End of training

README.md

@@ -4,6 +4,7 @@ license: apache-2.0
 base_model: Qwen/Qwen2.5-7B-Instruct
 tags:
 - llama-factory
+- full
 - generated_from_trainer
 model-index:
 - name: s1k-11-test-192
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # s1k-11-test-192
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on an unknown dataset.
+This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the mlfoundations-dev/s1k-1.1-test-192 dataset.
 
 ## Model description
 

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 6010137521160192.0,
+    "train_loss": 1.2243933081626892,
+    "train_runtime": 591.9737,
+    "train_samples_per_second": 0.324,
+    "train_steps_per_second": 0.003
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 6010137521160192.0,
+    "train_loss": 1.2243933081626892,
+    "train_runtime": 591.9737,
+    "train_samples_per_second": 0.324,
+    "train_steps_per_second": 0.003
+}

trainer_state.json

@@ -0,0 +1,56 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 2,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5,
+      "grad_norm": 6.930043673385507,
+      "learning_rate": 2e-05,
+      "loss": 1.2459,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 7.055667176181546,
+      "learning_rate": 0.0,
+      "loss": 1.2028,
+      "step": 2
+    },
+    {
+      "epoch": 1.0,
+      "step": 2,
+      "total_flos": 6010137521160192.0,
+      "train_loss": 1.2243933081626892,
+      "train_runtime": 591.9737,
+      "train_samples_per_second": 0.324,
+      "train_steps_per_second": 0.003
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 2,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6010137521160192.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}