Model save

README.md

@@ -27,7 +27,7 @@ print(output["generated_text"])
 
 ## Training procedure
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/noteam2235/huggingface/runs/h9o9adls) 
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/noteam2235/huggingface/runs/4xsgt4nu) 
 
 
 This model was trained with SFT.

all_results.json

@@ -1,8 +1,8 @@
 {
-    "total_flos": 427315691520.0,
-    "train_loss": 0.0,
-    "train_runtime": 3.3973,
-    "train_samples": 100,
-    "train_samples_per_second": 10.891,
-    "train_steps_per_second": 0.589
+    "total_flos": 1338922500096.0,
+    "train_loss": 0.8787662982940674,
+    "train_runtime": 52.0164,
+    "train_samples": 300,
+    "train_samples_per_second": 8.44,
+    "train_steps_per_second": 0.115
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:081546ce9a9403a817de3a122319a951510c3396cd7631c26afdac41207fedc4
+oid sha256:6d728507d2aa4a648f418b5491e02e84a26af476918a8e9218e9cb369ea3569b
 size 3087467144

train_results.json

@@ -1,8 +1,8 @@
 {
-    "total_flos": 427315691520.0,
-    "train_loss": 0.0,
-    "train_runtime": 3.3973,
-    "train_samples": 100,
-    "train_samples_per_second": 10.891,
-    "train_steps_per_second": 0.589
+    "total_flos": 1338922500096.0,
+    "train_loss": 0.8787662982940674,
+    "train_runtime": 52.0164,
+    "train_samples": 300,
+    "train_samples_per_second": 8.44,
+    "train_steps_per_second": 0.115
 }

trainer_state.json

@@ -1,25 +1,34 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.0,
-  "eval_steps": 500,
-  "global_step": 2,
+  "epoch": 0.8727272727272727,
+  "eval_steps": 100,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 1.0,
-      "step": 2,
-      "total_flos": 427315691520.0,
-      "train_loss": 0.0,
-      "train_runtime": 3.3973,
-      "train_samples_per_second": 10.891,
-      "train_steps_per_second": 0.589
+      "epoch": 0.7272727272727273,
+      "grad_norm": 1.3501643358314308,
+      "learning_rate": 1.9098300562505266e-06,
+      "loss": 0.8944,
+      "mean_token_accuracy": 0.7577449153561558,
+      "step": 5
+    },
+    {
+      "epoch": 0.8727272727272727,
+      "mean_token_accuracy": 0.7622872596745417,
+      "step": 6,
+      "total_flos": 1338922500096.0,
+      "train_loss": 0.8787662982940674,
+      "train_runtime": 52.0164,
+      "train_samples_per_second": 8.44,
+      "train_steps_per_second": 0.115
     }
   ],
-  "logging_steps": 500,
-  "max_steps": 2,
+  "logging_steps": 5,
+  "max_steps": 6,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 500,
@@ -29,13 +38,13 @@
         "should_epoch_stop": false,
         "should_evaluate": false,
         "should_log": false,
-        "should_save": true,
-        "should_training_stop": true
+        "should_save": false,
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 427315691520.0,
+  "total_flos": 1338922500096.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24ac7301cb7815df750ebd1d7281b65cae3d6d32590619b96f81b01c90d1f089
-size 6008
+oid sha256:deb35b2251125d46ac633df88868293fe4cfef8f450e9b8b8d0d500ffe8c97d6
+size 7416