Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,15 @@ 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
+qwen2.5-1.5b-instruct/checkpoint-142/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen2.5-1.5b-instruct/checkpoint-213/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen2.5-1.5b-instruct/checkpoint-71/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen2.5-1.5b-instruct/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen2.5-3b-instruct/checkpoint-142/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen2.5-3b-instruct/checkpoint-213/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen2.5-3b-instruct/checkpoint-71/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen2.5-3b-instruct/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen2.5-7b-instruct/checkpoint-142/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen2.5-7b-instruct/checkpoint-213/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen2.5-7b-instruct/checkpoint-71/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen2.5-7b-instruct/tokenizer.json filter=lfs diff=lfs merge=lfs -text

qwen2.5-1.5b-instruct/README.md

@@ -0,0 +1,69 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-1.5B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: qwen2.5-1.5b-instruct
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# qwen2.5-1.5b-instruct
+
+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 codealpaca_train_20k_trace_generation_valid dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5171
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- gradient_accumulation_steps: 128
+- total_train_batch_size: 256
+- total_eval_batch_size: 2
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 0.1
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.5380        | 0.7111 | 50   | 0.5587          |
+| 0.5060        | 1.4124 | 100  | 0.5292          |
+| 0.4743        | 2.1138 | 150  | 0.5197          |
+| 0.4765        | 2.8249 | 200  | 0.5171          |
+
+
+### Framework versions
+
+- Transformers 5.2.0
+- Pytorch 2.11.0+cu128
+- Datasets 4.0.0
+- Tokenizers 0.22.2

qwen2.5-1.5b-instruct/all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.5171241164207458,
+    "eval_runtime": 8.31,
+    "eval_samples_per_second": 24.067,
+    "eval_steps_per_second": 12.034,
+    "total_flos": 2.4727435500270387e+17,
+    "train_loss": 0.5265021298972654,
+    "train_runtime": 6756.1203,
+    "train_samples_per_second": 7.993,
+    "train_steps_per_second": 0.032
+}

qwen2.5-1.5b-instruct/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

qwen2.5-1.5b-instruct/checkpoint-142/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

qwen2.5-1.5b-instruct/checkpoint-142/config.json

@@ -0,0 +1,61 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "dtype": "float32",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 1000000.0,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.2.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

qwen2.5-1.5b-instruct/checkpoint-142/generation_config.json

@@ -0,0 +1,13 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "5.2.0"
+}

qwen2.5-1.5b-instruct/checkpoint-142/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bc57373d2a4ede43535c112481a822694621c0d07fe2d1a9ffed15afd3cd6d9
+size 6174895536

qwen2.5-1.5b-instruct/checkpoint-142/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0f047a0b7066f7bc7eb1e6f175b6ea18ddf4b1d0ee7cf376e26fb4fbf7b071c
+size 12350013801

qwen2.5-1.5b-instruct/checkpoint-142/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95e5fc2074c0df31522a514f862c86cb00d71c946a7f15cc9ec0e53a69fb28a7
+size 14917

qwen2.5-1.5b-instruct/checkpoint-142/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e7153eae67b6c9232a41bc996a2bf5b83229b8c7230d61911ac0fd40e64154e
+size 14917

qwen2.5-1.5b-instruct/checkpoint-142/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:922deb71175797a96c4bddc5e1cef1c097df38c0dfa52334e97c89e0f573f2bb
+size 1465

qwen2.5-1.5b-instruct/checkpoint-142/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
+size 11421892

qwen2.5-1.5b-instruct/checkpoint-142/tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

qwen2.5-1.5b-instruct/checkpoint-142/trainer_state.json

@@ -0,0 +1,1044 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 50,
+  "global_step": 142,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.014222222222222223,
+      "grad_norm": 0.03586147725582123,
+      "learning_rate": 0.0,
+      "loss": 0.9098724722862244,
+      "step": 1
+    },
+    {
+      "epoch": 0.028444444444444446,
+      "grad_norm": 0.03577122464776039,
+      "learning_rate": 4.5454545454545457e-07,
+      "loss": 0.9084522724151611,
+      "step": 2
+    },
+    {
+      "epoch": 0.042666666666666665,
+      "grad_norm": 0.031653374433517456,
+      "learning_rate": 9.090909090909091e-07,
+      "loss": 0.8834755420684814,
+      "step": 3
+    },
+    {
+      "epoch": 0.05688888888888889,
+      "grad_norm": 0.025831686332821846,
+      "learning_rate": 1.3636363636363636e-06,
+      "loss": 0.871230959892273,
+      "step": 4
+    },
+    {
+      "epoch": 0.07111111111111111,
+      "grad_norm": 0.019876576960086823,
+      "learning_rate": 1.8181818181818183e-06,
+      "loss": 0.7917206287384033,
+      "step": 5
+    },
+    {
+      "epoch": 0.08533333333333333,
+      "grad_norm": 0.018677273765206337,
+      "learning_rate": 2.2727272727272728e-06,
+      "loss": 0.8436126708984375,
+      "step": 6
+    },
+    {
+      "epoch": 0.09955555555555555,
+      "grad_norm": 0.017528358846902847,
+      "learning_rate": 2.7272727272727272e-06,
+      "loss": 0.8075190782546997,
+      "step": 7
+    },
+    {
+      "epoch": 0.11377777777777778,
+      "grad_norm": 0.01399513240903616,
+      "learning_rate": 3.181818181818182e-06,
+      "loss": 0.7754716873168945,
+      "step": 8
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 0.012644859962165356,
+      "learning_rate": 3.6363636363636366e-06,
+      "loss": 0.7459083199501038,
+      "step": 9
+    },
+    {
+      "epoch": 0.14222222222222222,
+      "grad_norm": 0.01209743320941925,
+      "learning_rate": 4.0909090909090915e-06,
+      "loss": 0.7365868091583252,
+      "step": 10
+    },
+    {
+      "epoch": 0.15644444444444444,
+      "grad_norm": 0.012133832089602947,
+      "learning_rate": 4.5454545454545455e-06,
+      "loss": 0.7119501829147339,
+      "step": 11
+    },
+    {
+      "epoch": 0.17066666666666666,
+      "grad_norm": 0.010017997585237026,
+      "learning_rate": 5e-06,
+      "loss": 0.6901087760925293,
+      "step": 12
+    },
+    {
+      "epoch": 0.18488888888888888,
+      "grad_norm": 0.009233366698026657,
+      "learning_rate": 5.4545454545454545e-06,
+      "loss": 0.6611638069152832,
+      "step": 13
+    },
+    {
+      "epoch": 0.1991111111111111,
+      "grad_norm": 0.00782010331749916,
+      "learning_rate": 5.90909090909091e-06,
+      "loss": 0.6715224981307983,
+      "step": 14
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 0.007341764867305756,
+      "learning_rate": 6.363636363636364e-06,
+      "loss": 0.6277110576629639,
+      "step": 15
+    },
+    {
+      "epoch": 0.22755555555555557,
+      "grad_norm": 0.00713470159098506,
+      "learning_rate": 6.818181818181818e-06,
+      "loss": 0.6689565181732178,
+      "step": 16
+    },
+    {
+      "epoch": 0.24177777777777779,
+      "grad_norm": 0.0067572277039289474,
+      "learning_rate": 7.272727272727273e-06,
+      "loss": 0.6363875865936279,
+      "step": 17
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 0.006228511221706867,
+      "learning_rate": 7.727272727272727e-06,
+      "loss": 0.6257224678993225,
+      "step": 18
+    },
+    {
+      "epoch": 0.2702222222222222,
+      "grad_norm": 0.006048806011676788,
+      "learning_rate": 8.181818181818183e-06,
+      "loss": 0.6355900764465332,
+      "step": 19
+    },
+    {
+      "epoch": 0.28444444444444444,
+      "grad_norm": 0.005988306365907192,
+      "learning_rate": 8.636363636363637e-06,
+      "loss": 0.6338369846343994,
+      "step": 20
+    },
+    {
+      "epoch": 0.2986666666666667,
+      "grad_norm": 0.005441761109977961,
+      "learning_rate": 9.090909090909091e-06,
+      "loss": 0.6133573055267334,
+      "step": 21
+    },
+    {
+      "epoch": 0.3128888888888889,
+      "grad_norm": 0.005174445919692516,
+      "learning_rate": 9.545454545454547e-06,
+      "loss": 0.6042410135269165,
+      "step": 22
+    },
+    {
+      "epoch": 0.32711111111111113,
+      "grad_norm": 0.005199746694415808,
+      "learning_rate": 1e-05,
+      "loss": 0.602219820022583,
+      "step": 23
+    },
+    {
+      "epoch": 0.3413333333333333,
+      "grad_norm": 0.005485028959810734,
+      "learning_rate": 9.999323662872998e-06,
+      "loss": 0.6062123775482178,
+      "step": 24
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 0.004896003287285566,
+      "learning_rate": 9.99729483446475e-06,
+      "loss": 0.6077945232391357,
+      "step": 25
+    },
+    {
+      "epoch": 0.36977777777777776,
+      "grad_norm": 0.00495151337236166,
+      "learning_rate": 9.993914063644053e-06,
+      "loss": 0.5923135280609131,
+      "step": 26
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 0.004744194447994232,
+      "learning_rate": 9.989182265027232e-06,
+      "loss": 0.5860621929168701,
+      "step": 27
+    },
+    {
+      "epoch": 0.3982222222222222,
+      "grad_norm": 0.004471767693758011,
+      "learning_rate": 9.98310071873072e-06,
+      "loss": 0.5823097229003906,
+      "step": 28
+    },
+    {
+      "epoch": 0.41244444444444445,
+      "grad_norm": 0.004788320977240801,
+      "learning_rate": 9.975671070024741e-06,
+      "loss": 0.5872600078582764,
+      "step": 29
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 0.0044632842764258385,
+      "learning_rate": 9.966895328888195e-06,
+      "loss": 0.6070278286933899,
+      "step": 30
+    },
+    {
+      "epoch": 0.4408888888888889,
+      "grad_norm": 0.004317905753850937,
+      "learning_rate": 9.956775869464901e-06,
+      "loss": 0.5780316591262817,
+      "step": 31
+    },
+    {
+      "epoch": 0.45511111111111113,
+      "grad_norm": 0.004291852004826069,
+      "learning_rate": 9.945315429421307e-06,
+      "loss": 0.5697590112686157,
+      "step": 32
+    },
+    {
+      "epoch": 0.4693333333333333,
+      "grad_norm": 0.003922830801457167,
+      "learning_rate": 9.932517109205849e-06,
+      "loss": 0.5747107267379761,
+      "step": 33
+    },
+    {
+      "epoch": 0.48355555555555557,
+      "grad_norm": 0.0041889771819114685,
+      "learning_rate": 9.918384371210178e-06,
+      "loss": 0.6021177172660828,
+      "step": 34
+    },
+    {
+      "epoch": 0.49777777777777776,
+      "grad_norm": 0.004147357773035765,
+      "learning_rate": 9.902921038832456e-06,
+      "loss": 0.5805741548538208,
+      "step": 35
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 0.0040724254213273525,
+      "learning_rate": 9.886131295443003e-06,
+      "loss": 0.5483200550079346,
+      "step": 36
+    },
+    {
+      "epoch": 0.5262222222222223,
+      "grad_norm": 0.004085644613951445,
+      "learning_rate": 9.868019683252543e-06,
+      "loss": 0.557392954826355,
+      "step": 37
+    },
+    {
+      "epoch": 0.5404444444444444,
+      "grad_norm": 0.004289102274924517,
+      "learning_rate": 9.848591102083375e-06,
+      "loss": 0.590857207775116,
+      "step": 38
+    },
+    {
+      "epoch": 0.5546666666666666,
+      "grad_norm": 0.0040345704182982445,
+      "learning_rate": 9.82785080804381e-06,
+      "loss": 0.5750541090965271,
+      "step": 39
+    },
+    {
+      "epoch": 0.5688888888888889,
+      "grad_norm": 0.004034748766571283,
+      "learning_rate": 9.805804412106197e-06,
+      "loss": 0.5949826240539551,
+      "step": 40
+    },
+    {
+      "epoch": 0.5831111111111111,
+      "grad_norm": 0.003911909181624651,
+      "learning_rate": 9.782457878588977e-06,
+      "loss": 0.5623177289962769,
+      "step": 41
+    },
+    {
+      "epoch": 0.5973333333333334,
+      "grad_norm": 0.0037001846358180046,
+      "learning_rate": 9.75781752354311e-06,
+      "loss": 0.5465081930160522,
+      "step": 42
+    },
+    {
+      "epoch": 0.6115555555555555,
+      "grad_norm": 0.0037095139268785715,
+      "learning_rate": 9.731890013043367e-06,
+      "loss": 0.5752100944519043,
+      "step": 43
+    },
+    {
+      "epoch": 0.6257777777777778,
+      "grad_norm": 0.003655617358162999,
+      "learning_rate": 9.704682361384941e-06,
+      "loss": 0.5452020168304443,
+      "step": 44
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.003784338477998972,
+      "learning_rate": 9.676201929185809e-06,
+      "loss": 0.5616332292556763,
+      "step": 45
+    },
+    {
+      "epoch": 0.6542222222222223,
+      "grad_norm": 0.003718078136444092,
+      "learning_rate": 9.646456421395447e-06,
+      "loss": 0.5558297634124756,
+      "step": 46
+    },
+    {
+      "epoch": 0.6684444444444444,
+      "grad_norm": 0.00395169947296381,
+      "learning_rate": 9.615453885210368e-06,
+      "loss": 0.5600595474243164,
+      "step": 47
+    },
+    {
+      "epoch": 0.6826666666666666,
+      "grad_norm": 0.003555440343916416,
+      "learning_rate": 9.583202707897075e-06,
+      "loss": 0.5372895002365112,
+      "step": 48
+    },
+    {
+      "epoch": 0.6968888888888889,
+      "grad_norm": 0.0037386869080364704,
+      "learning_rate": 9.549711614523007e-06,
+      "loss": 0.5322733521461487,
+      "step": 49
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 0.003739988896995783,
+      "learning_rate": 9.514989665596114e-06,
+      "loss": 0.5380419492721558,
+      "step": 50
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "eval_loss": 0.5587145090103149,
+      "eval_runtime": 8.7676,
+      "eval_samples_per_second": 22.811,
+      "eval_steps_per_second": 11.406,
+      "step": 50
+    },
+    {
+      "epoch": 0.7253333333333334,
+      "grad_norm": 0.0037539806216955185,
+      "learning_rate": 9.479046254613673e-06,
+      "loss": 0.5472225546836853,
+      "step": 51
+    },
+    {
+      "epoch": 0.7395555555555555,
+      "grad_norm": 0.003411181503906846,
+      "learning_rate": 9.441891105521005e-06,
+      "loss": 0.5134032964706421,
+      "step": 52
+    },
+    {
+      "epoch": 0.7537777777777778,
+      "grad_norm": 0.0037538670003414154,
+      "learning_rate": 9.40353427008083e-06,
+      "loss": 0.5361013412475586,
+      "step": 53
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 0.0036495670210570097,
+      "learning_rate": 9.3639861251539e-06,
+      "loss": 0.5299779772758484,
+      "step": 54
+    },
+    {
+      "epoch": 0.7822222222222223,
+      "grad_norm": 0.0037342547439038754,
+      "learning_rate": 9.323257369891702e-06,
+      "loss": 0.5607945919036865,
+      "step": 55
+    },
+    {
+      "epoch": 0.7964444444444444,
+      "grad_norm": 0.003572584595531225,
+      "learning_rate": 9.281359022841966e-06,
+      "loss": 0.5528460741043091,
+      "step": 56
+    },
+    {
+      "epoch": 0.8106666666666666,
+      "grad_norm": 0.003770101349800825,
+      "learning_rate": 9.238302418967757e-06,
+      "loss": 0.5440288186073303,
+      "step": 57
+    },
+    {
+      "epoch": 0.8248888888888889,
+      "grad_norm": 0.0036679303739219904,
+      "learning_rate": 9.194099206580981e-06,
+      "loss": 0.5564252138137817,
+      "step": 58
+    },
+    {
+      "epoch": 0.8391111111111111,
+      "grad_norm": 0.003834612900391221,
+      "learning_rate": 9.14876134419111e-06,
+      "loss": 0.5473330020904541,
+      "step": 59
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 0.003683249931782484,
+      "learning_rate": 9.102301097269974e-06,
+      "loss": 0.5463743209838867,
+      "step": 60
+    },
+    {
+      "epoch": 0.8675555555555555,
+      "grad_norm": 0.0036777963396161795,
+      "learning_rate": 9.05473103493355e-06,
+      "loss": 0.524878740310669,
+      "step": 61
+    },
+    {
+      "epoch": 0.8817777777777778,
+      "grad_norm": 0.0038230482023209333,
+      "learning_rate": 9.006064026541549e-06,
+      "loss": 0.5563522577285767,
+      "step": 62
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 0.003645201213657856,
+      "learning_rate": 8.956313238215824e-06,
+      "loss": 0.5059154033660889,
+      "step": 63
+    },
+    {
+      "epoch": 0.9102222222222223,
+      "grad_norm": 0.0035886459518224,
+      "learning_rate": 8.905492129278478e-06,
+      "loss": 0.5312881469726562,
+      "step": 64
+    },
+    {
+      "epoch": 0.9244444444444444,
+      "grad_norm": 0.003721872577443719,
+      "learning_rate": 8.85361444861063e-06,
+      "loss": 0.5358959436416626,
+      "step": 65
+    },
+    {
+      "epoch": 0.9386666666666666,
+      "grad_norm": 0.003683999879285693,
+      "learning_rate": 8.800694230932885e-06,
+      "loss": 0.5442053079605103,
+      "step": 66
+    },
+    {
+      "epoch": 0.9528888888888889,
+      "grad_norm": 0.0036851842887699604,
+      "learning_rate": 8.74674579300843e-06,
+      "loss": 0.5263723731040955,
+      "step": 67
+    },
+    {
+      "epoch": 0.9671111111111111,
+      "grad_norm": 0.003754258854314685,
+      "learning_rate": 8.691783729769874e-06,
+      "loss": 0.5200538039207458,
+      "step": 68
+    },
+    {
+      "epoch": 0.9813333333333333,
+      "grad_norm": 0.0038373274728655815,
+      "learning_rate": 8.635822910370793e-06,
+      "loss": 0.5452108383178711,
+      "step": 69
+    },
+    {
+      "epoch": 0.9955555555555555,
+      "grad_norm": 0.0039480882696807384,
+      "learning_rate": 8.578878474163115e-06,
+      "loss": 0.5066030621528625,
+      "step": 70
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.005897017661482096,
+      "learning_rate": 8.520965826601394e-06,
+      "loss": 0.5380499958992004,
+      "step": 71
+    },
+    {
+      "epoch": 1.0142222222222221,
+      "grad_norm": 0.0037728557363152504,
+      "learning_rate": 8.462100635075097e-06,
+      "loss": 0.5328541398048401,
+      "step": 72
+    },
+    {
+      "epoch": 1.0284444444444445,
+      "grad_norm": 0.003953218925744295,
+      "learning_rate": 8.40229882467003e-06,
+      "loss": 0.5096005201339722,
+      "step": 73
+    },
+    {
+      "epoch": 1.0426666666666666,
+      "grad_norm": 0.0036587677896022797,
+      "learning_rate": 8.341576573860049e-06,
+      "loss": 0.4889724850654602,
+      "step": 74
+    },
+    {
+      "epoch": 1.056888888888889,
+      "grad_norm": 0.0038338187150657177,
+      "learning_rate": 8.279950310130218e-06,
+      "loss": 0.5157173871994019,
+      "step": 75
+    },
+    {
+      "epoch": 1.0711111111111111,
+      "grad_norm": 0.003540106350556016,
+      "learning_rate": 8.2174367055326e-06,
+      "loss": 0.49691659212112427,
+      "step": 76
+    },
+    {
+      "epoch": 1.0853333333333333,
+      "grad_norm": 0.0037315969821065664,
+      "learning_rate": 8.154052672175888e-06,
+      "loss": 0.4873769283294678,
+      "step": 77
+    },
+    {
+      "epoch": 1.0995555555555556,
+      "grad_norm": 0.003963674418628216,
+      "learning_rate": 8.08981535765009e-06,
+      "loss": 0.5266215801239014,
+      "step": 78
+    },
+    {
+      "epoch": 1.1137777777777778,
+      "grad_norm": 0.0037685995921492577,
+      "learning_rate": 8.024742140387506e-06,
+      "loss": 0.5039150714874268,
+      "step": 79
+    },
+    {
+      "epoch": 1.1280000000000001,
+      "grad_norm": 0.003613364417105913,
+      "learning_rate": 7.95885062496126e-06,
+      "loss": 0.4896891117095947,
+      "step": 80
+    },
+    {
+      "epoch": 1.1422222222222222,
+      "grad_norm": 0.0037347134202718735,
+      "learning_rate": 7.892158637322647e-06,
+      "loss": 0.45997822284698486,
+      "step": 81
+    },
+    {
+      "epoch": 1.1564444444444444,
+      "grad_norm": 0.0037277438677847385,
+      "learning_rate": 7.824684219978591e-06,
+      "loss": 0.4917220175266266,
+      "step": 82
+    },
+    {
+      "epoch": 1.1706666666666667,
+      "grad_norm": 0.0034888957161456347,
+      "learning_rate": 7.756445627110523e-06,
+      "loss": 0.5024806261062622,
+      "step": 83
+    },
+    {
+      "epoch": 1.1848888888888889,
+      "grad_norm": 0.004098390229046345,
+      "learning_rate": 7.68746131963598e-06,
+      "loss": 0.5110447406768799,
+      "step": 84
+    },
+    {
+      "epoch": 1.199111111111111,
+      "grad_norm": 0.0036922753788530827,
+      "learning_rate": 7.6177499602143e-06,
+      "loss": 0.5031975507736206,
+      "step": 85
+    },
+    {
+      "epoch": 1.2133333333333334,
+      "grad_norm": 0.0035749904345721006,
+      "learning_rate": 7.547330408197695e-06,
+      "loss": 0.4899296164512634,
+      "step": 86
+    },
+    {
+      "epoch": 1.2275555555555555,
+      "grad_norm": 0.003764625173062086,
+      "learning_rate": 7.476221714529167e-06,
+      "loss": 0.5040560960769653,
+      "step": 87
+    },
+    {
+      "epoch": 1.2417777777777779,
+      "grad_norm": 0.003831087611615658,
+      "learning_rate": 7.404443116588548e-06,
+      "loss": 0.5307536125183105,
+      "step": 88
+    },
+    {
+      "epoch": 1.256,
+      "grad_norm": 0.003740105777978897,
+      "learning_rate": 7.332014032988123e-06,
+      "loss": 0.5025057792663574,
+      "step": 89
+    },
+    {
+      "epoch": 1.2702222222222221,
+      "grad_norm": 0.0038286929484456778,
+      "learning_rate": 7.2589540583192165e-06,
+      "loss": 0.5043497085571289,
+      "step": 90
+    },
+    {
+      "epoch": 1.2844444444444445,
+      "grad_norm": 0.003593199420720339,
+      "learning_rate": 7.185282957851175e-06,
+      "loss": 0.4883122444152832,
+      "step": 91
+    },
+    {
+      "epoch": 1.2986666666666666,
+      "grad_norm": 0.003721701679751277,
+      "learning_rate": 7.111020662184174e-06,
+      "loss": 0.5055882930755615,
+      "step": 92
+    },
+    {
+      "epoch": 1.3128888888888888,
+      "grad_norm": 0.0036744684912264347,
+      "learning_rate": 7.036187261857289e-06,
+      "loss": 0.4962804615497589,
+      "step": 93
+    },
+    {
+      "epoch": 1.3271111111111111,
+      "grad_norm": 0.004013169556856155,
+      "learning_rate": 6.960803001913315e-06,
+      "loss": 0.524259090423584,
+      "step": 94
+    },
+    {
+      "epoch": 1.3413333333333333,
+      "grad_norm": 0.003746299771592021,
+      "learning_rate": 6.884888276421766e-06,
+      "loss": 0.5073269009590149,
+      "step": 95
+    },
+    {
+      "epoch": 1.3555555555555556,
+      "grad_norm": 0.0036679194308817387,
+      "learning_rate": 6.8084636229615786e-06,
+      "loss": 0.4886914789676666,
+      "step": 96
+    },
+    {
+      "epoch": 1.3697777777777778,
+      "grad_norm": 0.00375540042296052,
+      "learning_rate": 6.731549717064975e-06,
+      "loss": 0.4920746088027954,
+      "step": 97
+    },
+    {
+      "epoch": 1.384,
+      "grad_norm": 0.003901587100699544,
+      "learning_rate": 6.654167366624009e-06,
+      "loss": 0.503207266330719,
+      "step": 98
+    },
+    {
+      "epoch": 1.3982222222222223,
+      "grad_norm": 0.003911704756319523,
+      "learning_rate": 6.576337506261314e-06,
+      "loss": 0.5012996196746826,
+      "step": 99
+    },
+    {
+      "epoch": 1.4124444444444444,
+      "grad_norm": 0.0035876361653208733,
+      "learning_rate": 6.498081191666549e-06,
+      "loss": 0.5059630274772644,
+      "step": 100
+    },
+    {
+      "epoch": 1.4124444444444444,
+      "eval_loss": 0.5291631817817688,
+      "eval_runtime": 10.3556,
+      "eval_samples_per_second": 19.313,
+      "eval_steps_per_second": 9.657,
+      "step": 100
+    },
+    {
+      "epoch": 1.4266666666666667,
+      "grad_norm": 0.003729900810867548,
+      "learning_rate": 6.419419593900109e-06,
+      "loss": 0.4896056056022644,
+      "step": 101
+    },
+    {
+      "epoch": 1.4408888888888889,
+      "grad_norm": 0.003648703685030341,
+      "learning_rate": 6.340373993665607e-06,
+      "loss": 0.48181772232055664,
+      "step": 102
+    },
+    {
+      "epoch": 1.455111111111111,
+      "grad_norm": 0.0035914399195462465,
+      "learning_rate": 6.2609657755527135e-06,
+      "loss": 0.4775124192237854,
+      "step": 103
+    },
+    {
+      "epoch": 1.4693333333333334,
+      "grad_norm": 0.0035880866926163435,
+      "learning_rate": 6.1812164222518626e-06,
+      "loss": 0.5167958736419678,
+      "step": 104
+    },
+    {
+      "epoch": 1.4835555555555555,
+      "grad_norm": 0.003788268193602562,
+      "learning_rate": 6.101147508742456e-06,
+      "loss": 0.4946171045303345,
+      "step": 105
+    },
+    {
+      "epoch": 1.4977777777777779,
+      "grad_norm": 0.0036002870183438063,
+      "learning_rate": 6.020780696456059e-06,
+      "loss": 0.4849076569080353,
+      "step": 106
+    },
+    {
+      "epoch": 1.512,
+      "grad_norm": 0.0036388293374329805,
+      "learning_rate": 5.940137727416247e-06,
+      "loss": 0.4958712160587311,
+      "step": 107
+    },
+    {
+      "epoch": 1.5262222222222221,
+      "grad_norm": 0.0034927036613225937,
+      "learning_rate": 5.859240418356614e-06,
+      "loss": 0.4822971820831299,
+      "step": 108
+    },
+    {
+      "epoch": 1.5404444444444443,
+      "grad_norm": 0.0038439796771854162,
+      "learning_rate": 5.778110654818602e-06,
+      "loss": 0.5280419588088989,
+      "step": 109
+    },
+    {
+      "epoch": 1.5546666666666666,
+      "grad_norm": 0.003715698141604662,
+      "learning_rate": 5.696770385230679e-06,
+      "loss": 0.4952104687690735,
+      "step": 110
+    },
+    {
+      "epoch": 1.568888888888889,
+      "grad_norm": 0.0036385883577167988,
+      "learning_rate": 5.615241614970546e-06,
+      "loss": 0.4887908101081848,
+      "step": 111
+    },
+    {
+      "epoch": 1.5831111111111111,
+      "grad_norm": 0.0036841081455349922,
+      "learning_rate": 5.533546400411899e-06,
+      "loss": 0.4928241968154907,
+      "step": 112
+    },
+    {
+      "epoch": 1.5973333333333333,
+      "grad_norm": 0.0036721359938383102,
+      "learning_rate": 5.4517068429574215e-06,
+      "loss": 0.5109080076217651,
+      "step": 113
+    },
+    {
+      "epoch": 1.6115555555555554,
+      "grad_norm": 0.0037413975223898888,
+      "learning_rate": 5.3697450830595775e-06,
+      "loss": 0.48911499977111816,
+      "step": 114
+    },
+    {
+      "epoch": 1.6257777777777778,
+      "grad_norm": 0.003966668155044317,
+      "learning_rate": 5.287683294230855e-06,
+      "loss": 0.49537116289138794,
+      "step": 115
+    },
+    {
+      "epoch": 1.6400000000000001,
+      "grad_norm": 0.0036018763203173876,
+      "learning_rate": 5.20554367704505e-06,
+      "loss": 0.4613257348537445,
+      "step": 116
+    },
+    {
+      "epoch": 1.6542222222222223,
+      "grad_norm": 0.0038206754252314568,
+      "learning_rate": 5.123348453131242e-06,
+      "loss": 0.5043697357177734,
+      "step": 117
+    },
+    {
+      "epoch": 1.6684444444444444,
+      "grad_norm": 0.0037831810768693686,
+      "learning_rate": 5.041119859162068e-06,
+      "loss": 0.48968735337257385,
+      "step": 118
+    },
+    {
+      "epoch": 1.6826666666666665,
+      "grad_norm": 0.0038370522670447826,
+      "learning_rate": 4.958880140837934e-06,
+      "loss": 0.49605250358581543,
+      "step": 119
+    },
+    {
+      "epoch": 1.696888888888889,
+      "grad_norm": 0.003586502280086279,
+      "learning_rate": 4.876651546868759e-06,
+      "loss": 0.4839916229248047,
+      "step": 120
+    },
+    {
+      "epoch": 1.7111111111111112,
+      "grad_norm": 0.003694413462653756,
+      "learning_rate": 4.794456322954953e-06,
+      "loss": 0.5173561573028564,
+      "step": 121
+    },
+    {
+      "epoch": 1.7253333333333334,
+      "grad_norm": 0.003933500964194536,
+      "learning_rate": 4.7123167057691446e-06,
+      "loss": 0.5177811980247498,
+      "step": 122
+    },
+    {
+      "epoch": 1.7395555555555555,
+      "grad_norm": 0.0036068507470190525,
+      "learning_rate": 4.630254916940424e-06,
+      "loss": 0.5164836049079895,
+      "step": 123
+    },
+    {
+      "epoch": 1.7537777777777777,
+      "grad_norm": 0.00349752651527524,
+      "learning_rate": 4.548293157042581e-06,
+      "loss": 0.5077825784683228,
+      "step": 124
+    },
+    {
+      "epoch": 1.768,
+      "grad_norm": 0.0037042393814772367,
+      "learning_rate": 4.466453599588103e-06,
+      "loss": 0.5107009410858154,
+      "step": 125
+    },
+    {
+      "epoch": 1.7822222222222224,
+      "grad_norm": 0.003853494767099619,
+      "learning_rate": 4.384758385029457e-06,
+      "loss": 0.4728143811225891,
+      "step": 126
+    },
+    {
+      "epoch": 1.7964444444444445,
+      "grad_norm": 0.0038627111352980137,
+      "learning_rate": 4.3032296147693225e-06,
+      "loss": 0.4858134984970093,
+      "step": 127
+    },
+    {
+      "epoch": 1.8106666666666666,
+      "grad_norm": 0.003657885594293475,
+      "learning_rate": 4.2218893451814005e-06,
+      "loss": 0.48357316851615906,
+      "step": 128
+    },
+    {
+      "epoch": 1.8248888888888888,
+      "grad_norm": 0.00355988135561347,
+      "learning_rate": 4.140759581643386e-06,
+      "loss": 0.49349913001060486,
+      "step": 129
+    },
+    {
+      "epoch": 1.8391111111111111,
+      "grad_norm": 0.004014762118458748,
+      "learning_rate": 4.059862272583755e-06,
+      "loss": 0.4969041347503662,
+      "step": 130
+    },
+    {
+      "epoch": 1.8533333333333335,
+      "grad_norm": 0.003631556173786521,
+      "learning_rate": 3.979219303543942e-06,
+      "loss": 0.47194504737854004,
+      "step": 131
+    },
+    {
+      "epoch": 1.8675555555555556,
+      "grad_norm": 0.003577238181605935,
+      "learning_rate": 3.898852491257547e-06,
+      "loss": 0.5020972490310669,
+      "step": 132
+    },
+    {
+      "epoch": 1.8817777777777778,
+      "grad_norm": 0.003780671861022711,
+      "learning_rate": 3.818783577748138e-06,
+      "loss": 0.5002884268760681,
+      "step": 133
+    },
+    {
+      "epoch": 1.896,
+      "grad_norm": 0.003708280622959137,
+      "learning_rate": 3.7390342244472886e-06,
+      "loss": 0.5007095336914062,
+      "step": 134
+    },
+    {
+      "epoch": 1.9102222222222223,
+      "grad_norm": 0.003498840844258666,
+      "learning_rate": 3.659626006334395e-06,
+      "loss": 0.4763813316822052,
+      "step": 135
+    },
+    {
+      "epoch": 1.9244444444444444,
+      "grad_norm": 0.003659547306597233,
+      "learning_rate": 3.5805804060998926e-06,
+      "loss": 0.48733818531036377,
+      "step": 136
+    },
+    {
+      "epoch": 1.9386666666666668,
+      "grad_norm": 0.003515617921948433,
+      "learning_rate": 3.501918808333453e-06,
+      "loss": 0.5118749141693115,
+      "step": 137
+    },
+    {
+      "epoch": 1.952888888888889,
+      "grad_norm": 0.0036544103641062975,
+      "learning_rate": 3.4236624937386874e-06,
+      "loss": 0.5178316831588745,
+      "step": 138
+    },
+    {
+      "epoch": 1.967111111111111,
+      "grad_norm": 0.003433604259043932,
+      "learning_rate": 3.3458326333759927e-06,
+      "loss": 0.4853537678718567,
+      "step": 139
+    },
+    {
+      "epoch": 1.9813333333333332,
+      "grad_norm": 0.003547502215951681,
+      "learning_rate": 3.268450282935026e-06,
+      "loss": 0.49210506677627563,
+      "step": 140
+    },
+    {
+      "epoch": 1.9955555555555555,
+      "grad_norm": 0.003462104359641671,
+      "learning_rate": 3.1915363770384223e-06,
+      "loss": 0.47841814160346985,
+      "step": 141
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.005856912117451429,
+      "learning_rate": 3.1151117235782346e-06,
+      "loss": 0.5034412145614624,
+      "step": 142
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 213,
+  "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": 1.648495698116608e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

qwen2.5-1.5b-instruct/checkpoint-142/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39e78c30a5784e935e65cb8fa1a73b2afb467afccc55e7223863b667252fac3b
+size 5649

qwen2.5-1.5b-instruct/checkpoint-213/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

qwen2.5-1.5b-instruct/checkpoint-213/config.json

@@ -0,0 +1,61 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "dtype": "float32",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 1000000.0,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.2.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

qwen2.5-1.5b-instruct/checkpoint-213/generation_config.json

@@ -0,0 +1,13 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "5.2.0"
+}

qwen2.5-1.5b-instruct/checkpoint-213/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f14867d928257934392dd2a17c62080e0613e998d7c4e10eba82a99bef35153
+size 6174895536

qwen2.5-1.5b-instruct/checkpoint-213/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47247bfc837aa5754be918243d2bc8ffb68d36278fb0e061bfc4345e106d04b1
+size 12350013801

qwen2.5-1.5b-instruct/checkpoint-213/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95e5fc2074c0df31522a514f862c86cb00d71c946a7f15cc9ec0e53a69fb28a7
+size 14917

qwen2.5-1.5b-instruct/checkpoint-213/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e7153eae67b6c9232a41bc996a2bf5b83229b8c7230d61911ac0fd40e64154e
+size 14917

qwen2.5-1.5b-instruct/checkpoint-213/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c38a67b98c17be81d4c6d00b60029cdedd43e9aba35ca28ec28ef946c400f268
+size 1465

qwen2.5-1.5b-instruct/checkpoint-213/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
+size 11421892

qwen2.5-1.5b-instruct/checkpoint-213/tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

qwen2.5-1.5b-instruct/checkpoint-213/trainer_state.json

@@ -0,0 +1,1557 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 50,
+  "global_step": 213,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.014222222222222223,
+      "grad_norm": 0.03586147725582123,
+      "learning_rate": 0.0,
+      "loss": 0.9098724722862244,
+      "step": 1
+    },
+    {
+      "epoch": 0.028444444444444446,
+      "grad_norm": 0.03577122464776039,
+      "learning_rate": 4.5454545454545457e-07,
+      "loss": 0.9084522724151611,
+      "step": 2
+    },
+    {
+      "epoch": 0.042666666666666665,
+      "grad_norm": 0.031653374433517456,
+      "learning_rate": 9.090909090909091e-07,
+      "loss": 0.8834755420684814,
+      "step": 3
+    },
+    {
+      "epoch": 0.05688888888888889,
+      "grad_norm": 0.025831686332821846,
+      "learning_rate": 1.3636363636363636e-06,
+      "loss": 0.871230959892273,
+      "step": 4
+    },
+    {
+      "epoch": 0.07111111111111111,
+      "grad_norm": 0.019876576960086823,
+      "learning_rate": 1.8181818181818183e-06,
+      "loss": 0.7917206287384033,
+      "step": 5
+    },
+    {
+      "epoch": 0.08533333333333333,
+      "grad_norm": 0.018677273765206337,
+      "learning_rate": 2.2727272727272728e-06,
+      "loss": 0.8436126708984375,
+      "step": 6
+    },
+    {
+      "epoch": 0.09955555555555555,
+      "grad_norm": 0.017528358846902847,
+      "learning_rate": 2.7272727272727272e-06,
+      "loss": 0.8075190782546997,
+      "step": 7
+    },
+    {
+      "epoch": 0.11377777777777778,
+      "grad_norm": 0.01399513240903616,
+      "learning_rate": 3.181818181818182e-06,
+      "loss": 0.7754716873168945,
+      "step": 8
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 0.012644859962165356,
+      "learning_rate": 3.6363636363636366e-06,
+      "loss": 0.7459083199501038,
+      "step": 9
+    },
+    {
+      "epoch": 0.14222222222222222,
+      "grad_norm": 0.01209743320941925,
+      "learning_rate": 4.0909090909090915e-06,
+      "loss": 0.7365868091583252,
+      "step": 10
+    },
+    {
+      "epoch": 0.15644444444444444,
+      "grad_norm": 0.012133832089602947,
+      "learning_rate": 4.5454545454545455e-06,
+      "loss": 0.7119501829147339,
+      "step": 11
+    },
+    {
+      "epoch": 0.17066666666666666,
+      "grad_norm": 0.010017997585237026,
+      "learning_rate": 5e-06,
+      "loss": 0.6901087760925293,
+      "step": 12
+    },
+    {
+      "epoch": 0.18488888888888888,
+      "grad_norm": 0.009233366698026657,
+      "learning_rate": 5.4545454545454545e-06,
+      "loss": 0.6611638069152832,
+      "step": 13
+    },
+    {
+      "epoch": 0.1991111111111111,
+      "grad_norm": 0.00782010331749916,
+      "learning_rate": 5.90909090909091e-06,
+      "loss": 0.6715224981307983,
+      "step": 14
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 0.007341764867305756,
+      "learning_rate": 6.363636363636364e-06,
+      "loss": 0.6277110576629639,
+      "step": 15
+    },
+    {
+      "epoch": 0.22755555555555557,
+      "grad_norm": 0.00713470159098506,
+      "learning_rate": 6.818181818181818e-06,
+      "loss": 0.6689565181732178,
+      "step": 16
+    },
+    {
+      "epoch": 0.24177777777777779,
+      "grad_norm": 0.0067572277039289474,
+      "learning_rate": 7.272727272727273e-06,
+      "loss": 0.6363875865936279,
+      "step": 17
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 0.006228511221706867,
+      "learning_rate": 7.727272727272727e-06,
+      "loss": 0.6257224678993225,
+      "step": 18
+    },
+    {
+      "epoch": 0.2702222222222222,
+      "grad_norm": 0.006048806011676788,
+      "learning_rate": 8.181818181818183e-06,
+      "loss": 0.6355900764465332,
+      "step": 19
+    },
+    {
+      "epoch": 0.28444444444444444,
+      "grad_norm": 0.005988306365907192,
+      "learning_rate": 8.636363636363637e-06,
+      "loss": 0.6338369846343994,
+      "step": 20
+    },
+    {
+      "epoch": 0.2986666666666667,
+      "grad_norm": 0.005441761109977961,
+      "learning_rate": 9.090909090909091e-06,
+      "loss": 0.6133573055267334,
+      "step": 21
+    },
+    {
+      "epoch": 0.3128888888888889,
+      "grad_norm": 0.005174445919692516,
+      "learning_rate": 9.545454545454547e-06,
+      "loss": 0.6042410135269165,
+      "step": 22
+    },
+    {
+      "epoch": 0.32711111111111113,
+      "grad_norm": 0.005199746694415808,
+      "learning_rate": 1e-05,
+      "loss": 0.602219820022583,
+      "step": 23
+    },
+    {
+      "epoch": 0.3413333333333333,
+      "grad_norm": 0.005485028959810734,
+      "learning_rate": 9.999323662872998e-06,
+      "loss": 0.6062123775482178,
+      "step": 24
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 0.004896003287285566,
+      "learning_rate": 9.99729483446475e-06,
+      "loss": 0.6077945232391357,
+      "step": 25
+    },
+    {
+      "epoch": 0.36977777777777776,
+      "grad_norm": 0.00495151337236166,
+      "learning_rate": 9.993914063644053e-06,
+      "loss": 0.5923135280609131,
+      "step": 26
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 0.004744194447994232,
+      "learning_rate": 9.989182265027232e-06,
+      "loss": 0.5860621929168701,
+      "step": 27
+    },
+    {
+      "epoch": 0.3982222222222222,
+      "grad_norm": 0.004471767693758011,
+      "learning_rate": 9.98310071873072e-06,
+      "loss": 0.5823097229003906,
+      "step": 28
+    },
+    {
+      "epoch": 0.41244444444444445,
+      "grad_norm": 0.004788320977240801,
+      "learning_rate": 9.975671070024741e-06,
+      "loss": 0.5872600078582764,
+      "step": 29
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 0.0044632842764258385,
+      "learning_rate": 9.966895328888195e-06,
+      "loss": 0.6070278286933899,
+      "step": 30
+    },
+    {
+      "epoch": 0.4408888888888889,
+      "grad_norm": 0.004317905753850937,
+      "learning_rate": 9.956775869464901e-06,
+      "loss": 0.5780316591262817,
+      "step": 31
+    },
+    {
+      "epoch": 0.45511111111111113,
+      "grad_norm": 0.004291852004826069,
+      "learning_rate": 9.945315429421307e-06,
+      "loss": 0.5697590112686157,
+      "step": 32
+    },
+    {
+      "epoch": 0.4693333333333333,
+      "grad_norm": 0.003922830801457167,
+      "learning_rate": 9.932517109205849e-06,
+      "loss": 0.5747107267379761,
+      "step": 33
+    },
+    {
+      "epoch": 0.48355555555555557,
+      "grad_norm": 0.0041889771819114685,
+      "learning_rate": 9.918384371210178e-06,
+      "loss": 0.6021177172660828,
+      "step": 34
+    },
+    {
+      "epoch": 0.49777777777777776,
+      "grad_norm": 0.004147357773035765,
+      "learning_rate": 9.902921038832456e-06,
+      "loss": 0.5805741548538208,
+      "step": 35
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 0.0040724254213273525,
+      "learning_rate": 9.886131295443003e-06,
+      "loss": 0.5483200550079346,
+      "step": 36
+    },
+    {
+      "epoch": 0.5262222222222223,
+      "grad_norm": 0.004085644613951445,
+      "learning_rate": 9.868019683252543e-06,
+      "loss": 0.557392954826355,
+      "step": 37
+    },
+    {
+      "epoch": 0.5404444444444444,
+      "grad_norm": 0.004289102274924517,
+      "learning_rate": 9.848591102083375e-06,
+      "loss": 0.590857207775116,
+      "step": 38
+    },
+    {
+      "epoch": 0.5546666666666666,
+      "grad_norm": 0.0040345704182982445,
+      "learning_rate": 9.82785080804381e-06,
+      "loss": 0.5750541090965271,
+      "step": 39
+    },
+    {
+      "epoch": 0.5688888888888889,
+      "grad_norm": 0.004034748766571283,
+      "learning_rate": 9.805804412106197e-06,
+      "loss": 0.5949826240539551,
+      "step": 40
+    },
+    {
+      "epoch": 0.5831111111111111,
+      "grad_norm": 0.003911909181624651,
+      "learning_rate": 9.782457878588977e-06,
+      "loss": 0.5623177289962769,
+      "step": 41
+    },
+    {
+      "epoch": 0.5973333333333334,
+      "grad_norm": 0.0037001846358180046,
+      "learning_rate": 9.75781752354311e-06,
+      "loss": 0.5465081930160522,
+      "step": 42
+    },
+    {
+      "epoch": 0.6115555555555555,
+      "grad_norm": 0.0037095139268785715,
+      "learning_rate": 9.731890013043367e-06,
+      "loss": 0.5752100944519043,
+      "step": 43
+    },
+    {
+      "epoch": 0.6257777777777778,
+      "grad_norm": 0.003655617358162999,
+      "learning_rate": 9.704682361384941e-06,
+      "loss": 0.5452020168304443,
+      "step": 44
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.003784338477998972,
+      "learning_rate": 9.676201929185809e-06,
+      "loss": 0.5616332292556763,
+      "step": 45
+    },
+    {
+      "epoch": 0.6542222222222223,
+      "grad_norm": 0.003718078136444092,
+      "learning_rate": 9.646456421395447e-06,
+      "loss": 0.5558297634124756,
+      "step": 46
+    },
+    {
+      "epoch": 0.6684444444444444,
+      "grad_norm": 0.00395169947296381,
+      "learning_rate": 9.615453885210368e-06,
+      "loss": 0.5600595474243164,
+      "step": 47
+    },
+    {
+      "epoch": 0.6826666666666666,
+      "grad_norm": 0.003555440343916416,
+      "learning_rate": 9.583202707897075e-06,
+      "loss": 0.5372895002365112,
+      "step": 48
+    },
+    {
+      "epoch": 0.6968888888888889,
+      "grad_norm": 0.0037386869080364704,
+      "learning_rate": 9.549711614523007e-06,
+      "loss": 0.5322733521461487,
+      "step": 49
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 0.003739988896995783,
+      "learning_rate": 9.514989665596114e-06,
+      "loss": 0.5380419492721558,
+      "step": 50
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "eval_loss": 0.5587145090103149,
+      "eval_runtime": 8.7676,
+      "eval_samples_per_second": 22.811,
+      "eval_steps_per_second": 11.406,
+      "step": 50
+    },
+    {
+      "epoch": 0.7253333333333334,
+      "grad_norm": 0.0037539806216955185,
+      "learning_rate": 9.479046254613673e-06,
+      "loss": 0.5472225546836853,
+      "step": 51
+    },
+    {
+      "epoch": 0.7395555555555555,
+      "grad_norm": 0.003411181503906846,
+      "learning_rate": 9.441891105521005e-06,
+      "loss": 0.5134032964706421,
+      "step": 52
+    },
+    {
+      "epoch": 0.7537777777777778,
+      "grad_norm": 0.0037538670003414154,
+      "learning_rate": 9.40353427008083e-06,
+      "loss": 0.5361013412475586,
+      "step": 53
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 0.0036495670210570097,
+      "learning_rate": 9.3639861251539e-06,
+      "loss": 0.5299779772758484,
+      "step": 54
+    },
+    {
+      "epoch": 0.7822222222222223,
+      "grad_norm": 0.0037342547439038754,
+      "learning_rate": 9.323257369891702e-06,
+      "loss": 0.5607945919036865,
+      "step": 55
+    },
+    {
+      "epoch": 0.7964444444444444,
+      "grad_norm": 0.003572584595531225,
+      "learning_rate": 9.281359022841966e-06,
+      "loss": 0.5528460741043091,
+      "step": 56
+    },
+    {
+      "epoch": 0.8106666666666666,
+      "grad_norm": 0.003770101349800825,
+      "learning_rate": 9.238302418967757e-06,
+      "loss": 0.5440288186073303,
+      "step": 57
+    },
+    {
+      "epoch": 0.8248888888888889,
+      "grad_norm": 0.0036679303739219904,
+      "learning_rate": 9.194099206580981e-06,
+      "loss": 0.5564252138137817,
+      "step": 58
+    },
+    {
+      "epoch": 0.8391111111111111,
+      "grad_norm": 0.003834612900391221,
+      "learning_rate": 9.14876134419111e-06,
+      "loss": 0.5473330020904541,
+      "step": 59
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 0.003683249931782484,
+      "learning_rate": 9.102301097269974e-06,
+      "loss": 0.5463743209838867,
+      "step": 60
+    },
+    {
+      "epoch": 0.8675555555555555,
+      "grad_norm": 0.0036777963396161795,
+      "learning_rate": 9.05473103493355e-06,
+      "loss": 0.524878740310669,
+      "step": 61
+    },
+    {
+      "epoch": 0.8817777777777778,
+      "grad_norm": 0.0038230482023209333,
+      "learning_rate": 9.006064026541549e-06,
+      "loss": 0.5563522577285767,
+      "step": 62
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 0.003645201213657856,
+      "learning_rate": 8.956313238215824e-06,
+      "loss": 0.5059154033660889,
+      "step": 63
+    },
+    {
+      "epoch": 0.9102222222222223,
+      "grad_norm": 0.0035886459518224,
+      "learning_rate": 8.905492129278478e-06,
+      "loss": 0.5312881469726562,
+      "step": 64
+    },
+    {
+      "epoch": 0.9244444444444444,
+      "grad_norm": 0.003721872577443719,
+      "learning_rate": 8.85361444861063e-06,
+      "loss": 0.5358959436416626,
+      "step": 65
+    },
+    {
+      "epoch": 0.9386666666666666,
+      "grad_norm": 0.003683999879285693,
+      "learning_rate": 8.800694230932885e-06,
+      "loss": 0.5442053079605103,
+      "step": 66
+    },
+    {
+      "epoch": 0.9528888888888889,
+      "grad_norm": 0.0036851842887699604,
+      "learning_rate": 8.74674579300843e-06,
+      "loss": 0.5263723731040955,
+      "step": 67
+    },
+    {
+      "epoch": 0.9671111111111111,
+      "grad_norm": 0.003754258854314685,
+      "learning_rate": 8.691783729769874e-06,
+      "loss": 0.5200538039207458,
+      "step": 68
+    },
+    {
+      "epoch": 0.9813333333333333,
+      "grad_norm": 0.0038373274728655815,
+      "learning_rate": 8.635822910370793e-06,
+      "loss": 0.5452108383178711,
+      "step": 69
+    },
+    {
+      "epoch": 0.9955555555555555,
+      "grad_norm": 0.0039480882696807384,
+      "learning_rate": 8.578878474163115e-06,
+      "loss": 0.5066030621528625,
+      "step": 70
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.005897017661482096,
+      "learning_rate": 8.520965826601394e-06,
+      "loss": 0.5380499958992004,
+      "step": 71
+    },
+    {
+      "epoch": 1.0142222222222221,
+      "grad_norm": 0.0037728557363152504,
+      "learning_rate": 8.462100635075097e-06,
+      "loss": 0.5328541398048401,
+      "step": 72
+    },
+    {
+      "epoch": 1.0284444444444445,
+      "grad_norm": 0.003953218925744295,
+      "learning_rate": 8.40229882467003e-06,
+      "loss": 0.5096005201339722,
+      "step": 73
+    },
+    {
+      "epoch": 1.0426666666666666,
+      "grad_norm": 0.0036587677896022797,
+      "learning_rate": 8.341576573860049e-06,
+      "loss": 0.4889724850654602,
+      "step": 74
+    },
+    {
+      "epoch": 1.056888888888889,
+      "grad_norm": 0.0038338187150657177,
+      "learning_rate": 8.279950310130218e-06,
+      "loss": 0.5157173871994019,
+      "step": 75
+    },
+    {
+      "epoch": 1.0711111111111111,
+      "grad_norm": 0.003540106350556016,
+      "learning_rate": 8.2174367055326e-06,
+      "loss": 0.49691659212112427,
+      "step": 76
+    },
+    {
+      "epoch": 1.0853333333333333,
+      "grad_norm": 0.0037315969821065664,
+      "learning_rate": 8.154052672175888e-06,
+      "loss": 0.4873769283294678,
+      "step": 77
+    },
+    {
+      "epoch": 1.0995555555555556,
+      "grad_norm": 0.003963674418628216,
+      "learning_rate": 8.08981535765009e-06,
+      "loss": 0.5266215801239014,
+      "step": 78
+    },
+    {
+      "epoch": 1.1137777777777778,
+      "grad_norm": 0.0037685995921492577,
+      "learning_rate": 8.024742140387506e-06,
+      "loss": 0.5039150714874268,
+      "step": 79
+    },
+    {
+      "epoch": 1.1280000000000001,
+      "grad_norm": 0.003613364417105913,
+      "learning_rate": 7.95885062496126e-06,
+      "loss": 0.4896891117095947,
+      "step": 80
+    },
+    {
+      "epoch": 1.1422222222222222,
+      "grad_norm": 0.0037347134202718735,
+      "learning_rate": 7.892158637322647e-06,
+      "loss": 0.45997822284698486,
+      "step": 81
+    },
+    {
+      "epoch": 1.1564444444444444,
+      "grad_norm": 0.0037277438677847385,
+      "learning_rate": 7.824684219978591e-06,
+      "loss": 0.4917220175266266,
+      "step": 82
+    },
+    {
+      "epoch": 1.1706666666666667,
+      "grad_norm": 0.0034888957161456347,
+      "learning_rate": 7.756445627110523e-06,
+      "loss": 0.5024806261062622,
+      "step": 83
+    },
+    {
+      "epoch": 1.1848888888888889,
+      "grad_norm": 0.004098390229046345,
+      "learning_rate": 7.68746131963598e-06,
+      "loss": 0.5110447406768799,
+      "step": 84
+    },
+    {
+      "epoch": 1.199111111111111,
+      "grad_norm": 0.0036922753788530827,
+      "learning_rate": 7.6177499602143e-06,
+      "loss": 0.5031975507736206,
+      "step": 85
+    },
+    {
+      "epoch": 1.2133333333333334,
+      "grad_norm": 0.0035749904345721006,
+      "learning_rate": 7.547330408197695e-06,
+      "loss": 0.4899296164512634,
+      "step": 86
+    },
+    {
+      "epoch": 1.2275555555555555,
+      "grad_norm": 0.003764625173062086,
+      "learning_rate": 7.476221714529167e-06,
+      "loss": 0.5040560960769653,
+      "step": 87
+    },
+    {
+      "epoch": 1.2417777777777779,
+      "grad_norm": 0.003831087611615658,
+      "learning_rate": 7.404443116588548e-06,
+      "loss": 0.5307536125183105,
+      "step": 88
+    },
+    {
+      "epoch": 1.256,
+      "grad_norm": 0.003740105777978897,
+      "learning_rate": 7.332014032988123e-06,
+      "loss": 0.5025057792663574,
+      "step": 89
+    },
+    {
+      "epoch": 1.2702222222222221,
+      "grad_norm": 0.0038286929484456778,
+      "learning_rate": 7.2589540583192165e-06,
+      "loss": 0.5043497085571289,
+      "step": 90
+    },
+    {
+      "epoch": 1.2844444444444445,
+      "grad_norm": 0.003593199420720339,
+      "learning_rate": 7.185282957851175e-06,
+      "loss": 0.4883122444152832,
+      "step": 91
+    },
+    {
+      "epoch": 1.2986666666666666,
+      "grad_norm": 0.003721701679751277,
+      "learning_rate": 7.111020662184174e-06,
+      "loss": 0.5055882930755615,
+      "step": 92
+    },
+    {
+      "epoch": 1.3128888888888888,
+      "grad_norm": 0.0036744684912264347,
+      "learning_rate": 7.036187261857289e-06,
+      "loss": 0.4962804615497589,
+      "step": 93
+    },
+    {
+      "epoch": 1.3271111111111111,
+      "grad_norm": 0.004013169556856155,
+      "learning_rate": 6.960803001913315e-06,
+      "loss": 0.524259090423584,
+      "step": 94
+    },
+    {
+      "epoch": 1.3413333333333333,
+      "grad_norm": 0.003746299771592021,
+      "learning_rate": 6.884888276421766e-06,
+      "loss": 0.5073269009590149,
+      "step": 95
+    },
+    {
+      "epoch": 1.3555555555555556,
+      "grad_norm": 0.0036679194308817387,
+      "learning_rate": 6.8084636229615786e-06,
+      "loss": 0.4886914789676666,
+      "step": 96
+    },
+    {
+      "epoch": 1.3697777777777778,
+      "grad_norm": 0.00375540042296052,
+      "learning_rate": 6.731549717064975e-06,
+      "loss": 0.4920746088027954,
+      "step": 97
+    },
+    {
+      "epoch": 1.384,
+      "grad_norm": 0.003901587100699544,
+      "learning_rate": 6.654167366624009e-06,
+      "loss": 0.503207266330719,
+      "step": 98
+    },
+    {
+      "epoch": 1.3982222222222223,
+      "grad_norm": 0.003911704756319523,
+      "learning_rate": 6.576337506261314e-06,
+      "loss": 0.5012996196746826,
+      "step": 99
+    },
+    {
+      "epoch": 1.4124444444444444,
+      "grad_norm": 0.0035876361653208733,
+      "learning_rate": 6.498081191666549e-06,
+      "loss": 0.5059630274772644,
+      "step": 100
+    },
+    {
+      "epoch": 1.4124444444444444,
+      "eval_loss": 0.5291631817817688,
+      "eval_runtime": 10.3556,
+      "eval_samples_per_second": 19.313,
+      "eval_steps_per_second": 9.657,
+      "step": 100
+    },
+    {
+      "epoch": 1.4266666666666667,
+      "grad_norm": 0.003729900810867548,
+      "learning_rate": 6.419419593900109e-06,
+      "loss": 0.4896056056022644,
+      "step": 101
+    },
+    {
+      "epoch": 1.4408888888888889,
+      "grad_norm": 0.003648703685030341,
+      "learning_rate": 6.340373993665607e-06,
+      "loss": 0.48181772232055664,
+      "step": 102
+    },
+    {
+      "epoch": 1.455111111111111,
+      "grad_norm": 0.0035914399195462465,
+      "learning_rate": 6.2609657755527135e-06,
+      "loss": 0.4775124192237854,
+      "step": 103
+    },
+    {
+      "epoch": 1.4693333333333334,
+      "grad_norm": 0.0035880866926163435,
+      "learning_rate": 6.1812164222518626e-06,
+      "loss": 0.5167958736419678,
+      "step": 104
+    },
+    {
+      "epoch": 1.4835555555555555,
+      "grad_norm": 0.003788268193602562,
+      "learning_rate": 6.101147508742456e-06,
+      "loss": 0.4946171045303345,
+      "step": 105
+    },
+    {
+      "epoch": 1.4977777777777779,
+      "grad_norm": 0.0036002870183438063,
+      "learning_rate": 6.020780696456059e-06,
+      "loss": 0.4849076569080353,
+      "step": 106
+    },
+    {
+      "epoch": 1.512,
+      "grad_norm": 0.0036388293374329805,
+      "learning_rate": 5.940137727416247e-06,
+      "loss": 0.4958712160587311,
+      "step": 107
+    },
+    {
+      "epoch": 1.5262222222222221,
+      "grad_norm": 0.0034927036613225937,
+      "learning_rate": 5.859240418356614e-06,
+      "loss": 0.4822971820831299,
+      "step": 108
+    },
+    {
+      "epoch": 1.5404444444444443,
+      "grad_norm": 0.0038439796771854162,
+      "learning_rate": 5.778110654818602e-06,
+      "loss": 0.5280419588088989,
+      "step": 109
+    },
+    {
+      "epoch": 1.5546666666666666,
+      "grad_norm": 0.003715698141604662,
+      "learning_rate": 5.696770385230679e-06,
+      "loss": 0.4952104687690735,
+      "step": 110
+    },
+    {
+      "epoch": 1.568888888888889,
+      "grad_norm": 0.0036385883577167988,
+      "learning_rate": 5.615241614970546e-06,
+      "loss": 0.4887908101081848,
+      "step": 111
+    },
+    {
+      "epoch": 1.5831111111111111,
+      "grad_norm": 0.0036841081455349922,
+      "learning_rate": 5.533546400411899e-06,
+      "loss": 0.4928241968154907,
+      "step": 112
+    },
+    {
+      "epoch": 1.5973333333333333,
+      "grad_norm": 0.0036721359938383102,
+      "learning_rate": 5.4517068429574215e-06,
+      "loss": 0.5109080076217651,
+      "step": 113
+    },
+    {
+      "epoch": 1.6115555555555554,
+      "grad_norm": 0.0037413975223898888,
+      "learning_rate": 5.3697450830595775e-06,
+      "loss": 0.48911499977111816,
+      "step": 114
+    },
+    {
+      "epoch": 1.6257777777777778,
+      "grad_norm": 0.003966668155044317,
+      "learning_rate": 5.287683294230855e-06,
+      "loss": 0.49537116289138794,
+      "step": 115
+    },
+    {
+      "epoch": 1.6400000000000001,
+      "grad_norm": 0.0036018763203173876,
+      "learning_rate": 5.20554367704505e-06,
+      "loss": 0.4613257348537445,
+      "step": 116
+    },
+    {
+      "epoch": 1.6542222222222223,
+      "grad_norm": 0.0038206754252314568,
+      "learning_rate": 5.123348453131242e-06,
+      "loss": 0.5043697357177734,
+      "step": 117
+    },
+    {
+      "epoch": 1.6684444444444444,
+      "grad_norm": 0.0037831810768693686,
+      "learning_rate": 5.041119859162068e-06,
+      "loss": 0.48968735337257385,
+      "step": 118
+    },
+    {
+      "epoch": 1.6826666666666665,
+      "grad_norm": 0.0038370522670447826,
+      "learning_rate": 4.958880140837934e-06,
+      "loss": 0.49605250358581543,
+      "step": 119
+    },
+    {
+      "epoch": 1.696888888888889,
+      "grad_norm": 0.003586502280086279,
+      "learning_rate": 4.876651546868759e-06,
+      "loss": 0.4839916229248047,
+      "step": 120
+    },
+    {
+      "epoch": 1.7111111111111112,
+      "grad_norm": 0.003694413462653756,
+      "learning_rate": 4.794456322954953e-06,
+      "loss": 0.5173561573028564,
+      "step": 121
+    },
+    {
+      "epoch": 1.7253333333333334,
+      "grad_norm": 0.003933500964194536,
+      "learning_rate": 4.7123167057691446e-06,
+      "loss": 0.5177811980247498,
+      "step": 122
+    },
+    {
+      "epoch": 1.7395555555555555,
+      "grad_norm": 0.0036068507470190525,
+      "learning_rate": 4.630254916940424e-06,
+      "loss": 0.5164836049079895,
+      "step": 123
+    },
+    {
+      "epoch": 1.7537777777777777,
+      "grad_norm": 0.00349752651527524,
+      "learning_rate": 4.548293157042581e-06,
+      "loss": 0.5077825784683228,
+      "step": 124
+    },
+    {
+      "epoch": 1.768,
+      "grad_norm": 0.0037042393814772367,
+      "learning_rate": 4.466453599588103e-06,
+      "loss": 0.5107009410858154,
+      "step": 125
+    },
+    {
+      "epoch": 1.7822222222222224,
+      "grad_norm": 0.003853494767099619,
+      "learning_rate": 4.384758385029457e-06,
+      "loss": 0.4728143811225891,
+      "step": 126
+    },
+    {
+      "epoch": 1.7964444444444445,
+      "grad_norm": 0.0038627111352980137,
+      "learning_rate": 4.3032296147693225e-06,
+      "loss": 0.4858134984970093,
+      "step": 127
+    },
+    {
+      "epoch": 1.8106666666666666,
+      "grad_norm": 0.003657885594293475,
+      "learning_rate": 4.2218893451814005e-06,
+      "loss": 0.48357316851615906,
+      "step": 128
+    },
+    {
+      "epoch": 1.8248888888888888,
+      "grad_norm": 0.00355988135561347,
+      "learning_rate": 4.140759581643386e-06,
+      "loss": 0.49349913001060486,
+      "step": 129
+    },
+    {
+      "epoch": 1.8391111111111111,
+      "grad_norm": 0.004014762118458748,
+      "learning_rate": 4.059862272583755e-06,
+      "loss": 0.4969041347503662,
+      "step": 130
+    },
+    {
+      "epoch": 1.8533333333333335,
+      "grad_norm": 0.003631556173786521,
+      "learning_rate": 3.979219303543942e-06,
+      "loss": 0.47194504737854004,
+      "step": 131
+    },
+    {
+      "epoch": 1.8675555555555556,
+      "grad_norm": 0.003577238181605935,
+      "learning_rate": 3.898852491257547e-06,
+      "loss": 0.5020972490310669,
+      "step": 132
+    },
+    {
+      "epoch": 1.8817777777777778,
+      "grad_norm": 0.003780671861022711,
+      "learning_rate": 3.818783577748138e-06,
+      "loss": 0.5002884268760681,
+      "step": 133
+    },
+    {
+      "epoch": 1.896,
+      "grad_norm": 0.003708280622959137,
+      "learning_rate": 3.7390342244472886e-06,
+      "loss": 0.5007095336914062,
+      "step": 134
+    },
+    {
+      "epoch": 1.9102222222222223,
+      "grad_norm": 0.003498840844258666,
+      "learning_rate": 3.659626006334395e-06,
+      "loss": 0.4763813316822052,
+      "step": 135
+    },
+    {
+      "epoch": 1.9244444444444444,
+      "grad_norm": 0.003659547306597233,
+      "learning_rate": 3.5805804060998926e-06,
+      "loss": 0.48733818531036377,
+      "step": 136
+    },
+    {
+      "epoch": 1.9386666666666668,
+      "grad_norm": 0.003515617921948433,
+      "learning_rate": 3.501918808333453e-06,
+      "loss": 0.5118749141693115,
+      "step": 137
+    },
+    {
+      "epoch": 1.952888888888889,
+      "grad_norm": 0.0036544103641062975,
+      "learning_rate": 3.4236624937386874e-06,
+      "loss": 0.5178316831588745,
+      "step": 138
+    },
+    {
+      "epoch": 1.967111111111111,
+      "grad_norm": 0.003433604259043932,
+      "learning_rate": 3.3458326333759927e-06,
+      "loss": 0.4853537678718567,
+      "step": 139
+    },
+    {
+      "epoch": 1.9813333333333332,
+      "grad_norm": 0.003547502215951681,
+      "learning_rate": 3.268450282935026e-06,
+      "loss": 0.49210506677627563,
+      "step": 140
+    },
+    {
+      "epoch": 1.9955555555555555,
+      "grad_norm": 0.003462104359641671,
+      "learning_rate": 3.1915363770384223e-06,
+      "loss": 0.47841814160346985,
+      "step": 141
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.005856912117451429,
+      "learning_rate": 3.1151117235782346e-06,
+      "loss": 0.5034412145614624,
+      "step": 142
+    },
+    {
+      "epoch": 2.014222222222222,
+      "grad_norm": 0.003923188429325819,
+      "learning_rate": 3.0391969980866874e-06,
+      "loss": 0.4864930808544159,
+      "step": 143
+    },
+    {
+      "epoch": 2.0284444444444443,
+      "grad_norm": 0.003596341237425804,
+      "learning_rate": 2.963812738142713e-06,
+      "loss": 0.4642598032951355,
+      "step": 144
+    },
+    {
+      "epoch": 2.042666666666667,
+      "grad_norm": 0.0038887078408151865,
+      "learning_rate": 2.8889793378158284e-06,
+      "loss": 0.48541027307510376,
+      "step": 145
+    },
+    {
+      "epoch": 2.056888888888889,
+      "grad_norm": 0.0034043709747493267,
+      "learning_rate": 2.814717042148827e-06,
+      "loss": 0.47221142053604126,
+      "step": 146
+    },
+    {
+      "epoch": 2.071111111111111,
+      "grad_norm": 0.0034274954814463854,
+      "learning_rate": 2.7410459416807856e-06,
+      "loss": 0.46124035120010376,
+      "step": 147
+    },
+    {
+      "epoch": 2.0853333333333333,
+      "grad_norm": 0.00352494022808969,
+      "learning_rate": 2.6679859670118785e-06,
+      "loss": 0.4869857430458069,
+      "step": 148
+    },
+    {
+      "epoch": 2.0995555555555554,
+      "grad_norm": 0.0035326213110238314,
+      "learning_rate": 2.5955568834114523e-06,
+      "loss": 0.45158863067626953,
+      "step": 149
+    },
+    {
+      "epoch": 2.113777777777778,
+      "grad_norm": 0.003645913675427437,
+      "learning_rate": 2.523778285470835e-06,
+      "loss": 0.4742748439311981,
+      "step": 150
+    },
+    {
+      "epoch": 2.113777777777778,
+      "eval_loss": 0.5196705460548401,
+      "eval_runtime": 15.8074,
+      "eval_samples_per_second": 12.652,
+      "eval_steps_per_second": 6.326,
+      "step": 150
+    },
+    {
+      "epoch": 2.128,
+      "grad_norm": 0.0036555698607116938,
+      "learning_rate": 2.452669591802307e-06,
+      "loss": 0.4526304602622986,
+      "step": 151
+    },
+    {
+      "epoch": 2.1422222222222222,
+      "grad_norm": 0.003359478199854493,
+      "learning_rate": 2.3822500397857016e-06,
+      "loss": 0.4651503562927246,
+      "step": 152
+    },
+    {
+      "epoch": 2.1564444444444444,
+      "grad_norm": 0.003462468506768346,
+      "learning_rate": 2.3125386803640188e-06,
+      "loss": 0.48414769768714905,
+      "step": 153
+    },
+    {
+      "epoch": 2.1706666666666665,
+      "grad_norm": 0.003318715374916792,
+      "learning_rate": 2.243554372889479e-06,
+      "loss": 0.462248295545578,
+      "step": 154
+    },
+    {
+      "epoch": 2.1848888888888887,
+      "grad_norm": 0.0034426096826791763,
+      "learning_rate": 2.1753157800214107e-06,
+      "loss": 0.4559134244918823,
+      "step": 155
+    },
+    {
+      "epoch": 2.1991111111111112,
+      "grad_norm": 0.0035529518499970436,
+      "learning_rate": 2.1078413626773547e-06,
+      "loss": 0.48357266187667847,
+      "step": 156
+    },
+    {
+      "epoch": 2.2133333333333334,
+      "grad_norm": 0.0034895483404397964,
+      "learning_rate": 2.0411493750387423e-06,
+      "loss": 0.4366765022277832,
+      "step": 157
+    },
+    {
+      "epoch": 2.2275555555555555,
+      "grad_norm": 0.003682621056213975,
+      "learning_rate": 1.9752578596124955e-06,
+      "loss": 0.4868413209915161,
+      "step": 158
+    },
+    {
+      "epoch": 2.2417777777777776,
+      "grad_norm": 0.0035529278684407473,
+      "learning_rate": 1.9101846423499113e-06,
+      "loss": 0.46049410104751587,
+      "step": 159
+    },
+    {
+      "epoch": 2.2560000000000002,
+      "grad_norm": 0.003581352299079299,
+      "learning_rate": 1.8459473278241125e-06,
+      "loss": 0.4605860412120819,
+      "step": 160
+    },
+    {
+      "epoch": 2.2702222222222224,
+      "grad_norm": 0.0033597166184335947,
+      "learning_rate": 1.7825632944674016e-06,
+      "loss": 0.46191370487213135,
+      "step": 161
+    },
+    {
+      "epoch": 2.2844444444444445,
+      "grad_norm": 0.003529531881213188,
+      "learning_rate": 1.7200496898697832e-06,
+      "loss": 0.4780347943305969,
+      "step": 162
+    },
+    {
+      "epoch": 2.2986666666666666,
+      "grad_norm": 0.0034702750854194164,
+      "learning_rate": 1.6584234261399535e-06,
+      "loss": 0.4648103713989258,
+      "step": 163
+    },
+    {
+      "epoch": 2.3128888888888888,
+      "grad_norm": 0.0036891205236315727,
+      "learning_rate": 1.5977011753299726e-06,
+      "loss": 0.46155521273612976,
+      "step": 164
+    },
+    {
+      "epoch": 2.327111111111111,
+      "grad_norm": 0.003741780063137412,
+      "learning_rate": 1.5378993649249053e-06,
+      "loss": 0.49238717555999756,
+      "step": 165
+    },
+    {
+      "epoch": 2.3413333333333335,
+      "grad_norm": 0.003572724526748061,
+      "learning_rate": 1.4790341733986085e-06,
+      "loss": 0.46214908361434937,
+      "step": 166
+    },
+    {
+      "epoch": 2.3555555555555556,
+      "grad_norm": 0.003393909428268671,
+      "learning_rate": 1.4211215258368866e-06,
+      "loss": 0.44751304388046265,
+      "step": 167
+    },
+    {
+      "epoch": 2.3697777777777778,
+      "grad_norm": 0.0035024855751544237,
+      "learning_rate": 1.3641770896292083e-06,
+      "loss": 0.4523189067840576,
+      "step": 168
+    },
+    {
+      "epoch": 2.384,
+      "grad_norm": 0.0034958638716489077,
+      "learning_rate": 1.3082162702301276e-06,
+      "loss": 0.46704721450805664,
+      "step": 169
+    },
+    {
+      "epoch": 2.398222222222222,
+      "grad_norm": 0.0035048348363488913,
+      "learning_rate": 1.2532542069915722e-06,
+      "loss": 0.47263163328170776,
+      "step": 170
+    },
+    {
+      "epoch": 2.4124444444444446,
+      "grad_norm": 0.0034445980563759804,
+      "learning_rate": 1.1993057690671174e-06,
+      "loss": 0.4592151641845703,
+      "step": 171
+    },
+    {
+      "epoch": 2.4266666666666667,
+      "grad_norm": 0.0034275518264621496,
+      "learning_rate": 1.1463855513893695e-06,
+      "loss": 0.4800827205181122,
+      "step": 172
+    },
+    {
+      "epoch": 2.440888888888889,
+      "grad_norm": 0.0034792288206517696,
+      "learning_rate": 1.0945078707215224e-06,
+      "loss": 0.4688478112220764,
+      "step": 173
+    },
+    {
+      "epoch": 2.455111111111111,
+      "grad_norm": 0.0035636303946375847,
+      "learning_rate": 1.0436867617841768e-06,
+      "loss": 0.46817073225975037,
+      "step": 174
+    },
+    {
+      "epoch": 2.469333333333333,
+      "grad_norm": 0.0033977399580180645,
+      "learning_rate": 9.939359734584552e-07,
+      "loss": 0.4763898253440857,
+      "step": 175
+    },
+    {
+      "epoch": 2.4835555555555557,
+      "grad_norm": 0.003528163768351078,
+      "learning_rate": 9.452689650664515e-07,
+      "loss": 0.480793833732605,
+      "step": 176
+    },
+    {
+      "epoch": 2.497777777777778,
+      "grad_norm": 0.00341871683485806,
+      "learning_rate": 8.976989027300265e-07,
+      "loss": 0.4694904088973999,
+      "step": 177
+    },
+    {
+      "epoch": 2.512,
+      "grad_norm": 0.003544109407812357,
+      "learning_rate": 8.512386558088919e-07,
+      "loss": 0.4877663254737854,
+      "step": 178
+    },
+    {
+      "epoch": 2.526222222222222,
+      "grad_norm": 0.0034784283488988876,
+      "learning_rate": 8.059007934190194e-07,
+      "loss": 0.46579453349113464,
+      "step": 179
+    },
+    {
+      "epoch": 2.5404444444444443,
+      "grad_norm": 0.003506515873596072,
+      "learning_rate": 7.61697581032243e-07,
+      "loss": 0.4954630434513092,
+      "step": 180
+    },
+    {
+      "epoch": 2.554666666666667,
+      "grad_norm": 0.003402002854272723,
+      "learning_rate": 7.186409771580355e-07,
+      "loss": 0.48210158944129944,
+      "step": 181
+    },
+    {
+      "epoch": 2.568888888888889,
+      "grad_norm": 0.003400753950700164,
+      "learning_rate": 6.76742630108298e-07,
+      "loss": 0.4673936069011688,
+      "step": 182
+    },
+    {
+      "epoch": 2.583111111111111,
+      "grad_norm": 0.0034171557053923607,
+      "learning_rate": 6.360138748461015e-07,
+      "loss": 0.46786054968833923,
+      "step": 183
+    },
+    {
+      "epoch": 2.5973333333333333,
+      "grad_norm": 0.003441787790507078,
+      "learning_rate": 5.964657299191712e-07,
+      "loss": 0.45768898725509644,
+      "step": 184
+    },
+    {
+      "epoch": 2.6115555555555554,
+      "grad_norm": 0.0034633874893188477,
+      "learning_rate": 5.581088944789953e-07,
+      "loss": 0.468585342168808,
+      "step": 185
+    },
+    {
+      "epoch": 2.6257777777777775,
+      "grad_norm": 0.0034696508664637804,
+      "learning_rate": 5.20953745386329e-07,
+      "loss": 0.4843568205833435,
+      "step": 186
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 0.003448233939707279,
+      "learning_rate": 4.850103344038853e-07,
+      "loss": 0.4747229218482971,
+      "step": 187
+    },
+    {
+      "epoch": 2.6542222222222223,
+      "grad_norm": 0.00340772676281631,
+      "learning_rate": 4.502883854769935e-07,
+      "loss": 0.44664108753204346,
+      "step": 188
+    },
+    {
+      "epoch": 2.6684444444444444,
+      "grad_norm": 0.0034893041010946035,
+      "learning_rate": 4.167972921029262e-07,
+      "loss": 0.47903192043304443,
+      "step": 189
+    },
+    {
+      "epoch": 2.6826666666666665,
+      "grad_norm": 0.003642126452177763,
+      "learning_rate": 3.8454611478963235e-07,
+      "loss": 0.4844057559967041,
+      "step": 190
+    },
+    {
+      "epoch": 2.696888888888889,
+      "grad_norm": 0.0034686627332121134,
+      "learning_rate": 3.535435786045538e-07,
+      "loss": 0.4564388394355774,
+      "step": 191
+    },
+    {
+      "epoch": 2.7111111111111112,
+      "grad_norm": 0.003412955440580845,
+      "learning_rate": 3.237980708141919e-07,
+      "loss": 0.47008293867111206,
+      "step": 192
+    },
+    {
+      "epoch": 2.7253333333333334,
+      "grad_norm": 0.0035507141146808863,
+      "learning_rate": 2.9531763861505967e-07,
+      "loss": 0.479957640171051,
+      "step": 193
+    },
+    {
+      "epoch": 2.7395555555555555,
+      "grad_norm": 0.0035486763808876276,
+      "learning_rate": 2.681099869566328e-07,
+      "loss": 0.44965675473213196,
+      "step": 194
+    },
+    {
+      "epoch": 2.7537777777777777,
+      "grad_norm": 0.0034812854137271643,
+      "learning_rate": 2.4218247645689306e-07,
+      "loss": 0.4747314453125,
+      "step": 195
+    },
+    {
+      "epoch": 2.768,
+      "grad_norm": 0.00335957994684577,
+      "learning_rate": 2.175421214110235e-07,
+      "loss": 0.45799821615219116,
+      "step": 196
+    },
+    {
+      "epoch": 2.7822222222222224,
+      "grad_norm": 0.0035609498154371977,
+      "learning_rate": 1.941955878938029e-07,
+      "loss": 0.47467684745788574,
+      "step": 197
+    },
+    {
+      "epoch": 2.7964444444444445,
+      "grad_norm": 0.003390205791220069,
+      "learning_rate": 1.721491919561913e-07,
+      "loss": 0.4817090332508087,
+      "step": 198
+    },
+    {
+      "epoch": 2.8106666666666666,
+      "grad_norm": 0.003445240668952465,
+      "learning_rate": 1.514088979166256e-07,
+      "loss": 0.4649164080619812,
+      "step": 199
+    },
+    {
+      "epoch": 2.824888888888889,
+      "grad_norm": 0.003372759558260441,
+      "learning_rate": 1.3198031674745814e-07,
+      "loss": 0.4765157699584961,
+      "step": 200
+    },
+    {
+      "epoch": 2.824888888888889,
+      "eval_loss": 0.5171427726745605,
+      "eval_runtime": 9.8598,
+      "eval_samples_per_second": 20.284,
+      "eval_steps_per_second": 10.142,
+      "step": 200
+    },
+    {
+      "epoch": 2.8391111111111114,
+      "grad_norm": 0.0034065141808241606,
+      "learning_rate": 1.138687045569975e-07,
+      "loss": 0.46831822395324707,
+      "step": 201
+    },
+    {
+      "epoch": 2.8533333333333335,
+      "grad_norm": 0.0034053055569529533,
+      "learning_rate": 9.70789611675449e-08,
+      "loss": 0.47398146986961365,
+      "step": 202
+    },
+    {
+      "epoch": 2.8675555555555556,
+      "grad_norm": 0.0034186639823019505,
+      "learning_rate": 8.161562878982399e-08,
+      "loss": 0.45744937658309937,
+      "step": 203
+    },
+    {
+      "epoch": 2.8817777777777778,
+      "grad_norm": 0.0034667483996599913,
+      "learning_rate": 6.74828907941516e-08,
+      "loss": 0.48529934883117676,
+      "step": 204
+    },
+    {
+      "epoch": 2.896,
+      "grad_norm": 0.003455272177234292,
+      "learning_rate": 5.468457057869358e-08,
+      "loss": 0.4858051836490631,
+      "step": 205
+    },
+    {
+      "epoch": 2.910222222222222,
+      "grad_norm": 0.0033815570641309023,
+      "learning_rate": 4.322413053509944e-08,
+      "loss": 0.4590516984462738,
+      "step": 206
+    },
+    {
+      "epoch": 2.924444444444444,
+      "grad_norm": 0.0034011146053671837,
+      "learning_rate": 3.31046711118066e-08,
+      "loss": 0.45788976550102234,
+      "step": 207
+    },
+    {
+      "epoch": 2.9386666666666668,
+      "grad_norm": 0.003420215332880616,
+      "learning_rate": 2.4328929975260262e-08,
+      "loss": 0.4702548086643219,
+      "step": 208
+    },
+    {
+      "epoch": 2.952888888888889,
+      "grad_norm": 0.0033962675370275974,
+      "learning_rate": 1.6899281269279756e-08,
+      "loss": 0.4560105800628662,
+      "step": 209
+    },
+    {
+      "epoch": 2.967111111111111,
+      "grad_norm": 0.003477597376331687,
+      "learning_rate": 1.0817734972768946e-08,
+      "loss": 0.46400371193885803,
+      "step": 210
+    },
+    {
+      "epoch": 2.981333333333333,
+      "grad_norm": 0.0036108316853642464,
+      "learning_rate": 6.085936355947897e-09,
+      "loss": 0.48368915915489197,
+      "step": 211
+    },
+    {
+      "epoch": 2.9955555555555557,
+      "grad_norm": 0.003335504326969385,
+      "learning_rate": 2.7051655352494654e-09,
+      "loss": 0.45437300205230713,
+      "step": 212
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.00642085587605834,
+      "learning_rate": 6.763371270035457e-10,
+      "loss": 0.5508654713630676,
+      "step": 213
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 213,
+  "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": 2.4727435500270387e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

qwen2.5-1.5b-instruct/checkpoint-213/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39e78c30a5784e935e65cb8fa1a73b2afb467afccc55e7223863b667252fac3b
+size 5649

qwen2.5-1.5b-instruct/checkpoint-71/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

qwen2.5-1.5b-instruct/checkpoint-71/config.json

@@ -0,0 +1,61 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "dtype": "float32",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 1000000.0,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.2.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

qwen2.5-1.5b-instruct/checkpoint-71/generation_config.json

@@ -0,0 +1,13 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "5.2.0"
+}

qwen2.5-1.5b-instruct/checkpoint-71/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1f0b1bbce5ea376a4ef5e6eb42573baa753fc0c17d93c09cfe0dcbcb8667dee
+size 6174895536

qwen2.5-1.5b-instruct/checkpoint-71/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23bb7c09eb4777a07e001a06cb196cc13c55aa7113596085a8060ccc4768e6d9
+size 12350013801

qwen2.5-1.5b-instruct/checkpoint-71/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95e5fc2074c0df31522a514f862c86cb00d71c946a7f15cc9ec0e53a69fb28a7
+size 14917

qwen2.5-1.5b-instruct/checkpoint-71/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e7153eae67b6c9232a41bc996a2bf5b83229b8c7230d61911ac0fd40e64154e
+size 14917

qwen2.5-1.5b-instruct/checkpoint-71/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c96c28f12671e2f5db493417daefb3ff0b1bc36602843e0d7ef6df3649c27b3
+size 1465

qwen2.5-1.5b-instruct/checkpoint-71/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
+size 11421892

qwen2.5-1.5b-instruct/checkpoint-71/tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

qwen2.5-1.5b-instruct/checkpoint-71/trainer_state.json

@@ -0,0 +1,539 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 50,
+  "global_step": 71,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.014222222222222223,
+      "grad_norm": 0.03586147725582123,
+      "learning_rate": 0.0,
+      "loss": 0.9098724722862244,
+      "step": 1
+    },
+    {
+      "epoch": 0.028444444444444446,
+      "grad_norm": 0.03577122464776039,
+      "learning_rate": 4.5454545454545457e-07,
+      "loss": 0.9084522724151611,
+      "step": 2
+    },
+    {
+      "epoch": 0.042666666666666665,
+      "grad_norm": 0.031653374433517456,
+      "learning_rate": 9.090909090909091e-07,
+      "loss": 0.8834755420684814,
+      "step": 3
+    },
+    {
+      "epoch": 0.05688888888888889,
+      "grad_norm": 0.025831686332821846,
+      "learning_rate": 1.3636363636363636e-06,
+      "loss": 0.871230959892273,
+      "step": 4
+    },
+    {
+      "epoch": 0.07111111111111111,
+      "grad_norm": 0.019876576960086823,
+      "learning_rate": 1.8181818181818183e-06,
+      "loss": 0.7917206287384033,
+      "step": 5
+    },
+    {
+      "epoch": 0.08533333333333333,
+      "grad_norm": 0.018677273765206337,
+      "learning_rate": 2.2727272727272728e-06,
+      "loss": 0.8436126708984375,
+      "step": 6
+    },
+    {
+      "epoch": 0.09955555555555555,
+      "grad_norm": 0.017528358846902847,
+      "learning_rate": 2.7272727272727272e-06,
+      "loss": 0.8075190782546997,
+      "step": 7
+    },
+    {
+      "epoch": 0.11377777777777778,
+      "grad_norm": 0.01399513240903616,
+      "learning_rate": 3.181818181818182e-06,
+      "loss": 0.7754716873168945,
+      "step": 8
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 0.012644859962165356,
+      "learning_rate": 3.6363636363636366e-06,
+      "loss": 0.7459083199501038,
+      "step": 9
+    },
+    {
+      "epoch": 0.14222222222222222,
+      "grad_norm": 0.01209743320941925,
+      "learning_rate": 4.0909090909090915e-06,
+      "loss": 0.7365868091583252,
+      "step": 10
+    },
+    {
+      "epoch": 0.15644444444444444,
+      "grad_norm": 0.012133832089602947,
+      "learning_rate": 4.5454545454545455e-06,
+      "loss": 0.7119501829147339,
+      "step": 11
+    },
+    {
+      "epoch": 0.17066666666666666,
+      "grad_norm": 0.010017997585237026,
+      "learning_rate": 5e-06,
+      "loss": 0.6901087760925293,
+      "step": 12
+    },
+    {
+      "epoch": 0.18488888888888888,
+      "grad_norm": 0.009233366698026657,
+      "learning_rate": 5.4545454545454545e-06,
+      "loss": 0.6611638069152832,
+      "step": 13
+    },
+    {
+      "epoch": 0.1991111111111111,
+      "grad_norm": 0.00782010331749916,
+      "learning_rate": 5.90909090909091e-06,
+      "loss": 0.6715224981307983,
+      "step": 14
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 0.007341764867305756,
+      "learning_rate": 6.363636363636364e-06,
+      "loss": 0.6277110576629639,
+      "step": 15
+    },
+    {
+      "epoch": 0.22755555555555557,
+      "grad_norm": 0.00713470159098506,
+      "learning_rate": 6.818181818181818e-06,
+      "loss": 0.6689565181732178,
+      "step": 16
+    },
+    {
+      "epoch": 0.24177777777777779,
+      "grad_norm": 0.0067572277039289474,
+      "learning_rate": 7.272727272727273e-06,
+      "loss": 0.6363875865936279,
+      "step": 17
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 0.006228511221706867,
+      "learning_rate": 7.727272727272727e-06,
+      "loss": 0.6257224678993225,
+      "step": 18
+    },
+    {
+      "epoch": 0.2702222222222222,
+      "grad_norm": 0.006048806011676788,
+      "learning_rate": 8.181818181818183e-06,
+      "loss": 0.6355900764465332,
+      "step": 19
+    },
+    {
+      "epoch": 0.28444444444444444,
+      "grad_norm": 0.005988306365907192,
+      "learning_rate": 8.636363636363637e-06,
+      "loss": 0.6338369846343994,
+      "step": 20
+    },
+    {
+      "epoch": 0.2986666666666667,
+      "grad_norm": 0.005441761109977961,
+      "learning_rate": 9.090909090909091e-06,
+      "loss": 0.6133573055267334,
+      "step": 21
+    },
+    {
+      "epoch": 0.3128888888888889,
+      "grad_norm": 0.005174445919692516,
+      "learning_rate": 9.545454545454547e-06,
+      "loss": 0.6042410135269165,
+      "step": 22
+    },
+    {
+      "epoch": 0.32711111111111113,
+      "grad_norm": 0.005199746694415808,
+      "learning_rate": 1e-05,
+      "loss": 0.602219820022583,
+      "step": 23
+    },
+    {
+      "epoch": 0.3413333333333333,
+      "grad_norm": 0.005485028959810734,
+      "learning_rate": 9.999323662872998e-06,
+      "loss": 0.6062123775482178,
+      "step": 24
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 0.004896003287285566,
+      "learning_rate": 9.99729483446475e-06,
+      "loss": 0.6077945232391357,
+      "step": 25
+    },
+    {
+      "epoch": 0.36977777777777776,
+      "grad_norm": 0.00495151337236166,
+      "learning_rate": 9.993914063644053e-06,
+      "loss": 0.5923135280609131,
+      "step": 26
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 0.004744194447994232,
+      "learning_rate": 9.989182265027232e-06,
+      "loss": 0.5860621929168701,
+      "step": 27
+    },
+    {
+      "epoch": 0.3982222222222222,
+      "grad_norm": 0.004471767693758011,
+      "learning_rate": 9.98310071873072e-06,
+      "loss": 0.5823097229003906,
+      "step": 28
+    },
+    {
+      "epoch": 0.41244444444444445,
+      "grad_norm": 0.004788320977240801,
+      "learning_rate": 9.975671070024741e-06,
+      "loss": 0.5872600078582764,
+      "step": 29
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 0.0044632842764258385,
+      "learning_rate": 9.966895328888195e-06,
+      "loss": 0.6070278286933899,
+      "step": 30
+    },
+    {
+      "epoch": 0.4408888888888889,
+      "grad_norm": 0.004317905753850937,
+      "learning_rate": 9.956775869464901e-06,
+      "loss": 0.5780316591262817,
+      "step": 31
+    },
+    {
+      "epoch": 0.45511111111111113,
+      "grad_norm": 0.004291852004826069,
+      "learning_rate": 9.945315429421307e-06,
+      "loss": 0.5697590112686157,
+      "step": 32
+    },
+    {
+      "epoch": 0.4693333333333333,
+      "grad_norm": 0.003922830801457167,
+      "learning_rate": 9.932517109205849e-06,
+      "loss": 0.5747107267379761,
+      "step": 33
+    },
+    {
+      "epoch": 0.48355555555555557,
+      "grad_norm": 0.0041889771819114685,
+      "learning_rate": 9.918384371210178e-06,
+      "loss": 0.6021177172660828,
+      "step": 34
+    },
+    {
+      "epoch": 0.49777777777777776,
+      "grad_norm": 0.004147357773035765,
+      "learning_rate": 9.902921038832456e-06,
+      "loss": 0.5805741548538208,
+      "step": 35
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 0.0040724254213273525,
+      "learning_rate": 9.886131295443003e-06,
+      "loss": 0.5483200550079346,
+      "step": 36
+    },
+    {
+      "epoch": 0.5262222222222223,
+      "grad_norm": 0.004085644613951445,
+      "learning_rate": 9.868019683252543e-06,
+      "loss": 0.557392954826355,
+      "step": 37
+    },
+    {
+      "epoch": 0.5404444444444444,
+      "grad_norm": 0.004289102274924517,
+      "learning_rate": 9.848591102083375e-06,
+      "loss": 0.590857207775116,
+      "step": 38
+    },
+    {
+      "epoch": 0.5546666666666666,
+      "grad_norm": 0.0040345704182982445,
+      "learning_rate": 9.82785080804381e-06,
+      "loss": 0.5750541090965271,
+      "step": 39
+    },
+    {
+      "epoch": 0.5688888888888889,
+      "grad_norm": 0.004034748766571283,
+      "learning_rate": 9.805804412106197e-06,
+      "loss": 0.5949826240539551,
+      "step": 40
+    },
+    {
+      "epoch": 0.5831111111111111,
+      "grad_norm": 0.003911909181624651,
+      "learning_rate": 9.782457878588977e-06,
+      "loss": 0.5623177289962769,
+      "step": 41
+    },
+    {
+      "epoch": 0.5973333333333334,
+      "grad_norm": 0.0037001846358180046,
+      "learning_rate": 9.75781752354311e-06,
+      "loss": 0.5465081930160522,
+      "step": 42
+    },
+    {
+      "epoch": 0.6115555555555555,
+      "grad_norm": 0.0037095139268785715,
+      "learning_rate": 9.731890013043367e-06,
+      "loss": 0.5752100944519043,
+      "step": 43
+    },
+    {
+      "epoch": 0.6257777777777778,
+      "grad_norm": 0.003655617358162999,
+      "learning_rate": 9.704682361384941e-06,
+      "loss": 0.5452020168304443,
+      "step": 44
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.003784338477998972,
+      "learning_rate": 9.676201929185809e-06,
+      "loss": 0.5616332292556763,
+      "step": 45
+    },
+    {
+      "epoch": 0.6542222222222223,
+      "grad_norm": 0.003718078136444092,
+      "learning_rate": 9.646456421395447e-06,
+      "loss": 0.5558297634124756,
+      "step": 46
+    },
+    {
+      "epoch": 0.6684444444444444,
+      "grad_norm": 0.00395169947296381,
+      "learning_rate": 9.615453885210368e-06,
+      "loss": 0.5600595474243164,
+      "step": 47
+    },
+    {
+      "epoch": 0.6826666666666666,
+      "grad_norm": 0.003555440343916416,
+      "learning_rate": 9.583202707897075e-06,
+      "loss": 0.5372895002365112,
+      "step": 48
+    },
+    {
+      "epoch": 0.6968888888888889,
+      "grad_norm": 0.0037386869080364704,
+      "learning_rate": 9.549711614523007e-06,
+      "loss": 0.5322733521461487,
+      "step": 49
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 0.003739988896995783,
+      "learning_rate": 9.514989665596114e-06,
+      "loss": 0.5380419492721558,
+      "step": 50
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "eval_loss": 0.5587145090103149,
+      "eval_runtime": 8.7676,
+      "eval_samples_per_second": 22.811,
+      "eval_steps_per_second": 11.406,
+      "step": 50
+    },
+    {
+      "epoch": 0.7253333333333334,
+      "grad_norm": 0.0037539806216955185,
+      "learning_rate": 9.479046254613673e-06,
+      "loss": 0.5472225546836853,
+      "step": 51
+    },
+    {
+      "epoch": 0.7395555555555555,
+      "grad_norm": 0.003411181503906846,
+      "learning_rate": 9.441891105521005e-06,
+      "loss": 0.5134032964706421,
+      "step": 52
+    },
+    {
+      "epoch": 0.7537777777777778,
+      "grad_norm": 0.0037538670003414154,
+      "learning_rate": 9.40353427008083e-06,
+      "loss": 0.5361013412475586,
+      "step": 53
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 0.0036495670210570097,
+      "learning_rate": 9.3639861251539e-06,
+      "loss": 0.5299779772758484,
+      "step": 54
+    },
+    {
+      "epoch": 0.7822222222222223,
+      "grad_norm": 0.0037342547439038754,
+      "learning_rate": 9.323257369891702e-06,
+      "loss": 0.5607945919036865,
+      "step": 55
+    },
+    {
+      "epoch": 0.7964444444444444,
+      "grad_norm": 0.003572584595531225,
+      "learning_rate": 9.281359022841966e-06,
+      "loss": 0.5528460741043091,
+      "step": 56
+    },
+    {
+      "epoch": 0.8106666666666666,
+      "grad_norm": 0.003770101349800825,
+      "learning_rate": 9.238302418967757e-06,
+      "loss": 0.5440288186073303,
+      "step": 57
+    },
+    {
+      "epoch": 0.8248888888888889,
+      "grad_norm": 0.0036679303739219904,
+      "learning_rate": 9.194099206580981e-06,
+      "loss": 0.5564252138137817,
+      "step": 58
+    },
+    {
+      "epoch": 0.8391111111111111,
+      "grad_norm": 0.003834612900391221,
+      "learning_rate": 9.14876134419111e-06,
+      "loss": 0.5473330020904541,
+      "step": 59
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 0.003683249931782484,
+      "learning_rate": 9.102301097269974e-06,
+      "loss": 0.5463743209838867,
+      "step": 60
+    },
+    {
+      "epoch": 0.8675555555555555,
+      "grad_norm": 0.0036777963396161795,
+      "learning_rate": 9.05473103493355e-06,
+      "loss": 0.524878740310669,
+      "step": 61
+    },
+    {
+      "epoch": 0.8817777777777778,
+      "grad_norm": 0.0038230482023209333,
+      "learning_rate": 9.006064026541549e-06,
+      "loss": 0.5563522577285767,
+      "step": 62
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 0.003645201213657856,
+      "learning_rate": 8.956313238215824e-06,
+      "loss": 0.5059154033660889,
+      "step": 63
+    },
+    {
+      "epoch": 0.9102222222222223,
+      "grad_norm": 0.0035886459518224,
+      "learning_rate": 8.905492129278478e-06,
+      "loss": 0.5312881469726562,
+      "step": 64
+    },
+    {
+      "epoch": 0.9244444444444444,
+      "grad_norm": 0.003721872577443719,
+      "learning_rate": 8.85361444861063e-06,
+      "loss": 0.5358959436416626,
+      "step": 65
+    },
+    {
+      "epoch": 0.9386666666666666,
+      "grad_norm": 0.003683999879285693,
+      "learning_rate": 8.800694230932885e-06,
+      "loss": 0.5442053079605103,
+      "step": 66
+    },
+    {
+      "epoch": 0.9528888888888889,
+      "grad_norm": 0.0036851842887699604,
+      "learning_rate": 8.74674579300843e-06,
+      "loss": 0.5263723731040955,
+      "step": 67
+    },
+    {
+      "epoch": 0.9671111111111111,
+      "grad_norm": 0.003754258854314685,
+      "learning_rate": 8.691783729769874e-06,
+      "loss": 0.5200538039207458,
+      "step": 68
+    },
+    {
+      "epoch": 0.9813333333333333,
+      "grad_norm": 0.0038373274728655815,
+      "learning_rate": 8.635822910370793e-06,
+      "loss": 0.5452108383178711,
+      "step": 69
+    },
+    {
+      "epoch": 0.9955555555555555,
+      "grad_norm": 0.0039480882696807384,
+      "learning_rate": 8.578878474163115e-06,
+      "loss": 0.5066030621528625,
+      "step": 70
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.005897017661482096,
+      "learning_rate": 8.520965826601394e-06,
+      "loss": 0.5380499958992004,
+      "step": 71
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 213,
+  "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": 8.242478482194432e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

qwen2.5-1.5b-instruct/checkpoint-71/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39e78c30a5784e935e65cb8fa1a73b2afb467afccc55e7223863b667252fac3b
+size 5649

qwen2.5-1.5b-instruct/config.json

@@ -0,0 +1,61 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "dtype": "float32",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 1000000.0,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.2.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

qwen2.5-1.5b-instruct/eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.5171241164207458,
+    "eval_runtime": 8.31,
+    "eval_samples_per_second": 24.067,
+    "eval_steps_per_second": 12.034
+}

qwen2.5-1.5b-instruct/generation_config.json

@@ -0,0 +1,13 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "5.2.0"
+}

qwen2.5-1.5b-instruct/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f14867d928257934392dd2a17c62080e0613e998d7c4e10eba82a99bef35153
+size 6174895536

qwen2.5-1.5b-instruct/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
+size 11421892

qwen2.5-1.5b-instruct/tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

qwen2.5-1.5b-instruct/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 2.4727435500270387e+17,
+    "train_loss": 0.5265021298972654,
+    "train_runtime": 6756.1203,
+    "train_samples_per_second": 7.993,
+    "train_steps_per_second": 0.032
+}

qwen2.5-1.5b-instruct/trainer_log.jsonl

@@ -0,0 +1,218 @@
+{"current_steps": 1, "total_steps": 213, "loss": 0.9098724722862244, "lr": 0.0, "epoch": 0.014222222222222223, "percentage": 0.47, "elapsed_time": "0:00:35", "remaining_time": "2:06:27"}
+{"current_steps": 2, "total_steps": 213, "loss": 0.9084522724151611, "lr": 4.5454545454545457e-07, "epoch": 0.028444444444444446, "percentage": 0.94, "elapsed_time": "0:01:09", "remaining_time": "2:02:58"}
+{"current_steps": 3, "total_steps": 213, "loss": 0.8834755420684814, "lr": 9.090909090909091e-07, "epoch": 0.042666666666666665, "percentage": 1.41, "elapsed_time": "0:01:44", "remaining_time": "2:02:28"}
+{"current_steps": 4, "total_steps": 213, "loss": 0.871230959892273, "lr": 1.3636363636363636e-06, "epoch": 0.05688888888888889, "percentage": 1.88, "elapsed_time": "0:02:18", "remaining_time": "2:00:49"}
+{"current_steps": 5, "total_steps": 213, "loss": 0.7917206287384033, "lr": 1.8181818181818183e-06, "epoch": 0.07111111111111111, "percentage": 2.35, "elapsed_time": "0:02:53", "remaining_time": "2:00:16"}
+{"current_steps": 6, "total_steps": 213, "loss": 0.8436126708984375, "lr": 2.2727272727272728e-06, "epoch": 0.08533333333333333, "percentage": 2.82, "elapsed_time": "0:03:27", "remaining_time": "1:59:28"}
+{"current_steps": 7, "total_steps": 213, "loss": 0.8075190782546997, "lr": 2.7272727272727272e-06, "epoch": 0.09955555555555555, "percentage": 3.29, "elapsed_time": "0:04:01", "remaining_time": "1:58:19"}
+{"current_steps": 8, "total_steps": 213, "loss": 0.7754716873168945, "lr": 3.181818181818182e-06, "epoch": 0.11377777777777778, "percentage": 3.76, "elapsed_time": "0:04:35", "remaining_time": "1:57:42"}
+{"current_steps": 9, "total_steps": 213, "loss": 0.7459083199501038, "lr": 3.6363636363636366e-06, "epoch": 0.128, "percentage": 4.23, "elapsed_time": "0:05:09", "remaining_time": "1:57:01"}
+{"current_steps": 10, "total_steps": 213, "loss": 0.7365868091583252, "lr": 4.0909090909090915e-06, "epoch": 0.14222222222222222, "percentage": 4.69, "elapsed_time": "0:05:45", "remaining_time": "1:56:44"}
+{"current_steps": 11, "total_steps": 213, "loss": 0.7119501829147339, "lr": 4.5454545454545455e-06, "epoch": 0.15644444444444444, "percentage": 5.16, "elapsed_time": "0:06:26", "remaining_time": "1:58:20"}
+{"current_steps": 12, "total_steps": 213, "loss": 0.6901087760925293, "lr": 5e-06, "epoch": 0.17066666666666666, "percentage": 5.63, "elapsed_time": "0:07:08", "remaining_time": "1:59:41"}
+{"current_steps": 13, "total_steps": 213, "loss": 0.6611638069152832, "lr": 5.4545454545454545e-06, "epoch": 0.18488888888888888, "percentage": 6.1, "elapsed_time": "0:07:50", "remaining_time": "2:00:40"}
+{"current_steps": 14, "total_steps": 213, "loss": 0.6715224981307983, "lr": 5.90909090909091e-06, "epoch": 0.1991111111111111, "percentage": 6.57, "elapsed_time": "0:08:33", "remaining_time": "2:01:35"}
+{"current_steps": 15, "total_steps": 213, "loss": 0.6277110576629639, "lr": 6.363636363636364e-06, "epoch": 0.21333333333333335, "percentage": 7.04, "elapsed_time": "0:09:14", "remaining_time": "2:02:01"}
+{"current_steps": 16, "total_steps": 213, "loss": 0.6689565181732178, "lr": 6.818181818181818e-06, "epoch": 0.22755555555555557, "percentage": 7.51, "elapsed_time": "0:09:56", "remaining_time": "2:02:24"}
+{"current_steps": 17, "total_steps": 213, "loss": 0.6363875865936279, "lr": 7.272727272727273e-06, "epoch": 0.24177777777777779, "percentage": 7.98, "elapsed_time": "0:10:38", "remaining_time": "2:02:36"}
+{"current_steps": 18, "total_steps": 213, "loss": 0.6257224678993225, "lr": 7.727272727272727e-06, "epoch": 0.256, "percentage": 8.45, "elapsed_time": "0:11:19", "remaining_time": "2:02:38"}
+{"current_steps": 19, "total_steps": 213, "loss": 0.6355900764465332, "lr": 8.181818181818183e-06, "epoch": 0.2702222222222222, "percentage": 8.92, "elapsed_time": "0:12:01", "remaining_time": "2:02:46"}
+{"current_steps": 20, "total_steps": 213, "loss": 0.6338369846343994, "lr": 8.636363636363637e-06, "epoch": 0.28444444444444444, "percentage": 9.39, "elapsed_time": "0:12:43", "remaining_time": "2:02:44"}
+{"current_steps": 21, "total_steps": 213, "loss": 0.6133573055267334, "lr": 9.090909090909091e-06, "epoch": 0.2986666666666667, "percentage": 9.86, "elapsed_time": "0:13:25", "remaining_time": "2:02:43"}
+{"current_steps": 22, "total_steps": 213, "loss": 0.6042410135269165, "lr": 9.545454545454547e-06, "epoch": 0.3128888888888889, "percentage": 10.33, "elapsed_time": "0:14:07", "remaining_time": "2:02:36"}
+{"current_steps": 23, "total_steps": 213, "loss": 0.602219820022583, "lr": 1e-05, "epoch": 0.32711111111111113, "percentage": 10.8, "elapsed_time": "0:14:49", "remaining_time": "2:02:28"}
+{"current_steps": 24, "total_steps": 213, "loss": 0.6062123775482178, "lr": 9.999323662872998e-06, "epoch": 0.3413333333333333, "percentage": 11.27, "elapsed_time": "0:15:30", "remaining_time": "2:02:11"}
+{"current_steps": 25, "total_steps": 213, "loss": 0.6077945232391357, "lr": 9.99729483446475e-06, "epoch": 0.35555555555555557, "percentage": 11.74, "elapsed_time": "0:16:13", "remaining_time": "2:01:57"}
+{"current_steps": 26, "total_steps": 213, "loss": 0.5923135280609131, "lr": 9.993914063644053e-06, "epoch": 0.36977777777777776, "percentage": 12.21, "elapsed_time": "0:16:54", "remaining_time": "2:01:36"}
+{"current_steps": 27, "total_steps": 213, "loss": 0.5860621929168701, "lr": 9.989182265027232e-06, "epoch": 0.384, "percentage": 12.68, "elapsed_time": "0:17:33", "remaining_time": "2:00:57"}
+{"current_steps": 28, "total_steps": 213, "loss": 0.5823097229003906, "lr": 9.98310071873072e-06, "epoch": 0.3982222222222222, "percentage": 13.15, "elapsed_time": "0:18:03", "remaining_time": "1:59:16"}
+{"current_steps": 29, "total_steps": 213, "loss": 0.5872600078582764, "lr": 9.975671070024741e-06, "epoch": 0.41244444444444445, "percentage": 13.62, "elapsed_time": "0:18:32", "remaining_time": "1:57:36"}
+{"current_steps": 30, "total_steps": 213, "loss": 0.6070278286933899, "lr": 9.966895328888195e-06, "epoch": 0.4266666666666667, "percentage": 14.08, "elapsed_time": "0:19:01", "remaining_time": "1:56:06"}
+{"current_steps": 31, "total_steps": 213, "loss": 0.5780316591262817, "lr": 9.956775869464901e-06, "epoch": 0.4408888888888889, "percentage": 14.55, "elapsed_time": "0:19:31", "remaining_time": "1:54:39"}
+{"current_steps": 32, "total_steps": 213, "loss": 0.5697590112686157, "lr": 9.945315429421307e-06, "epoch": 0.45511111111111113, "percentage": 15.02, "elapsed_time": "0:20:01", "remaining_time": "1:53:15"}
+{"current_steps": 33, "total_steps": 213, "loss": 0.5747107267379761, "lr": 9.932517109205849e-06, "epoch": 0.4693333333333333, "percentage": 15.49, "elapsed_time": "0:20:30", "remaining_time": "1:51:52"}
+{"current_steps": 34, "total_steps": 213, "loss": 0.6021177172660828, "lr": 9.918384371210178e-06, "epoch": 0.48355555555555557, "percentage": 15.96, "elapsed_time": "0:20:59", "remaining_time": "1:50:30"}
+{"current_steps": 35, "total_steps": 213, "loss": 0.5805741548538208, "lr": 9.902921038832456e-06, "epoch": 0.49777777777777776, "percentage": 16.43, "elapsed_time": "0:21:28", "remaining_time": "1:49:12"}
+{"current_steps": 36, "total_steps": 213, "loss": 0.5483200550079346, "lr": 9.886131295443003e-06, "epoch": 0.512, "percentage": 16.9, "elapsed_time": "0:21:57", "remaining_time": "1:47:58"}
+{"current_steps": 37, "total_steps": 213, "loss": 0.557392954826355, "lr": 9.868019683252543e-06, "epoch": 0.5262222222222223, "percentage": 17.37, "elapsed_time": "0:22:26", "remaining_time": "1:46:47"}
+{"current_steps": 38, "total_steps": 213, "loss": 0.590857207775116, "lr": 9.848591102083375e-06, "epoch": 0.5404444444444444, "percentage": 17.84, "elapsed_time": "0:22:55", "remaining_time": "1:45:36"}
+{"current_steps": 39, "total_steps": 213, "loss": 0.5750541090965271, "lr": 9.82785080804381e-06, "epoch": 0.5546666666666666, "percentage": 18.31, "elapsed_time": "0:23:25", "remaining_time": "1:44:29"}
+{"current_steps": 40, "total_steps": 213, "loss": 0.5949826240539551, "lr": 9.805804412106197e-06, "epoch": 0.5688888888888889, "percentage": 18.78, "elapsed_time": "0:23:53", "remaining_time": "1:43:21"}
+{"current_steps": 41, "total_steps": 213, "loss": 0.5623177289962769, "lr": 9.782457878588977e-06, "epoch": 0.5831111111111111, "percentage": 19.25, "elapsed_time": "0:24:23", "remaining_time": "1:42:20"}
+{"current_steps": 42, "total_steps": 213, "loss": 0.5465081930160522, "lr": 9.75781752354311e-06, "epoch": 0.5973333333333334, "percentage": 19.72, "elapsed_time": "0:24:54", "remaining_time": "1:41:22"}
+{"current_steps": 43, "total_steps": 213, "loss": 0.5752100944519043, "lr": 9.731890013043367e-06, "epoch": 0.6115555555555555, "percentage": 20.19, "elapsed_time": "0:25:23", "remaining_time": "1:40:22"}
+{"current_steps": 44, "total_steps": 213, "loss": 0.5452020168304443, "lr": 9.704682361384941e-06, "epoch": 0.6257777777777778, "percentage": 20.66, "elapsed_time": "0:25:54", "remaining_time": "1:39:31"}
+{"current_steps": 45, "total_steps": 213, "loss": 0.5616332292556763, "lr": 9.676201929185809e-06, "epoch": 0.64, "percentage": 21.13, "elapsed_time": "0:26:23", "remaining_time": "1:38:30"}
+{"current_steps": 46, "total_steps": 213, "loss": 0.5558297634124756, "lr": 9.646456421395447e-06, "epoch": 0.6542222222222223, "percentage": 21.6, "elapsed_time": "0:26:53", "remaining_time": "1:37:38"}
+{"current_steps": 47, "total_steps": 213, "loss": 0.5600595474243164, "lr": 9.615453885210368e-06, "epoch": 0.6684444444444444, "percentage": 22.07, "elapsed_time": "0:27:23", "remaining_time": "1:36:43"}
+{"current_steps": 48, "total_steps": 213, "loss": 0.5372895002365112, "lr": 9.583202707897075e-06, "epoch": 0.6826666666666666, "percentage": 22.54, "elapsed_time": "0:27:53", "remaining_time": "1:35:53"}
+{"current_steps": 49, "total_steps": 213, "loss": 0.5322733521461487, "lr": 9.549711614523007e-06, "epoch": 0.6968888888888889, "percentage": 23.0, "elapsed_time": "0:28:21", "remaining_time": "1:34:55"}
+{"current_steps": 50, "total_steps": 213, "loss": 0.5380419492721558, "lr": 9.514989665596114e-06, "epoch": 0.7111111111111111, "percentage": 23.47, "elapsed_time": "0:28:52", "remaining_time": "1:34:06"}
+{"current_steps": 50, "total_steps": 213, "eval_loss": 0.5587145090103149, "epoch": 0.7111111111111111, "percentage": 23.47, "elapsed_time": "0:29:01", "remaining_time": "1:34:37"}
+{"current_steps": 51, "total_steps": 213, "loss": 0.5472225546836853, "lr": 9.479046254613673e-06, "epoch": 0.7253333333333334, "percentage": 23.94, "elapsed_time": "0:29:32", "remaining_time": "1:33:48"}
+{"current_steps": 52, "total_steps": 213, "loss": 0.5134032964706421, "lr": 9.441891105521005e-06, "epoch": 0.7395555555555555, "percentage": 24.41, "elapsed_time": "0:30:03", "remaining_time": "1:33:03"}
+{"current_steps": 53, "total_steps": 213, "loss": 0.5361013412475586, "lr": 9.40353427008083e-06, "epoch": 0.7537777777777778, "percentage": 24.88, "elapsed_time": "0:30:33", "remaining_time": "1:32:15"}
+{"current_steps": 54, "total_steps": 213, "loss": 0.5299779772758484, "lr": 9.3639861251539e-06, "epoch": 0.768, "percentage": 25.35, "elapsed_time": "0:31:04", "remaining_time": "1:31:30"}
+{"current_steps": 55, "total_steps": 213, "loss": 0.5607945919036865, "lr": 9.323257369891702e-06, "epoch": 0.7822222222222223, "percentage": 25.82, "elapsed_time": "0:31:33", "remaining_time": "1:30:40"}
+{"current_steps": 56, "total_steps": 213, "loss": 0.5528460741043091, "lr": 9.281359022841966e-06, "epoch": 0.7964444444444444, "percentage": 26.29, "elapsed_time": "0:32:03", "remaining_time": "1:29:51"}
+{"current_steps": 57, "total_steps": 213, "loss": 0.5440288186073303, "lr": 9.238302418967757e-06, "epoch": 0.8106666666666666, "percentage": 26.76, "elapsed_time": "0:32:32", "remaining_time": "1:29:03"}
+{"current_steps": 58, "total_steps": 213, "loss": 0.5564252138137817, "lr": 9.194099206580981e-06, "epoch": 0.8248888888888889, "percentage": 27.23, "elapsed_time": "0:33:02", "remaining_time": "1:28:17"}
+{"current_steps": 59, "total_steps": 213, "loss": 0.5473330020904541, "lr": 9.14876134419111e-06, "epoch": 0.8391111111111111, "percentage": 27.7, "elapsed_time": "0:33:31", "remaining_time": "1:27:30"}
+{"current_steps": 60, "total_steps": 213, "loss": 0.5463743209838867, "lr": 9.102301097269974e-06, "epoch": 0.8533333333333334, "percentage": 28.17, "elapsed_time": "0:34:01", "remaining_time": "1:26:46"}
+{"current_steps": 61, "total_steps": 213, "loss": 0.524878740310669, "lr": 9.05473103493355e-06, "epoch": 0.8675555555555555, "percentage": 28.64, "elapsed_time": "0:34:31", "remaining_time": "1:26:01"}
+{"current_steps": 62, "total_steps": 213, "loss": 0.5563522577285767, "lr": 9.006064026541549e-06, "epoch": 0.8817777777777778, "percentage": 29.11, "elapsed_time": "0:35:00", "remaining_time": "1:25:14"}
+{"current_steps": 63, "total_steps": 213, "loss": 0.5059154033660889, "lr": 8.956313238215824e-06, "epoch": 0.896, "percentage": 29.58, "elapsed_time": "0:35:32", "remaining_time": "1:24:37"}
+{"current_steps": 64, "total_steps": 213, "loss": 0.5312881469726562, "lr": 8.905492129278478e-06, "epoch": 0.9102222222222223, "percentage": 30.05, "elapsed_time": "0:36:01", "remaining_time": "1:23:52"}
+{"current_steps": 65, "total_steps": 213, "loss": 0.5358959436416626, "lr": 8.85361444861063e-06, "epoch": 0.9244444444444444, "percentage": 30.52, "elapsed_time": "0:36:32", "remaining_time": "1:23:12"}
+{"current_steps": 66, "total_steps": 213, "loss": 0.5442053079605103, "lr": 8.800694230932885e-06, "epoch": 0.9386666666666666, "percentage": 30.99, "elapsed_time": "0:37:02", "remaining_time": "1:22:30"}
+{"current_steps": 67, "total_steps": 213, "loss": 0.5263723731040955, "lr": 8.74674579300843e-06, "epoch": 0.9528888888888889, "percentage": 31.46, "elapsed_time": "0:37:33", "remaining_time": "1:21:50"}
+{"current_steps": 68, "total_steps": 213, "loss": 0.5200538039207458, "lr": 8.691783729769874e-06, "epoch": 0.9671111111111111, "percentage": 31.92, "elapsed_time": "0:38:03", "remaining_time": "1:21:10"}
+{"current_steps": 69, "total_steps": 213, "loss": 0.5452108383178711, "lr": 8.635822910370793e-06, "epoch": 0.9813333333333333, "percentage": 32.39, "elapsed_time": "0:38:34", "remaining_time": "1:20:29"}
+{"current_steps": 70, "total_steps": 213, "loss": 0.5066030621528625, "lr": 8.578878474163115e-06, "epoch": 0.9955555555555555, "percentage": 32.86, "elapsed_time": "0:39:03", "remaining_time": "1:19:48"}
+{"current_steps": 71, "total_steps": 213, "loss": 0.5380499958992004, "lr": 8.520965826601394e-06, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:39:13", "remaining_time": "1:18:27"}
+{"current_steps": 72, "total_steps": 213, "loss": 0.5328541398048401, "lr": 8.462100635075097e-06, "epoch": 1.0142222222222221, "percentage": 33.8, "elapsed_time": "0:40:43", "remaining_time": "1:19:46"}
+{"current_steps": 73, "total_steps": 213, "loss": 0.5096005201339722, "lr": 8.40229882467003e-06, "epoch": 1.0284444444444445, "percentage": 34.27, "elapsed_time": "0:41:13", "remaining_time": "1:19:04"}
+{"current_steps": 74, "total_steps": 213, "loss": 0.4889724850654602, "lr": 8.341576573860049e-06, "epoch": 1.0426666666666666, "percentage": 34.74, "elapsed_time": "0:41:45", "remaining_time": "1:18:26"}
+{"current_steps": 75, "total_steps": 213, "loss": 0.5157173871994019, "lr": 8.279950310130218e-06, "epoch": 1.056888888888889, "percentage": 35.21, "elapsed_time": "0:42:15", "remaining_time": "1:17:45"}
+{"current_steps": 76, "total_steps": 213, "loss": 0.49691659212112427, "lr": 8.2174367055326e-06, "epoch": 1.0711111111111111, "percentage": 35.68, "elapsed_time": "0:42:44", "remaining_time": "1:17:03"}
+{"current_steps": 77, "total_steps": 213, "loss": 0.4873769283294678, "lr": 8.154052672175888e-06, "epoch": 1.0853333333333333, "percentage": 36.15, "elapsed_time": "0:43:14", "remaining_time": "1:16:21"}
+{"current_steps": 78, "total_steps": 213, "loss": 0.5266215801239014, "lr": 8.08981535765009e-06, "epoch": 1.0995555555555556, "percentage": 36.62, "elapsed_time": "0:43:44", "remaining_time": "1:15:42"}
+{"current_steps": 79, "total_steps": 213, "loss": 0.5039150714874268, "lr": 8.024742140387506e-06, "epoch": 1.1137777777777778, "percentage": 37.09, "elapsed_time": "0:44:13", "remaining_time": "1:15:01"}
+{"current_steps": 80, "total_steps": 213, "loss": 0.4896891117095947, "lr": 7.95885062496126e-06, "epoch": 1.1280000000000001, "percentage": 37.56, "elapsed_time": "0:44:43", "remaining_time": "1:14:21"}
+{"current_steps": 81, "total_steps": 213, "loss": 0.45997822284698486, "lr": 7.892158637322647e-06, "epoch": 1.1422222222222222, "percentage": 38.03, "elapsed_time": "0:45:12", "remaining_time": "1:13:40"}
+{"current_steps": 82, "total_steps": 213, "loss": 0.4917220175266266, "lr": 7.824684219978591e-06, "epoch": 1.1564444444444444, "percentage": 38.5, "elapsed_time": "0:45:42", "remaining_time": "1:13:01"}
+{"current_steps": 83, "total_steps": 213, "loss": 0.5024806261062622, "lr": 7.756445627110523e-06, "epoch": 1.1706666666666667, "percentage": 38.97, "elapsed_time": "0:46:13", "remaining_time": "1:12:23"}
+{"current_steps": 84, "total_steps": 213, "loss": 0.5110447406768799, "lr": 7.68746131963598e-06, "epoch": 1.1848888888888889, "percentage": 39.44, "elapsed_time": "0:46:42", "remaining_time": "1:11:43"}
+{"current_steps": 85, "total_steps": 213, "loss": 0.5031975507736206, "lr": 7.6177499602143e-06, "epoch": 1.199111111111111, "percentage": 39.91, "elapsed_time": "0:47:11", "remaining_time": "1:11:04"}
+{"current_steps": 86, "total_steps": 213, "loss": 0.4899296164512634, "lr": 7.547330408197695e-06, "epoch": 1.2133333333333334, "percentage": 40.38, "elapsed_time": "0:47:42", "remaining_time": "1:10:27"}
+{"current_steps": 87, "total_steps": 213, "loss": 0.5040560960769653, "lr": 7.476221714529167e-06, "epoch": 1.2275555555555555, "percentage": 40.85, "elapsed_time": "0:48:12", "remaining_time": "1:09:49"}
+{"current_steps": 88, "total_steps": 213, "loss": 0.5307536125183105, "lr": 7.404443116588548e-06, "epoch": 1.2417777777777779, "percentage": 41.31, "elapsed_time": "0:48:41", "remaining_time": "1:09:09"}
+{"current_steps": 89, "total_steps": 213, "loss": 0.5025057792663574, "lr": 7.332014032988123e-06, "epoch": 1.256, "percentage": 41.78, "elapsed_time": "0:49:10", "remaining_time": "1:08:31"}
+{"current_steps": 90, "total_steps": 213, "loss": 0.5043497085571289, "lr": 7.2589540583192165e-06, "epoch": 1.2702222222222221, "percentage": 42.25, "elapsed_time": "0:49:40", "remaining_time": "1:07:53"}
+{"current_steps": 91, "total_steps": 213, "loss": 0.4883122444152832, "lr": 7.185282957851175e-06, "epoch": 1.2844444444444445, "percentage": 42.72, "elapsed_time": "0:50:10", "remaining_time": "1:07:16"}
+{"current_steps": 92, "total_steps": 213, "loss": 0.5055882930755615, "lr": 7.111020662184174e-06, "epoch": 1.2986666666666666, "percentage": 43.19, "elapsed_time": "0:50:41", "remaining_time": "1:06:40"}
+{"current_steps": 93, "total_steps": 213, "loss": 0.4962804615497589, "lr": 7.036187261857289e-06, "epoch": 1.3128888888888888, "percentage": 43.66, "elapsed_time": "0:51:10", "remaining_time": "1:06:02"}
+{"current_steps": 94, "total_steps": 213, "loss": 0.524259090423584, "lr": 6.960803001913315e-06, "epoch": 1.3271111111111111, "percentage": 44.13, "elapsed_time": "0:51:39", "remaining_time": "1:05:23"}
+{"current_steps": 95, "total_steps": 213, "loss": 0.5073269009590149, "lr": 6.884888276421766e-06, "epoch": 1.3413333333333333, "percentage": 44.6, "elapsed_time": "0:52:08", "remaining_time": "1:04:46"}
+{"current_steps": 96, "total_steps": 213, "loss": 0.4886914789676666, "lr": 6.8084636229615786e-06, "epoch": 1.3555555555555556, "percentage": 45.07, "elapsed_time": "0:52:38", "remaining_time": "1:04:09"}
+{"current_steps": 97, "total_steps": 213, "loss": 0.4920746088027954, "lr": 6.731549717064975e-06, "epoch": 1.3697777777777778, "percentage": 45.54, "elapsed_time": "0:53:08", "remaining_time": "1:03:33"}
+{"current_steps": 98, "total_steps": 213, "loss": 0.503207266330719, "lr": 6.654167366624009e-06, "epoch": 1.384, "percentage": 46.01, "elapsed_time": "0:53:36", "remaining_time": "1:02:54"}
+{"current_steps": 99, "total_steps": 213, "loss": 0.5012996196746826, "lr": 6.576337506261314e-06, "epoch": 1.3982222222222223, "percentage": 46.48, "elapsed_time": "0:54:06", "remaining_time": "1:02:18"}
+{"current_steps": 100, "total_steps": 213, "loss": 0.5059630274772644, "lr": 6.498081191666549e-06, "epoch": 1.4124444444444444, "percentage": 46.95, "elapsed_time": "0:54:37", "remaining_time": "1:01:43"}
+{"current_steps": 100, "total_steps": 213, "eval_loss": 0.5291631817817688, "epoch": 1.4124444444444444, "percentage": 46.95, "elapsed_time": "0:54:47", "remaining_time": "1:01:54"}
+{"current_steps": 101, "total_steps": 213, "loss": 0.4896056056022644, "lr": 6.419419593900109e-06, "epoch": 1.4266666666666667, "percentage": 47.42, "elapsed_time": "0:55:16", "remaining_time": "1:01:17"}
+{"current_steps": 102, "total_steps": 213, "loss": 0.48181772232055664, "lr": 6.340373993665607e-06, "epoch": 1.4408888888888889, "percentage": 47.89, "elapsed_time": "0:55:45", "remaining_time": "1:00:41"}
+{"current_steps": 103, "total_steps": 213, "loss": 0.4775124192237854, "lr": 6.2609657755527135e-06, "epoch": 1.455111111111111, "percentage": 48.36, "elapsed_time": "0:56:15", "remaining_time": "1:00:04"}
+{"current_steps": 104, "total_steps": 213, "loss": 0.5167958736419678, "lr": 6.1812164222518626e-06, "epoch": 1.4693333333333334, "percentage": 48.83, "elapsed_time": "0:56:44", "remaining_time": "0:59:28"}
+{"current_steps": 105, "total_steps": 213, "loss": 0.4946171045303345, "lr": 6.101147508742456e-06, "epoch": 1.4835555555555555, "percentage": 49.3, "elapsed_time": "0:57:14", "remaining_time": "0:58:52"}
+{"current_steps": 106, "total_steps": 213, "loss": 0.4849076569080353, "lr": 6.020780696456059e-06, "epoch": 1.4977777777777779, "percentage": 49.77, "elapsed_time": "0:57:44", "remaining_time": "0:58:17"}
+{"current_steps": 107, "total_steps": 213, "loss": 0.4958712160587311, "lr": 5.940137727416247e-06, "epoch": 1.512, "percentage": 50.23, "elapsed_time": "0:58:15", "remaining_time": "0:57:42"}
+{"current_steps": 108, "total_steps": 213, "loss": 0.4822971820831299, "lr": 5.859240418356614e-06, "epoch": 1.5262222222222221, "percentage": 50.7, "elapsed_time": "0:58:45", "remaining_time": "0:57:07"}
+{"current_steps": 109, "total_steps": 213, "loss": 0.5280419588088989, "lr": 5.778110654818602e-06, "epoch": 1.5404444444444443, "percentage": 51.17, "elapsed_time": "0:59:14", "remaining_time": "0:56:31"}
+{"current_steps": 110, "total_steps": 213, "loss": 0.4952104687690735, "lr": 5.696770385230679e-06, "epoch": 1.5546666666666666, "percentage": 51.64, "elapsed_time": "0:59:44", "remaining_time": "0:55:55"}
+{"current_steps": 111, "total_steps": 213, "loss": 0.4887908101081848, "lr": 5.615241614970546e-06, "epoch": 1.568888888888889, "percentage": 52.11, "elapsed_time": "1:00:13", "remaining_time": "0:55:20"}
+{"current_steps": 112, "total_steps": 213, "loss": 0.4928241968154907, "lr": 5.533546400411899e-06, "epoch": 1.5831111111111111, "percentage": 52.58, "elapsed_time": "1:00:42", "remaining_time": "0:54:44"}
+{"current_steps": 113, "total_steps": 213, "loss": 0.5109080076217651, "lr": 5.4517068429574215e-06, "epoch": 1.5973333333333333, "percentage": 53.05, "elapsed_time": "1:01:12", "remaining_time": "0:54:10"}
+{"current_steps": 114, "total_steps": 213, "loss": 0.48911499977111816, "lr": 5.3697450830595775e-06, "epoch": 1.6115555555555554, "percentage": 53.52, "elapsed_time": "1:01:43", "remaining_time": "0:53:36"}
+{"current_steps": 115, "total_steps": 213, "loss": 0.49537116289138794, "lr": 5.287683294230855e-06, "epoch": 1.6257777777777778, "percentage": 53.99, "elapsed_time": "1:02:11", "remaining_time": "0:53:00"}
+{"current_steps": 116, "total_steps": 213, "loss": 0.4613257348537445, "lr": 5.20554367704505e-06, "epoch": 1.6400000000000001, "percentage": 54.46, "elapsed_time": "1:02:42", "remaining_time": "0:52:26"}
+{"current_steps": 117, "total_steps": 213, "loss": 0.5043697357177734, "lr": 5.123348453131242e-06, "epoch": 1.6542222222222223, "percentage": 54.93, "elapsed_time": "1:03:12", "remaining_time": "0:51:51"}
+{"current_steps": 118, "total_steps": 213, "loss": 0.48968735337257385, "lr": 5.041119859162068e-06, "epoch": 1.6684444444444444, "percentage": 55.4, "elapsed_time": "1:03:42", "remaining_time": "0:51:17"}
+{"current_steps": 119, "total_steps": 213, "loss": 0.49605250358581543, "lr": 4.958880140837934e-06, "epoch": 1.6826666666666665, "percentage": 55.87, "elapsed_time": "1:04:11", "remaining_time": "0:50:42"}
+{"current_steps": 120, "total_steps": 213, "loss": 0.4839916229248047, "lr": 4.876651546868759e-06, "epoch": 1.696888888888889, "percentage": 56.34, "elapsed_time": "1:04:41", "remaining_time": "0:50:07"}
+{"current_steps": 121, "total_steps": 213, "loss": 0.5173561573028564, "lr": 4.794456322954953e-06, "epoch": 1.7111111111111112, "percentage": 56.81, "elapsed_time": "1:05:11", "remaining_time": "0:49:34"}
+{"current_steps": 122, "total_steps": 213, "loss": 0.5177811980247498, "lr": 4.7123167057691446e-06, "epoch": 1.7253333333333334, "percentage": 57.28, "elapsed_time": "1:05:41", "remaining_time": "0:48:59"}
+{"current_steps": 123, "total_steps": 213, "loss": 0.5164836049079895, "lr": 4.630254916940424e-06, "epoch": 1.7395555555555555, "percentage": 57.75, "elapsed_time": "1:06:12", "remaining_time": "0:48:26"}
+{"current_steps": 124, "total_steps": 213, "loss": 0.5077825784683228, "lr": 4.548293157042581e-06, "epoch": 1.7537777777777777, "percentage": 58.22, "elapsed_time": "1:06:44", "remaining_time": "0:47:53"}
+{"current_steps": 125, "total_steps": 213, "loss": 0.5107009410858154, "lr": 4.466453599588103e-06, "epoch": 1.768, "percentage": 58.69, "elapsed_time": "1:07:14", "remaining_time": "0:47:20"}
+{"current_steps": 126, "total_steps": 213, "loss": 0.4728143811225891, "lr": 4.384758385029457e-06, "epoch": 1.7822222222222224, "percentage": 59.15, "elapsed_time": "1:07:44", "remaining_time": "0:46:46"}
+{"current_steps": 127, "total_steps": 213, "loss": 0.4858134984970093, "lr": 4.3032296147693225e-06, "epoch": 1.7964444444444445, "percentage": 59.62, "elapsed_time": "1:08:13", "remaining_time": "0:46:12"}
+{"current_steps": 128, "total_steps": 213, "loss": 0.48357316851615906, "lr": 4.2218893451814005e-06, "epoch": 1.8106666666666666, "percentage": 60.09, "elapsed_time": "1:08:43", "remaining_time": "0:45:38"}
+{"current_steps": 129, "total_steps": 213, "loss": 0.49349913001060486, "lr": 4.140759581643386e-06, "epoch": 1.8248888888888888, "percentage": 60.56, "elapsed_time": "1:09:14", "remaining_time": "0:45:05"}
+{"current_steps": 130, "total_steps": 213, "loss": 0.4969041347503662, "lr": 4.059862272583755e-06, "epoch": 1.8391111111111111, "percentage": 61.03, "elapsed_time": "1:09:44", "remaining_time": "0:44:31"}
+{"current_steps": 131, "total_steps": 213, "loss": 0.47194504737854004, "lr": 3.979219303543942e-06, "epoch": 1.8533333333333335, "percentage": 61.5, "elapsed_time": "1:10:15", "remaining_time": "0:43:58"}
+{"current_steps": 132, "total_steps": 213, "loss": 0.5020972490310669, "lr": 3.898852491257547e-06, "epoch": 1.8675555555555556, "percentage": 61.97, "elapsed_time": "1:10:45", "remaining_time": "0:43:25"}
+{"current_steps": 133, "total_steps": 213, "loss": 0.5002884268760681, "lr": 3.818783577748138e-06, "epoch": 1.8817777777777778, "percentage": 62.44, "elapsed_time": "1:11:15", "remaining_time": "0:42:51"}
+{"current_steps": 134, "total_steps": 213, "loss": 0.5007095336914062, "lr": 3.7390342244472886e-06, "epoch": 1.896, "percentage": 62.91, "elapsed_time": "1:11:44", "remaining_time": "0:42:17"}
+{"current_steps": 135, "total_steps": 213, "loss": 0.4763813316822052, "lr": 3.659626006334395e-06, "epoch": 1.9102222222222223, "percentage": 63.38, "elapsed_time": "1:12:13", "remaining_time": "0:41:43"}
+{"current_steps": 136, "total_steps": 213, "loss": 0.48733818531036377, "lr": 3.5805804060998926e-06, "epoch": 1.9244444444444444, "percentage": 63.85, "elapsed_time": "1:12:41", "remaining_time": "0:41:09"}
+{"current_steps": 137, "total_steps": 213, "loss": 0.5118749141693115, "lr": 3.501918808333453e-06, "epoch": 1.9386666666666668, "percentage": 64.32, "elapsed_time": "1:13:11", "remaining_time": "0:40:36"}
+{"current_steps": 138, "total_steps": 213, "loss": 0.5178316831588745, "lr": 3.4236624937386874e-06, "epoch": 1.952888888888889, "percentage": 64.79, "elapsed_time": "1:13:40", "remaining_time": "0:40:02"}
+{"current_steps": 139, "total_steps": 213, "loss": 0.4853537678718567, "lr": 3.3458326333759927e-06, "epoch": 1.967111111111111, "percentage": 65.26, "elapsed_time": "1:14:11", "remaining_time": "0:39:29"}
+{"current_steps": 140, "total_steps": 213, "loss": 0.49210506677627563, "lr": 3.268450282935026e-06, "epoch": 1.9813333333333332, "percentage": 65.73, "elapsed_time": "1:14:40", "remaining_time": "0:38:56"}
+{"current_steps": 141, "total_steps": 213, "loss": 0.47841814160346985, "lr": 3.1915363770384223e-06, "epoch": 1.9955555555555555, "percentage": 66.2, "elapsed_time": "1:15:11", "remaining_time": "0:38:23"}
+{"current_steps": 142, "total_steps": 213, "loss": 0.5034412145614624, "lr": 3.1151117235782346e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "1:15:21", "remaining_time": "0:37:40"}
+{"current_steps": 143, "total_steps": 213, "loss": 0.4864930808544159, "lr": 3.0391969980866874e-06, "epoch": 2.014222222222222, "percentage": 67.14, "elapsed_time": "1:16:43", "remaining_time": "0:37:33"}
+{"current_steps": 144, "total_steps": 213, "loss": 0.4642598032951355, "lr": 2.963812738142713e-06, "epoch": 2.0284444444444443, "percentage": 67.61, "elapsed_time": "1:17:14", "remaining_time": "0:37:00"}
+{"current_steps": 145, "total_steps": 213, "loss": 0.48541027307510376, "lr": 2.8889793378158284e-06, "epoch": 2.042666666666667, "percentage": 68.08, "elapsed_time": "1:17:43", "remaining_time": "0:36:27"}
+{"current_steps": 146, "total_steps": 213, "loss": 0.47221142053604126, "lr": 2.814717042148827e-06, "epoch": 2.056888888888889, "percentage": 68.54, "elapsed_time": "1:18:13", "remaining_time": "0:35:54"}
+{"current_steps": 147, "total_steps": 213, "loss": 0.46124035120010376, "lr": 2.7410459416807856e-06, "epoch": 2.071111111111111, "percentage": 69.01, "elapsed_time": "1:18:44", "remaining_time": "0:35:21"}
+{"current_steps": 148, "total_steps": 213, "loss": 0.4869857430458069, "lr": 2.6679859670118785e-06, "epoch": 2.0853333333333333, "percentage": 69.48, "elapsed_time": "1:19:13", "remaining_time": "0:34:47"}
+{"current_steps": 149, "total_steps": 213, "loss": 0.45158863067626953, "lr": 2.5955568834114523e-06, "epoch": 2.0995555555555554, "percentage": 69.95, "elapsed_time": "1:19:43", "remaining_time": "0:34:14"}
+{"current_steps": 150, "total_steps": 213, "loss": 0.4742748439311981, "lr": 2.523778285470835e-06, "epoch": 2.113777777777778, "percentage": 70.42, "elapsed_time": "1:20:14", "remaining_time": "0:33:42"}
+{"current_steps": 150, "total_steps": 213, "eval_loss": 0.5196705460548401, "epoch": 2.113777777777778, "percentage": 70.42, "elapsed_time": "1:20:30", "remaining_time": "0:33:48"}
+{"current_steps": 151, "total_steps": 213, "loss": 0.4526304602622986, "lr": 2.452669591802307e-06, "epoch": 2.128, "percentage": 70.89, "elapsed_time": "1:20:58", "remaining_time": "0:33:14"}
+{"current_steps": 152, "total_steps": 213, "loss": 0.4651503562927246, "lr": 2.3822500397857016e-06, "epoch": 2.1422222222222222, "percentage": 71.36, "elapsed_time": "1:21:28", "remaining_time": "0:32:41"}
+{"current_steps": 153, "total_steps": 213, "loss": 0.48414769768714905, "lr": 2.3125386803640188e-06, "epoch": 2.1564444444444444, "percentage": 71.83, "elapsed_time": "1:21:58", "remaining_time": "0:32:08"}
+{"current_steps": 154, "total_steps": 213, "loss": 0.462248295545578, "lr": 2.243554372889479e-06, "epoch": 2.1706666666666665, "percentage": 72.3, "elapsed_time": "1:22:28", "remaining_time": "0:31:35"}
+{"current_steps": 155, "total_steps": 213, "loss": 0.4559134244918823, "lr": 2.1753157800214107e-06, "epoch": 2.1848888888888887, "percentage": 72.77, "elapsed_time": "1:22:58", "remaining_time": "0:31:03"}
+{"current_steps": 156, "total_steps": 213, "loss": 0.48357266187667847, "lr": 2.1078413626773547e-06, "epoch": 2.1991111111111112, "percentage": 73.24, "elapsed_time": "1:23:28", "remaining_time": "0:30:30"}
+{"current_steps": 157, "total_steps": 213, "loss": 0.4366765022277832, "lr": 2.0411493750387423e-06, "epoch": 2.2133333333333334, "percentage": 73.71, "elapsed_time": "1:23:57", "remaining_time": "0:29:56"}
+{"current_steps": 158, "total_steps": 213, "loss": 0.4868413209915161, "lr": 1.9752578596124955e-06, "epoch": 2.2275555555555555, "percentage": 74.18, "elapsed_time": "1:24:26", "remaining_time": "0:29:23"}
+{"current_steps": 159, "total_steps": 213, "loss": 0.46049410104751587, "lr": 1.9101846423499113e-06, "epoch": 2.2417777777777776, "percentage": 74.65, "elapsed_time": "1:24:55", "remaining_time": "0:28:50"}
+{"current_steps": 160, "total_steps": 213, "loss": 0.4605860412120819, "lr": 1.8459473278241125e-06, "epoch": 2.2560000000000002, "percentage": 75.12, "elapsed_time": "1:25:25", "remaining_time": "0:28:17"}
+{"current_steps": 161, "total_steps": 213, "loss": 0.46191370487213135, "lr": 1.7825632944674016e-06, "epoch": 2.2702222222222224, "percentage": 75.59, "elapsed_time": "1:25:56", "remaining_time": "0:27:45"}
+{"current_steps": 162, "total_steps": 213, "loss": 0.4780347943305969, "lr": 1.7200496898697832e-06, "epoch": 2.2844444444444445, "percentage": 76.06, "elapsed_time": "1:26:25", "remaining_time": "0:27:12"}
+{"current_steps": 163, "total_steps": 213, "loss": 0.4648103713989258, "lr": 1.6584234261399535e-06, "epoch": 2.2986666666666666, "percentage": 76.53, "elapsed_time": "1:26:56", "remaining_time": "0:26:40"}
+{"current_steps": 164, "total_steps": 213, "loss": 0.46155521273612976, "lr": 1.5977011753299726e-06, "epoch": 2.3128888888888888, "percentage": 77.0, "elapsed_time": "1:27:24", "remaining_time": "0:26:07"}
+{"current_steps": 165, "total_steps": 213, "loss": 0.49238717555999756, "lr": 1.5378993649249053e-06, "epoch": 2.327111111111111, "percentage": 77.46, "elapsed_time": "1:27:52", "remaining_time": "0:25:33"}
+{"current_steps": 166, "total_steps": 213, "loss": 0.46214908361434937, "lr": 1.4790341733986085e-06, "epoch": 2.3413333333333335, "percentage": 77.93, "elapsed_time": "1:28:22", "remaining_time": "0:25:01"}
+{"current_steps": 167, "total_steps": 213, "loss": 0.44751304388046265, "lr": 1.4211215258368866e-06, "epoch": 2.3555555555555556, "percentage": 78.4, "elapsed_time": "1:28:53", "remaining_time": "0:24:29"}
+{"current_steps": 168, "total_steps": 213, "loss": 0.4523189067840576, "lr": 1.3641770896292083e-06, "epoch": 2.3697777777777778, "percentage": 78.87, "elapsed_time": "1:29:24", "remaining_time": "0:23:56"}
+{"current_steps": 169, "total_steps": 213, "loss": 0.46704721450805664, "lr": 1.3082162702301276e-06, "epoch": 2.384, "percentage": 79.34, "elapsed_time": "1:29:54", "remaining_time": "0:23:24"}
+{"current_steps": 170, "total_steps": 213, "loss": 0.47263163328170776, "lr": 1.2532542069915722e-06, "epoch": 2.398222222222222, "percentage": 79.81, "elapsed_time": "1:30:23", "remaining_time": "0:22:51"}
+{"current_steps": 171, "total_steps": 213, "loss": 0.4592151641845703, "lr": 1.1993057690671174e-06, "epoch": 2.4124444444444446, "percentage": 80.28, "elapsed_time": "1:30:53", "remaining_time": "0:22:19"}
+{"current_steps": 172, "total_steps": 213, "loss": 0.4800827205181122, "lr": 1.1463855513893695e-06, "epoch": 2.4266666666666667, "percentage": 80.75, "elapsed_time": "1:31:24", "remaining_time": "0:21:47"}
+{"current_steps": 173, "total_steps": 213, "loss": 0.4688478112220764, "lr": 1.0945078707215224e-06, "epoch": 2.440888888888889, "percentage": 81.22, "elapsed_time": "1:31:53", "remaining_time": "0:21:14"}
+{"current_steps": 174, "total_steps": 213, "loss": 0.46817073225975037, "lr": 1.0436867617841768e-06, "epoch": 2.455111111111111, "percentage": 81.69, "elapsed_time": "1:32:21", "remaining_time": "0:20:42"}
+{"current_steps": 175, "total_steps": 213, "loss": 0.4763898253440857, "lr": 9.939359734584552e-07, "epoch": 2.469333333333333, "percentage": 82.16, "elapsed_time": "1:32:51", "remaining_time": "0:20:09"}
+{"current_steps": 176, "total_steps": 213, "loss": 0.480793833732605, "lr": 9.452689650664515e-07, "epoch": 2.4835555555555557, "percentage": 82.63, "elapsed_time": "1:33:21", "remaining_time": "0:19:37"}
+{"current_steps": 177, "total_steps": 213, "loss": 0.4694904088973999, "lr": 8.976989027300265e-07, "epoch": 2.497777777777778, "percentage": 83.1, "elapsed_time": "1:33:51", "remaining_time": "0:19:05"}
+{"current_steps": 178, "total_steps": 213, "loss": 0.4877663254737854, "lr": 8.512386558088919e-07, "epoch": 2.512, "percentage": 83.57, "elapsed_time": "1:34:20", "remaining_time": "0:18:33"}
+{"current_steps": 179, "total_steps": 213, "loss": 0.46579453349113464, "lr": 8.059007934190194e-07, "epoch": 2.526222222222222, "percentage": 84.04, "elapsed_time": "1:34:51", "remaining_time": "0:18:00"}
+{"current_steps": 180, "total_steps": 213, "loss": 0.4954630434513092, "lr": 7.61697581032243e-07, "epoch": 2.5404444444444443, "percentage": 84.51, "elapsed_time": "1:35:20", "remaining_time": "0:17:28"}
+{"current_steps": 181, "total_steps": 213, "loss": 0.48210158944129944, "lr": 7.186409771580355e-07, "epoch": 2.554666666666667, "percentage": 84.98, "elapsed_time": "1:35:51", "remaining_time": "0:16:56"}
+{"current_steps": 182, "total_steps": 213, "loss": 0.4673936069011688, "lr": 6.76742630108298e-07, "epoch": 2.568888888888889, "percentage": 85.45, "elapsed_time": "1:36:21", "remaining_time": "0:16:24"}
+{"current_steps": 183, "total_steps": 213, "loss": 0.46786054968833923, "lr": 6.360138748461015e-07, "epoch": 2.583111111111111, "percentage": 85.92, "elapsed_time": "1:36:52", "remaining_time": "0:15:52"}
+{"current_steps": 184, "total_steps": 213, "loss": 0.45768898725509644, "lr": 5.964657299191712e-07, "epoch": 2.5973333333333333, "percentage": 86.38, "elapsed_time": "1:37:22", "remaining_time": "0:15:20"}
+{"current_steps": 185, "total_steps": 213, "loss": 0.468585342168808, "lr": 5.581088944789953e-07, "epoch": 2.6115555555555554, "percentage": 86.85, "elapsed_time": "1:37:53", "remaining_time": "0:14:48"}
+{"current_steps": 186, "total_steps": 213, "loss": 0.4843568205833435, "lr": 5.20953745386329e-07, "epoch": 2.6257777777777775, "percentage": 87.32, "elapsed_time": "1:38:23", "remaining_time": "0:14:16"}
+{"current_steps": 187, "total_steps": 213, "loss": 0.4747229218482971, "lr": 4.850103344038853e-07, "epoch": 2.64, "percentage": 87.79, "elapsed_time": "1:38:52", "remaining_time": "0:13:44"}
+{"current_steps": 188, "total_steps": 213, "loss": 0.44664108753204346, "lr": 4.502883854769935e-07, "epoch": 2.6542222222222223, "percentage": 88.26, "elapsed_time": "1:39:22", "remaining_time": "0:13:12"}
+{"current_steps": 189, "total_steps": 213, "loss": 0.47903192043304443, "lr": 4.167972921029262e-07, "epoch": 2.6684444444444444, "percentage": 88.73, "elapsed_time": "1:39:52", "remaining_time": "0:12:40"}
+{"current_steps": 190, "total_steps": 213, "loss": 0.4844057559967041, "lr": 3.8454611478963235e-07, "epoch": 2.6826666666666665, "percentage": 89.2, "elapsed_time": "1:40:21", "remaining_time": "0:12:08"}
+{"current_steps": 191, "total_steps": 213, "loss": 0.4564388394355774, "lr": 3.535435786045538e-07, "epoch": 2.696888888888889, "percentage": 89.67, "elapsed_time": "1:40:50", "remaining_time": "0:11:36"}
+{"current_steps": 192, "total_steps": 213, "loss": 0.47008293867111206, "lr": 3.237980708141919e-07, "epoch": 2.7111111111111112, "percentage": 90.14, "elapsed_time": "1:41:20", "remaining_time": "0:11:05"}
+{"current_steps": 193, "total_steps": 213, "loss": 0.479957640171051, "lr": 2.9531763861505967e-07, "epoch": 2.7253333333333334, "percentage": 90.61, "elapsed_time": "1:41:49", "remaining_time": "0:10:33"}
+{"current_steps": 194, "total_steps": 213, "loss": 0.44965675473213196, "lr": 2.681099869566328e-07, "epoch": 2.7395555555555555, "percentage": 91.08, "elapsed_time": "1:42:18", "remaining_time": "0:10:01"}
+{"current_steps": 195, "total_steps": 213, "loss": 0.4747314453125, "lr": 2.4218247645689306e-07, "epoch": 2.7537777777777777, "percentage": 91.55, "elapsed_time": "1:42:48", "remaining_time": "0:09:29"}
+{"current_steps": 196, "total_steps": 213, "loss": 0.45799821615219116, "lr": 2.175421214110235e-07, "epoch": 2.768, "percentage": 92.02, "elapsed_time": "1:43:18", "remaining_time": "0:08:57"}
+{"current_steps": 197, "total_steps": 213, "loss": 0.47467684745788574, "lr": 1.941955878938029e-07, "epoch": 2.7822222222222224, "percentage": 92.49, "elapsed_time": "1:43:48", "remaining_time": "0:08:25"}
+{"current_steps": 198, "total_steps": 213, "loss": 0.4817090332508087, "lr": 1.721491919561913e-07, "epoch": 2.7964444444444445, "percentage": 92.96, "elapsed_time": "1:44:17", "remaining_time": "0:07:54"}
+{"current_steps": 199, "total_steps": 213, "loss": 0.4649164080619812, "lr": 1.514088979166256e-07, "epoch": 2.8106666666666666, "percentage": 93.43, "elapsed_time": "1:44:47", "remaining_time": "0:07:22"}
+{"current_steps": 200, "total_steps": 213, "loss": 0.4765157699584961, "lr": 1.3198031674745814e-07, "epoch": 2.824888888888889, "percentage": 93.9, "elapsed_time": "1:45:17", "remaining_time": "0:06:50"}
+{"current_steps": 200, "total_steps": 213, "eval_loss": 0.5171427726745605, "epoch": 2.824888888888889, "percentage": 93.9, "elapsed_time": "1:45:27", "remaining_time": "0:06:51"}
+{"current_steps": 201, "total_steps": 213, "loss": 0.46831822395324707, "lr": 1.138687045569975e-07, "epoch": 2.8391111111111114, "percentage": 94.37, "elapsed_time": "1:45:58", "remaining_time": "0:06:19"}
+{"current_steps": 202, "total_steps": 213, "loss": 0.47398146986961365, "lr": 9.70789611675449e-08, "epoch": 2.8533333333333335, "percentage": 94.84, "elapsed_time": "1:46:28", "remaining_time": "0:05:47"}
+{"current_steps": 203, "total_steps": 213, "loss": 0.45744937658309937, "lr": 8.161562878982399e-08, "epoch": 2.8675555555555556, "percentage": 95.31, "elapsed_time": "1:46:57", "remaining_time": "0:05:16"}
+{"current_steps": 204, "total_steps": 213, "loss": 0.48529934883117676, "lr": 6.74828907941516e-08, "epoch": 2.8817777777777778, "percentage": 95.77, "elapsed_time": "1:47:26", "remaining_time": "0:04:44"}
+{"current_steps": 205, "total_steps": 213, "loss": 0.4858051836490631, "lr": 5.468457057869358e-08, "epoch": 2.896, "percentage": 96.24, "elapsed_time": "1:47:56", "remaining_time": "0:04:12"}
+{"current_steps": 206, "total_steps": 213, "loss": 0.4590516984462738, "lr": 4.322413053509944e-08, "epoch": 2.910222222222222, "percentage": 96.71, "elapsed_time": "1:48:28", "remaining_time": "0:03:41"}
+{"current_steps": 207, "total_steps": 213, "loss": 0.45788976550102234, "lr": 3.31046711118066e-08, "epoch": 2.924444444444444, "percentage": 97.18, "elapsed_time": "1:48:57", "remaining_time": "0:03:09"}
+{"current_steps": 208, "total_steps": 213, "loss": 0.4702548086643219, "lr": 2.4328929975260262e-08, "epoch": 2.9386666666666668, "percentage": 97.65, "elapsed_time": "1:49:27", "remaining_time": "0:02:37"}
+{"current_steps": 209, "total_steps": 213, "loss": 0.4560105800628662, "lr": 1.6899281269279756e-08, "epoch": 2.952888888888889, "percentage": 98.12, "elapsed_time": "1:49:56", "remaining_time": "0:02:06"}
+{"current_steps": 210, "total_steps": 213, "loss": 0.46400371193885803, "lr": 1.0817734972768946e-08, "epoch": 2.967111111111111, "percentage": 98.59, "elapsed_time": "1:50:25", "remaining_time": "0:01:34"}
+{"current_steps": 211, "total_steps": 213, "loss": 0.48368915915489197, "lr": 6.085936355947897e-09, "epoch": 2.981333333333333, "percentage": 99.06, "elapsed_time": "1:50:55", "remaining_time": "0:01:03"}
+{"current_steps": 212, "total_steps": 213, "loss": 0.45437300205230713, "lr": 2.7051655352494654e-09, "epoch": 2.9955555555555557, "percentage": 99.53, "elapsed_time": "1:51:24", "remaining_time": "0:00:31"}
+{"current_steps": 213, "total_steps": 213, "loss": 0.5508654713630676, "lr": 6.763371270035457e-10, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:51:34", "remaining_time": "0:00:00"}
+{"current_steps": 213, "total_steps": 213, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:52:32", "remaining_time": "0:00:00"}

qwen2.5-1.5b-instruct/trainer_state.json

@@ -0,0 +1,1566 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 50,
+  "global_step": 213,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.014222222222222223,
+      "grad_norm": 0.03586147725582123,
+      "learning_rate": 0.0,
+      "loss": 0.9098724722862244,
+      "step": 1
+    },
+    {
+      "epoch": 0.028444444444444446,
+      "grad_norm": 0.03577122464776039,
+      "learning_rate": 4.5454545454545457e-07,
+      "loss": 0.9084522724151611,
+      "step": 2
+    },
+    {
+      "epoch": 0.042666666666666665,
+      "grad_norm": 0.031653374433517456,
+      "learning_rate": 9.090909090909091e-07,
+      "loss": 0.8834755420684814,
+      "step": 3
+    },
+    {
+      "epoch": 0.05688888888888889,
+      "grad_norm": 0.025831686332821846,
+      "learning_rate": 1.3636363636363636e-06,
+      "loss": 0.871230959892273,
+      "step": 4
+    },
+    {
+      "epoch": 0.07111111111111111,
+      "grad_norm": 0.019876576960086823,
+      "learning_rate": 1.8181818181818183e-06,
+      "loss": 0.7917206287384033,
+      "step": 5
+    },
+    {
+      "epoch": 0.08533333333333333,
+      "grad_norm": 0.018677273765206337,
+      "learning_rate": 2.2727272727272728e-06,
+      "loss": 0.8436126708984375,
+      "step": 6
+    },
+    {
+      "epoch": 0.09955555555555555,
+      "grad_norm": 0.017528358846902847,
+      "learning_rate": 2.7272727272727272e-06,
+      "loss": 0.8075190782546997,
+      "step": 7
+    },
+    {
+      "epoch": 0.11377777777777778,
+      "grad_norm": 0.01399513240903616,
+      "learning_rate": 3.181818181818182e-06,
+      "loss": 0.7754716873168945,
+      "step": 8
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 0.012644859962165356,
+      "learning_rate": 3.6363636363636366e-06,
+      "loss": 0.7459083199501038,
+      "step": 9
+    },
+    {
+      "epoch": 0.14222222222222222,
+      "grad_norm": 0.01209743320941925,
+      "learning_rate": 4.0909090909090915e-06,
+      "loss": 0.7365868091583252,
+      "step": 10
+    },
+    {
+      "epoch": 0.15644444444444444,
+      "grad_norm": 0.012133832089602947,
+      "learning_rate": 4.5454545454545455e-06,
+      "loss": 0.7119501829147339,
+      "step": 11
+    },
+    {
+      "epoch": 0.17066666666666666,
+      "grad_norm": 0.010017997585237026,
+      "learning_rate": 5e-06,
+      "loss": 0.6901087760925293,
+      "step": 12
+    },
+    {
+      "epoch": 0.18488888888888888,
+      "grad_norm": 0.009233366698026657,
+      "learning_rate": 5.4545454545454545e-06,
+      "loss": 0.6611638069152832,
+      "step": 13
+    },
+    {
+      "epoch": 0.1991111111111111,
+      "grad_norm": 0.00782010331749916,
+      "learning_rate": 5.90909090909091e-06,
+      "loss": 0.6715224981307983,
+      "step": 14
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 0.007341764867305756,
+      "learning_rate": 6.363636363636364e-06,
+      "loss": 0.6277110576629639,
+      "step": 15
+    },
+    {
+      "epoch": 0.22755555555555557,
+      "grad_norm": 0.00713470159098506,
+      "learning_rate": 6.818181818181818e-06,
+      "loss": 0.6689565181732178,
+      "step": 16
+    },
+    {
+      "epoch": 0.24177777777777779,
+      "grad_norm": 0.0067572277039289474,
+      "learning_rate": 7.272727272727273e-06,
+      "loss": 0.6363875865936279,
+      "step": 17
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 0.006228511221706867,
+      "learning_rate": 7.727272727272727e-06,
+      "loss": 0.6257224678993225,
+      "step": 18
+    },
+    {
+      "epoch": 0.2702222222222222,
+      "grad_norm": 0.006048806011676788,
+      "learning_rate": 8.181818181818183e-06,
+      "loss": 0.6355900764465332,
+      "step": 19
+    },
+    {
+      "epoch": 0.28444444444444444,
+      "grad_norm": 0.005988306365907192,
+      "learning_rate": 8.636363636363637e-06,
+      "loss": 0.6338369846343994,
+      "step": 20
+    },
+    {
+      "epoch": 0.2986666666666667,
+      "grad_norm": 0.005441761109977961,
+      "learning_rate": 9.090909090909091e-06,
+      "loss": 0.6133573055267334,
+      "step": 21
+    },
+    {
+      "epoch": 0.3128888888888889,
+      "grad_norm": 0.005174445919692516,
+      "learning_rate": 9.545454545454547e-06,
+      "loss": 0.6042410135269165,
+      "step": 22
+    },
+    {
+      "epoch": 0.32711111111111113,
+      "grad_norm": 0.005199746694415808,
+      "learning_rate": 1e-05,
+      "loss": 0.602219820022583,
+      "step": 23
+    },
+    {
+      "epoch": 0.3413333333333333,
+      "grad_norm": 0.005485028959810734,
+      "learning_rate": 9.999323662872998e-06,
+      "loss": 0.6062123775482178,
+      "step": 24
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 0.004896003287285566,
+      "learning_rate": 9.99729483446475e-06,
+      "loss": 0.6077945232391357,
+      "step": 25
+    },
+    {
+      "epoch": 0.36977777777777776,
+      "grad_norm": 0.00495151337236166,
+      "learning_rate": 9.993914063644053e-06,
+      "loss": 0.5923135280609131,
+      "step": 26
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 0.004744194447994232,
+      "learning_rate": 9.989182265027232e-06,
+      "loss": 0.5860621929168701,
+      "step": 27
+    },
+    {
+      "epoch": 0.3982222222222222,
+      "grad_norm": 0.004471767693758011,
+      "learning_rate": 9.98310071873072e-06,
+      "loss": 0.5823097229003906,
+      "step": 28
+    },
+    {
+      "epoch": 0.41244444444444445,
+      "grad_norm": 0.004788320977240801,
+      "learning_rate": 9.975671070024741e-06,
+      "loss": 0.5872600078582764,
+      "step": 29
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 0.0044632842764258385,
+      "learning_rate": 9.966895328888195e-06,
+      "loss": 0.6070278286933899,
+      "step": 30
+    },
+    {
+      "epoch": 0.4408888888888889,
+      "grad_norm": 0.004317905753850937,
+      "learning_rate": 9.956775869464901e-06,
+      "loss": 0.5780316591262817,
+      "step": 31
+    },
+    {
+      "epoch": 0.45511111111111113,
+      "grad_norm": 0.004291852004826069,
+      "learning_rate": 9.945315429421307e-06,
+      "loss": 0.5697590112686157,
+      "step": 32
+    },
+    {
+      "epoch": 0.4693333333333333,
+      "grad_norm": 0.003922830801457167,
+      "learning_rate": 9.932517109205849e-06,
+      "loss": 0.5747107267379761,
+      "step": 33
+    },
+    {
+      "epoch": 0.48355555555555557,
+      "grad_norm": 0.0041889771819114685,
+      "learning_rate": 9.918384371210178e-06,
+      "loss": 0.6021177172660828,
+      "step": 34
+    },
+    {
+      "epoch": 0.49777777777777776,
+      "grad_norm": 0.004147357773035765,
+      "learning_rate": 9.902921038832456e-06,
+      "loss": 0.5805741548538208,
+      "step": 35
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 0.0040724254213273525,
+      "learning_rate": 9.886131295443003e-06,
+      "loss": 0.5483200550079346,
+      "step": 36
+    },
+    {
+      "epoch": 0.5262222222222223,
+      "grad_norm": 0.004085644613951445,
+      "learning_rate": 9.868019683252543e-06,
+      "loss": 0.557392954826355,
+      "step": 37
+    },
+    {
+      "epoch": 0.5404444444444444,
+      "grad_norm": 0.004289102274924517,
+      "learning_rate": 9.848591102083375e-06,
+      "loss": 0.590857207775116,
+      "step": 38
+    },
+    {
+      "epoch": 0.5546666666666666,
+      "grad_norm": 0.0040345704182982445,
+      "learning_rate": 9.82785080804381e-06,
+      "loss": 0.5750541090965271,
+      "step": 39
+    },
+    {
+      "epoch": 0.5688888888888889,
+      "grad_norm": 0.004034748766571283,
+      "learning_rate": 9.805804412106197e-06,
+      "loss": 0.5949826240539551,
+      "step": 40
+    },
+    {
+      "epoch": 0.5831111111111111,
+      "grad_norm": 0.003911909181624651,
+      "learning_rate": 9.782457878588977e-06,
+      "loss": 0.5623177289962769,
+      "step": 41
+    },
+    {
+      "epoch": 0.5973333333333334,
+      "grad_norm": 0.0037001846358180046,
+      "learning_rate": 9.75781752354311e-06,
+      "loss": 0.5465081930160522,
+      "step": 42
+    },
+    {
+      "epoch": 0.6115555555555555,
+      "grad_norm": 0.0037095139268785715,
+      "learning_rate": 9.731890013043367e-06,
+      "loss": 0.5752100944519043,
+      "step": 43
+    },
+    {
+      "epoch": 0.6257777777777778,
+      "grad_norm": 0.003655617358162999,
+      "learning_rate": 9.704682361384941e-06,
+      "loss": 0.5452020168304443,
+      "step": 44
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.003784338477998972,
+      "learning_rate": 9.676201929185809e-06,
+      "loss": 0.5616332292556763,
+      "step": 45
+    },
+    {
+      "epoch": 0.6542222222222223,
+      "grad_norm": 0.003718078136444092,
+      "learning_rate": 9.646456421395447e-06,
+      "loss": 0.5558297634124756,
+      "step": 46
+    },
+    {
+      "epoch": 0.6684444444444444,
+      "grad_norm": 0.00395169947296381,
+      "learning_rate": 9.615453885210368e-06,
+      "loss": 0.5600595474243164,
+      "step": 47
+    },
+    {
+      "epoch": 0.6826666666666666,
+      "grad_norm": 0.003555440343916416,
+      "learning_rate": 9.583202707897075e-06,
+      "loss": 0.5372895002365112,
+      "step": 48
+    },
+    {
+      "epoch": 0.6968888888888889,
+      "grad_norm": 0.0037386869080364704,
+      "learning_rate": 9.549711614523007e-06,
+      "loss": 0.5322733521461487,
+      "step": 49
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 0.003739988896995783,
+      "learning_rate": 9.514989665596114e-06,
+      "loss": 0.5380419492721558,
+      "step": 50
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "eval_loss": 0.5587145090103149,
+      "eval_runtime": 8.7676,
+      "eval_samples_per_second": 22.811,
+      "eval_steps_per_second": 11.406,
+      "step": 50
+    },
+    {
+      "epoch": 0.7253333333333334,
+      "grad_norm": 0.0037539806216955185,
+      "learning_rate": 9.479046254613673e-06,
+      "loss": 0.5472225546836853,
+      "step": 51
+    },
+    {
+      "epoch": 0.7395555555555555,
+      "grad_norm": 0.003411181503906846,
+      "learning_rate": 9.441891105521005e-06,
+      "loss": 0.5134032964706421,
+      "step": 52
+    },
+    {
+      "epoch": 0.7537777777777778,
+      "grad_norm": 0.0037538670003414154,
+      "learning_rate": 9.40353427008083e-06,
+      "loss": 0.5361013412475586,
+      "step": 53
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 0.0036495670210570097,
+      "learning_rate": 9.3639861251539e-06,
+      "loss": 0.5299779772758484,
+      "step": 54
+    },
+    {
+      "epoch": 0.7822222222222223,
+      "grad_norm": 0.0037342547439038754,
+      "learning_rate": 9.323257369891702e-06,
+      "loss": 0.5607945919036865,
+      "step": 55
+    },
+    {
+      "epoch": 0.7964444444444444,
+      "grad_norm": 0.003572584595531225,
+      "learning_rate": 9.281359022841966e-06,
+      "loss": 0.5528460741043091,
+      "step": 56
+    },
+    {
+      "epoch": 0.8106666666666666,
+      "grad_norm": 0.003770101349800825,
+      "learning_rate": 9.238302418967757e-06,
+      "loss": 0.5440288186073303,
+      "step": 57
+    },
+    {
+      "epoch": 0.8248888888888889,
+      "grad_norm": 0.0036679303739219904,
+      "learning_rate": 9.194099206580981e-06,
+      "loss": 0.5564252138137817,
+      "step": 58
+    },
+    {
+      "epoch": 0.8391111111111111,
+      "grad_norm": 0.003834612900391221,
+      "learning_rate": 9.14876134419111e-06,
+      "loss": 0.5473330020904541,
+      "step": 59
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 0.003683249931782484,
+      "learning_rate": 9.102301097269974e-06,
+      "loss": 0.5463743209838867,
+      "step": 60
+    },
+    {
+      "epoch": 0.8675555555555555,
+      "grad_norm": 0.0036777963396161795,
+      "learning_rate": 9.05473103493355e-06,
+      "loss": 0.524878740310669,
+      "step": 61
+    },
+    {
+      "epoch": 0.8817777777777778,
+      "grad_norm": 0.0038230482023209333,
+      "learning_rate": 9.006064026541549e-06,
+      "loss": 0.5563522577285767,
+      "step": 62
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 0.003645201213657856,
+      "learning_rate": 8.956313238215824e-06,
+      "loss": 0.5059154033660889,
+      "step": 63
+    },
+    {
+      "epoch": 0.9102222222222223,
+      "grad_norm": 0.0035886459518224,
+      "learning_rate": 8.905492129278478e-06,
+      "loss": 0.5312881469726562,
+      "step": 64
+    },
+    {
+      "epoch": 0.9244444444444444,
+      "grad_norm": 0.003721872577443719,
+      "learning_rate": 8.85361444861063e-06,
+      "loss": 0.5358959436416626,
+      "step": 65
+    },
+    {
+      "epoch": 0.9386666666666666,
+      "grad_norm": 0.003683999879285693,
+      "learning_rate": 8.800694230932885e-06,
+      "loss": 0.5442053079605103,
+      "step": 66
+    },
+    {
+      "epoch": 0.9528888888888889,
+      "grad_norm": 0.0036851842887699604,
+      "learning_rate": 8.74674579300843e-06,
+      "loss": 0.5263723731040955,
+      "step": 67
+    },
+    {
+      "epoch": 0.9671111111111111,
+      "grad_norm": 0.003754258854314685,
+      "learning_rate": 8.691783729769874e-06,
+      "loss": 0.5200538039207458,
+      "step": 68
+    },
+    {
+      "epoch": 0.9813333333333333,
+      "grad_norm": 0.0038373274728655815,
+      "learning_rate": 8.635822910370793e-06,
+      "loss": 0.5452108383178711,
+      "step": 69
+    },
+    {
+      "epoch": 0.9955555555555555,
+      "grad_norm": 0.0039480882696807384,
+      "learning_rate": 8.578878474163115e-06,
+      "loss": 0.5066030621528625,
+      "step": 70
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.005897017661482096,
+      "learning_rate": 8.520965826601394e-06,
+      "loss": 0.5380499958992004,
+      "step": 71
+    },
+    {
+      "epoch": 1.0142222222222221,
+      "grad_norm": 0.0037728557363152504,
+      "learning_rate": 8.462100635075097e-06,
+      "loss": 0.5328541398048401,
+      "step": 72
+    },
+    {
+      "epoch": 1.0284444444444445,
+      "grad_norm": 0.003953218925744295,
+      "learning_rate": 8.40229882467003e-06,
+      "loss": 0.5096005201339722,
+      "step": 73
+    },
+    {
+      "epoch": 1.0426666666666666,
+      "grad_norm": 0.0036587677896022797,
+      "learning_rate": 8.341576573860049e-06,
+      "loss": 0.4889724850654602,
+      "step": 74
+    },
+    {
+      "epoch": 1.056888888888889,
+      "grad_norm": 0.0038338187150657177,
+      "learning_rate": 8.279950310130218e-06,
+      "loss": 0.5157173871994019,
+      "step": 75
+    },
+    {
+      "epoch": 1.0711111111111111,
+      "grad_norm": 0.003540106350556016,
+      "learning_rate": 8.2174367055326e-06,
+      "loss": 0.49691659212112427,
+      "step": 76
+    },
+    {
+      "epoch": 1.0853333333333333,
+      "grad_norm": 0.0037315969821065664,
+      "learning_rate": 8.154052672175888e-06,
+      "loss": 0.4873769283294678,
+      "step": 77
+    },
+    {
+      "epoch": 1.0995555555555556,
+      "grad_norm": 0.003963674418628216,
+      "learning_rate": 8.08981535765009e-06,
+      "loss": 0.5266215801239014,
+      "step": 78
+    },
+    {
+      "epoch": 1.1137777777777778,
+      "grad_norm": 0.0037685995921492577,
+      "learning_rate": 8.024742140387506e-06,
+      "loss": 0.5039150714874268,
+      "step": 79
+    },
+    {
+      "epoch": 1.1280000000000001,
+      "grad_norm": 0.003613364417105913,
+      "learning_rate": 7.95885062496126e-06,
+      "loss": 0.4896891117095947,
+      "step": 80
+    },
+    {
+      "epoch": 1.1422222222222222,
+      "grad_norm": 0.0037347134202718735,
+      "learning_rate": 7.892158637322647e-06,
+      "loss": 0.45997822284698486,
+      "step": 81
+    },
+    {
+      "epoch": 1.1564444444444444,
+      "grad_norm": 0.0037277438677847385,
+      "learning_rate": 7.824684219978591e-06,
+      "loss": 0.4917220175266266,
+      "step": 82
+    },
+    {
+      "epoch": 1.1706666666666667,
+      "grad_norm": 0.0034888957161456347,
+      "learning_rate": 7.756445627110523e-06,
+      "loss": 0.5024806261062622,
+      "step": 83
+    },
+    {
+      "epoch": 1.1848888888888889,
+      "grad_norm": 0.004098390229046345,
+      "learning_rate": 7.68746131963598e-06,
+      "loss": 0.5110447406768799,
+      "step": 84
+    },
+    {
+      "epoch": 1.199111111111111,
+      "grad_norm": 0.0036922753788530827,
+      "learning_rate": 7.6177499602143e-06,
+      "loss": 0.5031975507736206,
+      "step": 85
+    },
+    {
+      "epoch": 1.2133333333333334,
+      "grad_norm": 0.0035749904345721006,
+      "learning_rate": 7.547330408197695e-06,
+      "loss": 0.4899296164512634,
+      "step": 86
+    },
+    {
+      "epoch": 1.2275555555555555,
+      "grad_norm": 0.003764625173062086,
+      "learning_rate": 7.476221714529167e-06,
+      "loss": 0.5040560960769653,
+      "step": 87
+    },
+    {
+      "epoch": 1.2417777777777779,
+      "grad_norm": 0.003831087611615658,
+      "learning_rate": 7.404443116588548e-06,
+      "loss": 0.5307536125183105,
+      "step": 88
+    },
+    {
+      "epoch": 1.256,
+      "grad_norm": 0.003740105777978897,
+      "learning_rate": 7.332014032988123e-06,
+      "loss": 0.5025057792663574,
+      "step": 89
+    },
+    {
+      "epoch": 1.2702222222222221,
+      "grad_norm": 0.0038286929484456778,
+      "learning_rate": 7.2589540583192165e-06,
+      "loss": 0.5043497085571289,
+      "step": 90
+    },
+    {
+      "epoch": 1.2844444444444445,
+      "grad_norm": 0.003593199420720339,
+      "learning_rate": 7.185282957851175e-06,
+      "loss": 0.4883122444152832,
+      "step": 91
+    },
+    {
+      "epoch": 1.2986666666666666,
+      "grad_norm": 0.003721701679751277,
+      "learning_rate": 7.111020662184174e-06,
+      "loss": 0.5055882930755615,
+      "step": 92
+    },
+    {
+      "epoch": 1.3128888888888888,
+      "grad_norm": 0.0036744684912264347,
+      "learning_rate": 7.036187261857289e-06,
+      "loss": 0.4962804615497589,
+      "step": 93
+    },
+    {
+      "epoch": 1.3271111111111111,
+      "grad_norm": 0.004013169556856155,
+      "learning_rate": 6.960803001913315e-06,
+      "loss": 0.524259090423584,
+      "step": 94
+    },
+    {
+      "epoch": 1.3413333333333333,
+      "grad_norm": 0.003746299771592021,
+      "learning_rate": 6.884888276421766e-06,
+      "loss": 0.5073269009590149,
+      "step": 95
+    },
+    {
+      "epoch": 1.3555555555555556,
+      "grad_norm": 0.0036679194308817387,
+      "learning_rate": 6.8084636229615786e-06,
+      "loss": 0.4886914789676666,
+      "step": 96
+    },
+    {
+      "epoch": 1.3697777777777778,
+      "grad_norm": 0.00375540042296052,
+      "learning_rate": 6.731549717064975e-06,
+      "loss": 0.4920746088027954,
+      "step": 97
+    },
+    {
+      "epoch": 1.384,
+      "grad_norm": 0.003901587100699544,
+      "learning_rate": 6.654167366624009e-06,
+      "loss": 0.503207266330719,
+      "step": 98
+    },
+    {
+      "epoch": 1.3982222222222223,
+      "grad_norm": 0.003911704756319523,
+      "learning_rate": 6.576337506261314e-06,
+      "loss": 0.5012996196746826,
+      "step": 99
+    },
+    {
+      "epoch": 1.4124444444444444,
+      "grad_norm": 0.0035876361653208733,
+      "learning_rate": 6.498081191666549e-06,
+      "loss": 0.5059630274772644,
+      "step": 100
+    },
+    {
+      "epoch": 1.4124444444444444,
+      "eval_loss": 0.5291631817817688,
+      "eval_runtime": 10.3556,
+      "eval_samples_per_second": 19.313,
+      "eval_steps_per_second": 9.657,
+      "step": 100
+    },
+    {
+      "epoch": 1.4266666666666667,
+      "grad_norm": 0.003729900810867548,
+      "learning_rate": 6.419419593900109e-06,
+      "loss": 0.4896056056022644,
+      "step": 101
+    },
+    {
+      "epoch": 1.4408888888888889,
+      "grad_norm": 0.003648703685030341,
+      "learning_rate": 6.340373993665607e-06,
+      "loss": 0.48181772232055664,
+      "step": 102
+    },
+    {
+      "epoch": 1.455111111111111,
+      "grad_norm": 0.0035914399195462465,
+      "learning_rate": 6.2609657755527135e-06,
+      "loss": 0.4775124192237854,
+      "step": 103
+    },
+    {
+      "epoch": 1.4693333333333334,
+      "grad_norm": 0.0035880866926163435,
+      "learning_rate": 6.1812164222518626e-06,
+      "loss": 0.5167958736419678,
+      "step": 104
+    },
+    {
+      "epoch": 1.4835555555555555,
+      "grad_norm": 0.003788268193602562,
+      "learning_rate": 6.101147508742456e-06,
+      "loss": 0.4946171045303345,
+      "step": 105
+    },
+    {
+      "epoch": 1.4977777777777779,
+      "grad_norm": 0.0036002870183438063,
+      "learning_rate": 6.020780696456059e-06,
+      "loss": 0.4849076569080353,
+      "step": 106
+    },
+    {
+      "epoch": 1.512,
+      "grad_norm": 0.0036388293374329805,
+      "learning_rate": 5.940137727416247e-06,
+      "loss": 0.4958712160587311,
+      "step": 107
+    },
+    {
+      "epoch": 1.5262222222222221,
+      "grad_norm": 0.0034927036613225937,
+      "learning_rate": 5.859240418356614e-06,
+      "loss": 0.4822971820831299,
+      "step": 108
+    },
+    {
+      "epoch": 1.5404444444444443,
+      "grad_norm": 0.0038439796771854162,
+      "learning_rate": 5.778110654818602e-06,
+      "loss": 0.5280419588088989,
+      "step": 109
+    },
+    {
+      "epoch": 1.5546666666666666,
+      "grad_norm": 0.003715698141604662,
+      "learning_rate": 5.696770385230679e-06,
+      "loss": 0.4952104687690735,
+      "step": 110
+    },
+    {
+      "epoch": 1.568888888888889,
+      "grad_norm": 0.0036385883577167988,
+      "learning_rate": 5.615241614970546e-06,
+      "loss": 0.4887908101081848,
+      "step": 111
+    },
+    {
+      "epoch": 1.5831111111111111,
+      "grad_norm": 0.0036841081455349922,
+      "learning_rate": 5.533546400411899e-06,
+      "loss": 0.4928241968154907,
+      "step": 112
+    },
+    {
+      "epoch": 1.5973333333333333,
+      "grad_norm": 0.0036721359938383102,
+      "learning_rate": 5.4517068429574215e-06,
+      "loss": 0.5109080076217651,
+      "step": 113
+    },
+    {
+      "epoch": 1.6115555555555554,
+      "grad_norm": 0.0037413975223898888,
+      "learning_rate": 5.3697450830595775e-06,
+      "loss": 0.48911499977111816,
+      "step": 114
+    },
+    {
+      "epoch": 1.6257777777777778,
+      "grad_norm": 0.003966668155044317,
+      "learning_rate": 5.287683294230855e-06,
+      "loss": 0.49537116289138794,
+      "step": 115
+    },
+    {
+      "epoch": 1.6400000000000001,
+      "grad_norm": 0.0036018763203173876,
+      "learning_rate": 5.20554367704505e-06,
+      "loss": 0.4613257348537445,
+      "step": 116
+    },
+    {
+      "epoch": 1.6542222222222223,
+      "grad_norm": 0.0038206754252314568,
+      "learning_rate": 5.123348453131242e-06,
+      "loss": 0.5043697357177734,
+      "step": 117
+    },
+    {
+      "epoch": 1.6684444444444444,
+      "grad_norm": 0.0037831810768693686,
+      "learning_rate": 5.041119859162068e-06,
+      "loss": 0.48968735337257385,
+      "step": 118
+    },
+    {
+      "epoch": 1.6826666666666665,
+      "grad_norm": 0.0038370522670447826,
+      "learning_rate": 4.958880140837934e-06,
+      "loss": 0.49605250358581543,
+      "step": 119
+    },
+    {
+      "epoch": 1.696888888888889,
+      "grad_norm": 0.003586502280086279,
+      "learning_rate": 4.876651546868759e-06,
+      "loss": 0.4839916229248047,
+      "step": 120
+    },
+    {
+      "epoch": 1.7111111111111112,
+      "grad_norm": 0.003694413462653756,
+      "learning_rate": 4.794456322954953e-06,
+      "loss": 0.5173561573028564,
+      "step": 121
+    },
+    {
+      "epoch": 1.7253333333333334,
+      "grad_norm": 0.003933500964194536,
+      "learning_rate": 4.7123167057691446e-06,
+      "loss": 0.5177811980247498,
+      "step": 122
+    },
+    {
+      "epoch": 1.7395555555555555,
+      "grad_norm": 0.0036068507470190525,
+      "learning_rate": 4.630254916940424e-06,
+      "loss": 0.5164836049079895,
+      "step": 123
+    },
+    {
+      "epoch": 1.7537777777777777,
+      "grad_norm": 0.00349752651527524,
+      "learning_rate": 4.548293157042581e-06,
+      "loss": 0.5077825784683228,
+      "step": 124
+    },
+    {
+      "epoch": 1.768,
+      "grad_norm": 0.0037042393814772367,
+      "learning_rate": 4.466453599588103e-06,
+      "loss": 0.5107009410858154,
+      "step": 125
+    },
+    {
+      "epoch": 1.7822222222222224,
+      "grad_norm": 0.003853494767099619,
+      "learning_rate": 4.384758385029457e-06,
+      "loss": 0.4728143811225891,
+      "step": 126
+    },
+    {
+      "epoch": 1.7964444444444445,
+      "grad_norm": 0.0038627111352980137,
+      "learning_rate": 4.3032296147693225e-06,
+      "loss": 0.4858134984970093,
+      "step": 127
+    },
+    {
+      "epoch": 1.8106666666666666,
+      "grad_norm": 0.003657885594293475,
+      "learning_rate": 4.2218893451814005e-06,
+      "loss": 0.48357316851615906,
+      "step": 128
+    },
+    {
+      "epoch": 1.8248888888888888,
+      "grad_norm": 0.00355988135561347,
+      "learning_rate": 4.140759581643386e-06,
+      "loss": 0.49349913001060486,
+      "step": 129
+    },
+    {
+      "epoch": 1.8391111111111111,
+      "grad_norm": 0.004014762118458748,
+      "learning_rate": 4.059862272583755e-06,
+      "loss": 0.4969041347503662,
+      "step": 130
+    },
+    {
+      "epoch": 1.8533333333333335,
+      "grad_norm": 0.003631556173786521,
+      "learning_rate": 3.979219303543942e-06,
+      "loss": 0.47194504737854004,
+      "step": 131
+    },
+    {
+      "epoch": 1.8675555555555556,
+      "grad_norm": 0.003577238181605935,
+      "learning_rate": 3.898852491257547e-06,
+      "loss": 0.5020972490310669,
+      "step": 132
+    },
+    {
+      "epoch": 1.8817777777777778,
+      "grad_norm": 0.003780671861022711,
+      "learning_rate": 3.818783577748138e-06,
+      "loss": 0.5002884268760681,
+      "step": 133
+    },
+    {
+      "epoch": 1.896,
+      "grad_norm": 0.003708280622959137,
+      "learning_rate": 3.7390342244472886e-06,
+      "loss": 0.5007095336914062,
+      "step": 134
+    },
+    {
+      "epoch": 1.9102222222222223,
+      "grad_norm": 0.003498840844258666,
+      "learning_rate": 3.659626006334395e-06,
+      "loss": 0.4763813316822052,
+      "step": 135
+    },
+    {
+      "epoch": 1.9244444444444444,
+      "grad_norm": 0.003659547306597233,
+      "learning_rate": 3.5805804060998926e-06,
+      "loss": 0.48733818531036377,
+      "step": 136
+    },
+    {
+      "epoch": 1.9386666666666668,
+      "grad_norm": 0.003515617921948433,
+      "learning_rate": 3.501918808333453e-06,
+      "loss": 0.5118749141693115,
+      "step": 137
+    },
+    {
+      "epoch": 1.952888888888889,
+      "grad_norm": 0.0036544103641062975,
+      "learning_rate": 3.4236624937386874e-06,
+      "loss": 0.5178316831588745,
+      "step": 138
+    },
+    {
+      "epoch": 1.967111111111111,
+      "grad_norm": 0.003433604259043932,
+      "learning_rate": 3.3458326333759927e-06,
+      "loss": 0.4853537678718567,
+      "step": 139
+    },
+    {
+      "epoch": 1.9813333333333332,
+      "grad_norm": 0.003547502215951681,
+      "learning_rate": 3.268450282935026e-06,
+      "loss": 0.49210506677627563,
+      "step": 140
+    },
+    {
+      "epoch": 1.9955555555555555,
+      "grad_norm": 0.003462104359641671,
+      "learning_rate": 3.1915363770384223e-06,
+      "loss": 0.47841814160346985,
+      "step": 141
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.005856912117451429,
+      "learning_rate": 3.1151117235782346e-06,
+      "loss": 0.5034412145614624,
+      "step": 142
+    },
+    {
+      "epoch": 2.014222222222222,
+      "grad_norm": 0.003923188429325819,
+      "learning_rate": 3.0391969980866874e-06,
+      "loss": 0.4864930808544159,
+      "step": 143
+    },
+    {
+      "epoch": 2.0284444444444443,
+      "grad_norm": 0.003596341237425804,
+      "learning_rate": 2.963812738142713e-06,
+      "loss": 0.4642598032951355,
+      "step": 144
+    },
+    {
+      "epoch": 2.042666666666667,
+      "grad_norm": 0.0038887078408151865,
+      "learning_rate": 2.8889793378158284e-06,
+      "loss": 0.48541027307510376,
+      "step": 145
+    },
+    {
+      "epoch": 2.056888888888889,
+      "grad_norm": 0.0034043709747493267,
+      "learning_rate": 2.814717042148827e-06,
+      "loss": 0.47221142053604126,
+      "step": 146
+    },
+    {
+      "epoch": 2.071111111111111,
+      "grad_norm": 0.0034274954814463854,
+      "learning_rate": 2.7410459416807856e-06,
+      "loss": 0.46124035120010376,
+      "step": 147
+    },
+    {
+      "epoch": 2.0853333333333333,
+      "grad_norm": 0.00352494022808969,
+      "learning_rate": 2.6679859670118785e-06,
+      "loss": 0.4869857430458069,
+      "step": 148
+    },
+    {
+      "epoch": 2.0995555555555554,
+      "grad_norm": 0.0035326213110238314,
+      "learning_rate": 2.5955568834114523e-06,
+      "loss": 0.45158863067626953,
+      "step": 149
+    },
+    {
+      "epoch": 2.113777777777778,
+      "grad_norm": 0.003645913675427437,
+      "learning_rate": 2.523778285470835e-06,
+      "loss": 0.4742748439311981,
+      "step": 150
+    },
+    {
+      "epoch": 2.113777777777778,
+      "eval_loss": 0.5196705460548401,
+      "eval_runtime": 15.8074,
+      "eval_samples_per_second": 12.652,
+      "eval_steps_per_second": 6.326,
+      "step": 150
+    },
+    {
+      "epoch": 2.128,
+      "grad_norm": 0.0036555698607116938,
+      "learning_rate": 2.452669591802307e-06,
+      "loss": 0.4526304602622986,
+      "step": 151
+    },
+    {
+      "epoch": 2.1422222222222222,
+      "grad_norm": 0.003359478199854493,
+      "learning_rate": 2.3822500397857016e-06,
+      "loss": 0.4651503562927246,
+      "step": 152
+    },
+    {
+      "epoch": 2.1564444444444444,
+      "grad_norm": 0.003462468506768346,
+      "learning_rate": 2.3125386803640188e-06,
+      "loss": 0.48414769768714905,
+      "step": 153
+    },
+    {
+      "epoch": 2.1706666666666665,
+      "grad_norm": 0.003318715374916792,
+      "learning_rate": 2.243554372889479e-06,
+      "loss": 0.462248295545578,
+      "step": 154
+    },
+    {
+      "epoch": 2.1848888888888887,
+      "grad_norm": 0.0034426096826791763,
+      "learning_rate": 2.1753157800214107e-06,
+      "loss": 0.4559134244918823,
+      "step": 155
+    },
+    {
+      "epoch": 2.1991111111111112,
+      "grad_norm": 0.0035529518499970436,
+      "learning_rate": 2.1078413626773547e-06,
+      "loss": 0.48357266187667847,
+      "step": 156
+    },
+    {
+      "epoch": 2.2133333333333334,
+      "grad_norm": 0.0034895483404397964,
+      "learning_rate": 2.0411493750387423e-06,
+      "loss": 0.4366765022277832,
+      "step": 157
+    },
+    {
+      "epoch": 2.2275555555555555,
+      "grad_norm": 0.003682621056213975,
+      "learning_rate": 1.9752578596124955e-06,
+      "loss": 0.4868413209915161,
+      "step": 158
+    },
+    {
+      "epoch": 2.2417777777777776,
+      "grad_norm": 0.0035529278684407473,
+      "learning_rate": 1.9101846423499113e-06,
+      "loss": 0.46049410104751587,
+      "step": 159
+    },
+    {
+      "epoch": 2.2560000000000002,
+      "grad_norm": 0.003581352299079299,
+      "learning_rate": 1.8459473278241125e-06,
+      "loss": 0.4605860412120819,
+      "step": 160
+    },
+    {
+      "epoch": 2.2702222222222224,
+      "grad_norm": 0.0033597166184335947,
+      "learning_rate": 1.7825632944674016e-06,
+      "loss": 0.46191370487213135,
+      "step": 161
+    },
+    {
+      "epoch": 2.2844444444444445,
+      "grad_norm": 0.003529531881213188,
+      "learning_rate": 1.7200496898697832e-06,
+      "loss": 0.4780347943305969,
+      "step": 162
+    },
+    {
+      "epoch": 2.2986666666666666,
+      "grad_norm": 0.0034702750854194164,
+      "learning_rate": 1.6584234261399535e-06,
+      "loss": 0.4648103713989258,
+      "step": 163
+    },
+    {
+      "epoch": 2.3128888888888888,
+      "grad_norm": 0.0036891205236315727,
+      "learning_rate": 1.5977011753299726e-06,
+      "loss": 0.46155521273612976,
+      "step": 164
+    },
+    {
+      "epoch": 2.327111111111111,
+      "grad_norm": 0.003741780063137412,
+      "learning_rate": 1.5378993649249053e-06,
+      "loss": 0.49238717555999756,
+      "step": 165
+    },
+    {
+      "epoch": 2.3413333333333335,
+      "grad_norm": 0.003572724526748061,
+      "learning_rate": 1.4790341733986085e-06,
+      "loss": 0.46214908361434937,
+      "step": 166
+    },
+    {
+      "epoch": 2.3555555555555556,
+      "grad_norm": 0.003393909428268671,
+      "learning_rate": 1.4211215258368866e-06,
+      "loss": 0.44751304388046265,
+      "step": 167
+    },
+    {
+      "epoch": 2.3697777777777778,
+      "grad_norm": 0.0035024855751544237,
+      "learning_rate": 1.3641770896292083e-06,
+      "loss": 0.4523189067840576,
+      "step": 168
+    },
+    {
+      "epoch": 2.384,
+      "grad_norm": 0.0034958638716489077,
+      "learning_rate": 1.3082162702301276e-06,
+      "loss": 0.46704721450805664,
+      "step": 169
+    },
+    {
+      "epoch": 2.398222222222222,
+      "grad_norm": 0.0035048348363488913,
+      "learning_rate": 1.2532542069915722e-06,
+      "loss": 0.47263163328170776,
+      "step": 170
+    },
+    {
+      "epoch": 2.4124444444444446,
+      "grad_norm": 0.0034445980563759804,
+      "learning_rate": 1.1993057690671174e-06,
+      "loss": 0.4592151641845703,
+      "step": 171
+    },
+    {
+      "epoch": 2.4266666666666667,
+      "grad_norm": 0.0034275518264621496,
+      "learning_rate": 1.1463855513893695e-06,
+      "loss": 0.4800827205181122,
+      "step": 172
+    },
+    {
+      "epoch": 2.440888888888889,
+      "grad_norm": 0.0034792288206517696,
+      "learning_rate": 1.0945078707215224e-06,
+      "loss": 0.4688478112220764,
+      "step": 173
+    },
+    {
+      "epoch": 2.455111111111111,
+      "grad_norm": 0.0035636303946375847,
+      "learning_rate": 1.0436867617841768e-06,
+      "loss": 0.46817073225975037,
+      "step": 174
+    },
+    {
+      "epoch": 2.469333333333333,
+      "grad_norm": 0.0033977399580180645,
+      "learning_rate": 9.939359734584552e-07,
+      "loss": 0.4763898253440857,
+      "step": 175
+    },
+    {
+      "epoch": 2.4835555555555557,
+      "grad_norm": 0.003528163768351078,
+      "learning_rate": 9.452689650664515e-07,
+      "loss": 0.480793833732605,
+      "step": 176
+    },
+    {
+      "epoch": 2.497777777777778,
+      "grad_norm": 0.00341871683485806,
+      "learning_rate": 8.976989027300265e-07,
+      "loss": 0.4694904088973999,
+      "step": 177
+    },
+    {
+      "epoch": 2.512,
+      "grad_norm": 0.003544109407812357,
+      "learning_rate": 8.512386558088919e-07,
+      "loss": 0.4877663254737854,
+      "step": 178
+    },
+    {
+      "epoch": 2.526222222222222,
+      "grad_norm": 0.0034784283488988876,
+      "learning_rate": 8.059007934190194e-07,
+      "loss": 0.46579453349113464,
+      "step": 179
+    },
+    {
+      "epoch": 2.5404444444444443,
+      "grad_norm": 0.003506515873596072,
+      "learning_rate": 7.61697581032243e-07,
+      "loss": 0.4954630434513092,
+      "step": 180
+    },
+    {
+      "epoch": 2.554666666666667,
+      "grad_norm": 0.003402002854272723,
+      "learning_rate": 7.186409771580355e-07,
+      "loss": 0.48210158944129944,
+      "step": 181
+    },
+    {
+      "epoch": 2.568888888888889,
+      "grad_norm": 0.003400753950700164,
+      "learning_rate": 6.76742630108298e-07,
+      "loss": 0.4673936069011688,
+      "step": 182
+    },
+    {
+      "epoch": 2.583111111111111,
+      "grad_norm": 0.0034171557053923607,
+      "learning_rate": 6.360138748461015e-07,
+      "loss": 0.46786054968833923,
+      "step": 183
+    },
+    {
+      "epoch": 2.5973333333333333,
+      "grad_norm": 0.003441787790507078,
+      "learning_rate": 5.964657299191712e-07,
+      "loss": 0.45768898725509644,
+      "step": 184
+    },
+    {
+      "epoch": 2.6115555555555554,
+      "grad_norm": 0.0034633874893188477,
+      "learning_rate": 5.581088944789953e-07,
+      "loss": 0.468585342168808,
+      "step": 185
+    },
+    {
+      "epoch": 2.6257777777777775,
+      "grad_norm": 0.0034696508664637804,
+      "learning_rate": 5.20953745386329e-07,
+      "loss": 0.4843568205833435,
+      "step": 186
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 0.003448233939707279,
+      "learning_rate": 4.850103344038853e-07,
+      "loss": 0.4747229218482971,
+      "step": 187
+    },
+    {
+      "epoch": 2.6542222222222223,
+      "grad_norm": 0.00340772676281631,
+      "learning_rate": 4.502883854769935e-07,
+      "loss": 0.44664108753204346,
+      "step": 188
+    },
+    {
+      "epoch": 2.6684444444444444,
+      "grad_norm": 0.0034893041010946035,
+      "learning_rate": 4.167972921029262e-07,
+      "loss": 0.47903192043304443,
+      "step": 189
+    },
+    {
+      "epoch": 2.6826666666666665,
+      "grad_norm": 0.003642126452177763,
+      "learning_rate": 3.8454611478963235e-07,
+      "loss": 0.4844057559967041,
+      "step": 190
+    },
+    {
+      "epoch": 2.696888888888889,
+      "grad_norm": 0.0034686627332121134,
+      "learning_rate": 3.535435786045538e-07,
+      "loss": 0.4564388394355774,
+      "step": 191
+    },
+    {
+      "epoch": 2.7111111111111112,
+      "grad_norm": 0.003412955440580845,
+      "learning_rate": 3.237980708141919e-07,
+      "loss": 0.47008293867111206,
+      "step": 192
+    },
+    {
+      "epoch": 2.7253333333333334,
+      "grad_norm": 0.0035507141146808863,
+      "learning_rate": 2.9531763861505967e-07,
+      "loss": 0.479957640171051,
+      "step": 193
+    },
+    {
+      "epoch": 2.7395555555555555,
+      "grad_norm": 0.0035486763808876276,
+      "learning_rate": 2.681099869566328e-07,
+      "loss": 0.44965675473213196,
+      "step": 194
+    },
+    {
+      "epoch": 2.7537777777777777,
+      "grad_norm": 0.0034812854137271643,
+      "learning_rate": 2.4218247645689306e-07,
+      "loss": 0.4747314453125,
+      "step": 195
+    },
+    {
+      "epoch": 2.768,
+      "grad_norm": 0.00335957994684577,
+      "learning_rate": 2.175421214110235e-07,
+      "loss": 0.45799821615219116,
+      "step": 196
+    },
+    {
+      "epoch": 2.7822222222222224,
+      "grad_norm": 0.0035609498154371977,
+      "learning_rate": 1.941955878938029e-07,
+      "loss": 0.47467684745788574,
+      "step": 197
+    },
+    {
+      "epoch": 2.7964444444444445,
+      "grad_norm": 0.003390205791220069,
+      "learning_rate": 1.721491919561913e-07,
+      "loss": 0.4817090332508087,
+      "step": 198
+    },
+    {
+      "epoch": 2.8106666666666666,
+      "grad_norm": 0.003445240668952465,
+      "learning_rate": 1.514088979166256e-07,
+      "loss": 0.4649164080619812,
+      "step": 199
+    },
+    {
+      "epoch": 2.824888888888889,
+      "grad_norm": 0.003372759558260441,
+      "learning_rate": 1.3198031674745814e-07,
+      "loss": 0.4765157699584961,
+      "step": 200
+    },
+    {
+      "epoch": 2.824888888888889,
+      "eval_loss": 0.5171427726745605,
+      "eval_runtime": 9.8598,
+      "eval_samples_per_second": 20.284,
+      "eval_steps_per_second": 10.142,
+      "step": 200
+    },
+    {
+      "epoch": 2.8391111111111114,
+      "grad_norm": 0.0034065141808241606,
+      "learning_rate": 1.138687045569975e-07,
+      "loss": 0.46831822395324707,
+      "step": 201
+    },
+    {
+      "epoch": 2.8533333333333335,
+      "grad_norm": 0.0034053055569529533,
+      "learning_rate": 9.70789611675449e-08,
+      "loss": 0.47398146986961365,
+      "step": 202
+    },
+    {
+      "epoch": 2.8675555555555556,
+      "grad_norm": 0.0034186639823019505,
+      "learning_rate": 8.161562878982399e-08,
+      "loss": 0.45744937658309937,
+      "step": 203
+    },
+    {
+      "epoch": 2.8817777777777778,
+      "grad_norm": 0.0034667483996599913,
+      "learning_rate": 6.74828907941516e-08,
+      "loss": 0.48529934883117676,
+      "step": 204
+    },
+    {
+      "epoch": 2.896,
+      "grad_norm": 0.003455272177234292,
+      "learning_rate": 5.468457057869358e-08,
+      "loss": 0.4858051836490631,
+      "step": 205
+    },
+    {
+      "epoch": 2.910222222222222,
+      "grad_norm": 0.0033815570641309023,
+      "learning_rate": 4.322413053509944e-08,
+      "loss": 0.4590516984462738,
+      "step": 206
+    },
+    {
+      "epoch": 2.924444444444444,
+      "grad_norm": 0.0034011146053671837,
+      "learning_rate": 3.31046711118066e-08,
+      "loss": 0.45788976550102234,
+      "step": 207
+    },
+    {
+      "epoch": 2.9386666666666668,
+      "grad_norm": 0.003420215332880616,
+      "learning_rate": 2.4328929975260262e-08,
+      "loss": 0.4702548086643219,
+      "step": 208
+    },
+    {
+      "epoch": 2.952888888888889,
+      "grad_norm": 0.0033962675370275974,
+      "learning_rate": 1.6899281269279756e-08,
+      "loss": 0.4560105800628662,
+      "step": 209
+    },
+    {
+      "epoch": 2.967111111111111,
+      "grad_norm": 0.003477597376331687,
+      "learning_rate": 1.0817734972768946e-08,
+      "loss": 0.46400371193885803,
+      "step": 210
+    },
+    {
+      "epoch": 2.981333333333333,
+      "grad_norm": 0.0036108316853642464,
+      "learning_rate": 6.085936355947897e-09,
+      "loss": 0.48368915915489197,
+      "step": 211
+    },
+    {
+      "epoch": 2.9955555555555557,
+      "grad_norm": 0.003335504326969385,
+      "learning_rate": 2.7051655352494654e-09,
+      "loss": 0.45437300205230713,
+      "step": 212
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.00642085587605834,
+      "learning_rate": 6.763371270035457e-10,
+      "loss": 0.5508654713630676,
+      "step": 213
+    },
+    {
+      "epoch": 3.0,
+      "step": 213,
+      "total_flos": 2.4727435500270387e+17,
+      "train_loss": 0.5265021298972654,
+      "train_runtime": 6756.1203,
+      "train_samples_per_second": 7.993,
+      "train_steps_per_second": 0.032
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 213,
+  "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": 2.4727435500270387e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

qwen2.5-1.5b-instruct/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39e78c30a5784e935e65cb8fa1a73b2afb467afccc55e7223863b667252fac3b
+size 5649