End of training

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text
+wandb/run-20250413_002204-33xvut2k/run-33xvut2k.wandb filter=lfs diff=lfs merge=lfs -text

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": 5944042269442048.0,
+    "train_loss": 1.2243931889533997,
+    "train_runtime": 384.9677,
+    "train_samples_per_second": 0.499,
+    "train_steps_per_second": 0.005
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 5944042269442048.0,
+    "train_loss": 1.2243931889533997,
+    "train_runtime": 384.9677,
+    "train_samples_per_second": 0.499,
+    "train_steps_per_second": 0.005
+}

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": 6.925258567695526,
+      "learning_rate": 2e-05,
+      "loss": 1.2459,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 7.060579782684043,
+      "learning_rate": 0.0,
+      "loss": 1.2028,
+      "step": 2
+    },
+    {
+      "epoch": 1.0,
+      "step": 2,
+      "total_flos": 5944042269442048.0,
+      "train_loss": 1.2243931889533997,
+      "train_runtime": 384.9677,
+      "train_samples_per_second": 0.499,
+      "train_steps_per_second": 0.005
+    }
+  ],
+  "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": 5944042269442048.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

wandb/run-20250413_002204-33xvut2k/files/output.log

@@ -52,3 +52,22 @@ Training completed. Do not forget to share your model on huggingface.co/models =
 [INFO|tokenization_utils_base.py:2655] 2025-04-13 00:35:38,673 >> Special tokens file saved in /data/horse/ws/ryma833h-DCFT_Shared/checkpoints/s1k-11-test-192/special_tokens_map.json
 [INFO|modelcard.py:449] 2025-04-13 00:35:39,180 >> Dropping the following result as it does not have all the necessary fields:
 {'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}}
+***** train metrics *****
+  epoch                    =        1.0
+  total_flos               =  5535820GF
+  train_loss               =     1.2244
+  train_runtime            = 0:06:24.96
+  train_samples_per_second =      0.499
+  train_steps_per_second   =      0.005
+Figure saved at: /data/horse/ws/ryma833h-DCFT_Shared/checkpoints/s1k-11-test-192/training_loss.png
+[WARNING|2025-04-13 00:35:56] llamafactory.extras.ploting:161 >> No metric eval_loss to plot.
+[WARNING|2025-04-13 00:35:56] llamafactory.extras.ploting:161 >> No metric eval_accuracy to plot.
+[INFO|trainer.py:3801] 2025-04-13 00:35:58,206 >> Saving model checkpoint to /data/horse/ws/ryma833h-DCFT_Shared/checkpoints/s1k-11-test-192
+[INFO|configuration_utils.py:414] 2025-04-13 00:35:58,211 >> Configuration saved in /data/horse/ws/ryma833h-DCFT_Shared/checkpoints/s1k-11-test-192/config.json
+[INFO|configuration_utils.py:865] 2025-04-13 00:35:58,212 >> Configuration saved in /data/horse/ws/ryma833h-DCFT_Shared/checkpoints/s1k-11-test-192/generation_config.json
+[INFO|modeling_utils.py:3043] 2025-04-13 00:36:12,746 >> The model is bigger than the maximum size per checkpoint (5GB) and is going to be split in 4 checkpoint shards. You can find where each parameters has been saved in the index located at /data/horse/ws/ryma833h-DCFT_Shared/checkpoints/s1k-11-test-192/model.safetensors.index.json.
+[INFO|tokenization_utils_base.py:2646] 2025-04-13 00:36:12,748 >> tokenizer config file saved in /data/horse/ws/ryma833h-DCFT_Shared/checkpoints/s1k-11-test-192/tokenizer_config.json
+[INFO|tokenization_utils_base.py:2655] 2025-04-13 00:36:12,749 >> Special tokens file saved in /data/horse/ws/ryma833h-DCFT_Shared/checkpoints/s1k-11-test-192/special_tokens_map.json
+[INFO|modelcard.py:449] 2025-04-13 00:36:12,992 >> Dropping the following result as it does not have all the necessary fields:
+{'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}}
+run-33xvut2k.wandb: 100%|██████████| 131k/131k [00:00<00:00, 174kB/s]