 1.96,
+      "learning_rate": 0.00010223463687150838,
+      "loss": 1.6119,
       "step": 350
     },
     {
-      "epoch": 14.04,
-      "learning_rate": 5.96e-05,
-      "loss": 0.7318,
+      "epoch": 1.96,
+      "learning_rate": 0.00010195530726256983,
+      "loss": 1.5464,
       "step": 351
     },
     {
-      "epoch": 14.08,
-      "learning_rate": 5.92e-05,
-      "loss": 0.8994,
+      "epoch": 1.97,
+      "learning_rate": 0.00010167597765363129,
+      "loss": 1.6901,
       "step": 352
     },
     {
-      "epoch": 14.12,
-      "learning_rate": 5.88e-05,
-      "loss": 0.9707,
+      "epoch": 1.97,
+      "learning_rate": 0.00010139664804469273,
+      "loss": 1.3511,
       "step": 353
     },
     {
-      "epoch": 14.16,
-      "learning_rate": 5.8399999999999997e-05,
-      "loss": 0.806,
+      "epoch": 1.98,
+      "learning_rate": 0.0001011173184357542,
+      "loss": 1.5434,
       "step": 354
     },
     {
-      "epoch": 14.2,
-      "learning_rate": 5.8e-05,
-      "loss": 1.0525,
+      "epoch": 1.98,
+      "learning_rate": 0.00010083798882681566,
+      "loss": 1.5891,
       "step": 355
     },
     {
-      "epoch": 14.24,
-      "learning_rate": 5.76e-05,
-      "loss": 0.7589,
+      "epoch": 1.99,
+      "learning_rate": 0.0001005586592178771,
+      "loss": 1.6658,
       "step": 356
     },
     {
-      "epoch": 14.28,
-      "learning_rate": 5.72e-05,
-      "loss": 0.7703,
+      "epoch": 1.99,
+      "learning_rate": 0.00010027932960893855,
+      "loss": 1.5657,
       "step": 357
     },
     {
-      "epoch": 14.32,
-      "learning_rate": 5.68e-05,
-      "loss": 0.9869,
+      "epoch": 2.0,
+      "learning_rate": 0.0001,
+      "loss": 1.7005,
       "step": 358
     },
     {
-      "epoch": 14.36,
-      "learning_rate": 5.6399999999999995e-05,
-      "loss": 0.9673,
+      "epoch": 2.01,
+      "learning_rate": 9.972067039106146e-05,
+      "loss": 1.4202,
       "step": 359
     },
     {
-      "epoch": 14.4,
-      "learning_rate": 5.6000000000000006e-05,
-      "loss": 0.9913,
+      "epoch": 2.01,
+      "learning_rate": 9.944134078212291e-05,
+      "loss": 1.5262,
       "step": 360
     },
     {
-      "epoch": 14.44,
-      "learning_rate": 5.560000000000001e-05,
-      "loss": 1.0219,
+      "epoch": 2.02,
+      "learning_rate": 9.916201117318436e-05,
+      "loss": 1.6323,
       "step": 361
     },
     {
-      "epoch": 14.48,
-      "learning_rate": 5.520000000000001e-05,
-      "loss": 0.8672,
+      "epoch": 2.02,
+      "learning_rate": 9.888268156424582e-05,
+      "loss": 1.5521,
       "step": 362
     },
     {
-      "epoch": 14.52,
-      "learning_rate": 5.4800000000000004e-05,
-      "loss": 1.0464,
+      "epoch": 2.03,
+      "learning_rate": 9.860335195530727e-05,
+      "loss": 1.5762,
       "step": 363
     },
     {
-      "epoch": 14.56,
-      "learning_rate": 5.440000000000001e-05,
-      "loss": 1.0109,
+      "epoch": 2.03,
+      "learning_rate": 9.832402234636872e-05,
+      "loss": 1.613,
       "step": 364
     },
     {
-      "epoch": 14.6,
-      "learning_rate": 5.4000000000000005e-05,
-      "loss": 0.9913,
+      "epoch": 2.04,
+      "learning_rate": 9.804469273743018e-05,
+      "loss": 1.4231,
       "step": 365
     },
     {
-      "epoch": 14.64,
-      "learning_rate": 5.360000000000001e-05,
-      "loss": 0.779,
+      "epoch": 2.04,
+      "learning_rate": 9.776536312849163e-05,
+      "loss": 1.5706,
       "step": 366
     },
     {
-      "epoch": 14.68,
-      "learning_rate": 5.3200000000000006e-05,
-      "loss": 0.8675,
+      "epoch": 2.05,
+      "learning_rate": 9.748603351955308e-05,
+      "loss": 1.5245,
       "step": 367
     },
     {
-      "epoch": 14.72,
-      "learning_rate": 5.28e-05,
-      "loss": 0.987,
+      "epoch": 2.06,
+      "learning_rate": 9.720670391061453e-05,
+      "loss": 1.4771,
       "step": 368
     },
     {
-      "epoch": 14.76,
-      "learning_rate": 5.2400000000000007e-05,
-      "loss": 0.741,
+      "epoch": 2.06,
+      "learning_rate": 9.692737430167597e-05,
+      "loss": 1.596,
       "step": 369
     },
     {
-      "epoch": 14.8,
-      "learning_rate": 5.2000000000000004e-05,
-      "loss": 0.9585,
+      "epoch": 2.07,
+      "learning_rate": 9.664804469273744e-05,
+      "loss": 1.537,
       "step": 370
     },
     {
-      "epoch": 14.84,
-      "learning_rate": 5.16e-05,
-      "loss": 0.8977,
+      "epoch": 2.07,
+      "learning_rate": 9.636871508379889e-05,
+      "loss": 1.4276,
       "step": 371
     },
     {
-      "epoch": 14.88,
-      "learning_rate": 5.1200000000000004e-05,
-      "loss": 0.7836,
+      "epoch": 2.08,
+      "learning_rate": 9.608938547486033e-05,
+      "loss": 1.4746,
       "step": 372
     },
     {
-      "epoch": 14.92,
-      "learning_rate": 5.08e-05,
-      "loss": 0.8461,
+      "epoch": 2.08,
+      "learning_rate": 9.581005586592178e-05,
+      "loss": 1.4374,
       "step": 373
     },
     {
-      "epoch": 14.96,
-      "learning_rate": 5.0400000000000005e-05,
-      "loss": 0.7531,
+      "epoch": 2.09,
+      "learning_rate": 9.553072625698325e-05,
+      "loss": 1.4704,
       "step": 374
     },
     {
-      "epoch": 15.0,
-      "learning_rate": 5e-05,
-      "loss": 0.8906,
+      "epoch": 2.09,
+      "learning_rate": 9.52513966480447e-05,
+      "loss": 1.5997,
       "step": 375
     },
     {
-      "epoch": 15.04,
-      "learning_rate": 4.96e-05,
-      "loss": 0.8793,
+      "epoch": 2.1,
+      "learning_rate": 9.497206703910614e-05,
+      "loss": 1.5034,
       "step": 376
     },
     {
-      "epoch": 15.08,
-      "learning_rate": 4.92e-05,
-      "loss": 0.8596,
+      "epoch": 2.11,
+      "learning_rate": 9.46927374301676e-05,
+      "loss": 1.6392,
       "step": 377
     },
     {
-      "epoch": 15.12,
-      "learning_rate": 4.88e-05,
-      "loss": 0.7947,
+      "epoch": 2.11,
+      "learning_rate": 9.441340782122905e-05,
+      "loss": 1.5611,
       "step": 378
     },
     {
-      "epoch": 15.16,
-      "learning_rate": 4.8400000000000004e-05,
-      "loss": 0.7976,
+      "epoch": 2.12,
+      "learning_rate": 9.413407821229052e-05,
+      "loss": 1.3384,
       "step": 379
     },
     {
-      "epoch": 15.2,
-      "learning_rate": 4.8e-05,
-      "loss": 0.9037,
+      "epoch": 2.12,
+      "learning_rate": 9.385474860335196e-05,
+      "loss": 1.5732,
       "step": 380
     },
     {
-      "epoch": 15.24,
-      "learning_rate": 4.76e-05,
-      "loss": 0.9863,
+      "epoch": 2.13,
+      "learning_rate": 9.357541899441341e-05,
+      "loss": 1.3874,
       "step": 381
     },
     {
-      "epoch": 15.28,
-      "learning_rate": 4.72e-05,
-      "loss": 0.7735,
+      "epoch": 2.13,
+      "learning_rate": 9.329608938547486e-05,
+      "loss": 1.4139,
       "step": 382
     },
     {
-      "epoch": 15.32,
-      "learning_rate": 4.6800000000000006e-05,
-      "loss": 0.6723,
+      "epoch": 2.14,
+      "learning_rate": 9.301675977653633e-05,
+      "loss": 1.5195,
       "step": 383
     },
     {
-      "epoch": 15.36,
-      "learning_rate": 4.64e-05,
-      "loss": 0.7002,
+      "epoch": 2.15,
+      "learning_rate": 9.273743016759777e-05,
+      "loss": 1.4371,
       "step": 384
     },
     {
-      "epoch": 15.4,
-      "learning_rate": 4.600000000000001e-05,
-      "loss": 0.9479,
+      "epoch": 2.15,
+      "learning_rate": 9.245810055865922e-05,
+      "loss": 1.4411,
       "step": 385
     },
     {
-      "epoch": 15.44,
-      "learning_rate": 4.5600000000000004e-05,
-      "loss": 0.8159,
+      "epoch": 2.16,
+      "learning_rate": 9.217877094972067e-05,
+      "loss": 1.5214,
       "step": 386
     },
     {
-      "epoch": 15.48,
-      "learning_rate": 4.52e-05,
-      "loss": 0.7954,
+      "epoch": 2.16,
+      "learning_rate": 9.189944134078213e-05,
+      "loss": 1.4971,
       "step": 387
     },
     {
-      "epoch": 15.52,
-      "learning_rate": 4.4800000000000005e-05,
-      "loss": 0.8016,
+      "epoch": 2.17,
+      "learning_rate": 9.162011173184358e-05,
+      "loss": 1.3453,
       "step": 388
     },
     {
-      "epoch": 15.56,
-      "learning_rate": 4.44e-05,
-      "loss": 0.7995,
+      "epoch": 2.17,
+      "learning_rate": 9.134078212290503e-05,
+      "loss": 1.394,
       "step": 389
     },
     {
-      "epoch": 15.6,
-      "learning_rate": 4.4000000000000006e-05,
-      "loss": 0.8243,
+      "epoch": 2.18,
+      "learning_rate": 9.106145251396648e-05,
+      "loss": 1.5058,
       "step": 390
     },
     {
-      "epoch": 15.64,
-      "learning_rate": 4.36e-05,
-      "loss": 0.8335,
+      "epoch": 2.18,
+      "learning_rate": 9.078212290502794e-05,
+      "loss": 1.4855,
       "step": 391
     },
     {
-      "epoch": 15.68,
-      "learning_rate": 4.32e-05,
-      "loss": 1.001,
+      "epoch": 2.19,
+      "learning_rate": 9.050279329608939e-05,
+      "loss": 1.4647,
       "step": 392
     },
     {
-      "epoch": 15.72,
-      "learning_rate": 4.2800000000000004e-05,
-      "loss": 0.9385,
+      "epoch": 2.2,
+      "learning_rate": 9.022346368715084e-05,
+      "loss": 1.3435,
       "step": 393
     },
     {
-      "epoch": 15.76,
-      "learning_rate": 4.24e-05,
-      "loss": 0.8796,
+      "epoch": 2.2,
+      "learning_rate": 8.99441340782123e-05,
+      "loss": 1.5815,
       "step": 394
     },
     {
-      "epoch": 15.8,
-      "learning_rate": 4.2e-05,
-      "loss": 0.98,
+      "epoch": 2.21,
+      "learning_rate": 8.966480446927375e-05,
+      "loss": 1.4742,
       "step": 395
     },
     {
-      "epoch": 15.84,
-      "learning_rate": 4.16e-05,
-      "loss": 0.7547,
+      "epoch": 2.21,
+      "learning_rate": 8.938547486033519e-05,
+      "loss": 1.5389,
       "step": 396
     },
     {
-      "epoch": 15.88,
-      "learning_rate": 4.12e-05,
-      "loss": 0.7943,
+      "epoch": 2.22,
+      "learning_rate": 8.910614525139666e-05,
+      "loss": 1.384,
       "step": 397
     },
     {
-      "epoch": 15.92,
-      "learning_rate": 4.08e-05,
-      "loss": 0.8135,
+      "epoch": 2.22,
+      "learning_rate": 8.882681564245811e-05,
+      "loss": 1.3967,
       "step": 398
     },
     {
-      "epoch": 15.96,
-      "learning_rate": 4.0400000000000006e-05,
-      "loss": 0.87,
+      "epoch": 2.23,
+      "learning_rate": 8.854748603351956e-05,
+      "loss": 1.442,
       "step": 399
     },
     {
-      "epoch": 16.0,
-      "learning_rate": 4e-05,
-      "loss": 0.8818,
+      "epoch": 2.23,
+      "learning_rate": 8.8268156424581e-05,
+      "loss": 1.396,
       "step": 400
     },
     {
-      "epoch": 16.04,
-      "learning_rate": 3.960000000000001e-05,
-      "loss": 1.0793,
+      "epoch": 2.24,
+      "learning_rate": 8.798882681564247e-05,
+      "loss": 1.4706,
       "step": 401
     },
     {
-      "epoch": 16.08,
-      "learning_rate": 3.9200000000000004e-05,
-      "loss": 0.6816,
+      "epoch": 2.25,
+      "learning_rate": 8.770949720670392e-05,
+      "loss": 1.4217,
       "step": 402
     },
     {
-      "epoch": 16.12,
-      "learning_rate": 3.88e-05,
-      "loss": 0.8138,
+      "epoch": 2.25,
+      "learning_rate": 8.743016759776537e-05,
+      "loss": 1.5617,
       "step": 403
     },
     {
-      "epoch": 16.16,
-      "learning_rate": 3.8400000000000005e-05,
-      "loss": 0.8002,
+      "epoch": 2.26,
+      "learning_rate": 8.715083798882681e-05,
+      "loss": 1.5701,
       "step": 404
     },
     {
-      "epoch": 16.2,
-      "learning_rate": 3.8e-05,
-      "loss": 0.7104,
+      "epoch": 2.26,
+      "learning_rate": 8.687150837988828e-05,
+      "loss": 1.3659,
       "step": 405
     },
     {
-      "epoch": 16.24,
-      "learning_rate": 3.76e-05,
-      "loss": 0.749,
+      "epoch": 2.27,
+      "learning_rate": 8.659217877094973e-05,
+      "loss": 1.3424,
       "step": 406
     },
     {
-      "epoch": 16.28,
-      "learning_rate": 3.72e-05,
-      "loss": 0.9713,
+      "epoch": 2.27,
+      "learning_rate": 8.631284916201118e-05,
+      "loss": 1.5782,
       "step": 407
     },
     {
-      "epoch": 16.32,
-      "learning_rate": 3.68e-05,
-      "loss": 0.9039,
+      "epoch": 2.28,
+      "learning_rate": 8.603351955307262e-05,
+      "loss": 1.3355,
       "step": 408
     },
     {
-      "epoch": 16.36,
-      "learning_rate": 3.6400000000000004e-05,
-      "loss": 0.7958,
+      "epoch": 2.28,
+      "learning_rate": 8.575418994413408e-05,
+      "loss": 1.4798,
       "step": 409
     },
     {
-      "epoch": 16.4,
-      "learning_rate": 3.6e-05,
-      "loss": 0.9242,
+      "epoch": 2.29,
+      "learning_rate": 8.547486033519554e-05,
+      "loss": 1.3813,
       "step": 410
     },
     {
-      "epoch": 16.44,
-      "learning_rate": 3.56e-05,
-      "loss": 0.7224,
+      "epoch": 2.3,
+      "learning_rate": 8.519553072625698e-05,
+      "loss": 1.6011,
       "step": 411
     },
     {
-      "epoch": 16.48,
-      "learning_rate": 3.52e-05,
-      "loss": 0.8227,
+      "epoch": 2.3,
+      "learning_rate": 8.491620111731844e-05,
+      "loss": 1.4596,
       "step": 412
     },
     {
-      "epoch": 16.52,
-      "learning_rate": 3.48e-05,
-      "loss": 0.7336,
+      "epoch": 2.31,
+      "learning_rate": 8.463687150837989e-05,
+      "loss": 1.4997,
       "step": 413
     },
     {
-      "epoch": 16.56,
-      "learning_rate": 3.4399999999999996e-05,
-      "loss": 0.801,
+      "epoch": 2.31,
+      "learning_rate": 8.435754189944135e-05,
+      "loss": 1.5255,
       "step": 414
     },
     {
-      "epoch": 16.6,
-      "learning_rate": 3.4000000000000007e-05,
-      "loss": 0.7649,
+      "epoch": 2.32,
+      "learning_rate": 8.40782122905028e-05,
+      "loss": 1.5305,
       "step": 415
     },
     {
-      "epoch": 16.64,
-      "learning_rate": 3.3600000000000004e-05,
-      "loss": 0.859,
+      "epoch": 2.32,
+      "learning_rate": 8.379888268156425e-05,
+      "loss": 1.3029,
       "step": 416
     },
     {
-      "epoch": 16.68,
-      "learning_rate": 3.32e-05,
-      "loss": 0.7702,
+      "epoch": 2.33,
+      "learning_rate": 8.35195530726257e-05,
+      "loss": 1.2046,
       "step": 417
     },
     {
-      "epoch": 16.72,
-      "learning_rate": 3.2800000000000004e-05,
-      "loss": 0.7585,
+      "epoch": 2.34,
+      "learning_rate": 8.324022346368715e-05,
+      "loss": 1.4985,
       "step": 418
     },
     {
-      "epoch": 16.76,
-      "learning_rate": 3.24e-05,
-      "loss": 0.6829,
+      "epoch": 2.34,
+      "learning_rate": 8.29608938547486e-05,
+      "loss": 1.3486,
       "step": 419
     },
     {
-      "epoch": 16.8,
-      "learning_rate": 3.2000000000000005e-05,
-      "loss": 0.8186,
+      "epoch": 2.35,
+      "learning_rate": 8.268156424581006e-05,
+      "loss": 1.2839,
       "step": 420
     },
     {
-      "epoch": 16.84,
-      "learning_rate": 3.16e-05,
-      "loss": 0.7649,
+      "epoch": 2.35,
+      "learning_rate": 8.240223463687151e-05,
+      "loss": 1.4286,
       "step": 421
     },
     {
-      "epoch": 16.88,
-      "learning_rate": 3.12e-05,
-      "loss": 0.8019,
+      "epoch": 2.36,
+      "learning_rate": 8.212290502793296e-05,
+      "loss": 1.3893,
       "step": 422
     },
     {
-      "epoch": 16.92,
-      "learning_rate": 3.08e-05,
-      "loss": 0.82,
+      "epoch": 2.36,
+      "learning_rate": 8.184357541899442e-05,
+      "loss": 1.5477,
       "step": 423
     },
     {
-      "epoch": 16.96,
-      "learning_rate": 3.04e-05,
-      "loss": 0.7077,
+      "epoch": 2.37,
+      "learning_rate": 8.156424581005587e-05,
+      "loss": 1.4973,
       "step": 424
     },
     {
-      "epoch": 17.0,
-      "learning_rate": 3e-05,
-      "loss": 0.7803,
+      "epoch": 2.37,
+      "learning_rate": 8.128491620111732e-05,
+      "loss": 1.3549,
       "step": 425
     },
     {
-      "epoch": 17.04,
-      "learning_rate": 2.96e-05,
-      "loss": 0.8311,
+      "epoch": 2.38,
+      "learning_rate": 8.100558659217878e-05,
+      "loss": 1.3966,
       "step": 426
     },
     {
-      "epoch": 17.08,
-      "learning_rate": 2.9199999999999998e-05,
-      "loss": 0.8245,
+      "epoch": 2.39,
+      "learning_rate": 8.072625698324023e-05,
+      "loss": 1.3974,
       "step": 427
     },
     {
-      "epoch": 17.12,
-      "learning_rate": 2.88e-05,
-      "loss": 0.6627,
+      "epoch": 2.39,
+      "learning_rate": 8.044692737430168e-05,
+      "loss": 1.5211,
       "step": 428
     },
     {
-      "epoch": 17.16,
-      "learning_rate": 2.84e-05,
-      "loss": 0.6721,
+      "epoch": 2.4,
+      "learning_rate": 8.016759776536313e-05,
+      "loss": 1.4751,
       "step": 429
     },
     {
-      "epoch": 17.2,
-      "learning_rate": 2.8000000000000003e-05,
-      "loss": 0.9004,
+      "epoch": 2.4,
+      "learning_rate": 7.988826815642459e-05,
+      "loss": 1.4322,
       "step": 430
     },
     {
-      "epoch": 17.24,
-      "learning_rate": 2.7600000000000003e-05,
-      "loss": 0.7606,
+      "epoch": 2.41,
+      "learning_rate": 7.960893854748604e-05,
+      "loss": 1.5991,
       "step": 431
     },
     {
-      "epoch": 17.28,
-      "learning_rate": 2.7200000000000004e-05,
-      "loss": 0.7235,
+      "epoch": 2.41,
+      "learning_rate": 7.93296089385475e-05,
+      "loss": 1.3288,
       "step": 432
     },
     {
-      "epoch": 17.32,
-      "learning_rate": 2.6800000000000004e-05,
-      "loss": 0.797,
+      "epoch": 2.42,
+      "learning_rate": 7.905027932960895e-05,
+      "loss": 1.4098,
       "step": 433
     },
     {
-      "epoch": 17.36,
-      "learning_rate": 2.64e-05,
-      "loss": 0.6312,
+      "epoch": 2.42,
+      "learning_rate": 7.87709497206704e-05,
+      "loss": 1.4819,
       "step": 434
     },
     {
-      "epoch": 17.4,
-      "learning_rate": 2.6000000000000002e-05,
-      "loss": 0.869,
+      "epoch": 2.43,
+      "learning_rate": 7.849162011173184e-05,
+      "loss": 1.4003,
       "step": 435
     },
     {
-      "epoch": 17.44,
-      "learning_rate": 2.5600000000000002e-05,
-      "loss": 0.7968,
+      "epoch": 2.44,
+      "learning_rate": 7.821229050279329e-05,
+      "loss": 1.3475,
       "step": 436
     },
     {
-      "epoch": 17.48,
-      "learning_rate": 2.5200000000000003e-05,
-      "loss": 0.6872,
+      "epoch": 2.44,
+      "learning_rate": 7.793296089385476e-05,
+      "loss": 1.3354,
       "step": 437
     },
     {
-      "epoch": 17.52,
-      "learning_rate": 2.48e-05,
-      "loss": 0.7272,
+      "epoch": 2.45,
+      "learning_rate": 7.765363128491621e-05,
+      "loss": 1.3144,
       "step": 438
     },
     {
-      "epoch": 17.56,
-      "learning_rate": 2.44e-05,
-      "loss": 0.7695,
+      "epoch": 2.45,
+      "learning_rate": 7.737430167597765e-05,
+      "loss": 1.4118,
       "step": 439
     },
     {
-      "epoch": 17.6,
-      "learning_rate": 2.4e-05,
-      "loss": 0.6806,
+      "epoch": 2.46,
+      "learning_rate": 7.70949720670391e-05,
+      "loss": 1.3716,
       "step": 440
     },
     {
-      "epoch": 17.64,
-      "learning_rate": 2.36e-05,
-      "loss": 0.9562,
+      "epoch": 2.46,
+      "learning_rate": 7.681564245810057e-05,
+      "loss": 1.4191,
       "step": 441
     },
     {
-      "epoch": 17.68,
-      "learning_rate": 2.32e-05,
-      "loss": 0.8659,
+      "epoch": 2.47,
+      "learning_rate": 7.653631284916202e-05,
+      "loss": 1.5173,
       "step": 442
     },
     {
-      "epoch": 17.72,
-      "learning_rate": 2.2800000000000002e-05,
-      "loss": 0.8259,
+      "epoch": 2.47,
+      "learning_rate": 7.625698324022346e-05,
+      "loss": 1.3005,
       "step": 443
     },
     {
-      "epoch": 17.76,
-      "learning_rate": 2.2400000000000002e-05,
-      "loss": 0.7056,
+      "epoch": 2.48,
+      "learning_rate": 7.597765363128491e-05,
+      "loss": 1.4586,
       "step": 444
     },
     {
-      "epoch": 17.8,
-      "learning_rate": 2.2000000000000003e-05,
-      "loss": 0.7251,
+      "epoch": 2.49,
+      "learning_rate": 7.569832402234637e-05,
+      "loss": 1.5086,
       "step": 445
     },
     {
-      "epoch": 17.84,
-      "learning_rate": 2.16e-05,
-      "loss": 0.8674,
+      "epoch": 2.49,
+      "learning_rate": 7.541899441340783e-05,
+      "loss": 1.5446,
       "step": 446
     },
     {
-      "epoch": 17.88,
-      "learning_rate": 2.12e-05,
-      "loss": 0.7127,
+      "epoch": 2.5,
+      "learning_rate": 7.513966480446927e-05,
+      "loss": 1.3274,
       "step": 447
     },
     {
-      "epoch": 17.92,
-      "learning_rate": 2.08e-05,
-      "loss": 0.849,
+      "epoch": 2.5,
+      "learning_rate": 7.486033519553073e-05,
+      "loss": 1.4424,
       "step": 448
     },
     {
-      "epoch": 17.96,
-      "learning_rate": 2.04e-05,
-      "loss": 0.7506,
+      "epoch": 2.51,
+      "learning_rate": 7.458100558659218e-05,
+      "loss": 1.2836,
       "step": 449
     },
     {
-      "epoch": 18.0,
-      "learning_rate": 2e-05,
-      "loss": 0.7262,
+      "epoch": 2.51,
+      "learning_rate": 7.430167597765365e-05,
+      "loss": 1.4322,
       "step": 450
     },
     {
-      "epoch": 18.04,
-      "learning_rate": 1.9600000000000002e-05,
-      "loss": 0.8102,
+      "epoch": 2.52,
+      "learning_rate": 7.402234636871509e-05,
+      "loss": 1.4168,
       "step": 451
     },
     {
-      "epoch": 18.08,
-      "learning_rate": 1.9200000000000003e-05,
-      "loss": 0.7843,
+      "epoch": 2.53,
+      "learning_rate": 7.374301675977654e-05,
+      "loss": 1.3892,
       "step": 452
     },
     {
-      "epoch": 18.12,
-      "learning_rate": 1.88e-05,
-      "loss": 0.6902,
+      "epoch": 2.53,
+      "learning_rate": 7.346368715083799e-05,
+      "loss": 1.6538,
       "step": 453
     },
     {
-      "epoch": 18.16,
-      "learning_rate": 1.84e-05,
-      "loss": 0.749,
+      "epoch": 2.54,
+      "learning_rate": 7.318435754189944e-05,
+      "loss": 1.4573,
       "step": 454
     },
     {
-      "epoch": 18.2,
-      "learning_rate": 1.8e-05,
-      "loss": 0.722,
+      "epoch": 2.54,
+      "learning_rate": 7.29050279329609e-05,
+      "loss": 1.4593,
       "step": 455
     },
     {
-      "epoch": 18.24,
-      "learning_rate": 1.76e-05,
-      "loss": 0.7015,
+      "epoch": 2.55,
+      "learning_rate": 7.262569832402235e-05,
+      "loss": 1.4316,
       "step": 456
     },
     {
-      "epoch": 18.28,
-      "learning_rate": 1.7199999999999998e-05,
-      "loss": 0.7451,
+      "epoch": 2.55,
+      "learning_rate": 7.23463687150838e-05,
+      "loss": 1.2702,
       "step": 457
     },
     {
-      "epoch": 18.32,
-      "learning_rate": 1.6800000000000002e-05,
-      "loss": 0.8411,
+      "epoch": 2.56,
+      "learning_rate": 7.206703910614526e-05,
+      "loss": 1.5458,
       "step": 458
     },
     {
-      "epoch": 18.36,
-      "learning_rate": 1.6400000000000002e-05,
-      "loss": 0.8594,
+      "epoch": 2.56,
+      "learning_rate": 7.178770949720671e-05,
+      "loss": 1.5179,
       "step": 459
     },
     {
-      "epoch": 18.4,
-      "learning_rate": 1.6000000000000003e-05,
-      "loss": 0.7394,
+      "epoch": 2.57,
+      "learning_rate": 7.150837988826816e-05,
+      "loss": 1.3844,
       "step": 460
     },
     {
-      "epoch": 18.44,
-      "learning_rate": 1.56e-05,
-      "loss": 0.8071,
+      "epoch": 2.58,
+      "learning_rate": 7.122905027932961e-05,
+      "loss": 1.3698,
       "step": 461
     },
     {
-      "epoch": 18.48,
-      "learning_rate": 1.52e-05,
-      "loss": 0.5883,
+      "epoch": 2.58,
+      "learning_rate": 7.094972067039107e-05,
+      "loss": 1.4396,
       "step": 462
     },
     {
-      "epoch": 18.52,
-      "learning_rate": 1.48e-05,
-      "loss": 0.5356,
+      "epoch": 2.59,
+      "learning_rate": 7.067039106145251e-05,
+      "loss": 1.5486,
       "step": 463
     },
     {
-      "epoch": 18.56,
-      "learning_rate": 1.44e-05,
-      "loss": 0.6916,
+      "epoch": 2.59,
+      "learning_rate": 7.039106145251397e-05,
+      "loss": 1.2032,
       "step": 464
     },
     {
-      "epoch": 18.6,
-      "learning_rate": 1.4000000000000001e-05,
-      "loss": 0.7899,
+      "epoch": 2.6,
+      "learning_rate": 7.011173184357543e-05,
+      "loss": 1.3434,
       "step": 465
     },
     {
-      "epoch": 18.64,
-      "learning_rate": 1.3600000000000002e-05,
-      "loss": 0.7651,
+      "epoch": 2.6,
+      "learning_rate": 6.983240223463688e-05,
+      "loss": 1.4065,
       "step": 466
     },
     {
-      "epoch": 18.68,
-      "learning_rate": 1.32e-05,
-      "loss": 0.7883,
+      "epoch": 2.61,
+      "learning_rate": 6.955307262569832e-05,
+      "loss": 1.3362,
       "step": 467
     },
     {
-      "epoch": 18.72,
-      "learning_rate": 1.2800000000000001e-05,
-      "loss": 0.8655,
+      "epoch": 2.61,
+      "learning_rate": 6.927374301675979e-05,
+      "loss": 1.375,
       "step": 468
     },
     {
-      "epoch": 18.76,
-      "learning_rate": 1.24e-05,
-      "loss": 0.6875,
+      "epoch": 2.62,
+      "learning_rate": 6.899441340782124e-05,
+      "loss": 1.4549,
       "step": 469
     },
     {
-      "epoch": 18.8,
-      "learning_rate": 1.2e-05,
-      "loss": 0.7629,
+      "epoch": 2.63,
+      "learning_rate": 6.871508379888269e-05,
+      "loss": 1.3724,
       "step": 470
     },
     {
-      "epoch": 18.84,
-      "learning_rate": 1.16e-05,
-      "loss": 0.5825,
+      "epoch": 2.63,
+      "learning_rate": 6.843575418994413e-05,
+      "loss": 1.1602,
       "step": 471
     },
     {
-      "epoch": 18.88,
-      "learning_rate": 1.1200000000000001e-05,
-      "loss": 0.6979,
+      "epoch": 2.64,
+      "learning_rate": 6.815642458100558e-05,
+      "loss": 1.4346,
       "step": 472
     },
     {
-      "epoch": 18.92,
-      "learning_rate": 1.08e-05,
-      "loss": 0.8777,
+      "epoch": 2.64,
+      "learning_rate": 6.787709497206705e-05,
+      "loss": 1.2877,
       "step": 473
     },
     {
-      "epoch": 18.96,
-      "learning_rate": 1.04e-05,
-      "loss": 0.7298,
+      "epoch": 2.65,
+      "learning_rate": 6.759776536312849e-05,
+      "loss": 1.394,
       "step": 474
     },
     {
-      "epoch": 19.0,
-      "learning_rate": 1e-05,
-      "loss": 0.8324,
+      "epoch": 2.65,
+      "learning_rate": 6.731843575418994e-05,
+      "loss": 1.3387,
       "step": 475
     },
     {
-      "epoch": 19.04,
-      "learning_rate": 9.600000000000001e-06,
-      "loss": 0.6186,
+      "epoch": 2.66,
+      "learning_rate": 6.70391061452514e-05,
+      "loss": 1.41,
       "step": 476
     },
     {
-      "epoch": 19.08,
-      "learning_rate": 9.2e-06,
-      "loss": 0.7853,
+      "epoch": 2.66,
+      "learning_rate": 6.675977653631286e-05,
+      "loss": 1.4299,
       "step": 477
     },
     {
-      "epoch": 19.12,
-      "learning_rate": 8.8e-06,
-      "loss": 0.5731,
+      "epoch": 2.67,
+      "learning_rate": 6.64804469273743e-05,
+      "loss": 1.3824,
       "step": 478
     },
     {
-      "epoch": 19.16,
-      "learning_rate": 8.400000000000001e-06,
-      "loss": 0.7915,
+      "epoch": 2.68,
+      "learning_rate": 6.620111731843575e-05,
+      "loss": 1.2656,
       "step": 479
     },
     {
-      "epoch": 19.2,
-      "learning_rate": 8.000000000000001e-06,
-      "loss": 0.83,
+      "epoch": 2.68,
+      "learning_rate": 6.59217877094972e-05,
+      "loss": 1.2811,
       "step": 480
     },
     {
-      "epoch": 19.24,
-      "learning_rate": 7.6e-06,
-      "loss": 0.7768,
+      "epoch": 2.69,
+      "learning_rate": 6.564245810055866e-05,
+      "loss": 1.6839,
       "step": 481
     },
     {
-      "epoch": 19.28,
-      "learning_rate": 7.2e-06,
-      "loss": 0.6634,
+      "epoch": 2.69,
+      "learning_rate": 6.536312849162011e-05,
+      "loss": 1.3089,
       "step": 482
     },
     {
-      "epoch": 19.32,
-      "learning_rate": 6.800000000000001e-06,
-      "loss": 0.657,
+      "epoch": 2.7,
+      "learning_rate": 6.508379888268157e-05,
+      "loss": 1.4323,
       "step": 483
     },
     {
-      "epoch": 19.36,
-      "learning_rate": 6.4000000000000006e-06,
-      "loss": 0.8127,
+      "epoch": 2.7,
+      "learning_rate": 6.480446927374302e-05,
+      "loss": 1.3439,
       "step": 484
     },
     {
-      "epoch": 19.4,
-      "learning_rate": 6e-06,
-      "loss": 0.7326,
+      "epoch": 2.71,
+      "learning_rate": 6.452513966480447e-05,
+      "loss": 1.3614,
       "step": 485
     },
     {
-      "epoch": 19.44,
-      "learning_rate": 5.600000000000001e-06,
-      "loss": 0.6168,
+      "epoch": 2.72,
+      "learning_rate": 6.424581005586592e-05,
+      "loss": 1.4974,
       "step": 486
     },
     {
-      "epoch": 19.48,
-      "learning_rate": 5.2e-06,
-      "loss": 0.7808,
+      "epoch": 2.72,
+      "learning_rate": 6.396648044692738e-05,
+      "loss": 1.4963,
       "step": 487
     },
     {
-      "epoch": 19.52,
-      "learning_rate": 4.800000000000001e-06,
-      "loss": 0.7509,
+      "epoch": 2.73,
+      "learning_rate": 6.368715083798883e-05,
+      "loss": 1.2902,
       "step": 488
     },
     {
-      "epoch": 19.56,
-      "learning_rate": 4.4e-06,
-      "loss": 0.7304,
+      "epoch": 2.73,
+      "learning_rate": 6.340782122905028e-05,
+      "loss": 1.3226,
       "step": 489
     },
     {
-      "epoch": 19.6,
-      "learning_rate": 4.000000000000001e-06,
-      "loss": 0.77,
+      "epoch": 2.74,
+      "learning_rate": 6.312849162011174e-05,
+      "loss": 1.4353,
       "step": 490
     },
     {
-      "epoch": 19.64,
-      "learning_rate": 3.6e-06,
-      "loss": 0.6577,
+      "epoch": 2.74,
+      "learning_rate": 6.284916201117319e-05,
+      "loss": 1.281,
       "step": 491
     },
     {
-      "epoch": 19.68,
-      "learning_rate": 3.2000000000000003e-06,
-      "loss": 0.6797,
+      "epoch": 2.75,
+      "learning_rate": 6.256983240223464e-05,
+      "loss": 1.3755,
       "step": 492
     },
     {
-      "epoch": 19.72,
-      "learning_rate": 2.8000000000000003e-06,
-      "loss": 0.807,
+      "epoch": 2.75,
+      "learning_rate": 6.22905027932961e-05,
+      "loss": 1.3811,
       "step": 493
     },
     {
-      "epoch": 19.76,
-      "learning_rate": 2.4000000000000003e-06,
-      "loss": 0.7484,
+      "epoch": 2.76,
+      "learning_rate": 6.201117318435755e-05,
+      "loss": 1.4627,
       "step": 494
     },
     {
-      "epoch": 19.8,
-      "learning_rate": 2.0000000000000003e-06,
-      "loss": 0.7582,
+      "epoch": 2.77,
+      "learning_rate": 6.1731843575419e-05,
+      "loss": 1.3482,
       "step": 495
     },
     {
-      "epoch": 19.84,
-      "learning_rate": 1.6000000000000001e-06,
-      "loss": 0.7102,
+      "epoch": 2.77,
+      "learning_rate": 6.145251396648045e-05,
+      "loss": 1.4274,
       "step": 496
     },
     {
-      "epoch": 19.88,
-      "learning_rate": 1.2000000000000002e-06,
-      "loss": 0.7078,
+      "epoch": 2.78,
+      "learning_rate": 6.11731843575419e-05,
+      "loss": 1.3465,
       "step": 497
     },
     {
-      "epoch": 19.92,
-      "learning_rate": 8.000000000000001e-07,
-      "loss": 0.7877,
+      "epoch": 2.78,
+      "learning_rate": 6.089385474860335e-05,
+      "loss": 1.2319,
       "step": 498
     },
     {
-      "epoch": 19.96,
-      "learning_rate": 4.0000000000000003e-07,
-      "loss": 0.8055,
+      "epoch": 2.79,
+      "learning_rate": 6.061452513966481e-05,
+      "loss": 1.2835,
       "step": 499
     },
     {
-      "epoch": 20.0,
-      "learning_rate": 0.0,
-      "loss": 0.6905,
+      "epoch": 2.79,
+      "learning_rate": 6.0335195530726265e-05,
+      "loss": 1.4836,
       "step": 500
     }
   ],
   "logging_steps": 1,
-  "max_steps": 500,
-  "num_train_epochs": 20,
+  "max_steps": 716,
+  "num_train_epochs": 4,
   "save_steps": 100,
-  "total_flos": 1.701892530444288e+17,
+  "total_flos": 2.572486267094016e+17,
   "trial_name": null,
   "trial_params": null
 }
diff --git a/checkpoint-500/training_args.bin b/checkpoint-500/training_args.bin
index 4de6572a838c337c9990635a9406ebf46c0ec336..c8672c716e925d0028b4938db147703f58656ff7 100644
--- a/checkpoint-500/training_args.bin
+++ b/checkpoint-500/training_args.bin
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ef74b31950ae6c8955316bed48c343fb06cda0cb6a8a54ca46ca3cb681c8736
+oid sha256:188ae1c421cc0c6435d1f71d8d3423ac4abc7dba0e6fc2efcbc4dbe77c741317
 size 4027
diff --git a/checkpoint-600/README.md b/checkpoint-600/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..08371015f02382e6fcba318f4aaea54ae52cd3c4
--- /dev/null
+++ b/checkpoint-600/README.md
@@ -0,0 +1,34 @@
+---
+library_name: peft
+---
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: True
+- load_in_4bit: False
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: True
+- load_in_4bit: False
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+### Framework versions
+
+- PEFT 0.6.0.dev0
+
+- PEFT 0.6.0.dev0
diff --git a/checkpoint-600/adapter_config.json b/checkpoint-600/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c661f74e40394c079de68f07861d73c341803b67
--- /dev/null
+++ b/checkpoint-600/adapter_config.json
@@ -0,0 +1,25 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "bigscience/bloomz-3b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "dense_4h_to_h",
+    "dense",
+    "dense_h_to_4h",
+    "query_key_value"
+  ],
+  "task_type": "CAUSAL_LM"
+}
\ No newline at end of file
diff --git a/checkpoint-600/adapter_model.bin b/checkpoint-600/adapter_model.bin
new file mode 100644
index 0000000000000000000000000000000000000000..8fbb1832de137e033b6dbf7ffc70284e5becb659
--- /dev/null
+++ b/checkpoint-600/adapter_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:435ffb177831605f5479223de5dfef343a64e6bc9f2d4e05fba2ab86e3d42c9b
+size 39409357
diff --git a/checkpoint-600/optimizer.pt b/checkpoint-600/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..64d125cfb1d1abce95ae8935c5159c5c4afc4d85
--- /dev/null
+++ b/checkpoint-600/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a67c0a0a04a16e60dc6df9ce52ee43c4b51d5e34c198de23f6afed8ff5bd6d3e
+size 78844421
diff --git a/checkpoint-600/rng_state.pth b/checkpoint-600/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..452f99ac534b9117d836494d73222e3d44e1523b
--- /dev/null
+++ b/checkpoint-600/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6869750f95a25c4e970298a33adf90e2d7ab52680bf3317239bff1b10103235
+size 14575
diff --git a/checkpoint-600/scheduler.pt b/checkpoint-600/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..dc91f19f9994d9dc5e2cb196fcfd876e3f7fe0c8
--- /dev/null
+++ b/checkpoint-600/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df189dbec1d9da6456fed4321f8fb7b9b04184c73d2cc55b1372ecebfa9aaaff
+size 627
diff --git a/checkpoint-600/special_tokens_map.json b/checkpoint-600/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..fdafe480f024ff444c7492147536765ce5d55a2d
--- /dev/null
+++ b/checkpoint-600/special_tokens_map.json
@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}
diff --git a/checkpoint-600/tokenizer.json b/checkpoint-600/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..673c31abdeadf6576c3c754df86459e1ad64e207
--- /dev/null
+++ b/checkpoint-600/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85b00d7db4df5df2e3f01cacc3feda246002a672f3356eec7f4b04a22eb0dfbe
+size 14500570
diff --git a/checkpoint-600/tokenizer_config.json b/checkpoint-600/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..4b56cc9c2965c07132c35df3e2972e93d98c82c3
--- /dev/null
+++ b/checkpoint-600/tokenizer_config.json
@@ -0,0 +1,10 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "BloomTokenizer",
+  "unk_token": "<unk>"
+}
diff --git a/checkpoint-600/trainer_state.json b/checkpoint-600/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..779b4f6d8a9d155187db4987b1d9f9ebcb34f156
--- /dev/null
+++ b/checkpoint-600/trainer_state.json
@@ -0,0 +1,3619 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.35195530726257,
+  "eval_steps": 500,
+  "global_step": 600,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00019972067039106145,
+      "loss": 2.6443,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00019944134078212292,
+      "loss": 2.4104,
+      "step": 2
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00019916201117318435,
+      "loss": 2.4975,
+      "step": 3
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00019888268156424582,
+      "loss": 2.3513,
+      "step": 4
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0001986033519553073,
+      "loss": 2.4274,
+      "step": 5
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00019832402234636873,
+      "loss": 2.3628,
+      "step": 6
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0001980446927374302,
+      "loss": 2.3567,
+      "step": 7
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00019776536312849163,
+      "loss": 2.4121,
+      "step": 8
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00019748603351955307,
+      "loss": 2.4033,
+      "step": 9
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00019720670391061454,
+      "loss": 2.2805,
+      "step": 10
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00019692737430167598,
+      "loss": 2.2639,
+      "step": 11
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00019664804469273744,
+      "loss": 2.2724,
+      "step": 12
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00019636871508379888,
+      "loss": 2.332,
+      "step": 13
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00019608938547486035,
+      "loss": 2.2261,
+      "step": 14
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00019581005586592182,
+      "loss": 2.2208,
+      "step": 15
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00019553072625698326,
+      "loss": 2.3351,
+      "step": 16
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0001952513966480447,
+      "loss": 2.2475,
+      "step": 17
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00019497206703910616,
+      "loss": 2.3283,
+      "step": 18
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0001946927374301676,
+      "loss": 2.1346,
+      "step": 19
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00019441340782122907,
+      "loss": 2.131,
+      "step": 20
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0001941340782122905,
+      "loss": 2.1718,
+      "step": 21
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00019385474860335195,
+      "loss": 2.2446,
+      "step": 22
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0001935754189944134,
+      "loss": 2.306,
+      "step": 23
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00019329608938547488,
+      "loss": 2.1908,
+      "step": 24
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00019301675977653632,
+      "loss": 2.2844,
+      "step": 25
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00019273743016759779,
+      "loss": 2.2235,
+      "step": 26
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00019245810055865922,
+      "loss": 2.1842,
+      "step": 27
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00019217877094972066,
+      "loss": 2.2675,
+      "step": 28
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00019189944134078213,
+      "loss": 2.2532,
+      "step": 29
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00019162011173184357,
+      "loss": 2.1788,
+      "step": 30
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00019134078212290504,
+      "loss": 2.2494,
+      "step": 31
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0001910614525139665,
+      "loss": 2.1995,
+      "step": 32
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00019078212290502794,
+      "loss": 2.1451,
+      "step": 33
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0001905027932960894,
+      "loss": 2.223,
+      "step": 34
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00019022346368715085,
+      "loss": 2.2854,
+      "step": 35
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0001899441340782123,
+      "loss": 2.2265,
+      "step": 36
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00018966480446927375,
+      "loss": 2.1214,
+      "step": 37
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0001893854748603352,
+      "loss": 2.1898,
+      "step": 38
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00018910614525139666,
+      "loss": 2.1974,
+      "step": 39
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0001888268156424581,
+      "loss": 2.2259,
+      "step": 40
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00018854748603351957,
+      "loss": 2.2094,
+      "step": 41
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00018826815642458103,
+      "loss": 2.1731,
+      "step": 42
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00018798882681564247,
+      "loss": 2.2373,
+      "step": 43
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0001877094972067039,
+      "loss": 2.2295,
+      "step": 44
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00018743016759776538,
+      "loss": 2.1947,
+      "step": 45
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00018715083798882682,
+      "loss": 2.2115,
+      "step": 46
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00018687150837988828,
+      "loss": 2.1224,
+      "step": 47
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00018659217877094972,
+      "loss": 2.2137,
+      "step": 48
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00018631284916201116,
+      "loss": 2.2338,
+      "step": 49
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00018603351955307266,
+      "loss": 2.1298,
+      "step": 50
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0001857541899441341,
+      "loss": 2.0883,
+      "step": 51
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00018547486033519553,
+      "loss": 2.1216,
+      "step": 52
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.000185195530726257,
+      "loss": 2.2112,
+      "step": 53
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00018491620111731844,
+      "loss": 2.1224,
+      "step": 54
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0001846368715083799,
+      "loss": 2.2375,
+      "step": 55
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00018435754189944135,
+      "loss": 2.2235,
+      "step": 56
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00018407821229050279,
+      "loss": 2.1682,
+      "step": 57
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00018379888268156425,
+      "loss": 2.2077,
+      "step": 58
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00018351955307262572,
+      "loss": 2.1596,
+      "step": 59
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00018324022346368716,
+      "loss": 2.1311,
+      "step": 60
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00018296089385474862,
+      "loss": 2.1333,
+      "step": 61
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00018268156424581006,
+      "loss": 2.0901,
+      "step": 62
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00018240223463687153,
+      "loss": 2.1971,
+      "step": 63
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00018212290502793297,
+      "loss": 2.2602,
+      "step": 64
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0001818435754189944,
+      "loss": 2.2194,
+      "step": 65
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00018156424581005588,
+      "loss": 2.1218,
+      "step": 66
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00018128491620111731,
+      "loss": 2.2049,
+      "step": 67
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00018100558659217878,
+      "loss": 2.1521,
+      "step": 68
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00018072625698324025,
+      "loss": 2.112,
+      "step": 69
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0001804469273743017,
+      "loss": 2.1906,
+      "step": 70
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00018016759776536313,
+      "loss": 2.1717,
+      "step": 71
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0001798882681564246,
+      "loss": 2.0712,
+      "step": 72
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00017960893854748603,
+      "loss": 2.141,
+      "step": 73
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0001793296089385475,
+      "loss": 2.0656,
+      "step": 74
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00017905027932960894,
+      "loss": 2.1125,
+      "step": 75
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00017877094972067038,
+      "loss": 2.0869,
+      "step": 76
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00017849162011173187,
+      "loss": 2.2478,
+      "step": 77
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0001782122905027933,
+      "loss": 2.1535,
+      "step": 78
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00017793296089385475,
+      "loss": 2.1927,
+      "step": 79
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00017765363128491622,
+      "loss": 2.1213,
+      "step": 80
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00017737430167597766,
+      "loss": 2.0981,
+      "step": 81
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00017709497206703912,
+      "loss": 2.1828,
+      "step": 82
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00017681564245810056,
+      "loss": 2.0562,
+      "step": 83
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.000176536312849162,
+      "loss": 2.1334,
+      "step": 84
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00017625698324022347,
+      "loss": 2.1225,
+      "step": 85
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00017597765363128493,
+      "loss": 2.2098,
+      "step": 86
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00017569832402234637,
+      "loss": 2.1519,
+      "step": 87
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00017541899441340784,
+      "loss": 2.1132,
+      "step": 88
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00017513966480446928,
+      "loss": 2.0333,
+      "step": 89
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00017486033519553075,
+      "loss": 2.2764,
+      "step": 90
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00017458100558659218,
+      "loss": 2.1838,
+      "step": 91
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00017430167597765362,
+      "loss": 2.1386,
+      "step": 92
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0001740223463687151,
+      "loss": 2.1034,
+      "step": 93
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00017374301675977656,
+      "loss": 2.0346,
+      "step": 94
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.000173463687150838,
+      "loss": 2.0274,
+      "step": 95
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00017318435754189946,
+      "loss": 2.1036,
+      "step": 96
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0001729050279329609,
+      "loss": 2.1208,
+      "step": 97
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00017262569832402237,
+      "loss": 2.0572,
+      "step": 98
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0001723463687150838,
+      "loss": 2.1702,
+      "step": 99
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00017206703910614525,
+      "loss": 2.1302,
+      "step": 100
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0001717877094972067,
+      "loss": 2.0175,
+      "step": 101
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00017150837988826815,
+      "loss": 2.1006,
+      "step": 102
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00017122905027932962,
+      "loss": 2.0662,
+      "step": 103
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00017094972067039109,
+      "loss": 1.988,
+      "step": 104
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00017067039106145253,
+      "loss": 2.1008,
+      "step": 105
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00017039106145251396,
+      "loss": 2.1482,
+      "step": 106
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00017011173184357543,
+      "loss": 2.1052,
+      "step": 107
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00016983240223463687,
+      "loss": 2.0978,
+      "step": 108
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00016955307262569834,
+      "loss": 2.1303,
+      "step": 109
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00016927374301675978,
+      "loss": 2.0794,
+      "step": 110
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00016899441340782122,
+      "loss": 2.1059,
+      "step": 111
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0001687150837988827,
+      "loss": 1.9642,
+      "step": 112
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00016843575418994415,
+      "loss": 2.0415,
+      "step": 113
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0001681564245810056,
+      "loss": 2.0795,
+      "step": 114
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00016787709497206705,
+      "loss": 2.0238,
+      "step": 115
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0001675977653631285,
+      "loss": 2.078,
+      "step": 116
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00016731843575418996,
+      "loss": 2.1362,
+      "step": 117
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0001670391061452514,
+      "loss": 2.0552,
+      "step": 118
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00016675977653631284,
+      "loss": 2.213,
+      "step": 119
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0001664804469273743,
+      "loss": 1.9999,
+      "step": 120
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00016620111731843577,
+      "loss": 2.06,
+      "step": 121
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0001659217877094972,
+      "loss": 2.0177,
+      "step": 122
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00016564245810055868,
+      "loss": 2.0504,
+      "step": 123
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00016536312849162012,
+      "loss": 2.0585,
+      "step": 124
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00016508379888268158,
+      "loss": 2.0273,
+      "step": 125
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00016480446927374302,
+      "loss": 2.0549,
+      "step": 126
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00016452513966480446,
+      "loss": 2.044,
+      "step": 127
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00016424581005586593,
+      "loss": 2.0731,
+      "step": 128
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00016396648044692737,
+      "loss": 2.0568,
+      "step": 129
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00016368715083798883,
+      "loss": 2.007,
+      "step": 130
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0001634078212290503,
+      "loss": 2.0707,
+      "step": 131
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00016312849162011174,
+      "loss": 1.9793,
+      "step": 132
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0001628491620111732,
+      "loss": 2.1311,
+      "step": 133
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.00016256983240223465,
+      "loss": 2.0016,
+      "step": 134
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.00016229050279329609,
+      "loss": 1.9945,
+      "step": 135
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00016201117318435755,
+      "loss": 2.0186,
+      "step": 136
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.000161731843575419,
+      "loss": 2.0971,
+      "step": 137
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00016145251396648046,
+      "loss": 2.0883,
+      "step": 138
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00016117318435754192,
+      "loss": 2.0803,
+      "step": 139
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00016089385474860336,
+      "loss": 2.0617,
+      "step": 140
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00016061452513966483,
+      "loss": 2.1265,
+      "step": 141
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00016033519553072627,
+      "loss": 2.0151,
+      "step": 142
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0001600558659217877,
+      "loss": 1.996,
+      "step": 143
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00015977653631284918,
+      "loss": 2.0164,
+      "step": 144
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00015949720670391061,
+      "loss": 2.0314,
+      "step": 145
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00015921787709497208,
+      "loss": 1.9501,
+      "step": 146
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00015893854748603352,
+      "loss": 2.087,
+      "step": 147
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.000158659217877095,
+      "loss": 2.0262,
+      "step": 148
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00015837988826815643,
+      "loss": 2.0765,
+      "step": 149
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0001581005586592179,
+      "loss": 2.105,
+      "step": 150
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00015782122905027933,
+      "loss": 1.9863,
+      "step": 151
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0001575418994413408,
+      "loss": 1.9873,
+      "step": 152
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00015726256983240224,
+      "loss": 2.0094,
+      "step": 153
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00015698324022346368,
+      "loss": 1.9141,
+      "step": 154
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00015670391061452514,
+      "loss": 1.917,
+      "step": 155
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00015642458100558658,
+      "loss": 2.109,
+      "step": 156
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.00015614525139664805,
+      "loss": 1.9799,
+      "step": 157
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.00015586592178770952,
+      "loss": 1.9571,
+      "step": 158
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00015558659217877096,
+      "loss": 1.9931,
+      "step": 159
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00015530726256983242,
+      "loss": 2.1004,
+      "step": 160
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.00015502793296089386,
+      "loss": 2.0385,
+      "step": 161
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0001547486033519553,
+      "loss": 1.9751,
+      "step": 162
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00015446927374301677,
+      "loss": 2.0544,
+      "step": 163
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0001541899441340782,
+      "loss": 2.0069,
+      "step": 164
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00015391061452513967,
+      "loss": 1.9576,
+      "step": 165
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00015363128491620114,
+      "loss": 1.8991,
+      "step": 166
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00015335195530726258,
+      "loss": 1.9336,
+      "step": 167
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00015307262569832405,
+      "loss": 1.9736,
+      "step": 168
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00015279329608938548,
+      "loss": 1.9702,
+      "step": 169
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00015251396648044692,
+      "loss": 1.9055,
+      "step": 170
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0001522346368715084,
+      "loss": 2.0503,
+      "step": 171
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00015195530726256983,
+      "loss": 2.0039,
+      "step": 172
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0001516759776536313,
+      "loss": 1.9406,
+      "step": 173
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00015139664804469274,
+      "loss": 2.0525,
+      "step": 174
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0001511173184357542,
+      "loss": 1.9234,
+      "step": 175
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00015083798882681567,
+      "loss": 1.8614,
+      "step": 176
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0001505586592178771,
+      "loss": 1.9616,
+      "step": 177
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00015027932960893855,
+      "loss": 1.9509,
+      "step": 178
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.9592,
+      "step": 179
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.00014972067039106145,
+      "loss": 1.8991,
+      "step": 180
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.00014944134078212292,
+      "loss": 1.9127,
+      "step": 181
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00014916201117318436,
+      "loss": 1.8982,
+      "step": 182
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.0001488826815642458,
+      "loss": 1.9534,
+      "step": 183
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.0001486033519553073,
+      "loss": 1.7794,
+      "step": 184
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.00014832402234636873,
+      "loss": 1.7958,
+      "step": 185
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.00014804469273743017,
+      "loss": 1.8282,
+      "step": 186
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.00014776536312849164,
+      "loss": 2.0423,
+      "step": 187
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.00014748603351955308,
+      "loss": 1.9282,
+      "step": 188
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.00014720670391061454,
+      "loss": 1.9072,
+      "step": 189
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.00014692737430167598,
+      "loss": 1.8665,
+      "step": 190
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.00014664804469273742,
+      "loss": 1.9021,
+      "step": 191
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0001463687150837989,
+      "loss": 1.7308,
+      "step": 192
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00014608938547486035,
+      "loss": 1.9165,
+      "step": 193
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.0001458100558659218,
+      "loss": 1.842,
+      "step": 194
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.00014553072625698326,
+      "loss": 1.9128,
+      "step": 195
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.0001452513966480447,
+      "loss": 1.8005,
+      "step": 196
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.00014497206703910614,
+      "loss": 1.8547,
+      "step": 197
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.0001446927374301676,
+      "loss": 1.9042,
+      "step": 198
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.00014441340782122905,
+      "loss": 1.8609,
+      "step": 199
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.0001441340782122905,
+      "loss": 1.9591,
+      "step": 200
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.00014385474860335195,
+      "loss": 1.8722,
+      "step": 201
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.00014357541899441342,
+      "loss": 1.8535,
+      "step": 202
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.00014329608938547488,
+      "loss": 1.8676,
+      "step": 203
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.00014301675977653632,
+      "loss": 1.8976,
+      "step": 204
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.00014273743016759776,
+      "loss": 1.7723,
+      "step": 205
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.00014245810055865923,
+      "loss": 1.8165,
+      "step": 206
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00014217877094972067,
+      "loss": 1.7811,
+      "step": 207
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00014189944134078214,
+      "loss": 1.908,
+      "step": 208
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.00014162011173184357,
+      "loss": 1.7663,
+      "step": 209
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.00014134078212290501,
+      "loss": 1.6779,
+      "step": 210
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.0001410614525139665,
+      "loss": 1.9039,
+      "step": 211
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00014078212290502795,
+      "loss": 1.8033,
+      "step": 212
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.00014050279329608939,
+      "loss": 1.8251,
+      "step": 213
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.00014022346368715085,
+      "loss": 1.8505,
+      "step": 214
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0001399441340782123,
+      "loss": 1.8147,
+      "step": 215
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.00013966480446927376,
+      "loss": 1.8419,
+      "step": 216
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.0001393854748603352,
+      "loss": 1.8401,
+      "step": 217
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.00013910614525139664,
+      "loss": 1.8912,
+      "step": 218
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.0001388268156424581,
+      "loss": 1.7548,
+      "step": 219
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.00013854748603351957,
+      "loss": 1.8741,
+      "step": 220
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.000138268156424581,
+      "loss": 1.9549,
+      "step": 221
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.00013798882681564248,
+      "loss": 1.9093,
+      "step": 222
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.00013770949720670392,
+      "loss": 1.7896,
+      "step": 223
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.00013743016759776538,
+      "loss": 1.8491,
+      "step": 224
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.00013715083798882682,
+      "loss": 1.7851,
+      "step": 225
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.00013687150837988826,
+      "loss": 1.6992,
+      "step": 226
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.00013659217877094973,
+      "loss": 1.9765,
+      "step": 227
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.00013631284916201117,
+      "loss": 1.8179,
+      "step": 228
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.00013603351955307263,
+      "loss": 1.8548,
+      "step": 229
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.0001357541899441341,
+      "loss": 1.8843,
+      "step": 230
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.00013547486033519554,
+      "loss": 1.9105,
+      "step": 231
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.00013519553072625698,
+      "loss": 1.8748,
+      "step": 232
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.00013491620111731844,
+      "loss": 1.7976,
+      "step": 233
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.00013463687150837988,
+      "loss": 1.7369,
+      "step": 234
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.00013435754189944135,
+      "loss": 1.7808,
+      "step": 235
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.0001340782122905028,
+      "loss": 1.8385,
+      "step": 236
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.00013379888268156423,
+      "loss": 1.8295,
+      "step": 237
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.00013351955307262572,
+      "loss": 1.757,
+      "step": 238
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.00013324022346368716,
+      "loss": 1.7904,
+      "step": 239
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.0001329608938547486,
+      "loss": 1.7632,
+      "step": 240
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.00013268156424581007,
+      "loss": 1.7867,
+      "step": 241
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.0001324022346368715,
+      "loss": 1.8259,
+      "step": 242
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.00013212290502793297,
+      "loss": 1.6655,
+      "step": 243
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.0001318435754189944,
+      "loss": 1.6848,
+      "step": 244
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.00013156424581005585,
+      "loss": 1.7931,
+      "step": 245
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.00013128491620111732,
+      "loss": 1.7868,
+      "step": 246
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.00013100558659217879,
+      "loss": 1.7732,
+      "step": 247
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.00013072625698324022,
+      "loss": 1.7851,
+      "step": 248
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.0001304469273743017,
+      "loss": 1.7406,
+      "step": 249
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.00013016759776536313,
+      "loss": 1.5853,
+      "step": 250
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.0001298882681564246,
+      "loss": 1.8271,
+      "step": 251
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.00012960893854748604,
+      "loss": 1.6054,
+      "step": 252
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.00012932960893854748,
+      "loss": 1.6884,
+      "step": 253
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.00012905027932960894,
+      "loss": 1.7333,
+      "step": 254
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.00012877094972067038,
+      "loss": 1.803,
+      "step": 255
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.00012849162011173185,
+      "loss": 1.63,
+      "step": 256
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.00012821229050279331,
+      "loss": 1.8023,
+      "step": 257
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.00012793296089385475,
+      "loss": 1.762,
+      "step": 258
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.00012765363128491622,
+      "loss": 1.7565,
+      "step": 259
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.00012737430167597766,
+      "loss": 1.5937,
+      "step": 260
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.0001270949720670391,
+      "loss": 1.7208,
+      "step": 261
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.00012681564245810057,
+      "loss": 1.8097,
+      "step": 262
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.000126536312849162,
+      "loss": 1.7042,
+      "step": 263
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.00012625698324022347,
+      "loss": 1.7892,
+      "step": 264
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 0.00012597765363128494,
+      "loss": 1.752,
+      "step": 265
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.00012569832402234638,
+      "loss": 1.7333,
+      "step": 266
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.00012541899441340784,
+      "loss": 1.7492,
+      "step": 267
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.00012513966480446928,
+      "loss": 1.818,
+      "step": 268
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.00012486033519553072,
+      "loss": 1.7146,
+      "step": 269
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 0.0001245810055865922,
+      "loss": 1.7958,
+      "step": 270
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 0.00012430167597765363,
+      "loss": 1.7212,
+      "step": 271
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 0.0001240223463687151,
+      "loss": 1.8835,
+      "step": 272
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 0.00012374301675977656,
+      "loss": 1.7486,
+      "step": 273
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 0.000123463687150838,
+      "loss": 1.8103,
+      "step": 274
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 0.00012318435754189944,
+      "loss": 1.7557,
+      "step": 275
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 0.0001229050279329609,
+      "loss": 1.6198,
+      "step": 276
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 0.00012262569832402235,
+      "loss": 1.6971,
+      "step": 277
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 0.0001223463687150838,
+      "loss": 1.668,
+      "step": 278
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 0.00012206703910614525,
+      "loss": 1.8795,
+      "step": 279
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 0.0001217877094972067,
+      "loss": 1.6412,
+      "step": 280
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 0.00012150837988826816,
+      "loss": 1.7497,
+      "step": 281
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 0.00012122905027932962,
+      "loss": 1.5577,
+      "step": 282
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 0.00012094972067039108,
+      "loss": 1.8049,
+      "step": 283
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 0.00012067039106145253,
+      "loss": 1.6834,
+      "step": 284
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 0.00012039106145251397,
+      "loss": 1.7978,
+      "step": 285
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.00012011173184357542,
+      "loss": 1.6558,
+      "step": 286
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.00011983240223463687,
+      "loss": 1.7561,
+      "step": 287
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 0.00011955307262569833,
+      "loss": 1.6807,
+      "step": 288
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 0.00011927374301675978,
+      "loss": 1.6937,
+      "step": 289
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 0.00011899441340782122,
+      "loss": 1.6591,
+      "step": 290
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 0.0001187150837988827,
+      "loss": 1.6771,
+      "step": 291
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 0.00011843575418994415,
+      "loss": 1.7743,
+      "step": 292
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 0.00011815642458100559,
+      "loss": 1.5857,
+      "step": 293
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 0.00011787709497206705,
+      "loss": 1.6999,
+      "step": 294
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 0.0001175977653631285,
+      "loss": 1.5661,
+      "step": 295
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 0.00011731843575418995,
+      "loss": 1.7235,
+      "step": 296
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 0.0001170391061452514,
+      "loss": 1.607,
+      "step": 297
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 0.00011675977653631284,
+      "loss": 1.68,
+      "step": 298
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 0.0001164804469273743,
+      "loss": 1.6938,
+      "step": 299
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 0.00011620111731843578,
+      "loss": 1.6315,
+      "step": 300
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 0.00011592178770949722,
+      "loss": 1.6802,
+      "step": 301
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 0.00011564245810055867,
+      "loss": 1.7174,
+      "step": 302
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 0.00011536312849162012,
+      "loss": 1.5212,
+      "step": 303
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 0.00011508379888268157,
+      "loss": 1.5808,
+      "step": 304
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 0.00011480446927374303,
+      "loss": 1.6152,
+      "step": 305
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 0.00011452513966480447,
+      "loss": 1.5435,
+      "step": 306
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 0.00011424581005586592,
+      "loss": 1.6603,
+      "step": 307
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 0.00011396648044692737,
+      "loss": 1.685,
+      "step": 308
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 0.00011368715083798884,
+      "loss": 1.6002,
+      "step": 309
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 0.00011340782122905029,
+      "loss": 1.6046,
+      "step": 310
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 0.00011312849162011174,
+      "loss": 1.5969,
+      "step": 311
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 0.0001128491620111732,
+      "loss": 1.5845,
+      "step": 312
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 0.00011256983240223464,
+      "loss": 1.8183,
+      "step": 313
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 0.00011229050279329609,
+      "loss": 1.6953,
+      "step": 314
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 0.00011201117318435754,
+      "loss": 1.7787,
+      "step": 315
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 0.000111731843575419,
+      "loss": 1.6422,
+      "step": 316
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 0.00011145251396648045,
+      "loss": 1.7034,
+      "step": 317
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 0.00011117318435754192,
+      "loss": 1.7301,
+      "step": 318
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 0.00011089385474860337,
+      "loss": 1.7084,
+      "step": 319
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 0.00011061452513966482,
+      "loss": 1.772,
+      "step": 320
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 0.00011033519553072626,
+      "loss": 1.5733,
+      "step": 321
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 0.00011005586592178771,
+      "loss": 1.6423,
+      "step": 322
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 0.00010977653631284917,
+      "loss": 1.5809,
+      "step": 323
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 0.00010949720670391062,
+      "loss": 1.6781,
+      "step": 324
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 0.00010921787709497207,
+      "loss": 1.6788,
+      "step": 325
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 0.00010893854748603351,
+      "loss": 1.6346,
+      "step": 326
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 0.00010865921787709499,
+      "loss": 1.6634,
+      "step": 327
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 0.00010837988826815643,
+      "loss": 1.7561,
+      "step": 328
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 0.00010810055865921788,
+      "loss": 1.66,
+      "step": 329
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 0.00010782122905027934,
+      "loss": 1.7298,
+      "step": 330
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 0.00010754189944134079,
+      "loss": 1.6893,
+      "step": 331
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 0.00010726256983240224,
+      "loss": 1.7631,
+      "step": 332
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 0.00010698324022346368,
+      "loss": 1.6633,
+      "step": 333
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 0.00010670391061452513,
+      "loss": 1.5388,
+      "step": 334
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 0.00010642458100558659,
+      "loss": 1.6718,
+      "step": 335
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 0.00010614525139664805,
+      "loss": 1.5536,
+      "step": 336
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 0.00010586592178770951,
+      "loss": 1.6483,
+      "step": 337
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 0.00010558659217877096,
+      "loss": 1.5774,
+      "step": 338
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 0.00010530726256983241,
+      "loss": 1.6366,
+      "step": 339
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 0.00010502793296089387,
+      "loss": 1.5567,
+      "step": 340
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 0.0001047486033519553,
+      "loss": 1.5323,
+      "step": 341
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 0.00010446927374301676,
+      "loss": 1.4608,
+      "step": 342
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 0.00010418994413407821,
+      "loss": 1.5933,
+      "step": 343
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 0.00010391061452513966,
+      "loss": 1.6625,
+      "step": 344
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 0.00010363128491620113,
+      "loss": 1.7236,
+      "step": 345
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 0.00010335195530726258,
+      "loss": 1.759,
+      "step": 346
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 0.00010307262569832404,
+      "loss": 1.7248,
+      "step": 347
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 0.00010279329608938548,
+      "loss": 1.5144,
+      "step": 348
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 0.00010251396648044693,
+      "loss": 1.6905,
+      "step": 349
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 0.00010223463687150838,
+      "loss": 1.6119,
+      "step": 350
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 0.00010195530726256983,
+      "loss": 1.5464,
+      "step": 351
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 0.00010167597765363129,
+      "loss": 1.6901,
+      "step": 352
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 0.00010139664804469273,
+      "loss": 1.3511,
+      "step": 353
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 0.0001011173184357542,
+      "loss": 1.5434,
+      "step": 354
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 0.00010083798882681566,
+      "loss": 1.5891,
+      "step": 355
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 0.0001005586592178771,
+      "loss": 1.6658,
+      "step": 356
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 0.00010027932960893855,
+      "loss": 1.5657,
+      "step": 357
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0001,
+      "loss": 1.7005,
+      "step": 358
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 9.972067039106146e-05,
+      "loss": 1.4202,
+      "step": 359
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 9.944134078212291e-05,
+      "loss": 1.5262,
+      "step": 360
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 9.916201117318436e-05,
+      "loss": 1.6323,
+      "step": 361
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 9.888268156424582e-05,
+      "loss": 1.5521,
+      "step": 362
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 9.860335195530727e-05,
+      "loss": 1.5762,
+      "step": 363
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 9.832402234636872e-05,
+      "loss": 1.613,
+      "step": 364
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 9.804469273743018e-05,
+      "loss": 1.4231,
+      "step": 365
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 9.776536312849163e-05,
+      "loss": 1.5706,
+      "step": 366
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 9.748603351955308e-05,
+      "loss": 1.5245,
+      "step": 367
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 9.720670391061453e-05,
+      "loss": 1.4771,
+      "step": 368
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 9.692737430167597e-05,
+      "loss": 1.596,
+      "step": 369
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 9.664804469273744e-05,
+      "loss": 1.537,
+      "step": 370
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 9.636871508379889e-05,
+      "loss": 1.4276,
+      "step": 371
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 9.608938547486033e-05,
+      "loss": 1.4746,
+      "step": 372
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 9.581005586592178e-05,
+      "loss": 1.4374,
+      "step": 373
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 9.553072625698325e-05,
+      "loss": 1.4704,
+      "step": 374
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 9.52513966480447e-05,
+      "loss": 1.5997,
+      "step": 375
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 9.497206703910614e-05,
+      "loss": 1.5034,
+      "step": 376
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 9.46927374301676e-05,
+      "loss": 1.6392,
+      "step": 377
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 9.441340782122905e-05,
+      "loss": 1.5611,
+      "step": 378
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 9.413407821229052e-05,
+      "loss": 1.3384,
+      "step": 379
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 9.385474860335196e-05,
+      "loss": 1.5732,
+      "step": 380
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 9.357541899441341e-05,
+      "loss": 1.3874,
+      "step": 381
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 9.329608938547486e-05,
+      "loss": 1.4139,
+      "step": 382
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 9.301675977653633e-05,
+      "loss": 1.5195,
+      "step": 383
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 9.273743016759777e-05,
+      "loss": 1.4371,
+      "step": 384
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 9.245810055865922e-05,
+      "loss": 1.4411,
+      "step": 385
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 9.217877094972067e-05,
+      "loss": 1.5214,
+      "step": 386
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 9.189944134078213e-05,
+      "loss": 1.4971,
+      "step": 387
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 9.162011173184358e-05,
+      "loss": 1.3453,
+      "step": 388
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 9.134078212290503e-05,
+      "loss": 1.394,
+      "step": 389
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 9.106145251396648e-05,
+      "loss": 1.5058,
+      "step": 390
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 9.078212290502794e-05,
+      "loss": 1.4855,
+      "step": 391
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 9.050279329608939e-05,
+      "loss": 1.4647,
+      "step": 392
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 9.022346368715084e-05,
+      "loss": 1.3435,
+      "step": 393
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 8.99441340782123e-05,
+      "loss": 1.5815,
+      "step": 394
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 8.966480446927375e-05,
+      "loss": 1.4742,
+      "step": 395
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 8.938547486033519e-05,
+      "loss": 1.5389,
+      "step": 396
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 8.910614525139666e-05,
+      "loss": 1.384,
+      "step": 397
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 8.882681564245811e-05,
+      "loss": 1.3967,
+      "step": 398
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 8.854748603351956e-05,
+      "loss": 1.442,
+      "step": 399
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 8.8268156424581e-05,
+      "loss": 1.396,
+      "step": 400
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 8.798882681564247e-05,
+      "loss": 1.4706,
+      "step": 401
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 8.770949720670392e-05,
+      "loss": 1.4217,
+      "step": 402
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 8.743016759776537e-05,
+      "loss": 1.5617,
+      "step": 403
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 8.715083798882681e-05,
+      "loss": 1.5701,
+      "step": 404
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 8.687150837988828e-05,
+      "loss": 1.3659,
+      "step": 405
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 8.659217877094973e-05,
+      "loss": 1.3424,
+      "step": 406
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 8.631284916201118e-05,
+      "loss": 1.5782,
+      "step": 407
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 8.603351955307262e-05,
+      "loss": 1.3355,
+      "step": 408
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 8.575418994413408e-05,
+      "loss": 1.4798,
+      "step": 409
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 8.547486033519554e-05,
+      "loss": 1.3813,
+      "step": 410
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 8.519553072625698e-05,
+      "loss": 1.6011,
+      "step": 411
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 8.491620111731844e-05,
+      "loss": 1.4596,
+      "step": 412
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 8.463687150837989e-05,
+      "loss": 1.4997,
+      "step": 413
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 8.435754189944135e-05,
+      "loss": 1.5255,
+      "step": 414
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 8.40782122905028e-05,
+      "loss": 1.5305,
+      "step": 415
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 8.379888268156425e-05,
+      "loss": 1.3029,
+      "step": 416
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 8.35195530726257e-05,
+      "loss": 1.2046,
+      "step": 417
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 8.324022346368715e-05,
+      "loss": 1.4985,
+      "step": 418
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 8.29608938547486e-05,
+      "loss": 1.3486,
+      "step": 419
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 8.268156424581006e-05,
+      "loss": 1.2839,
+      "step": 420
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 8.240223463687151e-05,
+      "loss": 1.4286,
+      "step": 421
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 8.212290502793296e-05,
+      "loss": 1.3893,
+      "step": 422
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 8.184357541899442e-05,
+      "loss": 1.5477,
+      "step": 423
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 8.156424581005587e-05,
+      "loss": 1.4973,
+      "step": 424
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 8.128491620111732e-05,
+      "loss": 1.3549,
+      "step": 425
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 8.100558659217878e-05,
+      "loss": 1.3966,
+      "step": 426
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 8.072625698324023e-05,
+      "loss": 1.3974,
+      "step": 427
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 8.044692737430168e-05,
+      "loss": 1.5211,
+      "step": 428
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 8.016759776536313e-05,
+      "loss": 1.4751,
+      "step": 429
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 7.988826815642459e-05,
+      "loss": 1.4322,
+      "step": 430
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 7.960893854748604e-05,
+      "loss": 1.5991,
+      "step": 431
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 7.93296089385475e-05,
+      "loss": 1.3288,
+      "step": 432
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 7.905027932960895e-05,
+      "loss": 1.4098,
+      "step": 433
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 7.87709497206704e-05,
+      "loss": 1.4819,
+      "step": 434
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 7.849162011173184e-05,
+      "loss": 1.4003,
+      "step": 435
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 7.821229050279329e-05,
+      "loss": 1.3475,
+      "step": 436
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 7.793296089385476e-05,
+      "loss": 1.3354,
+      "step": 437
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 7.765363128491621e-05,
+      "loss": 1.3144,
+      "step": 438
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 7.737430167597765e-05,
+      "loss": 1.4118,
+      "step": 439
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 7.70949720670391e-05,
+      "loss": 1.3716,
+      "step": 440
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 7.681564245810057e-05,
+      "loss": 1.4191,
+      "step": 441
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 7.653631284916202e-05,
+      "loss": 1.5173,
+      "step": 442
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 7.625698324022346e-05,
+      "loss": 1.3005,
+      "step": 443
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 7.597765363128491e-05,
+      "loss": 1.4586,
+      "step": 444
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 7.569832402234637e-05,
+      "loss": 1.5086,
+      "step": 445
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 7.541899441340783e-05,
+      "loss": 1.5446,
+      "step": 446
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 7.513966480446927e-05,
+      "loss": 1.3274,
+      "step": 447
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 7.486033519553073e-05,
+      "loss": 1.4424,
+      "step": 448
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 7.458100558659218e-05,
+      "loss": 1.2836,
+      "step": 449
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 7.430167597765365e-05,
+      "loss": 1.4322,
+      "step": 450
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 7.402234636871509e-05,
+      "loss": 1.4168,
+      "step": 451
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 7.374301675977654e-05,
+      "loss": 1.3892,
+      "step": 452
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 7.346368715083799e-05,
+      "loss": 1.6538,
+      "step": 453
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 7.318435754189944e-05,
+      "loss": 1.4573,
+      "step": 454
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 7.29050279329609e-05,
+      "loss": 1.4593,
+      "step": 455
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 7.262569832402235e-05,
+      "loss": 1.4316,
+      "step": 456
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 7.23463687150838e-05,
+      "loss": 1.2702,
+      "step": 457
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 7.206703910614526e-05,
+      "loss": 1.5458,
+      "step": 458
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 7.178770949720671e-05,
+      "loss": 1.5179,
+      "step": 459
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 7.150837988826816e-05,
+      "loss": 1.3844,
+      "step": 460
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 7.122905027932961e-05,
+      "loss": 1.3698,
+      "step": 461
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 7.094972067039107e-05,
+      "loss": 1.4396,
+      "step": 462
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 7.067039106145251e-05,
+      "loss": 1.5486,
+      "step": 463
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 7.039106145251397e-05,
+      "loss": 1.2032,
+      "step": 464
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 7.011173184357543e-05,
+      "loss": 1.3434,
+      "step": 465
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 6.983240223463688e-05,
+      "loss": 1.4065,
+      "step": 466
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 6.955307262569832e-05,
+      "loss": 1.3362,
+      "step": 467
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 6.927374301675979e-05,
+      "loss": 1.375,
+      "step": 468
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 6.899441340782124e-05,
+      "loss": 1.4549,
+      "step": 469
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 6.871508379888269e-05,
+      "loss": 1.3724,
+      "step": 470
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 6.843575418994413e-05,
+      "loss": 1.1602,
+      "step": 471
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 6.815642458100558e-05,
+      "loss": 1.4346,
+      "step": 472
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 6.787709497206705e-05,
+      "loss": 1.2877,
+      "step": 473
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 6.759776536312849e-05,
+      "loss": 1.394,
+      "step": 474
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 6.731843575418994e-05,
+      "loss": 1.3387,
+      "step": 475
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 6.70391061452514e-05,
+      "loss": 1.41,
+      "step": 476
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 6.675977653631286e-05,
+      "loss": 1.4299,
+      "step": 477
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 6.64804469273743e-05,
+      "loss": 1.3824,
+      "step": 478
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 6.620111731843575e-05,
+      "loss": 1.2656,
+      "step": 479
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 6.59217877094972e-05,
+      "loss": 1.2811,
+      "step": 480
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 6.564245810055866e-05,
+      "loss": 1.6839,
+      "step": 481
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 6.536312849162011e-05,
+      "loss": 1.3089,
+      "step": 482
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 6.508379888268157e-05,
+      "loss": 1.4323,
+      "step": 483
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 6.480446927374302e-05,
+      "loss": 1.3439,
+      "step": 484
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 6.452513966480447e-05,
+      "loss": 1.3614,
+      "step": 485
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 6.424581005586592e-05,
+      "loss": 1.4974,
+      "step": 486
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 6.396648044692738e-05,
+      "loss": 1.4963,
+      "step": 487
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 6.368715083798883e-05,
+      "loss": 1.2902,
+      "step": 488
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 6.340782122905028e-05,
+      "loss": 1.3226,
+      "step": 489
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 6.312849162011174e-05,
+      "loss": 1.4353,
+      "step": 490
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 6.284916201117319e-05,
+      "loss": 1.281,
+      "step": 491
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 6.256983240223464e-05,
+      "loss": 1.3755,
+      "step": 492
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 6.22905027932961e-05,
+      "loss": 1.3811,
+      "step": 493
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 6.201117318435755e-05,
+      "loss": 1.4627,
+      "step": 494
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 6.1731843575419e-05,
+      "loss": 1.3482,
+      "step": 495
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 6.145251396648045e-05,
+      "loss": 1.4274,
+      "step": 496
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 6.11731843575419e-05,
+      "loss": 1.3465,
+      "step": 497
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 6.089385474860335e-05,
+      "loss": 1.2319,
+      "step": 498
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 6.061452513966481e-05,
+      "loss": 1.2835,
+      "step": 499
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 6.0335195530726265e-05,
+      "loss": 1.4836,
+      "step": 500
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 6.005586592178771e-05,
+      "loss": 1.3878,
+      "step": 501
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 5.9776536312849164e-05,
+      "loss": 1.4367,
+      "step": 502
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 5.949720670391061e-05,
+      "loss": 1.2994,
+      "step": 503
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 5.9217877094972076e-05,
+      "loss": 1.3599,
+      "step": 504
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 5.893854748603352e-05,
+      "loss": 1.5357,
+      "step": 505
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 5.8659217877094976e-05,
+      "loss": 1.4497,
+      "step": 506
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 5.837988826815642e-05,
+      "loss": 1.3496,
+      "step": 507
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 5.810055865921789e-05,
+      "loss": 1.294,
+      "step": 508
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 5.7821229050279334e-05,
+      "loss": 1.4204,
+      "step": 509
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 5.754189944134079e-05,
+      "loss": 1.5231,
+      "step": 510
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 5.726256983240223e-05,
+      "loss": 1.3165,
+      "step": 511
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 5.6983240223463686e-05,
+      "loss": 1.0796,
+      "step": 512
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 5.6703910614525146e-05,
+      "loss": 1.4086,
+      "step": 513
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 5.64245810055866e-05,
+      "loss": 1.2895,
+      "step": 514
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 5.6145251396648045e-05,
+      "loss": 1.3024,
+      "step": 515
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 5.58659217877095e-05,
+      "loss": 1.2479,
+      "step": 516
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 5.558659217877096e-05,
+      "loss": 1.5232,
+      "step": 517
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 5.530726256983241e-05,
+      "loss": 1.2654,
+      "step": 518
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 5.502793296089386e-05,
+      "loss": 1.3018,
+      "step": 519
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 5.474860335195531e-05,
+      "loss": 1.3077,
+      "step": 520
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 5.4469273743016756e-05,
+      "loss": 1.3501,
+      "step": 521
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 5.4189944134078215e-05,
+      "loss": 1.2607,
+      "step": 522
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 5.391061452513967e-05,
+      "loss": 1.3819,
+      "step": 523
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 5.363128491620112e-05,
+      "loss": 1.321,
+      "step": 524
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 5.335195530726257e-05,
+      "loss": 1.3351,
+      "step": 525
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 5.307262569832403e-05,
+      "loss": 1.2205,
+      "step": 526
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 5.279329608938548e-05,
+      "loss": 1.2579,
+      "step": 527
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 5.251396648044693e-05,
+      "loss": 1.2771,
+      "step": 528
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 5.223463687150838e-05,
+      "loss": 1.3492,
+      "step": 529
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 5.195530726256983e-05,
+      "loss": 1.3232,
+      "step": 530
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 5.167597765363129e-05,
+      "loss": 1.2223,
+      "step": 531
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 5.139664804469274e-05,
+      "loss": 1.3983,
+      "step": 532
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 5.111731843575419e-05,
+      "loss": 1.2987,
+      "step": 533
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 5.0837988826815644e-05,
+      "loss": 1.3717,
+      "step": 534
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 5.05586592178771e-05,
+      "loss": 1.4467,
+      "step": 535
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 5.027932960893855e-05,
+      "loss": 1.4314,
+      "step": 536
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 5e-05,
+      "loss": 1.6593,
+      "step": 537
+    },
+    {
+      "epoch": 3.01,
+      "learning_rate": 4.9720670391061455e-05,
+      "loss": 1.3425,
+      "step": 538
+    },
+    {
+      "epoch": 3.01,
+      "learning_rate": 4.944134078212291e-05,
+      "loss": 1.4171,
+      "step": 539
+    },
+    {
+      "epoch": 3.02,
+      "learning_rate": 4.916201117318436e-05,
+      "loss": 1.3766,
+      "step": 540
+    },
+    {
+      "epoch": 3.02,
+      "learning_rate": 4.8882681564245814e-05,
+      "loss": 1.1605,
+      "step": 541
+    },
+    {
+      "epoch": 3.03,
+      "learning_rate": 4.860335195530727e-05,
+      "loss": 1.3132,
+      "step": 542
+    },
+    {
+      "epoch": 3.03,
+      "learning_rate": 4.832402234636872e-05,
+      "loss": 1.4128,
+      "step": 543
+    },
+    {
+      "epoch": 3.04,
+      "learning_rate": 4.8044692737430166e-05,
+      "loss": 1.4902,
+      "step": 544
+    },
+    {
+      "epoch": 3.04,
+      "learning_rate": 4.7765363128491626e-05,
+      "loss": 1.1832,
+      "step": 545
+    },
+    {
+      "epoch": 3.05,
+      "learning_rate": 4.748603351955307e-05,
+      "loss": 1.2019,
+      "step": 546
+    },
+    {
+      "epoch": 3.06,
+      "learning_rate": 4.7206703910614525e-05,
+      "loss": 1.2753,
+      "step": 547
+    },
+    {
+      "epoch": 3.06,
+      "learning_rate": 4.692737430167598e-05,
+      "loss": 1.2745,
+      "step": 548
+    },
+    {
+      "epoch": 3.07,
+      "learning_rate": 4.664804469273743e-05,
+      "loss": 1.3944,
+      "step": 549
+    },
+    {
+      "epoch": 3.07,
+      "learning_rate": 4.6368715083798884e-05,
+      "loss": 1.3676,
+      "step": 550
+    },
+    {
+      "epoch": 3.08,
+      "learning_rate": 4.6089385474860336e-05,
+      "loss": 1.3226,
+      "step": 551
+    },
+    {
+      "epoch": 3.08,
+      "learning_rate": 4.581005586592179e-05,
+      "loss": 1.134,
+      "step": 552
+    },
+    {
+      "epoch": 3.09,
+      "learning_rate": 4.553072625698324e-05,
+      "loss": 1.2143,
+      "step": 553
+    },
+    {
+      "epoch": 3.09,
+      "learning_rate": 4.5251396648044695e-05,
+      "loss": 1.2543,
+      "step": 554
+    },
+    {
+      "epoch": 3.1,
+      "learning_rate": 4.497206703910615e-05,
+      "loss": 1.2136,
+      "step": 555
+    },
+    {
+      "epoch": 3.11,
+      "learning_rate": 4.4692737430167594e-05,
+      "loss": 1.5303,
+      "step": 556
+    },
+    {
+      "epoch": 3.11,
+      "learning_rate": 4.4413407821229054e-05,
+      "loss": 1.2461,
+      "step": 557
+    },
+    {
+      "epoch": 3.12,
+      "learning_rate": 4.41340782122905e-05,
+      "loss": 1.3282,
+      "step": 558
+    },
+    {
+      "epoch": 3.12,
+      "learning_rate": 4.385474860335196e-05,
+      "loss": 1.201,
+      "step": 559
+    },
+    {
+      "epoch": 3.13,
+      "learning_rate": 4.3575418994413406e-05,
+      "loss": 1.188,
+      "step": 560
+    },
+    {
+      "epoch": 3.13,
+      "learning_rate": 4.3296089385474866e-05,
+      "loss": 1.2299,
+      "step": 561
+    },
+    {
+      "epoch": 3.14,
+      "learning_rate": 4.301675977653631e-05,
+      "loss": 1.2713,
+      "step": 562
+    },
+    {
+      "epoch": 3.15,
+      "learning_rate": 4.273743016759777e-05,
+      "loss": 1.2606,
+      "step": 563
+    },
+    {
+      "epoch": 3.15,
+      "learning_rate": 4.245810055865922e-05,
+      "loss": 1.2021,
+      "step": 564
+    },
+    {
+      "epoch": 3.16,
+      "learning_rate": 4.217877094972068e-05,
+      "loss": 1.243,
+      "step": 565
+    },
+    {
+      "epoch": 3.16,
+      "learning_rate": 4.1899441340782123e-05,
+      "loss": 1.2973,
+      "step": 566
+    },
+    {
+      "epoch": 3.17,
+      "learning_rate": 4.1620111731843576e-05,
+      "loss": 1.2369,
+      "step": 567
+    },
+    {
+      "epoch": 3.17,
+      "learning_rate": 4.134078212290503e-05,
+      "loss": 1.2729,
+      "step": 568
+    },
+    {
+      "epoch": 3.18,
+      "learning_rate": 4.106145251396648e-05,
+      "loss": 1.1511,
+      "step": 569
+    },
+    {
+      "epoch": 3.18,
+      "learning_rate": 4.0782122905027935e-05,
+      "loss": 1.3134,
+      "step": 570
+    },
+    {
+      "epoch": 3.19,
+      "learning_rate": 4.050279329608939e-05,
+      "loss": 1.3388,
+      "step": 571
+    },
+    {
+      "epoch": 3.2,
+      "learning_rate": 4.022346368715084e-05,
+      "loss": 1.3224,
+      "step": 572
+    },
+    {
+      "epoch": 3.2,
+      "learning_rate": 3.9944134078212294e-05,
+      "loss": 1.2827,
+      "step": 573
+    },
+    {
+      "epoch": 3.21,
+      "learning_rate": 3.966480446927375e-05,
+      "loss": 1.5265,
+      "step": 574
+    },
+    {
+      "epoch": 3.21,
+      "learning_rate": 3.93854748603352e-05,
+      "loss": 1.4008,
+      "step": 575
+    },
+    {
+      "epoch": 3.22,
+      "learning_rate": 3.9106145251396646e-05,
+      "loss": 1.1727,
+      "step": 576
+    },
+    {
+      "epoch": 3.22,
+      "learning_rate": 3.8826815642458106e-05,
+      "loss": 1.1999,
+      "step": 577
+    },
+    {
+      "epoch": 3.23,
+      "learning_rate": 3.854748603351955e-05,
+      "loss": 1.2031,
+      "step": 578
+    },
+    {
+      "epoch": 3.23,
+      "learning_rate": 3.826815642458101e-05,
+      "loss": 1.1469,
+      "step": 579
+    },
+    {
+      "epoch": 3.24,
+      "learning_rate": 3.798882681564246e-05,
+      "loss": 1.2784,
+      "step": 580
+    },
+    {
+      "epoch": 3.25,
+      "learning_rate": 3.770949720670392e-05,
+      "loss": 1.262,
+      "step": 581
+    },
+    {
+      "epoch": 3.25,
+      "learning_rate": 3.743016759776536e-05,
+      "loss": 1.224,
+      "step": 582
+    },
+    {
+      "epoch": 3.26,
+      "learning_rate": 3.715083798882682e-05,
+      "loss": 1.3554,
+      "step": 583
+    },
+    {
+      "epoch": 3.26,
+      "learning_rate": 3.687150837988827e-05,
+      "loss": 1.5137,
+      "step": 584
+    },
+    {
+      "epoch": 3.27,
+      "learning_rate": 3.659217877094972e-05,
+      "loss": 1.2462,
+      "step": 585
+    },
+    {
+      "epoch": 3.27,
+      "learning_rate": 3.6312849162011175e-05,
+      "loss": 1.2217,
+      "step": 586
+    },
+    {
+      "epoch": 3.28,
+      "learning_rate": 3.603351955307263e-05,
+      "loss": 1.2346,
+      "step": 587
+    },
+    {
+      "epoch": 3.28,
+      "learning_rate": 3.575418994413408e-05,
+      "loss": 1.3059,
+      "step": 588
+    },
+    {
+      "epoch": 3.29,
+      "learning_rate": 3.5474860335195534e-05,
+      "loss": 1.2355,
+      "step": 589
+    },
+    {
+      "epoch": 3.3,
+      "learning_rate": 3.519553072625699e-05,
+      "loss": 1.2233,
+      "step": 590
+    },
+    {
+      "epoch": 3.3,
+      "learning_rate": 3.491620111731844e-05,
+      "loss": 1.2014,
+      "step": 591
+    },
+    {
+      "epoch": 3.31,
+      "learning_rate": 3.463687150837989e-05,
+      "loss": 1.1919,
+      "step": 592
+    },
+    {
+      "epoch": 3.31,
+      "learning_rate": 3.4357541899441345e-05,
+      "loss": 1.2905,
+      "step": 593
+    },
+    {
+      "epoch": 3.32,
+      "learning_rate": 3.407821229050279e-05,
+      "loss": 1.0858,
+      "step": 594
+    },
+    {
+      "epoch": 3.32,
+      "learning_rate": 3.3798882681564244e-05,
+      "loss": 1.087,
+      "step": 595
+    },
+    {
+      "epoch": 3.33,
+      "learning_rate": 3.35195530726257e-05,
+      "loss": 1.1205,
+      "step": 596
+    },
+    {
+      "epoch": 3.34,
+      "learning_rate": 3.324022346368715e-05,
+      "loss": 1.1657,
+      "step": 597
+    },
+    {
+      "epoch": 3.34,
+      "learning_rate": 3.29608938547486e-05,
+      "loss": 1.5024,
+      "step": 598
+    },
+    {
+      "epoch": 3.35,
+      "learning_rate": 3.2681564245810056e-05,
+      "loss": 1.246,
+      "step": 599
+    },
+    {
+      "epoch": 3.35,
+      "learning_rate": 3.240223463687151e-05,
+      "loss": 1.4441,
+      "step": 600
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 716,
+  "num_train_epochs": 4,
+  "save_steps": 100,
+  "total_flos": 3.0851814594392064e+17,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-600/training_args.bin b/checkpoint-600/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c8672c716e925d0028b4938db147703f58656ff7
--- /dev/null
+++ b/checkpoint-600/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:188ae1c421cc0c6435d1f71d8d3423ac4abc7dba0e6fc2efcbc4dbe77c741317
+size 4027
diff --git a/checkpoint-700/README.md b/checkpoint-700/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..08371015f02382e6fcba318f4aaea54ae52cd3c4
--- /dev/null
+++ b/checkpoint-700/README.md
@@ -0,0 +1,34 @@
+---
+library_name: peft
+---
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: True
+- load_in_4bit: False
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: True
+- load_in_4bit: False
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+### Framework versions
+
+- PEFT 0.6.0.dev0
+
+- PEFT 0.6.0.dev0
diff --git a/checkpoint-700/adapter_config.json b/checkpoint-700/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..c661f74e40394c079de68f07861d73c341803b67
--- /dev/null
+++ b/checkpoint-700/adapter_config.json
@@ -0,0 +1,25 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "bigscience/bloomz-3b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "dense_4h_to_h",
+    "dense",
+    "dense_h_to_4h",
+    "query_key_value"
+  ],
+  "task_type": "CAUSAL_LM"
+}
\ No newline at end of file
diff --git a/checkpoint-700/adapter_model.bin b/checkpoint-700/adapter_model.bin
new file mode 100644
index 0000000000000000000000000000000000000000..0caec0282fb2027bbfc211849f9ba41039610438
--- /dev/null
+++ b/checkpoint-700/adapter_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d1b6626d0b27d106d068977d6a30f5fc34a5a358b55dafa50ff163993945015
+size 39409357
diff --git a/checkpoint-700/optimizer.pt b/checkpoint-700/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d65c53f0bec067303125e293857bdec3e9a6e893
--- /dev/null
+++ b/checkpoint-700/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ae4fe25030e7252e0627af5e03d7f17a8d31b5da0e6730e68e43565c8cd8867
+size 78844421
diff --git a/checkpoint-700/rng_state.pth b/checkpoint-700/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..452f99ac534b9117d836494d73222e3d44e1523b
--- /dev/null
+++ b/checkpoint-700/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6869750f95a25c4e970298a33adf90e2d7ab52680bf3317239bff1b10103235
+size 14575
diff --git a/checkpoint-700/scheduler.pt b/checkpoint-700/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..1358aafe4baa4670638ee88564b818147a3ea246
--- /dev/null
+++ b/checkpoint-700/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed66937ddb6bbdab2dab1a50e3279ef0e50829c8752c931e65a10f8a8aed77af
+size 627
diff --git a/checkpoint-700/special_tokens_map.json b/checkpoint-700/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..fdafe480f024ff444c7492147536765ce5d55a2d
--- /dev/null
+++ b/checkpoint-700/special_tokens_map.json
@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}
diff --git a/checkpoint-700/tokenizer.json b/checkpoint-700/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..673c31abdeadf6576c3c754df86459e1ad64e207
--- /dev/null
+++ b/checkpoint-700/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85b00d7db4df5df2e3f01cacc3feda246002a672f3356eec7f4b04a22eb0dfbe
+size 14500570
diff --git a/checkpoint-700/tokenizer_config.json b/checkpoint-700/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..4b56cc9c2965c07132c35df3e2972e93d98c82c3
--- /dev/null
+++ b/checkpoint-700/tokenizer_config.json
@@ -0,0 +1,10 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "BloomTokenizer",
+  "unk_token": "<unk>"
+}
diff --git a/checkpoint-700/trainer_state.json b/checkpoint-700/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..9168ec3620e1259528cd292a3d325413a2bd0a9a
--- /dev/null
+++ b/checkpoint-700/trainer_state.json
@@ -0,0 +1,4219 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.910614525139665,
+  "eval_steps": 500,
+  "global_step": 700,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00019972067039106145,
+      "loss": 2.6443,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00019944134078212292,
+      "loss": 2.4104,
+      "step": 2
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00019916201117318435,
+      "loss": 2.4975,
+      "step": 3
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00019888268156424582,
+      "loss": 2.3513,
+      "step": 4
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0001986033519553073,
+      "loss": 2.4274,
+      "step": 5
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00019832402234636873,
+      "loss": 2.3628,
+      "step": 6
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0001980446927374302,
+      "loss": 2.3567,
+      "step": 7
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00019776536312849163,
+      "loss": 2.4121,
+      "step": 8
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00019748603351955307,
+      "loss": 2.4033,
+      "step": 9
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00019720670391061454,
+      "loss": 2.2805,
+      "step": 10
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00019692737430167598,
+      "loss": 2.2639,
+      "step": 11
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00019664804469273744,
+      "loss": 2.2724,
+      "step": 12
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00019636871508379888,
+      "loss": 2.332,
+      "step": 13
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00019608938547486035,
+      "loss": 2.2261,
+      "step": 14
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00019581005586592182,
+      "loss": 2.2208,
+      "step": 15
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00019553072625698326,
+      "loss": 2.3351,
+      "step": 16
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0001952513966480447,
+      "loss": 2.2475,
+      "step": 17
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00019497206703910616,
+      "loss": 2.3283,
+      "step": 18
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0001946927374301676,
+      "loss": 2.1346,
+      "step": 19
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00019441340782122907,
+      "loss": 2.131,
+      "step": 20
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0001941340782122905,
+      "loss": 2.1718,
+      "step": 21
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00019385474860335195,
+      "loss": 2.2446,
+      "step": 22
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0001935754189944134,
+      "loss": 2.306,
+      "step": 23
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00019329608938547488,
+      "loss": 2.1908,
+      "step": 24
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00019301675977653632,
+      "loss": 2.2844,
+      "step": 25
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00019273743016759779,
+      "loss": 2.2235,
+      "step": 26
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00019245810055865922,
+      "loss": 2.1842,
+      "step": 27
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00019217877094972066,
+      "loss": 2.2675,
+      "step": 28
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00019189944134078213,
+      "loss": 2.2532,
+      "step": 29
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00019162011173184357,
+      "loss": 2.1788,
+      "step": 30
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00019134078212290504,
+      "loss": 2.2494,
+      "step": 31
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0001910614525139665,
+      "loss": 2.1995,
+      "step": 32
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00019078212290502794,
+      "loss": 2.1451,
+      "step": 33
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0001905027932960894,
+      "loss": 2.223,
+      "step": 34
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00019022346368715085,
+      "loss": 2.2854,
+      "step": 35
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0001899441340782123,
+      "loss": 2.2265,
+      "step": 36
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00018966480446927375,
+      "loss": 2.1214,
+      "step": 37
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0001893854748603352,
+      "loss": 2.1898,
+      "step": 38
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00018910614525139666,
+      "loss": 2.1974,
+      "step": 39
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0001888268156424581,
+      "loss": 2.2259,
+      "step": 40
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00018854748603351957,
+      "loss": 2.2094,
+      "step": 41
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00018826815642458103,
+      "loss": 2.1731,
+      "step": 42
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00018798882681564247,
+      "loss": 2.2373,
+      "step": 43
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0001877094972067039,
+      "loss": 2.2295,
+      "step": 44
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00018743016759776538,
+      "loss": 2.1947,
+      "step": 45
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00018715083798882682,
+      "loss": 2.2115,
+      "step": 46
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00018687150837988828,
+      "loss": 2.1224,
+      "step": 47
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00018659217877094972,
+      "loss": 2.2137,
+      "step": 48
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00018631284916201116,
+      "loss": 2.2338,
+      "step": 49
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00018603351955307266,
+      "loss": 2.1298,
+      "step": 50
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0001857541899441341,
+      "loss": 2.0883,
+      "step": 51
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00018547486033519553,
+      "loss": 2.1216,
+      "step": 52
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.000185195530726257,
+      "loss": 2.2112,
+      "step": 53
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00018491620111731844,
+      "loss": 2.1224,
+      "step": 54
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0001846368715083799,
+      "loss": 2.2375,
+      "step": 55
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00018435754189944135,
+      "loss": 2.2235,
+      "step": 56
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00018407821229050279,
+      "loss": 2.1682,
+      "step": 57
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00018379888268156425,
+      "loss": 2.2077,
+      "step": 58
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00018351955307262572,
+      "loss": 2.1596,
+      "step": 59
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00018324022346368716,
+      "loss": 2.1311,
+      "step": 60
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00018296089385474862,
+      "loss": 2.1333,
+      "step": 61
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00018268156424581006,
+      "loss": 2.0901,
+      "step": 62
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00018240223463687153,
+      "loss": 2.1971,
+      "step": 63
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00018212290502793297,
+      "loss": 2.2602,
+      "step": 64
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0001818435754189944,
+      "loss": 2.2194,
+      "step": 65
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00018156424581005588,
+      "loss": 2.1218,
+      "step": 66
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00018128491620111731,
+      "loss": 2.2049,
+      "step": 67
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00018100558659217878,
+      "loss": 2.1521,
+      "step": 68
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00018072625698324025,
+      "loss": 2.112,
+      "step": 69
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0001804469273743017,
+      "loss": 2.1906,
+      "step": 70
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00018016759776536313,
+      "loss": 2.1717,
+      "step": 71
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0001798882681564246,
+      "loss": 2.0712,
+      "step": 72
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00017960893854748603,
+      "loss": 2.141,
+      "step": 73
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0001793296089385475,
+      "loss": 2.0656,
+      "step": 74
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00017905027932960894,
+      "loss": 2.1125,
+      "step": 75
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00017877094972067038,
+      "loss": 2.0869,
+      "step": 76
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00017849162011173187,
+      "loss": 2.2478,
+      "step": 77
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0001782122905027933,
+      "loss": 2.1535,
+      "step": 78
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00017793296089385475,
+      "loss": 2.1927,
+      "step": 79
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00017765363128491622,
+      "loss": 2.1213,
+      "step": 80
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00017737430167597766,
+      "loss": 2.0981,
+      "step": 81
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00017709497206703912,
+      "loss": 2.1828,
+      "step": 82
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00017681564245810056,
+      "loss": 2.0562,
+      "step": 83
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.000176536312849162,
+      "loss": 2.1334,
+      "step": 84
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00017625698324022347,
+      "loss": 2.1225,
+      "step": 85
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00017597765363128493,
+      "loss": 2.2098,
+      "step": 86
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00017569832402234637,
+      "loss": 2.1519,
+      "step": 87
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00017541899441340784,
+      "loss": 2.1132,
+      "step": 88
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00017513966480446928,
+      "loss": 2.0333,
+      "step": 89
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00017486033519553075,
+      "loss": 2.2764,
+      "step": 90
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00017458100558659218,
+      "loss": 2.1838,
+      "step": 91
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00017430167597765362,
+      "loss": 2.1386,
+      "step": 92
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0001740223463687151,
+      "loss": 2.1034,
+      "step": 93
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00017374301675977656,
+      "loss": 2.0346,
+      "step": 94
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.000173463687150838,
+      "loss": 2.0274,
+      "step": 95
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00017318435754189946,
+      "loss": 2.1036,
+      "step": 96
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0001729050279329609,
+      "loss": 2.1208,
+      "step": 97
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00017262569832402237,
+      "loss": 2.0572,
+      "step": 98
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0001723463687150838,
+      "loss": 2.1702,
+      "step": 99
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00017206703910614525,
+      "loss": 2.1302,
+      "step": 100
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0001717877094972067,
+      "loss": 2.0175,
+      "step": 101
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00017150837988826815,
+      "loss": 2.1006,
+      "step": 102
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00017122905027932962,
+      "loss": 2.0662,
+      "step": 103
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00017094972067039109,
+      "loss": 1.988,
+      "step": 104
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00017067039106145253,
+      "loss": 2.1008,
+      "step": 105
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00017039106145251396,
+      "loss": 2.1482,
+      "step": 106
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00017011173184357543,
+      "loss": 2.1052,
+      "step": 107
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00016983240223463687,
+      "loss": 2.0978,
+      "step": 108
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00016955307262569834,
+      "loss": 2.1303,
+      "step": 109
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00016927374301675978,
+      "loss": 2.0794,
+      "step": 110
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00016899441340782122,
+      "loss": 2.1059,
+      "step": 111
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0001687150837988827,
+      "loss": 1.9642,
+      "step": 112
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00016843575418994415,
+      "loss": 2.0415,
+      "step": 113
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0001681564245810056,
+      "loss": 2.0795,
+      "step": 114
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00016787709497206705,
+      "loss": 2.0238,
+      "step": 115
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0001675977653631285,
+      "loss": 2.078,
+      "step": 116
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00016731843575418996,
+      "loss": 2.1362,
+      "step": 117
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0001670391061452514,
+      "loss": 2.0552,
+      "step": 118
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00016675977653631284,
+      "loss": 2.213,
+      "step": 119
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0001664804469273743,
+      "loss": 1.9999,
+      "step": 120
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00016620111731843577,
+      "loss": 2.06,
+      "step": 121
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0001659217877094972,
+      "loss": 2.0177,
+      "step": 122
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00016564245810055868,
+      "loss": 2.0504,
+      "step": 123
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00016536312849162012,
+      "loss": 2.0585,
+      "step": 124
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00016508379888268158,
+      "loss": 2.0273,
+      "step": 125
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00016480446927374302,
+      "loss": 2.0549,
+      "step": 126
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00016452513966480446,
+      "loss": 2.044,
+      "step": 127
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00016424581005586593,
+      "loss": 2.0731,
+      "step": 128
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00016396648044692737,
+      "loss": 2.0568,
+      "step": 129
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00016368715083798883,
+      "loss": 2.007,
+      "step": 130
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0001634078212290503,
+      "loss": 2.0707,
+      "step": 131
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00016312849162011174,
+      "loss": 1.9793,
+      "step": 132
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0001628491620111732,
+      "loss": 2.1311,
+      "step": 133
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.00016256983240223465,
+      "loss": 2.0016,
+      "step": 134
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.00016229050279329609,
+      "loss": 1.9945,
+      "step": 135
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00016201117318435755,
+      "loss": 2.0186,
+      "step": 136
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.000161731843575419,
+      "loss": 2.0971,
+      "step": 137
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00016145251396648046,
+      "loss": 2.0883,
+      "step": 138
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00016117318435754192,
+      "loss": 2.0803,
+      "step": 139
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00016089385474860336,
+      "loss": 2.0617,
+      "step": 140
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00016061452513966483,
+      "loss": 2.1265,
+      "step": 141
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00016033519553072627,
+      "loss": 2.0151,
+      "step": 142
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0001600558659217877,
+      "loss": 1.996,
+      "step": 143
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00015977653631284918,
+      "loss": 2.0164,
+      "step": 144
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00015949720670391061,
+      "loss": 2.0314,
+      "step": 145
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00015921787709497208,
+      "loss": 1.9501,
+      "step": 146
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00015893854748603352,
+      "loss": 2.087,
+      "step": 147
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.000158659217877095,
+      "loss": 2.0262,
+      "step": 148
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00015837988826815643,
+      "loss": 2.0765,
+      "step": 149
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0001581005586592179,
+      "loss": 2.105,
+      "step": 150
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00015782122905027933,
+      "loss": 1.9863,
+      "step": 151
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0001575418994413408,
+      "loss": 1.9873,
+      "step": 152
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00015726256983240224,
+      "loss": 2.0094,
+      "step": 153
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.00015698324022346368,
+      "loss": 1.9141,
+      "step": 154
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00015670391061452514,
+      "loss": 1.917,
+      "step": 155
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00015642458100558658,
+      "loss": 2.109,
+      "step": 156
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.00015614525139664805,
+      "loss": 1.9799,
+      "step": 157
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.00015586592178770952,
+      "loss": 1.9571,
+      "step": 158
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00015558659217877096,
+      "loss": 1.9931,
+      "step": 159
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00015530726256983242,
+      "loss": 2.1004,
+      "step": 160
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 0.00015502793296089386,
+      "loss": 2.0385,
+      "step": 161
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0001547486033519553,
+      "loss": 1.9751,
+      "step": 162
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00015446927374301677,
+      "loss": 2.0544,
+      "step": 163
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0001541899441340782,
+      "loss": 2.0069,
+      "step": 164
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.00015391061452513967,
+      "loss": 1.9576,
+      "step": 165
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00015363128491620114,
+      "loss": 1.8991,
+      "step": 166
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00015335195530726258,
+      "loss": 1.9336,
+      "step": 167
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00015307262569832405,
+      "loss": 1.9736,
+      "step": 168
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00015279329608938548,
+      "loss": 1.9702,
+      "step": 169
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00015251396648044692,
+      "loss": 1.9055,
+      "step": 170
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.0001522346368715084,
+      "loss": 2.0503,
+      "step": 171
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00015195530726256983,
+      "loss": 2.0039,
+      "step": 172
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0001516759776536313,
+      "loss": 1.9406,
+      "step": 173
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00015139664804469274,
+      "loss": 2.0525,
+      "step": 174
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0001511173184357542,
+      "loss": 1.9234,
+      "step": 175
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00015083798882681567,
+      "loss": 1.8614,
+      "step": 176
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0001505586592178771,
+      "loss": 1.9616,
+      "step": 177
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.00015027932960893855,
+      "loss": 1.9509,
+      "step": 178
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.9592,
+      "step": 179
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.00014972067039106145,
+      "loss": 1.8991,
+      "step": 180
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.00014944134078212292,
+      "loss": 1.9127,
+      "step": 181
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00014916201117318436,
+      "loss": 1.8982,
+      "step": 182
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.0001488826815642458,
+      "loss": 1.9534,
+      "step": 183
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.0001486033519553073,
+      "loss": 1.7794,
+      "step": 184
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.00014832402234636873,
+      "loss": 1.7958,
+      "step": 185
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.00014804469273743017,
+      "loss": 1.8282,
+      "step": 186
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.00014776536312849164,
+      "loss": 2.0423,
+      "step": 187
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.00014748603351955308,
+      "loss": 1.9282,
+      "step": 188
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.00014720670391061454,
+      "loss": 1.9072,
+      "step": 189
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.00014692737430167598,
+      "loss": 1.8665,
+      "step": 190
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.00014664804469273742,
+      "loss": 1.9021,
+      "step": 191
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0001463687150837989,
+      "loss": 1.7308,
+      "step": 192
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00014608938547486035,
+      "loss": 1.9165,
+      "step": 193
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.0001458100558659218,
+      "loss": 1.842,
+      "step": 194
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.00014553072625698326,
+      "loss": 1.9128,
+      "step": 195
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.0001452513966480447,
+      "loss": 1.8005,
+      "step": 196
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.00014497206703910614,
+      "loss": 1.8547,
+      "step": 197
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.0001446927374301676,
+      "loss": 1.9042,
+      "step": 198
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.00014441340782122905,
+      "loss": 1.8609,
+      "step": 199
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.0001441340782122905,
+      "loss": 1.9591,
+      "step": 200
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.00014385474860335195,
+      "loss": 1.8722,
+      "step": 201
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.00014357541899441342,
+      "loss": 1.8535,
+      "step": 202
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.00014329608938547488,
+      "loss": 1.8676,
+      "step": 203
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.00014301675977653632,
+      "loss": 1.8976,
+      "step": 204
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.00014273743016759776,
+      "loss": 1.7723,
+      "step": 205
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.00014245810055865923,
+      "loss": 1.8165,
+      "step": 206
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00014217877094972067,
+      "loss": 1.7811,
+      "step": 207
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00014189944134078214,
+      "loss": 1.908,
+      "step": 208
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.00014162011173184357,
+      "loss": 1.7663,
+      "step": 209
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.00014134078212290501,
+      "loss": 1.6779,
+      "step": 210
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.0001410614525139665,
+      "loss": 1.9039,
+      "step": 211
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00014078212290502795,
+      "loss": 1.8033,
+      "step": 212
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.00014050279329608939,
+      "loss": 1.8251,
+      "step": 213
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.00014022346368715085,
+      "loss": 1.8505,
+      "step": 214
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0001399441340782123,
+      "loss": 1.8147,
+      "step": 215
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.00013966480446927376,
+      "loss": 1.8419,
+      "step": 216
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.0001393854748603352,
+      "loss": 1.8401,
+      "step": 217
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.00013910614525139664,
+      "loss": 1.8912,
+      "step": 218
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.0001388268156424581,
+      "loss": 1.7548,
+      "step": 219
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.00013854748603351957,
+      "loss": 1.8741,
+      "step": 220
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 0.000138268156424581,
+      "loss": 1.9549,
+      "step": 221
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.00013798882681564248,
+      "loss": 1.9093,
+      "step": 222
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.00013770949720670392,
+      "loss": 1.7896,
+      "step": 223
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.00013743016759776538,
+      "loss": 1.8491,
+      "step": 224
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.00013715083798882682,
+      "loss": 1.7851,
+      "step": 225
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.00013687150837988826,
+      "loss": 1.6992,
+      "step": 226
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.00013659217877094973,
+      "loss": 1.9765,
+      "step": 227
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.00013631284916201117,
+      "loss": 1.8179,
+      "step": 228
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.00013603351955307263,
+      "loss": 1.8548,
+      "step": 229
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.0001357541899441341,
+      "loss": 1.8843,
+      "step": 230
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.00013547486033519554,
+      "loss": 1.9105,
+      "step": 231
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.00013519553072625698,
+      "loss": 1.8748,
+      "step": 232
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.00013491620111731844,
+      "loss": 1.7976,
+      "step": 233
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.00013463687150837988,
+      "loss": 1.7369,
+      "step": 234
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.00013435754189944135,
+      "loss": 1.7808,
+      "step": 235
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.0001340782122905028,
+      "loss": 1.8385,
+      "step": 236
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.00013379888268156423,
+      "loss": 1.8295,
+      "step": 237
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.00013351955307262572,
+      "loss": 1.757,
+      "step": 238
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.00013324022346368716,
+      "loss": 1.7904,
+      "step": 239
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.0001329608938547486,
+      "loss": 1.7632,
+      "step": 240
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.00013268156424581007,
+      "loss": 1.7867,
+      "step": 241
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.0001324022346368715,
+      "loss": 1.8259,
+      "step": 242
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.00013212290502793297,
+      "loss": 1.6655,
+      "step": 243
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.0001318435754189944,
+      "loss": 1.6848,
+      "step": 244
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.00013156424581005585,
+      "loss": 1.7931,
+      "step": 245
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.00013128491620111732,
+      "loss": 1.7868,
+      "step": 246
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.00013100558659217879,
+      "loss": 1.7732,
+      "step": 247
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.00013072625698324022,
+      "loss": 1.7851,
+      "step": 248
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.0001304469273743017,
+      "loss": 1.7406,
+      "step": 249
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.00013016759776536313,
+      "loss": 1.5853,
+      "step": 250
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.0001298882681564246,
+      "loss": 1.8271,
+      "step": 251
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.00012960893854748604,
+      "loss": 1.6054,
+      "step": 252
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.00012932960893854748,
+      "loss": 1.6884,
+      "step": 253
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.00012905027932960894,
+      "loss": 1.7333,
+      "step": 254
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.00012877094972067038,
+      "loss": 1.803,
+      "step": 255
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.00012849162011173185,
+      "loss": 1.63,
+      "step": 256
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.00012821229050279331,
+      "loss": 1.8023,
+      "step": 257
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.00012793296089385475,
+      "loss": 1.762,
+      "step": 258
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.00012765363128491622,
+      "loss": 1.7565,
+      "step": 259
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.00012737430167597766,
+      "loss": 1.5937,
+      "step": 260
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.0001270949720670391,
+      "loss": 1.7208,
+      "step": 261
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.00012681564245810057,
+      "loss": 1.8097,
+      "step": 262
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.000126536312849162,
+      "loss": 1.7042,
+      "step": 263
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.00012625698324022347,
+      "loss": 1.7892,
+      "step": 264
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 0.00012597765363128494,
+      "loss": 1.752,
+      "step": 265
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.00012569832402234638,
+      "loss": 1.7333,
+      "step": 266
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.00012541899441340784,
+      "loss": 1.7492,
+      "step": 267
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.00012513966480446928,
+      "loss": 1.818,
+      "step": 268
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.00012486033519553072,
+      "loss": 1.7146,
+      "step": 269
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 0.0001245810055865922,
+      "loss": 1.7958,
+      "step": 270
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 0.00012430167597765363,
+      "loss": 1.7212,
+      "step": 271
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 0.0001240223463687151,
+      "loss": 1.8835,
+      "step": 272
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 0.00012374301675977656,
+      "loss": 1.7486,
+      "step": 273
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 0.000123463687150838,
+      "loss": 1.8103,
+      "step": 274
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 0.00012318435754189944,
+      "loss": 1.7557,
+      "step": 275
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 0.0001229050279329609,
+      "loss": 1.6198,
+      "step": 276
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 0.00012262569832402235,
+      "loss": 1.6971,
+      "step": 277
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 0.0001223463687150838,
+      "loss": 1.668,
+      "step": 278
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 0.00012206703910614525,
+      "loss": 1.8795,
+      "step": 279
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 0.0001217877094972067,
+      "loss": 1.6412,
+      "step": 280
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 0.00012150837988826816,
+      "loss": 1.7497,
+      "step": 281
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 0.00012122905027932962,
+      "loss": 1.5577,
+      "step": 282
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 0.00012094972067039108,
+      "loss": 1.8049,
+      "step": 283
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 0.00012067039106145253,
+      "loss": 1.6834,
+      "step": 284
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 0.00012039106145251397,
+      "loss": 1.7978,
+      "step": 285
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.00012011173184357542,
+      "loss": 1.6558,
+      "step": 286
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.00011983240223463687,
+      "loss": 1.7561,
+      "step": 287
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 0.00011955307262569833,
+      "loss": 1.6807,
+      "step": 288
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 0.00011927374301675978,
+      "loss": 1.6937,
+      "step": 289
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 0.00011899441340782122,
+      "loss": 1.6591,
+      "step": 290
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 0.0001187150837988827,
+      "loss": 1.6771,
+      "step": 291
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 0.00011843575418994415,
+      "loss": 1.7743,
+      "step": 292
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 0.00011815642458100559,
+      "loss": 1.5857,
+      "step": 293
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 0.00011787709497206705,
+      "loss": 1.6999,
+      "step": 294
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 0.0001175977653631285,
+      "loss": 1.5661,
+      "step": 295
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 0.00011731843575418995,
+      "loss": 1.7235,
+      "step": 296
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 0.0001170391061452514,
+      "loss": 1.607,
+      "step": 297
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 0.00011675977653631284,
+      "loss": 1.68,
+      "step": 298
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 0.0001164804469273743,
+      "loss": 1.6938,
+      "step": 299
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 0.00011620111731843578,
+      "loss": 1.6315,
+      "step": 300
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 0.00011592178770949722,
+      "loss": 1.6802,
+      "step": 301
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 0.00011564245810055867,
+      "loss": 1.7174,
+      "step": 302
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 0.00011536312849162012,
+      "loss": 1.5212,
+      "step": 303
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 0.00011508379888268157,
+      "loss": 1.5808,
+      "step": 304
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 0.00011480446927374303,
+      "loss": 1.6152,
+      "step": 305
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 0.00011452513966480447,
+      "loss": 1.5435,
+      "step": 306
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 0.00011424581005586592,
+      "loss": 1.6603,
+      "step": 307
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 0.00011396648044692737,
+      "loss": 1.685,
+      "step": 308
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 0.00011368715083798884,
+      "loss": 1.6002,
+      "step": 309
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 0.00011340782122905029,
+      "loss": 1.6046,
+      "step": 310
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 0.00011312849162011174,
+      "loss": 1.5969,
+      "step": 311
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 0.0001128491620111732,
+      "loss": 1.5845,
+      "step": 312
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 0.00011256983240223464,
+      "loss": 1.8183,
+      "step": 313
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 0.00011229050279329609,
+      "loss": 1.6953,
+      "step": 314
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 0.00011201117318435754,
+      "loss": 1.7787,
+      "step": 315
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 0.000111731843575419,
+      "loss": 1.6422,
+      "step": 316
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 0.00011145251396648045,
+      "loss": 1.7034,
+      "step": 317
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 0.00011117318435754192,
+      "loss": 1.7301,
+      "step": 318
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 0.00011089385474860337,
+      "loss": 1.7084,
+      "step": 319
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 0.00011061452513966482,
+      "loss": 1.772,
+      "step": 320
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 0.00011033519553072626,
+      "loss": 1.5733,
+      "step": 321
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 0.00011005586592178771,
+      "loss": 1.6423,
+      "step": 322
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 0.00010977653631284917,
+      "loss": 1.5809,
+      "step": 323
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 0.00010949720670391062,
+      "loss": 1.6781,
+      "step": 324
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 0.00010921787709497207,
+      "loss": 1.6788,
+      "step": 325
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 0.00010893854748603351,
+      "loss": 1.6346,
+      "step": 326
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 0.00010865921787709499,
+      "loss": 1.6634,
+      "step": 327
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 0.00010837988826815643,
+      "loss": 1.7561,
+      "step": 328
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 0.00010810055865921788,
+      "loss": 1.66,
+      "step": 329
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 0.00010782122905027934,
+      "loss": 1.7298,
+      "step": 330
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 0.00010754189944134079,
+      "loss": 1.6893,
+      "step": 331
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 0.00010726256983240224,
+      "loss": 1.7631,
+      "step": 332
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 0.00010698324022346368,
+      "loss": 1.6633,
+      "step": 333
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 0.00010670391061452513,
+      "loss": 1.5388,
+      "step": 334
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 0.00010642458100558659,
+      "loss": 1.6718,
+      "step": 335
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 0.00010614525139664805,
+      "loss": 1.5536,
+      "step": 336
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 0.00010586592178770951,
+      "loss": 1.6483,
+      "step": 337
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 0.00010558659217877096,
+      "loss": 1.5774,
+      "step": 338
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 0.00010530726256983241,
+      "loss": 1.6366,
+      "step": 339
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 0.00010502793296089387,
+      "loss": 1.5567,
+      "step": 340
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 0.0001047486033519553,
+      "loss": 1.5323,
+      "step": 341
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 0.00010446927374301676,
+      "loss": 1.4608,
+      "step": 342
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 0.00010418994413407821,
+      "loss": 1.5933,
+      "step": 343
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 0.00010391061452513966,
+      "loss": 1.6625,
+      "step": 344
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 0.00010363128491620113,
+      "loss": 1.7236,
+      "step": 345
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 0.00010335195530726258,
+      "loss": 1.759,
+      "step": 346
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 0.00010307262569832404,
+      "loss": 1.7248,
+      "step": 347
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 0.00010279329608938548,
+      "loss": 1.5144,
+      "step": 348
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 0.00010251396648044693,
+      "loss": 1.6905,
+      "step": 349
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 0.00010223463687150838,
+      "loss": 1.6119,
+      "step": 350
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 0.00010195530726256983,
+      "loss": 1.5464,
+      "step": 351
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 0.00010167597765363129,
+      "loss": 1.6901,
+      "step": 352
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 0.00010139664804469273,
+      "loss": 1.3511,
+      "step": 353
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 0.0001011173184357542,
+      "loss": 1.5434,
+      "step": 354
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 0.00010083798882681566,
+      "loss": 1.5891,
+      "step": 355
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 0.0001005586592178771,
+      "loss": 1.6658,
+      "step": 356
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 0.00010027932960893855,
+      "loss": 1.5657,
+      "step": 357
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0001,
+      "loss": 1.7005,
+      "step": 358
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 9.972067039106146e-05,
+      "loss": 1.4202,
+      "step": 359
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 9.944134078212291e-05,
+      "loss": 1.5262,
+      "step": 360
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 9.916201117318436e-05,
+      "loss": 1.6323,
+      "step": 361
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 9.888268156424582e-05,
+      "loss": 1.5521,
+      "step": 362
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 9.860335195530727e-05,
+      "loss": 1.5762,
+      "step": 363
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 9.832402234636872e-05,
+      "loss": 1.613,
+      "step": 364
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 9.804469273743018e-05,
+      "loss": 1.4231,
+      "step": 365
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 9.776536312849163e-05,
+      "loss": 1.5706,
+      "step": 366
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 9.748603351955308e-05,
+      "loss": 1.5245,
+      "step": 367
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 9.720670391061453e-05,
+      "loss": 1.4771,
+      "step": 368
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 9.692737430167597e-05,
+      "loss": 1.596,
+      "step": 369
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 9.664804469273744e-05,
+      "loss": 1.537,
+      "step": 370
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 9.636871508379889e-05,
+      "loss": 1.4276,
+      "step": 371
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 9.608938547486033e-05,
+      "loss": 1.4746,
+      "step": 372
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 9.581005586592178e-05,
+      "loss": 1.4374,
+      "step": 373
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 9.553072625698325e-05,
+      "loss": 1.4704,
+      "step": 374
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 9.52513966480447e-05,
+      "loss": 1.5997,
+      "step": 375
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 9.497206703910614e-05,
+      "loss": 1.5034,
+      "step": 376
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 9.46927374301676e-05,
+      "loss": 1.6392,
+      "step": 377
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 9.441340782122905e-05,
+      "loss": 1.5611,
+      "step": 378
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 9.413407821229052e-05,
+      "loss": 1.3384,
+      "step": 379
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 9.385474860335196e-05,
+      "loss": 1.5732,
+      "step": 380
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 9.357541899441341e-05,
+      "loss": 1.3874,
+      "step": 381
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 9.329608938547486e-05,
+      "loss": 1.4139,
+      "step": 382
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 9.301675977653633e-05,
+      "loss": 1.5195,
+      "step": 383
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 9.273743016759777e-05,
+      "loss": 1.4371,
+      "step": 384
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 9.245810055865922e-05,
+      "loss": 1.4411,
+      "step": 385
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 9.217877094972067e-05,
+      "loss": 1.5214,
+      "step": 386
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 9.189944134078213e-05,
+      "loss": 1.4971,
+      "step": 387
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 9.162011173184358e-05,
+      "loss": 1.3453,
+      "step": 388
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 9.134078212290503e-05,
+      "loss": 1.394,
+      "step": 389
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 9.106145251396648e-05,
+      "loss": 1.5058,
+      "step": 390
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 9.078212290502794e-05,
+      "loss": 1.4855,
+      "step": 391
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 9.050279329608939e-05,
+      "loss": 1.4647,
+      "step": 392
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 9.022346368715084e-05,
+      "loss": 1.3435,
+      "step": 393
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 8.99441340782123e-05,
+      "loss": 1.5815,
+      "step": 394
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 8.966480446927375e-05,
+      "loss": 1.4742,
+      "step": 395
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 8.938547486033519e-05,
+      "loss": 1.5389,
+      "step": 396
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 8.910614525139666e-05,
+      "loss": 1.384,
+      "step": 397
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 8.882681564245811e-05,
+      "loss": 1.3967,
+      "step": 398
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 8.854748603351956e-05,
+      "loss": 1.442,
+      "step": 399
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 8.8268156424581e-05,
+      "loss": 1.396,
+      "step": 400
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 8.798882681564247e-05,
+      "loss": 1.4706,
+      "step": 401
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 8.770949720670392e-05,
+      "loss": 1.4217,
+      "step": 402
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 8.743016759776537e-05,
+      "loss": 1.5617,
+      "step": 403
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 8.715083798882681e-05,
+      "loss": 1.5701,
+      "step": 404
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 8.687150837988828e-05,
+      "loss": 1.3659,
+      "step": 405
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 8.659217877094973e-05,
+      "loss": 1.3424,
+      "step": 406
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 8.631284916201118e-05,
+      "loss": 1.5782,
+      "step": 407
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 8.603351955307262e-05,
+      "loss": 1.3355,
+      "step": 408
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 8.575418994413408e-05,
+      "loss": 1.4798,
+      "step": 409
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 8.547486033519554e-05,
+      "loss": 1.3813,
+      "step": 410
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 8.519553072625698e-05,
+      "loss": 1.6011,
+      "step": 411
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 8.491620111731844e-05,
+      "loss": 1.4596,
+      "step": 412
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 8.463687150837989e-05,
+      "loss": 1.4997,
+      "step": 413
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 8.435754189944135e-05,
+      "loss": 1.5255,
+      "step": 414
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 8.40782122905028e-05,
+      "loss": 1.5305,
+      "step": 415
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 8.379888268156425e-05,
+      "loss": 1.3029,
+      "step": 416
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 8.35195530726257e-05,
+      "loss": 1.2046,
+      "step": 417
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 8.324022346368715e-05,
+      "loss": 1.4985,
+      "step": 418
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 8.29608938547486e-05,
+      "loss": 1.3486,
+      "step": 419
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 8.268156424581006e-05,
+      "loss": 1.2839,
+      "step": 420
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 8.240223463687151e-05,
+      "loss": 1.4286,
+      "step": 421
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 8.212290502793296e-05,
+      "loss": 1.3893,
+      "step": 422
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 8.184357541899442e-05,
+      "loss": 1.5477,
+      "step": 423
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 8.156424581005587e-05,
+      "loss": 1.4973,
+      "step": 424
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 8.128491620111732e-05,
+      "loss": 1.3549,
+      "step": 425
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 8.100558659217878e-05,
+      "loss": 1.3966,
+      "step": 426
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 8.072625698324023e-05,
+      "loss": 1.3974,
+      "step": 427
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 8.044692737430168e-05,
+      "loss": 1.5211,
+      "step": 428
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 8.016759776536313e-05,
+      "loss": 1.4751,
+      "step": 429
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 7.988826815642459e-05,
+      "loss": 1.4322,
+      "step": 430
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 7.960893854748604e-05,
+      "loss": 1.5991,
+      "step": 431
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 7.93296089385475e-05,
+      "loss": 1.3288,
+      "step": 432
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 7.905027932960895e-05,
+      "loss": 1.4098,
+      "step": 433
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 7.87709497206704e-05,
+      "loss": 1.4819,
+      "step": 434
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 7.849162011173184e-05,
+      "loss": 1.4003,
+      "step": 435
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 7.821229050279329e-05,
+      "loss": 1.3475,
+      "step": 436
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 7.793296089385476e-05,
+      "loss": 1.3354,
+      "step": 437
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 7.765363128491621e-05,
+      "loss": 1.3144,
+      "step": 438
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 7.737430167597765e-05,
+      "loss": 1.4118,
+      "step": 439
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 7.70949720670391e-05,
+      "loss": 1.3716,
+      "step": 440
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 7.681564245810057e-05,
+      "loss": 1.4191,
+      "step": 441
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 7.653631284916202e-05,
+      "loss": 1.5173,
+      "step": 442
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 7.625698324022346e-05,
+      "loss": 1.3005,
+      "step": 443
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 7.597765363128491e-05,
+      "loss": 1.4586,
+      "step": 444
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 7.569832402234637e-05,
+      "loss": 1.5086,
+      "step": 445
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 7.541899441340783e-05,
+      "loss": 1.5446,
+      "step": 446
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 7.513966480446927e-05,
+      "loss": 1.3274,
+      "step": 447
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 7.486033519553073e-05,
+      "loss": 1.4424,
+      "step": 448
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 7.458100558659218e-05,
+      "loss": 1.2836,
+      "step": 449
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 7.430167597765365e-05,
+      "loss": 1.4322,
+      "step": 450
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 7.402234636871509e-05,
+      "loss": 1.4168,
+      "step": 451
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 7.374301675977654e-05,
+      "loss": 1.3892,
+      "step": 452
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 7.346368715083799e-05,
+      "loss": 1.6538,
+      "step": 453
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 7.318435754189944e-05,
+      "loss": 1.4573,
+      "step": 454
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 7.29050279329609e-05,
+      "loss": 1.4593,
+      "step": 455
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 7.262569832402235e-05,
+      "loss": 1.4316,
+      "step": 456
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 7.23463687150838e-05,
+      "loss": 1.2702,
+      "step": 457
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 7.206703910614526e-05,
+      "loss": 1.5458,
+      "step": 458
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 7.178770949720671e-05,
+      "loss": 1.5179,
+      "step": 459
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 7.150837988826816e-05,
+      "loss": 1.3844,
+      "step": 460
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 7.122905027932961e-05,
+      "loss": 1.3698,
+      "step": 461
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 7.094972067039107e-05,
+      "loss": 1.4396,
+      "step": 462
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 7.067039106145251e-05,
+      "loss": 1.5486,
+      "step": 463
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 7.039106145251397e-05,
+      "loss": 1.2032,
+      "step": 464
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 7.011173184357543e-05,
+      "loss": 1.3434,
+      "step": 465
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 6.983240223463688e-05,
+      "loss": 1.4065,
+      "step": 466
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 6.955307262569832e-05,
+      "loss": 1.3362,
+      "step": 467
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 6.927374301675979e-05,
+      "loss": 1.375,
+      "step": 468
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 6.899441340782124e-05,
+      "loss": 1.4549,
+      "step": 469
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 6.871508379888269e-05,
+      "loss": 1.3724,
+      "step": 470
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 6.843575418994413e-05,
+      "loss": 1.1602,
+      "step": 471
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 6.815642458100558e-05,
+      "loss": 1.4346,
+      "step": 472
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 6.787709497206705e-05,
+      "loss": 1.2877,
+      "step": 473
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 6.759776536312849e-05,
+      "loss": 1.394,
+      "step": 474
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 6.731843575418994e-05,
+      "loss": 1.3387,
+      "step": 475
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 6.70391061452514e-05,
+      "loss": 1.41,
+      "step": 476
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 6.675977653631286e-05,
+      "loss": 1.4299,
+      "step": 477
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 6.64804469273743e-05,
+      "loss": 1.3824,
+      "step": 478
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 6.620111731843575e-05,
+      "loss": 1.2656,
+      "step": 479
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 6.59217877094972e-05,
+      "loss": 1.2811,
+      "step": 480
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 6.564245810055866e-05,
+      "loss": 1.6839,
+      "step": 481
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 6.536312849162011e-05,
+      "loss": 1.3089,
+      "step": 482
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 6.508379888268157e-05,
+      "loss": 1.4323,
+      "step": 483
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 6.480446927374302e-05,
+      "loss": 1.3439,
+      "step": 484
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 6.452513966480447e-05,
+      "loss": 1.3614,
+      "step": 485
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 6.424581005586592e-05,
+      "loss": 1.4974,
+      "step": 486
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 6.396648044692738e-05,
+      "loss": 1.4963,
+      "step": 487
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 6.368715083798883e-05,
+      "loss": 1.2902,
+      "step": 488
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 6.340782122905028e-05,
+      "loss": 1.3226,
+      "step": 489
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 6.312849162011174e-05,
+      "loss": 1.4353,
+      "step": 490
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 6.284916201117319e-05,
+      "loss": 1.281,
+      "step": 491
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 6.256983240223464e-05,
+      "loss": 1.3755,
+      "step": 492
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 6.22905027932961e-05,
+      "loss": 1.3811,
+      "step": 493
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 6.201117318435755e-05,
+      "loss": 1.4627,
+      "step": 494
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 6.1731843575419e-05,
+      "loss": 1.3482,
+      "step": 495
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 6.145251396648045e-05,
+      "loss": 1.4274,
+      "step": 496
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 6.11731843575419e-05,
+      "loss": 1.3465,
+      "step": 497
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 6.089385474860335e-05,
+      "loss": 1.2319,
+      "step": 498
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 6.061452513966481e-05,
+      "loss": 1.2835,
+      "step": 499
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 6.0335195530726265e-05,
+      "loss": 1.4836,
+      "step": 500
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 6.005586592178771e-05,
+      "loss": 1.3878,
+      "step": 501
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 5.9776536312849164e-05,
+      "loss": 1.4367,
+      "step": 502
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 5.949720670391061e-05,
+      "loss": 1.2994,
+      "step": 503
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 5.9217877094972076e-05,
+      "loss": 1.3599,
+      "step": 504
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 5.893854748603352e-05,
+      "loss": 1.5357,
+      "step": 505
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 5.8659217877094976e-05,
+      "loss": 1.4497,
+      "step": 506
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 5.837988826815642e-05,
+      "loss": 1.3496,
+      "step": 507
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 5.810055865921789e-05,
+      "loss": 1.294,
+      "step": 508
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 5.7821229050279334e-05,
+      "loss": 1.4204,
+      "step": 509
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 5.754189944134079e-05,
+      "loss": 1.5231,
+      "step": 510
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 5.726256983240223e-05,
+      "loss": 1.3165,
+      "step": 511
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 5.6983240223463686e-05,
+      "loss": 1.0796,
+      "step": 512
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 5.6703910614525146e-05,
+      "loss": 1.4086,
+      "step": 513
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 5.64245810055866e-05,
+      "loss": 1.2895,
+      "step": 514
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 5.6145251396648045e-05,
+      "loss": 1.3024,
+      "step": 515
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 5.58659217877095e-05,
+      "loss": 1.2479,
+      "step": 516
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 5.558659217877096e-05,
+      "loss": 1.5232,
+      "step": 517
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 5.530726256983241e-05,
+      "loss": 1.2654,
+      "step": 518
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 5.502793296089386e-05,
+      "loss": 1.3018,
+      "step": 519
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 5.474860335195531e-05,
+      "loss": 1.3077,
+      "step": 520
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 5.4469273743016756e-05,
+      "loss": 1.3501,
+      "step": 521
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 5.4189944134078215e-05,
+      "loss": 1.2607,
+      "step": 522
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 5.391061452513967e-05,
+      "loss": 1.3819,
+      "step": 523
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 5.363128491620112e-05,
+      "loss": 1.321,
+      "step": 524
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 5.335195530726257e-05,
+      "loss": 1.3351,
+      "step": 525
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 5.307262569832403e-05,
+      "loss": 1.2205,
+      "step": 526
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 5.279329608938548e-05,
+      "loss": 1.2579,
+      "step": 527
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 5.251396648044693e-05,
+      "loss": 1.2771,
+      "step": 528
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 5.223463687150838e-05,
+      "loss": 1.3492,
+      "step": 529
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 5.195530726256983e-05,
+      "loss": 1.3232,
+      "step": 530
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 5.167597765363129e-05,
+      "loss": 1.2223,
+      "step": 531
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 5.139664804469274e-05,
+      "loss": 1.3983,
+      "step": 532
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 5.111731843575419e-05,
+      "loss": 1.2987,
+      "step": 533
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 5.0837988826815644e-05,
+      "loss": 1.3717,
+      "step": 534
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 5.05586592178771e-05,
+      "loss": 1.4467,
+      "step": 535
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 5.027932960893855e-05,
+      "loss": 1.4314,
+      "step": 536
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 5e-05,
+      "loss": 1.6593,
+      "step": 537
+    },
+    {
+      "epoch": 3.01,
+      "learning_rate": 4.9720670391061455e-05,
+      "loss": 1.3425,
+      "step": 538
+    },
+    {
+      "epoch": 3.01,
+      "learning_rate": 4.944134078212291e-05,
+      "loss": 1.4171,
+      "step": 539
+    },
+    {
+      "epoch": 3.02,
+      "learning_rate": 4.916201117318436e-05,
+      "loss": 1.3766,
+      "step": 540
+    },
+    {
+      "epoch": 3.02,
+      "learning_rate": 4.8882681564245814e-05,
+      "loss": 1.1605,
+      "step": 541
+    },
+    {
+      "epoch": 3.03,
+      "learning_rate": 4.860335195530727e-05,
+      "loss": 1.3132,
+      "step": 542
+    },
+    {
+      "epoch": 3.03,
+      "learning_rate": 4.832402234636872e-05,
+      "loss": 1.4128,
+      "step": 543
+    },
+    {
+      "epoch": 3.04,
+      "learning_rate": 4.8044692737430166e-05,
+      "loss": 1.4902,
+      "step": 544
+    },
+    {
+      "epoch": 3.04,
+      "learning_rate": 4.7765363128491626e-05,
+      "loss": 1.1832,
+      "step": 545
+    },
+    {
+      "epoch": 3.05,
+      "learning_rate": 4.748603351955307e-05,
+      "loss": 1.2019,
+      "step": 546
+    },
+    {
+      "epoch": 3.06,
+      "learning_rate": 4.7206703910614525e-05,
+      "loss": 1.2753,
+      "step": 547
+    },
+    {
+      "epoch": 3.06,
+      "learning_rate": 4.692737430167598e-05,
+      "loss": 1.2745,
+      "step": 548
+    },
+    {
+      "epoch": 3.07,
+      "learning_rate": 4.664804469273743e-05,
+      "loss": 1.3944,
+      "step": 549
+    },
+    {
+      "epoch": 3.07,
+      "learning_rate": 4.6368715083798884e-05,
+      "loss": 1.3676,
+      "step": 550
+    },
+    {
+      "epoch": 3.08,
+      "learning_rate": 4.6089385474860336e-05,
+      "loss": 1.3226,
+      "step": 551
+    },
+    {
+      "epoch": 3.08,
+      "learning_rate": 4.581005586592179e-05,
+      "loss": 1.134,
+      "step": 552
+    },
+    {
+      "epoch": 3.09,
+      "learning_rate": 4.553072625698324e-05,
+      "loss": 1.2143,
+      "step": 553
+    },
+    {
+      "epoch": 3.09,
+      "learning_rate": 4.5251396648044695e-05,
+      "loss": 1.2543,
+      "step": 554
+    },
+    {
+      "epoch": 3.1,
+      "learning_rate": 4.497206703910615e-05,
+      "loss": 1.2136,
+      "step": 555
+    },
+    {
+      "epoch": 3.11,
+      "learning_rate": 4.4692737430167594e-05,
+      "loss": 1.5303,
+      "step": 556
+    },
+    {
+      "epoch": 3.11,
+      "learning_rate": 4.4413407821229054e-05,
+      "loss": 1.2461,
+      "step": 557
+    },
+    {
+      "epoch": 3.12,
+      "learning_rate": 4.41340782122905e-05,
+      "loss": 1.3282,
+      "step": 558
+    },
+    {
+      "epoch": 3.12,
+      "learning_rate": 4.385474860335196e-05,
+      "loss": 1.201,
+      "step": 559
+    },
+    {
+      "epoch": 3.13,
+      "learning_rate": 4.3575418994413406e-05,
+      "loss": 1.188,
+      "step": 560
+    },
+    {
+      "epoch": 3.13,
+      "learning_rate": 4.3296089385474866e-05,
+      "loss": 1.2299,
+      "step": 561
+    },
+    {
+      "epoch": 3.14,
+      "learning_rate": 4.301675977653631e-05,
+      "loss": 1.2713,
+      "step": 562
+    },
+    {
+      "epoch": 3.15,
+      "learning_rate": 4.273743016759777e-05,
+      "loss": 1.2606,
+      "step": 563
+    },
+    {
+      "epoch": 3.15,
+      "learning_rate": 4.245810055865922e-05,
+      "loss": 1.2021,
+      "step": 564
+    },
+    {
+      "epoch": 3.16,
+      "learning_rate": 4.217877094972068e-05,
+      "loss": 1.243,
+      "step": 565
+    },
+    {
+      "epoch": 3.16,
+      "learning_rate": 4.1899441340782123e-05,
+      "loss": 1.2973,
+      "step": 566
+    },
+    {
+      "epoch": 3.17,
+      "learning_rate": 4.1620111731843576e-05,
+      "loss": 1.2369,
+      "step": 567
+    },
+    {
+      "epoch": 3.17,
+      "learning_rate": 4.134078212290503e-05,
+      "loss": 1.2729,
+      "step": 568
+    },
+    {
+      "epoch": 3.18,
+      "learning_rate": 4.106145251396648e-05,
+      "loss": 1.1511,
+      "step": 569
+    },
+    {
+      "epoch": 3.18,
+      "learning_rate": 4.0782122905027935e-05,
+      "loss": 1.3134,
+      "step": 570
+    },
+    {
+      "epoch": 3.19,
+      "learning_rate": 4.050279329608939e-05,
+      "loss": 1.3388,
+      "step": 571
+    },
+    {
+      "epoch": 3.2,
+      "learning_rate": 4.022346368715084e-05,
+      "loss": 1.3224,
+      "step": 572
+    },
+    {
+      "epoch": 3.2,
+      "learning_rate": 3.9944134078212294e-05,
+      "loss": 1.2827,
+      "step": 573
+    },
+    {
+      "epoch": 3.21,
+      "learning_rate": 3.966480446927375e-05,
+      "loss": 1.5265,
+      "step": 574
+    },
+    {
+      "epoch": 3.21,
+      "learning_rate": 3.93854748603352e-05,
+      "loss": 1.4008,
+      "step": 575
+    },
+    {
+      "epoch": 3.22,
+      "learning_rate": 3.9106145251396646e-05,
+      "loss": 1.1727,
+      "step": 576
+    },
+    {
+      "epoch": 3.22,
+      "learning_rate": 3.8826815642458106e-05,
+      "loss": 1.1999,
+      "step": 577
+    },
+    {
+      "epoch": 3.23,
+      "learning_rate": 3.854748603351955e-05,
+      "loss": 1.2031,
+      "step": 578
+    },
+    {
+      "epoch": 3.23,
+      "learning_rate": 3.826815642458101e-05,
+      "loss": 1.1469,
+      "step": 579
+    },
+    {
+      "epoch": 3.24,
+      "learning_rate": 3.798882681564246e-05,
+      "loss": 1.2784,
+      "step": 580
+    },
+    {
+      "epoch": 3.25,
+      "learning_rate": 3.770949720670392e-05,
+      "loss": 1.262,
+      "step": 581
+    },
+    {
+      "epoch": 3.25,
+      "learning_rate": 3.743016759776536e-05,
+      "loss": 1.224,
+      "step": 582
+    },
+    {
+      "epoch": 3.26,
+      "learning_rate": 3.715083798882682e-05,
+      "loss": 1.3554,
+      "step": 583
+    },
+    {
+      "epoch": 3.26,
+      "learning_rate": 3.687150837988827e-05,
+      "loss": 1.5137,
+      "step": 584
+    },
+    {
+      "epoch": 3.27,
+      "learning_rate": 3.659217877094972e-05,
+      "loss": 1.2462,
+      "step": 585
+    },
+    {
+      "epoch": 3.27,
+      "learning_rate": 3.6312849162011175e-05,
+      "loss": 1.2217,
+      "step": 586
+    },
+    {
+      "epoch": 3.28,
+      "learning_rate": 3.603351955307263e-05,
+      "loss": 1.2346,
+      "step": 587
+    },
+    {
+      "epoch": 3.28,
+      "learning_rate": 3.575418994413408e-05,
+      "loss": 1.3059,
+      "step": 588
+    },
+    {
+      "epoch": 3.29,
+      "learning_rate": 3.5474860335195534e-05,
+      "loss": 1.2355,
+      "step": 589
+    },
+    {
+      "epoch": 3.3,
+      "learning_rate": 3.519553072625699e-05,
+      "loss": 1.2233,
+      "step": 590
+    },
+    {
+      "epoch": 3.3,
+      "learning_rate": 3.491620111731844e-05,
+      "loss": 1.2014,
+      "step": 591
+    },
+    {
+      "epoch": 3.31,
+      "learning_rate": 3.463687150837989e-05,
+      "loss": 1.1919,
+      "step": 592
+    },
+    {
+      "epoch": 3.31,
+      "learning_rate": 3.4357541899441345e-05,
+      "loss": 1.2905,
+      "step": 593
+    },
+    {
+      "epoch": 3.32,
+      "learning_rate": 3.407821229050279e-05,
+      "loss": 1.0858,
+      "step": 594
+    },
+    {
+      "epoch": 3.32,
+      "learning_rate": 3.3798882681564244e-05,
+      "loss": 1.087,
+      "step": 595
+    },
+    {
+      "epoch": 3.33,
+      "learning_rate": 3.35195530726257e-05,
+      "loss": 1.1205,
+      "step": 596
+    },
+    {
+      "epoch": 3.34,
+      "learning_rate": 3.324022346368715e-05,
+      "loss": 1.1657,
+      "step": 597
+    },
+    {
+      "epoch": 3.34,
+      "learning_rate": 3.29608938547486e-05,
+      "loss": 1.5024,
+      "step": 598
+    },
+    {
+      "epoch": 3.35,
+      "learning_rate": 3.2681564245810056e-05,
+      "loss": 1.246,
+      "step": 599
+    },
+    {
+      "epoch": 3.35,
+      "learning_rate": 3.240223463687151e-05,
+      "loss": 1.4441,
+      "step": 600
+    },
+    {
+      "epoch": 3.36,
+      "learning_rate": 3.212290502793296e-05,
+      "loss": 1.19,
+      "step": 601
+    },
+    {
+      "epoch": 3.36,
+      "learning_rate": 3.1843575418994415e-05,
+      "loss": 1.2521,
+      "step": 602
+    },
+    {
+      "epoch": 3.37,
+      "learning_rate": 3.156424581005587e-05,
+      "loss": 1.2051,
+      "step": 603
+    },
+    {
+      "epoch": 3.37,
+      "learning_rate": 3.128491620111732e-05,
+      "loss": 1.4349,
+      "step": 604
+    },
+    {
+      "epoch": 3.38,
+      "learning_rate": 3.1005586592178774e-05,
+      "loss": 0.9633,
+      "step": 605
+    },
+    {
+      "epoch": 3.39,
+      "learning_rate": 3.0726256983240227e-05,
+      "loss": 1.4547,
+      "step": 606
+    },
+    {
+      "epoch": 3.39,
+      "learning_rate": 3.0446927374301676e-05,
+      "loss": 1.2496,
+      "step": 607
+    },
+    {
+      "epoch": 3.4,
+      "learning_rate": 3.0167597765363132e-05,
+      "loss": 1.4193,
+      "step": 608
+    },
+    {
+      "epoch": 3.4,
+      "learning_rate": 2.9888268156424582e-05,
+      "loss": 1.3427,
+      "step": 609
+    },
+    {
+      "epoch": 3.41,
+      "learning_rate": 2.9608938547486038e-05,
+      "loss": 1.3162,
+      "step": 610
+    },
+    {
+      "epoch": 3.41,
+      "learning_rate": 2.9329608938547488e-05,
+      "loss": 1.2194,
+      "step": 611
+    },
+    {
+      "epoch": 3.42,
+      "learning_rate": 2.9050279329608944e-05,
+      "loss": 1.3005,
+      "step": 612
+    },
+    {
+      "epoch": 3.42,
+      "learning_rate": 2.8770949720670394e-05,
+      "loss": 1.2581,
+      "step": 613
+    },
+    {
+      "epoch": 3.43,
+      "learning_rate": 2.8491620111731843e-05,
+      "loss": 1.1465,
+      "step": 614
+    },
+    {
+      "epoch": 3.44,
+      "learning_rate": 2.82122905027933e-05,
+      "loss": 1.1334,
+      "step": 615
+    },
+    {
+      "epoch": 3.44,
+      "learning_rate": 2.793296089385475e-05,
+      "loss": 1.3151,
+      "step": 616
+    },
+    {
+      "epoch": 3.45,
+      "learning_rate": 2.7653631284916205e-05,
+      "loss": 1.3295,
+      "step": 617
+    },
+    {
+      "epoch": 3.45,
+      "learning_rate": 2.7374301675977655e-05,
+      "loss": 1.0037,
+      "step": 618
+    },
+    {
+      "epoch": 3.46,
+      "learning_rate": 2.7094972067039108e-05,
+      "loss": 1.2604,
+      "step": 619
+    },
+    {
+      "epoch": 3.46,
+      "learning_rate": 2.681564245810056e-05,
+      "loss": 1.0984,
+      "step": 620
+    },
+    {
+      "epoch": 3.47,
+      "learning_rate": 2.6536312849162014e-05,
+      "loss": 1.3646,
+      "step": 621
+    },
+    {
+      "epoch": 3.47,
+      "learning_rate": 2.6256983240223466e-05,
+      "loss": 1.3652,
+      "step": 622
+    },
+    {
+      "epoch": 3.48,
+      "learning_rate": 2.5977653631284916e-05,
+      "loss": 1.355,
+      "step": 623
+    },
+    {
+      "epoch": 3.49,
+      "learning_rate": 2.569832402234637e-05,
+      "loss": 1.2907,
+      "step": 624
+    },
+    {
+      "epoch": 3.49,
+      "learning_rate": 2.5418994413407822e-05,
+      "loss": 1.2126,
+      "step": 625
+    },
+    {
+      "epoch": 3.5,
+      "learning_rate": 2.5139664804469275e-05,
+      "loss": 1.1342,
+      "step": 626
+    },
+    {
+      "epoch": 3.5,
+      "learning_rate": 2.4860335195530728e-05,
+      "loss": 1.1031,
+      "step": 627
+    },
+    {
+      "epoch": 3.51,
+      "learning_rate": 2.458100558659218e-05,
+      "loss": 1.2255,
+      "step": 628
+    },
+    {
+      "epoch": 3.51,
+      "learning_rate": 2.4301675977653633e-05,
+      "loss": 1.2866,
+      "step": 629
+    },
+    {
+      "epoch": 3.52,
+      "learning_rate": 2.4022346368715083e-05,
+      "loss": 1.1543,
+      "step": 630
+    },
+    {
+      "epoch": 3.53,
+      "learning_rate": 2.3743016759776536e-05,
+      "loss": 1.2531,
+      "step": 631
+    },
+    {
+      "epoch": 3.53,
+      "learning_rate": 2.346368715083799e-05,
+      "loss": 1.2455,
+      "step": 632
+    },
+    {
+      "epoch": 3.54,
+      "learning_rate": 2.3184357541899442e-05,
+      "loss": 1.2035,
+      "step": 633
+    },
+    {
+      "epoch": 3.54,
+      "learning_rate": 2.2905027932960895e-05,
+      "loss": 1.3482,
+      "step": 634
+    },
+    {
+      "epoch": 3.55,
+      "learning_rate": 2.2625698324022348e-05,
+      "loss": 1.1586,
+      "step": 635
+    },
+    {
+      "epoch": 3.55,
+      "learning_rate": 2.2346368715083797e-05,
+      "loss": 1.1665,
+      "step": 636
+    },
+    {
+      "epoch": 3.56,
+      "learning_rate": 2.206703910614525e-05,
+      "loss": 1.2767,
+      "step": 637
+    },
+    {
+      "epoch": 3.56,
+      "learning_rate": 2.1787709497206703e-05,
+      "loss": 1.302,
+      "step": 638
+    },
+    {
+      "epoch": 3.57,
+      "learning_rate": 2.1508379888268156e-05,
+      "loss": 1.2224,
+      "step": 639
+    },
+    {
+      "epoch": 3.58,
+      "learning_rate": 2.122905027932961e-05,
+      "loss": 1.1817,
+      "step": 640
+    },
+    {
+      "epoch": 3.58,
+      "learning_rate": 2.0949720670391062e-05,
+      "loss": 1.4949,
+      "step": 641
+    },
+    {
+      "epoch": 3.59,
+      "learning_rate": 2.0670391061452515e-05,
+      "loss": 1.2552,
+      "step": 642
+    },
+    {
+      "epoch": 3.59,
+      "learning_rate": 2.0391061452513968e-05,
+      "loss": 1.3075,
+      "step": 643
+    },
+    {
+      "epoch": 3.6,
+      "learning_rate": 2.011173184357542e-05,
+      "loss": 1.1825,
+      "step": 644
+    },
+    {
+      "epoch": 3.6,
+      "learning_rate": 1.9832402234636873e-05,
+      "loss": 1.484,
+      "step": 645
+    },
+    {
+      "epoch": 3.61,
+      "learning_rate": 1.9553072625698323e-05,
+      "loss": 1.1765,
+      "step": 646
+    },
+    {
+      "epoch": 3.61,
+      "learning_rate": 1.9273743016759776e-05,
+      "loss": 1.381,
+      "step": 647
+    },
+    {
+      "epoch": 3.62,
+      "learning_rate": 1.899441340782123e-05,
+      "loss": 1.2835,
+      "step": 648
+    },
+    {
+      "epoch": 3.63,
+      "learning_rate": 1.871508379888268e-05,
+      "loss": 1.235,
+      "step": 649
+    },
+    {
+      "epoch": 3.63,
+      "learning_rate": 1.8435754189944135e-05,
+      "loss": 1.2041,
+      "step": 650
+    },
+    {
+      "epoch": 3.64,
+      "learning_rate": 1.8156424581005588e-05,
+      "loss": 0.9949,
+      "step": 651
+    },
+    {
+      "epoch": 3.64,
+      "learning_rate": 1.787709497206704e-05,
+      "loss": 1.2147,
+      "step": 652
+    },
+    {
+      "epoch": 3.65,
+      "learning_rate": 1.7597765363128493e-05,
+      "loss": 1.3876,
+      "step": 653
+    },
+    {
+      "epoch": 3.65,
+      "learning_rate": 1.7318435754189946e-05,
+      "loss": 1.1255,
+      "step": 654
+    },
+    {
+      "epoch": 3.66,
+      "learning_rate": 1.7039106145251396e-05,
+      "loss": 1.2252,
+      "step": 655
+    },
+    {
+      "epoch": 3.66,
+      "learning_rate": 1.675977653631285e-05,
+      "loss": 1.303,
+      "step": 656
+    },
+    {
+      "epoch": 3.67,
+      "learning_rate": 1.64804469273743e-05,
+      "loss": 1.1023,
+      "step": 657
+    },
+    {
+      "epoch": 3.68,
+      "learning_rate": 1.6201117318435755e-05,
+      "loss": 1.1444,
+      "step": 658
+    },
+    {
+      "epoch": 3.68,
+      "learning_rate": 1.5921787709497207e-05,
+      "loss": 1.1893,
+      "step": 659
+    },
+    {
+      "epoch": 3.69,
+      "learning_rate": 1.564245810055866e-05,
+      "loss": 1.2557,
+      "step": 660
+    },
+    {
+      "epoch": 3.69,
+      "learning_rate": 1.5363128491620113e-05,
+      "loss": 1.3431,
+      "step": 661
+    },
+    {
+      "epoch": 3.7,
+      "learning_rate": 1.5083798882681566e-05,
+      "loss": 1.389,
+      "step": 662
+    },
+    {
+      "epoch": 3.7,
+      "learning_rate": 1.4804469273743019e-05,
+      "loss": 1.0841,
+      "step": 663
+    },
+    {
+      "epoch": 3.71,
+      "learning_rate": 1.4525139664804472e-05,
+      "loss": 1.1225,
+      "step": 664
+    },
+    {
+      "epoch": 3.72,
+      "learning_rate": 1.4245810055865922e-05,
+      "loss": 1.2914,
+      "step": 665
+    },
+    {
+      "epoch": 3.72,
+      "learning_rate": 1.3966480446927374e-05,
+      "loss": 1.2876,
+      "step": 666
+    },
+    {
+      "epoch": 3.73,
+      "learning_rate": 1.3687150837988827e-05,
+      "loss": 1.2285,
+      "step": 667
+    },
+    {
+      "epoch": 3.73,
+      "learning_rate": 1.340782122905028e-05,
+      "loss": 1.0809,
+      "step": 668
+    },
+    {
+      "epoch": 3.74,
+      "learning_rate": 1.3128491620111733e-05,
+      "loss": 1.0506,
+      "step": 669
+    },
+    {
+      "epoch": 3.74,
+      "learning_rate": 1.2849162011173184e-05,
+      "loss": 1.2041,
+      "step": 670
+    },
+    {
+      "epoch": 3.75,
+      "learning_rate": 1.2569832402234637e-05,
+      "loss": 1.1061,
+      "step": 671
+    },
+    {
+      "epoch": 3.75,
+      "learning_rate": 1.229050279329609e-05,
+      "loss": 1.2219,
+      "step": 672
+    },
+    {
+      "epoch": 3.76,
+      "learning_rate": 1.2011173184357542e-05,
+      "loss": 1.0946,
+      "step": 673
+    },
+    {
+      "epoch": 3.77,
+      "learning_rate": 1.1731843575418994e-05,
+      "loss": 1.089,
+      "step": 674
+    },
+    {
+      "epoch": 3.77,
+      "learning_rate": 1.1452513966480447e-05,
+      "loss": 1.237,
+      "step": 675
+    },
+    {
+      "epoch": 3.78,
+      "learning_rate": 1.1173184357541899e-05,
+      "loss": 1.4085,
+      "step": 676
+    },
+    {
+      "epoch": 3.78,
+      "learning_rate": 1.0893854748603351e-05,
+      "loss": 1.2196,
+      "step": 677
+    },
+    {
+      "epoch": 3.79,
+      "learning_rate": 1.0614525139664804e-05,
+      "loss": 1.1506,
+      "step": 678
+    },
+    {
+      "epoch": 3.79,
+      "learning_rate": 1.0335195530726257e-05,
+      "loss": 1.2791,
+      "step": 679
+    },
+    {
+      "epoch": 3.8,
+      "learning_rate": 1.005586592178771e-05,
+      "loss": 1.3344,
+      "step": 680
+    },
+    {
+      "epoch": 3.8,
+      "learning_rate": 9.776536312849161e-06,
+      "loss": 1.3458,
+      "step": 681
+    },
+    {
+      "epoch": 3.81,
+      "learning_rate": 9.497206703910614e-06,
+      "loss": 1.1622,
+      "step": 682
+    },
+    {
+      "epoch": 3.82,
+      "learning_rate": 9.217877094972067e-06,
+      "loss": 1.1179,
+      "step": 683
+    },
+    {
+      "epoch": 3.82,
+      "learning_rate": 8.93854748603352e-06,
+      "loss": 1.2485,
+      "step": 684
+    },
+    {
+      "epoch": 3.83,
+      "learning_rate": 8.659217877094973e-06,
+      "loss": 1.1207,
+      "step": 685
+    },
+    {
+      "epoch": 3.83,
+      "learning_rate": 8.379888268156424e-06,
+      "loss": 1.3791,
+      "step": 686
+    },
+    {
+      "epoch": 3.84,
+      "learning_rate": 8.100558659217877e-06,
+      "loss": 1.2976,
+      "step": 687
+    },
+    {
+      "epoch": 3.84,
+      "learning_rate": 7.82122905027933e-06,
+      "loss": 1.2041,
+      "step": 688
+    },
+    {
+      "epoch": 3.85,
+      "learning_rate": 7.541899441340783e-06,
+      "loss": 1.1002,
+      "step": 689
+    },
+    {
+      "epoch": 3.85,
+      "learning_rate": 7.262569832402236e-06,
+      "loss": 1.2982,
+      "step": 690
+    },
+    {
+      "epoch": 3.86,
+      "learning_rate": 6.983240223463687e-06,
+      "loss": 1.3469,
+      "step": 691
+    },
+    {
+      "epoch": 3.87,
+      "learning_rate": 6.70391061452514e-06,
+      "loss": 1.2923,
+      "step": 692
+    },
+    {
+      "epoch": 3.87,
+      "learning_rate": 6.424581005586592e-06,
+      "loss": 1.3308,
+      "step": 693
+    },
+    {
+      "epoch": 3.88,
+      "learning_rate": 6.145251396648045e-06,
+      "loss": 1.2588,
+      "step": 694
+    },
+    {
+      "epoch": 3.88,
+      "learning_rate": 5.865921787709497e-06,
+      "loss": 1.0669,
+      "step": 695
+    },
+    {
+      "epoch": 3.89,
+      "learning_rate": 5.586592178770949e-06,
+      "loss": 1.4808,
+      "step": 696
+    },
+    {
+      "epoch": 3.89,
+      "learning_rate": 5.307262569832402e-06,
+      "loss": 1.2714,
+      "step": 697
+    },
+    {
+      "epoch": 3.9,
+      "learning_rate": 5.027932960893855e-06,
+      "loss": 1.1979,
+      "step": 698
+    },
+    {
+      "epoch": 3.91,
+      "learning_rate": 4.748603351955307e-06,
+      "loss": 1.2548,
+      "step": 699
+    },
+    {
+      "epoch": 3.91,
+      "learning_rate": 4.46927374301676e-06,
+      "loss": 1.2473,
+      "step": 700
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 716,
+  "num_train_epochs": 4,
+  "save_steps": 100,
+  "total_flos": 3.6028388613095424e+17,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-700/training_args.bin b/checkpoint-700/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c8672c716e925d0028b4938db147703f58656ff7
--- /dev/null
+++ b/checkpoint-700/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:188ae1c421cc0c6435d1f71d8d3423ac4abc7dba0e6fc2efcbc4dbe77c741317
+size 4027