初始化项目，由ModelHub XC社区提供模型

Model: FlyPig23/Llama3.2-3B_Paper_Impact_SFT
Source: Original Platform

.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 +1,69 @@
+---
+library_name: transformers
+license: other
+base_model: meta-llama/Llama-3.2-3B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: Llama3.2-3B_Paper_Impact_SFT
+  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. -->
+
+# Llama3.2-3B_Paper_Impact_SFT
+
+This model is a fine-tuned version of [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct) on the paper_impact_sft_train dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1446
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 128
+- total_eval_batch_size: 32
+- optimizer: Use adamw_torch 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: 3.0
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.0607        | 0.7228 | 500  | 0.0733          |
+| 0.029         | 1.4452 | 1000 | 0.0819          |
+| 0.0058        | 2.1677 | 1500 | 0.1524          |
+| 0.005         | 2.8905 | 2000 | 0.1443          |
+
+
+### Framework versions
+
+- Transformers 4.57.1
+- Pytorch 2.6.0+cu124
+- Datasets 4.0.0
+- Tokenizers 0.22.1

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.1446007937192917,
+    "eval_runtime": 1173.577,
+    "eval_samples_per_second": 54.71,
+    "eval_steps_per_second": 1.71,
+    "total_flos": 6.274047864041636e+18,
+    "train_loss": 0.03664169063040653,
+    "train_runtime": 42810.6565,
+    "train_samples_per_second": 6.203,
+    "train_steps_per_second": 0.048
+}

chat_template.jinja

@@ -0,0 +1,93 @@
+{{- bos_token }}
+{%- if custom_tools is defined %}
+    {%- set tools = custom_tools %}
+{%- endif %}
+{%- if not tools_in_user_message is defined %}
+    {%- set tools_in_user_message = true %}
+{%- endif %}
+{%- if not date_string is defined %}
+    {%- if strftime_now is defined %}
+        {%- set date_string = strftime_now("%d %b %Y") %}
+    {%- else %}
+        {%- set date_string = "26 Jul 2024" %}
+    {%- endif %}
+{%- endif %}
+{%- if not tools is defined %}
+    {%- set tools = none %}
+{%- endif %}
+
+{#- This block extracts the system message, so we can slot it into the right place. #}
+{%- if messages[0]['role'] == 'system' %}
+    {%- set system_message = messages[0]['content']|trim %}
+    {%- set messages = messages[1:] %}
+{%- else %}
+    {%- set system_message = "" %}
+{%- endif %}
+
+{#- System message #}
+{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
+{%- if tools is not none %}
+    {{- "Environment: ipython\n" }}
+{%- endif %}
+{{- "Cutting Knowledge Date: December 2023\n" }}
+{{- "Today Date: " + date_string + "\n\n" }}
+{%- if tools is not none and not tools_in_user_message %}
+    {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
+    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
+    {{- "Do not use variables.\n\n" }}
+    {%- for t in tools %}
+        {{- t | tojson(indent=4) }}
+        {{- "\n\n" }}
+    {%- endfor %}
+{%- endif %}
+{{- system_message }}
+{{- "<|eot_id|>" }}
+
+{#- Custom tools are passed in a user message with some extra guidance #}
+{%- if tools_in_user_message and not tools is none %}
+    {#- Extract the first user message so we can plug it in here #}
+    {%- if messages | length != 0 %}
+        {%- set first_user_message = messages[0]['content']|trim %}
+        {%- set messages = messages[1:] %}
+    {%- else %}
+        {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
+{%- endif %}
+    {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
+    {{- "Given the following functions, please respond with a JSON for a function call " }}
+    {{- "with its proper arguments that best answers the given prompt.\n\n" }}
+    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
+    {{- "Do not use variables.\n\n" }}
+    {%- for t in tools %}
+        {{- t | tojson(indent=4) }}
+        {{- "\n\n" }}
+    {%- endfor %}
+    {{- first_user_message + "<|eot_id|>"}}
+{%- endif %}
+
+{%- for message in messages %}
+    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
+        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
+    {%- elif 'tool_calls' in message %}
+        {%- if not message.tool_calls|length == 1 %}
+            {{- raise_exception("This model only supports single tool-calls at once!") }}
+        {%- endif %}
+        {%- set tool_call = message.tool_calls[0].function %}
+        {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
+        {{- '{"name": "' + tool_call.name + '", ' }}
+        {{- '"parameters": ' }}
+        {{- tool_call.arguments | tojson }}
+        {{- "}" }}
+        {{- "<|eot_id|>" }}
+    {%- elif message.role == "tool" or message.role == "ipython" %}
+        {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
+        {%- if message.content is mapping or message.content is iterable %}
+            {{- message.content | tojson }}
+        {%- else %}
+            {{- message.content }}
+        {%- endif %}
+        {{- "<|eot_id|>" }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
+{%- endif %}

config.json

@@ -0,0 +1,36 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "dtype": "bfloat16",
+  "eos_token_id": 128009,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pad_token_id": 128009,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.1",
+  "use_cache": false,
+  "vocab_size": 128256
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.1446007937192917,
+    "eval_runtime": 1173.577,
+    "eval_samples_per_second": 54.71,
+    "eval_steps_per_second": 1.71
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128009,
+    128001,
+    128008,
+    128009
+  ],
+  "pad_token_id": 128009,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.57.1"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70b069115627dc3bfced60ba6c35f4554b9217422734022c58e316156a985e6e
+size 4965799096

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:366bdbfd0baceb9b04da2118a8e07f4cddbb04473525ab28725d44070bd67d2c
+size 2247734992

model.safetensors.index.json

@@ -0,0 +1,263 @@
+{
+  "metadata": {
+    "total_parameters": 3212749824,
+    "total_size": 7213504512
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,26 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|eot_id|>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 6.274047864041636e+18,
+    "train_loss": 0.03664169063040653,
+    "train_runtime": 42810.6565,
+    "train_samples_per_second": 6.203,
+    "train_steps_per_second": 0.048
+}

trainer_log.jsonl

@@ -0,0 +1,420 @@
+{"current_steps": 5, "total_steps": 2076, "loss": 0.2014, "lr": 3.846153846153847e-07, "epoch": 0.007228044813877846, "percentage": 0.24, "elapsed_time": "0:01:31", "remaining_time": "10:33:50"}
+{"current_steps": 10, "total_steps": 2076, "loss": 0.1441, "lr": 8.653846153846154e-07, "epoch": 0.014456089627755691, "percentage": 0.48, "elapsed_time": "0:03:05", "remaining_time": "10:38:05"}
+{"current_steps": 15, "total_steps": 2076, "loss": 0.0935, "lr": 1.3461538461538462e-06, "epoch": 0.02168413444163354, "percentage": 0.72, "elapsed_time": "0:04:39", "remaining_time": "10:40:05"}
+{"current_steps": 20, "total_steps": 2076, "loss": 0.0841, "lr": 1.826923076923077e-06, "epoch": 0.028912179255511383, "percentage": 0.96, "elapsed_time": "0:06:11", "remaining_time": "10:35:52"}
+{"current_steps": 25, "total_steps": 2076, "loss": 0.0844, "lr": 2.307692307692308e-06, "epoch": 0.03614022406938923, "percentage": 1.2, "elapsed_time": "0:07:38", "remaining_time": "10:26:48"}
+{"current_steps": 30, "total_steps": 2076, "loss": 0.0809, "lr": 2.7884615384615386e-06, "epoch": 0.04336826888326708, "percentage": 1.45, "elapsed_time": "0:09:09", "remaining_time": "10:24:53"}
+{"current_steps": 35, "total_steps": 2076, "loss": 0.0819, "lr": 3.2692307692307696e-06, "epoch": 0.05059631369714492, "percentage": 1.69, "elapsed_time": "0:10:40", "remaining_time": "10:22:48"}
+{"current_steps": 40, "total_steps": 2076, "loss": 0.0803, "lr": 3.7500000000000005e-06, "epoch": 0.057824358511022765, "percentage": 1.93, "elapsed_time": "0:12:06", "remaining_time": "10:16:27"}
+{"current_steps": 45, "total_steps": 2076, "loss": 0.0813, "lr": 4.230769230769231e-06, "epoch": 0.06505240332490062, "percentage": 2.17, "elapsed_time": "0:13:34", "remaining_time": "10:13:01"}
+{"current_steps": 50, "total_steps": 2076, "loss": 0.0801, "lr": 4.711538461538462e-06, "epoch": 0.07228044813877846, "percentage": 2.41, "elapsed_time": "0:15:00", "remaining_time": "10:08:18"}
+{"current_steps": 55, "total_steps": 2076, "loss": 0.0811, "lr": 5.192307692307693e-06, "epoch": 0.0795084929526563, "percentage": 2.65, "elapsed_time": "0:16:28", "remaining_time": "10:05:10"}
+{"current_steps": 60, "total_steps": 2076, "loss": 0.0806, "lr": 5.6730769230769235e-06, "epoch": 0.08673653776653416, "percentage": 2.89, "elapsed_time": "0:17:56", "remaining_time": "10:02:47"}
+{"current_steps": 65, "total_steps": 2076, "loss": 0.0808, "lr": 6.153846153846155e-06, "epoch": 0.093964582580412, "percentage": 3.13, "elapsed_time": "0:19:24", "remaining_time": "10:00:40"}
+{"current_steps": 70, "total_steps": 2076, "loss": 0.0808, "lr": 6.6346153846153846e-06, "epoch": 0.10119262739428984, "percentage": 3.37, "elapsed_time": "0:20:53", "remaining_time": "9:58:55"}
+{"current_steps": 75, "total_steps": 2076, "loss": 0.0805, "lr": 7.115384615384616e-06, "epoch": 0.10842067220816769, "percentage": 3.61, "elapsed_time": "0:22:16", "remaining_time": "9:54:11"}
+{"current_steps": 80, "total_steps": 2076, "loss": 0.0807, "lr": 7.5961538461538465e-06, "epoch": 0.11564871702204553, "percentage": 3.85, "elapsed_time": "0:23:50", "remaining_time": "9:54:50"}
+{"current_steps": 85, "total_steps": 2076, "loss": 0.0809, "lr": 8.076923076923077e-06, "epoch": 0.12287676183592339, "percentage": 4.09, "elapsed_time": "0:25:24", "remaining_time": "9:55:14"}
+{"current_steps": 90, "total_steps": 2076, "loss": 0.0812, "lr": 8.557692307692308e-06, "epoch": 0.13010480664980123, "percentage": 4.34, "elapsed_time": "0:26:53", "remaining_time": "9:53:18"}
+{"current_steps": 95, "total_steps": 2076, "loss": 0.08, "lr": 9.03846153846154e-06, "epoch": 0.13733285146367907, "percentage": 4.58, "elapsed_time": "0:28:25", "remaining_time": "9:52:37"}
+{"current_steps": 100, "total_steps": 2076, "loss": 0.08, "lr": 9.51923076923077e-06, "epoch": 0.14456089627755692, "percentage": 4.82, "elapsed_time": "0:29:55", "remaining_time": "9:51:18"}
+{"current_steps": 105, "total_steps": 2076, "loss": 0.0817, "lr": 1e-05, "epoch": 0.15178894109143476, "percentage": 5.06, "elapsed_time": "0:31:25", "remaining_time": "9:49:50"}
+{"current_steps": 110, "total_steps": 2076, "loss": 0.0805, "lr": 1.0480769230769232e-05, "epoch": 0.1590169859053126, "percentage": 5.3, "elapsed_time": "0:32:57", "remaining_time": "9:49:00"}
+{"current_steps": 115, "total_steps": 2076, "loss": 0.0797, "lr": 1.0961538461538464e-05, "epoch": 0.16624503071919045, "percentage": 5.54, "elapsed_time": "0:34:31", "remaining_time": "9:48:37"}
+{"current_steps": 120, "total_steps": 2076, "loss": 0.0808, "lr": 1.1442307692307693e-05, "epoch": 0.17347307553306832, "percentage": 5.78, "elapsed_time": "0:36:03", "remaining_time": "9:47:51"}
+{"current_steps": 125, "total_steps": 2076, "loss": 0.0805, "lr": 1.1923076923076925e-05, "epoch": 0.18070112034694616, "percentage": 6.02, "elapsed_time": "0:37:34", "remaining_time": "9:46:22"}
+{"current_steps": 130, "total_steps": 2076, "loss": 0.0836, "lr": 1.2403846153846156e-05, "epoch": 0.187929165160824, "percentage": 6.26, "elapsed_time": "0:39:07", "remaining_time": "9:45:33"}
+{"current_steps": 135, "total_steps": 2076, "loss": 0.0802, "lr": 1.2884615384615386e-05, "epoch": 0.19515720997470185, "percentage": 6.5, "elapsed_time": "0:40:41", "remaining_time": "9:45:06"}
+{"current_steps": 140, "total_steps": 2076, "loss": 0.0811, "lr": 1.3365384615384615e-05, "epoch": 0.2023852547885797, "percentage": 6.74, "elapsed_time": "0:42:08", "remaining_time": "9:42:50"}
+{"current_steps": 145, "total_steps": 2076, "loss": 0.0829, "lr": 1.3846153846153847e-05, "epoch": 0.20961329960245753, "percentage": 6.98, "elapsed_time": "0:43:42", "remaining_time": "9:41:59"}
+{"current_steps": 150, "total_steps": 2076, "loss": 0.0816, "lr": 1.4326923076923078e-05, "epoch": 0.21684134441633537, "percentage": 7.23, "elapsed_time": "0:45:12", "remaining_time": "9:40:31"}
+{"current_steps": 155, "total_steps": 2076, "loss": 0.0801, "lr": 1.480769230769231e-05, "epoch": 0.22406938923021322, "percentage": 7.47, "elapsed_time": "0:46:45", "remaining_time": "9:39:28"}
+{"current_steps": 160, "total_steps": 2076, "loss": 0.0813, "lr": 1.528846153846154e-05, "epoch": 0.23129743404409106, "percentage": 7.71, "elapsed_time": "0:48:16", "remaining_time": "9:38:00"}
+{"current_steps": 165, "total_steps": 2076, "loss": 0.0811, "lr": 1.576923076923077e-05, "epoch": 0.23852547885796893, "percentage": 7.95, "elapsed_time": "0:49:46", "remaining_time": "9:36:28"}
+{"current_steps": 170, "total_steps": 2076, "loss": 0.081, "lr": 1.6250000000000002e-05, "epoch": 0.24575352367184677, "percentage": 8.19, "elapsed_time": "0:51:12", "remaining_time": "9:34:04"}
+{"current_steps": 175, "total_steps": 2076, "loss": 0.0793, "lr": 1.673076923076923e-05, "epoch": 0.2529815684857246, "percentage": 8.43, "elapsed_time": "0:52:47", "remaining_time": "9:33:28"}
+{"current_steps": 180, "total_steps": 2076, "loss": 0.0811, "lr": 1.7211538461538465e-05, "epoch": 0.26020961329960246, "percentage": 8.67, "elapsed_time": "0:54:21", "remaining_time": "9:32:37"}
+{"current_steps": 185, "total_steps": 2076, "loss": 0.0819, "lr": 1.7692307692307694e-05, "epoch": 0.2674376581134803, "percentage": 8.91, "elapsed_time": "0:55:56", "remaining_time": "9:31:47"}
+{"current_steps": 190, "total_steps": 2076, "loss": 0.0797, "lr": 1.8173076923076924e-05, "epoch": 0.27466570292735815, "percentage": 9.15, "elapsed_time": "0:57:35", "remaining_time": "9:31:40"}
+{"current_steps": 195, "total_steps": 2076, "loss": 0.0792, "lr": 1.8653846153846157e-05, "epoch": 0.281893747741236, "percentage": 9.39, "elapsed_time": "0:59:00", "remaining_time": "9:29:16"}
+{"current_steps": 200, "total_steps": 2076, "loss": 0.0948, "lr": 1.9134615384615387e-05, "epoch": 0.28912179255511383, "percentage": 9.63, "elapsed_time": "1:00:32", "remaining_time": "9:27:57"}
+{"current_steps": 205, "total_steps": 2076, "loss": 0.0895, "lr": 1.9615384615384617e-05, "epoch": 0.2963498373689917, "percentage": 9.87, "elapsed_time": "1:02:06", "remaining_time": "9:26:54"}
+{"current_steps": 210, "total_steps": 2076, "loss": 0.0818, "lr": 1.999998585783488e-05, "epoch": 0.3035778821828695, "percentage": 10.12, "elapsed_time": "1:03:39", "remaining_time": "9:25:37"}
+{"current_steps": 215, "total_steps": 2076, "loss": 0.0812, "lr": 1.9999490886255767e-05, "epoch": 0.31080592699674736, "percentage": 10.36, "elapsed_time": "1:05:05", "remaining_time": "9:23:25"}
+{"current_steps": 220, "total_steps": 2076, "loss": 0.0814, "lr": 1.999828884642042e-05, "epoch": 0.3180339718106252, "percentage": 10.6, "elapsed_time": "1:06:41", "remaining_time": "9:22:40"}
+{"current_steps": 225, "total_steps": 2076, "loss": 0.0806, "lr": 1.9996379823325586e-05, "epoch": 0.32526201662450305, "percentage": 10.84, "elapsed_time": "1:08:10", "remaining_time": "9:20:53"}
+{"current_steps": 230, "total_steps": 2076, "loss": 0.0815, "lr": 1.9993763951959107e-05, "epoch": 0.3324900614383809, "percentage": 11.08, "elapsed_time": "1:09:39", "remaining_time": "9:19:03"}
+{"current_steps": 235, "total_steps": 2076, "loss": 0.0846, "lr": 1.9990441417290358e-05, "epoch": 0.3397181062522588, "percentage": 11.32, "elapsed_time": "1:11:13", "remaining_time": "9:18:01"}
+{"current_steps": 240, "total_steps": 2076, "loss": 0.0849, "lr": 1.9986412454257178e-05, "epoch": 0.34694615106613663, "percentage": 11.56, "elapsed_time": "1:12:41", "remaining_time": "9:16:03"}
+{"current_steps": 245, "total_steps": 2076, "loss": 0.0821, "lr": 1.998167734774926e-05, "epoch": 0.3541741958800145, "percentage": 11.8, "elapsed_time": "1:14:13", "remaining_time": "9:14:44"}
+{"current_steps": 250, "total_steps": 2076, "loss": 0.0808, "lr": 1.9976236432588002e-05, "epoch": 0.3614022406938923, "percentage": 12.04, "elapsed_time": "1:15:43", "remaining_time": "9:13:02"}
+{"current_steps": 255, "total_steps": 2076, "loss": 0.0805, "lr": 1.997009009350283e-05, "epoch": 0.36863028550777016, "percentage": 12.28, "elapsed_time": "1:17:16", "remaining_time": "9:11:51"}
+{"current_steps": 260, "total_steps": 2076, "loss": 0.081, "lr": 1.996323876510399e-05, "epoch": 0.375858330321648, "percentage": 12.52, "elapsed_time": "1:18:47", "remaining_time": "9:10:21"}
+{"current_steps": 265, "total_steps": 2076, "loss": 0.083, "lr": 1.9955682931851835e-05, "epoch": 0.38308637513552585, "percentage": 12.76, "elapsed_time": "1:20:17", "remaining_time": "9:08:41"}
+{"current_steps": 270, "total_steps": 2076, "loss": 0.0815, "lr": 1.994742312802255e-05, "epoch": 0.3903144199494037, "percentage": 13.01, "elapsed_time": "1:21:46", "remaining_time": "9:06:57"}
+{"current_steps": 275, "total_steps": 2076, "loss": 0.0801, "lr": 1.993845993767038e-05, "epoch": 0.39754246476328153, "percentage": 13.25, "elapsed_time": "1:23:16", "remaining_time": "9:05:23"}
+{"current_steps": 280, "total_steps": 2076, "loss": 0.0857, "lr": 1.9928793994586323e-05, "epoch": 0.4047705095771594, "percentage": 13.49, "elapsed_time": "1:24:47", "remaining_time": "9:03:53"}
+{"current_steps": 285, "total_steps": 2076, "loss": 0.0822, "lr": 1.9918425982253335e-05, "epoch": 0.4119985543910372, "percentage": 13.73, "elapsed_time": "1:26:20", "remaining_time": "9:02:32"}
+{"current_steps": 290, "total_steps": 2076, "loss": 0.0813, "lr": 1.9907356633797978e-05, "epoch": 0.41922659920491506, "percentage": 13.97, "elapsed_time": "1:27:52", "remaining_time": "9:01:14"}
+{"current_steps": 295, "total_steps": 2076, "loss": 0.0812, "lr": 1.9895586731938593e-05, "epoch": 0.4264546440187929, "percentage": 14.21, "elapsed_time": "1:29:22", "remaining_time": "8:59:37"}
+{"current_steps": 300, "total_steps": 2076, "loss": 0.0825, "lr": 1.9883117108929947e-05, "epoch": 0.43368268883267075, "percentage": 14.45, "elapsed_time": "1:30:56", "remaining_time": "8:58:23"}
+{"current_steps": 305, "total_steps": 2076, "loss": 0.0821, "lr": 1.986994864650439e-05, "epoch": 0.4409107336465486, "percentage": 14.69, "elapsed_time": "1:32:31", "remaining_time": "8:57:16"}
+{"current_steps": 310, "total_steps": 2076, "loss": 0.0817, "lr": 1.9856082275809508e-05, "epoch": 0.44813877846042643, "percentage": 14.93, "elapsed_time": "1:34:05", "remaining_time": "8:56:01"}
+{"current_steps": 315, "total_steps": 2076, "loss": 0.081, "lr": 1.9841518977342274e-05, "epoch": 0.4553668232743043, "percentage": 15.17, "elapsed_time": "1:35:33", "remaining_time": "8:54:14"}
+{"current_steps": 320, "total_steps": 2076, "loss": 0.081, "lr": 1.9826259780879716e-05, "epoch": 0.4625948680881821, "percentage": 15.41, "elapsed_time": "1:37:04", "remaining_time": "8:52:39"}
+{"current_steps": 325, "total_steps": 2076, "loss": 0.0806, "lr": 1.981030576540612e-05, "epoch": 0.46982291290206, "percentage": 15.66, "elapsed_time": "1:38:38", "remaining_time": "8:51:28"}
+{"current_steps": 330, "total_steps": 2076, "loss": 0.0799, "lr": 1.9793658059036697e-05, "epoch": 0.47705095771593786, "percentage": 15.9, "elapsed_time": "1:40:06", "remaining_time": "8:49:41"}
+{"current_steps": 335, "total_steps": 2076, "loss": 0.0813, "lr": 1.977631783893786e-05, "epoch": 0.4842790025298157, "percentage": 16.14, "elapsed_time": "1:41:35", "remaining_time": "8:48:00"}
+{"current_steps": 340, "total_steps": 2076, "loss": 0.0805, "lr": 1.975828633124394e-05, "epoch": 0.49150704734369355, "percentage": 16.38, "elapsed_time": "1:42:56", "remaining_time": "8:45:38"}
+{"current_steps": 345, "total_steps": 2076, "loss": 0.0804, "lr": 1.9739564810970534e-05, "epoch": 0.4987350921575714, "percentage": 16.62, "elapsed_time": "1:44:24", "remaining_time": "8:43:50"}
+{"current_steps": 350, "total_steps": 2076, "loss": 0.0802, "lr": 1.9720154601924295e-05, "epoch": 0.5059631369714492, "percentage": 16.86, "elapsed_time": "1:45:56", "remaining_time": "8:42:25"}
+{"current_steps": 355, "total_steps": 2076, "loss": 0.08, "lr": 1.9700057076609377e-05, "epoch": 0.5131911817853271, "percentage": 17.1, "elapsed_time": "1:47:24", "remaining_time": "8:40:43"}
+{"current_steps": 360, "total_steps": 2076, "loss": 0.0802, "lr": 1.967927365613034e-05, "epoch": 0.5204192265992049, "percentage": 17.34, "elapsed_time": "1:48:59", "remaining_time": "8:39:31"}
+{"current_steps": 365, "total_steps": 2076, "loss": 0.0799, "lr": 1.96578058100917e-05, "epoch": 0.5276472714130828, "percentage": 17.58, "elapsed_time": "1:50:30", "remaining_time": "8:38:00"}
+{"current_steps": 370, "total_steps": 2076, "loss": 0.081, "lr": 1.963565505649398e-05, "epoch": 0.5348753162269606, "percentage": 17.82, "elapsed_time": "1:52:01", "remaining_time": "8:36:31"}
+{"current_steps": 375, "total_steps": 2076, "loss": 0.0799, "lr": 1.961282296162639e-05, "epoch": 0.5421033610408384, "percentage": 18.06, "elapsed_time": "1:53:34", "remaining_time": "8:35:12"}
+{"current_steps": 380, "total_steps": 2076, "loss": 0.0855, "lr": 1.9589311139956086e-05, "epoch": 0.5493314058547163, "percentage": 18.3, "elapsed_time": "1:55:08", "remaining_time": "8:33:53"}
+{"current_steps": 385, "total_steps": 2076, "loss": 0.0809, "lr": 1.956512125401398e-05, "epoch": 0.5565594506685941, "percentage": 18.55, "elapsed_time": "1:56:44", "remaining_time": "8:32:46"}
+{"current_steps": 390, "total_steps": 2076, "loss": 0.0796, "lr": 1.9540255014277198e-05, "epoch": 0.563787495482472, "percentage": 18.79, "elapsed_time": "1:58:11", "remaining_time": "8:30:56"}
+{"current_steps": 395, "total_steps": 2076, "loss": 0.0792, "lr": 1.9514714179048138e-05, "epoch": 0.5710155402963498, "percentage": 19.03, "elapsed_time": "1:59:46", "remaining_time": "8:29:45"}
+{"current_steps": 400, "total_steps": 2076, "loss": 0.0791, "lr": 1.9488500554330126e-05, "epoch": 0.5782435851102277, "percentage": 19.27, "elapsed_time": "2:01:23", "remaining_time": "8:28:39"}
+{"current_steps": 405, "total_steps": 2076, "loss": 0.0794, "lr": 1.946161599369973e-05, "epoch": 0.5854716299241055, "percentage": 19.51, "elapsed_time": "2:03:00", "remaining_time": "8:27:31"}
+{"current_steps": 410, "total_steps": 2076, "loss": 0.0776, "lr": 1.9434062398175667e-05, "epoch": 0.5926996747379834, "percentage": 19.75, "elapsed_time": "2:04:26", "remaining_time": "8:25:38"}
+{"current_steps": 415, "total_steps": 2076, "loss": 0.0772, "lr": 1.9405841716084403e-05, "epoch": 0.5999277195518612, "percentage": 19.99, "elapsed_time": "2:06:01", "remaining_time": "8:24:25"}
+{"current_steps": 420, "total_steps": 2076, "loss": 0.0765, "lr": 1.937695594292238e-05, "epoch": 0.607155764365739, "percentage": 20.23, "elapsed_time": "2:07:36", "remaining_time": "8:23:10"}
+{"current_steps": 425, "total_steps": 2076, "loss": 0.075, "lr": 1.9347407121214917e-05, "epoch": 0.6143838091796169, "percentage": 20.47, "elapsed_time": "2:09:02", "remaining_time": "8:21:18"}
+{"current_steps": 430, "total_steps": 2076, "loss": 0.0706, "lr": 1.9317197340371764e-05, "epoch": 0.6216118539934947, "percentage": 20.71, "elapsed_time": "2:10:28", "remaining_time": "8:19:25"}
+{"current_steps": 435, "total_steps": 2076, "loss": 0.0827, "lr": 1.9286328736539385e-05, "epoch": 0.6288398988073726, "percentage": 20.95, "elapsed_time": "2:12:01", "remaining_time": "8:18:04"}
+{"current_steps": 440, "total_steps": 2076, "loss": 0.0815, "lr": 1.9254803492449894e-05, "epoch": 0.6360679436212504, "percentage": 21.19, "elapsed_time": "2:13:31", "remaining_time": "8:16:27"}
+{"current_steps": 445, "total_steps": 2076, "loss": 0.0816, "lr": 1.922262383726672e-05, "epoch": 0.6432959884351283, "percentage": 21.44, "elapsed_time": "2:15:02", "remaining_time": "8:14:56"}
+{"current_steps": 450, "total_steps": 2076, "loss": 0.0795, "lr": 1.9189792046426972e-05, "epoch": 0.6505240332490061, "percentage": 21.68, "elapsed_time": "2:16:34", "remaining_time": "8:13:29"}
+{"current_steps": 455, "total_steps": 2076, "loss": 0.0795, "lr": 1.9156310441480557e-05, "epoch": 0.6577520780628839, "percentage": 21.92, "elapsed_time": "2:18:06", "remaining_time": "8:12:01"}
+{"current_steps": 460, "total_steps": 2076, "loss": 0.0772, "lr": 1.912218138992601e-05, "epoch": 0.6649801228767618, "percentage": 22.16, "elapsed_time": "2:19:34", "remaining_time": "8:10:19"}
+{"current_steps": 465, "total_steps": 2076, "loss": 0.0732, "lr": 1.9087407305043085e-05, "epoch": 0.6722081676906397, "percentage": 22.4, "elapsed_time": "2:21:12", "remaining_time": "8:09:12"}
+{"current_steps": 470, "total_steps": 2076, "loss": 0.0694, "lr": 1.9051990645722133e-05, "epoch": 0.6794362125045176, "percentage": 22.64, "elapsed_time": "2:22:43", "remaining_time": "8:07:42"}
+{"current_steps": 475, "total_steps": 2076, "loss": 0.0676, "lr": 1.9015933916290202e-05, "epoch": 0.6866642573183954, "percentage": 22.88, "elapsed_time": "2:24:18", "remaining_time": "8:06:23"}
+{"current_steps": 480, "total_steps": 2076, "loss": 0.0635, "lr": 1.8979239666333975e-05, "epoch": 0.6938923021322733, "percentage": 23.12, "elapsed_time": "2:25:43", "remaining_time": "8:04:33"}
+{"current_steps": 485, "total_steps": 2076, "loss": 0.0636, "lr": 1.8941910490519483e-05, "epoch": 0.7011203469461511, "percentage": 23.36, "elapsed_time": "2:27:07", "remaining_time": "8:02:38"}
+{"current_steps": 490, "total_steps": 2076, "loss": 0.0648, "lr": 1.8903949028408636e-05, "epoch": 0.708348391760029, "percentage": 23.6, "elapsed_time": "2:28:38", "remaining_time": "8:01:06"}
+{"current_steps": 495, "total_steps": 2076, "loss": 0.062, "lr": 1.8865357964272576e-05, "epoch": 0.7155764365739068, "percentage": 23.84, "elapsed_time": "2:30:09", "remaining_time": "7:59:35"}
+{"current_steps": 500, "total_steps": 2076, "loss": 0.0607, "lr": 1.8826140026901873e-05, "epoch": 0.7228044813877846, "percentage": 24.08, "elapsed_time": "2:31:46", "remaining_time": "7:58:24"}
+{"current_steps": 500, "total_steps": 2076, "eval_loss": 0.07328393310308456, "epoch": 0.7228044813877846, "percentage": 24.08, "elapsed_time": "2:50:50", "remaining_time": "8:58:30"}
+{"current_steps": 505, "total_steps": 2076, "loss": 0.0631, "lr": 1.878629798941357e-05, "epoch": 0.7300325262016625, "percentage": 24.33, "elapsed_time": "2:52:52", "remaining_time": "8:57:47"}
+{"current_steps": 510, "total_steps": 2076, "loss": 0.064, "lr": 1.8745834669055085e-05, "epoch": 0.7372605710155403, "percentage": 24.57, "elapsed_time": "2:54:24", "remaining_time": "8:55:32"}
+{"current_steps": 515, "total_steps": 2076, "loss": 0.0618, "lr": 1.8704752927005034e-05, "epoch": 0.7444886158294182, "percentage": 24.81, "elapsed_time": "2:55:51", "remaining_time": "8:53:02"}
+{"current_steps": 520, "total_steps": 2076, "loss": 0.0613, "lr": 1.8663055668170873e-05, "epoch": 0.751716660643296, "percentage": 25.05, "elapsed_time": "2:57:27", "remaining_time": "8:50:59"}
+{"current_steps": 525, "total_steps": 2076, "loss": 0.0589, "lr": 1.8620745840983522e-05, "epoch": 0.7589447054571739, "percentage": 25.29, "elapsed_time": "2:58:59", "remaining_time": "8:48:48"}
+{"current_steps": 530, "total_steps": 2076, "loss": 0.0578, "lr": 1.857782643718887e-05, "epoch": 0.7661727502710517, "percentage": 25.53, "elapsed_time": "3:00:30", "remaining_time": "8:46:31"}
+{"current_steps": 535, "total_steps": 2076, "loss": 0.0561, "lr": 1.8534300491636225e-05, "epoch": 0.7734007950849295, "percentage": 25.77, "elapsed_time": "3:01:58", "remaining_time": "8:44:10"}
+{"current_steps": 540, "total_steps": 2076, "loss": 0.0615, "lr": 1.849017108206372e-05, "epoch": 0.7806288398988074, "percentage": 26.01, "elapsed_time": "3:03:30", "remaining_time": "8:41:57"}
+{"current_steps": 545, "total_steps": 2076, "loss": 0.0613, "lr": 1.844544132888068e-05, "epoch": 0.7878568847126852, "percentage": 26.25, "elapsed_time": "3:05:08", "remaining_time": "8:40:05"}
+{"current_steps": 550, "total_steps": 2076, "loss": 0.0546, "lr": 1.8400114394947003e-05, "epoch": 0.7950849295265631, "percentage": 26.49, "elapsed_time": "3:06:38", "remaining_time": "8:37:49"}
+{"current_steps": 555, "total_steps": 2076, "loss": 0.0521, "lr": 1.8354193485349468e-05, "epoch": 0.8023129743404409, "percentage": 26.73, "elapsed_time": "3:08:10", "remaining_time": "8:35:40"}
+{"current_steps": 560, "total_steps": 2076, "loss": 0.0581, "lr": 1.830768184717514e-05, "epoch": 0.8095410191543188, "percentage": 26.97, "elapsed_time": "3:09:34", "remaining_time": "8:33:13"}
+{"current_steps": 565, "total_steps": 2076, "loss": 0.0596, "lr": 1.8260582769281747e-05, "epoch": 0.8167690639681966, "percentage": 27.22, "elapsed_time": "3:11:03", "remaining_time": "8:30:58"}
+{"current_steps": 570, "total_steps": 2076, "loss": 0.0588, "lr": 1.821289958206513e-05, "epoch": 0.8239971087820744, "percentage": 27.46, "elapsed_time": "3:12:30", "remaining_time": "8:28:38"}
+{"current_steps": 575, "total_steps": 2076, "loss": 0.0584, "lr": 1.8164635657223755e-05, "epoch": 0.8312251535959523, "percentage": 27.7, "elapsed_time": "3:13:57", "remaining_time": "8:26:20"}
+{"current_steps": 580, "total_steps": 2076, "loss": 0.0558, "lr": 1.8115794407520287e-05, "epoch": 0.8384531984098301, "percentage": 27.94, "elapsed_time": "3:15:29", "remaining_time": "8:24:13"}
+{"current_steps": 585, "total_steps": 2076, "loss": 0.0524, "lr": 1.8066379286540278e-05, "epoch": 0.845681243223708, "percentage": 28.18, "elapsed_time": "3:16:53", "remaining_time": "8:21:50"}
+{"current_steps": 590, "total_steps": 2076, "loss": 0.0549, "lr": 1.8016393788447964e-05, "epoch": 0.8529092880375858, "percentage": 28.42, "elapsed_time": "3:18:36", "remaining_time": "8:20:12"}
+{"current_steps": 595, "total_steps": 2076, "loss": 0.0491, "lr": 1.7965841447739185e-05, "epoch": 0.8601373328514637, "percentage": 28.66, "elapsed_time": "3:20:14", "remaining_time": "8:18:23"}
+{"current_steps": 600, "total_steps": 2076, "loss": 0.0543, "lr": 1.7914725838991472e-05, "epoch": 0.8673653776653415, "percentage": 28.9, "elapsed_time": "3:21:43", "remaining_time": "8:16:14"}
+{"current_steps": 605, "total_steps": 2076, "loss": 0.051, "lr": 1.7863050576611267e-05, "epoch": 0.8745934224792193, "percentage": 29.14, "elapsed_time": "3:23:10", "remaining_time": "8:14:01"}
+{"current_steps": 610, "total_steps": 2076, "loss": 0.0553, "lr": 1.781081931457837e-05, "epoch": 0.8818214672930972, "percentage": 29.38, "elapsed_time": "3:24:49", "remaining_time": "8:12:14"}
+{"current_steps": 615, "total_steps": 2076, "loss": 0.0517, "lr": 1.7758035746187553e-05, "epoch": 0.889049512106975, "percentage": 29.62, "elapsed_time": "3:26:20", "remaining_time": "8:10:11"}
+{"current_steps": 620, "total_steps": 2076, "loss": 0.0545, "lr": 1.770470360378739e-05, "epoch": 0.8962775569208529, "percentage": 29.87, "elapsed_time": "3:27:53", "remaining_time": "8:08:12"}
+{"current_steps": 625, "total_steps": 2076, "loss": 0.0548, "lr": 1.7650826658516375e-05, "epoch": 0.9035056017347307, "percentage": 30.11, "elapsed_time": "3:29:22", "remaining_time": "8:06:05"}
+{"current_steps": 630, "total_steps": 2076, "loss": 0.0551, "lr": 1.7596408720036232e-05, "epoch": 0.9107336465486086, "percentage": 30.35, "elapsed_time": "3:30:51", "remaining_time": "8:03:57"}
+{"current_steps": 635, "total_steps": 2076, "loss": 0.05, "lr": 1.754145363626256e-05, "epoch": 0.9179616913624864, "percentage": 30.59, "elapsed_time": "3:32:14", "remaining_time": "8:01:37"}
+{"current_steps": 640, "total_steps": 2076, "loss": 0.0503, "lr": 1.748596529309271e-05, "epoch": 0.9251897361763642, "percentage": 30.83, "elapsed_time": "3:33:33", "remaining_time": "7:59:11"}
+{"current_steps": 645, "total_steps": 2076, "loss": 0.0488, "lr": 1.742994761413105e-05, "epoch": 0.9324177809902421, "percentage": 31.07, "elapsed_time": "3:35:00", "remaining_time": "7:57:00"}
+{"current_steps": 650, "total_steps": 2076, "loss": 0.0553, "lr": 1.73734045604115e-05, "epoch": 0.93964582580412, "percentage": 31.31, "elapsed_time": "3:36:36", "remaining_time": "7:55:12"}
+{"current_steps": 655, "total_steps": 2076, "loss": 0.0499, "lr": 1.731634013011745e-05, "epoch": 0.9468738706179979, "percentage": 31.55, "elapsed_time": "3:38:10", "remaining_time": "7:53:18"}
+{"current_steps": 660, "total_steps": 2076, "loss": 0.0521, "lr": 1.7258758358299053e-05, "epoch": 0.9541019154318757, "percentage": 31.79, "elapsed_time": "3:39:45", "remaining_time": "7:51:28"}
+{"current_steps": 665, "total_steps": 2076, "loss": 0.0505, "lr": 1.7200663316587897e-05, "epoch": 0.9613299602457536, "percentage": 32.03, "elapsed_time": "3:41:21", "remaining_time": "7:49:40"}
+{"current_steps": 670, "total_steps": 2076, "loss": 0.0537, "lr": 1.7142059112909107e-05, "epoch": 0.9685580050596314, "percentage": 32.27, "elapsed_time": "3:42:55", "remaining_time": "7:47:49"}
+{"current_steps": 675, "total_steps": 2076, "loss": 0.0466, "lr": 1.708294989119087e-05, "epoch": 0.9757860498735093, "percentage": 32.51, "elapsed_time": "3:44:29", "remaining_time": "7:45:57"}
+{"current_steps": 680, "total_steps": 2076, "loss": 0.0527, "lr": 1.7023339831071408e-05, "epoch": 0.9830140946873871, "percentage": 32.76, "elapsed_time": "3:46:00", "remaining_time": "7:43:59"}
+{"current_steps": 685, "total_steps": 2076, "loss": 0.0483, "lr": 1.696323314760344e-05, "epoch": 0.9902421395012649, "percentage": 33.0, "elapsed_time": "3:47:26", "remaining_time": "7:41:50"}
+{"current_steps": 690, "total_steps": 2076, "loss": 0.0483, "lr": 1.690263409095614e-05, "epoch": 0.9974701843151428, "percentage": 33.24, "elapsed_time": "3:48:59", "remaining_time": "7:39:59"}
+{"current_steps": 695, "total_steps": 2076, "loss": 0.0417, "lr": 1.6841546946114586e-05, "epoch": 1.0043368268883268, "percentage": 33.48, "elapsed_time": "3:50:31", "remaining_time": "7:38:04"}
+{"current_steps": 700, "total_steps": 2076, "loss": 0.0336, "lr": 1.6779976032576792e-05, "epoch": 1.0115648717022045, "percentage": 33.72, "elapsed_time": "3:52:06", "remaining_time": "7:36:15"}
+{"current_steps": 705, "total_steps": 2076, "loss": 0.0416, "lr": 1.6717925704048256e-05, "epoch": 1.0187929165160825, "percentage": 33.96, "elapsed_time": "3:53:36", "remaining_time": "7:34:16"}
+{"current_steps": 710, "total_steps": 2076, "loss": 0.0404, "lr": 1.6655400348134122e-05, "epoch": 1.0260209613299602, "percentage": 34.2, "elapsed_time": "3:55:12", "remaining_time": "7:32:32"}
+{"current_steps": 715, "total_steps": 2076, "loss": 0.0431, "lr": 1.659240438602891e-05, "epoch": 1.0332490061438382, "percentage": 34.44, "elapsed_time": "3:56:56", "remaining_time": "7:31:01"}
+{"current_steps": 720, "total_steps": 2076, "loss": 0.0419, "lr": 1.6528942272203912e-05, "epoch": 1.040477050957716, "percentage": 34.68, "elapsed_time": "3:58:29", "remaining_time": "7:29:09"}
+{"current_steps": 725, "total_steps": 2076, "loss": 0.0401, "lr": 1.6465018494092213e-05, "epoch": 1.0477050957715939, "percentage": 34.92, "elapsed_time": "3:59:58", "remaining_time": "7:27:11"}
+{"current_steps": 730, "total_steps": 2076, "loss": 0.0383, "lr": 1.6400637571771354e-05, "epoch": 1.0549331405854716, "percentage": 35.16, "elapsed_time": "4:01:35", "remaining_time": "7:25:27"}
+{"current_steps": 735, "total_steps": 2076, "loss": 0.0355, "lr": 1.633580405764376e-05, "epoch": 1.0621611853993496, "percentage": 35.4, "elapsed_time": "4:03:10", "remaining_time": "7:23:40"}
+{"current_steps": 740, "total_steps": 2076, "loss": 0.0393, "lr": 1.6270522536114813e-05, "epoch": 1.0693892302132273, "percentage": 35.65, "elapsed_time": "4:04:42", "remaining_time": "7:21:48"}
+{"current_steps": 745, "total_steps": 2076, "loss": 0.0353, "lr": 1.6204797623268675e-05, "epoch": 1.0766172750271052, "percentage": 35.89, "elapsed_time": "4:06:10", "remaining_time": "7:19:47"}
+{"current_steps": 750, "total_steps": 2076, "loss": 0.0395, "lr": 1.6138633966541905e-05, "epoch": 1.083845319840983, "percentage": 36.13, "elapsed_time": "4:07:44", "remaining_time": "7:17:59"}
+{"current_steps": 755, "total_steps": 2076, "loss": 0.0409, "lr": 1.6072036244394836e-05, "epoch": 1.091073364654861, "percentage": 36.37, "elapsed_time": "4:09:15", "remaining_time": "7:16:07"}
+{"current_steps": 760, "total_steps": 2076, "loss": 0.0382, "lr": 1.600500916598074e-05, "epoch": 1.0983014094687387, "percentage": 36.61, "elapsed_time": "4:10:47", "remaining_time": "7:14:16"}
+{"current_steps": 765, "total_steps": 2076, "loss": 0.0369, "lr": 1.5937557470812852e-05, "epoch": 1.1055294542826166, "percentage": 36.85, "elapsed_time": "4:12:18", "remaining_time": "7:12:23"}
+{"current_steps": 770, "total_steps": 2076, "loss": 0.0393, "lr": 1.5869685928429253e-05, "epoch": 1.1127574990964944, "percentage": 37.09, "elapsed_time": "4:13:50", "remaining_time": "7:10:32"}
+{"current_steps": 775, "total_steps": 2076, "loss": 0.0352, "lr": 1.5801399338055584e-05, "epoch": 1.1199855439103723, "percentage": 37.33, "elapsed_time": "4:15:25", "remaining_time": "7:08:46"}
+{"current_steps": 780, "total_steps": 2076, "loss": 0.0381, "lr": 1.5732702528265716e-05, "epoch": 1.12721358872425, "percentage": 37.57, "elapsed_time": "4:16:53", "remaining_time": "7:06:49"}
+{"current_steps": 785, "total_steps": 2076, "loss": 0.0367, "lr": 1.5663600356640306e-05, "epoch": 1.134441633538128, "percentage": 37.81, "elapsed_time": "4:18:27", "remaining_time": "7:05:04"}
+{"current_steps": 790, "total_steps": 2076, "loss": 0.0389, "lr": 1.5594097709423316e-05, "epoch": 1.1416696783520057, "percentage": 38.05, "elapsed_time": "4:20:01", "remaining_time": "7:03:17"}
+{"current_steps": 795, "total_steps": 2076, "loss": 0.0381, "lr": 1.552419950117651e-05, "epoch": 1.1488977231658837, "percentage": 38.29, "elapsed_time": "4:21:33", "remaining_time": "7:01:26"}
+{"current_steps": 800, "total_steps": 2076, "loss": 0.0343, "lr": 1.545391067443194e-05, "epoch": 1.1561257679797614, "percentage": 38.54, "elapsed_time": "4:22:58", "remaining_time": "6:59:27"}
+{"current_steps": 805, "total_steps": 2076, "loss": 0.0389, "lr": 1.538323619934247e-05, "epoch": 1.1633538127936394, "percentage": 38.78, "elapsed_time": "4:24:26", "remaining_time": "6:57:30"}
+{"current_steps": 810, "total_steps": 2076, "loss": 0.0366, "lr": 1.5312181073330295e-05, "epoch": 1.170581857607517, "percentage": 39.02, "elapsed_time": "4:26:03", "remaining_time": "6:55:50"}
+{"current_steps": 815, "total_steps": 2076, "loss": 0.0373, "lr": 1.524075032073363e-05, "epoch": 1.177809902421395, "percentage": 39.26, "elapsed_time": "4:27:37", "remaining_time": "6:54:04"}
+{"current_steps": 820, "total_steps": 2076, "loss": 0.0356, "lr": 1.5168948992451382e-05, "epoch": 1.1850379472352728, "percentage": 39.5, "elapsed_time": "4:29:09", "remaining_time": "6:52:16"}
+{"current_steps": 825, "total_steps": 2076, "loss": 0.0365, "lr": 1.5096782165586037e-05, "epoch": 1.1922659920491507, "percentage": 39.74, "elapsed_time": "4:30:39", "remaining_time": "6:50:24"}
+{"current_steps": 830, "total_steps": 2076, "loss": 0.0381, "lr": 1.5024254943084629e-05, "epoch": 1.1994940368630285, "percentage": 39.98, "elapsed_time": "4:32:06", "remaining_time": "6:48:29"}
+{"current_steps": 835, "total_steps": 2076, "loss": 0.0367, "lr": 1.495137245337794e-05, "epoch": 1.2067220816769064, "percentage": 40.22, "elapsed_time": "4:33:38", "remaining_time": "6:46:41"}
+{"current_steps": 840, "total_steps": 2076, "loss": 0.0356, "lr": 1.487813985001782e-05, "epoch": 1.2139501264907842, "percentage": 40.46, "elapsed_time": "4:35:08", "remaining_time": "6:44:50"}
+{"current_steps": 845, "total_steps": 2076, "loss": 0.0352, "lr": 1.480456231131283e-05, "epoch": 1.221178171304662, "percentage": 40.7, "elapsed_time": "4:36:48", "remaining_time": "6:43:14"}
+{"current_steps": 850, "total_steps": 2076, "loss": 0.0364, "lr": 1.4730645039962044e-05, "epoch": 1.2284062161185398, "percentage": 40.94, "elapsed_time": "4:38:27", "remaining_time": "6:41:38"}
+{"current_steps": 855, "total_steps": 2076, "loss": 0.0368, "lr": 1.4656393262687172e-05, "epoch": 1.2356342609324178, "percentage": 41.18, "elapsed_time": "4:40:04", "remaining_time": "6:39:57"}
+{"current_steps": 860, "total_steps": 2076, "loss": 0.0338, "lr": 1.4581812229862993e-05, "epoch": 1.2428623057462955, "percentage": 41.43, "elapsed_time": "4:41:35", "remaining_time": "6:38:09"}
+{"current_steps": 865, "total_steps": 2076, "loss": 0.0328, "lr": 1.4506907215146075e-05, "epoch": 1.2500903505601735, "percentage": 41.67, "elapsed_time": "4:43:10", "remaining_time": "6:36:26"}
+{"current_steps": 870, "total_steps": 2076, "loss": 0.0348, "lr": 1.443168351510189e-05, "epoch": 1.2573183953740514, "percentage": 41.91, "elapsed_time": "4:44:30", "remaining_time": "6:34:23"}
+{"current_steps": 875, "total_steps": 2076, "loss": 0.0341, "lr": 1.4356146448830277e-05, "epoch": 1.2645464401879292, "percentage": 42.15, "elapsed_time": "4:46:00", "remaining_time": "6:32:33"}
+{"current_steps": 880, "total_steps": 2076, "loss": 0.0379, "lr": 1.4280301357589349e-05, "epoch": 1.271774485001807, "percentage": 42.39, "elapsed_time": "4:47:34", "remaining_time": "6:30:50"}
+{"current_steps": 885, "total_steps": 2076, "loss": 0.0339, "lr": 1.4204153604417775e-05, "epoch": 1.2790025298156849, "percentage": 42.63, "elapsed_time": "4:49:11", "remaining_time": "6:29:10"}
+{"current_steps": 890, "total_steps": 2076, "loss": 0.0317, "lr": 1.4127708573755599e-05, "epoch": 1.2862305746295628, "percentage": 42.87, "elapsed_time": "4:50:47", "remaining_time": "6:27:30"}
+{"current_steps": 895, "total_steps": 2076, "loss": 0.0341, "lr": 1.4050971671063464e-05, "epoch": 1.2934586194434405, "percentage": 43.11, "elapsed_time": "4:52:16", "remaining_time": "6:25:40"}
+{"current_steps": 900, "total_steps": 2076, "loss": 0.0388, "lr": 1.3973948322440427e-05, "epoch": 1.3006866642573183, "percentage": 43.35, "elapsed_time": "4:53:49", "remaining_time": "6:23:55"}
+{"current_steps": 905, "total_steps": 2076, "loss": 0.0309, "lr": 1.3896643974240245e-05, "epoch": 1.3079147090711962, "percentage": 43.59, "elapsed_time": "4:55:22", "remaining_time": "6:22:11"}
+{"current_steps": 910, "total_steps": 2076, "loss": 0.0327, "lr": 1.3819064092686278e-05, "epoch": 1.3151427538850742, "percentage": 43.83, "elapsed_time": "4:56:52", "remaining_time": "6:20:23"}
+{"current_steps": 915, "total_steps": 2076, "loss": 0.0345, "lr": 1.3741214163484968e-05, "epoch": 1.322370798698952, "percentage": 44.08, "elapsed_time": "4:58:20", "remaining_time": "6:18:33"}
+{"current_steps": 920, "total_steps": 2076, "loss": 0.0336, "lr": 1.3663099691437945e-05, "epoch": 1.3295988435128296, "percentage": 44.32, "elapsed_time": "4:59:44", "remaining_time": "6:16:37"}
+{"current_steps": 925, "total_steps": 2076, "loss": 0.038, "lr": 1.3584726200052767e-05, "epoch": 1.3368268883267076, "percentage": 44.56, "elapsed_time": "5:01:17", "remaining_time": "6:14:54"}
+{"current_steps": 930, "total_steps": 2076, "loss": 0.0346, "lr": 1.3506099231152366e-05, "epoch": 1.3440549331405856, "percentage": 44.8, "elapsed_time": "5:02:51", "remaining_time": "6:13:12"}
+{"current_steps": 935, "total_steps": 2076, "loss": 0.0296, "lr": 1.3427224344483178e-05, "epoch": 1.3512829779544633, "percentage": 45.04, "elapsed_time": "5:04:20", "remaining_time": "6:11:23"}
+{"current_steps": 940, "total_steps": 2076, "loss": 0.0309, "lr": 1.3348107117322004e-05, "epoch": 1.3585110227683412, "percentage": 45.28, "elapsed_time": "5:05:47", "remaining_time": "6:09:33"}
+{"current_steps": 945, "total_steps": 2076, "loss": 0.028, "lr": 1.3268753144081652e-05, "epoch": 1.365739067582219, "percentage": 45.52, "elapsed_time": "5:07:16", "remaining_time": "6:07:44"}
+{"current_steps": 950, "total_steps": 2076, "loss": 0.0331, "lr": 1.3189168035915337e-05, "epoch": 1.372967112396097, "percentage": 45.76, "elapsed_time": "5:08:45", "remaining_time": "6:05:57"}
+{"current_steps": 955, "total_steps": 2076, "loss": 0.031, "lr": 1.3109357420319933e-05, "epoch": 1.3801951572099747, "percentage": 46.0, "elapsed_time": "5:10:14", "remaining_time": "6:04:09"}
+{"current_steps": 960, "total_steps": 2076, "loss": 0.0338, "lr": 1.3029326940738032e-05, "epoch": 1.3874232020238526, "percentage": 46.24, "elapsed_time": "5:11:45", "remaining_time": "6:02:24"}
+{"current_steps": 965, "total_steps": 2076, "loss": 0.0313, "lr": 1.2949082256158904e-05, "epoch": 1.3946512468377303, "percentage": 46.48, "elapsed_time": "5:13:13", "remaining_time": "6:00:37"}
+{"current_steps": 970, "total_steps": 2076, "loss": 0.0324, "lr": 1.286862904071835e-05, "epoch": 1.4018792916516083, "percentage": 46.72, "elapsed_time": "5:14:43", "remaining_time": "5:58:50"}
+{"current_steps": 975, "total_steps": 2076, "loss": 0.0312, "lr": 1.2787972983297472e-05, "epoch": 1.409107336465486, "percentage": 46.97, "elapsed_time": "5:16:10", "remaining_time": "5:57:01"}
+{"current_steps": 980, "total_steps": 2076, "loss": 0.0347, "lr": 1.2707119787120417e-05, "epoch": 1.416335381279364, "percentage": 47.21, "elapsed_time": "5:17:37", "remaining_time": "5:55:13"}
+{"current_steps": 985, "total_steps": 2076, "loss": 0.0317, "lr": 1.26260751693511e-05, "epoch": 1.4235634260932417, "percentage": 47.45, "elapsed_time": "5:19:08", "remaining_time": "5:53:28"}
+{"current_steps": 990, "total_steps": 2076, "loss": 0.0316, "lr": 1.254484486068893e-05, "epoch": 1.4307914709071197, "percentage": 47.69, "elapsed_time": "5:20:35", "remaining_time": "5:51:41"}
+{"current_steps": 995, "total_steps": 2076, "loss": 0.0324, "lr": 1.24634346049636e-05, "epoch": 1.4380195157209974, "percentage": 47.93, "elapsed_time": "5:22:06", "remaining_time": "5:49:56"}
+{"current_steps": 1000, "total_steps": 2076, "loss": 0.029, "lr": 1.2381850158728952e-05, "epoch": 1.4452475605348754, "percentage": 48.17, "elapsed_time": "5:23:42", "remaining_time": "5:48:18"}
+{"current_steps": 1000, "total_steps": 2076, "eval_loss": 0.08190815895795822, "epoch": 1.4452475605348754, "percentage": 48.17, "elapsed_time": "5:42:44", "remaining_time": "6:08:47"}
+{"current_steps": 1005, "total_steps": 2076, "loss": 0.0285, "lr": 1.2300097290855887e-05, "epoch": 1.452475605348753, "percentage": 48.41, "elapsed_time": "5:44:45", "remaining_time": "6:07:24"}
+{"current_steps": 1010, "total_steps": 2076, "loss": 0.0316, "lr": 1.2218181782124496e-05, "epoch": 1.459703650162631, "percentage": 48.65, "elapsed_time": "5:46:13", "remaining_time": "6:05:25"}
+{"current_steps": 1015, "total_steps": 2076, "loss": 0.0306, "lr": 1.2136109424815258e-05, "epoch": 1.466931694976509, "percentage": 48.89, "elapsed_time": "5:47:41", "remaining_time": "6:03:27"}
+{"current_steps": 1020, "total_steps": 2076, "loss": 0.03, "lr": 1.205388602229949e-05, "epoch": 1.4741597397903867, "percentage": 49.13, "elapsed_time": "5:49:17", "remaining_time": "6:01:37"}
+{"current_steps": 1025, "total_steps": 2076, "loss": 0.0341, "lr": 1.1971517388628972e-05, "epoch": 1.4813877846042645, "percentage": 49.37, "elapsed_time": "5:50:44", "remaining_time": "5:59:38"}
+{"current_steps": 1030, "total_steps": 2076, "loss": 0.0303, "lr": 1.1889009348124857e-05, "epoch": 1.4886158294181424, "percentage": 49.61, "elapsed_time": "5:52:11", "remaining_time": "5:57:39"}
+{"current_steps": 1035, "total_steps": 2076, "loss": 0.0276, "lr": 1.180636773496579e-05, "epoch": 1.4958438742320204, "percentage": 49.86, "elapsed_time": "5:53:38", "remaining_time": "5:55:41"}
+{"current_steps": 1040, "total_steps": 2076, "loss": 0.0273, "lr": 1.1723598392775415e-05, "epoch": 1.503071919045898, "percentage": 50.1, "elapsed_time": "5:55:07", "remaining_time": "5:53:45"}
+{"current_steps": 1045, "total_steps": 2076, "loss": 0.0299, "lr": 1.1640707174209147e-05, "epoch": 1.5102999638597758, "percentage": 50.34, "elapsed_time": "5:56:41", "remaining_time": "5:51:55"}
+{"current_steps": 1050, "total_steps": 2076, "loss": 0.0308, "lr": 1.1557699940540321e-05, "epoch": 1.5175280086736538, "percentage": 50.58, "elapsed_time": "5:58:13", "remaining_time": "5:50:02"}
+{"current_steps": 1055, "total_steps": 2076, "loss": 0.0278, "lr": 1.1474582561245767e-05, "epoch": 1.5247560534875317, "percentage": 50.82, "elapsed_time": "5:59:46", "remaining_time": "5:48:10"}
+{"current_steps": 1060, "total_steps": 2076, "loss": 0.0342, "lr": 1.1391360913590736e-05, "epoch": 1.5319840983014095, "percentage": 51.06, "elapsed_time": "6:01:16", "remaining_time": "5:46:17"}
+{"current_steps": 1065, "total_steps": 2076, "loss": 0.03, "lr": 1.1308040882213363e-05, "epoch": 1.5392121431152872, "percentage": 51.3, "elapsed_time": "6:02:48", "remaining_time": "5:44:24"}
+{"current_steps": 1070, "total_steps": 2076, "loss": 0.0279, "lr": 1.122462835870852e-05, "epoch": 1.5464401879291652, "percentage": 51.54, "elapsed_time": "6:04:19", "remaining_time": "5:42:31"}
+{"current_steps": 1075, "total_steps": 2076, "loss": 0.0263, "lr": 1.1141129241211246e-05, "epoch": 1.553668232743043, "percentage": 51.78, "elapsed_time": "6:05:56", "remaining_time": "5:40:45"}
+{"current_steps": 1080, "total_steps": 2076, "loss": 0.0365, "lr": 1.1057549433979675e-05, "epoch": 1.5608962775569208, "percentage": 52.02, "elapsed_time": "6:07:26", "remaining_time": "5:38:51"}
+{"current_steps": 1085, "total_steps": 2076, "loss": 0.0286, "lr": 1.0973894846977548e-05, "epoch": 1.5681243223707986, "percentage": 52.26, "elapsed_time": "6:09:00", "remaining_time": "5:37:02"}
+{"current_steps": 1090, "total_steps": 2076, "loss": 0.0264, "lr": 1.089017139545631e-05, "epoch": 1.5753523671846765, "percentage": 52.5, "elapsed_time": "6:10:25", "remaining_time": "5:35:04"}
+{"current_steps": 1095, "total_steps": 2076, "loss": 0.028, "lr": 1.0806384999536857e-05, "epoch": 1.5825804119985545, "percentage": 52.75, "elapsed_time": "6:11:52", "remaining_time": "5:33:09"}
+{"current_steps": 1100, "total_steps": 2076, "loss": 0.0247, "lr": 1.0722541583790898e-05, "epoch": 1.5898084568124322, "percentage": 52.99, "elapsed_time": "6:13:22", "remaining_time": "5:31:16"}
+{"current_steps": 1105, "total_steps": 2076, "loss": 0.0305, "lr": 1.0638647076822041e-05, "epoch": 1.59703650162631, "percentage": 53.23, "elapsed_time": "6:14:59", "remaining_time": "5:29:31"}
+{"current_steps": 1110, "total_steps": 2076, "loss": 0.0294, "lr": 1.0554707410846585e-05, "epoch": 1.604264546440188, "percentage": 53.47, "elapsed_time": "6:16:30", "remaining_time": "5:27:39"}
+{"current_steps": 1115, "total_steps": 2076, "loss": 0.028, "lr": 1.0470728521274028e-05, "epoch": 1.6114925912540659, "percentage": 53.71, "elapsed_time": "6:17:58", "remaining_time": "5:25:46"}
+{"current_steps": 1120, "total_steps": 2076, "loss": 0.0278, "lr": 1.0386716346287398e-05, "epoch": 1.6187206360679436, "percentage": 53.95, "elapsed_time": "6:19:29", "remaining_time": "5:23:55"}
+{"current_steps": 1125, "total_steps": 2076, "loss": 0.0312, "lr": 1.030267682642334e-05, "epoch": 1.6259486808818213, "percentage": 54.19, "elapsed_time": "6:20:57", "remaining_time": "5:22:02"}
+{"current_steps": 1130, "total_steps": 2076, "loss": 0.027, "lr": 1.0218615904152067e-05, "epoch": 1.6331767256956993, "percentage": 54.43, "elapsed_time": "6:22:30", "remaining_time": "5:20:13"}
+{"current_steps": 1135, "total_steps": 2076, "loss": 0.0301, "lr": 1.0134539523457172e-05, "epoch": 1.6404047705095772, "percentage": 54.67, "elapsed_time": "6:23:59", "remaining_time": "5:18:21"}
+{"current_steps": 1140, "total_steps": 2076, "loss": 0.027, "lr": 1.0050453629415317e-05, "epoch": 1.647632815323455, "percentage": 54.91, "elapsed_time": "6:25:30", "remaining_time": "5:16:31"}
+{"current_steps": 1145, "total_steps": 2076, "loss": 0.0307, "lr": 9.966364167775851e-06, "epoch": 1.6548608601373327, "percentage": 55.15, "elapsed_time": "6:27:03", "remaining_time": "5:14:43"}
+{"current_steps": 1150, "total_steps": 2076, "loss": 0.0267, "lr": 9.882277084540399e-06, "epoch": 1.6620889049512106, "percentage": 55.39, "elapsed_time": "6:28:31", "remaining_time": "5:12:50"}
+{"current_steps": 1155, "total_steps": 2076, "loss": 0.0255, "lr": 9.798198325542399e-06, "epoch": 1.6693169497650886, "percentage": 55.64, "elapsed_time": "6:29:57", "remaining_time": "5:10:56"}
+{"current_steps": 1160, "total_steps": 2076, "loss": 0.0277, "lr": 9.714133836026687e-06, "epoch": 1.6765449945789666, "percentage": 55.88, "elapsed_time": "6:31:21", "remaining_time": "5:09:01"}
+{"current_steps": 1165, "total_steps": 2076, "loss": 0.0248, "lr": 9.630089560229088e-06, "epoch": 1.6837730393928443, "percentage": 56.12, "elapsed_time": "6:32:58", "remaining_time": "5:07:17"}
+{"current_steps": 1170, "total_steps": 2076, "loss": 0.0298, "lr": 9.546071440956115e-06, "epoch": 1.691001084206722, "percentage": 56.36, "elapsed_time": "6:34:34", "remaining_time": "5:05:32"}
+{"current_steps": 1175, "total_steps": 2076, "loss": 0.0308, "lr": 9.46208541916474e-06, "epoch": 1.6982291290206, "percentage": 56.6, "elapsed_time": "6:36:07", "remaining_time": "5:03:44"}
+{"current_steps": 1180, "total_steps": 2076, "loss": 0.0293, "lr": 9.378137433542305e-06, "epoch": 1.705457173834478, "percentage": 56.84, "elapsed_time": "6:37:40", "remaining_time": "5:01:57"}
+{"current_steps": 1185, "total_steps": 2076, "loss": 0.0271, "lr": 9.294233420086604e-06, "epoch": 1.7126852186483557, "percentage": 57.08, "elapsed_time": "6:39:09", "remaining_time": "5:00:07"}
+{"current_steps": 1190, "total_steps": 2076, "loss": 0.0293, "lr": 9.210379311686129e-06, "epoch": 1.7199132634622334, "percentage": 57.32, "elapsed_time": "6:40:48", "remaining_time": "4:58:24"}
+{"current_steps": 1195, "total_steps": 2076, "loss": 0.0289, "lr": 9.12658103770058e-06, "epoch": 1.7271413082761113, "percentage": 57.56, "elapsed_time": "6:42:20", "remaining_time": "4:56:37"}
+{"current_steps": 1200, "total_steps": 2076, "loss": 0.0286, "lr": 9.042844523541572e-06, "epoch": 1.7343693530899893, "percentage": 57.8, "elapsed_time": "6:43:49", "remaining_time": "4:54:47"}
+{"current_steps": 1205, "total_steps": 2076, "loss": 0.0275, "lr": 8.95917569025366e-06, "epoch": 1.741597397903867, "percentage": 58.04, "elapsed_time": "6:45:19", "remaining_time": "4:52:58"}
+{"current_steps": 1210, "total_steps": 2076, "loss": 0.0239, "lr": 8.875580454095651e-06, "epoch": 1.7488254427177448, "percentage": 58.29, "elapsed_time": "6:46:44", "remaining_time": "4:51:06"}
+{"current_steps": 1215, "total_steps": 2076, "loss": 0.0262, "lr": 8.792064726122275e-06, "epoch": 1.7560534875316227, "percentage": 58.53, "elapsed_time": "6:48:14", "remaining_time": "4:49:17"}
+{"current_steps": 1220, "total_steps": 2076, "loss": 0.0277, "lr": 8.708634411766195e-06, "epoch": 1.7632815323455007, "percentage": 58.77, "elapsed_time": "6:49:44", "remaining_time": "4:47:29"}
+{"current_steps": 1225, "total_steps": 2076, "loss": 0.0235, "lr": 8.625295410420451e-06, "epoch": 1.7705095771593784, "percentage": 59.01, "elapsed_time": "6:51:12", "remaining_time": "4:45:40"}
+{"current_steps": 1230, "total_steps": 2076, "loss": 0.0271, "lr": 8.542053615021291e-06, "epoch": 1.7777376219732561, "percentage": 59.25, "elapsed_time": "6:52:40", "remaining_time": "4:43:50"}
+{"current_steps": 1235, "total_steps": 2076, "loss": 0.025, "lr": 8.4589149116315e-06, "epoch": 1.784965666787134, "percentage": 59.49, "elapsed_time": "6:54:08", "remaining_time": "4:42:01"}
+{"current_steps": 1240, "total_steps": 2076, "loss": 0.0294, "lr": 8.375885179024175e-06, "epoch": 1.792193711601012, "percentage": 59.73, "elapsed_time": "6:55:29", "remaining_time": "4:40:07"}
+{"current_steps": 1245, "total_steps": 2076, "loss": 0.0239, "lr": 8.292970288267043e-06, "epoch": 1.7994217564148898, "percentage": 59.97, "elapsed_time": "6:57:00", "remaining_time": "4:38:20"}
+{"current_steps": 1250, "total_steps": 2076, "loss": 0.0312, "lr": 8.21017610230732e-06, "epoch": 1.8066498012287675, "percentage": 60.21, "elapsed_time": "6:58:36", "remaining_time": "4:36:37"}
+{"current_steps": 1255, "total_steps": 2076, "loss": 0.0288, "lr": 8.12750847555713e-06, "epoch": 1.8138778460426455, "percentage": 60.45, "elapsed_time": "7:00:13", "remaining_time": "4:34:54"}
+{"current_steps": 1260, "total_steps": 2076, "loss": 0.0242, "lr": 8.044973253479544e-06, "epoch": 1.8211058908565234, "percentage": 60.69, "elapsed_time": "7:01:42", "remaining_time": "4:33:06"}
+{"current_steps": 1265, "total_steps": 2076, "loss": 0.0292, "lr": 7.96257627217524e-06, "epoch": 1.8283339356704011, "percentage": 60.93, "elapsed_time": "7:03:09", "remaining_time": "4:31:17"}
+{"current_steps": 1270, "total_steps": 2076, "loss": 0.0239, "lr": 7.880323357969838e-06, "epoch": 1.8355619804842789, "percentage": 61.18, "elapsed_time": "7:04:40", "remaining_time": "4:29:30"}
+{"current_steps": 1275, "total_steps": 2076, "loss": 0.0245, "lr": 7.798220327001898e-06, "epoch": 1.8427900252981568, "percentage": 61.42, "elapsed_time": "7:06:10", "remaining_time": "4:27:44"}
+{"current_steps": 1280, "total_steps": 2076, "loss": 0.0261, "lr": 7.716272984811688e-06, "epoch": 1.8500180701120348, "percentage": 61.66, "elapsed_time": "7:07:49", "remaining_time": "4:26:03"}
+{"current_steps": 1285, "total_steps": 2076, "loss": 0.0259, "lr": 7.634487125930649e-06, "epoch": 1.8572461149259125, "percentage": 61.9, "elapsed_time": "7:09:15", "remaining_time": "4:24:14"}
+{"current_steps": 1290, "total_steps": 2076, "loss": 0.0237, "lr": 7.55286853347167e-06, "epoch": 1.8644741597397902, "percentage": 62.14, "elapsed_time": "7:10:42", "remaining_time": "4:22:26"}
+{"current_steps": 1295, "total_steps": 2076, "loss": 0.0244, "lr": 7.471422978720162e-06, "epoch": 1.8717022045536682, "percentage": 62.38, "elapsed_time": "7:12:15", "remaining_time": "4:20:41"}
+{"current_steps": 1300, "total_steps": 2076, "loss": 0.0245, "lr": 7.3901562207259555e-06, "epoch": 1.8789302493675462, "percentage": 62.62, "elapsed_time": "7:13:46", "remaining_time": "4:18:55"}
+{"current_steps": 1305, "total_steps": 2076, "loss": 0.0216, "lr": 7.309074005896103e-06, "epoch": 1.8861582941814239, "percentage": 62.86, "elapsed_time": "7:15:19", "remaining_time": "4:17:11"}
+{"current_steps": 1310, "total_steps": 2076, "loss": 0.0278, "lr": 7.228182067588518e-06, "epoch": 1.8933863389953016, "percentage": 63.1, "elapsed_time": "7:16:51", "remaining_time": "4:15:26"}
+{"current_steps": 1315, "total_steps": 2076, "loss": 0.0258, "lr": 7.1474861257065866e-06, "epoch": 1.9006143838091796, "percentage": 63.34, "elapsed_time": "7:18:25", "remaining_time": "4:13:43"}
+{"current_steps": 1320, "total_steps": 2076, "loss": 0.0227, "lr": 7.066991886294702e-06, "epoch": 1.9078424286230575, "percentage": 63.58, "elapsed_time": "7:19:55", "remaining_time": "4:11:57"}
+{"current_steps": 1325, "total_steps": 2076, "loss": 0.0333, "lr": 6.9867050411347955e-06, "epoch": 1.9150704734369353, "percentage": 63.82, "elapsed_time": "7:21:28", "remaining_time": "4:10:13"}
+{"current_steps": 1330, "total_steps": 2076, "loss": 0.0235, "lr": 6.906631267343849e-06, "epoch": 1.922298518250813, "percentage": 64.07, "elapsed_time": "7:23:03", "remaining_time": "4:08:30"}
+{"current_steps": 1335, "total_steps": 2076, "loss": 0.0247, "lr": 6.826776226972489e-06, "epoch": 1.929526563064691, "percentage": 64.31, "elapsed_time": "7:24:31", "remaining_time": "4:06:44"}
+{"current_steps": 1340, "total_steps": 2076, "loss": 0.0281, "lr": 6.747145566604605e-06, "epoch": 1.936754607878569, "percentage": 64.55, "elapsed_time": "7:26:01", "remaining_time": "4:04:59"}
+{"current_steps": 1345, "total_steps": 2076, "loss": 0.0242, "lr": 6.667744916958085e-06, "epoch": 1.9439826526924469, "percentage": 64.79, "elapsed_time": "7:27:30", "remaining_time": "4:03:13"}
+{"current_steps": 1350, "total_steps": 2076, "loss": 0.0254, "lr": 6.588579892486657e-06, "epoch": 1.9512106975063246, "percentage": 65.03, "elapsed_time": "7:29:05", "remaining_time": "4:01:30"}
+{"current_steps": 1355, "total_steps": 2076, "loss": 0.0206, "lr": 6.5096560909828855e-06, "epoch": 1.9584387423202023, "percentage": 65.27, "elapsed_time": "7:30:30", "remaining_time": "3:59:43"}
+{"current_steps": 1360, "total_steps": 2076, "loss": 0.0223, "lr": 6.430979093182372e-06, "epoch": 1.9656667871340803, "percentage": 65.51, "elapsed_time": "7:32:06", "remaining_time": "3:58:01"}
+{"current_steps": 1365, "total_steps": 2076, "loss": 0.0281, "lr": 6.352554462369112e-06, "epoch": 1.9728948319479582, "percentage": 65.75, "elapsed_time": "7:33:42", "remaining_time": "3:56:19"}
+{"current_steps": 1370, "total_steps": 2076, "loss": 0.0234, "lr": 6.274387743982127e-06, "epoch": 1.980122876761836, "percentage": 65.99, "elapsed_time": "7:35:09", "remaining_time": "3:54:33"}
+{"current_steps": 1375, "total_steps": 2076, "loss": 0.0218, "lr": 6.196484465223343e-06, "epoch": 1.9873509215757137, "percentage": 66.23, "elapsed_time": "7:36:41", "remaining_time": "3:52:49"}
+{"current_steps": 1380, "total_steps": 2076, "loss": 0.0267, "lr": 6.1188501346667536e-06, "epoch": 1.9945789663895916, "percentage": 66.47, "elapsed_time": "7:38:15", "remaining_time": "3:51:07"}
+{"current_steps": 1385, "total_steps": 2076, "loss": 0.0196, "lr": 6.04149024186891e-06, "epoch": 2.0014456089627757, "percentage": 66.71, "elapsed_time": "7:39:39", "remaining_time": "3:49:20"}
+{"current_steps": 1390, "total_steps": 2076, "loss": 0.0085, "lr": 5.964410256980762e-06, "epoch": 2.0086736537766536, "percentage": 66.96, "elapsed_time": "7:41:09", "remaining_time": "3:47:35"}
+{"current_steps": 1395, "total_steps": 2076, "loss": 0.0064, "lr": 5.887615630360836e-06, "epoch": 2.015901698590531, "percentage": 67.2, "elapsed_time": "7:42:44", "remaining_time": "3:45:53"}
+{"current_steps": 1400, "total_steps": 2076, "loss": 0.0058, "lr": 5.811111792189873e-06, "epoch": 2.023129743404409, "percentage": 67.44, "elapsed_time": "7:44:14", "remaining_time": "3:44:09"}
+{"current_steps": 1405, "total_steps": 2076, "loss": 0.0052, "lr": 5.734904152086829e-06, "epoch": 2.030357788218287, "percentage": 67.68, "elapsed_time": "7:45:48", "remaining_time": "3:42:27"}
+{"current_steps": 1410, "total_steps": 2076, "loss": 0.0054, "lr": 5.658998098726361e-06, "epoch": 2.037585833032165, "percentage": 67.92, "elapsed_time": "7:47:15", "remaining_time": "3:40:42"}
+{"current_steps": 1415, "total_steps": 2076, "loss": 0.0043, "lr": 5.583398999457812e-06, "epoch": 2.0448138778460425, "percentage": 68.16, "elapsed_time": "7:48:41", "remaining_time": "3:38:56"}
+{"current_steps": 1420, "total_steps": 2076, "loss": 0.0041, "lr": 5.508112199925659e-06, "epoch": 2.0520419226599205, "percentage": 68.4, "elapsed_time": "7:50:01", "remaining_time": "3:37:08"}
+{"current_steps": 1425, "total_steps": 2076, "loss": 0.0038, "lr": 5.433143023691547e-06, "epoch": 2.0592699674737984, "percentage": 68.64, "elapsed_time": "7:51:33", "remaining_time": "3:35:25"}
+{"current_steps": 1430, "total_steps": 2076, "loss": 0.0044, "lr": 5.358496771857831e-06, "epoch": 2.0664980122876764, "percentage": 68.88, "elapsed_time": "7:53:05", "remaining_time": "3:33:43"}
+{"current_steps": 1435, "total_steps": 2076, "loss": 0.0052, "lr": 5.284178722692743e-06, "epoch": 2.073726057101554, "percentage": 69.12, "elapsed_time": "7:54:46", "remaining_time": "3:32:04"}
+{"current_steps": 1440, "total_steps": 2076, "loss": 0.0037, "lr": 5.2101941312571724e-06, "epoch": 2.080954101915432, "percentage": 69.36, "elapsed_time": "7:56:22", "remaining_time": "3:30:23"}
+{"current_steps": 1445, "total_steps": 2076, "loss": 0.0047, "lr": 5.136548229033065e-06, "epoch": 2.08818214672931, "percentage": 69.61, "elapsed_time": "7:58:00", "remaining_time": "3:28:44"}
+{"current_steps": 1450, "total_steps": 2076, "loss": 0.0052, "lr": 5.063246223553509e-06, "epoch": 2.0954101915431878, "percentage": 69.85, "elapsed_time": "7:59:26", "remaining_time": "3:26:59"}
+{"current_steps": 1455, "total_steps": 2076, "loss": 0.0045, "lr": 4.990293298034505e-06, "epoch": 2.1026382363570653, "percentage": 70.09, "elapsed_time": "8:01:10", "remaining_time": "3:25:22"}
+{"current_steps": 1460, "total_steps": 2076, "loss": 0.0041, "lr": 4.917694611008477e-06, "epoch": 2.109866281170943, "percentage": 70.33, "elapsed_time": "8:02:42", "remaining_time": "3:23:39"}
+{"current_steps": 1465, "total_steps": 2076, "loss": 0.0051, "lr": 4.845455295959468e-06, "epoch": 2.117094325984821, "percentage": 70.57, "elapsed_time": "8:04:16", "remaining_time": "3:21:58"}
+{"current_steps": 1470, "total_steps": 2076, "loss": 0.0065, "lr": 4.773580460960195e-06, "epoch": 2.124322370798699, "percentage": 70.81, "elapsed_time": "8:05:49", "remaining_time": "3:20:16"}
+{"current_steps": 1475, "total_steps": 2076, "loss": 0.0052, "lr": 4.702075188310826e-06, "epoch": 2.1315504156125766, "percentage": 71.05, "elapsed_time": "8:07:26", "remaining_time": "3:18:36"}
+{"current_steps": 1480, "total_steps": 2076, "loss": 0.0048, "lr": 4.6309445341796286e-06, "epoch": 2.1387784604264546, "percentage": 71.29, "elapsed_time": "8:09:00", "remaining_time": "3:16:55"}
+{"current_steps": 1485, "total_steps": 2076, "loss": 0.0035, "lr": 4.5601935282454255e-06, "epoch": 2.1460065052403325, "percentage": 71.53, "elapsed_time": "8:10:26", "remaining_time": "3:15:11"}
+{"current_steps": 1490, "total_steps": 2076, "loss": 0.0046, "lr": 4.489827173341957e-06, "epoch": 2.1532345500542105, "percentage": 71.77, "elapsed_time": "8:11:56", "remaining_time": "3:13:28"}
+{"current_steps": 1495, "total_steps": 2076, "loss": 0.0066, "lr": 4.419850445104126e-06, "epoch": 2.160462594868088, "percentage": 72.01, "elapsed_time": "8:13:33", "remaining_time": "3:11:48"}
+{"current_steps": 1500, "total_steps": 2076, "loss": 0.0058, "lr": 4.350268291616166e-06, "epoch": 2.167690639681966, "percentage": 72.25, "elapsed_time": "8:15:05", "remaining_time": "3:10:06"}
+{"current_steps": 1500, "total_steps": 2076, "eval_loss": 0.15236619114875793, "epoch": 2.167690639681966, "percentage": 72.25, "elapsed_time": "8:34:08", "remaining_time": "3:17:25"}
+{"current_steps": 1505, "total_steps": 2076, "loss": 0.0047, "lr": 4.281085633061764e-06, "epoch": 2.174918684495844, "percentage": 72.5, "elapsed_time": "8:36:01", "remaining_time": "3:15:46"}
+{"current_steps": 1510, "total_steps": 2076, "loss": 0.0078, "lr": 4.212307361376146e-06, "epoch": 2.182146729309722, "percentage": 72.74, "elapsed_time": "8:37:32", "remaining_time": "3:13:59"}
+{"current_steps": 1515, "total_steps": 2076, "loss": 0.0043, "lr": 4.1439383399001865e-06, "epoch": 2.1893747741235994, "percentage": 72.98, "elapsed_time": "8:39:07", "remaining_time": "3:12:13"}
+{"current_steps": 1520, "total_steps": 2076, "loss": 0.0045, "lr": 4.075983403036479e-06, "epoch": 2.1966028189374773, "percentage": 73.22, "elapsed_time": "8:40:41", "remaining_time": "3:10:27"}
+{"current_steps": 1525, "total_steps": 2076, "loss": 0.0073, "lr": 4.0084473559075335e-06, "epoch": 2.2038308637513553, "percentage": 73.46, "elapsed_time": "8:42:14", "remaining_time": "3:08:41"}
+{"current_steps": 1530, "total_steps": 2076, "loss": 0.006, "lr": 3.941334974015981e-06, "epoch": 2.2110589085652332, "percentage": 73.7, "elapsed_time": "8:43:44", "remaining_time": "3:06:54"}
+{"current_steps": 1535, "total_steps": 2076, "loss": 0.0047, "lr": 3.874651002906915e-06, "epoch": 2.2182869533791107, "percentage": 73.94, "elapsed_time": "8:45:16", "remaining_time": "3:05:07"}
+{"current_steps": 1540, "total_steps": 2076, "loss": 0.0049, "lr": 3.8084001578323093e-06, "epoch": 2.2255149981929887, "percentage": 74.18, "elapsed_time": "8:46:47", "remaining_time": "3:03:21"}
+{"current_steps": 1545, "total_steps": 2076, "loss": 0.0069, "lr": 3.7425871234176134e-06, "epoch": 2.2327430430068667, "percentage": 74.42, "elapsed_time": "8:48:26", "remaining_time": "3:01:37"}
+{"current_steps": 1550, "total_steps": 2076, "loss": 0.0034, "lr": 3.6772165533305024e-06, "epoch": 2.2399710878207446, "percentage": 74.66, "elapsed_time": "8:49:55", "remaining_time": "2:59:49"}
+{"current_steps": 1555, "total_steps": 2076, "loss": 0.0045, "lr": 3.6122930699518057e-06, "epoch": 2.2471991326346226, "percentage": 74.9, "elapsed_time": "8:51:18", "remaining_time": "2:58:00"}
+{"current_steps": 1560, "total_steps": 2076, "loss": 0.0049, "lr": 3.5478212640486652e-06, "epoch": 2.2544271774485, "percentage": 75.14, "elapsed_time": "8:52:52", "remaining_time": "2:56:15"}
+{"current_steps": 1565, "total_steps": 2076, "loss": 0.0034, "lr": 3.483805694449913e-06, "epoch": 2.261655222262378, "percentage": 75.39, "elapsed_time": "8:54:16", "remaining_time": "2:54:26"}
+{"current_steps": 1570, "total_steps": 2076, "loss": 0.0044, "lr": 3.420250887723722e-06, "epoch": 2.268883267076256, "percentage": 75.63, "elapsed_time": "8:55:49", "remaining_time": "2:52:41"}
+{"current_steps": 1575, "total_steps": 2076, "loss": 0.0037, "lr": 3.357161337857523e-06, "epoch": 2.2761113118901335, "percentage": 75.87, "elapsed_time": "8:57:18", "remaining_time": "2:50:54"}
+{"current_steps": 1580, "total_steps": 2076, "loss": 0.0051, "lr": 3.2945415059402363e-06, "epoch": 2.2833393567040114, "percentage": 76.11, "elapsed_time": "8:58:52", "remaining_time": "2:49:09"}
+{"current_steps": 1585, "total_steps": 2076, "loss": 0.0036, "lr": 3.232395819846824e-06, "epoch": 2.2905674015178894, "percentage": 76.35, "elapsed_time": "9:00:22", "remaining_time": "2:47:23"}
+{"current_steps": 1590, "total_steps": 2076, "loss": 0.003, "lr": 3.170728673925206e-06, "epoch": 2.2977954463317674, "percentage": 76.59, "elapsed_time": "9:01:47", "remaining_time": "2:45:36"}
+{"current_steps": 1595, "total_steps": 2076, "loss": 0.0056, "lr": 3.1095444286855112e-06, "epoch": 2.3050234911456453, "percentage": 76.83, "elapsed_time": "9:03:13", "remaining_time": "2:43:49"}
+{"current_steps": 1600, "total_steps": 2076, "loss": 0.0047, "lr": 3.04884741049176e-06, "epoch": 2.312251535959523, "percentage": 77.07, "elapsed_time": "9:04:44", "remaining_time": "2:42:03"}
+{"current_steps": 1605, "total_steps": 2076, "loss": 0.005, "lr": 2.9886419112559396e-06, "epoch": 2.3194795807734008, "percentage": 77.31, "elapsed_time": "9:06:18", "remaining_time": "2:40:19"}
+{"current_steps": 1610, "total_steps": 2076, "loss": 0.0065, "lr": 2.9289321881345257e-06, "epoch": 2.3267076255872787, "percentage": 77.55, "elapsed_time": "9:07:51", "remaining_time": "2:38:34"}
+{"current_steps": 1615, "total_steps": 2076, "loss": 0.0029, "lr": 2.86972246322745e-06, "epoch": 2.3339356704011567, "percentage": 77.79, "elapsed_time": "9:09:11", "remaining_time": "2:36:46"}
+{"current_steps": 1620, "total_steps": 2076, "loss": 0.0029, "lr": 2.8110169232795615e-06, "epoch": 2.341163715215034, "percentage": 78.03, "elapsed_time": "9:10:37", "remaining_time": "2:34:59"}
+{"current_steps": 1625, "total_steps": 2076, "loss": 0.0059, "lr": 2.752819719384573e-06, "epoch": 2.348391760028912, "percentage": 78.28, "elapsed_time": "9:12:01", "remaining_time": "2:33:12"}
+{"current_steps": 1630, "total_steps": 2076, "loss": 0.0046, "lr": 2.6951349666915404e-06, "epoch": 2.35561980484279, "percentage": 78.52, "elapsed_time": "9:13:31", "remaining_time": "2:31:27"}
+{"current_steps": 1635, "total_steps": 2076, "loss": 0.005, "lr": 2.637966744113877e-06, "epoch": 2.362847849656668, "percentage": 78.76, "elapsed_time": "9:15:05", "remaining_time": "2:29:43"}
+{"current_steps": 1640, "total_steps": 2076, "loss": 0.0046, "lr": 2.581319094040927e-06, "epoch": 2.3700758944705456, "percentage": 79.0, "elapsed_time": "9:16:29", "remaining_time": "2:27:56"}
+{"current_steps": 1645, "total_steps": 2076, "loss": 0.0036, "lr": 2.5251960220521422e-06, "epoch": 2.3773039392844235, "percentage": 79.24, "elapsed_time": "9:17:53", "remaining_time": "2:26:10"}
+{"current_steps": 1650, "total_steps": 2076, "loss": 0.0043, "lr": 2.4696014966338267e-06, "epoch": 2.3845319840983015, "percentage": 79.48, "elapsed_time": "9:19:25", "remaining_time": "2:24:25"}
+{"current_steps": 1655, "total_steps": 2076, "loss": 0.0031, "lr": 2.4145394488985307e-06, "epoch": 2.3917600289121794, "percentage": 79.72, "elapsed_time": "9:20:56", "remaining_time": "2:22:41"}
+{"current_steps": 1660, "total_steps": 2076, "loss": 0.0039, "lr": 2.360013772307086e-06, "epoch": 2.398988073726057, "percentage": 79.96, "elapsed_time": "9:22:31", "remaining_time": "2:20:58"}
+{"current_steps": 1665, "total_steps": 2076, "loss": 0.0041, "lr": 2.3060283223932876e-06, "epoch": 2.406216118539935, "percentage": 80.2, "elapsed_time": "9:24:09", "remaining_time": "2:19:15"}
+{"current_steps": 1670, "total_steps": 2076, "loss": 0.0062, "lr": 2.252586916491275e-06, "epoch": 2.413444163353813, "percentage": 80.44, "elapsed_time": "9:25:47", "remaining_time": "2:17:33"}
+{"current_steps": 1675, "total_steps": 2076, "loss": 0.0048, "lr": 2.1996933334656044e-06, "epoch": 2.420672208167691, "percentage": 80.68, "elapsed_time": "9:27:16", "remaining_time": "2:15:48"}
+{"current_steps": 1680, "total_steps": 2076, "loss": 0.0064, "lr": 2.1473513134440425e-06, "epoch": 2.4279002529815683, "percentage": 80.92, "elapsed_time": "9:29:03", "remaining_time": "2:14:07"}
+{"current_steps": 1685, "total_steps": 2076, "loss": 0.005, "lr": 2.0955645575531e-06, "epoch": 2.4351282977954463, "percentage": 81.17, "elapsed_time": "9:30:35", "remaining_time": "2:12:24"}
+{"current_steps": 1690, "total_steps": 2076, "loss": 0.0056, "lr": 2.0443367276563277e-06, "epoch": 2.442356342609324, "percentage": 81.41, "elapsed_time": "9:32:17", "remaining_time": "2:10:42"}
+{"current_steps": 1695, "total_steps": 2076, "loss": 0.0058, "lr": 1.9936714460953743e-06, "epoch": 2.449584387423202, "percentage": 81.65, "elapsed_time": "9:33:56", "remaining_time": "2:09:00"}
+{"current_steps": 1700, "total_steps": 2076, "loss": 0.0038, "lr": 1.9435722954338675e-06, "epoch": 2.4568124322370797, "percentage": 81.89, "elapsed_time": "9:35:20", "remaining_time": "2:07:15"}
+{"current_steps": 1705, "total_steps": 2076, "loss": 0.0042, "lr": 1.8940428182040715e-06, "epoch": 2.4640404770509576, "percentage": 82.13, "elapsed_time": "9:36:50", "remaining_time": "2:05:31"}
+{"current_steps": 1710, "total_steps": 2076, "loss": 0.0029, "lr": 1.8450865166564003e-06, "epoch": 2.4712685218648356, "percentage": 82.37, "elapsed_time": "9:38:20", "remaining_time": "2:03:47"}
+{"current_steps": 1715, "total_steps": 2076, "loss": 0.0041, "lr": 1.7967068525117658e-06, "epoch": 2.4784965666787135, "percentage": 82.61, "elapsed_time": "9:40:06", "remaining_time": "2:02:06"}
+{"current_steps": 1720, "total_steps": 2076, "loss": 0.0039, "lr": 1.7489072467168166e-06, "epoch": 2.485724611492591, "percentage": 82.85, "elapsed_time": "9:41:37", "remaining_time": "2:00:22"}
+{"current_steps": 1725, "total_steps": 2076, "loss": 0.0062, "lr": 1.7016910792020191e-06, "epoch": 2.492952656306469, "percentage": 83.09, "elapsed_time": "9:43:12", "remaining_time": "1:58:40"}
+{"current_steps": 1730, "total_steps": 2076, "loss": 0.0033, "lr": 1.6550616886426718e-06, "epoch": 2.500180701120347, "percentage": 83.33, "elapsed_time": "9:44:46", "remaining_time": "1:56:57"}
+{"current_steps": 1735, "total_steps": 2076, "loss": 0.005, "lr": 1.609022372222827e-06, "epoch": 2.507408745934225, "percentage": 83.57, "elapsed_time": "9:46:16", "remaining_time": "1:55:13"}
+{"current_steps": 1740, "total_steps": 2076, "loss": 0.004, "lr": 1.5635763854021424e-06, "epoch": 2.514636790748103, "percentage": 83.82, "elapsed_time": "9:47:52", "remaining_time": "1:53:31"}
+{"current_steps": 1745, "total_steps": 2076, "loss": 0.0044, "lr": 1.5187269416856875e-06, "epoch": 2.5218648355619804, "percentage": 84.06, "elapsed_time": "9:49:28", "remaining_time": "1:51:48"}
+{"current_steps": 1750, "total_steps": 2076, "loss": 0.003, "lr": 1.474477212396712e-06, "epoch": 2.5290928803758583, "percentage": 84.3, "elapsed_time": "9:51:06", "remaining_time": "1:50:06"}
+{"current_steps": 1755, "total_steps": 2076, "loss": 0.0046, "lr": 1.4308303264524115e-06, "epoch": 2.5363209251897363, "percentage": 84.54, "elapsed_time": "9:52:38", "remaining_time": "1:48:23"}
+{"current_steps": 1760, "total_steps": 2076, "loss": 0.0037, "lr": 1.3877893701426637e-06, "epoch": 2.543548970003614, "percentage": 84.78, "elapsed_time": "9:54:16", "remaining_time": "1:46:41"}
+{"current_steps": 1765, "total_steps": 2076, "loss": 0.0056, "lr": 1.3453573869118097e-06, "epoch": 2.5507770148174918, "percentage": 85.02, "elapsed_time": "9:55:39", "remaining_time": "1:44:57"}
+{"current_steps": 1770, "total_steps": 2076, "loss": 0.0063, "lr": 1.3035373771434356e-06, "epoch": 2.5580050596313697, "percentage": 85.26, "elapsed_time": "9:57:13", "remaining_time": "1:43:14"}
+{"current_steps": 1775, "total_steps": 2076, "loss": 0.0049, "lr": 1.2623322979482355e-06, "epoch": 2.5652331044452477, "percentage": 85.5, "elapsed_time": "9:58:49", "remaining_time": "1:41:32"}
+{"current_steps": 1780, "total_steps": 2076, "loss": 0.0042, "lr": 1.2217450629548955e-06, "epoch": 2.5724611492591256, "percentage": 85.74, "elapsed_time": "10:00:14", "remaining_time": "1:39:48"}
+{"current_steps": 1785, "total_steps": 2076, "loss": 0.0025, "lr": 1.181778542104075e-06, "epoch": 2.579689194073003, "percentage": 85.98, "elapsed_time": "10:01:53", "remaining_time": "1:38:07"}
+{"current_steps": 1790, "total_steps": 2076, "loss": 0.0047, "lr": 1.1424355614454718e-06, "epoch": 2.586917238886881, "percentage": 86.22, "elapsed_time": "10:03:30", "remaining_time": "1:36:25"}
+{"current_steps": 1795, "total_steps": 2076, "loss": 0.0078, "lr": 1.1037189029379925e-06, "epoch": 2.594145283700759, "percentage": 86.46, "elapsed_time": "10:05:11", "remaining_time": "1:34:44"}
+{"current_steps": 1800, "total_steps": 2076, "loss": 0.0051, "lr": 1.0656313042530376e-06, "epoch": 2.6013733285146365, "percentage": 86.71, "elapsed_time": "10:06:46", "remaining_time": "1:33:02"}
+{"current_steps": 1805, "total_steps": 2076, "loss": 0.0057, "lr": 1.028175458580918e-06, "epoch": 2.6086013733285145, "percentage": 86.95, "elapsed_time": "10:08:19", "remaining_time": "1:31:20"}
+{"current_steps": 1810, "total_steps": 2076, "loss": 0.0029, "lr": 9.913540144404254e-07, "epoch": 2.6158294181423924, "percentage": 87.19, "elapsed_time": "10:09:52", "remaining_time": "1:29:37"}
+{"current_steps": 1815, "total_steps": 2076, "loss": 0.0058, "lr": 9.551695754915447e-07, "epoch": 2.6230574629562704, "percentage": 87.43, "elapsed_time": "10:11:27", "remaining_time": "1:27:55"}
+{"current_steps": 1820, "total_steps": 2076, "loss": 0.0056, "lr": 9.196247003513537e-07, "epoch": 2.6302855077701484, "percentage": 87.67, "elapsed_time": "10:13:01", "remaining_time": "1:26:13"}
+{"current_steps": 1825, "total_steps": 2076, "loss": 0.0042, "lr": 8.84721902413097e-07, "epoch": 2.637513552584026, "percentage": 87.91, "elapsed_time": "10:14:36", "remaining_time": "1:24:31"}
+{"current_steps": 1830, "total_steps": 2076, "loss": 0.0043, "lr": 8.50463649668477e-07, "epoch": 2.644741597397904, "percentage": 88.15, "elapsed_time": "10:16:01", "remaining_time": "1:22:48"}
+{"current_steps": 1835, "total_steps": 2076, "loss": 0.0047, "lr": 8.168523645331216e-07, "epoch": 2.6519696422117818, "percentage": 88.39, "elapsed_time": "10:17:28", "remaining_time": "1:21:05"}
+{"current_steps": 1840, "total_steps": 2076, "loss": 0.0041, "lr": 7.838904236753087e-07, "epoch": 2.6591976870256593, "percentage": 88.63, "elapsed_time": "10:19:04", "remaining_time": "1:19:24"}
+{"current_steps": 1845, "total_steps": 2076, "loss": 0.0065, "lr": 7.515801578479032e-07, "epoch": 2.6664257318395372, "percentage": 88.87, "elapsed_time": "10:20:37", "remaining_time": "1:17:42"}
+{"current_steps": 1850, "total_steps": 2076, "loss": 0.003, "lr": 7.199238517235541e-07, "epoch": 2.673653776653415, "percentage": 89.11, "elapsed_time": "10:22:09", "remaining_time": "1:16:00"}
+{"current_steps": 1855, "total_steps": 2076, "loss": 0.0036, "lr": 6.889237437331398e-07, "epoch": 2.680881821467293, "percentage": 89.35, "elapsed_time": "10:23:43", "remaining_time": "1:14:18"}
+{"current_steps": 1860, "total_steps": 2076, "loss": 0.005, "lr": 6.585820259074882e-07, "epoch": 2.688109866281171, "percentage": 89.6, "elapsed_time": "10:25:30", "remaining_time": "1:12:38"}
+{"current_steps": 1865, "total_steps": 2076, "loss": 0.0061, "lr": 6.289008437223798e-07, "epoch": 2.6953379110950486, "percentage": 89.84, "elapsed_time": "10:27:03", "remaining_time": "1:10:56"}
+{"current_steps": 1870, "total_steps": 2076, "loss": 0.0044, "lr": 5.998822959468409e-07, "epoch": 2.7025659559089266, "percentage": 90.08, "elapsed_time": "10:28:38", "remaining_time": "1:09:15"}
+{"current_steps": 1875, "total_steps": 2076, "loss": 0.0052, "lr": 5.715284344947358e-07, "epoch": 2.7097940007228045, "percentage": 90.32, "elapsed_time": "10:30:14", "remaining_time": "1:07:33"}
+{"current_steps": 1880, "total_steps": 2076, "loss": 0.004, "lr": 5.438412642796686e-07, "epoch": 2.7170220455366825, "percentage": 90.56, "elapsed_time": "10:31:55", "remaining_time": "1:05:52"}
+{"current_steps": 1885, "total_steps": 2076, "loss": 0.0046, "lr": 5.168227430732353e-07, "epoch": 2.7242500903505604, "percentage": 90.8, "elapsed_time": "10:33:31", "remaining_time": "1:04:11"}
+{"current_steps": 1890, "total_steps": 2076, "loss": 0.005, "lr": 4.904747813665656e-07, "epoch": 2.731478135164438, "percentage": 91.04, "elapsed_time": "10:35:05", "remaining_time": "1:02:30"}
+{"current_steps": 1895, "total_steps": 2076, "loss": 0.0056, "lr": 4.6479924223524655e-07, "epoch": 2.738706179978316, "percentage": 91.28, "elapsed_time": "10:36:39", "remaining_time": "1:00:48"}
+{"current_steps": 1900, "total_steps": 2076, "loss": 0.004, "lr": 4.39797941207577e-07, "epoch": 2.745934224792194, "percentage": 91.52, "elapsed_time": "10:38:10", "remaining_time": "0:59:06"}
+{"current_steps": 1905, "total_steps": 2076, "loss": 0.0052, "lr": 4.1547264613619243e-07, "epoch": 2.7531622696060714, "percentage": 91.76, "elapsed_time": "10:39:46", "remaining_time": "0:57:25"}
+{"current_steps": 1910, "total_steps": 2076, "loss": 0.0055, "lr": 3.9182507707305915e-07, "epoch": 2.7603903144199493, "percentage": 92.0, "elapsed_time": "10:41:17", "remaining_time": "0:55:44"}
+{"current_steps": 1915, "total_steps": 2076, "loss": 0.0043, "lr": 3.6885690614785197e-07, "epoch": 2.7676183592338273, "percentage": 92.24, "elapsed_time": "10:42:58", "remaining_time": "0:54:03"}
+{"current_steps": 1920, "total_steps": 2076, "loss": 0.0046, "lr": 3.4656975744970846e-07, "epoch": 2.774846404047705, "percentage": 92.49, "elapsed_time": "10:44:29", "remaining_time": "0:52:21"}
+{"current_steps": 1925, "total_steps": 2076, "loss": 0.0028, "lr": 3.249652069124032e-07, "epoch": 2.782074448861583, "percentage": 92.73, "elapsed_time": "10:45:57", "remaining_time": "0:50:40"}
+{"current_steps": 1930, "total_steps": 2076, "loss": 0.0048, "lr": 3.040447822028958e-07, "epoch": 2.7893024936754607, "percentage": 92.97, "elapsed_time": "10:47:29", "remaining_time": "0:48:58"}
+{"current_steps": 1935, "total_steps": 2076, "loss": 0.004, "lr": 2.838099626133206e-07, "epoch": 2.7965305384893386, "percentage": 93.21, "elapsed_time": "10:49:01", "remaining_time": "0:47:17"}
+{"current_steps": 1940, "total_steps": 2076, "loss": 0.0069, "lr": 2.642621789563848e-07, "epoch": 2.8037585833032166, "percentage": 93.45, "elapsed_time": "10:50:38", "remaining_time": "0:45:36"}
+{"current_steps": 1945, "total_steps": 2076, "loss": 0.0037, "lr": 2.4540281346418946e-07, "epoch": 2.810986628117094, "percentage": 93.69, "elapsed_time": "10:52:12", "remaining_time": "0:43:55"}
+{"current_steps": 1950, "total_steps": 2076, "loss": 0.0036, "lr": 2.2723319969049307e-07, "epoch": 2.818214672930972, "percentage": 93.93, "elapsed_time": "10:53:49", "remaining_time": "0:42:14"}
+{"current_steps": 1955, "total_steps": 2076, "loss": 0.0024, "lr": 2.0975462241642042e-07, "epoch": 2.82544271774485, "percentage": 94.17, "elapsed_time": "10:55:16", "remaining_time": "0:40:33"}
+{"current_steps": 1960, "total_steps": 2076, "loss": 0.0052, "lr": 1.9296831755960753e-07, "epoch": 2.832670762558728, "percentage": 94.41, "elapsed_time": "10:56:49", "remaining_time": "0:38:52"}
+{"current_steps": 1965, "total_steps": 2076, "loss": 0.0037, "lr": 1.76875472086816e-07, "epoch": 2.839898807372606, "percentage": 94.65, "elapsed_time": "10:58:28", "remaining_time": "0:37:11"}
+{"current_steps": 1970, "total_steps": 2076, "loss": 0.0038, "lr": 1.6147722392999887e-07, "epoch": 2.8471268521864834, "percentage": 94.89, "elapsed_time": "11:00:00", "remaining_time": "0:35:30"}
+{"current_steps": 1975, "total_steps": 2076, "loss": 0.0049, "lr": 1.467746619058341e-07, "epoch": 2.8543548970003614, "percentage": 95.13, "elapsed_time": "11:01:31", "remaining_time": "0:33:49"}
+{"current_steps": 1980, "total_steps": 2076, "loss": 0.0042, "lr": 1.327688256387416e-07, "epoch": 2.8615829418142393, "percentage": 95.38, "elapsed_time": "11:03:04", "remaining_time": "0:32:08"}
+{"current_steps": 1985, "total_steps": 2076, "loss": 0.0035, "lr": 1.1946070548736532e-07, "epoch": 2.868810986628117, "percentage": 95.62, "elapsed_time": "11:04:33", "remaining_time": "0:30:27"}
+{"current_steps": 1990, "total_steps": 2076, "loss": 0.0038, "lr": 1.0685124247454159e-07, "epoch": 2.876039031441995, "percentage": 95.86, "elapsed_time": "11:06:01", "remaining_time": "0:28:46"}
+{"current_steps": 1995, "total_steps": 2076, "loss": 0.0043, "lr": 9.494132822077007e-08, "epoch": 2.8832670762558728, "percentage": 96.1, "elapsed_time": "11:07:38", "remaining_time": "0:27:06"}
+{"current_steps": 2000, "total_steps": 2076, "loss": 0.005, "lr": 8.373180488115529e-08, "epoch": 2.8904951210697507, "percentage": 96.34, "elapsed_time": "11:09:15", "remaining_time": "0:25:25"}
+{"current_steps": 2000, "total_steps": 2076, "eval_loss": 0.1443248987197876, "epoch": 2.8904951210697507, "percentage": 96.34, "elapsed_time": "11:29:15", "remaining_time": "0:26:11"}
+{"current_steps": 2005, "total_steps": 2076, "loss": 0.0043, "lr": 7.322346508586209e-08, "epoch": 2.8977231658836287, "percentage": 96.58, "elapsed_time": "11:31:13", "remaining_time": "0:24:28"}
+{"current_steps": 2010, "total_steps": 2076, "loss": 0.0048, "lr": 6.341705188407043e-08, "epoch": 2.904951210697506, "percentage": 96.82, "elapsed_time": "11:32:43", "remaining_time": "0:22:44"}
+{"current_steps": 2015, "total_steps": 2076, "loss": 0.0054, "lr": 5.431325869143189e-08, "epoch": 2.912179255511384, "percentage": 97.06, "elapsed_time": "11:34:18", "remaining_time": "0:21:01"}
+{"current_steps": 2020, "total_steps": 2076, "loss": 0.0038, "lr": 4.5912729241036624e-08, "epoch": 2.919407300325262, "percentage": 97.3, "elapsed_time": "11:35:59", "remaining_time": "0:19:17"}
+{"current_steps": 2025, "total_steps": 2076, "loss": 0.0038, "lr": 3.821605753789648e-08, "epoch": 2.9266353451391396, "percentage": 97.54, "elapsed_time": "11:37:28", "remaining_time": "0:17:33"}
+{"current_steps": 2030, "total_steps": 2076, "loss": 0.0028, "lr": 3.122378781694524e-08, "epoch": 2.933863389953018, "percentage": 97.78, "elapsed_time": "11:38:49", "remaining_time": "0:15:50"}
+{"current_steps": 2035, "total_steps": 2076, "loss": 0.0041, "lr": 2.493641450454942e-08, "epoch": 2.9410914347668955, "percentage": 98.03, "elapsed_time": "11:40:23", "remaining_time": "0:14:06"}
+{"current_steps": 2040, "total_steps": 2076, "loss": 0.0037, "lr": 1.93543821835529e-08, "epoch": 2.9483194795807735, "percentage": 98.27, "elapsed_time": "11:42:03", "remaining_time": "0:12:23"}
+{"current_steps": 2045, "total_steps": 2076, "loss": 0.0041, "lr": 1.4478085561835387e-08, "epoch": 2.9555475243946514, "percentage": 98.51, "elapsed_time": "11:43:35", "remaining_time": "0:10:39"}
+{"current_steps": 2050, "total_steps": 2076, "loss": 0.0043, "lr": 1.0307869444406981e-08, "epoch": 2.962775569208529, "percentage": 98.75, "elapsed_time": "11:45:14", "remaining_time": "0:08:56"}
+{"current_steps": 2055, "total_steps": 2076, "loss": 0.0053, "lr": 6.844028709024342e-09, "epoch": 2.970003614022407, "percentage": 98.99, "elapsed_time": "11:46:47", "remaining_time": "0:07:13"}
+{"current_steps": 2060, "total_steps": 2076, "loss": 0.0043, "lr": 4.086808285338472e-09, "epoch": 2.977231658836285, "percentage": 99.23, "elapsed_time": "11:48:24", "remaining_time": "0:05:30"}
+{"current_steps": 2065, "total_steps": 2076, "loss": 0.0034, "lr": 2.0364031375819104e-09, "epoch": 2.9844597036501628, "percentage": 99.47, "elapsed_time": "11:49:46", "remaining_time": "0:03:46"}
+{"current_steps": 2070, "total_steps": 2076, "loss": 0.0055, "lr": 6.929582507719801e-10, "epoch": 2.9916877484640407, "percentage": 99.71, "elapsed_time": "11:51:16", "remaining_time": "0:02:03"}
+{"current_steps": 2075, "total_steps": 2076, "loss": 0.0047, "lr": 5.6568620471209035e-11, "epoch": 2.9989157932779182, "percentage": 99.95, "elapsed_time": "11:52:47", "remaining_time": "0:00:20"}
+{"current_steps": 2076, "total_steps": 2076, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "11:53:29", "remaining_time": "0:00:00"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:916e08054bd8e9396d6811d6bce8ada0998bfb7dd3fe3287853319e5c2d6147c
+size 7352