Commit
•
f44f5e1
1
Parent(s):
8c2ad85
Upload folder using huggingface_hub (#2)
Browse files- Upload folder using huggingface_hub (3fc3228c305001f5153783062e25faa45ab205e6)
This view is limited to 50 files because it contains too many changes.
See raw diff
- README.md +0 -13
- adapter_model.bin +1 -1
- checkpoint-100/README.md +34 -0
- checkpoint-100/adapter_config.json +23 -0
- checkpoint-100/adapter_model.bin +3 -0
- checkpoint-100/optimizer.pt +3 -0
- checkpoint-100/rng_state.pth +3 -0
- checkpoint-100/scheduler.pt +3 -0
- checkpoint-100/special_tokens_map.json +6 -0
- checkpoint-100/tokenizer.json +3 -0
- checkpoint-100/tokenizer_config.json +10 -0
- checkpoint-100/trainer_state.json +619 -0
- checkpoint-100/training_args.bin +3 -0
- checkpoint-1000/README.md +34 -0
- checkpoint-1000/adapter_config.json +23 -0
- checkpoint-1000/adapter_model.bin +3 -0
- checkpoint-1000/optimizer.pt +3 -0
- checkpoint-1000/rng_state.pth +3 -0
- checkpoint-1000/scheduler.pt +3 -0
- checkpoint-1000/special_tokens_map.json +6 -0
- checkpoint-1000/tokenizer.json +3 -0
- checkpoint-1000/tokenizer_config.json +10 -0
- checkpoint-1000/trainer_state.json +0 -0
- checkpoint-1000/training_args.bin +3 -0
- checkpoint-200/README.md +34 -0
- checkpoint-200/adapter_config.json +23 -0
- checkpoint-200/adapter_model.bin +3 -0
- checkpoint-200/optimizer.pt +3 -0
- checkpoint-200/rng_state.pth +3 -0
- checkpoint-200/scheduler.pt +3 -0
- checkpoint-200/special_tokens_map.json +6 -0
- checkpoint-200/tokenizer.json +3 -0
- checkpoint-200/tokenizer_config.json +10 -0
- checkpoint-200/trainer_state.json +1219 -0
- checkpoint-200/training_args.bin +3 -0
- checkpoint-300/README.md +34 -0
- checkpoint-300/adapter_config.json +23 -0
- checkpoint-300/adapter_model.bin +3 -0
- checkpoint-300/optimizer.pt +3 -0
- checkpoint-300/rng_state.pth +3 -0
- checkpoint-300/scheduler.pt +3 -0
- checkpoint-300/special_tokens_map.json +6 -0
- checkpoint-300/tokenizer.json +3 -0
- checkpoint-300/tokenizer_config.json +10 -0
- checkpoint-300/trainer_state.json +1819 -0
- checkpoint-300/training_args.bin +3 -0
- checkpoint-400/README.md +34 -0
- checkpoint-400/adapter_config.json +23 -0
- checkpoint-400/adapter_model.bin +3 -0
- checkpoint-400/optimizer.pt +3 -0
README.md
CHANGED
|
@@ -4,18 +4,6 @@ library_name: peft
|
|
| 4 |
## Training procedure
|
| 5 |
|
| 6 |
|
| 7 |
-
The following `bitsandbytes` quantization config was used during training:
|
| 8 |
-
- quant_method: bitsandbytes
|
| 9 |
-
- load_in_8bit: True
|
| 10 |
-
- load_in_4bit: False
|
| 11 |
-
- llm_int8_threshold: 6.0
|
| 12 |
-
- llm_int8_skip_modules: None
|
| 13 |
-
- llm_int8_enable_fp32_cpu_offload: False
|
| 14 |
-
- llm_int8_has_fp16_weight: False
|
| 15 |
-
- bnb_4bit_quant_type: fp4
|
| 16 |
-
- bnb_4bit_use_double_quant: False
|
| 17 |
-
- bnb_4bit_compute_dtype: float32
|
| 18 |
-
|
| 19 |
The following `bitsandbytes` quantization config was used during training:
|
| 20 |
- quant_method: bitsandbytes
|
| 21 |
- load_in_8bit: True
|
|
@@ -29,6 +17,5 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 29 |
- bnb_4bit_compute_dtype: float32
|
| 30 |
### Framework versions
|
| 31 |
|
| 32 |
-
- PEFT 0.6.0.dev0
|
| 33 |
|
| 34 |
- PEFT 0.6.0.dev0
|
|
|
|
| 4 |
## Training procedure
|
| 5 |
|
| 6 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
The following `bitsandbytes` quantization config was used during training:
|
| 8 |
- quant_method: bitsandbytes
|
| 9 |
- load_in_8bit: True
|
|
|
|
| 17 |
- bnb_4bit_compute_dtype: float32
|
| 18 |
### Framework versions
|
| 19 |
|
|
|
|
| 20 |
|
| 21 |
- PEFT 0.6.0.dev0
|
adapter_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 39409357
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3b30c921122a83376cb2c88c534b193ab3d6346073d4445956d15f6d88cbb610
|
| 3 |
size 39409357
|
checkpoint-100/README.md
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
---
|
| 4 |
+
## Training procedure
|
| 5 |
+
|
| 6 |
+
|
| 7 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 8 |
+
- quant_method: bitsandbytes
|
| 9 |
+
- load_in_8bit: True
|
| 10 |
+
- load_in_4bit: False
|
| 11 |
+
- llm_int8_threshold: 6.0
|
| 12 |
+
- llm_int8_skip_modules: None
|
| 13 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 14 |
+
- llm_int8_has_fp16_weight: False
|
| 15 |
+
- bnb_4bit_quant_type: fp4
|
| 16 |
+
- bnb_4bit_use_double_quant: False
|
| 17 |
+
- bnb_4bit_compute_dtype: float32
|
| 18 |
+
|
| 19 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 20 |
+
- quant_method: bitsandbytes
|
| 21 |
+
- load_in_8bit: True
|
| 22 |
+
- load_in_4bit: False
|
| 23 |
+
- llm_int8_threshold: 6.0
|
| 24 |
+
- llm_int8_skip_modules: None
|
| 25 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 26 |
+
- llm_int8_has_fp16_weight: False
|
| 27 |
+
- bnb_4bit_quant_type: fp4
|
| 28 |
+
- bnb_4bit_use_double_quant: False
|
| 29 |
+
- bnb_4bit_compute_dtype: float32
|
| 30 |
+
### Framework versions
|
| 31 |
+
|
| 32 |
+
- PEFT 0.6.0.dev0
|
| 33 |
+
|
| 34 |
+
- PEFT 0.6.0.dev0
|
checkpoint-100/adapter_config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "bigscience/bloomz-3b",
|
| 4 |
+
"bias": "none",
|
| 5 |
+
"fan_in_fan_out": false,
|
| 6 |
+
"inference_mode": true,
|
| 7 |
+
"init_lora_weights": true,
|
| 8 |
+
"layers_pattern": null,
|
| 9 |
+
"layers_to_transform": null,
|
| 10 |
+
"lora_alpha": 16,
|
| 11 |
+
"lora_dropout": 0.0,
|
| 12 |
+
"modules_to_save": null,
|
| 13 |
+
"peft_type": "LORA",
|
| 14 |
+
"r": 8,
|
| 15 |
+
"revision": null,
|
| 16 |
+
"target_modules": [
|
| 17 |
+
"dense_4h_to_h",
|
| 18 |
+
"dense",
|
| 19 |
+
"dense_h_to_4h",
|
| 20 |
+
"query_key_value"
|
| 21 |
+
],
|
| 22 |
+
"task_type": "CAUSAL_LM"
|
| 23 |
+
}
|
checkpoint-100/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6ed4e680e8bd7c8d67e0d7f4b56e9acead397bfed8e4ada826388336fbb68352
|
| 3 |
+
size 39409357
|
checkpoint-100/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9aaf758f69c081ea407315416366c593e3d483404a11cdc46f7a6bcf8426f6c7
|
| 3 |
+
size 78844421
|
checkpoint-100/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b2278a87cdf86c3f9219223c847f6b27f6b7f15b8226b617f38936e8ff2cbcde
|
| 3 |
+
size 14575
|
checkpoint-100/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:88d541c44943f7d01b3a3c6f9781b89528a9b1d1baccd0d6004ff689a88b2849
|
| 3 |
+
size 627
|
checkpoint-100/special_tokens_map.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"eos_token": "</s>",
|
| 4 |
+
"pad_token": "<pad>",
|
| 5 |
+
"unk_token": "<unk>"
|
| 6 |
+
}
|
checkpoint-100/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:85b00d7db4df5df2e3f01cacc3feda246002a672f3356eec7f4b04a22eb0dfbe
|
| 3 |
+
size 14500570
|
checkpoint-100/tokenizer_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"clean_up_tokenization_spaces": false,
|
| 5 |
+
"eos_token": "</s>",
|
| 6 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 7 |
+
"pad_token": "<pad>",
|
| 8 |
+
"tokenizer_class": "BloomTokenizer",
|
| 9 |
+
"unk_token": "<unk>"
|
| 10 |
+
}
|
checkpoint-100/trainer_state.json
ADDED
|
@@ -0,0 +1,619 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.28368794326241137,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 100,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"learning_rate": 0.00019981060606060605,
|
| 14 |
+
"loss": 2.9206,
|
| 15 |
+
"step": 1
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.01,
|
| 19 |
+
"learning_rate": 0.00019962121212121212,
|
| 20 |
+
"loss": 2.7609,
|
| 21 |
+
"step": 2
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.01,
|
| 25 |
+
"learning_rate": 0.0001994318181818182,
|
| 26 |
+
"loss": 2.6878,
|
| 27 |
+
"step": 3
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.01,
|
| 31 |
+
"learning_rate": 0.00019924242424242426,
|
| 32 |
+
"loss": 2.6697,
|
| 33 |
+
"step": 4
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.01,
|
| 37 |
+
"learning_rate": 0.0001990530303030303,
|
| 38 |
+
"loss": 2.5818,
|
| 39 |
+
"step": 5
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.02,
|
| 43 |
+
"learning_rate": 0.00019886363636363637,
|
| 44 |
+
"loss": 2.5396,
|
| 45 |
+
"step": 6
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.02,
|
| 49 |
+
"learning_rate": 0.00019867424242424244,
|
| 50 |
+
"loss": 2.5265,
|
| 51 |
+
"step": 7
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.02,
|
| 55 |
+
"learning_rate": 0.0001984848484848485,
|
| 56 |
+
"loss": 2.5475,
|
| 57 |
+
"step": 8
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.03,
|
| 61 |
+
"learning_rate": 0.00019829545454545455,
|
| 62 |
+
"loss": 2.4835,
|
| 63 |
+
"step": 9
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.03,
|
| 67 |
+
"learning_rate": 0.0001981060606060606,
|
| 68 |
+
"loss": 2.4559,
|
| 69 |
+
"step": 10
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.03,
|
| 73 |
+
"learning_rate": 0.0001979166666666667,
|
| 74 |
+
"loss": 2.4511,
|
| 75 |
+
"step": 11
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.03,
|
| 79 |
+
"learning_rate": 0.00019772727272727273,
|
| 80 |
+
"loss": 2.4592,
|
| 81 |
+
"step": 12
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.04,
|
| 85 |
+
"learning_rate": 0.0001975378787878788,
|
| 86 |
+
"loss": 2.4495,
|
| 87 |
+
"step": 13
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.04,
|
| 91 |
+
"learning_rate": 0.00019734848484848484,
|
| 92 |
+
"loss": 2.4714,
|
| 93 |
+
"step": 14
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.04,
|
| 97 |
+
"learning_rate": 0.00019715909090909094,
|
| 98 |
+
"loss": 2.4302,
|
| 99 |
+
"step": 15
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.05,
|
| 103 |
+
"learning_rate": 0.00019696969696969698,
|
| 104 |
+
"loss": 2.4097,
|
| 105 |
+
"step": 16
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.05,
|
| 109 |
+
"learning_rate": 0.00019678030303030305,
|
| 110 |
+
"loss": 2.4523,
|
| 111 |
+
"step": 17
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.05,
|
| 115 |
+
"learning_rate": 0.0001965909090909091,
|
| 116 |
+
"loss": 2.4325,
|
| 117 |
+
"step": 18
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.05,
|
| 121 |
+
"learning_rate": 0.00019640151515151516,
|
| 122 |
+
"loss": 2.4125,
|
| 123 |
+
"step": 19
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.06,
|
| 127 |
+
"learning_rate": 0.00019621212121212123,
|
| 128 |
+
"loss": 2.4329,
|
| 129 |
+
"step": 20
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.06,
|
| 133 |
+
"learning_rate": 0.00019602272727272727,
|
| 134 |
+
"loss": 2.3471,
|
| 135 |
+
"step": 21
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.06,
|
| 139 |
+
"learning_rate": 0.00019583333333333334,
|
| 140 |
+
"loss": 2.3012,
|
| 141 |
+
"step": 22
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.07,
|
| 145 |
+
"learning_rate": 0.0001956439393939394,
|
| 146 |
+
"loss": 2.3869,
|
| 147 |
+
"step": 23
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.07,
|
| 151 |
+
"learning_rate": 0.00019545454545454548,
|
| 152 |
+
"loss": 2.3822,
|
| 153 |
+
"step": 24
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.07,
|
| 157 |
+
"learning_rate": 0.00019526515151515152,
|
| 158 |
+
"loss": 2.3427,
|
| 159 |
+
"step": 25
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.07,
|
| 163 |
+
"learning_rate": 0.0001950757575757576,
|
| 164 |
+
"loss": 2.3659,
|
| 165 |
+
"step": 26
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.08,
|
| 169 |
+
"learning_rate": 0.00019488636363636366,
|
| 170 |
+
"loss": 2.3826,
|
| 171 |
+
"step": 27
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.08,
|
| 175 |
+
"learning_rate": 0.0001946969696969697,
|
| 176 |
+
"loss": 2.3532,
|
| 177 |
+
"step": 28
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.08,
|
| 181 |
+
"learning_rate": 0.00019450757575757577,
|
| 182 |
+
"loss": 2.3828,
|
| 183 |
+
"step": 29
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.09,
|
| 187 |
+
"learning_rate": 0.0001943181818181818,
|
| 188 |
+
"loss": 2.3133,
|
| 189 |
+
"step": 30
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.09,
|
| 193 |
+
"learning_rate": 0.0001941287878787879,
|
| 194 |
+
"loss": 2.3613,
|
| 195 |
+
"step": 31
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.09,
|
| 199 |
+
"learning_rate": 0.00019393939393939395,
|
| 200 |
+
"loss": 2.3867,
|
| 201 |
+
"step": 32
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.09,
|
| 205 |
+
"learning_rate": 0.00019375000000000002,
|
| 206 |
+
"loss": 2.2966,
|
| 207 |
+
"step": 33
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.1,
|
| 211 |
+
"learning_rate": 0.00019356060606060606,
|
| 212 |
+
"loss": 2.3436,
|
| 213 |
+
"step": 34
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.1,
|
| 217 |
+
"learning_rate": 0.00019337121212121213,
|
| 218 |
+
"loss": 2.3425,
|
| 219 |
+
"step": 35
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.1,
|
| 223 |
+
"learning_rate": 0.0001931818181818182,
|
| 224 |
+
"loss": 2.307,
|
| 225 |
+
"step": 36
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.1,
|
| 229 |
+
"learning_rate": 0.00019299242424242424,
|
| 230 |
+
"loss": 2.3521,
|
| 231 |
+
"step": 37
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.11,
|
| 235 |
+
"learning_rate": 0.0001928030303030303,
|
| 236 |
+
"loss": 2.3302,
|
| 237 |
+
"step": 38
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.11,
|
| 241 |
+
"learning_rate": 0.00019261363636363635,
|
| 242 |
+
"loss": 2.312,
|
| 243 |
+
"step": 39
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.11,
|
| 247 |
+
"learning_rate": 0.00019242424242424245,
|
| 248 |
+
"loss": 2.3655,
|
| 249 |
+
"step": 40
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.12,
|
| 253 |
+
"learning_rate": 0.0001922348484848485,
|
| 254 |
+
"loss": 2.344,
|
| 255 |
+
"step": 41
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.12,
|
| 259 |
+
"learning_rate": 0.00019204545454545456,
|
| 260 |
+
"loss": 2.3373,
|
| 261 |
+
"step": 42
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.12,
|
| 265 |
+
"learning_rate": 0.0001918560606060606,
|
| 266 |
+
"loss": 2.3331,
|
| 267 |
+
"step": 43
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.12,
|
| 271 |
+
"learning_rate": 0.00019166666666666667,
|
| 272 |
+
"loss": 2.3376,
|
| 273 |
+
"step": 44
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.13,
|
| 277 |
+
"learning_rate": 0.00019147727272727274,
|
| 278 |
+
"loss": 2.3369,
|
| 279 |
+
"step": 45
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.13,
|
| 283 |
+
"learning_rate": 0.00019128787878787878,
|
| 284 |
+
"loss": 2.3413,
|
| 285 |
+
"step": 46
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.13,
|
| 289 |
+
"learning_rate": 0.00019109848484848485,
|
| 290 |
+
"loss": 2.3212,
|
| 291 |
+
"step": 47
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.14,
|
| 295 |
+
"learning_rate": 0.00019090909090909092,
|
| 296 |
+
"loss": 2.307,
|
| 297 |
+
"step": 48
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.14,
|
| 301 |
+
"learning_rate": 0.000190719696969697,
|
| 302 |
+
"loss": 2.2929,
|
| 303 |
+
"step": 49
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.14,
|
| 307 |
+
"learning_rate": 0.00019053030303030303,
|
| 308 |
+
"loss": 2.2873,
|
| 309 |
+
"step": 50
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.14,
|
| 313 |
+
"learning_rate": 0.0001903409090909091,
|
| 314 |
+
"loss": 2.3098,
|
| 315 |
+
"step": 51
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.15,
|
| 319 |
+
"learning_rate": 0.00019015151515151517,
|
| 320 |
+
"loss": 2.3129,
|
| 321 |
+
"step": 52
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.15,
|
| 325 |
+
"learning_rate": 0.0001899621212121212,
|
| 326 |
+
"loss": 2.3038,
|
| 327 |
+
"step": 53
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.15,
|
| 331 |
+
"learning_rate": 0.00018977272727272728,
|
| 332 |
+
"loss": 2.286,
|
| 333 |
+
"step": 54
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.16,
|
| 337 |
+
"learning_rate": 0.00018958333333333332,
|
| 338 |
+
"loss": 2.3388,
|
| 339 |
+
"step": 55
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.16,
|
| 343 |
+
"learning_rate": 0.00018939393939393942,
|
| 344 |
+
"loss": 2.3193,
|
| 345 |
+
"step": 56
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.16,
|
| 349 |
+
"learning_rate": 0.00018920454545454546,
|
| 350 |
+
"loss": 2.3136,
|
| 351 |
+
"step": 57
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.16,
|
| 355 |
+
"learning_rate": 0.00018901515151515153,
|
| 356 |
+
"loss": 2.3141,
|
| 357 |
+
"step": 58
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.17,
|
| 361 |
+
"learning_rate": 0.00018882575757575757,
|
| 362 |
+
"loss": 2.3646,
|
| 363 |
+
"step": 59
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.17,
|
| 367 |
+
"learning_rate": 0.00018863636363636364,
|
| 368 |
+
"loss": 2.3318,
|
| 369 |
+
"step": 60
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.17,
|
| 373 |
+
"learning_rate": 0.0001884469696969697,
|
| 374 |
+
"loss": 2.2977,
|
| 375 |
+
"step": 61
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.18,
|
| 379 |
+
"learning_rate": 0.00018825757575757575,
|
| 380 |
+
"loss": 2.2764,
|
| 381 |
+
"step": 62
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.18,
|
| 385 |
+
"learning_rate": 0.00018806818181818182,
|
| 386 |
+
"loss": 2.3095,
|
| 387 |
+
"step": 63
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.18,
|
| 391 |
+
"learning_rate": 0.0001878787878787879,
|
| 392 |
+
"loss": 2.252,
|
| 393 |
+
"step": 64
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.18,
|
| 397 |
+
"learning_rate": 0.00018768939393939396,
|
| 398 |
+
"loss": 2.2786,
|
| 399 |
+
"step": 65
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.19,
|
| 403 |
+
"learning_rate": 0.0001875,
|
| 404 |
+
"loss": 2.2789,
|
| 405 |
+
"step": 66
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.19,
|
| 409 |
+
"learning_rate": 0.00018731060606060607,
|
| 410 |
+
"loss": 2.2841,
|
| 411 |
+
"step": 67
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.19,
|
| 415 |
+
"learning_rate": 0.00018712121212121212,
|
| 416 |
+
"loss": 2.3436,
|
| 417 |
+
"step": 68
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.2,
|
| 421 |
+
"learning_rate": 0.00018693181818181818,
|
| 422 |
+
"loss": 2.2956,
|
| 423 |
+
"step": 69
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.2,
|
| 427 |
+
"learning_rate": 0.00018674242424242425,
|
| 428 |
+
"loss": 2.2353,
|
| 429 |
+
"step": 70
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.2,
|
| 433 |
+
"learning_rate": 0.0001865530303030303,
|
| 434 |
+
"loss": 2.2772,
|
| 435 |
+
"step": 71
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.2,
|
| 439 |
+
"learning_rate": 0.00018636363636363636,
|
| 440 |
+
"loss": 2.2496,
|
| 441 |
+
"step": 72
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.21,
|
| 445 |
+
"learning_rate": 0.00018617424242424243,
|
| 446 |
+
"loss": 2.2477,
|
| 447 |
+
"step": 73
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.21,
|
| 451 |
+
"learning_rate": 0.0001859848484848485,
|
| 452 |
+
"loss": 2.2791,
|
| 453 |
+
"step": 74
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.21,
|
| 457 |
+
"learning_rate": 0.00018579545454545454,
|
| 458 |
+
"loss": 2.2799,
|
| 459 |
+
"step": 75
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.22,
|
| 463 |
+
"learning_rate": 0.00018560606060606061,
|
| 464 |
+
"loss": 2.3132,
|
| 465 |
+
"step": 76
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.22,
|
| 469 |
+
"learning_rate": 0.00018541666666666668,
|
| 470 |
+
"loss": 2.2542,
|
| 471 |
+
"step": 77
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.22,
|
| 475 |
+
"learning_rate": 0.00018522727272727273,
|
| 476 |
+
"loss": 2.2609,
|
| 477 |
+
"step": 78
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.22,
|
| 481 |
+
"learning_rate": 0.0001850378787878788,
|
| 482 |
+
"loss": 2.2819,
|
| 483 |
+
"step": 79
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.23,
|
| 487 |
+
"learning_rate": 0.00018484848484848484,
|
| 488 |
+
"loss": 2.2844,
|
| 489 |
+
"step": 80
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.23,
|
| 493 |
+
"learning_rate": 0.00018465909090909093,
|
| 494 |
+
"loss": 2.2542,
|
| 495 |
+
"step": 81
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.23,
|
| 499 |
+
"learning_rate": 0.00018446969696969697,
|
| 500 |
+
"loss": 2.2603,
|
| 501 |
+
"step": 82
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.24,
|
| 505 |
+
"learning_rate": 0.00018428030303030304,
|
| 506 |
+
"loss": 2.2832,
|
| 507 |
+
"step": 83
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.24,
|
| 511 |
+
"learning_rate": 0.00018409090909090909,
|
| 512 |
+
"loss": 2.2869,
|
| 513 |
+
"step": 84
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.24,
|
| 517 |
+
"learning_rate": 0.00018390151515151518,
|
| 518 |
+
"loss": 2.2646,
|
| 519 |
+
"step": 85
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.24,
|
| 523 |
+
"learning_rate": 0.00018371212121212122,
|
| 524 |
+
"loss": 2.2698,
|
| 525 |
+
"step": 86
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.25,
|
| 529 |
+
"learning_rate": 0.00018352272727272727,
|
| 530 |
+
"loss": 2.2757,
|
| 531 |
+
"step": 87
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 0.25,
|
| 535 |
+
"learning_rate": 0.00018333333333333334,
|
| 536 |
+
"loss": 2.2544,
|
| 537 |
+
"step": 88
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.25,
|
| 541 |
+
"learning_rate": 0.0001831439393939394,
|
| 542 |
+
"loss": 2.2678,
|
| 543 |
+
"step": 89
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.26,
|
| 547 |
+
"learning_rate": 0.00018295454545454547,
|
| 548 |
+
"loss": 2.2778,
|
| 549 |
+
"step": 90
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.26,
|
| 553 |
+
"learning_rate": 0.00018276515151515152,
|
| 554 |
+
"loss": 2.2027,
|
| 555 |
+
"step": 91
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.26,
|
| 559 |
+
"learning_rate": 0.00018257575757575758,
|
| 560 |
+
"loss": 2.2167,
|
| 561 |
+
"step": 92
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.26,
|
| 565 |
+
"learning_rate": 0.00018238636363636365,
|
| 566 |
+
"loss": 2.2602,
|
| 567 |
+
"step": 93
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 0.27,
|
| 571 |
+
"learning_rate": 0.00018219696969696972,
|
| 572 |
+
"loss": 2.2736,
|
| 573 |
+
"step": 94
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.27,
|
| 577 |
+
"learning_rate": 0.00018200757575757577,
|
| 578 |
+
"loss": 2.2443,
|
| 579 |
+
"step": 95
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.27,
|
| 583 |
+
"learning_rate": 0.00018181818181818183,
|
| 584 |
+
"loss": 2.2299,
|
| 585 |
+
"step": 96
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.28,
|
| 589 |
+
"learning_rate": 0.0001816287878787879,
|
| 590 |
+
"loss": 2.2644,
|
| 591 |
+
"step": 97
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.28,
|
| 595 |
+
"learning_rate": 0.00018143939393939395,
|
| 596 |
+
"loss": 2.259,
|
| 597 |
+
"step": 98
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.28,
|
| 601 |
+
"learning_rate": 0.00018125000000000001,
|
| 602 |
+
"loss": 2.2567,
|
| 603 |
+
"step": 99
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.28,
|
| 607 |
+
"learning_rate": 0.00018106060606060606,
|
| 608 |
+
"loss": 2.2599,
|
| 609 |
+
"step": 100
|
| 610 |
+
}
|
| 611 |
+
],
|
| 612 |
+
"logging_steps": 1,
|
| 613 |
+
"max_steps": 1056,
|
| 614 |
+
"num_train_epochs": 3,
|
| 615 |
+
"save_steps": 100,
|
| 616 |
+
"total_flos": 2.5310590559514624e+17,
|
| 617 |
+
"trial_name": null,
|
| 618 |
+
"trial_params": null
|
| 619 |
+
}
|
checkpoint-100/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:50303c7f1586feb001f01b7e968e567295f501ef6c6407e28250c458696a43af
|
| 3 |
+
size 4155
|
checkpoint-1000/README.md
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
---
|
| 4 |
+
## Training procedure
|
| 5 |
+
|
| 6 |
+
|
| 7 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 8 |
+
- quant_method: bitsandbytes
|
| 9 |
+
- load_in_8bit: True
|
| 10 |
+
- load_in_4bit: False
|
| 11 |
+
- llm_int8_threshold: 6.0
|
| 12 |
+
- llm_int8_skip_modules: None
|
| 13 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 14 |
+
- llm_int8_has_fp16_weight: False
|
| 15 |
+
- bnb_4bit_quant_type: fp4
|
| 16 |
+
- bnb_4bit_use_double_quant: False
|
| 17 |
+
- bnb_4bit_compute_dtype: float32
|
| 18 |
+
|
| 19 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 20 |
+
- quant_method: bitsandbytes
|
| 21 |
+
- load_in_8bit: True
|
| 22 |
+
- load_in_4bit: False
|
| 23 |
+
- llm_int8_threshold: 6.0
|
| 24 |
+
- llm_int8_skip_modules: None
|
| 25 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 26 |
+
- llm_int8_has_fp16_weight: False
|
| 27 |
+
- bnb_4bit_quant_type: fp4
|
| 28 |
+
- bnb_4bit_use_double_quant: False
|
| 29 |
+
- bnb_4bit_compute_dtype: float32
|
| 30 |
+
### Framework versions
|
| 31 |
+
|
| 32 |
+
- PEFT 0.6.0.dev0
|
| 33 |
+
|
| 34 |
+
- PEFT 0.6.0.dev0
|
checkpoint-1000/adapter_config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "bigscience/bloomz-3b",
|
| 4 |
+
"bias": "none",
|
| 5 |
+
"fan_in_fan_out": false,
|
| 6 |
+
"inference_mode": true,
|
| 7 |
+
"init_lora_weights": true,
|
| 8 |
+
"layers_pattern": null,
|
| 9 |
+
"layers_to_transform": null,
|
| 10 |
+
"lora_alpha": 16,
|
| 11 |
+
"lora_dropout": 0.0,
|
| 12 |
+
"modules_to_save": null,
|
| 13 |
+
"peft_type": "LORA",
|
| 14 |
+
"r": 8,
|
| 15 |
+
"revision": null,
|
| 16 |
+
"target_modules": [
|
| 17 |
+
"dense_4h_to_h",
|
| 18 |
+
"dense",
|
| 19 |
+
"dense_h_to_4h",
|
| 20 |
+
"query_key_value"
|
| 21 |
+
],
|
| 22 |
+
"task_type": "CAUSAL_LM"
|
| 23 |
+
}
|
checkpoint-1000/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:881578bad3c9206920de4787c4a9d6c8e57d77588bf0d7db0d25ed4f90f349ff
|
| 3 |
+
size 39409357
|
checkpoint-1000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:88cf590bf3d40f0fa16ea88522ca56ed0dba7a8e23b2c081d85df96fc1152aed
|
| 3 |
+
size 78844421
|
checkpoint-1000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7508d4b8dd267de5cc58e972da25236687927651336a28f292c92f7f23951475
|
| 3 |
+
size 14575
|
checkpoint-1000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f23cbb71419e97e268c2c3c9dacfadbf31269deafbdadf5d827840e02e7f3fc8
|
| 3 |
+
size 627
|
checkpoint-1000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"eos_token": "</s>",
|
| 4 |
+
"pad_token": "<pad>",
|
| 5 |
+
"unk_token": "<unk>"
|
| 6 |
+
}
|
checkpoint-1000/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:85b00d7db4df5df2e3f01cacc3feda246002a672f3356eec7f4b04a22eb0dfbe
|
| 3 |
+
size 14500570
|
checkpoint-1000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"clean_up_tokenization_spaces": false,
|
| 5 |
+
"eos_token": "</s>",
|
| 6 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 7 |
+
"pad_token": "<pad>",
|
| 8 |
+
"tokenizer_class": "BloomTokenizer",
|
| 9 |
+
"unk_token": "<unk>"
|
| 10 |
+
}
|
checkpoint-1000/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:50303c7f1586feb001f01b7e968e567295f501ef6c6407e28250c458696a43af
|
| 3 |
+
size 4155
|
checkpoint-200/README.md
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
---
|
| 4 |
+
## Training procedure
|
| 5 |
+
|
| 6 |
+
|
| 7 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 8 |
+
- quant_method: bitsandbytes
|
| 9 |
+
- load_in_8bit: True
|
| 10 |
+
- load_in_4bit: False
|
| 11 |
+
- llm_int8_threshold: 6.0
|
| 12 |
+
- llm_int8_skip_modules: None
|
| 13 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 14 |
+
- llm_int8_has_fp16_weight: False
|
| 15 |
+
- bnb_4bit_quant_type: fp4
|
| 16 |
+
- bnb_4bit_use_double_quant: False
|
| 17 |
+
- bnb_4bit_compute_dtype: float32
|
| 18 |
+
|
| 19 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 20 |
+
- quant_method: bitsandbytes
|
| 21 |
+
- load_in_8bit: True
|
| 22 |
+
- load_in_4bit: False
|
| 23 |
+
- llm_int8_threshold: 6.0
|
| 24 |
+
- llm_int8_skip_modules: None
|
| 25 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 26 |
+
- llm_int8_has_fp16_weight: False
|
| 27 |
+
- bnb_4bit_quant_type: fp4
|
| 28 |
+
- bnb_4bit_use_double_quant: False
|
| 29 |
+
- bnb_4bit_compute_dtype: float32
|
| 30 |
+
### Framework versions
|
| 31 |
+
|
| 32 |
+
- PEFT 0.6.0.dev0
|
| 33 |
+
|
| 34 |
+
- PEFT 0.6.0.dev0
|
checkpoint-200/adapter_config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "bigscience/bloomz-3b",
|
| 4 |
+
"bias": "none",
|
| 5 |
+
"fan_in_fan_out": false,
|
| 6 |
+
"inference_mode": true,
|
| 7 |
+
"init_lora_weights": true,
|
| 8 |
+
"layers_pattern": null,
|
| 9 |
+
"layers_to_transform": null,
|
| 10 |
+
"lora_alpha": 16,
|
| 11 |
+
"lora_dropout": 0.0,
|
| 12 |
+
"modules_to_save": null,
|
| 13 |
+
"peft_type": "LORA",
|
| 14 |
+
"r": 8,
|
| 15 |
+
"revision": null,
|
| 16 |
+
"target_modules": [
|
| 17 |
+
"dense_4h_to_h",
|
| 18 |
+
"dense",
|
| 19 |
+
"dense_h_to_4h",
|
| 20 |
+
"query_key_value"
|
| 21 |
+
],
|
| 22 |
+
"task_type": "CAUSAL_LM"
|
| 23 |
+
}
|
checkpoint-200/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:af970fa4c3a5656856f672174ec36ac064378101c5eb1d725a132c5f169062a0
|
| 3 |
+
size 39409357
|
checkpoint-200/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:da756f223a08e8635e8fe5fae5ef9d2173d86392bb4169cb415818a13d98abd2
|
| 3 |
+
size 78844421
|
checkpoint-200/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b2278a87cdf86c3f9219223c847f6b27f6b7f15b8226b617f38936e8ff2cbcde
|
| 3 |
+
size 14575
|
checkpoint-200/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:84eda105b04e1ff8992a03ec3c10699744eae4e45155e29019b4fa919b2d986a
|
| 3 |
+
size 627
|
checkpoint-200/special_tokens_map.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"eos_token": "</s>",
|
| 4 |
+
"pad_token": "<pad>",
|
| 5 |
+
"unk_token": "<unk>"
|
| 6 |
+
}
|
checkpoint-200/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:85b00d7db4df5df2e3f01cacc3feda246002a672f3356eec7f4b04a22eb0dfbe
|
| 3 |
+
size 14500570
|
checkpoint-200/tokenizer_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"clean_up_tokenization_spaces": false,
|
| 5 |
+
"eos_token": "</s>",
|
| 6 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 7 |
+
"pad_token": "<pad>",
|
| 8 |
+
"tokenizer_class": "BloomTokenizer",
|
| 9 |
+
"unk_token": "<unk>"
|
| 10 |
+
}
|
checkpoint-200/trainer_state.json
ADDED
|
@@ -0,0 +1,1219 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.5673758865248227,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 200,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"learning_rate": 0.00019981060606060605,
|
| 14 |
+
"loss": 2.9206,
|
| 15 |
+
"step": 1
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.01,
|
| 19 |
+
"learning_rate": 0.00019962121212121212,
|
| 20 |
+
"loss": 2.7609,
|
| 21 |
+
"step": 2
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.01,
|
| 25 |
+
"learning_rate": 0.0001994318181818182,
|
| 26 |
+
"loss": 2.6878,
|
| 27 |
+
"step": 3
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.01,
|
| 31 |
+
"learning_rate": 0.00019924242424242426,
|
| 32 |
+
"loss": 2.6697,
|
| 33 |
+
"step": 4
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.01,
|
| 37 |
+
"learning_rate": 0.0001990530303030303,
|
| 38 |
+
"loss": 2.5818,
|
| 39 |
+
"step": 5
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.02,
|
| 43 |
+
"learning_rate": 0.00019886363636363637,
|
| 44 |
+
"loss": 2.5396,
|
| 45 |
+
"step": 6
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.02,
|
| 49 |
+
"learning_rate": 0.00019867424242424244,
|
| 50 |
+
"loss": 2.5265,
|
| 51 |
+
"step": 7
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.02,
|
| 55 |
+
"learning_rate": 0.0001984848484848485,
|
| 56 |
+
"loss": 2.5475,
|
| 57 |
+
"step": 8
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.03,
|
| 61 |
+
"learning_rate": 0.00019829545454545455,
|
| 62 |
+
"loss": 2.4835,
|
| 63 |
+
"step": 9
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.03,
|
| 67 |
+
"learning_rate": 0.0001981060606060606,
|
| 68 |
+
"loss": 2.4559,
|
| 69 |
+
"step": 10
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.03,
|
| 73 |
+
"learning_rate": 0.0001979166666666667,
|
| 74 |
+
"loss": 2.4511,
|
| 75 |
+
"step": 11
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.03,
|
| 79 |
+
"learning_rate": 0.00019772727272727273,
|
| 80 |
+
"loss": 2.4592,
|
| 81 |
+
"step": 12
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.04,
|
| 85 |
+
"learning_rate": 0.0001975378787878788,
|
| 86 |
+
"loss": 2.4495,
|
| 87 |
+
"step": 13
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.04,
|
| 91 |
+
"learning_rate": 0.00019734848484848484,
|
| 92 |
+
"loss": 2.4714,
|
| 93 |
+
"step": 14
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.04,
|
| 97 |
+
"learning_rate": 0.00019715909090909094,
|
| 98 |
+
"loss": 2.4302,
|
| 99 |
+
"step": 15
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.05,
|
| 103 |
+
"learning_rate": 0.00019696969696969698,
|
| 104 |
+
"loss": 2.4097,
|
| 105 |
+
"step": 16
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.05,
|
| 109 |
+
"learning_rate": 0.00019678030303030305,
|
| 110 |
+
"loss": 2.4523,
|
| 111 |
+
"step": 17
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.05,
|
| 115 |
+
"learning_rate": 0.0001965909090909091,
|
| 116 |
+
"loss": 2.4325,
|
| 117 |
+
"step": 18
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.05,
|
| 121 |
+
"learning_rate": 0.00019640151515151516,
|
| 122 |
+
"loss": 2.4125,
|
| 123 |
+
"step": 19
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.06,
|
| 127 |
+
"learning_rate": 0.00019621212121212123,
|
| 128 |
+
"loss": 2.4329,
|
| 129 |
+
"step": 20
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.06,
|
| 133 |
+
"learning_rate": 0.00019602272727272727,
|
| 134 |
+
"loss": 2.3471,
|
| 135 |
+
"step": 21
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.06,
|
| 139 |
+
"learning_rate": 0.00019583333333333334,
|
| 140 |
+
"loss": 2.3012,
|
| 141 |
+
"step": 22
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.07,
|
| 145 |
+
"learning_rate": 0.0001956439393939394,
|
| 146 |
+
"loss": 2.3869,
|
| 147 |
+
"step": 23
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.07,
|
| 151 |
+
"learning_rate": 0.00019545454545454548,
|
| 152 |
+
"loss": 2.3822,
|
| 153 |
+
"step": 24
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.07,
|
| 157 |
+
"learning_rate": 0.00019526515151515152,
|
| 158 |
+
"loss": 2.3427,
|
| 159 |
+
"step": 25
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.07,
|
| 163 |
+
"learning_rate": 0.0001950757575757576,
|
| 164 |
+
"loss": 2.3659,
|
| 165 |
+
"step": 26
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.08,
|
| 169 |
+
"learning_rate": 0.00019488636363636366,
|
| 170 |
+
"loss": 2.3826,
|
| 171 |
+
"step": 27
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.08,
|
| 175 |
+
"learning_rate": 0.0001946969696969697,
|
| 176 |
+
"loss": 2.3532,
|
| 177 |
+
"step": 28
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.08,
|
| 181 |
+
"learning_rate": 0.00019450757575757577,
|
| 182 |
+
"loss": 2.3828,
|
| 183 |
+
"step": 29
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.09,
|
| 187 |
+
"learning_rate": 0.0001943181818181818,
|
| 188 |
+
"loss": 2.3133,
|
| 189 |
+
"step": 30
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.09,
|
| 193 |
+
"learning_rate": 0.0001941287878787879,
|
| 194 |
+
"loss": 2.3613,
|
| 195 |
+
"step": 31
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.09,
|
| 199 |
+
"learning_rate": 0.00019393939393939395,
|
| 200 |
+
"loss": 2.3867,
|
| 201 |
+
"step": 32
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.09,
|
| 205 |
+
"learning_rate": 0.00019375000000000002,
|
| 206 |
+
"loss": 2.2966,
|
| 207 |
+
"step": 33
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.1,
|
| 211 |
+
"learning_rate": 0.00019356060606060606,
|
| 212 |
+
"loss": 2.3436,
|
| 213 |
+
"step": 34
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.1,
|
| 217 |
+
"learning_rate": 0.00019337121212121213,
|
| 218 |
+
"loss": 2.3425,
|
| 219 |
+
"step": 35
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.1,
|
| 223 |
+
"learning_rate": 0.0001931818181818182,
|
| 224 |
+
"loss": 2.307,
|
| 225 |
+
"step": 36
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.1,
|
| 229 |
+
"learning_rate": 0.00019299242424242424,
|
| 230 |
+
"loss": 2.3521,
|
| 231 |
+
"step": 37
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.11,
|
| 235 |
+
"learning_rate": 0.0001928030303030303,
|
| 236 |
+
"loss": 2.3302,
|
| 237 |
+
"step": 38
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.11,
|
| 241 |
+
"learning_rate": 0.00019261363636363635,
|
| 242 |
+
"loss": 2.312,
|
| 243 |
+
"step": 39
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.11,
|
| 247 |
+
"learning_rate": 0.00019242424242424245,
|
| 248 |
+
"loss": 2.3655,
|
| 249 |
+
"step": 40
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.12,
|
| 253 |
+
"learning_rate": 0.0001922348484848485,
|
| 254 |
+
"loss": 2.344,
|
| 255 |
+
"step": 41
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.12,
|
| 259 |
+
"learning_rate": 0.00019204545454545456,
|
| 260 |
+
"loss": 2.3373,
|
| 261 |
+
"step": 42
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.12,
|
| 265 |
+
"learning_rate": 0.0001918560606060606,
|
| 266 |
+
"loss": 2.3331,
|
| 267 |
+
"step": 43
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.12,
|
| 271 |
+
"learning_rate": 0.00019166666666666667,
|
| 272 |
+
"loss": 2.3376,
|
| 273 |
+
"step": 44
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.13,
|
| 277 |
+
"learning_rate": 0.00019147727272727274,
|
| 278 |
+
"loss": 2.3369,
|
| 279 |
+
"step": 45
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.13,
|
| 283 |
+
"learning_rate": 0.00019128787878787878,
|
| 284 |
+
"loss": 2.3413,
|
| 285 |
+
"step": 46
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.13,
|
| 289 |
+
"learning_rate": 0.00019109848484848485,
|
| 290 |
+
"loss": 2.3212,
|
| 291 |
+
"step": 47
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.14,
|
| 295 |
+
"learning_rate": 0.00019090909090909092,
|
| 296 |
+
"loss": 2.307,
|
| 297 |
+
"step": 48
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.14,
|
| 301 |
+
"learning_rate": 0.000190719696969697,
|
| 302 |
+
"loss": 2.2929,
|
| 303 |
+
"step": 49
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.14,
|
| 307 |
+
"learning_rate": 0.00019053030303030303,
|
| 308 |
+
"loss": 2.2873,
|
| 309 |
+
"step": 50
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.14,
|
| 313 |
+
"learning_rate": 0.0001903409090909091,
|
| 314 |
+
"loss": 2.3098,
|
| 315 |
+
"step": 51
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.15,
|
| 319 |
+
"learning_rate": 0.00019015151515151517,
|
| 320 |
+
"loss": 2.3129,
|
| 321 |
+
"step": 52
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.15,
|
| 325 |
+
"learning_rate": 0.0001899621212121212,
|
| 326 |
+
"loss": 2.3038,
|
| 327 |
+
"step": 53
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.15,
|
| 331 |
+
"learning_rate": 0.00018977272727272728,
|
| 332 |
+
"loss": 2.286,
|
| 333 |
+
"step": 54
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.16,
|
| 337 |
+
"learning_rate": 0.00018958333333333332,
|
| 338 |
+
"loss": 2.3388,
|
| 339 |
+
"step": 55
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.16,
|
| 343 |
+
"learning_rate": 0.00018939393939393942,
|
| 344 |
+
"loss": 2.3193,
|
| 345 |
+
"step": 56
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.16,
|
| 349 |
+
"learning_rate": 0.00018920454545454546,
|
| 350 |
+
"loss": 2.3136,
|
| 351 |
+
"step": 57
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.16,
|
| 355 |
+
"learning_rate": 0.00018901515151515153,
|
| 356 |
+
"loss": 2.3141,
|
| 357 |
+
"step": 58
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.17,
|
| 361 |
+
"learning_rate": 0.00018882575757575757,
|
| 362 |
+
"loss": 2.3646,
|
| 363 |
+
"step": 59
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.17,
|
| 367 |
+
"learning_rate": 0.00018863636363636364,
|
| 368 |
+
"loss": 2.3318,
|
| 369 |
+
"step": 60
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.17,
|
| 373 |
+
"learning_rate": 0.0001884469696969697,
|
| 374 |
+
"loss": 2.2977,
|
| 375 |
+
"step": 61
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.18,
|
| 379 |
+
"learning_rate": 0.00018825757575757575,
|
| 380 |
+
"loss": 2.2764,
|
| 381 |
+
"step": 62
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.18,
|
| 385 |
+
"learning_rate": 0.00018806818181818182,
|
| 386 |
+
"loss": 2.3095,
|
| 387 |
+
"step": 63
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.18,
|
| 391 |
+
"learning_rate": 0.0001878787878787879,
|
| 392 |
+
"loss": 2.252,
|
| 393 |
+
"step": 64
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.18,
|
| 397 |
+
"learning_rate": 0.00018768939393939396,
|
| 398 |
+
"loss": 2.2786,
|
| 399 |
+
"step": 65
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.19,
|
| 403 |
+
"learning_rate": 0.0001875,
|
| 404 |
+
"loss": 2.2789,
|
| 405 |
+
"step": 66
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.19,
|
| 409 |
+
"learning_rate": 0.00018731060606060607,
|
| 410 |
+
"loss": 2.2841,
|
| 411 |
+
"step": 67
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.19,
|
| 415 |
+
"learning_rate": 0.00018712121212121212,
|
| 416 |
+
"loss": 2.3436,
|
| 417 |
+
"step": 68
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.2,
|
| 421 |
+
"learning_rate": 0.00018693181818181818,
|
| 422 |
+
"loss": 2.2956,
|
| 423 |
+
"step": 69
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.2,
|
| 427 |
+
"learning_rate": 0.00018674242424242425,
|
| 428 |
+
"loss": 2.2353,
|
| 429 |
+
"step": 70
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.2,
|
| 433 |
+
"learning_rate": 0.0001865530303030303,
|
| 434 |
+
"loss": 2.2772,
|
| 435 |
+
"step": 71
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.2,
|
| 439 |
+
"learning_rate": 0.00018636363636363636,
|
| 440 |
+
"loss": 2.2496,
|
| 441 |
+
"step": 72
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.21,
|
| 445 |
+
"learning_rate": 0.00018617424242424243,
|
| 446 |
+
"loss": 2.2477,
|
| 447 |
+
"step": 73
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.21,
|
| 451 |
+
"learning_rate": 0.0001859848484848485,
|
| 452 |
+
"loss": 2.2791,
|
| 453 |
+
"step": 74
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.21,
|
| 457 |
+
"learning_rate": 0.00018579545454545454,
|
| 458 |
+
"loss": 2.2799,
|
| 459 |
+
"step": 75
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.22,
|
| 463 |
+
"learning_rate": 0.00018560606060606061,
|
| 464 |
+
"loss": 2.3132,
|
| 465 |
+
"step": 76
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.22,
|
| 469 |
+
"learning_rate": 0.00018541666666666668,
|
| 470 |
+
"loss": 2.2542,
|
| 471 |
+
"step": 77
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.22,
|
| 475 |
+
"learning_rate": 0.00018522727272727273,
|
| 476 |
+
"loss": 2.2609,
|
| 477 |
+
"step": 78
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.22,
|
| 481 |
+
"learning_rate": 0.0001850378787878788,
|
| 482 |
+
"loss": 2.2819,
|
| 483 |
+
"step": 79
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.23,
|
| 487 |
+
"learning_rate": 0.00018484848484848484,
|
| 488 |
+
"loss": 2.2844,
|
| 489 |
+
"step": 80
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.23,
|
| 493 |
+
"learning_rate": 0.00018465909090909093,
|
| 494 |
+
"loss": 2.2542,
|
| 495 |
+
"step": 81
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.23,
|
| 499 |
+
"learning_rate": 0.00018446969696969697,
|
| 500 |
+
"loss": 2.2603,
|
| 501 |
+
"step": 82
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.24,
|
| 505 |
+
"learning_rate": 0.00018428030303030304,
|
| 506 |
+
"loss": 2.2832,
|
| 507 |
+
"step": 83
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.24,
|
| 511 |
+
"learning_rate": 0.00018409090909090909,
|
| 512 |
+
"loss": 2.2869,
|
| 513 |
+
"step": 84
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.24,
|
| 517 |
+
"learning_rate": 0.00018390151515151518,
|
| 518 |
+
"loss": 2.2646,
|
| 519 |
+
"step": 85
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.24,
|
| 523 |
+
"learning_rate": 0.00018371212121212122,
|
| 524 |
+
"loss": 2.2698,
|
| 525 |
+
"step": 86
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.25,
|
| 529 |
+
"learning_rate": 0.00018352272727272727,
|
| 530 |
+
"loss": 2.2757,
|
| 531 |
+
"step": 87
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 0.25,
|
| 535 |
+
"learning_rate": 0.00018333333333333334,
|
| 536 |
+
"loss": 2.2544,
|
| 537 |
+
"step": 88
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.25,
|
| 541 |
+
"learning_rate": 0.0001831439393939394,
|
| 542 |
+
"loss": 2.2678,
|
| 543 |
+
"step": 89
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.26,
|
| 547 |
+
"learning_rate": 0.00018295454545454547,
|
| 548 |
+
"loss": 2.2778,
|
| 549 |
+
"step": 90
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.26,
|
| 553 |
+
"learning_rate": 0.00018276515151515152,
|
| 554 |
+
"loss": 2.2027,
|
| 555 |
+
"step": 91
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.26,
|
| 559 |
+
"learning_rate": 0.00018257575757575758,
|
| 560 |
+
"loss": 2.2167,
|
| 561 |
+
"step": 92
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.26,
|
| 565 |
+
"learning_rate": 0.00018238636363636365,
|
| 566 |
+
"loss": 2.2602,
|
| 567 |
+
"step": 93
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 0.27,
|
| 571 |
+
"learning_rate": 0.00018219696969696972,
|
| 572 |
+
"loss": 2.2736,
|
| 573 |
+
"step": 94
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.27,
|
| 577 |
+
"learning_rate": 0.00018200757575757577,
|
| 578 |
+
"loss": 2.2443,
|
| 579 |
+
"step": 95
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.27,
|
| 583 |
+
"learning_rate": 0.00018181818181818183,
|
| 584 |
+
"loss": 2.2299,
|
| 585 |
+
"step": 96
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.28,
|
| 589 |
+
"learning_rate": 0.0001816287878787879,
|
| 590 |
+
"loss": 2.2644,
|
| 591 |
+
"step": 97
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.28,
|
| 595 |
+
"learning_rate": 0.00018143939393939395,
|
| 596 |
+
"loss": 2.259,
|
| 597 |
+
"step": 98
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.28,
|
| 601 |
+
"learning_rate": 0.00018125000000000001,
|
| 602 |
+
"loss": 2.2567,
|
| 603 |
+
"step": 99
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.28,
|
| 607 |
+
"learning_rate": 0.00018106060606060606,
|
| 608 |
+
"loss": 2.2599,
|
| 609 |
+
"step": 100
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.29,
|
| 613 |
+
"learning_rate": 0.00018087121212121213,
|
| 614 |
+
"loss": 2.2091,
|
| 615 |
+
"step": 101
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 0.29,
|
| 619 |
+
"learning_rate": 0.0001806818181818182,
|
| 620 |
+
"loss": 2.2312,
|
| 621 |
+
"step": 102
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 0.29,
|
| 625 |
+
"learning_rate": 0.00018049242424242426,
|
| 626 |
+
"loss": 2.1869,
|
| 627 |
+
"step": 103
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.3,
|
| 631 |
+
"learning_rate": 0.0001803030303030303,
|
| 632 |
+
"loss": 2.2023,
|
| 633 |
+
"step": 104
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.3,
|
| 637 |
+
"learning_rate": 0.00018011363636363638,
|
| 638 |
+
"loss": 2.2132,
|
| 639 |
+
"step": 105
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.3,
|
| 643 |
+
"learning_rate": 0.00017992424242424244,
|
| 644 |
+
"loss": 2.2612,
|
| 645 |
+
"step": 106
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 0.3,
|
| 649 |
+
"learning_rate": 0.0001797348484848485,
|
| 650 |
+
"loss": 2.2109,
|
| 651 |
+
"step": 107
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 0.31,
|
| 655 |
+
"learning_rate": 0.00017954545454545456,
|
| 656 |
+
"loss": 2.215,
|
| 657 |
+
"step": 108
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.31,
|
| 661 |
+
"learning_rate": 0.0001793560606060606,
|
| 662 |
+
"loss": 2.2114,
|
| 663 |
+
"step": 109
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 0.31,
|
| 667 |
+
"learning_rate": 0.0001791666666666667,
|
| 668 |
+
"loss": 2.2203,
|
| 669 |
+
"step": 110
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.31,
|
| 673 |
+
"learning_rate": 0.00017897727272727274,
|
| 674 |
+
"loss": 2.2594,
|
| 675 |
+
"step": 111
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.32,
|
| 679 |
+
"learning_rate": 0.0001787878787878788,
|
| 680 |
+
"loss": 2.2001,
|
| 681 |
+
"step": 112
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.32,
|
| 685 |
+
"learning_rate": 0.00017859848484848485,
|
| 686 |
+
"loss": 2.2046,
|
| 687 |
+
"step": 113
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 0.32,
|
| 691 |
+
"learning_rate": 0.00017840909090909092,
|
| 692 |
+
"loss": 2.1907,
|
| 693 |
+
"step": 114
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 0.33,
|
| 697 |
+
"learning_rate": 0.00017821969696969699,
|
| 698 |
+
"loss": 2.2539,
|
| 699 |
+
"step": 115
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 0.33,
|
| 703 |
+
"learning_rate": 0.00017803030303030303,
|
| 704 |
+
"loss": 2.2335,
|
| 705 |
+
"step": 116
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 0.33,
|
| 709 |
+
"learning_rate": 0.0001778409090909091,
|
| 710 |
+
"loss": 2.2171,
|
| 711 |
+
"step": 117
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.33,
|
| 715 |
+
"learning_rate": 0.00017765151515151517,
|
| 716 |
+
"loss": 2.2278,
|
| 717 |
+
"step": 118
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.34,
|
| 721 |
+
"learning_rate": 0.00017746212121212123,
|
| 722 |
+
"loss": 2.231,
|
| 723 |
+
"step": 119
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.34,
|
| 727 |
+
"learning_rate": 0.00017727272727272728,
|
| 728 |
+
"loss": 2.2141,
|
| 729 |
+
"step": 120
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.34,
|
| 733 |
+
"learning_rate": 0.00017708333333333335,
|
| 734 |
+
"loss": 2.2432,
|
| 735 |
+
"step": 121
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 0.35,
|
| 739 |
+
"learning_rate": 0.00017689393939393942,
|
| 740 |
+
"loss": 2.2266,
|
| 741 |
+
"step": 122
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.35,
|
| 745 |
+
"learning_rate": 0.00017670454545454546,
|
| 746 |
+
"loss": 2.1929,
|
| 747 |
+
"step": 123
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.35,
|
| 751 |
+
"learning_rate": 0.00017651515151515153,
|
| 752 |
+
"loss": 2.2077,
|
| 753 |
+
"step": 124
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 0.35,
|
| 757 |
+
"learning_rate": 0.00017632575757575757,
|
| 758 |
+
"loss": 2.2133,
|
| 759 |
+
"step": 125
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.36,
|
| 763 |
+
"learning_rate": 0.00017613636363636366,
|
| 764 |
+
"loss": 2.2251,
|
| 765 |
+
"step": 126
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.36,
|
| 769 |
+
"learning_rate": 0.0001759469696969697,
|
| 770 |
+
"loss": 2.2265,
|
| 771 |
+
"step": 127
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 0.36,
|
| 775 |
+
"learning_rate": 0.00017575757575757578,
|
| 776 |
+
"loss": 2.2186,
|
| 777 |
+
"step": 128
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 0.37,
|
| 781 |
+
"learning_rate": 0.00017556818181818182,
|
| 782 |
+
"loss": 2.1925,
|
| 783 |
+
"step": 129
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 0.37,
|
| 787 |
+
"learning_rate": 0.0001753787878787879,
|
| 788 |
+
"loss": 2.1956,
|
| 789 |
+
"step": 130
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.37,
|
| 793 |
+
"learning_rate": 0.00017518939393939396,
|
| 794 |
+
"loss": 2.2459,
|
| 795 |
+
"step": 131
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 0.37,
|
| 799 |
+
"learning_rate": 0.000175,
|
| 800 |
+
"loss": 2.22,
|
| 801 |
+
"step": 132
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.38,
|
| 805 |
+
"learning_rate": 0.00017481060606060607,
|
| 806 |
+
"loss": 2.2143,
|
| 807 |
+
"step": 133
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.38,
|
| 811 |
+
"learning_rate": 0.0001746212121212121,
|
| 812 |
+
"loss": 2.2359,
|
| 813 |
+
"step": 134
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 0.38,
|
| 817 |
+
"learning_rate": 0.0001744318181818182,
|
| 818 |
+
"loss": 2.2058,
|
| 819 |
+
"step": 135
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 0.39,
|
| 823 |
+
"learning_rate": 0.00017424242424242425,
|
| 824 |
+
"loss": 2.2307,
|
| 825 |
+
"step": 136
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 0.39,
|
| 829 |
+
"learning_rate": 0.00017405303030303032,
|
| 830 |
+
"loss": 2.2062,
|
| 831 |
+
"step": 137
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.39,
|
| 835 |
+
"learning_rate": 0.00017386363636363636,
|
| 836 |
+
"loss": 2.1796,
|
| 837 |
+
"step": 138
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 0.39,
|
| 841 |
+
"learning_rate": 0.00017367424242424243,
|
| 842 |
+
"loss": 2.2054,
|
| 843 |
+
"step": 139
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.4,
|
| 847 |
+
"learning_rate": 0.0001734848484848485,
|
| 848 |
+
"loss": 2.1651,
|
| 849 |
+
"step": 140
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.4,
|
| 853 |
+
"learning_rate": 0.00017329545454545454,
|
| 854 |
+
"loss": 2.2159,
|
| 855 |
+
"step": 141
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 0.4,
|
| 859 |
+
"learning_rate": 0.0001731060606060606,
|
| 860 |
+
"loss": 2.1988,
|
| 861 |
+
"step": 142
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 0.41,
|
| 865 |
+
"learning_rate": 0.00017291666666666668,
|
| 866 |
+
"loss": 2.1676,
|
| 867 |
+
"step": 143
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 0.41,
|
| 871 |
+
"learning_rate": 0.00017272727272727275,
|
| 872 |
+
"loss": 2.1725,
|
| 873 |
+
"step": 144
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.41,
|
| 877 |
+
"learning_rate": 0.0001725378787878788,
|
| 878 |
+
"loss": 2.2205,
|
| 879 |
+
"step": 145
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 0.41,
|
| 883 |
+
"learning_rate": 0.00017234848484848486,
|
| 884 |
+
"loss": 2.1486,
|
| 885 |
+
"step": 146
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.42,
|
| 889 |
+
"learning_rate": 0.00017215909090909093,
|
| 890 |
+
"loss": 2.147,
|
| 891 |
+
"step": 147
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.42,
|
| 895 |
+
"learning_rate": 0.00017196969696969697,
|
| 896 |
+
"loss": 2.1651,
|
| 897 |
+
"step": 148
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 0.42,
|
| 901 |
+
"learning_rate": 0.00017178030303030304,
|
| 902 |
+
"loss": 2.1983,
|
| 903 |
+
"step": 149
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 0.43,
|
| 907 |
+
"learning_rate": 0.00017159090909090908,
|
| 908 |
+
"loss": 2.1778,
|
| 909 |
+
"step": 150
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 0.43,
|
| 913 |
+
"learning_rate": 0.00017140151515151518,
|
| 914 |
+
"loss": 2.1631,
|
| 915 |
+
"step": 151
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.43,
|
| 919 |
+
"learning_rate": 0.00017121212121212122,
|
| 920 |
+
"loss": 2.1442,
|
| 921 |
+
"step": 152
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 0.43,
|
| 925 |
+
"learning_rate": 0.0001710227272727273,
|
| 926 |
+
"loss": 2.1397,
|
| 927 |
+
"step": 153
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.44,
|
| 931 |
+
"learning_rate": 0.00017083333333333333,
|
| 932 |
+
"loss": 2.1697,
|
| 933 |
+
"step": 154
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.44,
|
| 937 |
+
"learning_rate": 0.0001706439393939394,
|
| 938 |
+
"loss": 2.1451,
|
| 939 |
+
"step": 155
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 0.44,
|
| 943 |
+
"learning_rate": 0.00017045454545454547,
|
| 944 |
+
"loss": 2.1789,
|
| 945 |
+
"step": 156
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 0.45,
|
| 949 |
+
"learning_rate": 0.0001702651515151515,
|
| 950 |
+
"loss": 2.1037,
|
| 951 |
+
"step": 157
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 0.45,
|
| 955 |
+
"learning_rate": 0.00017007575757575758,
|
| 956 |
+
"loss": 2.1698,
|
| 957 |
+
"step": 158
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.45,
|
| 961 |
+
"learning_rate": 0.00016988636363636365,
|
| 962 |
+
"loss": 2.1538,
|
| 963 |
+
"step": 159
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 0.45,
|
| 967 |
+
"learning_rate": 0.00016969696969696972,
|
| 968 |
+
"loss": 2.2015,
|
| 969 |
+
"step": 160
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.46,
|
| 973 |
+
"learning_rate": 0.00016950757575757576,
|
| 974 |
+
"loss": 2.179,
|
| 975 |
+
"step": 161
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.46,
|
| 979 |
+
"learning_rate": 0.00016931818181818183,
|
| 980 |
+
"loss": 2.1766,
|
| 981 |
+
"step": 162
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 0.46,
|
| 985 |
+
"learning_rate": 0.0001691287878787879,
|
| 986 |
+
"loss": 2.1646,
|
| 987 |
+
"step": 163
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 0.47,
|
| 991 |
+
"learning_rate": 0.00016893939393939394,
|
| 992 |
+
"loss": 2.1694,
|
| 993 |
+
"step": 164
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 0.47,
|
| 997 |
+
"learning_rate": 0.00016875,
|
| 998 |
+
"loss": 2.1562,
|
| 999 |
+
"step": 165
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.47,
|
| 1003 |
+
"learning_rate": 0.00016856060606060605,
|
| 1004 |
+
"loss": 2.1551,
|
| 1005 |
+
"step": 166
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 0.47,
|
| 1009 |
+
"learning_rate": 0.00016837121212121212,
|
| 1010 |
+
"loss": 2.1652,
|
| 1011 |
+
"step": 167
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.48,
|
| 1015 |
+
"learning_rate": 0.0001681818181818182,
|
| 1016 |
+
"loss": 2.1594,
|
| 1017 |
+
"step": 168
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.48,
|
| 1021 |
+
"learning_rate": 0.00016799242424242426,
|
| 1022 |
+
"loss": 2.1674,
|
| 1023 |
+
"step": 169
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 0.48,
|
| 1027 |
+
"learning_rate": 0.0001678030303030303,
|
| 1028 |
+
"loss": 2.1378,
|
| 1029 |
+
"step": 170
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 0.49,
|
| 1033 |
+
"learning_rate": 0.00016761363636363637,
|
| 1034 |
+
"loss": 2.1447,
|
| 1035 |
+
"step": 171
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 0.49,
|
| 1039 |
+
"learning_rate": 0.00016742424242424244,
|
| 1040 |
+
"loss": 2.1451,
|
| 1041 |
+
"step": 172
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.49,
|
| 1045 |
+
"learning_rate": 0.00016723484848484848,
|
| 1046 |
+
"loss": 2.1336,
|
| 1047 |
+
"step": 173
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 0.49,
|
| 1051 |
+
"learning_rate": 0.00016704545454545455,
|
| 1052 |
+
"loss": 2.1231,
|
| 1053 |
+
"step": 174
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.5,
|
| 1057 |
+
"learning_rate": 0.0001668560606060606,
|
| 1058 |
+
"loss": 2.1143,
|
| 1059 |
+
"step": 175
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.5,
|
| 1063 |
+
"learning_rate": 0.0001666666666666667,
|
| 1064 |
+
"loss": 2.1316,
|
| 1065 |
+
"step": 176
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 0.5,
|
| 1069 |
+
"learning_rate": 0.00016647727272727273,
|
| 1070 |
+
"loss": 2.1281,
|
| 1071 |
+
"step": 177
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 0.5,
|
| 1075 |
+
"learning_rate": 0.0001662878787878788,
|
| 1076 |
+
"loss": 2.136,
|
| 1077 |
+
"step": 178
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 0.51,
|
| 1081 |
+
"learning_rate": 0.00016609848484848484,
|
| 1082 |
+
"loss": 2.1279,
|
| 1083 |
+
"step": 179
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 0.51,
|
| 1087 |
+
"learning_rate": 0.00016590909090909094,
|
| 1088 |
+
"loss": 2.1421,
|
| 1089 |
+
"step": 180
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 0.51,
|
| 1093 |
+
"learning_rate": 0.00016571969696969698,
|
| 1094 |
+
"loss": 2.1541,
|
| 1095 |
+
"step": 181
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.52,
|
| 1099 |
+
"learning_rate": 0.00016553030303030305,
|
| 1100 |
+
"loss": 2.1293,
|
| 1101 |
+
"step": 182
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.52,
|
| 1105 |
+
"learning_rate": 0.0001653409090909091,
|
| 1106 |
+
"loss": 2.1294,
|
| 1107 |
+
"step": 183
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 0.52,
|
| 1111 |
+
"learning_rate": 0.00016515151515151516,
|
| 1112 |
+
"loss": 2.1459,
|
| 1113 |
+
"step": 184
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 0.52,
|
| 1117 |
+
"learning_rate": 0.00016496212121212123,
|
| 1118 |
+
"loss": 2.1113,
|
| 1119 |
+
"step": 185
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.53,
|
| 1123 |
+
"learning_rate": 0.00016477272727272727,
|
| 1124 |
+
"loss": 2.1394,
|
| 1125 |
+
"step": 186
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 0.53,
|
| 1129 |
+
"learning_rate": 0.00016458333333333334,
|
| 1130 |
+
"loss": 2.1321,
|
| 1131 |
+
"step": 187
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 0.53,
|
| 1135 |
+
"learning_rate": 0.0001643939393939394,
|
| 1136 |
+
"loss": 2.148,
|
| 1137 |
+
"step": 188
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.54,
|
| 1141 |
+
"learning_rate": 0.00016420454545454548,
|
| 1142 |
+
"loss": 2.1631,
|
| 1143 |
+
"step": 189
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.54,
|
| 1147 |
+
"learning_rate": 0.00016401515151515152,
|
| 1148 |
+
"loss": 2.1276,
|
| 1149 |
+
"step": 190
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 0.54,
|
| 1153 |
+
"learning_rate": 0.0001638257575757576,
|
| 1154 |
+
"loss": 2.0706,
|
| 1155 |
+
"step": 191
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 0.54,
|
| 1159 |
+
"learning_rate": 0.00016363636363636366,
|
| 1160 |
+
"loss": 2.127,
|
| 1161 |
+
"step": 192
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.55,
|
| 1165 |
+
"learning_rate": 0.0001634469696969697,
|
| 1166 |
+
"loss": 2.1449,
|
| 1167 |
+
"step": 193
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 0.55,
|
| 1171 |
+
"learning_rate": 0.00016325757575757577,
|
| 1172 |
+
"loss": 2.1204,
|
| 1173 |
+
"step": 194
|
| 1174 |
+
},
|
| 1175 |
+
{
|
| 1176 |
+
"epoch": 0.55,
|
| 1177 |
+
"learning_rate": 0.0001630681818181818,
|
| 1178 |
+
"loss": 2.0904,
|
| 1179 |
+
"step": 195
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.56,
|
| 1183 |
+
"learning_rate": 0.0001628787878787879,
|
| 1184 |
+
"loss": 2.1129,
|
| 1185 |
+
"step": 196
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.56,
|
| 1189 |
+
"learning_rate": 0.00016268939393939395,
|
| 1190 |
+
"loss": 2.1036,
|
| 1191 |
+
"step": 197
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 0.56,
|
| 1195 |
+
"learning_rate": 0.00016250000000000002,
|
| 1196 |
+
"loss": 2.1509,
|
| 1197 |
+
"step": 198
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 0.56,
|
| 1201 |
+
"learning_rate": 0.00016231060606060606,
|
| 1202 |
+
"loss": 2.1239,
|
| 1203 |
+
"step": 199
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.57,
|
| 1207 |
+
"learning_rate": 0.00016212121212121213,
|
| 1208 |
+
"loss": 2.145,
|
| 1209 |
+
"step": 200
|
| 1210 |
+
}
|
| 1211 |
+
],
|
| 1212 |
+
"logging_steps": 1,
|
| 1213 |
+
"max_steps": 1056,
|
| 1214 |
+
"num_train_epochs": 3,
|
| 1215 |
+
"save_steps": 100,
|
| 1216 |
+
"total_flos": 5.0683926177970176e+17,
|
| 1217 |
+
"trial_name": null,
|
| 1218 |
+
"trial_params": null
|
| 1219 |
+
}
|
checkpoint-200/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:50303c7f1586feb001f01b7e968e567295f501ef6c6407e28250c458696a43af
|
| 3 |
+
size 4155
|
checkpoint-300/README.md
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
---
|
| 4 |
+
## Training procedure
|
| 5 |
+
|
| 6 |
+
|
| 7 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 8 |
+
- quant_method: bitsandbytes
|
| 9 |
+
- load_in_8bit: True
|
| 10 |
+
- load_in_4bit: False
|
| 11 |
+
- llm_int8_threshold: 6.0
|
| 12 |
+
- llm_int8_skip_modules: None
|
| 13 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 14 |
+
- llm_int8_has_fp16_weight: False
|
| 15 |
+
- bnb_4bit_quant_type: fp4
|
| 16 |
+
- bnb_4bit_use_double_quant: False
|
| 17 |
+
- bnb_4bit_compute_dtype: float32
|
| 18 |
+
|
| 19 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 20 |
+
- quant_method: bitsandbytes
|
| 21 |
+
- load_in_8bit: True
|
| 22 |
+
- load_in_4bit: False
|
| 23 |
+
- llm_int8_threshold: 6.0
|
| 24 |
+
- llm_int8_skip_modules: None
|
| 25 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 26 |
+
- llm_int8_has_fp16_weight: False
|
| 27 |
+
- bnb_4bit_quant_type: fp4
|
| 28 |
+
- bnb_4bit_use_double_quant: False
|
| 29 |
+
- bnb_4bit_compute_dtype: float32
|
| 30 |
+
### Framework versions
|
| 31 |
+
|
| 32 |
+
- PEFT 0.6.0.dev0
|
| 33 |
+
|
| 34 |
+
- PEFT 0.6.0.dev0
|
checkpoint-300/adapter_config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "bigscience/bloomz-3b",
|
| 4 |
+
"bias": "none",
|
| 5 |
+
"fan_in_fan_out": false,
|
| 6 |
+
"inference_mode": true,
|
| 7 |
+
"init_lora_weights": true,
|
| 8 |
+
"layers_pattern": null,
|
| 9 |
+
"layers_to_transform": null,
|
| 10 |
+
"lora_alpha": 16,
|
| 11 |
+
"lora_dropout": 0.0,
|
| 12 |
+
"modules_to_save": null,
|
| 13 |
+
"peft_type": "LORA",
|
| 14 |
+
"r": 8,
|
| 15 |
+
"revision": null,
|
| 16 |
+
"target_modules": [
|
| 17 |
+
"dense_4h_to_h",
|
| 18 |
+
"dense",
|
| 19 |
+
"dense_h_to_4h",
|
| 20 |
+
"query_key_value"
|
| 21 |
+
],
|
| 22 |
+
"task_type": "CAUSAL_LM"
|
| 23 |
+
}
|
checkpoint-300/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d73a6061995dfd3470fb05f76f5e41d5f8e33b867534c494972efadc2689f043
|
| 3 |
+
size 39409357
|
checkpoint-300/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e907c311aa285e9bae5575de3a9db0ba37e8290ea4e2ddeb374df9aed022a507
|
| 3 |
+
size 78844421
|
checkpoint-300/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b2278a87cdf86c3f9219223c847f6b27f6b7f15b8226b617f38936e8ff2cbcde
|
| 3 |
+
size 14575
|
checkpoint-300/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e94d9046da30e8144679cc9c489e77f8d73da1feed453b2a636a27ad2550580f
|
| 3 |
+
size 627
|
checkpoint-300/special_tokens_map.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"eos_token": "</s>",
|
| 4 |
+
"pad_token": "<pad>",
|
| 5 |
+
"unk_token": "<unk>"
|
| 6 |
+
}
|
checkpoint-300/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:85b00d7db4df5df2e3f01cacc3feda246002a672f3356eec7f4b04a22eb0dfbe
|
| 3 |
+
size 14500570
|
checkpoint-300/tokenizer_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"clean_up_tokenization_spaces": false,
|
| 5 |
+
"eos_token": "</s>",
|
| 6 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 7 |
+
"pad_token": "<pad>",
|
| 8 |
+
"tokenizer_class": "BloomTokenizer",
|
| 9 |
+
"unk_token": "<unk>"
|
| 10 |
+
}
|
checkpoint-300/trainer_state.json
ADDED
|
@@ -0,0 +1,1819 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.851063829787234,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 300,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"learning_rate": 0.00019981060606060605,
|
| 14 |
+
"loss": 2.9206,
|
| 15 |
+
"step": 1
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.01,
|
| 19 |
+
"learning_rate": 0.00019962121212121212,
|
| 20 |
+
"loss": 2.7609,
|
| 21 |
+
"step": 2
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.01,
|
| 25 |
+
"learning_rate": 0.0001994318181818182,
|
| 26 |
+
"loss": 2.6878,
|
| 27 |
+
"step": 3
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.01,
|
| 31 |
+
"learning_rate": 0.00019924242424242426,
|
| 32 |
+
"loss": 2.6697,
|
| 33 |
+
"step": 4
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.01,
|
| 37 |
+
"learning_rate": 0.0001990530303030303,
|
| 38 |
+
"loss": 2.5818,
|
| 39 |
+
"step": 5
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.02,
|
| 43 |
+
"learning_rate": 0.00019886363636363637,
|
| 44 |
+
"loss": 2.5396,
|
| 45 |
+
"step": 6
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.02,
|
| 49 |
+
"learning_rate": 0.00019867424242424244,
|
| 50 |
+
"loss": 2.5265,
|
| 51 |
+
"step": 7
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.02,
|
| 55 |
+
"learning_rate": 0.0001984848484848485,
|
| 56 |
+
"loss": 2.5475,
|
| 57 |
+
"step": 8
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.03,
|
| 61 |
+
"learning_rate": 0.00019829545454545455,
|
| 62 |
+
"loss": 2.4835,
|
| 63 |
+
"step": 9
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.03,
|
| 67 |
+
"learning_rate": 0.0001981060606060606,
|
| 68 |
+
"loss": 2.4559,
|
| 69 |
+
"step": 10
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.03,
|
| 73 |
+
"learning_rate": 0.0001979166666666667,
|
| 74 |
+
"loss": 2.4511,
|
| 75 |
+
"step": 11
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.03,
|
| 79 |
+
"learning_rate": 0.00019772727272727273,
|
| 80 |
+
"loss": 2.4592,
|
| 81 |
+
"step": 12
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.04,
|
| 85 |
+
"learning_rate": 0.0001975378787878788,
|
| 86 |
+
"loss": 2.4495,
|
| 87 |
+
"step": 13
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.04,
|
| 91 |
+
"learning_rate": 0.00019734848484848484,
|
| 92 |
+
"loss": 2.4714,
|
| 93 |
+
"step": 14
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.04,
|
| 97 |
+
"learning_rate": 0.00019715909090909094,
|
| 98 |
+
"loss": 2.4302,
|
| 99 |
+
"step": 15
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.05,
|
| 103 |
+
"learning_rate": 0.00019696969696969698,
|
| 104 |
+
"loss": 2.4097,
|
| 105 |
+
"step": 16
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.05,
|
| 109 |
+
"learning_rate": 0.00019678030303030305,
|
| 110 |
+
"loss": 2.4523,
|
| 111 |
+
"step": 17
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.05,
|
| 115 |
+
"learning_rate": 0.0001965909090909091,
|
| 116 |
+
"loss": 2.4325,
|
| 117 |
+
"step": 18
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.05,
|
| 121 |
+
"learning_rate": 0.00019640151515151516,
|
| 122 |
+
"loss": 2.4125,
|
| 123 |
+
"step": 19
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.06,
|
| 127 |
+
"learning_rate": 0.00019621212121212123,
|
| 128 |
+
"loss": 2.4329,
|
| 129 |
+
"step": 20
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.06,
|
| 133 |
+
"learning_rate": 0.00019602272727272727,
|
| 134 |
+
"loss": 2.3471,
|
| 135 |
+
"step": 21
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.06,
|
| 139 |
+
"learning_rate": 0.00019583333333333334,
|
| 140 |
+
"loss": 2.3012,
|
| 141 |
+
"step": 22
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.07,
|
| 145 |
+
"learning_rate": 0.0001956439393939394,
|
| 146 |
+
"loss": 2.3869,
|
| 147 |
+
"step": 23
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.07,
|
| 151 |
+
"learning_rate": 0.00019545454545454548,
|
| 152 |
+
"loss": 2.3822,
|
| 153 |
+
"step": 24
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.07,
|
| 157 |
+
"learning_rate": 0.00019526515151515152,
|
| 158 |
+
"loss": 2.3427,
|
| 159 |
+
"step": 25
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.07,
|
| 163 |
+
"learning_rate": 0.0001950757575757576,
|
| 164 |
+
"loss": 2.3659,
|
| 165 |
+
"step": 26
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.08,
|
| 169 |
+
"learning_rate": 0.00019488636363636366,
|
| 170 |
+
"loss": 2.3826,
|
| 171 |
+
"step": 27
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.08,
|
| 175 |
+
"learning_rate": 0.0001946969696969697,
|
| 176 |
+
"loss": 2.3532,
|
| 177 |
+
"step": 28
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.08,
|
| 181 |
+
"learning_rate": 0.00019450757575757577,
|
| 182 |
+
"loss": 2.3828,
|
| 183 |
+
"step": 29
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.09,
|
| 187 |
+
"learning_rate": 0.0001943181818181818,
|
| 188 |
+
"loss": 2.3133,
|
| 189 |
+
"step": 30
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.09,
|
| 193 |
+
"learning_rate": 0.0001941287878787879,
|
| 194 |
+
"loss": 2.3613,
|
| 195 |
+
"step": 31
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.09,
|
| 199 |
+
"learning_rate": 0.00019393939393939395,
|
| 200 |
+
"loss": 2.3867,
|
| 201 |
+
"step": 32
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.09,
|
| 205 |
+
"learning_rate": 0.00019375000000000002,
|
| 206 |
+
"loss": 2.2966,
|
| 207 |
+
"step": 33
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.1,
|
| 211 |
+
"learning_rate": 0.00019356060606060606,
|
| 212 |
+
"loss": 2.3436,
|
| 213 |
+
"step": 34
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.1,
|
| 217 |
+
"learning_rate": 0.00019337121212121213,
|
| 218 |
+
"loss": 2.3425,
|
| 219 |
+
"step": 35
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.1,
|
| 223 |
+
"learning_rate": 0.0001931818181818182,
|
| 224 |
+
"loss": 2.307,
|
| 225 |
+
"step": 36
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.1,
|
| 229 |
+
"learning_rate": 0.00019299242424242424,
|
| 230 |
+
"loss": 2.3521,
|
| 231 |
+
"step": 37
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.11,
|
| 235 |
+
"learning_rate": 0.0001928030303030303,
|
| 236 |
+
"loss": 2.3302,
|
| 237 |
+
"step": 38
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.11,
|
| 241 |
+
"learning_rate": 0.00019261363636363635,
|
| 242 |
+
"loss": 2.312,
|
| 243 |
+
"step": 39
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.11,
|
| 247 |
+
"learning_rate": 0.00019242424242424245,
|
| 248 |
+
"loss": 2.3655,
|
| 249 |
+
"step": 40
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.12,
|
| 253 |
+
"learning_rate": 0.0001922348484848485,
|
| 254 |
+
"loss": 2.344,
|
| 255 |
+
"step": 41
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.12,
|
| 259 |
+
"learning_rate": 0.00019204545454545456,
|
| 260 |
+
"loss": 2.3373,
|
| 261 |
+
"step": 42
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.12,
|
| 265 |
+
"learning_rate": 0.0001918560606060606,
|
| 266 |
+
"loss": 2.3331,
|
| 267 |
+
"step": 43
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.12,
|
| 271 |
+
"learning_rate": 0.00019166666666666667,
|
| 272 |
+
"loss": 2.3376,
|
| 273 |
+
"step": 44
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.13,
|
| 277 |
+
"learning_rate": 0.00019147727272727274,
|
| 278 |
+
"loss": 2.3369,
|
| 279 |
+
"step": 45
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.13,
|
| 283 |
+
"learning_rate": 0.00019128787878787878,
|
| 284 |
+
"loss": 2.3413,
|
| 285 |
+
"step": 46
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.13,
|
| 289 |
+
"learning_rate": 0.00019109848484848485,
|
| 290 |
+
"loss": 2.3212,
|
| 291 |
+
"step": 47
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.14,
|
| 295 |
+
"learning_rate": 0.00019090909090909092,
|
| 296 |
+
"loss": 2.307,
|
| 297 |
+
"step": 48
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.14,
|
| 301 |
+
"learning_rate": 0.000190719696969697,
|
| 302 |
+
"loss": 2.2929,
|
| 303 |
+
"step": 49
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.14,
|
| 307 |
+
"learning_rate": 0.00019053030303030303,
|
| 308 |
+
"loss": 2.2873,
|
| 309 |
+
"step": 50
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.14,
|
| 313 |
+
"learning_rate": 0.0001903409090909091,
|
| 314 |
+
"loss": 2.3098,
|
| 315 |
+
"step": 51
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.15,
|
| 319 |
+
"learning_rate": 0.00019015151515151517,
|
| 320 |
+
"loss": 2.3129,
|
| 321 |
+
"step": 52
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.15,
|
| 325 |
+
"learning_rate": 0.0001899621212121212,
|
| 326 |
+
"loss": 2.3038,
|
| 327 |
+
"step": 53
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.15,
|
| 331 |
+
"learning_rate": 0.00018977272727272728,
|
| 332 |
+
"loss": 2.286,
|
| 333 |
+
"step": 54
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.16,
|
| 337 |
+
"learning_rate": 0.00018958333333333332,
|
| 338 |
+
"loss": 2.3388,
|
| 339 |
+
"step": 55
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.16,
|
| 343 |
+
"learning_rate": 0.00018939393939393942,
|
| 344 |
+
"loss": 2.3193,
|
| 345 |
+
"step": 56
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.16,
|
| 349 |
+
"learning_rate": 0.00018920454545454546,
|
| 350 |
+
"loss": 2.3136,
|
| 351 |
+
"step": 57
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.16,
|
| 355 |
+
"learning_rate": 0.00018901515151515153,
|
| 356 |
+
"loss": 2.3141,
|
| 357 |
+
"step": 58
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.17,
|
| 361 |
+
"learning_rate": 0.00018882575757575757,
|
| 362 |
+
"loss": 2.3646,
|
| 363 |
+
"step": 59
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.17,
|
| 367 |
+
"learning_rate": 0.00018863636363636364,
|
| 368 |
+
"loss": 2.3318,
|
| 369 |
+
"step": 60
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.17,
|
| 373 |
+
"learning_rate": 0.0001884469696969697,
|
| 374 |
+
"loss": 2.2977,
|
| 375 |
+
"step": 61
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.18,
|
| 379 |
+
"learning_rate": 0.00018825757575757575,
|
| 380 |
+
"loss": 2.2764,
|
| 381 |
+
"step": 62
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.18,
|
| 385 |
+
"learning_rate": 0.00018806818181818182,
|
| 386 |
+
"loss": 2.3095,
|
| 387 |
+
"step": 63
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.18,
|
| 391 |
+
"learning_rate": 0.0001878787878787879,
|
| 392 |
+
"loss": 2.252,
|
| 393 |
+
"step": 64
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.18,
|
| 397 |
+
"learning_rate": 0.00018768939393939396,
|
| 398 |
+
"loss": 2.2786,
|
| 399 |
+
"step": 65
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.19,
|
| 403 |
+
"learning_rate": 0.0001875,
|
| 404 |
+
"loss": 2.2789,
|
| 405 |
+
"step": 66
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.19,
|
| 409 |
+
"learning_rate": 0.00018731060606060607,
|
| 410 |
+
"loss": 2.2841,
|
| 411 |
+
"step": 67
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.19,
|
| 415 |
+
"learning_rate": 0.00018712121212121212,
|
| 416 |
+
"loss": 2.3436,
|
| 417 |
+
"step": 68
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.2,
|
| 421 |
+
"learning_rate": 0.00018693181818181818,
|
| 422 |
+
"loss": 2.2956,
|
| 423 |
+
"step": 69
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.2,
|
| 427 |
+
"learning_rate": 0.00018674242424242425,
|
| 428 |
+
"loss": 2.2353,
|
| 429 |
+
"step": 70
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.2,
|
| 433 |
+
"learning_rate": 0.0001865530303030303,
|
| 434 |
+
"loss": 2.2772,
|
| 435 |
+
"step": 71
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.2,
|
| 439 |
+
"learning_rate": 0.00018636363636363636,
|
| 440 |
+
"loss": 2.2496,
|
| 441 |
+
"step": 72
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.21,
|
| 445 |
+
"learning_rate": 0.00018617424242424243,
|
| 446 |
+
"loss": 2.2477,
|
| 447 |
+
"step": 73
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.21,
|
| 451 |
+
"learning_rate": 0.0001859848484848485,
|
| 452 |
+
"loss": 2.2791,
|
| 453 |
+
"step": 74
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.21,
|
| 457 |
+
"learning_rate": 0.00018579545454545454,
|
| 458 |
+
"loss": 2.2799,
|
| 459 |
+
"step": 75
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.22,
|
| 463 |
+
"learning_rate": 0.00018560606060606061,
|
| 464 |
+
"loss": 2.3132,
|
| 465 |
+
"step": 76
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.22,
|
| 469 |
+
"learning_rate": 0.00018541666666666668,
|
| 470 |
+
"loss": 2.2542,
|
| 471 |
+
"step": 77
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.22,
|
| 475 |
+
"learning_rate": 0.00018522727272727273,
|
| 476 |
+
"loss": 2.2609,
|
| 477 |
+
"step": 78
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.22,
|
| 481 |
+
"learning_rate": 0.0001850378787878788,
|
| 482 |
+
"loss": 2.2819,
|
| 483 |
+
"step": 79
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.23,
|
| 487 |
+
"learning_rate": 0.00018484848484848484,
|
| 488 |
+
"loss": 2.2844,
|
| 489 |
+
"step": 80
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.23,
|
| 493 |
+
"learning_rate": 0.00018465909090909093,
|
| 494 |
+
"loss": 2.2542,
|
| 495 |
+
"step": 81
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.23,
|
| 499 |
+
"learning_rate": 0.00018446969696969697,
|
| 500 |
+
"loss": 2.2603,
|
| 501 |
+
"step": 82
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.24,
|
| 505 |
+
"learning_rate": 0.00018428030303030304,
|
| 506 |
+
"loss": 2.2832,
|
| 507 |
+
"step": 83
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.24,
|
| 511 |
+
"learning_rate": 0.00018409090909090909,
|
| 512 |
+
"loss": 2.2869,
|
| 513 |
+
"step": 84
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.24,
|
| 517 |
+
"learning_rate": 0.00018390151515151518,
|
| 518 |
+
"loss": 2.2646,
|
| 519 |
+
"step": 85
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.24,
|
| 523 |
+
"learning_rate": 0.00018371212121212122,
|
| 524 |
+
"loss": 2.2698,
|
| 525 |
+
"step": 86
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.25,
|
| 529 |
+
"learning_rate": 0.00018352272727272727,
|
| 530 |
+
"loss": 2.2757,
|
| 531 |
+
"step": 87
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 0.25,
|
| 535 |
+
"learning_rate": 0.00018333333333333334,
|
| 536 |
+
"loss": 2.2544,
|
| 537 |
+
"step": 88
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.25,
|
| 541 |
+
"learning_rate": 0.0001831439393939394,
|
| 542 |
+
"loss": 2.2678,
|
| 543 |
+
"step": 89
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.26,
|
| 547 |
+
"learning_rate": 0.00018295454545454547,
|
| 548 |
+
"loss": 2.2778,
|
| 549 |
+
"step": 90
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.26,
|
| 553 |
+
"learning_rate": 0.00018276515151515152,
|
| 554 |
+
"loss": 2.2027,
|
| 555 |
+
"step": 91
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.26,
|
| 559 |
+
"learning_rate": 0.00018257575757575758,
|
| 560 |
+
"loss": 2.2167,
|
| 561 |
+
"step": 92
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.26,
|
| 565 |
+
"learning_rate": 0.00018238636363636365,
|
| 566 |
+
"loss": 2.2602,
|
| 567 |
+
"step": 93
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 0.27,
|
| 571 |
+
"learning_rate": 0.00018219696969696972,
|
| 572 |
+
"loss": 2.2736,
|
| 573 |
+
"step": 94
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.27,
|
| 577 |
+
"learning_rate": 0.00018200757575757577,
|
| 578 |
+
"loss": 2.2443,
|
| 579 |
+
"step": 95
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.27,
|
| 583 |
+
"learning_rate": 0.00018181818181818183,
|
| 584 |
+
"loss": 2.2299,
|
| 585 |
+
"step": 96
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.28,
|
| 589 |
+
"learning_rate": 0.0001816287878787879,
|
| 590 |
+
"loss": 2.2644,
|
| 591 |
+
"step": 97
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.28,
|
| 595 |
+
"learning_rate": 0.00018143939393939395,
|
| 596 |
+
"loss": 2.259,
|
| 597 |
+
"step": 98
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.28,
|
| 601 |
+
"learning_rate": 0.00018125000000000001,
|
| 602 |
+
"loss": 2.2567,
|
| 603 |
+
"step": 99
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.28,
|
| 607 |
+
"learning_rate": 0.00018106060606060606,
|
| 608 |
+
"loss": 2.2599,
|
| 609 |
+
"step": 100
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.29,
|
| 613 |
+
"learning_rate": 0.00018087121212121213,
|
| 614 |
+
"loss": 2.2091,
|
| 615 |
+
"step": 101
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 0.29,
|
| 619 |
+
"learning_rate": 0.0001806818181818182,
|
| 620 |
+
"loss": 2.2312,
|
| 621 |
+
"step": 102
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 0.29,
|
| 625 |
+
"learning_rate": 0.00018049242424242426,
|
| 626 |
+
"loss": 2.1869,
|
| 627 |
+
"step": 103
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.3,
|
| 631 |
+
"learning_rate": 0.0001803030303030303,
|
| 632 |
+
"loss": 2.2023,
|
| 633 |
+
"step": 104
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.3,
|
| 637 |
+
"learning_rate": 0.00018011363636363638,
|
| 638 |
+
"loss": 2.2132,
|
| 639 |
+
"step": 105
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.3,
|
| 643 |
+
"learning_rate": 0.00017992424242424244,
|
| 644 |
+
"loss": 2.2612,
|
| 645 |
+
"step": 106
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 0.3,
|
| 649 |
+
"learning_rate": 0.0001797348484848485,
|
| 650 |
+
"loss": 2.2109,
|
| 651 |
+
"step": 107
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 0.31,
|
| 655 |
+
"learning_rate": 0.00017954545454545456,
|
| 656 |
+
"loss": 2.215,
|
| 657 |
+
"step": 108
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.31,
|
| 661 |
+
"learning_rate": 0.0001793560606060606,
|
| 662 |
+
"loss": 2.2114,
|
| 663 |
+
"step": 109
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 0.31,
|
| 667 |
+
"learning_rate": 0.0001791666666666667,
|
| 668 |
+
"loss": 2.2203,
|
| 669 |
+
"step": 110
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.31,
|
| 673 |
+
"learning_rate": 0.00017897727272727274,
|
| 674 |
+
"loss": 2.2594,
|
| 675 |
+
"step": 111
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.32,
|
| 679 |
+
"learning_rate": 0.0001787878787878788,
|
| 680 |
+
"loss": 2.2001,
|
| 681 |
+
"step": 112
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.32,
|
| 685 |
+
"learning_rate": 0.00017859848484848485,
|
| 686 |
+
"loss": 2.2046,
|
| 687 |
+
"step": 113
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 0.32,
|
| 691 |
+
"learning_rate": 0.00017840909090909092,
|
| 692 |
+
"loss": 2.1907,
|
| 693 |
+
"step": 114
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 0.33,
|
| 697 |
+
"learning_rate": 0.00017821969696969699,
|
| 698 |
+
"loss": 2.2539,
|
| 699 |
+
"step": 115
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 0.33,
|
| 703 |
+
"learning_rate": 0.00017803030303030303,
|
| 704 |
+
"loss": 2.2335,
|
| 705 |
+
"step": 116
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 0.33,
|
| 709 |
+
"learning_rate": 0.0001778409090909091,
|
| 710 |
+
"loss": 2.2171,
|
| 711 |
+
"step": 117
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.33,
|
| 715 |
+
"learning_rate": 0.00017765151515151517,
|
| 716 |
+
"loss": 2.2278,
|
| 717 |
+
"step": 118
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.34,
|
| 721 |
+
"learning_rate": 0.00017746212121212123,
|
| 722 |
+
"loss": 2.231,
|
| 723 |
+
"step": 119
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.34,
|
| 727 |
+
"learning_rate": 0.00017727272727272728,
|
| 728 |
+
"loss": 2.2141,
|
| 729 |
+
"step": 120
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.34,
|
| 733 |
+
"learning_rate": 0.00017708333333333335,
|
| 734 |
+
"loss": 2.2432,
|
| 735 |
+
"step": 121
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 0.35,
|
| 739 |
+
"learning_rate": 0.00017689393939393942,
|
| 740 |
+
"loss": 2.2266,
|
| 741 |
+
"step": 122
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.35,
|
| 745 |
+
"learning_rate": 0.00017670454545454546,
|
| 746 |
+
"loss": 2.1929,
|
| 747 |
+
"step": 123
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.35,
|
| 751 |
+
"learning_rate": 0.00017651515151515153,
|
| 752 |
+
"loss": 2.2077,
|
| 753 |
+
"step": 124
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 0.35,
|
| 757 |
+
"learning_rate": 0.00017632575757575757,
|
| 758 |
+
"loss": 2.2133,
|
| 759 |
+
"step": 125
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.36,
|
| 763 |
+
"learning_rate": 0.00017613636363636366,
|
| 764 |
+
"loss": 2.2251,
|
| 765 |
+
"step": 126
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.36,
|
| 769 |
+
"learning_rate": 0.0001759469696969697,
|
| 770 |
+
"loss": 2.2265,
|
| 771 |
+
"step": 127
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 0.36,
|
| 775 |
+
"learning_rate": 0.00017575757575757578,
|
| 776 |
+
"loss": 2.2186,
|
| 777 |
+
"step": 128
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 0.37,
|
| 781 |
+
"learning_rate": 0.00017556818181818182,
|
| 782 |
+
"loss": 2.1925,
|
| 783 |
+
"step": 129
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 0.37,
|
| 787 |
+
"learning_rate": 0.0001753787878787879,
|
| 788 |
+
"loss": 2.1956,
|
| 789 |
+
"step": 130
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.37,
|
| 793 |
+
"learning_rate": 0.00017518939393939396,
|
| 794 |
+
"loss": 2.2459,
|
| 795 |
+
"step": 131
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 0.37,
|
| 799 |
+
"learning_rate": 0.000175,
|
| 800 |
+
"loss": 2.22,
|
| 801 |
+
"step": 132
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.38,
|
| 805 |
+
"learning_rate": 0.00017481060606060607,
|
| 806 |
+
"loss": 2.2143,
|
| 807 |
+
"step": 133
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.38,
|
| 811 |
+
"learning_rate": 0.0001746212121212121,
|
| 812 |
+
"loss": 2.2359,
|
| 813 |
+
"step": 134
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 0.38,
|
| 817 |
+
"learning_rate": 0.0001744318181818182,
|
| 818 |
+
"loss": 2.2058,
|
| 819 |
+
"step": 135
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 0.39,
|
| 823 |
+
"learning_rate": 0.00017424242424242425,
|
| 824 |
+
"loss": 2.2307,
|
| 825 |
+
"step": 136
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 0.39,
|
| 829 |
+
"learning_rate": 0.00017405303030303032,
|
| 830 |
+
"loss": 2.2062,
|
| 831 |
+
"step": 137
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.39,
|
| 835 |
+
"learning_rate": 0.00017386363636363636,
|
| 836 |
+
"loss": 2.1796,
|
| 837 |
+
"step": 138
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 0.39,
|
| 841 |
+
"learning_rate": 0.00017367424242424243,
|
| 842 |
+
"loss": 2.2054,
|
| 843 |
+
"step": 139
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.4,
|
| 847 |
+
"learning_rate": 0.0001734848484848485,
|
| 848 |
+
"loss": 2.1651,
|
| 849 |
+
"step": 140
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.4,
|
| 853 |
+
"learning_rate": 0.00017329545454545454,
|
| 854 |
+
"loss": 2.2159,
|
| 855 |
+
"step": 141
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 0.4,
|
| 859 |
+
"learning_rate": 0.0001731060606060606,
|
| 860 |
+
"loss": 2.1988,
|
| 861 |
+
"step": 142
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 0.41,
|
| 865 |
+
"learning_rate": 0.00017291666666666668,
|
| 866 |
+
"loss": 2.1676,
|
| 867 |
+
"step": 143
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 0.41,
|
| 871 |
+
"learning_rate": 0.00017272727272727275,
|
| 872 |
+
"loss": 2.1725,
|
| 873 |
+
"step": 144
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.41,
|
| 877 |
+
"learning_rate": 0.0001725378787878788,
|
| 878 |
+
"loss": 2.2205,
|
| 879 |
+
"step": 145
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 0.41,
|
| 883 |
+
"learning_rate": 0.00017234848484848486,
|
| 884 |
+
"loss": 2.1486,
|
| 885 |
+
"step": 146
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.42,
|
| 889 |
+
"learning_rate": 0.00017215909090909093,
|
| 890 |
+
"loss": 2.147,
|
| 891 |
+
"step": 147
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.42,
|
| 895 |
+
"learning_rate": 0.00017196969696969697,
|
| 896 |
+
"loss": 2.1651,
|
| 897 |
+
"step": 148
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 0.42,
|
| 901 |
+
"learning_rate": 0.00017178030303030304,
|
| 902 |
+
"loss": 2.1983,
|
| 903 |
+
"step": 149
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 0.43,
|
| 907 |
+
"learning_rate": 0.00017159090909090908,
|
| 908 |
+
"loss": 2.1778,
|
| 909 |
+
"step": 150
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 0.43,
|
| 913 |
+
"learning_rate": 0.00017140151515151518,
|
| 914 |
+
"loss": 2.1631,
|
| 915 |
+
"step": 151
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.43,
|
| 919 |
+
"learning_rate": 0.00017121212121212122,
|
| 920 |
+
"loss": 2.1442,
|
| 921 |
+
"step": 152
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 0.43,
|
| 925 |
+
"learning_rate": 0.0001710227272727273,
|
| 926 |
+
"loss": 2.1397,
|
| 927 |
+
"step": 153
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.44,
|
| 931 |
+
"learning_rate": 0.00017083333333333333,
|
| 932 |
+
"loss": 2.1697,
|
| 933 |
+
"step": 154
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.44,
|
| 937 |
+
"learning_rate": 0.0001706439393939394,
|
| 938 |
+
"loss": 2.1451,
|
| 939 |
+
"step": 155
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 0.44,
|
| 943 |
+
"learning_rate": 0.00017045454545454547,
|
| 944 |
+
"loss": 2.1789,
|
| 945 |
+
"step": 156
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 0.45,
|
| 949 |
+
"learning_rate": 0.0001702651515151515,
|
| 950 |
+
"loss": 2.1037,
|
| 951 |
+
"step": 157
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 0.45,
|
| 955 |
+
"learning_rate": 0.00017007575757575758,
|
| 956 |
+
"loss": 2.1698,
|
| 957 |
+
"step": 158
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.45,
|
| 961 |
+
"learning_rate": 0.00016988636363636365,
|
| 962 |
+
"loss": 2.1538,
|
| 963 |
+
"step": 159
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 0.45,
|
| 967 |
+
"learning_rate": 0.00016969696969696972,
|
| 968 |
+
"loss": 2.2015,
|
| 969 |
+
"step": 160
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.46,
|
| 973 |
+
"learning_rate": 0.00016950757575757576,
|
| 974 |
+
"loss": 2.179,
|
| 975 |
+
"step": 161
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.46,
|
| 979 |
+
"learning_rate": 0.00016931818181818183,
|
| 980 |
+
"loss": 2.1766,
|
| 981 |
+
"step": 162
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 0.46,
|
| 985 |
+
"learning_rate": 0.0001691287878787879,
|
| 986 |
+
"loss": 2.1646,
|
| 987 |
+
"step": 163
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 0.47,
|
| 991 |
+
"learning_rate": 0.00016893939393939394,
|
| 992 |
+
"loss": 2.1694,
|
| 993 |
+
"step": 164
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 0.47,
|
| 997 |
+
"learning_rate": 0.00016875,
|
| 998 |
+
"loss": 2.1562,
|
| 999 |
+
"step": 165
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.47,
|
| 1003 |
+
"learning_rate": 0.00016856060606060605,
|
| 1004 |
+
"loss": 2.1551,
|
| 1005 |
+
"step": 166
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 0.47,
|
| 1009 |
+
"learning_rate": 0.00016837121212121212,
|
| 1010 |
+
"loss": 2.1652,
|
| 1011 |
+
"step": 167
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.48,
|
| 1015 |
+
"learning_rate": 0.0001681818181818182,
|
| 1016 |
+
"loss": 2.1594,
|
| 1017 |
+
"step": 168
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.48,
|
| 1021 |
+
"learning_rate": 0.00016799242424242426,
|
| 1022 |
+
"loss": 2.1674,
|
| 1023 |
+
"step": 169
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 0.48,
|
| 1027 |
+
"learning_rate": 0.0001678030303030303,
|
| 1028 |
+
"loss": 2.1378,
|
| 1029 |
+
"step": 170
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 0.49,
|
| 1033 |
+
"learning_rate": 0.00016761363636363637,
|
| 1034 |
+
"loss": 2.1447,
|
| 1035 |
+
"step": 171
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 0.49,
|
| 1039 |
+
"learning_rate": 0.00016742424242424244,
|
| 1040 |
+
"loss": 2.1451,
|
| 1041 |
+
"step": 172
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.49,
|
| 1045 |
+
"learning_rate": 0.00016723484848484848,
|
| 1046 |
+
"loss": 2.1336,
|
| 1047 |
+
"step": 173
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 0.49,
|
| 1051 |
+
"learning_rate": 0.00016704545454545455,
|
| 1052 |
+
"loss": 2.1231,
|
| 1053 |
+
"step": 174
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.5,
|
| 1057 |
+
"learning_rate": 0.0001668560606060606,
|
| 1058 |
+
"loss": 2.1143,
|
| 1059 |
+
"step": 175
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.5,
|
| 1063 |
+
"learning_rate": 0.0001666666666666667,
|
| 1064 |
+
"loss": 2.1316,
|
| 1065 |
+
"step": 176
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 0.5,
|
| 1069 |
+
"learning_rate": 0.00016647727272727273,
|
| 1070 |
+
"loss": 2.1281,
|
| 1071 |
+
"step": 177
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 0.5,
|
| 1075 |
+
"learning_rate": 0.0001662878787878788,
|
| 1076 |
+
"loss": 2.136,
|
| 1077 |
+
"step": 178
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 0.51,
|
| 1081 |
+
"learning_rate": 0.00016609848484848484,
|
| 1082 |
+
"loss": 2.1279,
|
| 1083 |
+
"step": 179
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 0.51,
|
| 1087 |
+
"learning_rate": 0.00016590909090909094,
|
| 1088 |
+
"loss": 2.1421,
|
| 1089 |
+
"step": 180
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 0.51,
|
| 1093 |
+
"learning_rate": 0.00016571969696969698,
|
| 1094 |
+
"loss": 2.1541,
|
| 1095 |
+
"step": 181
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.52,
|
| 1099 |
+
"learning_rate": 0.00016553030303030305,
|
| 1100 |
+
"loss": 2.1293,
|
| 1101 |
+
"step": 182
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.52,
|
| 1105 |
+
"learning_rate": 0.0001653409090909091,
|
| 1106 |
+
"loss": 2.1294,
|
| 1107 |
+
"step": 183
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 0.52,
|
| 1111 |
+
"learning_rate": 0.00016515151515151516,
|
| 1112 |
+
"loss": 2.1459,
|
| 1113 |
+
"step": 184
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 0.52,
|
| 1117 |
+
"learning_rate": 0.00016496212121212123,
|
| 1118 |
+
"loss": 2.1113,
|
| 1119 |
+
"step": 185
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.53,
|
| 1123 |
+
"learning_rate": 0.00016477272727272727,
|
| 1124 |
+
"loss": 2.1394,
|
| 1125 |
+
"step": 186
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 0.53,
|
| 1129 |
+
"learning_rate": 0.00016458333333333334,
|
| 1130 |
+
"loss": 2.1321,
|
| 1131 |
+
"step": 187
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 0.53,
|
| 1135 |
+
"learning_rate": 0.0001643939393939394,
|
| 1136 |
+
"loss": 2.148,
|
| 1137 |
+
"step": 188
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.54,
|
| 1141 |
+
"learning_rate": 0.00016420454545454548,
|
| 1142 |
+
"loss": 2.1631,
|
| 1143 |
+
"step": 189
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.54,
|
| 1147 |
+
"learning_rate": 0.00016401515151515152,
|
| 1148 |
+
"loss": 2.1276,
|
| 1149 |
+
"step": 190
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 0.54,
|
| 1153 |
+
"learning_rate": 0.0001638257575757576,
|
| 1154 |
+
"loss": 2.0706,
|
| 1155 |
+
"step": 191
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 0.54,
|
| 1159 |
+
"learning_rate": 0.00016363636363636366,
|
| 1160 |
+
"loss": 2.127,
|
| 1161 |
+
"step": 192
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.55,
|
| 1165 |
+
"learning_rate": 0.0001634469696969697,
|
| 1166 |
+
"loss": 2.1449,
|
| 1167 |
+
"step": 193
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 0.55,
|
| 1171 |
+
"learning_rate": 0.00016325757575757577,
|
| 1172 |
+
"loss": 2.1204,
|
| 1173 |
+
"step": 194
|
| 1174 |
+
},
|
| 1175 |
+
{
|
| 1176 |
+
"epoch": 0.55,
|
| 1177 |
+
"learning_rate": 0.0001630681818181818,
|
| 1178 |
+
"loss": 2.0904,
|
| 1179 |
+
"step": 195
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.56,
|
| 1183 |
+
"learning_rate": 0.0001628787878787879,
|
| 1184 |
+
"loss": 2.1129,
|
| 1185 |
+
"step": 196
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.56,
|
| 1189 |
+
"learning_rate": 0.00016268939393939395,
|
| 1190 |
+
"loss": 2.1036,
|
| 1191 |
+
"step": 197
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 0.56,
|
| 1195 |
+
"learning_rate": 0.00016250000000000002,
|
| 1196 |
+
"loss": 2.1509,
|
| 1197 |
+
"step": 198
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 0.56,
|
| 1201 |
+
"learning_rate": 0.00016231060606060606,
|
| 1202 |
+
"loss": 2.1239,
|
| 1203 |
+
"step": 199
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.57,
|
| 1207 |
+
"learning_rate": 0.00016212121212121213,
|
| 1208 |
+
"loss": 2.145,
|
| 1209 |
+
"step": 200
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 0.57,
|
| 1213 |
+
"learning_rate": 0.0001619318181818182,
|
| 1214 |
+
"loss": 2.1221,
|
| 1215 |
+
"step": 201
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 0.57,
|
| 1219 |
+
"learning_rate": 0.00016174242424242424,
|
| 1220 |
+
"loss": 2.1181,
|
| 1221 |
+
"step": 202
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 0.58,
|
| 1225 |
+
"learning_rate": 0.0001615530303030303,
|
| 1226 |
+
"loss": 2.1306,
|
| 1227 |
+
"step": 203
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.58,
|
| 1231 |
+
"learning_rate": 0.00016136363636363635,
|
| 1232 |
+
"loss": 2.0199,
|
| 1233 |
+
"step": 204
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 0.58,
|
| 1237 |
+
"learning_rate": 0.00016117424242424245,
|
| 1238 |
+
"loss": 2.1178,
|
| 1239 |
+
"step": 205
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 0.58,
|
| 1243 |
+
"learning_rate": 0.0001609848484848485,
|
| 1244 |
+
"loss": 2.1584,
|
| 1245 |
+
"step": 206
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.59,
|
| 1249 |
+
"learning_rate": 0.00016079545454545456,
|
| 1250 |
+
"loss": 2.0872,
|
| 1251 |
+
"step": 207
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 0.59,
|
| 1255 |
+
"learning_rate": 0.0001606060606060606,
|
| 1256 |
+
"loss": 2.1033,
|
| 1257 |
+
"step": 208
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 0.59,
|
| 1261 |
+
"learning_rate": 0.00016041666666666667,
|
| 1262 |
+
"loss": 2.1381,
|
| 1263 |
+
"step": 209
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.6,
|
| 1267 |
+
"learning_rate": 0.00016022727272727274,
|
| 1268 |
+
"loss": 2.1127,
|
| 1269 |
+
"step": 210
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.6,
|
| 1273 |
+
"learning_rate": 0.00016003787878787878,
|
| 1274 |
+
"loss": 2.1077,
|
| 1275 |
+
"step": 211
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 0.6,
|
| 1279 |
+
"learning_rate": 0.00015984848484848485,
|
| 1280 |
+
"loss": 2.0984,
|
| 1281 |
+
"step": 212
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"epoch": 0.6,
|
| 1285 |
+
"learning_rate": 0.00015965909090909092,
|
| 1286 |
+
"loss": 2.0994,
|
| 1287 |
+
"step": 213
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.61,
|
| 1291 |
+
"learning_rate": 0.000159469696969697,
|
| 1292 |
+
"loss": 2.096,
|
| 1293 |
+
"step": 214
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 0.61,
|
| 1297 |
+
"learning_rate": 0.00015928030303030303,
|
| 1298 |
+
"loss": 2.0909,
|
| 1299 |
+
"step": 215
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 0.61,
|
| 1303 |
+
"learning_rate": 0.0001590909090909091,
|
| 1304 |
+
"loss": 2.118,
|
| 1305 |
+
"step": 216
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.62,
|
| 1309 |
+
"learning_rate": 0.00015890151515151517,
|
| 1310 |
+
"loss": 2.0783,
|
| 1311 |
+
"step": 217
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.62,
|
| 1315 |
+
"learning_rate": 0.0001587121212121212,
|
| 1316 |
+
"loss": 2.0876,
|
| 1317 |
+
"step": 218
|
| 1318 |
+
},
|
| 1319 |
+
{
|
| 1320 |
+
"epoch": 0.62,
|
| 1321 |
+
"learning_rate": 0.00015852272727272728,
|
| 1322 |
+
"loss": 2.0581,
|
| 1323 |
+
"step": 219
|
| 1324 |
+
},
|
| 1325 |
+
{
|
| 1326 |
+
"epoch": 0.62,
|
| 1327 |
+
"learning_rate": 0.00015833333333333332,
|
| 1328 |
+
"loss": 2.0548,
|
| 1329 |
+
"step": 220
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.63,
|
| 1333 |
+
"learning_rate": 0.00015814393939393942,
|
| 1334 |
+
"loss": 2.0595,
|
| 1335 |
+
"step": 221
|
| 1336 |
+
},
|
| 1337 |
+
{
|
| 1338 |
+
"epoch": 0.63,
|
| 1339 |
+
"learning_rate": 0.00015795454545454546,
|
| 1340 |
+
"loss": 2.0719,
|
| 1341 |
+
"step": 222
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 0.63,
|
| 1345 |
+
"learning_rate": 0.00015776515151515153,
|
| 1346 |
+
"loss": 2.0903,
|
| 1347 |
+
"step": 223
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 0.64,
|
| 1351 |
+
"learning_rate": 0.00015757575757575757,
|
| 1352 |
+
"loss": 2.0941,
|
| 1353 |
+
"step": 224
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.64,
|
| 1357 |
+
"learning_rate": 0.00015738636363636364,
|
| 1358 |
+
"loss": 2.0926,
|
| 1359 |
+
"step": 225
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 0.64,
|
| 1363 |
+
"learning_rate": 0.0001571969696969697,
|
| 1364 |
+
"loss": 2.0816,
|
| 1365 |
+
"step": 226
|
| 1366 |
+
},
|
| 1367 |
+
{
|
| 1368 |
+
"epoch": 0.64,
|
| 1369 |
+
"learning_rate": 0.00015700757575757575,
|
| 1370 |
+
"loss": 2.0894,
|
| 1371 |
+
"step": 227
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.65,
|
| 1375 |
+
"learning_rate": 0.00015681818181818182,
|
| 1376 |
+
"loss": 2.0798,
|
| 1377 |
+
"step": 228
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 0.65,
|
| 1381 |
+
"learning_rate": 0.0001566287878787879,
|
| 1382 |
+
"loss": 2.0672,
|
| 1383 |
+
"step": 229
|
| 1384 |
+
},
|
| 1385 |
+
{
|
| 1386 |
+
"epoch": 0.65,
|
| 1387 |
+
"learning_rate": 0.00015643939393939396,
|
| 1388 |
+
"loss": 2.0787,
|
| 1389 |
+
"step": 230
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.66,
|
| 1393 |
+
"learning_rate": 0.00015625,
|
| 1394 |
+
"loss": 2.0611,
|
| 1395 |
+
"step": 231
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.66,
|
| 1399 |
+
"learning_rate": 0.00015606060606060607,
|
| 1400 |
+
"loss": 2.0805,
|
| 1401 |
+
"step": 232
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 0.66,
|
| 1405 |
+
"learning_rate": 0.00015587121212121211,
|
| 1406 |
+
"loss": 2.053,
|
| 1407 |
+
"step": 233
|
| 1408 |
+
},
|
| 1409 |
+
{
|
| 1410 |
+
"epoch": 0.66,
|
| 1411 |
+
"learning_rate": 0.00015568181818181818,
|
| 1412 |
+
"loss": 2.0575,
|
| 1413 |
+
"step": 234
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.67,
|
| 1417 |
+
"learning_rate": 0.00015549242424242425,
|
| 1418 |
+
"loss": 2.0459,
|
| 1419 |
+
"step": 235
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"epoch": 0.67,
|
| 1423 |
+
"learning_rate": 0.0001553030303030303,
|
| 1424 |
+
"loss": 2.0635,
|
| 1425 |
+
"step": 236
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"epoch": 0.67,
|
| 1429 |
+
"learning_rate": 0.00015511363636363636,
|
| 1430 |
+
"loss": 2.0335,
|
| 1431 |
+
"step": 237
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 0.68,
|
| 1435 |
+
"learning_rate": 0.00015492424242424243,
|
| 1436 |
+
"loss": 2.0681,
|
| 1437 |
+
"step": 238
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.68,
|
| 1441 |
+
"learning_rate": 0.0001547348484848485,
|
| 1442 |
+
"loss": 2.0748,
|
| 1443 |
+
"step": 239
|
| 1444 |
+
},
|
| 1445 |
+
{
|
| 1446 |
+
"epoch": 0.68,
|
| 1447 |
+
"learning_rate": 0.00015454545454545454,
|
| 1448 |
+
"loss": 2.1091,
|
| 1449 |
+
"step": 240
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 0.68,
|
| 1453 |
+
"learning_rate": 0.0001543560606060606,
|
| 1454 |
+
"loss": 2.0732,
|
| 1455 |
+
"step": 241
|
| 1456 |
+
},
|
| 1457 |
+
{
|
| 1458 |
+
"epoch": 0.69,
|
| 1459 |
+
"learning_rate": 0.00015416666666666668,
|
| 1460 |
+
"loss": 2.0746,
|
| 1461 |
+
"step": 242
|
| 1462 |
+
},
|
| 1463 |
+
{
|
| 1464 |
+
"epoch": 0.69,
|
| 1465 |
+
"learning_rate": 0.00015397727272727272,
|
| 1466 |
+
"loss": 2.0306,
|
| 1467 |
+
"step": 243
|
| 1468 |
+
},
|
| 1469 |
+
{
|
| 1470 |
+
"epoch": 0.69,
|
| 1471 |
+
"learning_rate": 0.0001537878787878788,
|
| 1472 |
+
"loss": 2.0864,
|
| 1473 |
+
"step": 244
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 0.7,
|
| 1477 |
+
"learning_rate": 0.00015359848484848484,
|
| 1478 |
+
"loss": 2.0664,
|
| 1479 |
+
"step": 245
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.7,
|
| 1483 |
+
"learning_rate": 0.00015340909090909093,
|
| 1484 |
+
"loss": 2.0801,
|
| 1485 |
+
"step": 246
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"epoch": 0.7,
|
| 1489 |
+
"learning_rate": 0.00015321969696969697,
|
| 1490 |
+
"loss": 2.0799,
|
| 1491 |
+
"step": 247
|
| 1492 |
+
},
|
| 1493 |
+
{
|
| 1494 |
+
"epoch": 0.7,
|
| 1495 |
+
"learning_rate": 0.00015303030303030304,
|
| 1496 |
+
"loss": 2.0621,
|
| 1497 |
+
"step": 248
|
| 1498 |
+
},
|
| 1499 |
+
{
|
| 1500 |
+
"epoch": 0.71,
|
| 1501 |
+
"learning_rate": 0.00015284090909090909,
|
| 1502 |
+
"loss": 2.0687,
|
| 1503 |
+
"step": 249
|
| 1504 |
+
},
|
| 1505 |
+
{
|
| 1506 |
+
"epoch": 0.71,
|
| 1507 |
+
"learning_rate": 0.00015265151515151515,
|
| 1508 |
+
"loss": 2.018,
|
| 1509 |
+
"step": 250
|
| 1510 |
+
},
|
| 1511 |
+
{
|
| 1512 |
+
"epoch": 0.71,
|
| 1513 |
+
"learning_rate": 0.00015246212121212122,
|
| 1514 |
+
"loss": 2.0256,
|
| 1515 |
+
"step": 251
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 0.71,
|
| 1519 |
+
"learning_rate": 0.00015227272727272727,
|
| 1520 |
+
"loss": 2.0736,
|
| 1521 |
+
"step": 252
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.72,
|
| 1525 |
+
"learning_rate": 0.00015208333333333333,
|
| 1526 |
+
"loss": 2.0609,
|
| 1527 |
+
"step": 253
|
| 1528 |
+
},
|
| 1529 |
+
{
|
| 1530 |
+
"epoch": 0.72,
|
| 1531 |
+
"learning_rate": 0.0001518939393939394,
|
| 1532 |
+
"loss": 2.0539,
|
| 1533 |
+
"step": 254
|
| 1534 |
+
},
|
| 1535 |
+
{
|
| 1536 |
+
"epoch": 0.72,
|
| 1537 |
+
"learning_rate": 0.00015170454545454547,
|
| 1538 |
+
"loss": 2.0282,
|
| 1539 |
+
"step": 255
|
| 1540 |
+
},
|
| 1541 |
+
{
|
| 1542 |
+
"epoch": 0.73,
|
| 1543 |
+
"learning_rate": 0.00015151515151515152,
|
| 1544 |
+
"loss": 2.0417,
|
| 1545 |
+
"step": 256
|
| 1546 |
+
},
|
| 1547 |
+
{
|
| 1548 |
+
"epoch": 0.73,
|
| 1549 |
+
"learning_rate": 0.00015132575757575758,
|
| 1550 |
+
"loss": 2.0333,
|
| 1551 |
+
"step": 257
|
| 1552 |
+
},
|
| 1553 |
+
{
|
| 1554 |
+
"epoch": 0.73,
|
| 1555 |
+
"learning_rate": 0.00015113636363636365,
|
| 1556 |
+
"loss": 2.0428,
|
| 1557 |
+
"step": 258
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 0.73,
|
| 1561 |
+
"learning_rate": 0.00015094696969696972,
|
| 1562 |
+
"loss": 2.045,
|
| 1563 |
+
"step": 259
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 0.74,
|
| 1567 |
+
"learning_rate": 0.00015075757575757576,
|
| 1568 |
+
"loss": 2.0463,
|
| 1569 |
+
"step": 260
|
| 1570 |
+
},
|
| 1571 |
+
{
|
| 1572 |
+
"epoch": 0.74,
|
| 1573 |
+
"learning_rate": 0.0001505681818181818,
|
| 1574 |
+
"loss": 2.0539,
|
| 1575 |
+
"step": 261
|
| 1576 |
+
},
|
| 1577 |
+
{
|
| 1578 |
+
"epoch": 0.74,
|
| 1579 |
+
"learning_rate": 0.0001503787878787879,
|
| 1580 |
+
"loss": 2.0184,
|
| 1581 |
+
"step": 262
|
| 1582 |
+
},
|
| 1583 |
+
{
|
| 1584 |
+
"epoch": 0.75,
|
| 1585 |
+
"learning_rate": 0.00015018939393939394,
|
| 1586 |
+
"loss": 2.0858,
|
| 1587 |
+
"step": 263
|
| 1588 |
+
},
|
| 1589 |
+
{
|
| 1590 |
+
"epoch": 0.75,
|
| 1591 |
+
"learning_rate": 0.00015000000000000001,
|
| 1592 |
+
"loss": 2.0239,
|
| 1593 |
+
"step": 264
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 0.75,
|
| 1597 |
+
"learning_rate": 0.00014981060606060606,
|
| 1598 |
+
"loss": 2.0425,
|
| 1599 |
+
"step": 265
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 0.75,
|
| 1603 |
+
"learning_rate": 0.00014962121212121213,
|
| 1604 |
+
"loss": 2.0263,
|
| 1605 |
+
"step": 266
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 0.76,
|
| 1609 |
+
"learning_rate": 0.0001494318181818182,
|
| 1610 |
+
"loss": 2.042,
|
| 1611 |
+
"step": 267
|
| 1612 |
+
},
|
| 1613 |
+
{
|
| 1614 |
+
"epoch": 0.76,
|
| 1615 |
+
"learning_rate": 0.00014924242424242426,
|
| 1616 |
+
"loss": 2.026,
|
| 1617 |
+
"step": 268
|
| 1618 |
+
},
|
| 1619 |
+
{
|
| 1620 |
+
"epoch": 0.76,
|
| 1621 |
+
"learning_rate": 0.0001490530303030303,
|
| 1622 |
+
"loss": 2.0411,
|
| 1623 |
+
"step": 269
|
| 1624 |
+
},
|
| 1625 |
+
{
|
| 1626 |
+
"epoch": 0.77,
|
| 1627 |
+
"learning_rate": 0.00014886363636363635,
|
| 1628 |
+
"loss": 2.028,
|
| 1629 |
+
"step": 270
|
| 1630 |
+
},
|
| 1631 |
+
{
|
| 1632 |
+
"epoch": 0.77,
|
| 1633 |
+
"learning_rate": 0.00014867424242424244,
|
| 1634 |
+
"loss": 2.0172,
|
| 1635 |
+
"step": 271
|
| 1636 |
+
},
|
| 1637 |
+
{
|
| 1638 |
+
"epoch": 0.77,
|
| 1639 |
+
"learning_rate": 0.00014848484848484849,
|
| 1640 |
+
"loss": 2.0196,
|
| 1641 |
+
"step": 272
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 0.77,
|
| 1645 |
+
"learning_rate": 0.00014829545454545455,
|
| 1646 |
+
"loss": 2.0142,
|
| 1647 |
+
"step": 273
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 0.78,
|
| 1651 |
+
"learning_rate": 0.0001481060606060606,
|
| 1652 |
+
"loss": 2.0265,
|
| 1653 |
+
"step": 274
|
| 1654 |
+
},
|
| 1655 |
+
{
|
| 1656 |
+
"epoch": 0.78,
|
| 1657 |
+
"learning_rate": 0.0001479166666666667,
|
| 1658 |
+
"loss": 2.0353,
|
| 1659 |
+
"step": 275
|
| 1660 |
+
},
|
| 1661 |
+
{
|
| 1662 |
+
"epoch": 0.78,
|
| 1663 |
+
"learning_rate": 0.00014772727272727274,
|
| 1664 |
+
"loss": 2.0327,
|
| 1665 |
+
"step": 276
|
| 1666 |
+
},
|
| 1667 |
+
{
|
| 1668 |
+
"epoch": 0.79,
|
| 1669 |
+
"learning_rate": 0.0001475378787878788,
|
| 1670 |
+
"loss": 2.0188,
|
| 1671 |
+
"step": 277
|
| 1672 |
+
},
|
| 1673 |
+
{
|
| 1674 |
+
"epoch": 0.79,
|
| 1675 |
+
"learning_rate": 0.00014734848484848485,
|
| 1676 |
+
"loss": 1.9987,
|
| 1677 |
+
"step": 278
|
| 1678 |
+
},
|
| 1679 |
+
{
|
| 1680 |
+
"epoch": 0.79,
|
| 1681 |
+
"learning_rate": 0.00014715909090909092,
|
| 1682 |
+
"loss": 2.0141,
|
| 1683 |
+
"step": 279
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 0.79,
|
| 1687 |
+
"learning_rate": 0.00014696969696969698,
|
| 1688 |
+
"loss": 2.0403,
|
| 1689 |
+
"step": 280
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 0.8,
|
| 1693 |
+
"learning_rate": 0.00014678030303030303,
|
| 1694 |
+
"loss": 1.9977,
|
| 1695 |
+
"step": 281
|
| 1696 |
+
},
|
| 1697 |
+
{
|
| 1698 |
+
"epoch": 0.8,
|
| 1699 |
+
"learning_rate": 0.0001465909090909091,
|
| 1700 |
+
"loss": 1.9674,
|
| 1701 |
+
"step": 282
|
| 1702 |
+
},
|
| 1703 |
+
{
|
| 1704 |
+
"epoch": 0.8,
|
| 1705 |
+
"learning_rate": 0.00014640151515151517,
|
| 1706 |
+
"loss": 1.9984,
|
| 1707 |
+
"step": 283
|
| 1708 |
+
},
|
| 1709 |
+
{
|
| 1710 |
+
"epoch": 0.81,
|
| 1711 |
+
"learning_rate": 0.00014621212121212123,
|
| 1712 |
+
"loss": 1.9796,
|
| 1713 |
+
"step": 284
|
| 1714 |
+
},
|
| 1715 |
+
{
|
| 1716 |
+
"epoch": 0.81,
|
| 1717 |
+
"learning_rate": 0.00014602272727272728,
|
| 1718 |
+
"loss": 2.0139,
|
| 1719 |
+
"step": 285
|
| 1720 |
+
},
|
| 1721 |
+
{
|
| 1722 |
+
"epoch": 0.81,
|
| 1723 |
+
"learning_rate": 0.00014583333333333335,
|
| 1724 |
+
"loss": 1.9866,
|
| 1725 |
+
"step": 286
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 0.81,
|
| 1729 |
+
"learning_rate": 0.00014564393939393941,
|
| 1730 |
+
"loss": 2.0208,
|
| 1731 |
+
"step": 287
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 0.82,
|
| 1735 |
+
"learning_rate": 0.00014545454545454546,
|
| 1736 |
+
"loss": 1.9844,
|
| 1737 |
+
"step": 288
|
| 1738 |
+
},
|
| 1739 |
+
{
|
| 1740 |
+
"epoch": 0.82,
|
| 1741 |
+
"learning_rate": 0.00014526515151515153,
|
| 1742 |
+
"loss": 2.0082,
|
| 1743 |
+
"step": 289
|
| 1744 |
+
},
|
| 1745 |
+
{
|
| 1746 |
+
"epoch": 0.82,
|
| 1747 |
+
"learning_rate": 0.00014507575757575757,
|
| 1748 |
+
"loss": 1.984,
|
| 1749 |
+
"step": 290
|
| 1750 |
+
},
|
| 1751 |
+
{
|
| 1752 |
+
"epoch": 0.83,
|
| 1753 |
+
"learning_rate": 0.00014488636363636366,
|
| 1754 |
+
"loss": 2.0015,
|
| 1755 |
+
"step": 291
|
| 1756 |
+
},
|
| 1757 |
+
{
|
| 1758 |
+
"epoch": 0.83,
|
| 1759 |
+
"learning_rate": 0.0001446969696969697,
|
| 1760 |
+
"loss": 2.0209,
|
| 1761 |
+
"step": 292
|
| 1762 |
+
},
|
| 1763 |
+
{
|
| 1764 |
+
"epoch": 0.83,
|
| 1765 |
+
"learning_rate": 0.00014450757575757578,
|
| 1766 |
+
"loss": 1.9728,
|
| 1767 |
+
"step": 293
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 0.83,
|
| 1771 |
+
"learning_rate": 0.00014431818181818182,
|
| 1772 |
+
"loss": 2.0032,
|
| 1773 |
+
"step": 294
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 0.84,
|
| 1777 |
+
"learning_rate": 0.00014412878787878789,
|
| 1778 |
+
"loss": 1.9641,
|
| 1779 |
+
"step": 295
|
| 1780 |
+
},
|
| 1781 |
+
{
|
| 1782 |
+
"epoch": 0.84,
|
| 1783 |
+
"learning_rate": 0.00014393939393939396,
|
| 1784 |
+
"loss": 1.9945,
|
| 1785 |
+
"step": 296
|
| 1786 |
+
},
|
| 1787 |
+
{
|
| 1788 |
+
"epoch": 0.84,
|
| 1789 |
+
"learning_rate": 0.00014375,
|
| 1790 |
+
"loss": 1.9658,
|
| 1791 |
+
"step": 297
|
| 1792 |
+
},
|
| 1793 |
+
{
|
| 1794 |
+
"epoch": 0.85,
|
| 1795 |
+
"learning_rate": 0.00014356060606060607,
|
| 1796 |
+
"loss": 1.9907,
|
| 1797 |
+
"step": 298
|
| 1798 |
+
},
|
| 1799 |
+
{
|
| 1800 |
+
"epoch": 0.85,
|
| 1801 |
+
"learning_rate": 0.0001433712121212121,
|
| 1802 |
+
"loss": 1.9935,
|
| 1803 |
+
"step": 299
|
| 1804 |
+
},
|
| 1805 |
+
{
|
| 1806 |
+
"epoch": 0.85,
|
| 1807 |
+
"learning_rate": 0.0001431818181818182,
|
| 1808 |
+
"loss": 1.9897,
|
| 1809 |
+
"step": 300
|
| 1810 |
+
}
|
| 1811 |
+
],
|
| 1812 |
+
"logging_steps": 1,
|
| 1813 |
+
"max_steps": 1056,
|
| 1814 |
+
"num_train_epochs": 3,
|
| 1815 |
+
"save_steps": 100,
|
| 1816 |
+
"total_flos": 7.603665299822592e+17,
|
| 1817 |
+
"trial_name": null,
|
| 1818 |
+
"trial_params": null
|
| 1819 |
+
}
|
checkpoint-300/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:50303c7f1586feb001f01b7e968e567295f501ef6c6407e28250c458696a43af
|
| 3 |
+
size 4155
|
checkpoint-400/README.md
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
---
|
| 4 |
+
## Training procedure
|
| 5 |
+
|
| 6 |
+
|
| 7 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 8 |
+
- quant_method: bitsandbytes
|
| 9 |
+
- load_in_8bit: True
|
| 10 |
+
- load_in_4bit: False
|
| 11 |
+
- llm_int8_threshold: 6.0
|
| 12 |
+
- llm_int8_skip_modules: None
|
| 13 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 14 |
+
- llm_int8_has_fp16_weight: False
|
| 15 |
+
- bnb_4bit_quant_type: fp4
|
| 16 |
+
- bnb_4bit_use_double_quant: False
|
| 17 |
+
- bnb_4bit_compute_dtype: float32
|
| 18 |
+
|
| 19 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 20 |
+
- quant_method: bitsandbytes
|
| 21 |
+
- load_in_8bit: True
|
| 22 |
+
- load_in_4bit: False
|
| 23 |
+
- llm_int8_threshold: 6.0
|
| 24 |
+
- llm_int8_skip_modules: None
|
| 25 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 26 |
+
- llm_int8_has_fp16_weight: False
|
| 27 |
+
- bnb_4bit_quant_type: fp4
|
| 28 |
+
- bnb_4bit_use_double_quant: False
|
| 29 |
+
- bnb_4bit_compute_dtype: float32
|
| 30 |
+
### Framework versions
|
| 31 |
+
|
| 32 |
+
- PEFT 0.6.0.dev0
|
| 33 |
+
|
| 34 |
+
- PEFT 0.6.0.dev0
|
checkpoint-400/adapter_config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "bigscience/bloomz-3b",
|
| 4 |
+
"bias": "none",
|
| 5 |
+
"fan_in_fan_out": false,
|
| 6 |
+
"inference_mode": true,
|
| 7 |
+
"init_lora_weights": true,
|
| 8 |
+
"layers_pattern": null,
|
| 9 |
+
"layers_to_transform": null,
|
| 10 |
+
"lora_alpha": 16,
|
| 11 |
+
"lora_dropout": 0.0,
|
| 12 |
+
"modules_to_save": null,
|
| 13 |
+
"peft_type": "LORA",
|
| 14 |
+
"r": 8,
|
| 15 |
+
"revision": null,
|
| 16 |
+
"target_modules": [
|
| 17 |
+
"dense_4h_to_h",
|
| 18 |
+
"dense",
|
| 19 |
+
"dense_h_to_4h",
|
| 20 |
+
"query_key_value"
|
| 21 |
+
],
|
| 22 |
+
"task_type": "CAUSAL_LM"
|
| 23 |
+
}
|
checkpoint-400/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:51647d6c0564017d9193f228b6d8bc208d4d6a55f7e4bd08dc9d1ce64d9903c8
|
| 3 |
+
size 39409357
|
checkpoint-400/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2d805d92e1fdea1995c4b0f014cc6ddb5ca33b3be6d4ed4e3c1caf4f79c61bad
|
| 3 |
+
size 78844421
|