Upload folder using huggingface_hub

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-309/tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,59 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: Qwen/Qwen2.5-Coder-1.5B-Instruct
+tags:
+- llama-factory
+- generated_from_trainer
+model-index:
+- name: ml815-model8
+  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. -->
+
+# ml815-model8
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B-Instruct) on an unknown dataset.
+
+## 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: 2e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- total_train_batch_size: 32
+- total_eval_batch_size: 32
+- 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_ratio: 0.1
+- num_epochs: 1.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.55.0
+- Pytorch 2.8.0+rocm6.3
+- Datasets 3.6.0
+- Tokenizers 0.21.1

checkpoint-309/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-309/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 %}

checkpoint-309/config.json

@@ -0,0 +1,58 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "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": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.55.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

checkpoint-309/generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "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": "4.55.0"
+}

checkpoint-309/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:322d924ceee94bdf461dff59a46b2429c6cab9d61bef41ffa086578272033511
+size 3554214752

checkpoint-309/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_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|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-309/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

checkpoint-309/tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_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|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-309/trainer_state.json

@@ -0,0 +1,244 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 309,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.032362459546925564,
+      "grad_norm": 3.9236679077148438,
+      "learning_rate": 5.806451612903226e-06,
+      "loss": 0.598,
+      "step": 10
+    },
+    {
+      "epoch": 0.06472491909385113,
+      "grad_norm": 1.8179429769515991,
+      "learning_rate": 1.2258064516129034e-05,
+      "loss": 0.2223,
+      "step": 20
+    },
+    {
+      "epoch": 0.0970873786407767,
+      "grad_norm": 1.024856686592102,
+      "learning_rate": 1.870967741935484e-05,
+      "loss": 0.1167,
+      "step": 30
+    },
+    {
+      "epoch": 0.12944983818770225,
+      "grad_norm": 0.9101268649101257,
+      "learning_rate": 1.9959162014075553e-05,
+      "loss": 0.0923,
+      "step": 40
+    },
+    {
+      "epoch": 0.16181229773462782,
+      "grad_norm": 0.5613371729850769,
+      "learning_rate": 1.9793829188147406e-05,
+      "loss": 0.078,
+      "step": 50
+    },
+    {
+      "epoch": 0.1941747572815534,
+      "grad_norm": 0.9140991568565369,
+      "learning_rate": 1.9503556665478066e-05,
+      "loss": 0.0795,
+      "step": 60
+    },
+    {
+      "epoch": 0.22653721682847897,
+      "grad_norm": 0.5968174338340759,
+      "learning_rate": 1.9092047447238775e-05,
+      "loss": 0.0635,
+      "step": 70
+    },
+    {
+      "epoch": 0.2588996763754045,
+      "grad_norm": 0.4374071955680847,
+      "learning_rate": 1.856455114887056e-05,
+      "loss": 0.0583,
+      "step": 80
+    },
+    {
+      "epoch": 0.2912621359223301,
+      "grad_norm": 0.4676224887371063,
+      "learning_rate": 1.792779703083777e-05,
+      "loss": 0.0662,
+      "step": 90
+    },
+    {
+      "epoch": 0.32362459546925565,
+      "grad_norm": 0.5119790434837341,
+      "learning_rate": 1.7189908153577473e-05,
+      "loss": 0.0589,
+      "step": 100
+    },
+    {
+      "epoch": 0.3559870550161812,
+      "grad_norm": 0.543942391872406,
+      "learning_rate": 1.636029775176862e-05,
+      "loss": 0.0586,
+      "step": 110
+    },
+    {
+      "epoch": 0.3883495145631068,
+      "grad_norm": 0.4500238001346588,
+      "learning_rate": 1.544954914987238e-05,
+      "loss": 0.0568,
+      "step": 120
+    },
+    {
+      "epoch": 0.42071197411003236,
+      "grad_norm": 0.3425617516040802,
+      "learning_rate": 1.4469280750858854e-05,
+      "loss": 0.0524,
+      "step": 130
+    },
+    {
+      "epoch": 0.45307443365695793,
+      "grad_norm": 0.3619914650917053,
+      "learning_rate": 1.3431997820456592e-05,
+      "loss": 0.0486,
+      "step": 140
+    },
+    {
+      "epoch": 0.4854368932038835,
+      "grad_norm": 1.788984775543213,
+      "learning_rate": 1.2350932957710322e-05,
+      "loss": 0.0472,
+      "step": 150
+    },
+    {
+      "epoch": 0.517799352750809,
+      "grad_norm": 0.44366371631622314,
+      "learning_rate": 1.1239877286961123e-05,
+      "loss": 0.0467,
+      "step": 160
+    },
+    {
+      "epoch": 0.5501618122977346,
+      "grad_norm": 0.378680557012558,
+      "learning_rate": 1.01130045247298e-05,
+      "loss": 0.0503,
+      "step": 170
+    },
+    {
+      "epoch": 0.5825242718446602,
+      "grad_norm": 0.48776954412460327,
+      "learning_rate": 8.98469016587892e-06,
+      "loss": 0.0441,
+      "step": 180
+    },
+    {
+      "epoch": 0.6148867313915858,
+      "grad_norm": 0.37561851739883423,
+      "learning_rate": 7.869328095692313e-06,
+      "loss": 0.0431,
+      "step": 190
+    },
+    {
+      "epoch": 0.6472491909385113,
+      "grad_norm": 0.35846513509750366,
+      "learning_rate": 6.781146967348283e-06,
+      "loss": 0.0433,
+      "step": 200
+    },
+    {
+      "epoch": 0.6796116504854369,
+      "grad_norm": 0.34934285283088684,
+      "learning_rate": 5.7340286872557515e-06,
+      "loss": 0.0367,
+      "step": 210
+    },
+    {
+      "epoch": 0.7119741100323624,
+      "grad_norm": 0.3203984498977661,
+      "learning_rate": 4.7413313238324556e-06,
+      "loss": 0.0425,
+      "step": 220
+    },
+    {
+      "epoch": 0.7443365695792881,
+      "grad_norm": 0.399088591337204,
+      "learning_rate": 3.815718698874672e-06,
+      "loss": 0.0424,
+      "step": 230
+    },
+    {
+      "epoch": 0.7766990291262136,
+      "grad_norm": 0.3292689621448517,
+      "learning_rate": 2.9689988354181742e-06,
+      "loss": 0.0383,
+      "step": 240
+    },
+    {
+      "epoch": 0.8090614886731392,
+      "grad_norm": 0.2965834140777588,
+      "learning_rate": 2.211973323008041e-06,
+      "loss": 0.0423,
+      "step": 250
+    },
+    {
+      "epoch": 0.8414239482200647,
+      "grad_norm": 0.4333046078681946,
+      "learning_rate": 1.5542995220217961e-06,
+      "loss": 0.0417,
+      "step": 260
+    },
+    {
+      "epoch": 0.8737864077669902,
+      "grad_norm": 0.36212387681007385,
+      "learning_rate": 1.0043673649027519e-06,
+      "loss": 0.0381,
+      "step": 270
+    },
+    {
+      "epoch": 0.9061488673139159,
+      "grad_norm": 0.2634587585926056,
+      "learning_rate": 5.691923259479093e-07,
+      "loss": 0.0379,
+      "step": 280
+    },
+    {
+      "epoch": 0.9385113268608414,
+      "grad_norm": 0.27783694863319397,
+      "learning_rate": 2.5432592503288e-07,
+      "loss": 0.0384,
+      "step": 290
+    },
+    {
+      "epoch": 0.970873786407767,
+      "grad_norm": 0.33753329515457153,
+      "learning_rate": 6.378490697611761e-08,
+      "loss": 0.0407,
+      "step": 300
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 309,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.151751154761728e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-309/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30feb462d1b0752eecf948911bc0c307d2f48dbefb87f035cb0e15de35d0d2a9
+size 8081

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "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": "4.55.0"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec78405aa0f46702c112138d196d27aa79ddc898ddf41da23b2d9da1cc80e900
+oid sha256:322d924ceee94bdf461dff59a46b2429c6cab9d61bef41ffa086578272033511
 size 3554214752

trainer_log.jsonl

@@ -9,3 +9,23 @@
 {"current_steps": 90, "total_steps": 309, "loss": 0.0662, "lr": 1.792779703083777e-05, "epoch": 0.2912621359223301, "percentage": 29.13, "elapsed_time": "0:11:17", "remaining_time": "0:27:29"}
 {"current_steps": 100, "total_steps": 309, "loss": 0.0589, "lr": 1.7189908153577473e-05, "epoch": 0.32362459546925565, "percentage": 32.36, "elapsed_time": "0:12:30", "remaining_time": "0:26:08"}
 {"current_steps": 110, "total_steps": 309, "loss": 0.0586, "lr": 1.636029775176862e-05, "epoch": 0.3559870550161812, "percentage": 35.6, "elapsed_time": "0:14:14", "remaining_time": "0:25:46"}
+{"current_steps": 120, "total_steps": 309, "loss": 0.0568, "lr": 1.544954914987238e-05, "epoch": 0.3883495145631068, "percentage": 38.83, "elapsed_time": "0:15:32", "remaining_time": "0:24:28"}
+{"current_steps": 130, "total_steps": 309, "loss": 0.0524, "lr": 1.4469280750858854e-05, "epoch": 0.42071197411003236, "percentage": 42.07, "elapsed_time": "0:16:42", "remaining_time": "0:23:00"}
+{"current_steps": 140, "total_steps": 309, "loss": 0.0486, "lr": 1.3431997820456592e-05, "epoch": 0.45307443365695793, "percentage": 45.31, "elapsed_time": "0:17:57", "remaining_time": "0:21:41"}
+{"current_steps": 150, "total_steps": 309, "loss": 0.0472, "lr": 1.2350932957710322e-05, "epoch": 0.4854368932038835, "percentage": 48.54, "elapsed_time": "0:19:06", "remaining_time": "0:20:15"}
+{"current_steps": 160, "total_steps": 309, "loss": 0.0467, "lr": 1.1239877286961123e-05, "epoch": 0.517799352750809, "percentage": 51.78, "elapsed_time": "0:20:16", "remaining_time": "0:18:52"}
+{"current_steps": 170, "total_steps": 309, "loss": 0.0503, "lr": 1.01130045247298e-05, "epoch": 0.5501618122977346, "percentage": 55.02, "elapsed_time": "0:21:34", "remaining_time": "0:17:38"}
+{"current_steps": 180, "total_steps": 309, "loss": 0.0441, "lr": 8.98469016587892e-06, "epoch": 0.5825242718446602, "percentage": 58.25, "elapsed_time": "0:22:47", "remaining_time": "0:16:19"}
+{"current_steps": 190, "total_steps": 309, "loss": 0.0431, "lr": 7.869328095692313e-06, "epoch": 0.6148867313915858, "percentage": 61.49, "elapsed_time": "0:24:01", "remaining_time": "0:15:03"}
+{"current_steps": 200, "total_steps": 309, "loss": 0.0433, "lr": 6.781146967348283e-06, "epoch": 0.6472491909385113, "percentage": 64.72, "elapsed_time": "0:25:13", "remaining_time": "0:13:44"}
+{"current_steps": 210, "total_steps": 309, "loss": 0.0367, "lr": 5.7340286872557515e-06, "epoch": 0.6796116504854369, "percentage": 67.96, "elapsed_time": "0:26:46", "remaining_time": "0:12:37"}
+{"current_steps": 220, "total_steps": 309, "loss": 0.0425, "lr": 4.7413313238324556e-06, "epoch": 0.7119741100323624, "percentage": 71.2, "elapsed_time": "0:28:05", "remaining_time": "0:11:21"}
+{"current_steps": 230, "total_steps": 309, "loss": 0.0424, "lr": 3.815718698874672e-06, "epoch": 0.7443365695792881, "percentage": 74.43, "elapsed_time": "0:29:19", "remaining_time": "0:10:04"}
+{"current_steps": 240, "total_steps": 309, "loss": 0.0383, "lr": 2.9689988354181742e-06, "epoch": 0.7766990291262136, "percentage": 77.67, "elapsed_time": "0:30:37", "remaining_time": "0:08:48"}
+{"current_steps": 250, "total_steps": 309, "loss": 0.0423, "lr": 2.211973323008041e-06, "epoch": 0.8090614886731392, "percentage": 80.91, "elapsed_time": "0:31:48", "remaining_time": "0:07:30"}
+{"current_steps": 260, "total_steps": 309, "loss": 0.0417, "lr": 1.5542995220217961e-06, "epoch": 0.8414239482200647, "percentage": 84.14, "elapsed_time": "0:33:05", "remaining_time": "0:06:14"}
+{"current_steps": 270, "total_steps": 309, "loss": 0.0381, "lr": 1.0043673649027519e-06, "epoch": 0.8737864077669902, "percentage": 87.38, "elapsed_time": "0:34:18", "remaining_time": "0:04:57"}
+{"current_steps": 280, "total_steps": 309, "loss": 0.0379, "lr": 5.691923259479093e-07, "epoch": 0.9061488673139159, "percentage": 90.61, "elapsed_time": "0:35:40", "remaining_time": "0:03:41"}
+{"current_steps": 290, "total_steps": 309, "loss": 0.0384, "lr": 2.5432592503288e-07, "epoch": 0.9385113268608414, "percentage": 93.85, "elapsed_time": "0:36:58", "remaining_time": "0:02:25"}
+{"current_steps": 300, "total_steps": 309, "loss": 0.0407, "lr": 6.378490697611761e-08, "epoch": 0.970873786407767, "percentage": 97.09, "elapsed_time": "0:38:16", "remaining_time": "0:01:08"}
+{"current_steps": 309, "total_steps": 309, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:40:20", "remaining_time": "0:00:00"}