Reset repository without checkpoints directories

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,60 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: Qwen/Qwen3-8B
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: nl2bash-2ep-restore-hp
+  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. -->
+
+# nl2bash-2ep-restore-hp
+
+This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on the DCAgent/nl2bash-2ep 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: 4e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 16
+- total_train_batch_size: 16
+- total_eval_batch_size: 128
+- 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: 6.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.56.0
+- Pytorch 2.7.0+cu128
+- Datasets 3.6.0
+- Tokenizers 0.22.1

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|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
+}

all_results.json

@@ -0,0 +1,16 @@
+{
+    "achieved_tflops_per_gpu": 0.001193822706401171,
+    "achieved_tflops_per_gpu_theoretical": 1124.784314857292,
+    "epoch": 6.0,
+    "loss_nan_ranks": 0,
+    "loss_rank_avg": 0.08076979219913483,
+    "mfu_percent": 8.436909585874e-05,
+    "mfu_percent_theoretical": 79.49005758708778,
+    "total_flos": 140364736167936.0,
+    "train_loss": 0.16821050625614803,
+    "train_runtime": 7348.4915,
+    "train_samples_per_second": 5.31,
+    "train_steps_per_second": 0.332,
+    "valid_targets_mean": 624.3,
+    "valid_targets_min": 380
+}

chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# 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' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- 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' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,68 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "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",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.56.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.56.0"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a90ed25b3f0e2dcb15da6adab1318269ff932cd9e3e2d650690eb35b17312e86
+size 4902257696

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b5c37541e27645be93baafd291e56326a3b066b4b4bc222f226ad16b6d9c939
+size 4915960368

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c319ff9a23aeeb259b814d5cf8707de2b306c6a8771cf8e40f932e131f99c24
+size 4983068496

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:602e9b42f8810333fbb692a4c5831f65d89044944ba242c186761f3133ded350
+size 1580230264

model.safetensors.index.json

@@ -0,0 +1,407 @@
+{
+  "metadata": {
+    "total_parameters": 308224,
+    "total_size": 16381470720
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

run_summary.json

@@ -0,0 +1,12 @@
+{
+  "agent_name": null,
+  "training_start": null,
+  "training_end": null,
+  "created_by": "DCAgent",
+  "base_model_name": "Qwen/Qwen3-8B",
+  "dataset_name": "DCAgent/nl2bash-2ep",
+  "training_type": "SFT",
+  "training_parameters": "https://huggingface.co/penfever/nl2bash-2ep-restore-hp/blob/main/config.json",
+  "wandb_link": "https://wandb.ai/dogml/dc-agent/runs/nl2bash-2ep_hub-model-id_nl2bash-2ep-restore-hp_Qwen3-8B",
+  "traces_location_s3": null
+}

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
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "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
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "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
+}

train_results.json

@@ -0,0 +1,16 @@
+{
+    "achieved_tflops_per_gpu": 0.001193822706401171,
+    "achieved_tflops_per_gpu_theoretical": 1124.784314857292,
+    "epoch": 6.0,
+    "loss_nan_ranks": 0,
+    "loss_rank_avg": 0.08076979219913483,
+    "mfu_percent": 8.436909585874e-05,
+    "mfu_percent_theoretical": 79.49005758708778,
+    "total_flos": 140364736167936.0,
+    "train_loss": 0.16821050625614803,
+    "train_runtime": 7348.4915,
+    "train_samples_per_second": 5.31,
+    "train_steps_per_second": 0.332,
+    "valid_targets_mean": 624.3,
+    "valid_targets_min": 380
+}

trainer_log.jsonl

@@ -0,0 +1,489 @@
+{"current_steps": 5, "total_steps": 2442, "loss": 1.0268, "lr": 6.530612244897961e-07, "epoch": 0.012285012285012284, "percentage": 0.2, "elapsed_time": "0:00:22", "remaining_time": "3:02:48"}
+{"current_steps": 10, "total_steps": 2442, "loss": 0.9836, "lr": 1.469387755102041e-06, "epoch": 0.02457002457002457, "percentage": 0.41, "elapsed_time": "0:00:35", "remaining_time": "2:23:48"}
+{"current_steps": 15, "total_steps": 2442, "loss": 0.9821, "lr": 2.285714285714286e-06, "epoch": 0.036855036855036855, "percentage": 0.61, "elapsed_time": "0:00:47", "remaining_time": "2:09:26"}
+{"current_steps": 20, "total_steps": 2442, "loss": 0.8773, "lr": 3.1020408163265307e-06, "epoch": 0.04914004914004914, "percentage": 0.82, "elapsed_time": "0:01:01", "remaining_time": "2:04:13"}
+{"current_steps": 25, "total_steps": 2442, "loss": 0.82, "lr": 3.9183673469387755e-06, "epoch": 0.06142506142506143, "percentage": 1.02, "elapsed_time": "0:01:14", "remaining_time": "2:00:29"}
+{"current_steps": 30, "total_steps": 2442, "loss": 0.6919, "lr": 4.734693877551021e-06, "epoch": 0.07371007371007371, "percentage": 1.23, "elapsed_time": "0:01:27", "remaining_time": "1:57:42"}
+{"current_steps": 35, "total_steps": 2442, "loss": 0.6329, "lr": 5.551020408163266e-06, "epoch": 0.085995085995086, "percentage": 1.43, "elapsed_time": "0:01:40", "remaining_time": "1:55:34"}
+{"current_steps": 40, "total_steps": 2442, "loss": 0.5631, "lr": 6.36734693877551e-06, "epoch": 0.09828009828009827, "percentage": 1.64, "elapsed_time": "0:01:53", "remaining_time": "1:53:47"}
+{"current_steps": 45, "total_steps": 2442, "loss": 0.4885, "lr": 7.183673469387755e-06, "epoch": 0.11056511056511056, "percentage": 1.84, "elapsed_time": "0:02:06", "remaining_time": "1:52:44"}
+{"current_steps": 50, "total_steps": 2442, "loss": 0.4598, "lr": 8.000000000000001e-06, "epoch": 0.12285012285012285, "percentage": 2.05, "elapsed_time": "0:02:20", "remaining_time": "1:51:47"}
+{"current_steps": 55, "total_steps": 2442, "loss": 0.4127, "lr": 8.816326530612247e-06, "epoch": 0.13513513513513514, "percentage": 2.25, "elapsed_time": "0:02:32", "remaining_time": "1:50:17"}
+{"current_steps": 60, "total_steps": 2442, "loss": 0.4035, "lr": 9.63265306122449e-06, "epoch": 0.14742014742014742, "percentage": 2.46, "elapsed_time": "0:02:45", "remaining_time": "1:49:11"}
+{"current_steps": 65, "total_steps": 2442, "loss": 0.3729, "lr": 1.0448979591836737e-05, "epoch": 0.1597051597051597, "percentage": 2.66, "elapsed_time": "0:02:57", "remaining_time": "1:48:22"}
+{"current_steps": 70, "total_steps": 2442, "loss": 0.3651, "lr": 1.126530612244898e-05, "epoch": 0.171990171990172, "percentage": 2.87, "elapsed_time": "0:03:10", "remaining_time": "1:47:44"}
+{"current_steps": 75, "total_steps": 2442, "loss": 0.3538, "lr": 1.2081632653061225e-05, "epoch": 0.18427518427518427, "percentage": 3.07, "elapsed_time": "0:03:23", "remaining_time": "1:46:52"}
+{"current_steps": 80, "total_steps": 2442, "loss": 0.3303, "lr": 1.2897959183673469e-05, "epoch": 0.19656019656019655, "percentage": 3.28, "elapsed_time": "0:03:35", "remaining_time": "1:46:10"}
+{"current_steps": 85, "total_steps": 2442, "loss": 0.3245, "lr": 1.3714285714285716e-05, "epoch": 0.20884520884520885, "percentage": 3.48, "elapsed_time": "0:03:48", "remaining_time": "1:45:45"}
+{"current_steps": 90, "total_steps": 2442, "loss": 0.2952, "lr": 1.4530612244897961e-05, "epoch": 0.22113022113022113, "percentage": 3.69, "elapsed_time": "0:04:01", "remaining_time": "1:45:07"}
+{"current_steps": 95, "total_steps": 2442, "loss": 0.3211, "lr": 1.5346938775510204e-05, "epoch": 0.2334152334152334, "percentage": 3.89, "elapsed_time": "0:04:13", "remaining_time": "1:44:22"}
+{"current_steps": 100, "total_steps": 2442, "loss": 0.3009, "lr": 1.616326530612245e-05, "epoch": 0.2457002457002457, "percentage": 4.1, "elapsed_time": "0:04:25", "remaining_time": "1:43:49"}
+{"current_steps": 105, "total_steps": 2442, "loss": 0.2913, "lr": 1.6979591836734695e-05, "epoch": 0.257985257985258, "percentage": 4.3, "elapsed_time": "0:05:38", "remaining_time": "2:05:41"}
+{"current_steps": 110, "total_steps": 2442, "loss": 0.2983, "lr": 1.779591836734694e-05, "epoch": 0.2702702702702703, "percentage": 4.5, "elapsed_time": "0:05:52", "remaining_time": "2:04:25"}
+{"current_steps": 115, "total_steps": 2442, "loss": 0.2739, "lr": 1.8612244897959185e-05, "epoch": 0.28255528255528256, "percentage": 4.71, "elapsed_time": "0:06:04", "remaining_time": "2:02:55"}
+{"current_steps": 120, "total_steps": 2442, "loss": 0.2961, "lr": 1.942857142857143e-05, "epoch": 0.29484029484029484, "percentage": 4.91, "elapsed_time": "0:06:17", "remaining_time": "2:01:35"}
+{"current_steps": 125, "total_steps": 2442, "loss": 0.2921, "lr": 2.0244897959183672e-05, "epoch": 0.3071253071253071, "percentage": 5.12, "elapsed_time": "0:06:29", "remaining_time": "2:00:19"}
+{"current_steps": 130, "total_steps": 2442, "loss": 0.2818, "lr": 2.106122448979592e-05, "epoch": 0.3194103194103194, "percentage": 5.32, "elapsed_time": "0:06:41", "remaining_time": "1:59:03"}
+{"current_steps": 135, "total_steps": 2442, "loss": 0.2917, "lr": 2.1877551020408166e-05, "epoch": 0.3316953316953317, "percentage": 5.53, "elapsed_time": "0:06:54", "remaining_time": "1:58:00"}
+{"current_steps": 140, "total_steps": 2442, "loss": 0.2826, "lr": 2.269387755102041e-05, "epoch": 0.343980343980344, "percentage": 5.73, "elapsed_time": "0:07:06", "remaining_time": "1:56:58"}
+{"current_steps": 145, "total_steps": 2442, "loss": 0.2606, "lr": 2.3510204081632656e-05, "epoch": 0.35626535626535627, "percentage": 5.94, "elapsed_time": "0:07:19", "remaining_time": "1:55:58"}
+{"current_steps": 150, "total_steps": 2442, "loss": 0.2773, "lr": 2.4326530612244898e-05, "epoch": 0.36855036855036855, "percentage": 6.14, "elapsed_time": "0:07:31", "remaining_time": "1:54:58"}
+{"current_steps": 155, "total_steps": 2442, "loss": 0.2662, "lr": 2.5142857142857143e-05, "epoch": 0.3808353808353808, "percentage": 6.35, "elapsed_time": "0:07:43", "remaining_time": "1:53:59"}
+{"current_steps": 160, "total_steps": 2442, "loss": 0.2813, "lr": 2.5959183673469392e-05, "epoch": 0.3931203931203931, "percentage": 6.55, "elapsed_time": "0:07:56", "remaining_time": "1:53:16"}
+{"current_steps": 165, "total_steps": 2442, "loss": 0.2607, "lr": 2.6775510204081637e-05, "epoch": 0.40540540540540543, "percentage": 6.76, "elapsed_time": "0:08:09", "remaining_time": "1:52:30"}
+{"current_steps": 170, "total_steps": 2442, "loss": 0.2724, "lr": 2.7591836734693882e-05, "epoch": 0.4176904176904177, "percentage": 6.96, "elapsed_time": "0:08:21", "remaining_time": "1:51:46"}
+{"current_steps": 175, "total_steps": 2442, "loss": 0.2629, "lr": 2.8408163265306124e-05, "epoch": 0.42997542997543, "percentage": 7.17, "elapsed_time": "0:08:34", "remaining_time": "1:51:07"}
+{"current_steps": 180, "total_steps": 2442, "loss": 0.2757, "lr": 2.922448979591837e-05, "epoch": 0.44226044226044225, "percentage": 7.37, "elapsed_time": "0:08:46", "remaining_time": "1:50:20"}
+{"current_steps": 185, "total_steps": 2442, "loss": 0.2585, "lr": 3.0040816326530614e-05, "epoch": 0.45454545454545453, "percentage": 7.58, "elapsed_time": "0:08:59", "remaining_time": "1:49:38"}
+{"current_steps": 190, "total_steps": 2442, "loss": 0.2652, "lr": 3.085714285714286e-05, "epoch": 0.4668304668304668, "percentage": 7.78, "elapsed_time": "0:09:11", "remaining_time": "1:49:00"}
+{"current_steps": 195, "total_steps": 2442, "loss": 0.2643, "lr": 3.1673469387755105e-05, "epoch": 0.47911547911547914, "percentage": 7.99, "elapsed_time": "0:09:24", "remaining_time": "1:48:28"}
+{"current_steps": 200, "total_steps": 2442, "loss": 0.2535, "lr": 3.2489795918367346e-05, "epoch": 0.4914004914004914, "percentage": 8.19, "elapsed_time": "0:09:37", "remaining_time": "1:47:51"}
+{"current_steps": 205, "total_steps": 2442, "loss": 0.2663, "lr": 3.3306122448979595e-05, "epoch": 0.5036855036855037, "percentage": 8.39, "elapsed_time": "0:10:49", "remaining_time": "1:58:07"}
+{"current_steps": 210, "total_steps": 2442, "loss": 0.2574, "lr": 3.4122448979591843e-05, "epoch": 0.515970515970516, "percentage": 8.6, "elapsed_time": "0:11:01", "remaining_time": "1:57:13"}
+{"current_steps": 215, "total_steps": 2442, "loss": 0.253, "lr": 3.4938775510204085e-05, "epoch": 0.5282555282555282, "percentage": 8.8, "elapsed_time": "0:11:14", "remaining_time": "1:56:27"}
+{"current_steps": 220, "total_steps": 2442, "loss": 0.2443, "lr": 3.575510204081633e-05, "epoch": 0.5405405405405406, "percentage": 9.01, "elapsed_time": "0:11:27", "remaining_time": "1:55:40"}
+{"current_steps": 225, "total_steps": 2442, "loss": 0.2535, "lr": 3.6571428571428576e-05, "epoch": 0.5528255528255528, "percentage": 9.21, "elapsed_time": "0:11:39", "remaining_time": "1:54:51"}
+{"current_steps": 230, "total_steps": 2442, "loss": 0.2513, "lr": 3.738775510204082e-05, "epoch": 0.5651105651105651, "percentage": 9.42, "elapsed_time": "0:11:51", "remaining_time": "1:54:04"}
+{"current_steps": 235, "total_steps": 2442, "loss": 0.2429, "lr": 3.8204081632653066e-05, "epoch": 0.5773955773955773, "percentage": 9.62, "elapsed_time": "0:12:03", "remaining_time": "1:53:13"}
+{"current_steps": 240, "total_steps": 2442, "loss": 0.2402, "lr": 3.902040816326531e-05, "epoch": 0.5896805896805897, "percentage": 9.83, "elapsed_time": "0:12:16", "remaining_time": "1:52:33"}
+{"current_steps": 245, "total_steps": 2442, "loss": 0.2553, "lr": 3.983673469387755e-05, "epoch": 0.601965601965602, "percentage": 10.03, "elapsed_time": "0:12:28", "remaining_time": "1:51:52"}
+{"current_steps": 250, "total_steps": 2442, "loss": 0.2569, "lr": 3.9999672841332876e-05, "epoch": 0.6142506142506142, "percentage": 10.24, "elapsed_time": "0:12:40", "remaining_time": "1:51:07"}
+{"current_steps": 255, "total_steps": 2442, "loss": 0.2583, "lr": 3.999834377759164e-05, "epoch": 0.6265356265356266, "percentage": 10.44, "elapsed_time": "0:12:52", "remaining_time": "1:50:23"}
+{"current_steps": 260, "total_steps": 2442, "loss": 0.2602, "lr": 3.999599242924703e-05, "epoch": 0.6388206388206388, "percentage": 10.65, "elapsed_time": "0:13:05", "remaining_time": "1:49:48"}
+{"current_steps": 265, "total_steps": 2442, "loss": 0.2446, "lr": 3.999261891649637e-05, "epoch": 0.6511056511056511, "percentage": 10.85, "elapsed_time": "0:13:16", "remaining_time": "1:49:06"}
+{"current_steps": 270, "total_steps": 2442, "loss": 0.2553, "lr": 3.9988223411788436e-05, "epoch": 0.6633906633906634, "percentage": 11.06, "elapsed_time": "0:13:29", "remaining_time": "1:48:28"}
+{"current_steps": 275, "total_steps": 2442, "loss": 0.2441, "lr": 3.998280613981468e-05, "epoch": 0.6756756756756757, "percentage": 11.26, "elapsed_time": "0:13:41", "remaining_time": "1:47:53"}
+{"current_steps": 280, "total_steps": 2442, "loss": 0.2533, "lr": 3.9976367377497725e-05, "epoch": 0.687960687960688, "percentage": 11.47, "elapsed_time": "0:13:53", "remaining_time": "1:47:16"}
+{"current_steps": 285, "total_steps": 2442, "loss": 0.2428, "lr": 3.99689074539772e-05, "epoch": 0.7002457002457002, "percentage": 11.67, "elapsed_time": "0:14:06", "remaining_time": "1:46:46"}
+{"current_steps": 290, "total_steps": 2442, "loss": 0.2366, "lr": 3.9960426750592936e-05, "epoch": 0.7125307125307125, "percentage": 11.88, "elapsed_time": "0:14:18", "remaining_time": "1:46:11"}
+{"current_steps": 295, "total_steps": 2442, "loss": 0.2372, "lr": 3.995092570086546e-05, "epoch": 0.7248157248157249, "percentage": 12.08, "elapsed_time": "0:14:30", "remaining_time": "1:45:31"}
+{"current_steps": 300, "total_steps": 2442, "loss": 0.2362, "lr": 3.9940404790473825e-05, "epoch": 0.7371007371007371, "percentage": 12.29, "elapsed_time": "0:14:42", "remaining_time": "1:45:02"}
+{"current_steps": 305, "total_steps": 2442, "loss": 0.2423, "lr": 3.992886455723082e-05, "epoch": 0.7493857493857494, "percentage": 12.49, "elapsed_time": "0:15:57", "remaining_time": "1:51:46"}
+{"current_steps": 310, "total_steps": 2442, "loss": 0.2429, "lr": 3.991630559105541e-05, "epoch": 0.7616707616707616, "percentage": 12.69, "elapsed_time": "0:16:10", "remaining_time": "1:51:11"}
+{"current_steps": 315, "total_steps": 2442, "loss": 0.2401, "lr": 3.990272853394268e-05, "epoch": 0.773955773955774, "percentage": 12.9, "elapsed_time": "0:16:22", "remaining_time": "1:50:34"}
+{"current_steps": 320, "total_steps": 2442, "loss": 0.2272, "lr": 3.988813407993089e-05, "epoch": 0.7862407862407862, "percentage": 13.1, "elapsed_time": "0:16:35", "remaining_time": "1:50:00"}
+{"current_steps": 325, "total_steps": 2442, "loss": 0.2387, "lr": 3.987252297506613e-05, "epoch": 0.7985257985257985, "percentage": 13.31, "elapsed_time": "0:16:47", "remaining_time": "1:49:20"}
+{"current_steps": 330, "total_steps": 2442, "loss": 0.2361, "lr": 3.9855896017364075e-05, "epoch": 0.8108108108108109, "percentage": 13.51, "elapsed_time": "0:16:58", "remaining_time": "1:48:41"}
+{"current_steps": 335, "total_steps": 2442, "loss": 0.2425, "lr": 3.983825405676927e-05, "epoch": 0.8230958230958231, "percentage": 13.72, "elapsed_time": "0:17:11", "remaining_time": "1:48:05"}
+{"current_steps": 340, "total_steps": 2442, "loss": 0.2361, "lr": 3.981959799511161e-05, "epoch": 0.8353808353808354, "percentage": 13.92, "elapsed_time": "0:17:23", "remaining_time": "1:47:29"}
+{"current_steps": 345, "total_steps": 2442, "loss": 0.2391, "lr": 3.979992878606032e-05, "epoch": 0.8476658476658476, "percentage": 14.13, "elapsed_time": "0:17:35", "remaining_time": "1:46:56"}
+{"current_steps": 350, "total_steps": 2442, "loss": 0.2423, "lr": 3.977924743507513e-05, "epoch": 0.85995085995086, "percentage": 14.33, "elapsed_time": "0:17:48", "remaining_time": "1:46:23"}
+{"current_steps": 355, "total_steps": 2442, "loss": 0.2541, "lr": 3.975755499935492e-05, "epoch": 0.8722358722358723, "percentage": 14.54, "elapsed_time": "0:17:59", "remaining_time": "1:45:45"}
+{"current_steps": 360, "total_steps": 2442, "loss": 0.2315, "lr": 3.973485258778368e-05, "epoch": 0.8845208845208845, "percentage": 14.74, "elapsed_time": "0:18:11", "remaining_time": "1:45:10"}
+{"current_steps": 365, "total_steps": 2442, "loss": 0.242, "lr": 3.971114136087379e-05, "epoch": 0.8968058968058968, "percentage": 14.95, "elapsed_time": "0:18:23", "remaining_time": "1:44:41"}
+{"current_steps": 370, "total_steps": 2442, "loss": 0.2506, "lr": 3.968642253070675e-05, "epoch": 0.9090909090909091, "percentage": 15.15, "elapsed_time": "0:18:36", "remaining_time": "1:44:10"}
+{"current_steps": 375, "total_steps": 2442, "loss": 0.2419, "lr": 3.966069736087116e-05, "epoch": 0.9213759213759214, "percentage": 15.36, "elapsed_time": "0:18:49", "remaining_time": "1:43:46"}
+{"current_steps": 380, "total_steps": 2442, "loss": 0.23, "lr": 3.963396716639818e-05, "epoch": 0.9336609336609336, "percentage": 15.56, "elapsed_time": "0:19:01", "remaining_time": "1:43:16"}
+{"current_steps": 385, "total_steps": 2442, "loss": 0.229, "lr": 3.960623331369427e-05, "epoch": 0.9459459459459459, "percentage": 15.77, "elapsed_time": "0:19:15", "remaining_time": "1:42:51"}
+{"current_steps": 390, "total_steps": 2442, "loss": 0.2246, "lr": 3.957749722047138e-05, "epoch": 0.9582309582309583, "percentage": 15.97, "elapsed_time": "0:19:27", "remaining_time": "1:42:20"}
+{"current_steps": 395, "total_steps": 2442, "loss": 0.2306, "lr": 3.9547760355674405e-05, "epoch": 0.9705159705159705, "percentage": 16.18, "elapsed_time": "0:19:40", "remaining_time": "1:41:55"}
+{"current_steps": 400, "total_steps": 2442, "loss": 0.2432, "lr": 3.951702423940621e-05, "epoch": 0.9828009828009828, "percentage": 16.38, "elapsed_time": "0:19:52", "remaining_time": "1:41:27"}
+{"current_steps": 405, "total_steps": 2442, "loss": 0.2285, "lr": 3.948529044284981e-05, "epoch": 0.995085995085995, "percentage": 16.58, "elapsed_time": "0:21:01", "remaining_time": "1:45:46"}
+{"current_steps": 410, "total_steps": 2442, "loss": 0.2126, "lr": 3.9452560588188135e-05, "epoch": 1.0073710073710074, "percentage": 16.79, "elapsed_time": "0:21:13", "remaining_time": "1:45:10"}
+{"current_steps": 415, "total_steps": 2442, "loss": 0.2122, "lr": 3.9418836348521045e-05, "epoch": 1.0196560196560196, "percentage": 16.99, "elapsed_time": "0:21:25", "remaining_time": "1:44:36"}
+{"current_steps": 420, "total_steps": 2442, "loss": 0.2053, "lr": 3.9384119447779854e-05, "epoch": 1.031941031941032, "percentage": 17.2, "elapsed_time": "0:21:36", "remaining_time": "1:44:01"}
+{"current_steps": 425, "total_steps": 2442, "loss": 0.2151, "lr": 3.934841166063919e-05, "epoch": 1.0442260442260443, "percentage": 17.4, "elapsed_time": "0:21:48", "remaining_time": "1:43:28"}
+{"current_steps": 430, "total_steps": 2442, "loss": 0.1999, "lr": 3.931171481242625e-05, "epoch": 1.0565110565110565, "percentage": 17.61, "elapsed_time": "0:22:00", "remaining_time": "1:42:59"}
+{"current_steps": 435, "total_steps": 2442, "loss": 0.2029, "lr": 3.927403077902753e-05, "epoch": 1.0687960687960687, "percentage": 17.81, "elapsed_time": "0:22:12", "remaining_time": "1:42:26"}
+{"current_steps": 440, "total_steps": 2442, "loss": 0.2007, "lr": 3.9235361486792905e-05, "epoch": 1.0810810810810811, "percentage": 18.02, "elapsed_time": "0:22:24", "remaining_time": "1:41:55"}
+{"current_steps": 445, "total_steps": 2442, "loss": 0.2222, "lr": 3.9195708912437176e-05, "epoch": 1.0933660933660934, "percentage": 18.22, "elapsed_time": "0:22:36", "remaining_time": "1:41:27"}
+{"current_steps": 450, "total_steps": 2442, "loss": 0.2028, "lr": 3.915507508293901e-05, "epoch": 1.1056511056511056, "percentage": 18.43, "elapsed_time": "0:22:48", "remaining_time": "1:40:57"}
+{"current_steps": 455, "total_steps": 2442, "loss": 0.1981, "lr": 3.911346207543734e-05, "epoch": 1.117936117936118, "percentage": 18.63, "elapsed_time": "0:22:59", "remaining_time": "1:40:26"}
+{"current_steps": 460, "total_steps": 2442, "loss": 0.2154, "lr": 3.907087201712515e-05, "epoch": 1.1302211302211302, "percentage": 18.84, "elapsed_time": "0:23:12", "remaining_time": "1:39:58"}
+{"current_steps": 465, "total_steps": 2442, "loss": 0.2037, "lr": 3.902730708514078e-05, "epoch": 1.1425061425061425, "percentage": 19.04, "elapsed_time": "0:23:24", "remaining_time": "1:39:29"}
+{"current_steps": 470, "total_steps": 2442, "loss": 0.1997, "lr": 3.8982769506456616e-05, "epoch": 1.154791154791155, "percentage": 19.25, "elapsed_time": "0:23:35", "remaining_time": "1:38:58"}
+{"current_steps": 475, "total_steps": 2442, "loss": 0.2022, "lr": 3.893726155776524e-05, "epoch": 1.1670761670761671, "percentage": 19.45, "elapsed_time": "0:23:47", "remaining_time": "1:38:30"}
+{"current_steps": 480, "total_steps": 2442, "loss": 0.2131, "lr": 3.8890785565363046e-05, "epoch": 1.1793611793611793, "percentage": 19.66, "elapsed_time": "0:23:59", "remaining_time": "1:38:05"}
+{"current_steps": 485, "total_steps": 2442, "loss": 0.2136, "lr": 3.884334390503136e-05, "epoch": 1.1916461916461916, "percentage": 19.86, "elapsed_time": "0:24:12", "remaining_time": "1:37:40"}
+{"current_steps": 490, "total_steps": 2442, "loss": 0.209, "lr": 3.8794939001914955e-05, "epoch": 1.203931203931204, "percentage": 20.07, "elapsed_time": "0:24:24", "remaining_time": "1:37:13"}
+{"current_steps": 495, "total_steps": 2442, "loss": 0.2161, "lr": 3.87455733303981e-05, "epoch": 1.2162162162162162, "percentage": 20.27, "elapsed_time": "0:24:36", "remaining_time": "1:36:46"}
+{"current_steps": 500, "total_steps": 2442, "loss": 0.2058, "lr": 3.869524941397805e-05, "epoch": 1.2285012285012284, "percentage": 20.48, "elapsed_time": "0:24:47", "remaining_time": "1:36:19"}
+{"current_steps": 505, "total_steps": 2442, "loss": 0.209, "lr": 3.8643969825136095e-05, "epoch": 1.2407862407862407, "percentage": 20.68, "elapsed_time": "0:26:00", "remaining_time": "1:39:44"}
+{"current_steps": 510, "total_steps": 2442, "loss": 0.2134, "lr": 3.8591737185206024e-05, "epoch": 1.253071253071253, "percentage": 20.88, "elapsed_time": "0:26:11", "remaining_time": "1:39:14"}
+{"current_steps": 515, "total_steps": 2442, "loss": 0.2046, "lr": 3.853855416424011e-05, "epoch": 1.2653562653562653, "percentage": 21.09, "elapsed_time": "0:26:23", "remaining_time": "1:38:46"}
+{"current_steps": 520, "total_steps": 2442, "loss": 0.2129, "lr": 3.848442348087267e-05, "epoch": 1.2776412776412776, "percentage": 21.29, "elapsed_time": "0:26:35", "remaining_time": "1:38:18"}
+{"current_steps": 525, "total_steps": 2442, "loss": 0.2027, "lr": 3.842934790218106e-05, "epoch": 1.28992628992629, "percentage": 21.5, "elapsed_time": "0:26:48", "remaining_time": "1:37:51"}
+{"current_steps": 530, "total_steps": 2442, "loss": 0.2111, "lr": 3.837333024354422e-05, "epoch": 1.3022113022113022, "percentage": 21.7, "elapsed_time": "0:27:00", "remaining_time": "1:37:25"}
+{"current_steps": 535, "total_steps": 2442, "loss": 0.197, "lr": 3.8316373368498794e-05, "epoch": 1.3144963144963144, "percentage": 21.91, "elapsed_time": "0:27:12", "remaining_time": "1:36:57"}
+{"current_steps": 540, "total_steps": 2442, "loss": 0.2112, "lr": 3.82584801885927e-05, "epoch": 1.3267813267813269, "percentage": 22.11, "elapsed_time": "0:27:24", "remaining_time": "1:36:31"}
+{"current_steps": 545, "total_steps": 2442, "loss": 0.2215, "lr": 3.8199653663236336e-05, "epoch": 1.339066339066339, "percentage": 22.32, "elapsed_time": "0:27:36", "remaining_time": "1:36:05"}
+{"current_steps": 550, "total_steps": 2442, "loss": 0.2102, "lr": 3.813989679955128e-05, "epoch": 1.3513513513513513, "percentage": 22.52, "elapsed_time": "0:27:48", "remaining_time": "1:35:38"}
+{"current_steps": 555, "total_steps": 2442, "loss": 0.1973, "lr": 3.8079212652216595e-05, "epoch": 1.3636363636363638, "percentage": 22.73, "elapsed_time": "0:27:59", "remaining_time": "1:35:09"}
+{"current_steps": 560, "total_steps": 2442, "loss": 0.2009, "lr": 3.8017604323312616e-05, "epoch": 1.375921375921376, "percentage": 22.93, "elapsed_time": "0:28:10", "remaining_time": "1:34:42"}
+{"current_steps": 565, "total_steps": 2442, "loss": 0.2136, "lr": 3.795507496216246e-05, "epoch": 1.3882063882063882, "percentage": 23.14, "elapsed_time": "0:28:22", "remaining_time": "1:34:16"}
+{"current_steps": 570, "total_steps": 2442, "loss": 0.2026, "lr": 3.789162776517098e-05, "epoch": 1.4004914004914004, "percentage": 23.34, "elapsed_time": "0:28:34", "remaining_time": "1:33:52"}
+{"current_steps": 575, "total_steps": 2442, "loss": 0.2183, "lr": 3.78272659756614e-05, "epoch": 1.4127764127764126, "percentage": 23.55, "elapsed_time": "0:28:47", "remaining_time": "1:33:30"}
+{"current_steps": 580, "total_steps": 2442, "loss": 0.2177, "lr": 3.776199288370948e-05, "epoch": 1.425061425061425, "percentage": 23.75, "elapsed_time": "0:29:00", "remaining_time": "1:33:06"}
+{"current_steps": 585, "total_steps": 2442, "loss": 0.2022, "lr": 3.7695811825975386e-05, "epoch": 1.4373464373464373, "percentage": 23.96, "elapsed_time": "0:29:12", "remaining_time": "1:32:43"}
+{"current_steps": 590, "total_steps": 2442, "loss": 0.1979, "lr": 3.76287261855331e-05, "epoch": 1.4496314496314495, "percentage": 24.16, "elapsed_time": "0:29:25", "remaining_time": "1:32:20"}
+{"current_steps": 595, "total_steps": 2442, "loss": 0.2058, "lr": 3.7560739391697465e-05, "epoch": 1.461916461916462, "percentage": 24.37, "elapsed_time": "0:29:37", "remaining_time": "1:31:56"}
+{"current_steps": 600, "total_steps": 2442, "loss": 0.2011, "lr": 3.749185491984891e-05, "epoch": 1.4742014742014742, "percentage": 24.57, "elapsed_time": "0:29:49", "remaining_time": "1:31:33"}
+{"current_steps": 605, "total_steps": 2442, "loss": 0.1951, "lr": 3.7422076291255785e-05, "epoch": 1.4864864864864864, "percentage": 24.77, "elapsed_time": "0:31:03", "remaining_time": "1:34:17"}
+{"current_steps": 610, "total_steps": 2442, "loss": 0.2005, "lr": 3.7351407072894356e-05, "epoch": 1.4987714987714988, "percentage": 24.98, "elapsed_time": "0:31:14", "remaining_time": "1:33:49"}
+{"current_steps": 615, "total_steps": 2442, "loss": 0.2165, "lr": 3.7279850877266486e-05, "epoch": 1.511056511056511, "percentage": 25.18, "elapsed_time": "0:31:26", "remaining_time": "1:33:23"}
+{"current_steps": 620, "total_steps": 2442, "loss": 0.1904, "lr": 3.720741136221491e-05, "epoch": 1.5233415233415233, "percentage": 25.39, "elapsed_time": "0:31:37", "remaining_time": "1:32:56"}
+{"current_steps": 625, "total_steps": 2442, "loss": 0.2087, "lr": 3.713409223073636e-05, "epoch": 1.5356265356265357, "percentage": 25.59, "elapsed_time": "0:31:49", "remaining_time": "1:32:32"}
+{"current_steps": 630, "total_steps": 2442, "loss": 0.1998, "lr": 3.705989723079214e-05, "epoch": 1.547911547911548, "percentage": 25.8, "elapsed_time": "0:32:01", "remaining_time": "1:32:07"}
+{"current_steps": 635, "total_steps": 2442, "loss": 0.2005, "lr": 3.698483015511665e-05, "epoch": 1.5601965601965602, "percentage": 26.0, "elapsed_time": "0:32:13", "remaining_time": "1:31:43"}
+{"current_steps": 640, "total_steps": 2442, "loss": 0.2034, "lr": 3.690889484102344e-05, "epoch": 1.5724815724815726, "percentage": 26.21, "elapsed_time": "0:32:25", "remaining_time": "1:31:18"}
+{"current_steps": 645, "total_steps": 2442, "loss": 0.213, "lr": 3.683209517020908e-05, "epoch": 1.5847665847665846, "percentage": 26.41, "elapsed_time": "0:32:37", "remaining_time": "1:30:54"}
+{"current_steps": 650, "total_steps": 2442, "loss": 0.2036, "lr": 3.675443506855473e-05, "epoch": 1.597051597051597, "percentage": 26.62, "elapsed_time": "0:32:50", "remaining_time": "1:30:31"}
+{"current_steps": 655, "total_steps": 2442, "loss": 0.201, "lr": 3.6675918505925456e-05, "epoch": 1.6093366093366095, "percentage": 26.82, "elapsed_time": "0:33:01", "remaining_time": "1:30:07"}
+{"current_steps": 660, "total_steps": 2442, "loss": 0.2068, "lr": 3.6596549495967276e-05, "epoch": 1.6216216216216215, "percentage": 27.03, "elapsed_time": "0:33:13", "remaining_time": "1:29:42"}
+{"current_steps": 665, "total_steps": 2442, "loss": 0.1991, "lr": 3.651633209590202e-05, "epoch": 1.633906633906634, "percentage": 27.23, "elapsed_time": "0:33:25", "remaining_time": "1:29:19"}
+{"current_steps": 670, "total_steps": 2442, "loss": 0.2345, "lr": 3.6435270406319914e-05, "epoch": 1.6461916461916462, "percentage": 27.44, "elapsed_time": "0:33:37", "remaining_time": "1:28:56"}
+{"current_steps": 675, "total_steps": 2442, "loss": 0.2002, "lr": 3.635336857096997e-05, "epoch": 1.6584766584766584, "percentage": 27.64, "elapsed_time": "0:33:49", "remaining_time": "1:28:33"}
+{"current_steps": 680, "total_steps": 2442, "loss": 0.1991, "lr": 3.627063077654815e-05, "epoch": 1.6707616707616708, "percentage": 27.85, "elapsed_time": "0:34:02", "remaining_time": "1:28:11"}
+{"current_steps": 685, "total_steps": 2442, "loss": 0.2105, "lr": 3.618706125248337e-05, "epoch": 1.683046683046683, "percentage": 28.05, "elapsed_time": "0:34:14", "remaining_time": "1:27:48"}
+{"current_steps": 690, "total_steps": 2442, "loss": 0.2097, "lr": 3.6102664270721275e-05, "epoch": 1.6953316953316953, "percentage": 28.26, "elapsed_time": "0:34:25", "remaining_time": "1:27:25"}
+{"current_steps": 695, "total_steps": 2442, "loss": 0.2029, "lr": 3.601744414550589e-05, "epoch": 1.7076167076167077, "percentage": 28.46, "elapsed_time": "0:34:38", "remaining_time": "1:27:03"}
+{"current_steps": 700, "total_steps": 2442, "loss": 0.2099, "lr": 3.593140523315906e-05, "epoch": 1.71990171990172, "percentage": 28.67, "elapsed_time": "0:34:49", "remaining_time": "1:26:40"}
+{"current_steps": 705, "total_steps": 2442, "loss": 0.202, "lr": 3.584455193185778e-05, "epoch": 1.7321867321867321, "percentage": 28.87, "elapsed_time": "0:36:05", "remaining_time": "1:28:54"}
+{"current_steps": 710, "total_steps": 2442, "loss": 0.2032, "lr": 3.575688868140933e-05, "epoch": 1.7444717444717446, "percentage": 29.07, "elapsed_time": "0:36:17", "remaining_time": "1:28:32"}
+{"current_steps": 715, "total_steps": 2442, "loss": 0.2051, "lr": 3.566841996302438e-05, "epoch": 1.7567567567567568, "percentage": 29.28, "elapsed_time": "0:36:29", "remaining_time": "1:28:09"}
+{"current_steps": 720, "total_steps": 2442, "loss": 0.2064, "lr": 3.557915029908787e-05, "epoch": 1.769041769041769, "percentage": 29.48, "elapsed_time": "0:36:41", "remaining_time": "1:27:44"}
+{"current_steps": 725, "total_steps": 2442, "loss": 0.206, "lr": 3.548908425292784e-05, "epoch": 1.7813267813267815, "percentage": 29.69, "elapsed_time": "0:36:53", "remaining_time": "1:27:22"}
+{"current_steps": 730, "total_steps": 2442, "loss": 0.2016, "lr": 3.5398226428582165e-05, "epoch": 1.7936117936117935, "percentage": 29.89, "elapsed_time": "0:37:05", "remaining_time": "1:26:58"}
+{"current_steps": 735, "total_steps": 2442, "loss": 0.2119, "lr": 3.530658147056321e-05, "epoch": 1.805896805896806, "percentage": 30.1, "elapsed_time": "0:37:17", "remaining_time": "1:26:35"}
+{"current_steps": 740, "total_steps": 2442, "loss": 0.208, "lr": 3.521415406362041e-05, "epoch": 1.8181818181818183, "percentage": 30.3, "elapsed_time": "0:37:29", "remaining_time": "1:26:13"}
+{"current_steps": 745, "total_steps": 2442, "loss": 0.2038, "lr": 3.512094893250076e-05, "epoch": 1.8304668304668303, "percentage": 30.51, "elapsed_time": "0:37:41", "remaining_time": "1:25:50"}
+{"current_steps": 750, "total_steps": 2442, "loss": 0.1969, "lr": 3.5026970841707366e-05, "epoch": 1.8427518427518428, "percentage": 30.71, "elapsed_time": "0:37:53", "remaining_time": "1:25:27"}
+{"current_steps": 755, "total_steps": 2442, "loss": 0.1963, "lr": 3.493222459525579e-05, "epoch": 1.855036855036855, "percentage": 30.92, "elapsed_time": "0:38:05", "remaining_time": "1:25:06"}
+{"current_steps": 760, "total_steps": 2442, "loss": 0.2029, "lr": 3.483671503642858e-05, "epoch": 1.8673218673218672, "percentage": 31.12, "elapsed_time": "0:38:17", "remaining_time": "1:24:45"}
+{"current_steps": 765, "total_steps": 2442, "loss": 0.2019, "lr": 3.474044704752761e-05, "epoch": 1.8796068796068797, "percentage": 31.33, "elapsed_time": "0:38:30", "remaining_time": "1:24:24"}
+{"current_steps": 770, "total_steps": 2442, "loss": 0.2028, "lr": 3.464342554962454e-05, "epoch": 1.8918918918918919, "percentage": 31.53, "elapsed_time": "0:38:42", "remaining_time": "1:24:02"}
+{"current_steps": 775, "total_steps": 2442, "loss": 0.2004, "lr": 3.4545655502309254e-05, "epoch": 1.904176904176904, "percentage": 31.74, "elapsed_time": "0:38:54", "remaining_time": "1:23:40"}
+{"current_steps": 780, "total_steps": 2442, "loss": 0.1997, "lr": 3.444714190343633e-05, "epoch": 1.9164619164619165, "percentage": 31.94, "elapsed_time": "0:39:06", "remaining_time": "1:23:20"}
+{"current_steps": 785, "total_steps": 2442, "loss": 0.2049, "lr": 3.434788978886957e-05, "epoch": 1.9287469287469288, "percentage": 32.15, "elapsed_time": "0:39:19", "remaining_time": "1:23:00"}
+{"current_steps": 790, "total_steps": 2442, "loss": 0.1911, "lr": 3.424790423222455e-05, "epoch": 1.941031941031941, "percentage": 32.35, "elapsed_time": "0:39:31", "remaining_time": "1:22:39"}
+{"current_steps": 795, "total_steps": 2442, "loss": 0.1911, "lr": 3.414719034460928e-05, "epoch": 1.9533169533169534, "percentage": 32.56, "elapsed_time": "0:39:42", "remaining_time": "1:22:16"}
+{"current_steps": 800, "total_steps": 2442, "loss": 0.1979, "lr": 3.404575327436294e-05, "epoch": 1.9656019656019657, "percentage": 32.76, "elapsed_time": "0:39:54", "remaining_time": "1:21:55"}
+{"current_steps": 805, "total_steps": 2442, "loss": 0.1951, "lr": 3.3943598206792665e-05, "epoch": 1.9778869778869779, "percentage": 32.96, "elapsed_time": "0:41:04", "remaining_time": "1:23:31"}
+{"current_steps": 810, "total_steps": 2442, "loss": 0.1965, "lr": 3.384073036390857e-05, "epoch": 1.9901719901719903, "percentage": 33.17, "elapsed_time": "0:41:16", "remaining_time": "1:23:10"}
+{"current_steps": 815, "total_steps": 2442, "loss": 0.1931, "lr": 3.373715500415667e-05, "epoch": 2.0024570024570023, "percentage": 33.37, "elapsed_time": "0:41:29", "remaining_time": "1:22:50"}
+{"current_steps": 820, "total_steps": 2442, "loss": 0.1674, "lr": 3.363287742215023e-05, "epoch": 2.0147420147420148, "percentage": 33.58, "elapsed_time": "0:41:41", "remaining_time": "1:22:27"}
+{"current_steps": 825, "total_steps": 2442, "loss": 0.1721, "lr": 3.352790294839898e-05, "epoch": 2.027027027027027, "percentage": 33.78, "elapsed_time": "0:41:53", "remaining_time": "1:22:06"}
+{"current_steps": 830, "total_steps": 2442, "loss": 0.1628, "lr": 3.3422236949036726e-05, "epoch": 2.039312039312039, "percentage": 33.99, "elapsed_time": "0:42:05", "remaining_time": "1:21:45"}
+{"current_steps": 835, "total_steps": 2442, "loss": 0.1633, "lr": 3.331588482554697e-05, "epoch": 2.0515970515970516, "percentage": 34.19, "elapsed_time": "0:42:17", "remaining_time": "1:21:23"}
+{"current_steps": 840, "total_steps": 2442, "loss": 0.1711, "lr": 3.320885201448684e-05, "epoch": 2.063882063882064, "percentage": 34.4, "elapsed_time": "0:42:30", "remaining_time": "1:21:03"}
+{"current_steps": 845, "total_steps": 2442, "loss": 0.1621, "lr": 3.310114398720917e-05, "epoch": 2.076167076167076, "percentage": 34.6, "elapsed_time": "0:42:41", "remaining_time": "1:20:41"}
+{"current_steps": 850, "total_steps": 2442, "loss": 0.1673, "lr": 3.299276624958281e-05, "epoch": 2.0884520884520885, "percentage": 34.81, "elapsed_time": "0:42:53", "remaining_time": "1:20:20"}
+{"current_steps": 855, "total_steps": 2442, "loss": 0.1621, "lr": 3.288372434171116e-05, "epoch": 2.100737100737101, "percentage": 35.01, "elapsed_time": "0:43:05", "remaining_time": "1:19:59"}
+{"current_steps": 860, "total_steps": 2442, "loss": 0.1638, "lr": 3.2774023837648986e-05, "epoch": 2.113022113022113, "percentage": 35.22, "elapsed_time": "0:43:17", "remaining_time": "1:19:38"}
+{"current_steps": 865, "total_steps": 2442, "loss": 0.1642, "lr": 3.26636703451175e-05, "epoch": 2.1253071253071254, "percentage": 35.42, "elapsed_time": "0:43:29", "remaining_time": "1:19:17"}
+{"current_steps": 870, "total_steps": 2442, "loss": 0.1623, "lr": 3.2552669505217646e-05, "epoch": 2.1375921375921374, "percentage": 35.63, "elapsed_time": "0:43:41", "remaining_time": "1:18:57"}
+{"current_steps": 875, "total_steps": 2442, "loss": 0.1623, "lr": 3.24410269921418e-05, "epoch": 2.14987714987715, "percentage": 35.83, "elapsed_time": "0:43:54", "remaining_time": "1:18:37"}
+{"current_steps": 880, "total_steps": 2442, "loss": 0.1691, "lr": 3.232874851288367e-05, "epoch": 2.1621621621621623, "percentage": 36.04, "elapsed_time": "0:44:05", "remaining_time": "1:18:16"}
+{"current_steps": 885, "total_steps": 2442, "loss": 0.1697, "lr": 3.221583980694659e-05, "epoch": 2.1744471744471743, "percentage": 36.24, "elapsed_time": "0:44:17", "remaining_time": "1:17:55"}
+{"current_steps": 890, "total_steps": 2442, "loss": 0.1635, "lr": 3.21023066460501e-05, "epoch": 2.1867321867321867, "percentage": 36.45, "elapsed_time": "0:44:30", "remaining_time": "1:17:36"}
+{"current_steps": 895, "total_steps": 2442, "loss": 0.1661, "lr": 3.198815483383492e-05, "epoch": 2.199017199017199, "percentage": 36.65, "elapsed_time": "0:44:42", "remaining_time": "1:17:15"}
+{"current_steps": 900, "total_steps": 2442, "loss": 0.1625, "lr": 3.1873390205566295e-05, "epoch": 2.211302211302211, "percentage": 36.86, "elapsed_time": "0:44:53", "remaining_time": "1:16:55"}
+{"current_steps": 905, "total_steps": 2442, "loss": 0.1676, "lr": 3.175801862783565e-05, "epoch": 2.2235872235872236, "percentage": 37.06, "elapsed_time": "0:46:05", "remaining_time": "1:18:16"}
+{"current_steps": 910, "total_steps": 2442, "loss": 0.1679, "lr": 3.164204599826077e-05, "epoch": 2.235872235872236, "percentage": 37.26, "elapsed_time": "0:46:17", "remaining_time": "1:17:55"}
+{"current_steps": 915, "total_steps": 2442, "loss": 0.161, "lr": 3.1525478245184245e-05, "epoch": 2.248157248157248, "percentage": 37.47, "elapsed_time": "0:46:28", "remaining_time": "1:17:33"}
+{"current_steps": 920, "total_steps": 2442, "loss": 0.1598, "lr": 3.140832132737051e-05, "epoch": 2.2604422604422605, "percentage": 37.67, "elapsed_time": "0:46:40", "remaining_time": "1:17:12"}
+{"current_steps": 925, "total_steps": 2442, "loss": 0.1655, "lr": 3.129058123370116e-05, "epoch": 2.2727272727272725, "percentage": 37.88, "elapsed_time": "0:46:52", "remaining_time": "1:16:52"}
+{"current_steps": 930, "total_steps": 2442, "loss": 0.1602, "lr": 3.117226398286887e-05, "epoch": 2.285012285012285, "percentage": 38.08, "elapsed_time": "0:47:04", "remaining_time": "1:16:31"}
+{"current_steps": 935, "total_steps": 2442, "loss": 0.1674, "lr": 3.105337562306968e-05, "epoch": 2.2972972972972974, "percentage": 38.29, "elapsed_time": "0:47:15", "remaining_time": "1:16:09"}
+{"current_steps": 940, "total_steps": 2442, "loss": 0.1607, "lr": 3.0933922231693854e-05, "epoch": 2.30958230958231, "percentage": 38.49, "elapsed_time": "0:47:27", "remaining_time": "1:15:49"}
+{"current_steps": 945, "total_steps": 2442, "loss": 0.1648, "lr": 3.08139099150152e-05, "epoch": 2.321867321867322, "percentage": 38.7, "elapsed_time": "0:47:39", "remaining_time": "1:15:30"}
+{"current_steps": 950, "total_steps": 2442, "loss": 0.1638, "lr": 3.069334480787893e-05, "epoch": 2.3341523341523343, "percentage": 38.9, "elapsed_time": "0:47:51", "remaining_time": "1:15:09"}
+{"current_steps": 955, "total_steps": 2442, "loss": 0.1587, "lr": 3.057223307338806e-05, "epoch": 2.3464373464373462, "percentage": 39.11, "elapsed_time": "0:48:03", "remaining_time": "1:14:49"}
+{"current_steps": 960, "total_steps": 2442, "loss": 0.1675, "lr": 3.0450580902588346e-05, "epoch": 2.3587223587223587, "percentage": 39.31, "elapsed_time": "0:48:15", "remaining_time": "1:14:29"}
+{"current_steps": 965, "total_steps": 2442, "loss": 0.1623, "lr": 3.032839451415182e-05, "epoch": 2.371007371007371, "percentage": 39.52, "elapsed_time": "0:48:27", "remaining_time": "1:14:09"}
+{"current_steps": 970, "total_steps": 2442, "loss": 0.1573, "lr": 3.0205680154058904e-05, "epoch": 2.383292383292383, "percentage": 39.72, "elapsed_time": "0:48:39", "remaining_time": "1:13:49"}
+{"current_steps": 975, "total_steps": 2442, "loss": 0.1681, "lr": 3.0082444095279117e-05, "epoch": 2.3955773955773956, "percentage": 39.93, "elapsed_time": "0:48:51", "remaining_time": "1:13:30"}
+{"current_steps": 980, "total_steps": 2442, "loss": 0.1636, "lr": 2.9958692637450406e-05, "epoch": 2.407862407862408, "percentage": 40.13, "elapsed_time": "0:49:03", "remaining_time": "1:13:10"}
+{"current_steps": 985, "total_steps": 2442, "loss": 0.1584, "lr": 2.983443210655714e-05, "epoch": 2.42014742014742, "percentage": 40.34, "elapsed_time": "0:49:14", "remaining_time": "1:12:50"}
+{"current_steps": 990, "total_steps": 2442, "loss": 0.1705, "lr": 2.9709668854606706e-05, "epoch": 2.4324324324324325, "percentage": 40.54, "elapsed_time": "0:49:26", "remaining_time": "1:12:31"}
+{"current_steps": 995, "total_steps": 2442, "loss": 0.1747, "lr": 2.9584409259304828e-05, "epoch": 2.444717444717445, "percentage": 40.75, "elapsed_time": "0:49:38", "remaining_time": "1:12:11"}
+{"current_steps": 1000, "total_steps": 2442, "loss": 0.1699, "lr": 2.945865972372954e-05, "epoch": 2.457002457002457, "percentage": 40.95, "elapsed_time": "0:49:50", "remaining_time": "1:11:52"}
+{"current_steps": 1005, "total_steps": 2442, "loss": 0.1627, "lr": 2.9332426676003858e-05, "epoch": 2.4692874692874693, "percentage": 41.15, "elapsed_time": "0:51:03", "remaining_time": "1:13:00"}
+{"current_steps": 1010, "total_steps": 2442, "loss": 0.163, "lr": 2.920571656896722e-05, "epoch": 2.4815724815724813, "percentage": 41.36, "elapsed_time": "0:51:16", "remaining_time": "1:12:41"}
+{"current_steps": 1015, "total_steps": 2442, "loss": 0.1665, "lr": 2.907853587984558e-05, "epoch": 2.493857493857494, "percentage": 41.56, "elapsed_time": "0:51:28", "remaining_time": "1:12:22"}
+{"current_steps": 1020, "total_steps": 2442, "loss": 0.171, "lr": 2.8950891109920333e-05, "epoch": 2.506142506142506, "percentage": 41.77, "elapsed_time": "0:51:40", "remaining_time": "1:12:02"}
+{"current_steps": 1025, "total_steps": 2442, "loss": 0.1704, "lr": 2.882278878419597e-05, "epoch": 2.5184275184275187, "percentage": 41.97, "elapsed_time": "0:51:53", "remaining_time": "1:11:44"}
+{"current_steps": 1030, "total_steps": 2442, "loss": 0.1646, "lr": 2.8694235451066538e-05, "epoch": 2.5307125307125307, "percentage": 42.18, "elapsed_time": "0:52:05", "remaining_time": "1:11:24"}
+{"current_steps": 1035, "total_steps": 2442, "loss": 0.1597, "lr": 2.8565237681980876e-05, "epoch": 2.542997542997543, "percentage": 42.38, "elapsed_time": "0:52:18", "remaining_time": "1:11:06"}
+{"current_steps": 1040, "total_steps": 2442, "loss": 0.164, "lr": 2.843580207110672e-05, "epoch": 2.555282555282555, "percentage": 42.59, "elapsed_time": "0:52:30", "remaining_time": "1:10:46"}
+{"current_steps": 1045, "total_steps": 2442, "loss": 0.1712, "lr": 2.830593523499361e-05, "epoch": 2.5675675675675675, "percentage": 42.79, "elapsed_time": "0:52:42", "remaining_time": "1:10:28"}
+{"current_steps": 1050, "total_steps": 2442, "loss": 0.1657, "lr": 2.8175643812234627e-05, "epoch": 2.57985257985258, "percentage": 43.0, "elapsed_time": "0:52:54", "remaining_time": "1:10:08"}
+{"current_steps": 1055, "total_steps": 2442, "loss": 0.1635, "lr": 2.8044934463127108e-05, "epoch": 2.592137592137592, "percentage": 43.2, "elapsed_time": "0:53:06", "remaining_time": "1:09:49"}
+{"current_steps": 1060, "total_steps": 2442, "loss": 0.1613, "lr": 2.7913813869332112e-05, "epoch": 2.6044226044226044, "percentage": 43.41, "elapsed_time": "0:53:18", "remaining_time": "1:09:29"}
+{"current_steps": 1065, "total_steps": 2442, "loss": 0.1653, "lr": 2.7782288733532915e-05, "epoch": 2.616707616707617, "percentage": 43.61, "elapsed_time": "0:53:30", "remaining_time": "1:09:11"}
+{"current_steps": 1070, "total_steps": 2442, "loss": 0.1574, "lr": 2.7650365779092346e-05, "epoch": 2.628992628992629, "percentage": 43.82, "elapsed_time": "0:53:42", "remaining_time": "1:08:52"}
+{"current_steps": 1075, "total_steps": 2442, "loss": 0.1656, "lr": 2.751805174970912e-05, "epoch": 2.6412776412776413, "percentage": 44.02, "elapsed_time": "0:53:54", "remaining_time": "1:08:33"}
+{"current_steps": 1080, "total_steps": 2442, "loss": 0.1684, "lr": 2.7385353409073093e-05, "epoch": 2.6535626535626538, "percentage": 44.23, "elapsed_time": "0:54:07", "remaining_time": "1:08:15"}
+{"current_steps": 1085, "total_steps": 2442, "loss": 0.1625, "lr": 2.725227754051953e-05, "epoch": 2.6658476658476657, "percentage": 44.43, "elapsed_time": "0:54:18", "remaining_time": "1:07:55"}
+{"current_steps": 1090, "total_steps": 2442, "loss": 0.1576, "lr": 2.711883094668234e-05, "epoch": 2.678132678132678, "percentage": 44.64, "elapsed_time": "0:54:32", "remaining_time": "1:07:38"}
+{"current_steps": 1095, "total_steps": 2442, "loss": 0.1675, "lr": 2.698502044914633e-05, "epoch": 2.69041769041769, "percentage": 44.84, "elapsed_time": "0:54:44", "remaining_time": "1:07:19"}
+{"current_steps": 1100, "total_steps": 2442, "loss": 0.1645, "lr": 2.685085288809853e-05, "epoch": 2.7027027027027026, "percentage": 45.05, "elapsed_time": "0:54:56", "remaining_time": "1:07:01"}
+{"current_steps": 1105, "total_steps": 2442, "loss": 0.165, "lr": 2.671633512197848e-05, "epoch": 2.714987714987715, "percentage": 45.25, "elapsed_time": "0:56:04", "remaining_time": "1:07:50"}
+{"current_steps": 1110, "total_steps": 2442, "loss": 0.1717, "lr": 2.658147402712768e-05, "epoch": 2.7272727272727275, "percentage": 45.45, "elapsed_time": "0:56:16", "remaining_time": "1:07:32"}
+{"current_steps": 1115, "total_steps": 2442, "loss": 0.1595, "lr": 2.6446276497438064e-05, "epoch": 2.7395577395577395, "percentage": 45.66, "elapsed_time": "0:56:28", "remaining_time": "1:07:12"}
+{"current_steps": 1120, "total_steps": 2442, "loss": 0.167, "lr": 2.6310749443999593e-05, "epoch": 2.751842751842752, "percentage": 45.86, "elapsed_time": "0:56:40", "remaining_time": "1:06:53"}
+{"current_steps": 1125, "total_steps": 2442, "loss": 0.159, "lr": 2.617489979474699e-05, "epoch": 2.764127764127764, "percentage": 46.07, "elapsed_time": "0:56:53", "remaining_time": "1:06:35"}
+{"current_steps": 1130, "total_steps": 2442, "loss": 0.1683, "lr": 2.6038734494105562e-05, "epoch": 2.7764127764127764, "percentage": 46.27, "elapsed_time": "0:57:05", "remaining_time": "1:06:16"}
+{"current_steps": 1135, "total_steps": 2442, "loss": 0.1604, "lr": 2.590226050263625e-05, "epoch": 2.788697788697789, "percentage": 46.48, "elapsed_time": "0:57:17", "remaining_time": "1:05:58"}
+{"current_steps": 1140, "total_steps": 2442, "loss": 0.1664, "lr": 2.5765484796679768e-05, "epoch": 2.800982800982801, "percentage": 46.68, "elapsed_time": "0:57:29", "remaining_time": "1:05:39"}
+{"current_steps": 1145, "total_steps": 2442, "loss": 0.1651, "lr": 2.5628414368000035e-05, "epoch": 2.8132678132678133, "percentage": 46.89, "elapsed_time": "0:57:40", "remaining_time": "1:05:20"}
+{"current_steps": 1150, "total_steps": 2442, "loss": 0.1685, "lr": 2.5491056223426746e-05, "epoch": 2.8255528255528253, "percentage": 47.09, "elapsed_time": "0:57:53", "remaining_time": "1:05:02"}
+{"current_steps": 1155, "total_steps": 2442, "loss": 0.1632, "lr": 2.5353417384497166e-05, "epoch": 2.8378378378378377, "percentage": 47.3, "elapsed_time": "0:58:04", "remaining_time": "1:04:43"}
+{"current_steps": 1160, "total_steps": 2442, "loss": 0.1673, "lr": 2.5215504887097243e-05, "epoch": 2.85012285012285, "percentage": 47.5, "elapsed_time": "0:58:16", "remaining_time": "1:04:24"}
+{"current_steps": 1165, "total_steps": 2442, "loss": 0.1594, "lr": 2.5077325781101918e-05, "epoch": 2.8624078624078626, "percentage": 47.71, "elapsed_time": "0:58:27", "remaining_time": "1:04:05"}
+{"current_steps": 1170, "total_steps": 2442, "loss": 0.1673, "lr": 2.493888713001476e-05, "epoch": 2.8746928746928746, "percentage": 47.91, "elapsed_time": "0:58:39", "remaining_time": "1:03:46"}
+{"current_steps": 1175, "total_steps": 2442, "loss": 0.1593, "lr": 2.480019601060687e-05, "epoch": 2.886977886977887, "percentage": 48.12, "elapsed_time": "0:58:51", "remaining_time": "1:03:28"}
+{"current_steps": 1180, "total_steps": 2442, "loss": 0.1712, "lr": 2.4661259512555176e-05, "epoch": 2.899262899262899, "percentage": 48.32, "elapsed_time": "0:59:03", "remaining_time": "1:03:09"}
+{"current_steps": 1185, "total_steps": 2442, "loss": 0.1724, "lr": 2.4522084738079933e-05, "epoch": 2.9115479115479115, "percentage": 48.53, "elapsed_time": "0:59:15", "remaining_time": "1:02:51"}
+{"current_steps": 1190, "total_steps": 2442, "loss": 0.1625, "lr": 2.4382678801581762e-05, "epoch": 2.923832923832924, "percentage": 48.73, "elapsed_time": "0:59:27", "remaining_time": "1:02:33"}
+{"current_steps": 1195, "total_steps": 2442, "loss": 0.1646, "lr": 2.4243048829277916e-05, "epoch": 2.9361179361179364, "percentage": 48.94, "elapsed_time": "0:59:39", "remaining_time": "1:02:14"}
+{"current_steps": 1200, "total_steps": 2442, "loss": 0.1628, "lr": 2.410320195883802e-05, "epoch": 2.9484029484029484, "percentage": 49.14, "elapsed_time": "0:59:50", "remaining_time": "1:01:56"}
+{"current_steps": 1205, "total_steps": 2442, "loss": 0.1679, "lr": 2.396314533901918e-05, "epoch": 2.960687960687961, "percentage": 49.34, "elapsed_time": "1:00:59", "remaining_time": "1:02:36"}
+{"current_steps": 1210, "total_steps": 2442, "loss": 0.1636, "lr": 2.3822886129300603e-05, "epoch": 2.972972972972973, "percentage": 49.55, "elapsed_time": "1:01:10", "remaining_time": "1:02:17"}
+{"current_steps": 1215, "total_steps": 2442, "loss": 0.1639, "lr": 2.368243149951755e-05, "epoch": 2.9852579852579852, "percentage": 49.75, "elapsed_time": "1:01:22", "remaining_time": "1:01:58"}
+{"current_steps": 1220, "total_steps": 2442, "loss": 0.1668, "lr": 2.3541788629494865e-05, "epoch": 2.9975429975429977, "percentage": 49.96, "elapsed_time": "1:01:34", "remaining_time": "1:01:40"}
+{"current_steps": 1225, "total_steps": 2442, "loss": 0.1331, "lr": 2.3400964708679944e-05, "epoch": 3.0098280098280097, "percentage": 50.16, "elapsed_time": "1:01:47", "remaining_time": "1:01:22"}
+{"current_steps": 1230, "total_steps": 2442, "loss": 0.1314, "lr": 2.325996693577522e-05, "epoch": 3.022113022113022, "percentage": 50.37, "elapsed_time": "1:01:59", "remaining_time": "1:01:04"}
+{"current_steps": 1235, "total_steps": 2442, "loss": 0.1298, "lr": 2.311880251837019e-05, "epoch": 3.0343980343980346, "percentage": 50.57, "elapsed_time": "1:02:10", "remaining_time": "1:00:45"}
+{"current_steps": 1240, "total_steps": 2442, "loss": 0.1348, "lr": 2.2977478672572933e-05, "epoch": 3.0466830466830466, "percentage": 50.78, "elapsed_time": "1:02:22", "remaining_time": "1:00:27"}
+{"current_steps": 1245, "total_steps": 2442, "loss": 0.1246, "lr": 2.2836002622641297e-05, "epoch": 3.058968058968059, "percentage": 50.98, "elapsed_time": "1:02:33", "remaining_time": "1:00:08"}
+{"current_steps": 1250, "total_steps": 2442, "loss": 0.1286, "lr": 2.269438160061354e-05, "epoch": 3.0712530712530715, "percentage": 51.19, "elapsed_time": "1:02:46", "remaining_time": "0:59:51"}
+{"current_steps": 1255, "total_steps": 2442, "loss": 0.1226, "lr": 2.2552622845938698e-05, "epoch": 3.0835380835380835, "percentage": 51.39, "elapsed_time": "1:02:57", "remaining_time": "0:59:33"}
+{"current_steps": 1260, "total_steps": 2442, "loss": 0.1335, "lr": 2.2410733605106462e-05, "epoch": 3.095823095823096, "percentage": 51.6, "elapsed_time": "1:03:09", "remaining_time": "0:59:14"}
+{"current_steps": 1265, "total_steps": 2442, "loss": 0.1306, "lr": 2.2268721131276805e-05, "epoch": 3.108108108108108, "percentage": 51.8, "elapsed_time": "1:03:22", "remaining_time": "0:58:57"}
+{"current_steps": 1270, "total_steps": 2442, "loss": 0.1228, "lr": 2.2126592683909154e-05, "epoch": 3.1203931203931203, "percentage": 52.01, "elapsed_time": "1:03:34", "remaining_time": "0:58:39"}
+{"current_steps": 1275, "total_steps": 2442, "loss": 0.1279, "lr": 2.1984355528391342e-05, "epoch": 3.1326781326781328, "percentage": 52.21, "elapsed_time": "1:03:46", "remaining_time": "0:58:22"}
+{"current_steps": 1280, "total_steps": 2442, "loss": 0.1282, "lr": 2.1842016935668188e-05, "epoch": 3.1449631449631448, "percentage": 52.42, "elapsed_time": "1:03:58", "remaining_time": "0:58:04"}
+{"current_steps": 1285, "total_steps": 2442, "loss": 0.1341, "lr": 2.169958418186982e-05, "epoch": 3.157248157248157, "percentage": 52.62, "elapsed_time": "1:04:10", "remaining_time": "0:57:47"}
+{"current_steps": 1290, "total_steps": 2442, "loss": 0.1315, "lr": 2.1557064547939754e-05, "epoch": 3.1695331695331697, "percentage": 52.83, "elapsed_time": "1:04:23", "remaining_time": "0:57:29"}
+{"current_steps": 1295, "total_steps": 2442, "loss": 0.1371, "lr": 2.1414465319262666e-05, "epoch": 3.1818181818181817, "percentage": 53.03, "elapsed_time": "1:04:35", "remaining_time": "0:57:12"}
+{"current_steps": 1300, "total_steps": 2442, "loss": 0.1272, "lr": 2.1271793785291997e-05, "epoch": 3.194103194103194, "percentage": 53.24, "elapsed_time": "1:04:47", "remaining_time": "0:56:55"}
+{"current_steps": 1305, "total_steps": 2442, "loss": 0.1316, "lr": 2.1129057239177337e-05, "epoch": 3.2063882063882065, "percentage": 53.44, "elapsed_time": "1:05:56", "remaining_time": "0:57:27"}
+{"current_steps": 1310, "total_steps": 2442, "loss": 0.1319, "lr": 2.0986262977391577e-05, "epoch": 3.2186732186732185, "percentage": 53.64, "elapsed_time": "1:06:08", "remaining_time": "0:57:09"}
+{"current_steps": 1315, "total_steps": 2442, "loss": 0.1312, "lr": 2.084341829935796e-05, "epoch": 3.230958230958231, "percentage": 53.85, "elapsed_time": "1:06:19", "remaining_time": "0:56:50"}
+{"current_steps": 1320, "total_steps": 2442, "loss": 0.1219, "lr": 2.0700530507076916e-05, "epoch": 3.2432432432432434, "percentage": 54.05, "elapsed_time": "1:06:31", "remaining_time": "0:56:33"}
+{"current_steps": 1325, "total_steps": 2442, "loss": 0.1278, "lr": 2.0557606904752833e-05, "epoch": 3.2555282555282554, "percentage": 54.26, "elapsed_time": "1:06:43", "remaining_time": "0:56:14"}
+{"current_steps": 1330, "total_steps": 2442, "loss": 0.1221, "lr": 2.0414654798420622e-05, "epoch": 3.267813267813268, "percentage": 54.46, "elapsed_time": "1:06:54", "remaining_time": "0:55:56"}
+{"current_steps": 1335, "total_steps": 2442, "loss": 0.1269, "lr": 2.02716814955723e-05, "epoch": 3.2800982800982803, "percentage": 54.67, "elapsed_time": "1:07:06", "remaining_time": "0:55:38"}
+{"current_steps": 1340, "total_steps": 2442, "loss": 0.1305, "lr": 2.0128694304783406e-05, "epoch": 3.2923832923832923, "percentage": 54.87, "elapsed_time": "1:07:18", "remaining_time": "0:55:21"}
+{"current_steps": 1345, "total_steps": 2442, "loss": 0.1296, "lr": 1.9985700535339406e-05, "epoch": 3.3046683046683047, "percentage": 55.08, "elapsed_time": "1:07:29", "remaining_time": "0:55:03"}
+{"current_steps": 1350, "total_steps": 2442, "loss": 0.1332, "lr": 1.984270749686207e-05, "epoch": 3.3169533169533167, "percentage": 55.28, "elapsed_time": "1:07:41", "remaining_time": "0:54:45"}
+{"current_steps": 1355, "total_steps": 2442, "loss": 0.1347, "lr": 1.9699722498935786e-05, "epoch": 3.329238329238329, "percentage": 55.49, "elapsed_time": "1:07:53", "remaining_time": "0:54:27"}
+{"current_steps": 1360, "total_steps": 2442, "loss": 0.1271, "lr": 1.9556752850733933e-05, "epoch": 3.3415233415233416, "percentage": 55.69, "elapsed_time": "1:08:05", "remaining_time": "0:54:10"}
+{"current_steps": 1365, "total_steps": 2442, "loss": 0.1286, "lr": 1.9413805860645242e-05, "epoch": 3.3538083538083536, "percentage": 55.9, "elapsed_time": "1:08:18", "remaining_time": "0:53:53"}
+{"current_steps": 1370, "total_steps": 2442, "loss": 0.1296, "lr": 1.9270888835900165e-05, "epoch": 3.366093366093366, "percentage": 56.1, "elapsed_time": "1:08:30", "remaining_time": "0:53:36"}
+{"current_steps": 1375, "total_steps": 2442, "loss": 0.1287, "lr": 1.9128009082197417e-05, "epoch": 3.3783783783783785, "percentage": 56.31, "elapsed_time": "1:08:42", "remaining_time": "0:53:19"}
+{"current_steps": 1380, "total_steps": 2442, "loss": 0.1292, "lr": 1.8985173903330428e-05, "epoch": 3.3906633906633905, "percentage": 56.51, "elapsed_time": "1:08:54", "remaining_time": "0:53:01"}
+{"current_steps": 1385, "total_steps": 2442, "loss": 0.1264, "lr": 1.884239060081407e-05, "epoch": 3.402948402948403, "percentage": 56.72, "elapsed_time": "1:09:06", "remaining_time": "0:52:44"}
+{"current_steps": 1390, "total_steps": 2442, "loss": 0.1234, "lr": 1.869966647351135e-05, "epoch": 3.4152334152334154, "percentage": 56.92, "elapsed_time": "1:09:18", "remaining_time": "0:52:27"}
+{"current_steps": 1395, "total_steps": 2442, "loss": 0.1306, "lr": 1.8557008817260343e-05, "epoch": 3.4275184275184274, "percentage": 57.13, "elapsed_time": "1:09:30", "remaining_time": "0:52:10"}
+{"current_steps": 1400, "total_steps": 2442, "loss": 0.1301, "lr": 1.8414424924501222e-05, "epoch": 3.43980343980344, "percentage": 57.33, "elapsed_time": "1:09:42", "remaining_time": "0:51:52"}
+{"current_steps": 1405, "total_steps": 2442, "loss": 0.1266, "lr": 1.827192208390347e-05, "epoch": 3.4520884520884523, "percentage": 57.53, "elapsed_time": "1:10:48", "remaining_time": "0:52:15"}
+{"current_steps": 1410, "total_steps": 2442, "loss": 0.1279, "lr": 1.812950757999334e-05, "epoch": 3.4643734643734643, "percentage": 57.74, "elapsed_time": "1:11:00", "remaining_time": "0:51:58"}
+{"current_steps": 1415, "total_steps": 2442, "loss": 0.1275, "lr": 1.7987188692781417e-05, "epoch": 3.4766584766584767, "percentage": 57.94, "elapsed_time": "1:11:12", "remaining_time": "0:51:40"}
+{"current_steps": 1420, "total_steps": 2442, "loss": 0.1339, "lr": 1.784497269739052e-05, "epoch": 3.488943488943489, "percentage": 58.15, "elapsed_time": "1:11:23", "remaining_time": "0:51:23"}
+{"current_steps": 1425, "total_steps": 2442, "loss": 0.1283, "lr": 1.770286686368381e-05, "epoch": 3.501228501228501, "percentage": 58.35, "elapsed_time": "1:11:36", "remaining_time": "0:51:06"}
+{"current_steps": 1430, "total_steps": 2442, "loss": 0.131, "lr": 1.756087845589312e-05, "epoch": 3.5135135135135136, "percentage": 58.56, "elapsed_time": "1:11:48", "remaining_time": "0:50:49"}
+{"current_steps": 1435, "total_steps": 2442, "loss": 0.1323, "lr": 1.7419014732247683e-05, "epoch": 3.5257985257985256, "percentage": 58.76, "elapsed_time": "1:12:00", "remaining_time": "0:50:31"}
+{"current_steps": 1440, "total_steps": 2442, "loss": 0.1373, "lr": 1.7277282944603047e-05, "epoch": 3.538083538083538, "percentage": 58.97, "elapsed_time": "1:12:12", "remaining_time": "0:50:14"}
+{"current_steps": 1445, "total_steps": 2442, "loss": 0.1313, "lr": 1.713569033807041e-05, "epoch": 3.5503685503685505, "percentage": 59.17, "elapsed_time": "1:12:25", "remaining_time": "0:49:57"}
+{"current_steps": 1450, "total_steps": 2442, "loss": 0.1237, "lr": 1.6994244150646244e-05, "epoch": 3.562653562653563, "percentage": 59.38, "elapsed_time": "1:12:36", "remaining_time": "0:49:40"}
+{"current_steps": 1455, "total_steps": 2442, "loss": 0.1238, "lr": 1.6852951612842278e-05, "epoch": 3.574938574938575, "percentage": 59.58, "elapsed_time": "1:12:48", "remaining_time": "0:49:23"}
+{"current_steps": 1460, "total_steps": 2442, "loss": 0.1299, "lr": 1.671181994731595e-05, "epoch": 3.5872235872235874, "percentage": 59.79, "elapsed_time": "1:13:00", "remaining_time": "0:49:06"}
+{"current_steps": 1465, "total_steps": 2442, "loss": 0.1339, "lr": 1.6570856368501108e-05, "epoch": 3.5995085995085994, "percentage": 59.99, "elapsed_time": "1:13:12", "remaining_time": "0:48:49"}
+{"current_steps": 1470, "total_steps": 2442, "loss": 0.1275, "lr": 1.643006808223931e-05, "epoch": 3.611793611793612, "percentage": 60.2, "elapsed_time": "1:13:24", "remaining_time": "0:48:32"}
+{"current_steps": 1475, "total_steps": 2442, "loss": 0.1257, "lr": 1.6289462285411387e-05, "epoch": 3.6240786240786242, "percentage": 60.4, "elapsed_time": "1:13:36", "remaining_time": "0:48:15"}
+{"current_steps": 1480, "total_steps": 2442, "loss": 0.1281, "lr": 1.614904616556962e-05, "epoch": 3.6363636363636362, "percentage": 60.61, "elapsed_time": "1:13:48", "remaining_time": "0:47:58"}
+{"current_steps": 1485, "total_steps": 2442, "loss": 0.126, "lr": 1.6008826900570294e-05, "epoch": 3.6486486486486487, "percentage": 60.81, "elapsed_time": "1:13:59", "remaining_time": "0:47:41"}
+{"current_steps": 1490, "total_steps": 2442, "loss": 0.1284, "lr": 1.586881165820675e-05, "epoch": 3.6609336609336607, "percentage": 61.02, "elapsed_time": "1:14:11", "remaining_time": "0:47:24"}
+{"current_steps": 1495, "total_steps": 2442, "loss": 0.1276, "lr": 1.5729007595843037e-05, "epoch": 3.673218673218673, "percentage": 61.22, "elapsed_time": "1:14:23", "remaining_time": "0:47:07"}
+{"current_steps": 1500, "total_steps": 2442, "loss": 0.1325, "lr": 1.5589421860047986e-05, "epoch": 3.6855036855036856, "percentage": 61.43, "elapsed_time": "1:14:36", "remaining_time": "0:46:50"}
+{"current_steps": 1505, "total_steps": 2442, "loss": 0.1309, "lr": 1.5450061586229903e-05, "epoch": 3.697788697788698, "percentage": 61.63, "elapsed_time": "1:15:47", "remaining_time": "0:47:11"}
+{"current_steps": 1510, "total_steps": 2442, "loss": 0.1259, "lr": 1.5310933898271864e-05, "epoch": 3.71007371007371, "percentage": 61.83, "elapsed_time": "1:15:59", "remaining_time": "0:46:54"}
+{"current_steps": 1515, "total_steps": 2442, "loss": 0.1321, "lr": 1.5172045908167462e-05, "epoch": 3.7223587223587224, "percentage": 62.04, "elapsed_time": "1:16:11", "remaining_time": "0:46:37"}
+{"current_steps": 1520, "total_steps": 2442, "loss": 0.1275, "lr": 1.5033404715657344e-05, "epoch": 3.7346437346437344, "percentage": 62.24, "elapsed_time": "1:16:22", "remaining_time": "0:46:19"}
+{"current_steps": 1525, "total_steps": 2442, "loss": 0.1372, "lr": 1.4895017407866217e-05, "epoch": 3.746928746928747, "percentage": 62.45, "elapsed_time": "1:16:35", "remaining_time": "0:46:03"}
+{"current_steps": 1530, "total_steps": 2442, "loss": 0.1289, "lr": 1.4756891058940606e-05, "epoch": 3.7592137592137593, "percentage": 62.65, "elapsed_time": "1:16:47", "remaining_time": "0:45:46"}
+{"current_steps": 1535, "total_steps": 2442, "loss": 0.1302, "lr": 1.4619032729687223e-05, "epoch": 3.7714987714987718, "percentage": 62.86, "elapsed_time": "1:16:59", "remaining_time": "0:45:29"}
+{"current_steps": 1540, "total_steps": 2442, "loss": 0.1325, "lr": 1.4481449467212004e-05, "epoch": 3.7837837837837838, "percentage": 63.06, "elapsed_time": "1:17:10", "remaining_time": "0:45:12"}
+{"current_steps": 1545, "total_steps": 2442, "loss": 0.1333, "lr": 1.4344148304559926e-05, "epoch": 3.796068796068796, "percentage": 63.27, "elapsed_time": "1:17:22", "remaining_time": "0:44:55"}
+{"current_steps": 1550, "total_steps": 2442, "loss": 0.1265, "lr": 1.4207136260355426e-05, "epoch": 3.808353808353808, "percentage": 63.47, "elapsed_time": "1:17:34", "remaining_time": "0:44:38"}
+{"current_steps": 1555, "total_steps": 2442, "loss": 0.1298, "lr": 1.4070420338443667e-05, "epoch": 3.8206388206388207, "percentage": 63.68, "elapsed_time": "1:17:45", "remaining_time": "0:44:21"}
+{"current_steps": 1560, "total_steps": 2442, "loss": 0.1296, "lr": 1.3934007527532494e-05, "epoch": 3.832923832923833, "percentage": 63.88, "elapsed_time": "1:17:56", "remaining_time": "0:44:04"}
+{"current_steps": 1565, "total_steps": 2442, "loss": 0.1239, "lr": 1.3797904800835174e-05, "epoch": 3.845208845208845, "percentage": 64.09, "elapsed_time": "1:18:08", "remaining_time": "0:43:47"}
+{"current_steps": 1570, "total_steps": 2442, "loss": 0.1237, "lr": 1.3662119115713968e-05, "epoch": 3.8574938574938575, "percentage": 64.29, "elapsed_time": "1:18:20", "remaining_time": "0:43:30"}
+{"current_steps": 1575, "total_steps": 2442, "loss": 0.1263, "lr": 1.3526657413324427e-05, "epoch": 3.8697788697788695, "percentage": 64.5, "elapsed_time": "1:18:32", "remaining_time": "0:43:13"}
+{"current_steps": 1580, "total_steps": 2442, "loss": 0.1319, "lr": 1.3391526618260636e-05, "epoch": 3.882063882063882, "percentage": 64.7, "elapsed_time": "1:18:43", "remaining_time": "0:42:57"}
+{"current_steps": 1585, "total_steps": 2442, "loss": 0.1329, "lr": 1.3256733638201172e-05, "epoch": 3.8943488943488944, "percentage": 64.91, "elapsed_time": "1:18:55", "remaining_time": "0:42:40"}
+{"current_steps": 1590, "total_steps": 2442, "loss": 0.1251, "lr": 1.3122285363556053e-05, "epoch": 3.906633906633907, "percentage": 65.11, "elapsed_time": "1:19:07", "remaining_time": "0:42:23"}
+{"current_steps": 1595, "total_steps": 2442, "loss": 0.1255, "lr": 1.2988188667114487e-05, "epoch": 3.918918918918919, "percentage": 65.32, "elapsed_time": "1:19:19", "remaining_time": "0:42:07"}
+{"current_steps": 1600, "total_steps": 2442, "loss": 0.1296, "lr": 1.2854450403693526e-05, "epoch": 3.9312039312039313, "percentage": 65.52, "elapsed_time": "1:19:30", "remaining_time": "0:41:50"}
+{"current_steps": 1605, "total_steps": 2442, "loss": 0.1278, "lr": 1.272107740978769e-05, "epoch": 3.9434889434889433, "percentage": 65.72, "elapsed_time": "1:20:44", "remaining_time": "0:42:06"}
+{"current_steps": 1610, "total_steps": 2442, "loss": 0.1282, "lr": 1.2588076503219475e-05, "epoch": 3.9557739557739557, "percentage": 65.93, "elapsed_time": "1:20:56", "remaining_time": "0:41:49"}
+{"current_steps": 1615, "total_steps": 2442, "loss": 0.1253, "lr": 1.2455454482790859e-05, "epoch": 3.968058968058968, "percentage": 66.13, "elapsed_time": "1:21:07", "remaining_time": "0:41:32"}
+{"current_steps": 1620, "total_steps": 2442, "loss": 0.1251, "lr": 1.2323218127935714e-05, "epoch": 3.98034398034398, "percentage": 66.34, "elapsed_time": "1:21:19", "remaining_time": "0:41:15"}
+{"current_steps": 1625, "total_steps": 2442, "loss": 0.1271, "lr": 1.2191374198373309e-05, "epoch": 3.9926289926289926, "percentage": 66.54, "elapsed_time": "1:21:30", "remaining_time": "0:40:58"}
+{"current_steps": 1630, "total_steps": 2442, "loss": 0.12, "lr": 1.2059929433762734e-05, "epoch": 4.004914004914005, "percentage": 66.75, "elapsed_time": "1:21:43", "remaining_time": "0:40:42"}
+{"current_steps": 1635, "total_steps": 2442, "loss": 0.1024, "lr": 1.1928890553358352e-05, "epoch": 4.017199017199017, "percentage": 66.95, "elapsed_time": "1:21:54", "remaining_time": "0:40:25"}
+{"current_steps": 1640, "total_steps": 2442, "loss": 0.1027, "lr": 1.1798264255666387e-05, "epoch": 4.0294840294840295, "percentage": 67.16, "elapsed_time": "1:22:06", "remaining_time": "0:40:09"}
+{"current_steps": 1645, "total_steps": 2442, "loss": 0.1032, "lr": 1.1668057218102436e-05, "epoch": 4.041769041769042, "percentage": 67.36, "elapsed_time": "1:22:18", "remaining_time": "0:39:52"}
+{"current_steps": 1650, "total_steps": 2442, "loss": 0.1013, "lr": 1.1538276096650175e-05, "epoch": 4.054054054054054, "percentage": 67.57, "elapsed_time": "1:22:31", "remaining_time": "0:39:36"}
+{"current_steps": 1655, "total_steps": 2442, "loss": 0.0984, "lr": 1.1408927525521118e-05, "epoch": 4.066339066339066, "percentage": 67.77, "elapsed_time": "1:22:42", "remaining_time": "0:39:20"}
+{"current_steps": 1660, "total_steps": 2442, "loss": 0.0993, "lr": 1.1280018116815438e-05, "epoch": 4.078624078624078, "percentage": 67.98, "elapsed_time": "1:22:54", "remaining_time": "0:39:03"}
+{"current_steps": 1665, "total_steps": 2442, "loss": 0.0998, "lr": 1.115155446018404e-05, "epoch": 4.090909090909091, "percentage": 68.18, "elapsed_time": "1:23:06", "remaining_time": "0:38:47"}
+{"current_steps": 1670, "total_steps": 2442, "loss": 0.0972, "lr": 1.1023543122491626e-05, "epoch": 4.103194103194103, "percentage": 68.39, "elapsed_time": "1:23:18", "remaining_time": "0:38:30"}
+{"current_steps": 1675, "total_steps": 2442, "loss": 0.1014, "lr": 1.089599064748108e-05, "epoch": 4.115479115479116, "percentage": 68.59, "elapsed_time": "1:23:29", "remaining_time": "0:38:14"}
+{"current_steps": 1680, "total_steps": 2442, "loss": 0.1002, "lr": 1.0768903555438927e-05, "epoch": 4.127764127764128, "percentage": 68.8, "elapsed_time": "1:23:41", "remaining_time": "0:37:57"}
+{"current_steps": 1685, "total_steps": 2442, "loss": 0.097, "lr": 1.0642288342862007e-05, "epoch": 4.14004914004914, "percentage": 69.0, "elapsed_time": "1:23:53", "remaining_time": "0:37:41"}
+{"current_steps": 1690, "total_steps": 2442, "loss": 0.0981, "lr": 1.051615148212544e-05, "epoch": 4.152334152334152, "percentage": 69.21, "elapsed_time": "1:24:04", "remaining_time": "0:37:24"}
+{"current_steps": 1695, "total_steps": 2442, "loss": 0.0987, "lr": 1.0390499421151706e-05, "epoch": 4.164619164619165, "percentage": 69.41, "elapsed_time": "1:24:16", "remaining_time": "0:37:08"}
+{"current_steps": 1700, "total_steps": 2442, "loss": 0.0984, "lr": 1.0265338583081088e-05, "epoch": 4.176904176904177, "percentage": 69.62, "elapsed_time": "1:24:28", "remaining_time": "0:36:52"}
+{"current_steps": 1705, "total_steps": 2442, "loss": 0.1003, "lr": 1.0140675365943284e-05, "epoch": 4.1891891891891895, "percentage": 69.82, "elapsed_time": "1:25:37", "remaining_time": "0:37:00"}
+{"current_steps": 1710, "total_steps": 2442, "loss": 0.1038, "lr": 1.0016516142330404e-05, "epoch": 4.201474201474202, "percentage": 70.02, "elapsed_time": "1:25:49", "remaining_time": "0:36:44"}
+{"current_steps": 1715, "total_steps": 2442, "loss": 0.1029, "lr": 9.89286725907117e-06, "epoch": 4.2137592137592135, "percentage": 70.23, "elapsed_time": "1:26:00", "remaining_time": "0:36:27"}
+{"current_steps": 1720, "total_steps": 2442, "loss": 0.1015, "lr": 9.769735036906475e-06, "epoch": 4.226044226044226, "percentage": 70.43, "elapsed_time": "1:26:12", "remaining_time": "0:36:11"}
+{"current_steps": 1725, "total_steps": 2442, "loss": 0.1034, "lr": 9.647125770166321e-06, "epoch": 4.238329238329238, "percentage": 70.64, "elapsed_time": "1:26:24", "remaining_time": "0:35:54"}
+{"current_steps": 1730, "total_steps": 2442, "loss": 0.1022, "lr": 9.525045726448001e-06, "epoch": 4.250614250614251, "percentage": 70.84, "elapsed_time": "1:26:36", "remaining_time": "0:35:38"}
+{"current_steps": 1735, "total_steps": 2442, "loss": 0.0999, "lr": 9.40350114629577e-06, "epoch": 4.262899262899263, "percentage": 71.05, "elapsed_time": "1:26:48", "remaining_time": "0:35:22"}
+{"current_steps": 1740, "total_steps": 2442, "loss": 0.1007, "lr": 9.282498242881784e-06, "epoch": 4.275184275184275, "percentage": 71.25, "elapsed_time": "1:27:00", "remaining_time": "0:35:06"}
+{"current_steps": 1745, "total_steps": 2442, "loss": 0.0992, "lr": 9.162043201688517e-06, "epoch": 4.287469287469287, "percentage": 71.46, "elapsed_time": "1:27:12", "remaining_time": "0:34:49"}
+{"current_steps": 1750, "total_steps": 2442, "loss": 0.0969, "lr": 9.042142180192596e-06, "epoch": 4.2997542997543, "percentage": 71.66, "elapsed_time": "1:27:24", "remaining_time": "0:34:33"}
+{"current_steps": 1755, "total_steps": 2442, "loss": 0.0978, "lr": 8.92280130754998e-06, "epoch": 4.312039312039312, "percentage": 71.87, "elapsed_time": "1:27:36", "remaining_time": "0:34:17"}
+{"current_steps": 1760, "total_steps": 2442, "loss": 0.1017, "lr": 8.804026684282694e-06, "epoch": 4.324324324324325, "percentage": 72.07, "elapsed_time": "1:27:48", "remaining_time": "0:34:01"}
+{"current_steps": 1765, "total_steps": 2442, "loss": 0.0998, "lr": 8.685824381966975e-06, "epoch": 4.336609336609337, "percentage": 72.28, "elapsed_time": "1:28:00", "remaining_time": "0:33:45"}
+{"current_steps": 1770, "total_steps": 2442, "loss": 0.098, "lr": 8.568200442922865e-06, "epoch": 4.348894348894349, "percentage": 72.48, "elapsed_time": "1:28:13", "remaining_time": "0:33:29"}
+{"current_steps": 1775, "total_steps": 2442, "loss": 0.1044, "lr": 8.451160879905398e-06, "epoch": 4.361179361179361, "percentage": 72.69, "elapsed_time": "1:28:24", "remaining_time": "0:33:13"}
+{"current_steps": 1780, "total_steps": 2442, "loss": 0.0998, "lr": 8.33471167579717e-06, "epoch": 4.3734643734643734, "percentage": 72.89, "elapsed_time": "1:28:36", "remaining_time": "0:32:57"}
+{"current_steps": 1785, "total_steps": 2442, "loss": 0.1058, "lr": 8.218858783302566e-06, "epoch": 4.385749385749386, "percentage": 73.1, "elapsed_time": "1:28:48", "remaining_time": "0:32:41"}
+{"current_steps": 1790, "total_steps": 2442, "loss": 0.1008, "lr": 8.103608124643412e-06, "epoch": 4.398034398034398, "percentage": 73.3, "elapsed_time": "1:29:00", "remaining_time": "0:32:25"}
+{"current_steps": 1795, "total_steps": 2442, "loss": 0.1021, "lr": 7.988965591256284e-06, "epoch": 4.41031941031941, "percentage": 73.51, "elapsed_time": "1:29:12", "remaining_time": "0:32:09"}
+{"current_steps": 1800, "total_steps": 2442, "loss": 0.1047, "lr": 7.874937043491331e-06, "epoch": 4.422604422604422, "percentage": 73.71, "elapsed_time": "1:29:24", "remaining_time": "0:31:53"}
+{"current_steps": 1805, "total_steps": 2442, "loss": 0.1008, "lr": 7.761528310312679e-06, "epoch": 4.434889434889435, "percentage": 73.91, "elapsed_time": "1:30:35", "remaining_time": "0:31:58"}
+{"current_steps": 1810, "total_steps": 2442, "loss": 0.1001, "lr": 7.648745189000511e-06, "epoch": 4.447174447174447, "percentage": 74.12, "elapsed_time": "1:30:47", "remaining_time": "0:31:41"}
+{"current_steps": 1815, "total_steps": 2442, "loss": 0.1034, "lr": 7.536593444854663e-06, "epoch": 4.45945945945946, "percentage": 74.32, "elapsed_time": "1:30:58", "remaining_time": "0:31:25"}
+{"current_steps": 1820, "total_steps": 2442, "loss": 0.1001, "lr": 7.4250788108999686e-06, "epoch": 4.471744471744472, "percentage": 74.53, "elapsed_time": "1:31:10", "remaining_time": "0:31:09"}
+{"current_steps": 1825, "total_steps": 2442, "loss": 0.1036, "lr": 7.314206987593162e-06, "epoch": 4.484029484029484, "percentage": 74.73, "elapsed_time": "1:31:22", "remaining_time": "0:30:53"}
+{"current_steps": 1830, "total_steps": 2442, "loss": 0.1006, "lr": 7.203983642531462e-06, "epoch": 4.496314496314496, "percentage": 74.94, "elapsed_time": "1:31:34", "remaining_time": "0:30:37"}
+{"current_steps": 1835, "total_steps": 2442, "loss": 0.1075, "lr": 7.094414410162913e-06, "epoch": 4.5085995085995085, "percentage": 75.14, "elapsed_time": "1:31:46", "remaining_time": "0:30:21"}
+{"current_steps": 1840, "total_steps": 2442, "loss": 0.103, "lr": 6.985504891498291e-06, "epoch": 4.520884520884521, "percentage": 75.35, "elapsed_time": "1:31:58", "remaining_time": "0:30:05"}
+{"current_steps": 1845, "total_steps": 2442, "loss": 0.1007, "lr": 6.8772606538248285e-06, "epoch": 4.533169533169533, "percentage": 75.55, "elapsed_time": "1:32:10", "remaining_time": "0:29:49"}
+{"current_steps": 1850, "total_steps": 2442, "loss": 0.1052, "lr": 6.769687230421638e-06, "epoch": 4.545454545454545, "percentage": 75.76, "elapsed_time": "1:32:22", "remaining_time": "0:29:33"}
+{"current_steps": 1855, "total_steps": 2442, "loss": 0.1027, "lr": 6.662790120276803e-06, "epoch": 4.557739557739557, "percentage": 75.96, "elapsed_time": "1:32:34", "remaining_time": "0:29:17"}
+{"current_steps": 1860, "total_steps": 2442, "loss": 0.1013, "lr": 6.556574787806344e-06, "epoch": 4.57002457002457, "percentage": 76.17, "elapsed_time": "1:32:46", "remaining_time": "0:29:01"}
+{"current_steps": 1865, "total_steps": 2442, "loss": 0.1009, "lr": 6.451046662574831e-06, "epoch": 4.582309582309582, "percentage": 76.37, "elapsed_time": "1:32:57", "remaining_time": "0:28:45"}
+{"current_steps": 1870, "total_steps": 2442, "loss": 0.1012, "lr": 6.346211139017877e-06, "epoch": 4.594594594594595, "percentage": 76.58, "elapsed_time": "1:33:09", "remaining_time": "0:28:29"}
+{"current_steps": 1875, "total_steps": 2442, "loss": 0.1015, "lr": 6.242073576166337e-06, "epoch": 4.606879606879607, "percentage": 76.78, "elapsed_time": "1:33:21", "remaining_time": "0:28:14"}
+{"current_steps": 1880, "total_steps": 2442, "loss": 0.0959, "lr": 6.138639297372404e-06, "epoch": 4.61916461916462, "percentage": 76.99, "elapsed_time": "1:33:33", "remaining_time": "0:27:58"}
+{"current_steps": 1885, "total_steps": 2442, "loss": 0.0998, "lr": 6.035913590037479e-06, "epoch": 4.631449631449631, "percentage": 77.19, "elapsed_time": "1:33:45", "remaining_time": "0:27:42"}
+{"current_steps": 1890, "total_steps": 2442, "loss": 0.1016, "lr": 5.933901705341851e-06, "epoch": 4.643734643734644, "percentage": 77.4, "elapsed_time": "1:33:57", "remaining_time": "0:27:26"}
+{"current_steps": 1895, "total_steps": 2442, "loss": 0.095, "lr": 5.832608857976321e-06, "epoch": 4.656019656019656, "percentage": 77.6, "elapsed_time": "1:34:09", "remaining_time": "0:27:10"}
+{"current_steps": 1900, "total_steps": 2442, "loss": 0.1022, "lr": 5.732040225875584e-06, "epoch": 4.6683046683046685, "percentage": 77.81, "elapsed_time": "1:34:21", "remaining_time": "0:26:55"}
+{"current_steps": 1905, "total_steps": 2442, "loss": 0.1008, "lr": 5.632200949953579e-06, "epoch": 4.680589680589681, "percentage": 78.01, "elapsed_time": "1:35:29", "remaining_time": "0:26:55"}
+{"current_steps": 1910, "total_steps": 2442, "loss": 0.0966, "lr": 5.533096133840677e-06, "epoch": 4.6928746928746925, "percentage": 78.21, "elapsed_time": "1:35:41", "remaining_time": "0:26:39"}
+{"current_steps": 1915, "total_steps": 2442, "loss": 0.0929, "lr": 5.434730843622778e-06, "epoch": 4.705159705159705, "percentage": 78.42, "elapsed_time": "1:35:54", "remaining_time": "0:26:23"}
+{"current_steps": 1920, "total_steps": 2442, "loss": 0.0953, "lr": 5.337110107582377e-06, "epoch": 4.717444717444717, "percentage": 78.62, "elapsed_time": "1:36:05", "remaining_time": "0:26:07"}
+{"current_steps": 1925, "total_steps": 2442, "loss": 0.1005, "lr": 5.2402389159414755e-06, "epoch": 4.72972972972973, "percentage": 78.83, "elapsed_time": "1:36:17", "remaining_time": "0:25:51"}
+{"current_steps": 1930, "total_steps": 2442, "loss": 0.0945, "lr": 5.144122220606542e-06, "epoch": 4.742014742014742, "percentage": 79.03, "elapsed_time": "1:36:30", "remaining_time": "0:25:36"}
+{"current_steps": 1935, "total_steps": 2442, "loss": 0.0964, "lr": 5.048764934915349e-06, "epoch": 4.754299754299755, "percentage": 79.24, "elapsed_time": "1:36:42", "remaining_time": "0:25:20"}
+{"current_steps": 1940, "total_steps": 2442, "loss": 0.0987, "lr": 4.954171933385805e-06, "epoch": 4.766584766584766, "percentage": 79.44, "elapsed_time": "1:36:54", "remaining_time": "0:25:04"}
+{"current_steps": 1945, "total_steps": 2442, "loss": 0.1008, "lr": 4.8603480514667836e-06, "epoch": 4.778869778869779, "percentage": 79.65, "elapsed_time": "1:37:06", "remaining_time": "0:24:48"}
+{"current_steps": 1950, "total_steps": 2442, "loss": 0.1025, "lr": 4.767298085290963e-06, "epoch": 4.791154791154791, "percentage": 79.85, "elapsed_time": "1:37:18", "remaining_time": "0:24:32"}
+{"current_steps": 1955, "total_steps": 2442, "loss": 0.1015, "lr": 4.675026791429624e-06, "epoch": 4.803439803439804, "percentage": 80.06, "elapsed_time": "1:37:29", "remaining_time": "0:24:17"}
+{"current_steps": 1960, "total_steps": 2442, "loss": 0.0955, "lr": 4.583538886649525e-06, "epoch": 4.815724815724816, "percentage": 80.26, "elapsed_time": "1:37:41", "remaining_time": "0:24:01"}
+{"current_steps": 1965, "total_steps": 2442, "loss": 0.1003, "lr": 4.492839047671764e-06, "epoch": 4.828009828009828, "percentage": 80.47, "elapsed_time": "1:37:53", "remaining_time": "0:23:45"}
+{"current_steps": 1970, "total_steps": 2442, "loss": 0.098, "lr": 4.4029319109327465e-06, "epoch": 4.84029484029484, "percentage": 80.67, "elapsed_time": "1:38:05", "remaining_time": "0:23:30"}
+{"current_steps": 1975, "total_steps": 2442, "loss": 0.0973, "lr": 4.313822072347136e-06, "epoch": 4.8525798525798525, "percentage": 80.88, "elapsed_time": "1:38:17", "remaining_time": "0:23:14"}
+{"current_steps": 1980, "total_steps": 2442, "loss": 0.0965, "lr": 4.22551408707296e-06, "epoch": 4.864864864864865, "percentage": 81.08, "elapsed_time": "1:38:29", "remaining_time": "0:22:58"}
+{"current_steps": 1985, "total_steps": 2442, "loss": 0.1015, "lr": 4.138012469278714e-06, "epoch": 4.877149877149877, "percentage": 81.29, "elapsed_time": "1:38:40", "remaining_time": "0:22:43"}
+{"current_steps": 1990, "total_steps": 2442, "loss": 0.1031, "lr": 4.051321691912649e-06, "epoch": 4.88943488943489, "percentage": 81.49, "elapsed_time": "1:38:52", "remaining_time": "0:22:27"}
+{"current_steps": 1995, "total_steps": 2442, "loss": 0.0991, "lr": 3.9654461864740935e-06, "epoch": 4.901719901719901, "percentage": 81.7, "elapsed_time": "1:39:03", "remaining_time": "0:22:11"}
+{"current_steps": 2000, "total_steps": 2442, "loss": 0.0968, "lr": 3.880390342786915e-06, "epoch": 4.914004914004914, "percentage": 81.9, "elapsed_time": "1:39:15", "remaining_time": "0:21:56"}
+{"current_steps": 2005, "total_steps": 2442, "loss": 0.0932, "lr": 3.7961585087751516e-06, "epoch": 4.926289926289926, "percentage": 82.1, "elapsed_time": "1:40:26", "remaining_time": "0:21:53"}
+{"current_steps": 2010, "total_steps": 2442, "loss": 0.0997, "lr": 3.71275499024071e-06, "epoch": 4.938574938574939, "percentage": 82.31, "elapsed_time": "1:40:38", "remaining_time": "0:21:37"}
+{"current_steps": 2015, "total_steps": 2442, "loss": 0.0942, "lr": 3.6301840506433083e-06, "epoch": 4.950859950859951, "percentage": 82.51, "elapsed_time": "1:40:50", "remaining_time": "0:21:22"}
+{"current_steps": 2020, "total_steps": 2442, "loss": 0.0978, "lr": 3.5484499108824853e-06, "epoch": 4.963144963144963, "percentage": 82.72, "elapsed_time": "1:41:02", "remaining_time": "0:21:06"}
+{"current_steps": 2025, "total_steps": 2442, "loss": 0.1029, "lr": 3.4675567490818727e-06, "epoch": 4.975429975429975, "percentage": 82.92, "elapsed_time": "1:41:14", "remaining_time": "0:20:50"}
+{"current_steps": 2030, "total_steps": 2442, "loss": 0.0975, "lr": 3.3875087003756036e-06, "epoch": 4.987714987714988, "percentage": 83.13, "elapsed_time": "1:41:26", "remaining_time": "0:20:35"}
+{"current_steps": 2035, "total_steps": 2442, "loss": 0.0966, "lr": 3.30830985669691e-06, "epoch": 5.0, "percentage": 83.33, "elapsed_time": "1:41:38", "remaining_time": "0:20:19"}
+{"current_steps": 2040, "total_steps": 2442, "loss": 0.0854, "lr": 3.22996426656899e-06, "epoch": 5.012285012285012, "percentage": 83.54, "elapsed_time": "1:41:50", "remaining_time": "0:20:04"}
+{"current_steps": 2045, "total_steps": 2442, "loss": 0.0836, "lr": 3.1524759348980096e-06, "epoch": 5.024570024570025, "percentage": 83.74, "elapsed_time": "1:42:02", "remaining_time": "0:19:48"}
+{"current_steps": 2050, "total_steps": 2442, "loss": 0.0828, "lr": 3.0758488227684212e-06, "epoch": 5.036855036855036, "percentage": 83.95, "elapsed_time": "1:42:13", "remaining_time": "0:19:32"}
+{"current_steps": 2055, "total_steps": 2442, "loss": 0.0889, "lr": 3.0000868472404423e-06, "epoch": 5.049140049140049, "percentage": 84.15, "elapsed_time": "1:42:26", "remaining_time": "0:19:17"}
+{"current_steps": 2060, "total_steps": 2442, "loss": 0.0868, "lr": 2.9251938811498436e-06, "epoch": 5.061425061425061, "percentage": 84.36, "elapsed_time": "1:42:37", "remaining_time": "0:19:01"}
+{"current_steps": 2065, "total_steps": 2442, "loss": 0.0859, "lr": 2.8511737529099704e-06, "epoch": 5.073710073710074, "percentage": 84.56, "elapsed_time": "1:42:49", "remaining_time": "0:18:46"}
+{"current_steps": 2070, "total_steps": 2442, "loss": 0.0875, "lr": 2.7780302463160235e-06, "epoch": 5.085995085995086, "percentage": 84.77, "elapsed_time": "1:43:01", "remaining_time": "0:18:30"}
+{"current_steps": 2075, "total_steps": 2442, "loss": 0.0875, "lr": 2.705767100351673e-06, "epoch": 5.098280098280099, "percentage": 84.97, "elapsed_time": "1:43:12", "remaining_time": "0:18:15"}
+{"current_steps": 2080, "total_steps": 2442, "loss": 0.0872, "lr": 2.634388008997899e-06, "epoch": 5.11056511056511, "percentage": 85.18, "elapsed_time": "1:43:25", "remaining_time": "0:17:59"}
+{"current_steps": 2085, "total_steps": 2442, "loss": 0.0817, "lr": 2.5638966210441597e-06, "epoch": 5.122850122850123, "percentage": 85.38, "elapsed_time": "1:43:37", "remaining_time": "0:17:44"}
+{"current_steps": 2090, "total_steps": 2442, "loss": 0.0865, "lr": 2.4942965399018926e-06, "epoch": 5.135135135135135, "percentage": 85.59, "elapsed_time": "1:43:48", "remaining_time": "0:17:29"}
+{"current_steps": 2095, "total_steps": 2442, "loss": 0.0867, "lr": 2.425591323420289e-06, "epoch": 5.1474201474201475, "percentage": 85.79, "elapsed_time": "1:44:01", "remaining_time": "0:17:13"}
+{"current_steps": 2100, "total_steps": 2442, "loss": 0.0851, "lr": 2.357784483704444e-06, "epoch": 5.15970515970516, "percentage": 86.0, "elapsed_time": "1:44:12", "remaining_time": "0:16:58"}
+{"current_steps": 2105, "total_steps": 2442, "loss": 0.0835, "lr": 2.2908794869358044e-06, "epoch": 5.171990171990172, "percentage": 86.2, "elapsed_time": "1:45:25", "remaining_time": "0:16:52"}
+{"current_steps": 2110, "total_steps": 2442, "loss": 0.0891, "lr": 2.2248797531949952e-06, "epoch": 5.184275184275184, "percentage": 86.4, "elapsed_time": "1:45:36", "remaining_time": "0:16:37"}
+{"current_steps": 2115, "total_steps": 2442, "loss": 0.0859, "lr": 2.1597886562869917e-06, "epoch": 5.196560196560196, "percentage": 86.61, "elapsed_time": "1:45:48", "remaining_time": "0:16:21"}
+{"current_steps": 2120, "total_steps": 2442, "loss": 0.0842, "lr": 2.095609523568638e-06, "epoch": 5.208845208845209, "percentage": 86.81, "elapsed_time": "1:46:00", "remaining_time": "0:16:06"}
+{"current_steps": 2125, "total_steps": 2442, "loss": 0.087, "lr": 2.0323456357785855e-06, "epoch": 5.221130221130221, "percentage": 87.02, "elapsed_time": "1:46:12", "remaining_time": "0:15:50"}
+{"current_steps": 2130, "total_steps": 2442, "loss": 0.0878, "lr": 1.970000226869553e-06, "epoch": 5.233415233415234, "percentage": 87.22, "elapsed_time": "1:46:23", "remaining_time": "0:15:35"}
+{"current_steps": 2135, "total_steps": 2442, "loss": 0.0806, "lr": 1.90857648384305e-06, "epoch": 5.245700245700245, "percentage": 87.43, "elapsed_time": "1:46:35", "remaining_time": "0:15:19"}
+{"current_steps": 2140, "total_steps": 2442, "loss": 0.0828, "lr": 1.848077546586431e-06, "epoch": 5.257985257985258, "percentage": 87.63, "elapsed_time": "1:46:47", "remaining_time": "0:15:04"}
+{"current_steps": 2145, "total_steps": 2442, "loss": 0.083, "lr": 1.7885065077123976e-06, "epoch": 5.27027027027027, "percentage": 87.84, "elapsed_time": "1:46:58", "remaining_time": "0:14:48"}
+{"current_steps": 2150, "total_steps": 2442, "loss": 0.0834, "lr": 1.7298664124009245e-06, "epoch": 5.282555282555283, "percentage": 88.04, "elapsed_time": "1:47:11", "remaining_time": "0:14:33"}
+{"current_steps": 2155, "total_steps": 2442, "loss": 0.0826, "lr": 1.672160258243567e-06, "epoch": 5.294840294840295, "percentage": 88.25, "elapsed_time": "1:47:23", "remaining_time": "0:14:18"}
+{"current_steps": 2160, "total_steps": 2442, "loss": 0.0868, "lr": 1.615390995090258e-06, "epoch": 5.3071253071253075, "percentage": 88.45, "elapsed_time": "1:47:35", "remaining_time": "0:14:02"}
+{"current_steps": 2165, "total_steps": 2442, "loss": 0.0812, "lr": 1.559561524898492e-06, "epoch": 5.319410319410319, "percentage": 88.66, "elapsed_time": "1:47:47", "remaining_time": "0:13:47"}
+{"current_steps": 2170, "total_steps": 2442, "loss": 0.0875, "lr": 1.5046747015849893e-06, "epoch": 5.3316953316953315, "percentage": 88.86, "elapsed_time": "1:47:59", "remaining_time": "0:13:32"}
+{"current_steps": 2175, "total_steps": 2442, "loss": 0.087, "lr": 1.4507333308798255e-06, "epoch": 5.343980343980344, "percentage": 89.07, "elapsed_time": "1:48:11", "remaining_time": "0:13:16"}
+{"current_steps": 2180, "total_steps": 2442, "loss": 0.0771, "lr": 1.3977401701829752e-06, "epoch": 5.356265356265356, "percentage": 89.27, "elapsed_time": "1:48:22", "remaining_time": "0:13:01"}
+{"current_steps": 2185, "total_steps": 2442, "loss": 0.0871, "lr": 1.345697928423384e-06, "epoch": 5.368550368550369, "percentage": 89.48, "elapsed_time": "1:48:34", "remaining_time": "0:12:46"}
+{"current_steps": 2190, "total_steps": 2442, "loss": 0.0835, "lr": 1.2946092659204767e-06, "epoch": 5.38083538083538, "percentage": 89.68, "elapsed_time": "1:48:46", "remaining_time": "0:12:31"}
+{"current_steps": 2195, "total_steps": 2442, "loss": 0.0843, "lr": 1.244476794248175e-06, "epoch": 5.393120393120393, "percentage": 89.89, "elapsed_time": "1:48:58", "remaining_time": "0:12:15"}
+{"current_steps": 2200, "total_steps": 2442, "loss": 0.0834, "lr": 1.1953030761014017e-06, "epoch": 5.405405405405405, "percentage": 90.09, "elapsed_time": "1:49:10", "remaining_time": "0:12:00"}
+{"current_steps": 2205, "total_steps": 2442, "loss": 0.0834, "lr": 1.147090625165055e-06, "epoch": 5.417690417690418, "percentage": 90.29, "elapsed_time": "1:50:21", "remaining_time": "0:11:51"}
+{"current_steps": 2210, "total_steps": 2442, "loss": 0.0868, "lr": 1.0998419059855503e-06, "epoch": 5.42997542997543, "percentage": 90.5, "elapsed_time": "1:50:33", "remaining_time": "0:11:36"}
+{"current_steps": 2215, "total_steps": 2442, "loss": 0.0836, "lr": 1.053559333844798e-06, "epoch": 5.442260442260443, "percentage": 90.7, "elapsed_time": "1:50:45", "remaining_time": "0:11:21"}
+{"current_steps": 2220, "total_steps": 2442, "loss": 0.0798, "lr": 1.0082452746367721e-06, "epoch": 5.454545454545454, "percentage": 90.91, "elapsed_time": "1:50:56", "remaining_time": "0:11:05"}
+{"current_steps": 2225, "total_steps": 2442, "loss": 0.0847, "lr": 9.639020447465475e-07, "epoch": 5.466830466830467, "percentage": 91.11, "elapsed_time": "1:51:07", "remaining_time": "0:10:50"}
+{"current_steps": 2230, "total_steps": 2442, "loss": 0.0825, "lr": 9.205319109318922e-07, "epoch": 5.479115479115479, "percentage": 91.32, "elapsed_time": "1:51:19", "remaining_time": "0:10:35"}
+{"current_steps": 2235, "total_steps": 2442, "loss": 0.0844, "lr": 8.781370902074049e-07, "epoch": 5.4914004914004915, "percentage": 91.52, "elapsed_time": "1:51:31", "remaining_time": "0:10:19"}
+{"current_steps": 2240, "total_steps": 2442, "loss": 0.0829, "lr": 8.367197497311719e-07, "epoch": 5.503685503685504, "percentage": 91.73, "elapsed_time": "1:51:44", "remaining_time": "0:10:04"}
+{"current_steps": 2245, "total_steps": 2442, "loss": 0.0832, "lr": 7.962820066939958e-07, "epoch": 5.515970515970516, "percentage": 91.93, "elapsed_time": "1:51:55", "remaining_time": "0:09:49"}
+{"current_steps": 2250, "total_steps": 2442, "loss": 0.0835, "lr": 7.568259282111645e-07, "epoch": 5.528255528255528, "percentage": 92.14, "elapsed_time": "1:52:06", "remaining_time": "0:09:34"}
+{"current_steps": 2255, "total_steps": 2442, "loss": 0.0889, "lr": 7.183535312167755e-07, "epoch": 5.54054054054054, "percentage": 92.34, "elapsed_time": "1:52:18", "remaining_time": "0:09:18"}
+{"current_steps": 2260, "total_steps": 2442, "loss": 0.0791, "lr": 6.808667823606474e-07, "epoch": 5.552825552825553, "percentage": 92.55, "elapsed_time": "1:52:30", "remaining_time": "0:09:03"}
+{"current_steps": 2265, "total_steps": 2442, "loss": 0.0836, "lr": 6.443675979077779e-07, "epoch": 5.565110565110565, "percentage": 92.75, "elapsed_time": "1:52:42", "remaining_time": "0:08:48"}
+{"current_steps": 2270, "total_steps": 2442, "loss": 0.0777, "lr": 6.088578436403847e-07, "epoch": 5.577395577395578, "percentage": 92.96, "elapsed_time": "1:52:54", "remaining_time": "0:08:33"}
+{"current_steps": 2275, "total_steps": 2442, "loss": 0.0809, "lr": 5.743393347625436e-07, "epoch": 5.58968058968059, "percentage": 93.16, "elapsed_time": "1:53:07", "remaining_time": "0:08:18"}
+{"current_steps": 2280, "total_steps": 2442, "loss": 0.0829, "lr": 5.408138358073833e-07, "epoch": 5.601965601965602, "percentage": 93.37, "elapsed_time": "1:53:18", "remaining_time": "0:08:03"}
+{"current_steps": 2285, "total_steps": 2442, "loss": 0.0816, "lr": 5.082830605468969e-07, "epoch": 5.614250614250614, "percentage": 93.57, "elapsed_time": "1:53:31", "remaining_time": "0:07:47"}
+{"current_steps": 2290, "total_steps": 2442, "loss": 0.0834, "lr": 4.767486719043235e-07, "epoch": 5.6265356265356266, "percentage": 93.78, "elapsed_time": "1:53:43", "remaining_time": "0:07:32"}
+{"current_steps": 2295, "total_steps": 2442, "loss": 0.0824, "lr": 4.4621228186915833e-07, "epoch": 5.638820638820639, "percentage": 93.98, "elapsed_time": "1:53:55", "remaining_time": "0:07:17"}
+{"current_steps": 2300, "total_steps": 2442, "loss": 0.084, "lr": 4.166754514147275e-07, "epoch": 5.651105651105651, "percentage": 94.19, "elapsed_time": "1:54:07", "remaining_time": "0:07:02"}
+{"current_steps": 2305, "total_steps": 2442, "loss": 0.0791, "lr": 3.881396904184231e-07, "epoch": 5.663390663390663, "percentage": 94.39, "elapsed_time": "1:55:16", "remaining_time": "0:06:51"}
+{"current_steps": 2310, "total_steps": 2442, "loss": 0.0793, "lr": 3.6060645758449584e-07, "epoch": 5.675675675675675, "percentage": 94.59, "elapsed_time": "1:55:28", "remaining_time": "0:06:35"}
+{"current_steps": 2315, "total_steps": 2442, "loss": 0.0851, "lr": 3.34077160369497e-07, "epoch": 5.687960687960688, "percentage": 94.8, "elapsed_time": "1:55:40", "remaining_time": "0:06:20"}
+{"current_steps": 2320, "total_steps": 2442, "loss": 0.0877, "lr": 3.08553154910336e-07, "epoch": 5.7002457002457, "percentage": 95.0, "elapsed_time": "1:55:52", "remaining_time": "0:06:05"}
+{"current_steps": 2325, "total_steps": 2442, "loss": 0.0809, "lr": 2.840357459549492e-07, "epoch": 5.712530712530713, "percentage": 95.21, "elapsed_time": "1:56:04", "remaining_time": "0:05:50"}
+{"current_steps": 2330, "total_steps": 2442, "loss": 0.085, "lr": 2.6052618679560884e-07, "epoch": 5.724815724815725, "percentage": 95.41, "elapsed_time": "1:56:16", "remaining_time": "0:05:35"}
+{"current_steps": 2335, "total_steps": 2442, "loss": 0.0789, "lr": 2.380256792048541e-07, "epoch": 5.737100737100737, "percentage": 95.62, "elapsed_time": "1:56:28", "remaining_time": "0:05:20"}
+{"current_steps": 2340, "total_steps": 2442, "loss": 0.0823, "lr": 2.1653537337405383e-07, "epoch": 5.749385749385749, "percentage": 95.82, "elapsed_time": "1:56:40", "remaining_time": "0:05:05"}
+{"current_steps": 2345, "total_steps": 2442, "loss": 0.0795, "lr": 1.9605636785462234e-07, "epoch": 5.761670761670762, "percentage": 96.03, "elapsed_time": "1:56:52", "remaining_time": "0:04:50"}
+{"current_steps": 2350, "total_steps": 2442, "loss": 0.0809, "lr": 1.7658970950185095e-07, "epoch": 5.773955773955774, "percentage": 96.23, "elapsed_time": "1:57:04", "remaining_time": "0:04:35"}
+{"current_steps": 2355, "total_steps": 2442, "loss": 0.0815, "lr": 1.5813639342140197e-07, "epoch": 5.7862407862407865, "percentage": 96.44, "elapsed_time": "1:57:16", "remaining_time": "0:04:19"}
+{"current_steps": 2360, "total_steps": 2442, "loss": 0.0809, "lr": 1.4069736291843605e-07, "epoch": 5.798525798525798, "percentage": 96.64, "elapsed_time": "1:57:28", "remaining_time": "0:04:04"}
+{"current_steps": 2365, "total_steps": 2442, "loss": 0.0839, "lr": 1.242735094493952e-07, "epoch": 5.8108108108108105, "percentage": 96.85, "elapsed_time": "1:57:39", "remaining_time": "0:03:49"}
+{"current_steps": 2370, "total_steps": 2442, "loss": 0.082, "lr": 1.0886567257643033e-07, "epoch": 5.823095823095823, "percentage": 97.05, "elapsed_time": "1:57:52", "remaining_time": "0:03:34"}
+{"current_steps": 2375, "total_steps": 2442, "loss": 0.0847, "lr": 9.447463992448891e-08, "epoch": 5.835380835380835, "percentage": 97.26, "elapsed_time": "1:58:03", "remaining_time": "0:03:19"}
+{"current_steps": 2380, "total_steps": 2442, "loss": 0.0819, "lr": 8.110114714104277e-08, "epoch": 5.847665847665848, "percentage": 97.46, "elapsed_time": "1:58:15", "remaining_time": "0:03:04"}
+{"current_steps": 2385, "total_steps": 2442, "loss": 0.0812, "lr": 6.874587785849152e-08, "epoch": 5.85995085995086, "percentage": 97.67, "elapsed_time": "1:58:26", "remaining_time": "0:02:49"}
+{"current_steps": 2390, "total_steps": 2442, "loss": 0.0845, "lr": 5.7409463659219286e-08, "epoch": 5.872235872235873, "percentage": 97.87, "elapsed_time": "1:58:37", "remaining_time": "0:02:34"}
+{"current_steps": 2395, "total_steps": 2442, "loss": 0.0805, "lr": 4.709248404329625e-08, "epoch": 5.884520884520884, "percentage": 98.08, "elapsed_time": "1:58:50", "remaining_time": "0:02:19"}
+{"current_steps": 2400, "total_steps": 2442, "loss": 0.0807, "lr": 3.7795466398868885e-08, "epoch": 5.896805896805897, "percentage": 98.28, "elapsed_time": "1:59:01", "remaining_time": "0:02:04"}
+{"current_steps": 2405, "total_steps": 2442, "loss": 0.0813, "lr": 2.9518885975192702e-08, "epoch": 5.909090909090909, "percentage": 98.48, "elapsed_time": "2:00:20", "remaining_time": "0:01:51"}
+{"current_steps": 2410, "total_steps": 2442, "loss": 0.088, "lr": 2.226316585833832e-08, "epoch": 5.921375921375922, "percentage": 98.69, "elapsed_time": "2:00:32", "remaining_time": "0:01:36"}
+{"current_steps": 2415, "total_steps": 2442, "loss": 0.0863, "lr": 1.6028676949570997e-08, "epoch": 5.933660933660933, "percentage": 98.89, "elapsed_time": "2:00:44", "remaining_time": "0:01:20"}
+{"current_steps": 2420, "total_steps": 2442, "loss": 0.0797, "lr": 1.0815737946383575e-08, "epoch": 5.945945945945946, "percentage": 99.1, "elapsed_time": "2:00:56", "remaining_time": "0:01:05"}
+{"current_steps": 2425, "total_steps": 2442, "loss": 0.086, "lr": 6.624615326207284e-09, "epoch": 5.958230958230958, "percentage": 99.3, "elapsed_time": "2:01:08", "remaining_time": "0:00:50"}
+{"current_steps": 2430, "total_steps": 2442, "loss": 0.0888, "lr": 3.4555233327893124e-09, "epoch": 5.9705159705159705, "percentage": 99.51, "elapsed_time": "2:01:19", "remaining_time": "0:00:35"}
+{"current_steps": 2435, "total_steps": 2442, "loss": 0.0785, "lr": 1.3086239652415621e-09, "epoch": 5.982800982800983, "percentage": 99.71, "elapsed_time": "2:01:32", "remaining_time": "0:00:20"}
+{"current_steps": 2440, "total_steps": 2442, "loss": 0.0843, "lr": 1.840269697628294e-10, "epoch": 5.995085995085995, "percentage": 99.92, "elapsed_time": "2:01:43", "remaining_time": "0:00:05"}
+{"current_steps": 2442, "total_steps": 2442, "epoch": 6.0, "percentage": 100.0, "elapsed_time": "2:02:26", "remaining_time": "0:00:00"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d7a44a9aa144cd27a7d96652e2397e2d0312f3d4666c4c8b39e0bc249a58902
+size 8657