End of training

README.md

@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Extractor_Adaptor_Qwen3_r8plus
 
-This model is a fine-tuned version of [Qwen/Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B) on an unknown dataset.
+This model is a fine-tuned version of [Qwen/Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B) on the web_finetune_train dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.3760
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.3759682774543762,
+    "eval_runtime": 231.8213,
+    "eval_samples_per_second": 4.102,
+    "eval_steps_per_second": 1.027,
+    "total_flos": 1.3864992889634816e+16,
+    "train_loss": 0.40865129894680446,
+    "train_runtime": 2517.946,
+    "train_samples_per_second": 1.133,
+    "train_steps_per_second": 0.036
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.3759682774543762,
+    "eval_runtime": 231.8213,
+    "eval_samples_per_second": 4.102,
+    "eval_steps_per_second": 1.027
+}

runs/Dec27_05-26-58_41b2859543c6/events.out.tfevents.1766816032.41b2859543c6.134.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46cad5f3d158505d2306a1ef413d1ab8546f00b376970fd9f835743245b9fb69
+size 354

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 1.3864992889634816e+16,
+    "train_loss": 0.40865129894680446,
+    "train_runtime": 2517.946,
+    "train_samples_per_second": 1.133,
+    "train_steps_per_second": 0.036
+}

trainer_state.json

@@ -0,0 +1,177 @@
+{
+  "best_global_step": 50,
+  "best_metric": 0.3759682774543762,
+  "best_model_checkpoint": "/kaggle/working/Llama-Factory-out/checkpoint-50",
+  "epoch": 1.0,
+  "eval_steps": 50,
+  "global_step": 90,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.056100981767180924,
+      "grad_norm": 8.957350730895996,
+      "learning_rate": 4.444444444444444e-06,
+      "loss": 1.2444,
+      "step": 5
+    },
+    {
+      "epoch": 0.11220196353436185,
+      "grad_norm": 3.013394594192505,
+      "learning_rate": 1e-05,
+      "loss": 0.4911,
+      "step": 10
+    },
+    {
+      "epoch": 0.16830294530154277,
+      "grad_norm": 2.6695518493652344,
+      "learning_rate": 1.555555555555556e-05,
+      "loss": 0.3866,
+      "step": 15
+    },
+    {
+      "epoch": 0.2244039270687237,
+      "grad_norm": 2.688660144805908,
+      "learning_rate": 1.999048221581858e-05,
+      "loss": 0.406,
+      "step": 20
+    },
+    {
+      "epoch": 0.2805049088359046,
+      "grad_norm": 2.5806634426116943,
+      "learning_rate": 1.9659258262890683e-05,
+      "loss": 0.377,
+      "step": 25
+    },
+    {
+      "epoch": 0.33660589060308554,
+      "grad_norm": 2.4478094577789307,
+      "learning_rate": 1.887010833178222e-05,
+      "loss": 0.3554,
+      "step": 30
+    },
+    {
+      "epoch": 0.39270687237026647,
+      "grad_norm": 2.0873756408691406,
+      "learning_rate": 1.766044443118978e-05,
+      "loss": 0.4276,
+      "step": 35
+    },
+    {
+      "epoch": 0.4488078541374474,
+      "grad_norm": 1.726032018661499,
+      "learning_rate": 1.608761429008721e-05,
+      "loss": 0.3038,
+      "step": 40
+    },
+    {
+      "epoch": 0.5049088359046283,
+      "grad_norm": 2.1292402744293213,
+      "learning_rate": 1.4226182617406996e-05,
+      "loss": 0.3521,
+      "step": 45
+    },
+    {
+      "epoch": 0.5610098176718092,
+      "grad_norm": 2.8500609397888184,
+      "learning_rate": 1.2164396139381029e-05,
+      "loss": 0.3865,
+      "step": 50
+    },
+    {
+      "epoch": 0.5610098176718092,
+      "eval_loss": 0.3759682774543762,
+      "eval_runtime": 233.0757,
+      "eval_samples_per_second": 4.08,
+      "eval_steps_per_second": 1.021,
+      "step": 50
+    },
+    {
+      "epoch": 0.6171107994389902,
+      "grad_norm": 1.648816704750061,
+      "learning_rate": 1e-05,
+      "loss": 0.3668,
+      "step": 55
+    },
+    {
+      "epoch": 0.6732117812061711,
+      "grad_norm": 1.4755737781524658,
+      "learning_rate": 7.835603860618973e-06,
+      "loss": 0.3061,
+      "step": 60
+    },
+    {
+      "epoch": 0.729312762973352,
+      "grad_norm": 1.2600551843643188,
+      "learning_rate": 5.773817382593008e-06,
+      "loss": 0.3963,
+      "step": 65
+    },
+    {
+      "epoch": 0.7854137447405329,
+      "grad_norm": 1.612899661064148,
+      "learning_rate": 3.912385709912794e-06,
+      "loss": 0.3179,
+      "step": 70
+    },
+    {
+      "epoch": 0.8415147265077139,
+      "grad_norm": 1.2310423851013184,
+      "learning_rate": 2.339555568810221e-06,
+      "loss": 0.3536,
+      "step": 75
+    },
+    {
+      "epoch": 0.8976157082748948,
+      "grad_norm": 1.7635549306869507,
+      "learning_rate": 1.129891668217783e-06,
+      "loss": 0.3133,
+      "step": 80
+    },
+    {
+      "epoch": 0.9537166900420757,
+      "grad_norm": 1.8376754522323608,
+      "learning_rate": 3.4074173710931804e-07,
+      "loss": 0.3641,
+      "step": 85
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.9177987575531006,
+      "learning_rate": 9.517784181422018e-09,
+      "loss": 0.2073,
+      "step": 90
+    },
+    {
+      "epoch": 1.0,
+      "step": 90,
+      "total_flos": 1.3864992889634816e+16,
+      "train_loss": 0.40865129894680446,
+      "train_runtime": 2517.946,
+      "train_samples_per_second": 1.133,
+      "train_steps_per_second": 0.036
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 90,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.3864992889634816e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}