Upload task output ac92fa52-28b8-479a-b5d5-a678407b5011

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip 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

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 24,
+  "model_type": "qwen2",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "unsloth_version": "2024.9",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,15 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "max_length": 32768,
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.51.3"
+}

loss.txt

@@ -0,0 +1 @@
+166,1.4646453857421875

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28c55f72a64a9f2fb4d72715f0ef031374c9a1a790f1e960ded5c1e3f6618fcd
+size 988097824

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
+size 11418266

tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,281 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9761904761904763,
+  "eval_steps": 500,
+  "global_step": 166,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05952380952380952,
+      "grad_norm": 7.34375,
+      "learning_rate": 8.815157634604766e-06,
+      "loss": 1.8887,
+      "step": 5
+    },
+    {
+      "epoch": 0.11904761904761904,
+      "grad_norm": 3.90625,
+      "learning_rate": 1.983410467786072e-05,
+      "loss": 1.718,
+      "step": 10
+    },
+    {
+      "epoch": 0.17857142857142858,
+      "grad_norm": 2.796875,
+      "learning_rate": 3.085305172111668e-05,
+      "loss": 1.5748,
+      "step": 15
+    },
+    {
+      "epoch": 0.23809523809523808,
+      "grad_norm": 2.625,
+      "learning_rate": 4.187199876437263e-05,
+      "loss": 1.5417,
+      "step": 20
+    },
+    {
+      "epoch": 0.2976190476190476,
+      "grad_norm": 2.1875,
+      "learning_rate": 5.28909458076286e-05,
+      "loss": 1.5065,
+      "step": 25
+    },
+    {
+      "epoch": 0.35714285714285715,
+      "grad_norm": 2.359375,
+      "learning_rate": 6.390989285088455e-05,
+      "loss": 1.4201,
+      "step": 30
+    },
+    {
+      "epoch": 0.4166666666666667,
+      "grad_norm": 2.265625,
+      "learning_rate": 7.492883989414051e-05,
+      "loss": 1.4179,
+      "step": 35
+    },
+    {
+      "epoch": 0.47619047619047616,
+      "grad_norm": 2.25,
+      "learning_rate": 7.708414308620465e-05,
+      "loss": 1.3922,
+      "step": 40
+    },
+    {
+      "epoch": 0.5357142857142857,
+      "grad_norm": 1.8671875,
+      "learning_rate": 7.688744639389479e-05,
+      "loss": 1.3509,
+      "step": 45
+    },
+    {
+      "epoch": 0.5952380952380952,
+      "grad_norm": 2.59375,
+      "learning_rate": 7.654053825785006e-05,
+      "loss": 1.3861,
+      "step": 50
+    },
+    {
+      "epoch": 0.6547619047619048,
+      "grad_norm": 2.40625,
+      "learning_rate": 7.604523563706609e-05,
+      "loss": 1.3591,
+      "step": 55
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 2.046875,
+      "learning_rate": 7.540413271847275e-05,
+      "loss": 1.3542,
+      "step": 60
+    },
+    {
+      "epoch": 0.7738095238095238,
+      "grad_norm": 1.9375,
+      "learning_rate": 7.462058732967345e-05,
+      "loss": 1.3694,
+      "step": 65
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 1.9375,
+      "learning_rate": 7.369870335205563e-05,
+      "loss": 1.3377,
+      "step": 70
+    },
+    {
+      "epoch": 0.8928571428571429,
+      "grad_norm": 2.0625,
+      "learning_rate": 7.264330922638506e-05,
+      "loss": 1.2981,
+      "step": 75
+    },
+    {
+      "epoch": 0.9523809523809523,
+      "grad_norm": 1.9140625,
+      "learning_rate": 7.145993266346274e-05,
+      "loss": 1.3101,
+      "step": 80
+    },
+    {
+      "epoch": 0.9880952380952381,
+      "eval_loss": 1.5184645652770996,
+      "eval_runtime": 6.8095,
+      "eval_samples_per_second": 29.371,
+      "eval_steps_per_second": 29.371,
+      "step": 83
+    },
+    {
+      "epoch": 1.0119047619047619,
+      "grad_norm": 2.125,
+      "learning_rate": 7.015477169229925e-05,
+      "loss": 1.2726,
+      "step": 85
+    },
+    {
+      "epoch": 1.0714285714285714,
+      "grad_norm": 2.0625,
+      "learning_rate": 6.873466219744416e-05,
+      "loss": 1.2178,
+      "step": 90
+    },
+    {
+      "epoch": 1.130952380952381,
+      "grad_norm": 2.015625,
+      "learning_rate": 6.72070421154961e-05,
+      "loss": 1.1864,
+      "step": 95
+    },
+    {
+      "epoch": 1.1904761904761905,
+      "grad_norm": 1.8828125,
+      "learning_rate": 6.55799124783174e-05,
+      "loss": 1.1736,
+      "step": 100
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 1.9375,
+      "learning_rate": 6.386179550699237e-05,
+      "loss": 1.179,
+      "step": 105
+    },
+    {
+      "epoch": 1.3095238095238095,
+      "grad_norm": 1.953125,
+      "learning_rate": 6.206168997601557e-05,
+      "loss": 1.1931,
+      "step": 110
+    },
+    {
+      "epoch": 1.369047619047619,
+      "grad_norm": 1.8125,
+      "learning_rate": 6.0189024081493556e-05,
+      "loss": 1.1593,
+      "step": 115
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 2.1875,
+      "learning_rate": 5.825360606021676e-05,
+      "loss": 1.1416,
+      "step": 120
+    },
+    {
+      "epoch": 1.4880952380952381,
+      "grad_norm": 1.828125,
+      "learning_rate": 5.626557281823805e-05,
+      "loss": 1.1742,
+      "step": 125
+    },
+    {
+      "epoch": 1.5476190476190477,
+      "grad_norm": 1.6640625,
+      "learning_rate": 5.423533683801979e-05,
+      "loss": 1.172,
+      "step": 130
+    },
+    {
+      "epoch": 1.6071428571428572,
+      "grad_norm": 1.6171875,
+      "learning_rate": 5.2173531642227546e-05,
+      "loss": 1.1783,
+      "step": 135
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 1.8203125,
+      "learning_rate": 5.009095609980816e-05,
+      "loss": 1.1861,
+      "step": 140
+    },
+    {
+      "epoch": 1.7261904761904763,
+      "grad_norm": 1.6796875,
+      "learning_rate": 4.799851786605331e-05,
+      "loss": 1.1517,
+      "step": 145
+    },
+    {
+      "epoch": 1.7857142857142856,
+      "grad_norm": 1.609375,
+      "learning_rate": 4.590717625288627e-05,
+      "loss": 1.1703,
+      "step": 150
+    },
+    {
+      "epoch": 1.8452380952380953,
+      "grad_norm": 1.90625,
+      "learning_rate": 4.382788482859252e-05,
+      "loss": 1.1476,
+      "step": 155
+    },
+    {
+      "epoch": 1.9047619047619047,
+      "grad_norm": 1.7734375,
+      "learning_rate": 4.177153404763354e-05,
+      "loss": 1.1682,
+      "step": 160
+    },
+    {
+      "epoch": 1.9642857142857144,
+      "grad_norm": 1.6328125,
+      "learning_rate": 3.974889421102398e-05,
+      "loss": 1.1397,
+      "step": 165
+    },
+    {
+      "epoch": 1.9761904761904763,
+      "eval_loss": 1.4646453857421875,
+      "eval_runtime": 6.7251,
+      "eval_samples_per_second": 29.739,
+      "eval_steps_per_second": 29.739,
+      "step": 166
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 252,
+  "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": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.0175749958192333e+17,
+  "train_batch_size": 140,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebe9af9cadaa6d212d9f4a97461ffa4480594d6bdb8d3fa080e3d0c70b3fad71
+size 5688