End of training

README.md

@@ -4,6 +4,7 @@ license: apache-2.0
 base_model: Qwen/Qwen2.5-1.5B-Instruct
 tags:
 - llama-factory
+- lora
 - generated_from_trainer
 model-index:
 - name: last_version
@@ -15,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # last_version
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) on an unknown dataset.
+This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) on the chat_train dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.8377
+- Loss: 1.8395
 
 ## Model description
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 1.839530110359192,
+    "eval_runtime": 498.8921,
+    "eval_samples_per_second": 0.108,
+    "eval_steps_per_second": 0.108,
+    "total_flos": 994098989383680.0,
+    "train_loss": 1.8405975977579752,
+    "train_runtime": 23722.9763,
+    "train_samples_per_second": 0.04,
+    "train_steps_per_second": 0.005
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 1.839530110359192,
+    "eval_runtime": 498.8921,
+    "eval_samples_per_second": 0.108,
+    "eval_steps_per_second": 0.108
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 994098989383680.0,
+    "train_loss": 1.8405975977579752,
+    "train_runtime": 23722.9763,
+    "train_samples_per_second": 0.04,
+    "train_steps_per_second": 0.005
+}

trainer_state.json

@@ -0,0 +1,58 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 100,
+  "global_step": 120,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.5,
+      "grad_norm": 3.227240562438965,
+      "learning_rate": 9.042397785550405e-06,
+      "loss": 1.9625,
+      "step": 100
+    },
+    {
+      "epoch": 2.5,
+      "eval_loss": 1.8376805782318115,
+      "eval_runtime": 533.9255,
+      "eval_samples_per_second": 0.101,
+      "eval_steps_per_second": 0.101,
+      "step": 100
+    },
+    {
+      "epoch": 3.0,
+      "step": 120,
+      "total_flos": 994098989383680.0,
+      "train_loss": 1.8405975977579752,
+      "train_runtime": 23722.9763,
+      "train_samples_per_second": 0.04,
+      "train_steps_per_second": 0.005
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 120,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 994098989383680.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}