Training in progress, step 2, checkpoint

last-checkpoint/README.md

@@ -4,6 +4,42 @@ library_name: peft
 ## Training procedure
 
 
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: float16
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: float16
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: float16
+
 The following `bitsandbytes` quantization config was used during training:
 - quant_method: bitsandbytes
 - load_in_8bit: False
@@ -17,5 +53,8 @@ The following `bitsandbytes` quantization config was used during training:
 - bnb_4bit_compute_dtype: float16
 ### Framework versions
 
+- PEFT 0.5.0
+- PEFT 0.5.0
+- PEFT 0.5.0
 
 - PEFT 0.5.0

last-checkpoint/adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36c36f565cee153168e16fab891a20aef7b385171ac78c5722366eb330db1e78
+oid sha256:894902fc83ce981ce902d325f92c66c93f068f601ec88ba81ca2818c4f4ea82c
 size 40137613

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3b3dab902f654a25e94e3ae343233a6f70542e70de8175dda45b60e2be64cde
+oid sha256:f41804539ce4dbc951729526a56d2696d7d2042884d136c4e448563b20767c9c
 size 40036040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04c3113c32b4000e515b8d0f088a79febc7bae6b99372543b69f4d5d6af8d9ee
+oid sha256:b5f1842a91acf8bc3388db088cf49775e50c5c216645f7d35ef69df393c50c91
 size 20523679

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9f2d7e8bf2ed7515ccab34b515d3863906e4d6e9f597722937aaa40e93ad4ba
+oid sha256:18aff74b667dba3ffb21fc4e30c6282bcfa51148f5f176894821bf027611df3f
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8078c9f184228e33330b036411337dd5e5bec4381d5a61fcfdc2d0a6a6021bc
+oid sha256:359ea6d423af08e8e9047ba958e9726b4e403615b5c587f71a606d0689d2621a
 size 627

last-checkpoint/trainer_state.json

@@ -1,123 +1,32 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.0,
-  "eval_steps": 25,
-  "global_step": 200,
+  "epoch": 0.025,
+  "eval_steps": 2,
+  "global_step": 2,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.25,
-      "learning_rate": 0.0001,
-      "loss": 1.6153,
-      "step": 25
+      "epoch": 0.03,
+      "learning_rate": 0.001,
+      "loss": 3.1823,
+      "step": 2
     },
     {
-      "epoch": 0.25,
-      "eval_runtime": 216.6929,
-      "eval_samples_per_second": 1.846,
-      "eval_steps_per_second": 0.157,
-      "step": 25
-    },
-    {
-      "epoch": 0.5,
-      "learning_rate": 0.0001,
-      "loss": 0.6312,
-      "step": 50
-    },
-    {
-      "epoch": 0.5,
-      "eval_runtime": 217.0379,
-      "eval_samples_per_second": 1.843,
-      "eval_steps_per_second": 0.157,
-      "step": 50
-    },
-    {
-      "epoch": 0.75,
-      "learning_rate": 0.0001,
-      "loss": 0.6063,
-      "step": 75
-    },
-    {
-      "epoch": 0.75,
-      "eval_runtime": 216.6607,
-      "eval_samples_per_second": 1.846,
-      "eval_steps_per_second": 0.157,
-      "step": 75
-    },
-    {
-      "epoch": 1.0,
-      "learning_rate": 0.0001,
-      "loss": 0.5707,
-      "step": 100
-    },
-    {
-      "epoch": 1.0,
-      "eval_runtime": 216.7207,
-      "eval_samples_per_second": 1.846,
-      "eval_steps_per_second": 0.157,
-      "step": 100
-    },
-    {
-      "epoch": 1.25,
-      "learning_rate": 0.0001,
-      "loss": 0.4976,
-      "step": 125
-    },
-    {
-      "epoch": 1.25,
-      "eval_runtime": 216.1906,
-      "eval_samples_per_second": 1.85,
-      "eval_steps_per_second": 0.157,
-      "step": 125
-    },
-    {
-      "epoch": 1.5,
-      "learning_rate": 0.0001,
-      "loss": 0.5296,
-      "step": 150
-    },
-    {
-      "epoch": 1.5,
-      "eval_runtime": 216.4796,
-      "eval_samples_per_second": 1.848,
-      "eval_steps_per_second": 0.157,
-      "step": 150
-    },
-    {
-      "epoch": 1.75,
-      "learning_rate": 0.0001,
-      "loss": 0.5748,
-      "step": 175
-    },
-    {
-      "epoch": 1.75,
-      "eval_runtime": 216.7074,
-      "eval_samples_per_second": 1.846,
-      "eval_steps_per_second": 0.157,
-      "step": 175
-    },
-    {
-      "epoch": 2.0,
-      "learning_rate": 0.0001,
-      "loss": 0.5471,
-      "step": 200
-    },
-    {
-      "epoch": 2.0,
-      "eval_runtime": 216.7005,
-      "eval_samples_per_second": 1.846,
-      "eval_steps_per_second": 0.157,
-      "step": 200
+      "epoch": 0.03,
+      "eval_runtime": 127.9324,
+      "eval_samples_per_second": 1.759,
+      "eval_steps_per_second": 0.227,
+      "step": 2
     }
   ],
-  "logging_steps": 25,
-  "max_steps": 200,
-  "num_train_epochs": 2,
-  "save_steps": 25,
-  "total_flos": 3.32202164355072e+16,
+  "logging_steps": 2,
+  "max_steps": 240,
+  "num_train_epochs": 3,
+  "save_steps": 2,
+  "total_flos": 332202164355072.0,
   "trial_name": null,
   "trial_params": null
 }

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c8c27537b3f48a590e7245cfc358a5c006cb5add7444724e14c4fd4a1f89680
-size 4091
+oid sha256:887525ecb45e22150885f827b7fded85dffa90a11a9d2671d3af44cae52f9aff
+size 4027