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: models2
@@ -15,7 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # models2
 
-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 news_finetune_train dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1162
 
 ## Model description
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.11616294831037521,
+    "eval_runtime": 65.0617,
+    "eval_samples_per_second": 1.537,
+    "eval_steps_per_second": 1.537,
+    "total_flos": 1107581215948800.0,
+    "train_loss": 0.23672364275062494,
+    "train_runtime": 593.0713,
+    "train_samples_per_second": 0.506,
+    "train_steps_per_second": 0.086
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.11616294831037521,
+    "eval_runtime": 65.0617,
+    "eval_samples_per_second": 1.537,
+    "eval_steps_per_second": 1.537
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1107581215948800.0,
+    "train_loss": 0.23672364275062494,
+    "train_runtime": 593.0713,
+    "train_samples_per_second": 0.506,
+    "train_steps_per_second": 0.086
+}

trainer_state.json

@@ -0,0 +1,77 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 100,
+  "global_step": 51,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5882352941176471,
+      "grad_norm": 1.863926649093628,
+      "learning_rate": 9.806308479691595e-05,
+      "loss": 0.8435,
+      "step": 10
+    },
+    {
+      "epoch": 1.1764705882352942,
+      "grad_norm": 0.47435468435287476,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 0.1557,
+      "step": 20
+    },
+    {
+      "epoch": 1.7647058823529411,
+      "grad_norm": 0.36670321226119995,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.0779,
+      "step": 30
+    },
+    {
+      "epoch": 2.3529411764705883,
+      "grad_norm": 0.31751275062561035,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.0654,
+      "step": 40
+    },
+    {
+      "epoch": 2.9411764705882355,
+      "grad_norm": 0.46291136741638184,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.0641,
+      "step": 50
+    },
+    {
+      "epoch": 3.0,
+      "step": 51,
+      "total_flos": 1107581215948800.0,
+      "train_loss": 0.23672364275062494,
+      "train_runtime": 593.0713,
+      "train_samples_per_second": 0.506,
+      "train_steps_per_second": 0.086
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 51,
+  "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": 1107581215948800.0,
+  "train_batch_size": 3,
+  "trial_name": null,
+  "trial_params": null
+}