Upload task output 2de0ddab-27eb-430d-8b3b-8360ebeab915

.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 +1,28 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 2816,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 16,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.51.3"
+}

loss.txt

@@ -0,0 +1 @@
+60,1.2711824178695679

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:553fc5db8f27f1adb880b113697ccb151c2e639834ce3a4fda6e36218dbeb373
+size 928008104

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "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 +1,44 @@
+{
+  "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": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,142 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.857142857142857,
+  "eval_steps": 500,
+  "global_step": 60,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23809523809523808,
+      "grad_norm": 3.078125,
+      "learning_rate": 1.1171428571428571e-05,
+      "loss": 1.6553,
+      "step": 5
+    },
+    {
+      "epoch": 0.47619047619047616,
+      "grad_norm": 2.5625,
+      "learning_rate": 2.5135714285714285e-05,
+      "loss": 1.5594,
+      "step": 10
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 2.5625,
+      "learning_rate": 3.91e-05,
+      "loss": 1.4914,
+      "step": 15
+    },
+    {
+      "epoch": 0.9523809523809523,
+      "grad_norm": 2.078125,
+      "learning_rate": 5.306428571428571e-05,
+      "loss": 1.3912,
+      "step": 20
+    },
+    {
+      "epoch": 0.9523809523809523,
+      "eval_loss": 1.416105031967163,
+      "eval_runtime": 10.5759,
+      "eval_samples_per_second": 13.332,
+      "eval_steps_per_second": 13.332,
+      "step": 20
+    },
+    {
+      "epoch": 1.1904761904761905,
+      "grad_norm": 2.265625,
+      "learning_rate": 6.702857142857144e-05,
+      "loss": 1.304,
+      "step": 25
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 1.9609375,
+      "learning_rate": 8.099285714285715e-05,
+      "loss": 1.2533,
+      "step": 30
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 2.875,
+      "learning_rate": 9.495714285714286e-05,
+      "loss": 1.2274,
+      "step": 35
+    },
+    {
+      "epoch": 1.9047619047619047,
+      "grad_norm": 2.109375,
+      "learning_rate": 9.339386807685766e-05,
+      "loss": 1.2204,
+      "step": 40
+    },
+    {
+      "epoch": 1.9047619047619047,
+      "eval_loss": 1.3032252788543701,
+      "eval_runtime": 10.4999,
+      "eval_samples_per_second": 13.429,
+      "eval_steps_per_second": 13.429,
+      "step": 40
+    },
+    {
+      "epoch": 2.142857142857143,
+      "grad_norm": 1.84375,
+      "learning_rate": 7.716526096571837e-05,
+      "loss": 1.0658,
+      "step": 45
+    },
+    {
+      "epoch": 2.380952380952381,
+      "grad_norm": 1.5390625,
+      "learning_rate": 5.3762500000000006e-05,
+      "loss": 1.0063,
+      "step": 50
+    },
+    {
+      "epoch": 2.619047619047619,
+      "grad_norm": 1.4375,
+      "learning_rate": 3.0359739034281636e-05,
+      "loss": 0.9935,
+      "step": 55
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 1.390625,
+      "learning_rate": 1.4131131923142345e-05,
+      "loss": 0.9698,
+      "step": 60
+    },
+    {
+      "epoch": 2.857142857142857,
+      "eval_loss": 1.2711824178695679,
+      "eval_runtime": 10.5832,
+      "eval_samples_per_second": 13.323,
+      "eval_steps_per_second": 13.323,
+      "step": 60
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 63,
+  "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": 1.5825719078682624e+16,
+  "train_batch_size": 70,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73701181b35c18d88b452fd5a47284b0f3f64642404c6bbe9046602d31bca860
+size 5688