Model save

README.md

@@ -27,15 +27,15 @@ 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/rohanbayya1205-san-jose-state-university/huggingface/runs/wf116seg) 
+[<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/rohanbayya1205-san-jose-state-university/huggingface/runs/setdmiv0) 
 
 
 This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
 
 ### Framework versions
 
-- TRL: 0.16.0.dev0
-- Transformers: 4.49.0
+- TRL: 0.16.0
+- Transformers: 4.50.0
 - Pytorch: 2.5.1
 - Datasets: 3.3.2
 - Tokenizers: 0.21.0

all_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.010941930115222931,
-    "train_runtime": 4898.9111,
-    "train_samples": 800,
-    "train_samples_per_second": 0.163,
+    "train_loss": 0.025846945121884346,
+    "train_runtime": 5654.5918,
+    "train_samples": 512,
+    "train_samples_per_second": 0.091,
     "train_steps_per_second": 0.0
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.010941930115222931,
-    "train_runtime": 4898.9111,
-    "train_samples": 800,
-    "train_samples_per_second": 0.163,
+    "train_loss": 0.025846945121884346,
+    "train_runtime": 5654.5918,
+    "train_samples": 512,
+    "train_samples_per_second": 0.091,
     "train_steps_per_second": 0.0
 }

trainer_state.json

@@ -1,8 +1,9 @@
 {
+  "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.64,
-  "eval_steps": 100,
+  "epoch": 1.0,
+  "eval_steps": 500,
   "global_step": 1,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
@@ -10,18 +11,27 @@
   "log_history": [
     {
       "clip_ratio": 0.0,
-      "completion_length": 678.875,
-      "epoch": 0.64,
+      "completion_length": 675.4326171875,
+      "epoch": 1.0,
+      "grad_norm": 0.011617695912718773,
       "kl": 0.0,
-      "reward": 0.2314453125,
-      "reward_std": 0.20854125346522778,
-      "rewards/accuracy_reward": 0.0703125,
-      "rewards/format_reward": 0.1611328125,
+      "learning_rate": 2e-05,
+      "loss": 0.0258,
+      "num_tokens": 875773.0,
+      "reward": 0.6923828125,
+      "reward_std": 0.33076575957238674,
+      "rewards/accuracy_reward": 0.0634765625,
+      "rewards/format_reward": 0.107421875,
+      "rewards/tag_count_reward": 0.521484375,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
       "step": 1,
       "total_flos": 0.0,
-      "train_loss": 0.010941930115222931,
-      "train_runtime": 4898.9111,
-      "train_samples_per_second": 0.163,
+      "train_loss": 0.025846945121884346,
+      "train_runtime": 5654.5918,
+      "train_samples_per_second": 0.091,
       "train_steps_per_second": 0.0
     }
   ],
@@ -36,8 +46,8 @@
         "should_epoch_stop": false,
         "should_evaluate": false,
         "should_log": false,
-        "should_save": false,
-        "should_training_stop": false
+        "should_save": true,
+        "should_training_stop": true
       },
       "attributes": {}
     }