初始化项目,由ModelHub XC社区提供模型
Model: abdoul-rz/qwen3-4b-beauty-mix Source: Original Platform
This commit is contained in:
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -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
|
||||
61
README.md
Normal file
61
README.md
Normal file
@@ -0,0 +1,61 @@
|
||||
---
|
||||
library_name: transformers
|
||||
license: other
|
||||
base_model: Qwen/Qwen3-4B
|
||||
tags:
|
||||
- llama-factory
|
||||
- full
|
||||
- generated_from_trainer
|
||||
model-index:
|
||||
- name: beauty-mix
|
||||
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. -->
|
||||
|
||||
# beauty-mix
|
||||
|
||||
This model is a fine-tuned version of [Qwen/Qwen3-4B](https://huggingface.co/Qwen/Qwen3-4B) on the beauty-mix dataset.
|
||||
|
||||
## Model description
|
||||
|
||||
More information needed
|
||||
|
||||
## Intended uses & limitations
|
||||
|
||||
More information needed
|
||||
|
||||
## Training and evaluation data
|
||||
|
||||
More information needed
|
||||
|
||||
## Training procedure
|
||||
|
||||
### Training hyperparameters
|
||||
|
||||
The following hyperparameters were used during training:
|
||||
- learning_rate: 5e-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 OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
||||
- lr_scheduler_type: cosine
|
||||
- lr_scheduler_warmup_ratio: 0.1
|
||||
- num_epochs: 1.0
|
||||
|
||||
### Training results
|
||||
|
||||
|
||||
|
||||
### Framework versions
|
||||
|
||||
- Transformers 4.57.1
|
||||
- Pytorch 2.9.1+cu128
|
||||
- Datasets 4.0.0
|
||||
- Tokenizers 0.22.2
|
||||
1308
added_tokens.json
Normal file
1308
added_tokens.json
Normal file
File diff suppressed because it is too large
Load Diff
8
all_results.json
Normal file
8
all_results.json
Normal file
@@ -0,0 +1,8 @@
|
||||
{
|
||||
"epoch": 1.0,
|
||||
"total_flos": 1.7136144572775137e+19,
|
||||
"train_loss": 0.7275813773740559,
|
||||
"train_runtime": 21314.9758,
|
||||
"train_samples_per_second": 58.741,
|
||||
"train_steps_per_second": 0.459
|
||||
}
|
||||
61
chat_template.jinja
Normal file
61
chat_template.jinja
Normal file
@@ -0,0 +1,61 @@
|
||||
{%- if tools %}
|
||||
{{- '<|im_start|>system\n' }}
|
||||
{%- if messages[0].role == 'system' %}
|
||||
{{- messages[0].content + '\n\n' }}
|
||||
{%- endif %}
|
||||
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
||||
{%- for tool in tools %}
|
||||
{{- "\n" }}
|
||||
{{- tool | tojson }}
|
||||
{%- endfor %}
|
||||
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
||||
{%- else %}
|
||||
{%- if messages[0].role == 'system' %}
|
||||
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- for message in messages %}
|
||||
{%- if message.content is string %}
|
||||
{%- set content = message.content %}
|
||||
{%- else %}
|
||||
{%- set content = '' %}
|
||||
{%- endif %}
|
||||
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
||||
{%- elif message.role == "assistant" %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||
{%- if message.tool_calls %}
|
||||
{%- for tool_call in message.tool_calls %}
|
||||
{%- if (loop.first and content) or (not loop.first) %}
|
||||
{{- '\n' }}
|
||||
{%- endif %}
|
||||
{%- if tool_call.function %}
|
||||
{%- set tool_call = tool_call.function %}
|
||||
{%- endif %}
|
||||
{{- '<tool_call>\n{"name": "' }}
|
||||
{{- tool_call.name }}
|
||||
{{- '", "arguments": ' }}
|
||||
{%- if tool_call.arguments is string %}
|
||||
{{- tool_call.arguments }}
|
||||
{%- else %}
|
||||
{{- tool_call.arguments | tojson }}
|
||||
{%- endif %}
|
||||
{{- '}\n</tool_call>' }}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- elif message.role == "tool" %}
|
||||
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
||||
{{- '<|im_start|>user' }}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_response>\n' }}
|
||||
{{- content }}
|
||||
{{- '\n</tool_response>' }}
|
||||
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- if add_generation_prompt %}
|
||||
{{- '<|im_start|>assistant\n' }}
|
||||
{%- endif %}
|
||||
68
config.json
Normal file
68
config.json
Normal file
@@ -0,0 +1,68 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen3ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 151645,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 2560,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 9728,
|
||||
"layer_types": [
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention"
|
||||
],
|
||||
"max_position_embeddings": 262144,
|
||||
"max_window_layers": 36,
|
||||
"model_type": "qwen3",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 36,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 151643,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 5000000,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": true,
|
||||
"transformers_version": "4.57.1",
|
||||
"use_cache": false,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 152949
|
||||
}
|
||||
12
generation_config.json
Normal file
12
generation_config.json
Normal file
@@ -0,0 +1,12 @@
|
||||
{
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"pad_token_id": 151643,
|
||||
"temperature": 0.7,
|
||||
"top_k": 20,
|
||||
"top_p": 0.8,
|
||||
"transformers_version": "4.57.1"
|
||||
}
|
||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model-00001-of-00002.safetensors
Normal file
3
model-00001-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:aa69762e7daa94a8ce33b260d988af9ba2980adae9429519d253fc4217b13c93
|
||||
size 4972401920
|
||||
3
model-00002-of-00002.safetensors
Normal file
3
model-00002-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3393804ab1512b1c40780e041a4c821824353a5b717f2f7c19ed904e4bef18ba
|
||||
size 3860865704
|
||||
407
model.safetensors.index.json
Normal file
407
model.safetensors.index.json
Normal file
@@ -0,0 +1,407 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_parameters": 4025061376,
|
||||
"total_size": 8833221632
|
||||
},
|
||||
"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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.weight": "model-00001-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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.29.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_norm.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_norm.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.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00002-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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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_norm.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"
|
||||
}
|
||||
}
|
||||
1298
special_tokens_map.json
Normal file
1298
special_tokens_map.json
Normal file
File diff suppressed because it is too large
Load Diff
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3bcd0ab896130d768fa805cf9a6ffeacac3cbb78921e1b68a664da7735314452
|
||||
size 11660194
|
||||
11747
tokenizer_config.json
Normal file
11747
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
8
train_results.json
Normal file
8
train_results.json
Normal file
@@ -0,0 +1,8 @@
|
||||
{
|
||||
"epoch": 1.0,
|
||||
"total_flos": 1.7136144572775137e+19,
|
||||
"train_loss": 0.7275813773740559,
|
||||
"train_runtime": 21314.9758,
|
||||
"train_samples_per_second": 58.741,
|
||||
"train_steps_per_second": 0.459
|
||||
}
|
||||
979
trainer_log.jsonl
Normal file
979
trainer_log.jsonl
Normal file
@@ -0,0 +1,979 @@
|
||||
{"current_steps": 10, "total_steps": 9782, "loss": 5.7729, "lr": 4.596527068437181e-07, "epoch": 0.0010223119584941345, "percentage": 0.1, "elapsed_time": "0:00:14", "remaining_time": "4:03:49"}
|
||||
{"current_steps": 20, "total_steps": 9782, "loss": 5.4769, "lr": 9.703779366700715e-07, "epoch": 0.002044623916988269, "percentage": 0.2, "elapsed_time": "0:00:28", "remaining_time": "3:50:55"}
|
||||
{"current_steps": 30, "total_steps": 9782, "loss": 4.1936, "lr": 1.481103166496425e-06, "epoch": 0.0030669358754824034, "percentage": 0.31, "elapsed_time": "0:00:42", "remaining_time": "3:51:03"}
|
||||
{"current_steps": 40, "total_steps": 9782, "loss": 3.9063, "lr": 1.9918283963227787e-06, "epoch": 0.004089247833976538, "percentage": 0.41, "elapsed_time": "0:00:55", "remaining_time": "3:46:58"}
|
||||
{"current_steps": 50, "total_steps": 9782, "loss": 3.3878, "lr": 2.502553626149132e-06, "epoch": 0.005111559792470672, "percentage": 0.51, "elapsed_time": "0:01:09", "remaining_time": "3:45:50"}
|
||||
{"current_steps": 60, "total_steps": 9782, "loss": 3.1355, "lr": 3.013278855975485e-06, "epoch": 0.006133871750964807, "percentage": 0.61, "elapsed_time": "0:01:23", "remaining_time": "3:46:03"}
|
||||
{"current_steps": 70, "total_steps": 9782, "loss": 2.9229, "lr": 3.5240040858018386e-06, "epoch": 0.007156183709458941, "percentage": 0.72, "elapsed_time": "0:01:37", "remaining_time": "3:44:44"}
|
||||
{"current_steps": 80, "total_steps": 9782, "loss": 2.7581, "lr": 4.034729315628192e-06, "epoch": 0.008178495667953076, "percentage": 0.82, "elapsed_time": "0:01:51", "remaining_time": "3:45:16"}
|
||||
{"current_steps": 90, "total_steps": 9782, "loss": 2.9603, "lr": 4.5454545454545455e-06, "epoch": 0.00920080762644721, "percentage": 0.92, "elapsed_time": "0:02:05", "remaining_time": "3:46:04"}
|
||||
{"current_steps": 100, "total_steps": 9782, "loss": 2.8967, "lr": 5.056179775280899e-06, "epoch": 0.010223119584941345, "percentage": 1.02, "elapsed_time": "0:02:19", "remaining_time": "3:45:46"}
|
||||
{"current_steps": 110, "total_steps": 9782, "loss": 2.8365, "lr": 5.5669050051072524e-06, "epoch": 0.011245431543435479, "percentage": 1.12, "elapsed_time": "0:02:33", "remaining_time": "3:45:08"}
|
||||
{"current_steps": 120, "total_steps": 9782, "loss": 2.529, "lr": 6.077630234933606e-06, "epoch": 0.012267743501929614, "percentage": 1.23, "elapsed_time": "0:02:48", "remaining_time": "3:46:39"}
|
||||
{"current_steps": 130, "total_steps": 9782, "loss": 2.5749, "lr": 6.58835546475996e-06, "epoch": 0.013290055460423748, "percentage": 1.33, "elapsed_time": "0:03:03", "remaining_time": "3:46:40"}
|
||||
{"current_steps": 140, "total_steps": 9782, "loss": 2.4756, "lr": 7.099080694586313e-06, "epoch": 0.014312367418917882, "percentage": 1.43, "elapsed_time": "0:03:18", "remaining_time": "3:47:56"}
|
||||
{"current_steps": 150, "total_steps": 9782, "loss": 2.5418, "lr": 7.609805924412666e-06, "epoch": 0.015334679377412017, "percentage": 1.53, "elapsed_time": "0:03:32", "remaining_time": "3:47:47"}
|
||||
{"current_steps": 160, "total_steps": 9782, "loss": 2.4251, "lr": 8.120531154239019e-06, "epoch": 0.01635699133590615, "percentage": 1.64, "elapsed_time": "0:03:48", "remaining_time": "3:48:31"}
|
||||
{"current_steps": 170, "total_steps": 9782, "loss": 2.3459, "lr": 8.631256384065373e-06, "epoch": 0.017379303294400288, "percentage": 1.74, "elapsed_time": "0:04:03", "remaining_time": "3:49:01"}
|
||||
{"current_steps": 180, "total_steps": 9782, "loss": 2.1922, "lr": 9.141981613891727e-06, "epoch": 0.01840161525289442, "percentage": 1.84, "elapsed_time": "0:04:18", "remaining_time": "3:49:31"}
|
||||
{"current_steps": 190, "total_steps": 9782, "loss": 2.1388, "lr": 9.65270684371808e-06, "epoch": 0.019423927211388557, "percentage": 1.94, "elapsed_time": "0:04:33", "remaining_time": "3:49:44"}
|
||||
{"current_steps": 200, "total_steps": 9782, "loss": 2.1335, "lr": 1.0163432073544434e-05, "epoch": 0.02044623916988269, "percentage": 2.04, "elapsed_time": "0:04:48", "remaining_time": "3:50:43"}
|
||||
{"current_steps": 210, "total_steps": 9782, "loss": 2.0611, "lr": 1.0674157303370787e-05, "epoch": 0.021468551128376825, "percentage": 2.15, "elapsed_time": "0:05:03", "remaining_time": "3:50:53"}
|
||||
{"current_steps": 220, "total_steps": 9782, "loss": 2.0277, "lr": 1.118488253319714e-05, "epoch": 0.022490863086870958, "percentage": 2.25, "elapsed_time": "0:05:19", "remaining_time": "3:51:11"}
|
||||
{"current_steps": 230, "total_steps": 9782, "loss": 2.083, "lr": 1.1695607763023494e-05, "epoch": 0.023513175045365094, "percentage": 2.35, "elapsed_time": "0:05:34", "remaining_time": "3:51:28"}
|
||||
{"current_steps": 240, "total_steps": 9782, "loss": 1.9243, "lr": 1.2206332992849848e-05, "epoch": 0.024535487003859227, "percentage": 2.45, "elapsed_time": "0:05:50", "remaining_time": "3:52:07"}
|
||||
{"current_steps": 250, "total_steps": 9782, "loss": 1.9579, "lr": 1.27170582226762e-05, "epoch": 0.025557798962353363, "percentage": 2.56, "elapsed_time": "0:06:05", "remaining_time": "3:52:18"}
|
||||
{"current_steps": 260, "total_steps": 9782, "loss": 1.926, "lr": 1.3227783452502553e-05, "epoch": 0.026580110920847496, "percentage": 2.66, "elapsed_time": "0:06:23", "remaining_time": "3:53:59"}
|
||||
{"current_steps": 270, "total_steps": 9782, "loss": 1.855, "lr": 1.3738508682328908e-05, "epoch": 0.027602422879341632, "percentage": 2.76, "elapsed_time": "0:06:39", "remaining_time": "3:54:28"}
|
||||
{"current_steps": 280, "total_steps": 9782, "loss": 1.8568, "lr": 1.424923391215526e-05, "epoch": 0.028624734837835765, "percentage": 2.86, "elapsed_time": "0:06:56", "remaining_time": "3:55:26"}
|
||||
{"current_steps": 290, "total_steps": 9782, "loss": 1.8934, "lr": 1.4759959141981613e-05, "epoch": 0.0296470467963299, "percentage": 2.96, "elapsed_time": "0:07:12", "remaining_time": "3:55:52"}
|
||||
{"current_steps": 300, "total_steps": 9782, "loss": 1.8093, "lr": 1.5270684371807967e-05, "epoch": 0.030669358754824034, "percentage": 3.07, "elapsed_time": "0:07:28", "remaining_time": "3:56:18"}
|
||||
{"current_steps": 310, "total_steps": 9782, "loss": 1.8581, "lr": 1.578140960163432e-05, "epoch": 0.03169167071331817, "percentage": 3.17, "elapsed_time": "0:07:44", "remaining_time": "3:56:25"}
|
||||
{"current_steps": 320, "total_steps": 9782, "loss": 1.8639, "lr": 1.6292134831460676e-05, "epoch": 0.0327139826718123, "percentage": 3.27, "elapsed_time": "0:08:00", "remaining_time": "3:56:41"}
|
||||
{"current_steps": 330, "total_steps": 9782, "loss": 1.8074, "lr": 1.680286006128703e-05, "epoch": 0.03373629463030644, "percentage": 3.37, "elapsed_time": "0:08:16", "remaining_time": "3:57:02"}
|
||||
{"current_steps": 340, "total_steps": 9782, "loss": 1.7677, "lr": 1.731358529111338e-05, "epoch": 0.034758606588800575, "percentage": 3.48, "elapsed_time": "0:08:34", "remaining_time": "3:57:59"}
|
||||
{"current_steps": 350, "total_steps": 9782, "loss": 1.8268, "lr": 1.7824310520939735e-05, "epoch": 0.035780918547294704, "percentage": 3.58, "elapsed_time": "0:08:51", "remaining_time": "3:58:30"}
|
||||
{"current_steps": 360, "total_steps": 9782, "loss": 1.8369, "lr": 1.833503575076609e-05, "epoch": 0.03680323050578884, "percentage": 3.68, "elapsed_time": "0:09:06", "remaining_time": "3:58:33"}
|
||||
{"current_steps": 370, "total_steps": 9782, "loss": 1.6866, "lr": 1.884576098059244e-05, "epoch": 0.03782554246428298, "percentage": 3.78, "elapsed_time": "0:09:25", "remaining_time": "3:59:34"}
|
||||
{"current_steps": 380, "total_steps": 9782, "loss": 1.6996, "lr": 1.9356486210418795e-05, "epoch": 0.03884785442277711, "percentage": 3.88, "elapsed_time": "0:09:42", "remaining_time": "4:00:03"}
|
||||
{"current_steps": 390, "total_steps": 9782, "loss": 1.7623, "lr": 1.986721144024515e-05, "epoch": 0.03987016638127124, "percentage": 3.99, "elapsed_time": "0:09:58", "remaining_time": "4:00:13"}
|
||||
{"current_steps": 400, "total_steps": 9782, "loss": 1.7848, "lr": 2.03779366700715e-05, "epoch": 0.04089247833976538, "percentage": 4.09, "elapsed_time": "0:10:15", "remaining_time": "4:00:32"}
|
||||
{"current_steps": 410, "total_steps": 9782, "loss": 1.7764, "lr": 2.0888661899897858e-05, "epoch": 0.041914790298259515, "percentage": 4.19, "elapsed_time": "0:10:31", "remaining_time": "4:00:44"}
|
||||
{"current_steps": 420, "total_steps": 9782, "loss": 1.7455, "lr": 2.139938712972421e-05, "epoch": 0.04293710225675365, "percentage": 4.29, "elapsed_time": "0:10:49", "remaining_time": "4:01:11"}
|
||||
{"current_steps": 430, "total_steps": 9782, "loss": 1.7515, "lr": 2.1910112359550563e-05, "epoch": 0.04395941421524778, "percentage": 4.4, "elapsed_time": "0:11:04", "remaining_time": "4:00:59"}
|
||||
{"current_steps": 440, "total_steps": 9782, "loss": 1.7321, "lr": 2.2420837589376917e-05, "epoch": 0.044981726173741916, "percentage": 4.5, "elapsed_time": "0:11:22", "remaining_time": "4:01:21"}
|
||||
{"current_steps": 450, "total_steps": 9782, "loss": 1.7107, "lr": 2.2931562819203268e-05, "epoch": 0.04600403813223605, "percentage": 4.6, "elapsed_time": "0:11:38", "remaining_time": "4:01:30"}
|
||||
{"current_steps": 460, "total_steps": 9782, "loss": 1.7197, "lr": 2.3442288049029623e-05, "epoch": 0.04702635009073019, "percentage": 4.7, "elapsed_time": "0:11:55", "remaining_time": "4:01:31"}
|
||||
{"current_steps": 470, "total_steps": 9782, "loss": 1.6227, "lr": 2.3953013278855977e-05, "epoch": 0.04804866204922432, "percentage": 4.8, "elapsed_time": "0:12:12", "remaining_time": "4:01:59"}
|
||||
{"current_steps": 480, "total_steps": 9782, "loss": 1.573, "lr": 2.446373850868233e-05, "epoch": 0.049070974007718454, "percentage": 4.91, "elapsed_time": "0:12:31", "remaining_time": "4:02:42"}
|
||||
{"current_steps": 490, "total_steps": 9782, "loss": 1.581, "lr": 2.4974463738508682e-05, "epoch": 0.05009328596621259, "percentage": 5.01, "elapsed_time": "0:12:49", "remaining_time": "4:03:08"}
|
||||
{"current_steps": 500, "total_steps": 9782, "loss": 1.5403, "lr": 2.548518896833504e-05, "epoch": 0.05111559792470673, "percentage": 5.11, "elapsed_time": "0:13:06", "remaining_time": "4:03:26"}
|
||||
{"current_steps": 510, "total_steps": 9782, "loss": 1.5419, "lr": 2.599591419816139e-05, "epoch": 0.052137909883200856, "percentage": 5.21, "elapsed_time": "0:13:23", "remaining_time": "4:03:31"}
|
||||
{"current_steps": 520, "total_steps": 9782, "loss": 1.544, "lr": 2.6506639427987745e-05, "epoch": 0.05316022184169499, "percentage": 5.32, "elapsed_time": "0:13:40", "remaining_time": "4:03:39"}
|
||||
{"current_steps": 530, "total_steps": 9782, "loss": 1.4898, "lr": 2.70173646578141e-05, "epoch": 0.05418253380018913, "percentage": 5.42, "elapsed_time": "0:13:58", "remaining_time": "4:03:55"}
|
||||
{"current_steps": 540, "total_steps": 9782, "loss": 1.4654, "lr": 2.752808988764045e-05, "epoch": 0.055204845758683264, "percentage": 5.52, "elapsed_time": "0:14:15", "remaining_time": "4:04:09"}
|
||||
{"current_steps": 550, "total_steps": 9782, "loss": 1.3641, "lr": 2.8038815117466805e-05, "epoch": 0.056227157717177394, "percentage": 5.62, "elapsed_time": "0:14:34", "remaining_time": "4:04:30"}
|
||||
{"current_steps": 560, "total_steps": 9782, "loss": 1.3263, "lr": 2.854954034729316e-05, "epoch": 0.05724946967567153, "percentage": 5.72, "elapsed_time": "0:14:53", "remaining_time": "4:05:08"}
|
||||
{"current_steps": 570, "total_steps": 9782, "loss": 1.3474, "lr": 2.906026557711951e-05, "epoch": 0.058271781634165666, "percentage": 5.83, "elapsed_time": "0:15:10", "remaining_time": "4:05:15"}
|
||||
{"current_steps": 580, "total_steps": 9782, "loss": 1.3702, "lr": 2.9570990806945864e-05, "epoch": 0.0592940935926598, "percentage": 5.93, "elapsed_time": "0:15:26", "remaining_time": "4:05:05"}
|
||||
{"current_steps": 590, "total_steps": 9782, "loss": 1.3567, "lr": 3.008171603677222e-05, "epoch": 0.06031640555115393, "percentage": 6.03, "elapsed_time": "0:15:43", "remaining_time": "4:04:55"}
|
||||
{"current_steps": 600, "total_steps": 9782, "loss": 1.2809, "lr": 3.059244126659857e-05, "epoch": 0.06133871750964807, "percentage": 6.13, "elapsed_time": "0:16:01", "remaining_time": "4:05:08"}
|
||||
{"current_steps": 610, "total_steps": 9782, "loss": 1.2442, "lr": 3.110316649642493e-05, "epoch": 0.062361029468142204, "percentage": 6.24, "elapsed_time": "0:16:19", "remaining_time": "4:05:32"}
|
||||
{"current_steps": 620, "total_steps": 9782, "loss": 1.2309, "lr": 3.1613891726251275e-05, "epoch": 0.06338334142663633, "percentage": 6.34, "elapsed_time": "0:16:38", "remaining_time": "4:05:59"}
|
||||
{"current_steps": 630, "total_steps": 9782, "loss": 1.1752, "lr": 3.212461695607763e-05, "epoch": 0.06440565338513048, "percentage": 6.44, "elapsed_time": "0:16:58", "remaining_time": "4:06:29"}
|
||||
{"current_steps": 640, "total_steps": 9782, "loss": 1.2686, "lr": 3.263534218590398e-05, "epoch": 0.0654279653436246, "percentage": 6.54, "elapsed_time": "0:17:15", "remaining_time": "4:06:28"}
|
||||
{"current_steps": 650, "total_steps": 9782, "loss": 1.2698, "lr": 3.314606741573034e-05, "epoch": 0.06645027730211873, "percentage": 6.64, "elapsed_time": "0:17:32", "remaining_time": "4:06:28"}
|
||||
{"current_steps": 660, "total_steps": 9782, "loss": 1.1724, "lr": 3.365679264555669e-05, "epoch": 0.06747258926061288, "percentage": 6.75, "elapsed_time": "0:17:50", "remaining_time": "4:06:38"}
|
||||
{"current_steps": 670, "total_steps": 9782, "loss": 1.3131, "lr": 3.4167517875383046e-05, "epoch": 0.06849490121910701, "percentage": 6.85, "elapsed_time": "0:18:09", "remaining_time": "4:06:52"}
|
||||
{"current_steps": 680, "total_steps": 9782, "loss": 1.1841, "lr": 3.46782431052094e-05, "epoch": 0.06951721317760115, "percentage": 6.95, "elapsed_time": "0:18:28", "remaining_time": "4:07:10"}
|
||||
{"current_steps": 690, "total_steps": 9782, "loss": 1.2088, "lr": 3.5188968335035755e-05, "epoch": 0.07053952513609528, "percentage": 7.05, "elapsed_time": "0:18:46", "remaining_time": "4:07:23"}
|
||||
{"current_steps": 700, "total_steps": 9782, "loss": 1.1739, "lr": 3.569969356486211e-05, "epoch": 0.07156183709458941, "percentage": 7.16, "elapsed_time": "0:19:03", "remaining_time": "4:07:17"}
|
||||
{"current_steps": 710, "total_steps": 9782, "loss": 1.2373, "lr": 3.621041879468846e-05, "epoch": 0.07258414905308355, "percentage": 7.26, "elapsed_time": "0:19:21", "remaining_time": "4:07:15"}
|
||||
{"current_steps": 720, "total_steps": 9782, "loss": 1.1339, "lr": 3.672114402451481e-05, "epoch": 0.07360646101157768, "percentage": 7.36, "elapsed_time": "0:19:39", "remaining_time": "4:07:31"}
|
||||
{"current_steps": 730, "total_steps": 9782, "loss": 1.1807, "lr": 3.7231869254341165e-05, "epoch": 0.07462877297007181, "percentage": 7.46, "elapsed_time": "0:19:58", "remaining_time": "4:07:39"}
|
||||
{"current_steps": 740, "total_steps": 9782, "loss": 1.1803, "lr": 3.774259448416752e-05, "epoch": 0.07565108492856595, "percentage": 7.56, "elapsed_time": "0:20:16", "remaining_time": "4:07:40"}
|
||||
{"current_steps": 750, "total_steps": 9782, "loss": 1.1964, "lr": 3.8253319713993874e-05, "epoch": 0.07667339688706008, "percentage": 7.67, "elapsed_time": "0:20:33", "remaining_time": "4:07:36"}
|
||||
{"current_steps": 760, "total_steps": 9782, "loss": 1.1366, "lr": 3.876404494382023e-05, "epoch": 0.07769570884555423, "percentage": 7.77, "elapsed_time": "0:20:51", "remaining_time": "4:07:40"}
|
||||
{"current_steps": 770, "total_steps": 9782, "loss": 1.2463, "lr": 3.927477017364658e-05, "epoch": 0.07871802080404836, "percentage": 7.87, "elapsed_time": "0:21:09", "remaining_time": "4:07:35"}
|
||||
{"current_steps": 780, "total_steps": 9782, "loss": 1.2779, "lr": 3.978549540347294e-05, "epoch": 0.07974033276254248, "percentage": 7.97, "elapsed_time": "0:21:26", "remaining_time": "4:07:24"}
|
||||
{"current_steps": 790, "total_steps": 9782, "loss": 1.1991, "lr": 4.0296220633299284e-05, "epoch": 0.08076264472103663, "percentage": 8.08, "elapsed_time": "0:21:44", "remaining_time": "4:07:29"}
|
||||
{"current_steps": 800, "total_steps": 9782, "loss": 1.1226, "lr": 4.080694586312564e-05, "epoch": 0.08178495667953076, "percentage": 8.18, "elapsed_time": "0:22:03", "remaining_time": "4:07:43"}
|
||||
{"current_steps": 810, "total_steps": 9782, "loss": 1.0991, "lr": 4.131767109295199e-05, "epoch": 0.0828072686380249, "percentage": 8.28, "elapsed_time": "0:22:22", "remaining_time": "4:07:48"}
|
||||
{"current_steps": 820, "total_steps": 9782, "loss": 1.1443, "lr": 4.182839632277835e-05, "epoch": 0.08382958059651903, "percentage": 8.38, "elapsed_time": "0:22:40", "remaining_time": "4:07:48"}
|
||||
{"current_steps": 830, "total_steps": 9782, "loss": 1.1085, "lr": 4.23391215526047e-05, "epoch": 0.08485189255501316, "percentage": 8.48, "elapsed_time": "0:22:59", "remaining_time": "4:07:53"}
|
||||
{"current_steps": 840, "total_steps": 9782, "loss": 1.1038, "lr": 4.2849846782431056e-05, "epoch": 0.0858742045135073, "percentage": 8.59, "elapsed_time": "0:23:18", "remaining_time": "4:08:12"}
|
||||
{"current_steps": 850, "total_steps": 9782, "loss": 1.0814, "lr": 4.33605720122574e-05, "epoch": 0.08689651647200143, "percentage": 8.69, "elapsed_time": "0:23:38", "remaining_time": "4:08:21"}
|
||||
{"current_steps": 860, "total_steps": 9782, "loss": 1.1028, "lr": 4.387129724208376e-05, "epoch": 0.08791882843049556, "percentage": 8.79, "elapsed_time": "0:23:55", "remaining_time": "4:08:15"}
|
||||
{"current_steps": 870, "total_steps": 9782, "loss": 1.0584, "lr": 4.438202247191011e-05, "epoch": 0.0889411403889897, "percentage": 8.89, "elapsed_time": "0:24:15", "remaining_time": "4:08:25"}
|
||||
{"current_steps": 880, "total_steps": 9782, "loss": 1.1062, "lr": 4.489274770173647e-05, "epoch": 0.08996345234748383, "percentage": 9.0, "elapsed_time": "0:24:32", "remaining_time": "4:08:18"}
|
||||
{"current_steps": 890, "total_steps": 9782, "loss": 1.0567, "lr": 4.540347293156282e-05, "epoch": 0.09098576430597798, "percentage": 9.1, "elapsed_time": "0:24:53", "remaining_time": "4:08:38"}
|
||||
{"current_steps": 900, "total_steps": 9782, "loss": 1.0518, "lr": 4.5914198161389175e-05, "epoch": 0.0920080762644721, "percentage": 9.2, "elapsed_time": "0:25:13", "remaining_time": "4:08:59"}
|
||||
{"current_steps": 910, "total_steps": 9782, "loss": 1.0511, "lr": 4.642492339121553e-05, "epoch": 0.09303038822296623, "percentage": 9.3, "elapsed_time": "0:25:32", "remaining_time": "4:09:01"}
|
||||
{"current_steps": 920, "total_steps": 9782, "loss": 1.0845, "lr": 4.693564862104188e-05, "epoch": 0.09405270018146038, "percentage": 9.41, "elapsed_time": "0:25:51", "remaining_time": "4:09:01"}
|
||||
{"current_steps": 930, "total_steps": 9782, "loss": 1.0651, "lr": 4.744637385086824e-05, "epoch": 0.0950750121399545, "percentage": 9.51, "elapsed_time": "0:26:09", "remaining_time": "4:08:57"}
|
||||
{"current_steps": 940, "total_steps": 9782, "loss": 1.0411, "lr": 4.795709908069459e-05, "epoch": 0.09609732409844864, "percentage": 9.61, "elapsed_time": "0:26:28", "remaining_time": "4:09:05"}
|
||||
{"current_steps": 950, "total_steps": 9782, "loss": 1.062, "lr": 4.846782431052094e-05, "epoch": 0.09711963605694278, "percentage": 9.71, "elapsed_time": "0:26:49", "remaining_time": "4:09:21"}
|
||||
{"current_steps": 960, "total_steps": 9782, "loss": 1.0559, "lr": 4.8978549540347294e-05, "epoch": 0.09814194801543691, "percentage": 9.81, "elapsed_time": "0:27:09", "remaining_time": "4:09:30"}
|
||||
{"current_steps": 970, "total_steps": 9782, "loss": 1.0672, "lr": 4.948927477017365e-05, "epoch": 0.09916425997393105, "percentage": 9.92, "elapsed_time": "0:27:28", "remaining_time": "4:09:40"}
|
||||
{"current_steps": 980, "total_steps": 9782, "loss": 1.028, "lr": 5e-05, "epoch": 0.10018657193242518, "percentage": 10.02, "elapsed_time": "0:27:49", "remaining_time": "4:09:57"}
|
||||
{"current_steps": 990, "total_steps": 9782, "loss": 1.0349, "lr": 4.9999840798229326e-05, "epoch": 0.10120888389091931, "percentage": 10.12, "elapsed_time": "0:28:10", "remaining_time": "4:10:11"}
|
||||
{"current_steps": 1000, "total_steps": 9782, "loss": 1.0208, "lr": 4.999936319494492e-05, "epoch": 0.10223119584941345, "percentage": 10.22, "elapsed_time": "0:28:31", "remaining_time": "4:10:31"}
|
||||
{"current_steps": 1010, "total_steps": 9782, "loss": 1.0962, "lr": 4.9998567196229584e-05, "epoch": 0.10325350780790758, "percentage": 10.33, "elapsed_time": "0:28:50", "remaining_time": "4:10:27"}
|
||||
{"current_steps": 1020, "total_steps": 9782, "loss": 1.0357, "lr": 4.999745281222129e-05, "epoch": 0.10427581976640171, "percentage": 10.43, "elapsed_time": "0:29:10", "remaining_time": "4:10:34"}
|
||||
{"current_steps": 1030, "total_steps": 9782, "loss": 1.041, "lr": 4.9996020057112994e-05, "epoch": 0.10529813172489585, "percentage": 10.53, "elapsed_time": "0:29:29", "remaining_time": "4:10:33"}
|
||||
{"current_steps": 1040, "total_steps": 9782, "loss": 1.0324, "lr": 4.999426894915245e-05, "epoch": 0.10632044368338998, "percentage": 10.63, "elapsed_time": "0:29:50", "remaining_time": "4:10:46"}
|
||||
{"current_steps": 1050, "total_steps": 9782, "loss": 1.0059, "lr": 4.9992199510642035e-05, "epoch": 0.10734275564188413, "percentage": 10.73, "elapsed_time": "0:30:10", "remaining_time": "4:10:54"}
|
||||
{"current_steps": 1060, "total_steps": 9782, "loss": 1.0207, "lr": 4.99898117679384e-05, "epoch": 0.10836506760037826, "percentage": 10.84, "elapsed_time": "0:30:30", "remaining_time": "4:10:58"}
|
||||
{"current_steps": 1070, "total_steps": 9782, "loss": 0.998, "lr": 4.998710575145218e-05, "epoch": 0.10938737955887239, "percentage": 10.94, "elapsed_time": "0:30:48", "remaining_time": "4:10:52"}
|
||||
{"current_steps": 1080, "total_steps": 9782, "loss": 1.004, "lr": 4.9984081495647586e-05, "epoch": 0.11040969151736653, "percentage": 11.04, "elapsed_time": "0:31:07", "remaining_time": "4:10:47"}
|
||||
{"current_steps": 1090, "total_steps": 9782, "loss": 0.9903, "lr": 4.998073903904196e-05, "epoch": 0.11143200347586066, "percentage": 11.14, "elapsed_time": "0:31:28", "remaining_time": "4:10:58"}
|
||||
{"current_steps": 1100, "total_steps": 9782, "loss": 0.9785, "lr": 4.99770784242053e-05, "epoch": 0.11245431543435479, "percentage": 11.25, "elapsed_time": "0:31:49", "remaining_time": "4:11:11"}
|
||||
{"current_steps": 1110, "total_steps": 9782, "loss": 0.9604, "lr": 4.997309969775973e-05, "epoch": 0.11347662739284893, "percentage": 11.35, "elapsed_time": "0:32:11", "remaining_time": "4:11:30"}
|
||||
{"current_steps": 1120, "total_steps": 9782, "loss": 0.9544, "lr": 4.996880291037886e-05, "epoch": 0.11449893935134306, "percentage": 11.45, "elapsed_time": "0:32:31", "remaining_time": "4:11:35"}
|
||||
{"current_steps": 1130, "total_steps": 9782, "loss": 0.96, "lr": 4.99641881167872e-05, "epoch": 0.1155212513098372, "percentage": 11.55, "elapsed_time": "0:32:51", "remaining_time": "4:11:37"}
|
||||
{"current_steps": 1140, "total_steps": 9782, "loss": 0.9925, "lr": 4.995925537575939e-05, "epoch": 0.11654356326833133, "percentage": 11.65, "elapsed_time": "0:33:11", "remaining_time": "4:11:35"}
|
||||
{"current_steps": 1150, "total_steps": 9782, "loss": 0.957, "lr": 4.9954004750119545e-05, "epoch": 0.11756587522682546, "percentage": 11.76, "elapsed_time": "0:33:31", "remaining_time": "4:11:39"}
|
||||
{"current_steps": 1160, "total_steps": 9782, "loss": 0.9667, "lr": 4.994843630674036e-05, "epoch": 0.1185881871853196, "percentage": 11.86, "elapsed_time": "0:33:53", "remaining_time": "4:11:57"}
|
||||
{"current_steps": 1170, "total_steps": 9782, "loss": 0.9849, "lr": 4.9942550116542316e-05, "epoch": 0.11961049914381373, "percentage": 11.96, "elapsed_time": "0:34:12", "remaining_time": "4:11:47"}
|
||||
{"current_steps": 1180, "total_steps": 9782, "loss": 0.9447, "lr": 4.993634625449278e-05, "epoch": 0.12063281110230786, "percentage": 12.06, "elapsed_time": "0:34:33", "remaining_time": "4:11:54"}
|
||||
{"current_steps": 1190, "total_steps": 9782, "loss": 0.9484, "lr": 4.992982479960501e-05, "epoch": 0.121655123060802, "percentage": 12.17, "elapsed_time": "0:34:54", "remaining_time": "4:12:03"}
|
||||
{"current_steps": 1200, "total_steps": 9782, "loss": 0.9355, "lr": 4.9922985834937176e-05, "epoch": 0.12267743501929614, "percentage": 12.27, "elapsed_time": "0:35:14", "remaining_time": "4:12:05"}
|
||||
{"current_steps": 1210, "total_steps": 9782, "loss": 0.9548, "lr": 4.99158294475913e-05, "epoch": 0.12369974697779028, "percentage": 12.37, "elapsed_time": "0:35:35", "remaining_time": "4:12:06"}
|
||||
{"current_steps": 1220, "total_steps": 9782, "loss": 0.9643, "lr": 4.990835572871215e-05, "epoch": 0.12472205893628441, "percentage": 12.47, "elapsed_time": "0:35:54", "remaining_time": "4:12:00"}
|
||||
{"current_steps": 1230, "total_steps": 9782, "loss": 0.9715, "lr": 4.990056477348607e-05, "epoch": 0.12574437089477855, "percentage": 12.57, "elapsed_time": "0:36:14", "remaining_time": "4:12:01"}
|
||||
{"current_steps": 1240, "total_steps": 9782, "loss": 0.958, "lr": 4.9892456681139766e-05, "epoch": 0.12676668285327267, "percentage": 12.68, "elapsed_time": "0:36:35", "remaining_time": "4:12:07"}
|
||||
{"current_steps": 1250, "total_steps": 9782, "loss": 0.9318, "lr": 4.9884031554939046e-05, "epoch": 0.1277889948117668, "percentage": 12.78, "elapsed_time": "0:36:57", "remaining_time": "4:12:12"}
|
||||
{"current_steps": 1260, "total_steps": 9782, "loss": 0.9508, "lr": 4.987528950218753e-05, "epoch": 0.12881130677026095, "percentage": 12.88, "elapsed_time": "0:37:18", "remaining_time": "4:12:17"}
|
||||
{"current_steps": 1270, "total_steps": 9782, "loss": 0.9465, "lr": 4.9866230634225205e-05, "epoch": 0.12983361872875507, "percentage": 12.98, "elapsed_time": "0:37:38", "remaining_time": "4:12:18"}
|
||||
{"current_steps": 1280, "total_steps": 9782, "loss": 0.9644, "lr": 4.985685506642713e-05, "epoch": 0.1308559306872492, "percentage": 13.09, "elapsed_time": "0:37:57", "remaining_time": "4:12:08"}
|
||||
{"current_steps": 1290, "total_steps": 9782, "loss": 0.9413, "lr": 4.984716291820185e-05, "epoch": 0.13187824264574335, "percentage": 13.19, "elapsed_time": "0:38:19", "remaining_time": "4:12:14"}
|
||||
{"current_steps": 1300, "total_steps": 9782, "loss": 0.9211, "lr": 4.983715431298994e-05, "epoch": 0.13290055460423747, "percentage": 13.29, "elapsed_time": "0:38:39", "remaining_time": "4:12:14"}
|
||||
{"current_steps": 1310, "total_steps": 9782, "loss": 0.9363, "lr": 4.982682937826242e-05, "epoch": 0.1339228665627316, "percentage": 13.39, "elapsed_time": "0:38:57", "remaining_time": "4:11:57"}
|
||||
{"current_steps": 1320, "total_steps": 9782, "loss": 0.9249, "lr": 4.98161882455191e-05, "epoch": 0.13494517852122576, "percentage": 13.49, "elapsed_time": "0:39:18", "remaining_time": "4:12:00"}
|
||||
{"current_steps": 1330, "total_steps": 9782, "loss": 0.917, "lr": 4.9805231050286984e-05, "epoch": 0.1359674904797199, "percentage": 13.6, "elapsed_time": "0:39:39", "remaining_time": "4:12:01"}
|
||||
{"current_steps": 1340, "total_steps": 9782, "loss": 0.9237, "lr": 4.979395793211844e-05, "epoch": 0.13698980243821401, "percentage": 13.7, "elapsed_time": "0:39:58", "remaining_time": "4:11:53"}
|
||||
{"current_steps": 1350, "total_steps": 9782, "loss": 0.9131, "lr": 4.978236903458951e-05, "epoch": 0.13801211439670816, "percentage": 13.8, "elapsed_time": "0:40:21", "remaining_time": "4:12:02"}
|
||||
{"current_steps": 1360, "total_steps": 9782, "loss": 0.9017, "lr": 4.977046450529802e-05, "epoch": 0.1390344263552023, "percentage": 13.9, "elapsed_time": "0:40:41", "remaining_time": "4:11:58"}
|
||||
{"current_steps": 1370, "total_steps": 9782, "loss": 0.9052, "lr": 4.975824449586176e-05, "epoch": 0.14005673831369642, "percentage": 14.01, "elapsed_time": "0:41:01", "remaining_time": "4:11:53"}
|
||||
{"current_steps": 1380, "total_steps": 9782, "loss": 0.9122, "lr": 4.9745709161916486e-05, "epoch": 0.14107905027219056, "percentage": 14.11, "elapsed_time": "0:41:21", "remaining_time": "4:11:48"}
|
||||
{"current_steps": 1390, "total_steps": 9782, "loss": 0.8869, "lr": 4.9732858663114005e-05, "epoch": 0.1421013622306847, "percentage": 14.21, "elapsed_time": "0:41:40", "remaining_time": "4:11:39"}
|
||||
{"current_steps": 1400, "total_steps": 9782, "loss": 0.895, "lr": 4.9719693163120065e-05, "epoch": 0.14312367418917882, "percentage": 14.31, "elapsed_time": "0:42:01", "remaining_time": "4:11:36"}
|
||||
{"current_steps": 1410, "total_steps": 9782, "loss": 0.9005, "lr": 4.9706212829612354e-05, "epoch": 0.14414598614767296, "percentage": 14.41, "elapsed_time": "0:42:22", "remaining_time": "4:11:36"}
|
||||
{"current_steps": 1420, "total_steps": 9782, "loss": 0.9035, "lr": 4.969241783427832e-05, "epoch": 0.1451682981061671, "percentage": 14.52, "elapsed_time": "0:42:42", "remaining_time": "4:11:28"}
|
||||
{"current_steps": 1430, "total_steps": 9782, "loss": 0.8931, "lr": 4.967830835281295e-05, "epoch": 0.14619061006466122, "percentage": 14.62, "elapsed_time": "0:43:03", "remaining_time": "4:11:26"}
|
||||
{"current_steps": 1440, "total_steps": 9782, "loss": 0.8974, "lr": 4.966388456491662e-05, "epoch": 0.14721292202315536, "percentage": 14.72, "elapsed_time": "0:43:23", "remaining_time": "4:11:24"}
|
||||
{"current_steps": 1450, "total_steps": 9782, "loss": 0.8968, "lr": 4.9649146654292726e-05, "epoch": 0.1482352339816495, "percentage": 14.82, "elapsed_time": "0:43:44", "remaining_time": "4:11:21"}
|
||||
{"current_steps": 1460, "total_steps": 9782, "loss": 0.8884, "lr": 4.963409480864539e-05, "epoch": 0.14925754594014362, "percentage": 14.93, "elapsed_time": "0:44:05", "remaining_time": "4:11:20"}
|
||||
{"current_steps": 1470, "total_steps": 9782, "loss": 0.8909, "lr": 4.961872921967705e-05, "epoch": 0.15027985789863776, "percentage": 15.03, "elapsed_time": "0:44:27", "remaining_time": "4:11:23"}
|
||||
{"current_steps": 1480, "total_steps": 9782, "loss": 0.8943, "lr": 4.960305008308603e-05, "epoch": 0.1513021698571319, "percentage": 15.13, "elapsed_time": "0:44:47", "remaining_time": "4:11:16"}
|
||||
{"current_steps": 1490, "total_steps": 9782, "loss": 0.8738, "lr": 4.958705759856402e-05, "epoch": 0.15232448181562605, "percentage": 15.23, "elapsed_time": "0:45:09", "remaining_time": "4:11:18"}
|
||||
{"current_steps": 1500, "total_steps": 9782, "loss": 0.8694, "lr": 4.957075196979357e-05, "epoch": 0.15334679377412017, "percentage": 15.33, "elapsed_time": "0:45:29", "remaining_time": "4:11:13"}
|
||||
{"current_steps": 1510, "total_steps": 9782, "loss": 0.8818, "lr": 4.955413340444549e-05, "epoch": 0.1543691057326143, "percentage": 15.44, "elapsed_time": "0:45:50", "remaining_time": "4:11:08"}
|
||||
{"current_steps": 1520, "total_steps": 9782, "loss": 0.8919, "lr": 4.953720211417618e-05, "epoch": 0.15539141769110845, "percentage": 15.54, "elapsed_time": "0:46:11", "remaining_time": "4:11:04"}
|
||||
{"current_steps": 1530, "total_steps": 9782, "loss": 0.8995, "lr": 4.9519958314624946e-05, "epoch": 0.15641372964960257, "percentage": 15.64, "elapsed_time": "0:46:30", "remaining_time": "4:10:51"}
|
||||
{"current_steps": 1540, "total_steps": 9782, "loss": 0.8765, "lr": 4.950240222541126e-05, "epoch": 0.1574360416080967, "percentage": 15.74, "elapsed_time": "0:46:51", "remaining_time": "4:10:45"}
|
||||
{"current_steps": 1550, "total_steps": 9782, "loss": 0.8499, "lr": 4.948453407013196e-05, "epoch": 0.15845835356659085, "percentage": 15.85, "elapsed_time": "0:47:13", "remaining_time": "4:10:46"}
|
||||
{"current_steps": 1560, "total_steps": 9782, "loss": 0.8548, "lr": 4.946635407635841e-05, "epoch": 0.15948066552508497, "percentage": 15.95, "elapsed_time": "0:47:34", "remaining_time": "4:10:43"}
|
||||
{"current_steps": 1570, "total_steps": 9782, "loss": 0.8672, "lr": 4.944786247563359e-05, "epoch": 0.1605029774835791, "percentage": 16.05, "elapsed_time": "0:47:56", "remaining_time": "4:10:43"}
|
||||
{"current_steps": 1580, "total_steps": 9782, "loss": 0.8623, "lr": 4.942905950346913e-05, "epoch": 0.16152528944207326, "percentage": 16.15, "elapsed_time": "0:48:17", "remaining_time": "4:10:39"}
|
||||
{"current_steps": 1590, "total_steps": 9782, "loss": 0.8593, "lr": 4.940994539934236e-05, "epoch": 0.16254760140056737, "percentage": 16.25, "elapsed_time": "0:48:39", "remaining_time": "4:10:42"}
|
||||
{"current_steps": 1600, "total_steps": 9782, "loss": 0.8537, "lr": 4.939052040669321e-05, "epoch": 0.16356991335906151, "percentage": 16.36, "elapsed_time": "0:48:59", "remaining_time": "4:10:33"}
|
||||
{"current_steps": 1610, "total_steps": 9782, "loss": 0.86, "lr": 4.9370784772921144e-05, "epoch": 0.16459222531755566, "percentage": 16.46, "elapsed_time": "0:49:20", "remaining_time": "4:10:28"}
|
||||
{"current_steps": 1620, "total_steps": 9782, "loss": 0.8699, "lr": 4.935073874938199e-05, "epoch": 0.1656145372760498, "percentage": 16.56, "elapsed_time": "0:49:40", "remaining_time": "4:10:18"}
|
||||
{"current_steps": 1630, "total_steps": 9782, "loss": 0.8693, "lr": 4.933038259138474e-05, "epoch": 0.16663684923454392, "percentage": 16.66, "elapsed_time": "0:50:01", "remaining_time": "4:10:09"}
|
||||
{"current_steps": 1640, "total_steps": 9782, "loss": 0.8659, "lr": 4.93097165581883e-05, "epoch": 0.16765916119303806, "percentage": 16.77, "elapsed_time": "0:50:22", "remaining_time": "4:10:03"}
|
||||
{"current_steps": 1650, "total_steps": 9782, "loss": 0.8549, "lr": 4.9288740912998204e-05, "epoch": 0.1686814731515322, "percentage": 16.87, "elapsed_time": "0:50:43", "remaining_time": "4:10:01"}
|
||||
{"current_steps": 1660, "total_steps": 9782, "loss": 0.8619, "lr": 4.926745592296324e-05, "epoch": 0.16970378511002632, "percentage": 16.97, "elapsed_time": "0:51:04", "remaining_time": "4:09:56"}
|
||||
{"current_steps": 1670, "total_steps": 9782, "loss": 0.8707, "lr": 4.924586185917206e-05, "epoch": 0.17072609706852046, "percentage": 17.07, "elapsed_time": "0:51:25", "remaining_time": "4:09:50"}
|
||||
{"current_steps": 1680, "total_steps": 9782, "loss": 0.8548, "lr": 4.922395899664971e-05, "epoch": 0.1717484090270146, "percentage": 17.17, "elapsed_time": "0:51:47", "remaining_time": "4:09:44"}
|
||||
{"current_steps": 1690, "total_steps": 9782, "loss": 0.8434, "lr": 4.920174761435416e-05, "epoch": 0.17277072098550872, "percentage": 17.28, "elapsed_time": "0:52:07", "remaining_time": "4:09:36"}
|
||||
{"current_steps": 1700, "total_steps": 9782, "loss": 0.8513, "lr": 4.917922799517271e-05, "epoch": 0.17379303294400286, "percentage": 17.38, "elapsed_time": "0:52:28", "remaining_time": "4:09:29"}
|
||||
{"current_steps": 1710, "total_steps": 9782, "loss": 0.8633, "lr": 4.915640042591842e-05, "epoch": 0.174815344902497, "percentage": 17.48, "elapsed_time": "0:52:49", "remaining_time": "4:09:20"}
|
||||
{"current_steps": 1720, "total_steps": 9782, "loss": 0.8498, "lr": 4.913326519732645e-05, "epoch": 0.17583765686099112, "percentage": 17.58, "elapsed_time": "0:53:10", "remaining_time": "4:09:14"}
|
||||
{"current_steps": 1730, "total_steps": 9782, "loss": 0.8496, "lr": 4.910982260405036e-05, "epoch": 0.17685996881948526, "percentage": 17.69, "elapsed_time": "0:53:31", "remaining_time": "4:09:06"}
|
||||
{"current_steps": 1740, "total_steps": 9782, "loss": 0.8552, "lr": 4.908607294465832e-05, "epoch": 0.1778822807779794, "percentage": 17.79, "elapsed_time": "0:53:52", "remaining_time": "4:08:58"}
|
||||
{"current_steps": 1750, "total_steps": 9782, "loss": 0.8437, "lr": 4.906201652162937e-05, "epoch": 0.17890459273647352, "percentage": 17.89, "elapsed_time": "0:54:13", "remaining_time": "4:08:52"}
|
||||
{"current_steps": 1760, "total_steps": 9782, "loss": 0.8414, "lr": 4.903765364134953e-05, "epoch": 0.17992690469496767, "percentage": 17.99, "elapsed_time": "0:54:35", "remaining_time": "4:08:50"}
|
||||
{"current_steps": 1770, "total_steps": 9782, "loss": 0.8326, "lr": 4.9012984614107855e-05, "epoch": 0.1809492166534618, "percentage": 18.09, "elapsed_time": "0:54:56", "remaining_time": "4:08:43"}
|
||||
{"current_steps": 1780, "total_steps": 9782, "loss": 0.8274, "lr": 4.89880097540926e-05, "epoch": 0.18197152861195595, "percentage": 18.2, "elapsed_time": "0:55:17", "remaining_time": "4:08:32"}
|
||||
{"current_steps": 1790, "total_steps": 9782, "loss": 0.8408, "lr": 4.896272937938713e-05, "epoch": 0.18299384057045007, "percentage": 18.3, "elapsed_time": "0:55:38", "remaining_time": "4:08:24"}
|
||||
{"current_steps": 1800, "total_steps": 9782, "loss": 0.8256, "lr": 4.8937143811965845e-05, "epoch": 0.1840161525289442, "percentage": 18.4, "elapsed_time": "0:56:00", "remaining_time": "4:08:20"}
|
||||
{"current_steps": 1810, "total_steps": 9782, "loss": 0.8373, "lr": 4.8911253377690194e-05, "epoch": 0.18503846448743835, "percentage": 18.5, "elapsed_time": "0:56:21", "remaining_time": "4:08:14"}
|
||||
{"current_steps": 1820, "total_steps": 9782, "loss": 0.838, "lr": 4.888505840630439e-05, "epoch": 0.18606077644593247, "percentage": 18.61, "elapsed_time": "0:56:44", "remaining_time": "4:08:11"}
|
||||
{"current_steps": 1830, "total_steps": 9782, "loss": 0.8294, "lr": 4.8858559231431297e-05, "epoch": 0.1870830884044266, "percentage": 18.71, "elapsed_time": "0:57:06", "remaining_time": "4:08:08"}
|
||||
{"current_steps": 1840, "total_steps": 9782, "loss": 0.8239, "lr": 4.883175619056817e-05, "epoch": 0.18810540036292075, "percentage": 18.81, "elapsed_time": "0:57:27", "remaining_time": "4:08:01"}
|
||||
{"current_steps": 1850, "total_steps": 9782, "loss": 0.8337, "lr": 4.880464962508234e-05, "epoch": 0.18912771232141487, "percentage": 18.91, "elapsed_time": "0:57:49", "remaining_time": "4:07:53"}
|
||||
{"current_steps": 1860, "total_steps": 9782, "loss": 0.8073, "lr": 4.877723988020685e-05, "epoch": 0.190150024279909, "percentage": 19.01, "elapsed_time": "0:58:10", "remaining_time": "4:07:45"}
|
||||
{"current_steps": 1870, "total_steps": 9782, "loss": 0.8298, "lr": 4.8749527305036106e-05, "epoch": 0.19117233623840316, "percentage": 19.12, "elapsed_time": "0:58:30", "remaining_time": "4:07:34"}
|
||||
{"current_steps": 1880, "total_steps": 9782, "loss": 0.8239, "lr": 4.872151225252138e-05, "epoch": 0.19219464819689727, "percentage": 19.22, "elapsed_time": "0:58:51", "remaining_time": "4:07:23"}
|
||||
{"current_steps": 1890, "total_steps": 9782, "loss": 0.8259, "lr": 4.8693195079466364e-05, "epoch": 0.19321696015539142, "percentage": 19.32, "elapsed_time": "0:59:14", "remaining_time": "4:07:22"}
|
||||
{"current_steps": 1900, "total_steps": 9782, "loss": 0.8143, "lr": 4.866457614652257e-05, "epoch": 0.19423927211388556, "percentage": 19.42, "elapsed_time": "0:59:36", "remaining_time": "4:07:16"}
|
||||
{"current_steps": 1910, "total_steps": 9782, "loss": 0.8107, "lr": 4.863565581818479e-05, "epoch": 0.19526158407237967, "percentage": 19.53, "elapsed_time": "0:59:56", "remaining_time": "4:07:04"}
|
||||
{"current_steps": 1920, "total_steps": 9782, "loss": 0.8147, "lr": 4.860643446278642e-05, "epoch": 0.19628389603087382, "percentage": 19.63, "elapsed_time": "1:00:18", "remaining_time": "4:06:57"}
|
||||
{"current_steps": 1930, "total_steps": 9782, "loss": 0.8233, "lr": 4.8576912452494784e-05, "epoch": 0.19730620798936796, "percentage": 19.73, "elapsed_time": "1:00:40", "remaining_time": "4:06:51"}
|
||||
{"current_steps": 1940, "total_steps": 9782, "loss": 0.822, "lr": 4.854709016330639e-05, "epoch": 0.1983285199478621, "percentage": 19.83, "elapsed_time": "1:01:03", "remaining_time": "4:06:47"}
|
||||
{"current_steps": 1950, "total_steps": 9782, "loss": 0.8115, "lr": 4.851696797504212e-05, "epoch": 0.19935083190635622, "percentage": 19.93, "elapsed_time": "1:01:26", "remaining_time": "4:06:46"}
|
||||
{"current_steps": 1960, "total_steps": 9782, "loss": 0.7992, "lr": 4.8486546271342454e-05, "epoch": 0.20037314386485036, "percentage": 20.04, "elapsed_time": "1:01:49", "remaining_time": "4:06:43"}
|
||||
{"current_steps": 1970, "total_steps": 9782, "loss": 0.8257, "lr": 4.845582543966251e-05, "epoch": 0.2013954558233445, "percentage": 20.14, "elapsed_time": "1:02:10", "remaining_time": "4:06:31"}
|
||||
{"current_steps": 1980, "total_steps": 9782, "loss": 0.8047, "lr": 4.842480587126714e-05, "epoch": 0.20241776778183862, "percentage": 20.24, "elapsed_time": "1:02:31", "remaining_time": "4:06:22"}
|
||||
{"current_steps": 1990, "total_steps": 9782, "loss": 0.801, "lr": 4.839348796122598e-05, "epoch": 0.20344007974033276, "percentage": 20.34, "elapsed_time": "1:02:52", "remaining_time": "4:06:11"}
|
||||
{"current_steps": 2000, "total_steps": 9782, "loss": 0.7989, "lr": 4.8361872108408364e-05, "epoch": 0.2044623916988269, "percentage": 20.45, "elapsed_time": "1:03:13", "remaining_time": "4:06:01"}
|
||||
{"current_steps": 2010, "total_steps": 9782, "loss": 0.8003, "lr": 4.8329958715478266e-05, "epoch": 0.20548470365732102, "percentage": 20.55, "elapsed_time": "1:03:35", "remaining_time": "4:05:53"}
|
||||
{"current_steps": 2020, "total_steps": 9782, "loss": 0.8073, "lr": 4.829774818888918e-05, "epoch": 0.20650701561581516, "percentage": 20.65, "elapsed_time": "1:03:58", "remaining_time": "4:05:47"}
|
||||
{"current_steps": 2030, "total_steps": 9782, "loss": 0.8002, "lr": 4.826524093887894e-05, "epoch": 0.2075293275743093, "percentage": 20.75, "elapsed_time": "1:04:20", "remaining_time": "4:05:42"}
|
||||
{"current_steps": 2040, "total_steps": 9782, "loss": 0.827, "lr": 4.8232437379464476e-05, "epoch": 0.20855163953280342, "percentage": 20.85, "elapsed_time": "1:04:42", "remaining_time": "4:05:34"}
|
||||
{"current_steps": 2050, "total_steps": 9782, "loss": 0.8016, "lr": 4.819933792843659e-05, "epoch": 0.20957395149129757, "percentage": 20.96, "elapsed_time": "1:05:05", "remaining_time": "4:05:30"}
|
||||
{"current_steps": 2060, "total_steps": 9782, "loss": 0.8076, "lr": 4.816594300735455e-05, "epoch": 0.2105962634497917, "percentage": 21.06, "elapsed_time": "1:05:27", "remaining_time": "4:05:21"}
|
||||
{"current_steps": 2070, "total_steps": 9782, "loss": 0.8076, "lr": 4.813225304154083e-05, "epoch": 0.21161857540828583, "percentage": 21.16, "elapsed_time": "1:05:50", "remaining_time": "4:05:17"}
|
||||
{"current_steps": 2080, "total_steps": 9782, "loss": 0.7971, "lr": 4.8098268460075594e-05, "epoch": 0.21264088736677997, "percentage": 21.26, "elapsed_time": "1:06:12", "remaining_time": "4:05:09"}
|
||||
{"current_steps": 2090, "total_steps": 9782, "loss": 0.8014, "lr": 4.8063989695791267e-05, "epoch": 0.2136631993252741, "percentage": 21.37, "elapsed_time": "1:06:34", "remaining_time": "4:05:01"}
|
||||
{"current_steps": 2100, "total_steps": 9782, "loss": 0.8007, "lr": 4.8029417185267076e-05, "epoch": 0.21468551128376825, "percentage": 21.47, "elapsed_time": "1:06:56", "remaining_time": "4:04:52"}
|
||||
{"current_steps": 2110, "total_steps": 9782, "loss": 0.792, "lr": 4.79945513688234e-05, "epoch": 0.21570782324226237, "percentage": 21.57, "elapsed_time": "1:07:18", "remaining_time": "4:04:43"}
|
||||
{"current_steps": 2120, "total_steps": 9782, "loss": 0.796, "lr": 4.795939269051622e-05, "epoch": 0.2167301352007565, "percentage": 21.67, "elapsed_time": "1:07:40", "remaining_time": "4:04:33"}
|
||||
{"current_steps": 2130, "total_steps": 9782, "loss": 0.7966, "lr": 4.792394159813144e-05, "epoch": 0.21775244715925066, "percentage": 21.77, "elapsed_time": "1:08:04", "remaining_time": "4:04:34"}
|
||||
{"current_steps": 2140, "total_steps": 9782, "loss": 0.8042, "lr": 4.7888198543179184e-05, "epoch": 0.21877475911774477, "percentage": 21.88, "elapsed_time": "1:08:27", "remaining_time": "4:04:27"}
|
||||
{"current_steps": 2150, "total_steps": 9782, "loss": 0.782, "lr": 4.785216398088809e-05, "epoch": 0.21979707107623891, "percentage": 21.98, "elapsed_time": "1:08:47", "remaining_time": "4:04:13"}
|
||||
{"current_steps": 2160, "total_steps": 9782, "loss": 0.7934, "lr": 4.781583837019942e-05, "epoch": 0.22081938303473306, "percentage": 22.08, "elapsed_time": "1:09:10", "remaining_time": "4:04:04"}
|
||||
{"current_steps": 2170, "total_steps": 9782, "loss": 0.7964, "lr": 4.7779222173761306e-05, "epoch": 0.22184169499322717, "percentage": 22.18, "elapsed_time": "1:09:31", "remaining_time": "4:03:51"}
|
||||
{"current_steps": 2180, "total_steps": 9782, "loss": 0.7834, "lr": 4.774231585792282e-05, "epoch": 0.22286400695172132, "percentage": 22.29, "elapsed_time": "1:09:53", "remaining_time": "4:03:42"}
|
||||
{"current_steps": 2190, "total_steps": 9782, "loss": 0.7816, "lr": 4.770511989272803e-05, "epoch": 0.22388631891021546, "percentage": 22.39, "elapsed_time": "1:10:14", "remaining_time": "4:03:31"}
|
||||
{"current_steps": 2200, "total_steps": 9782, "loss": 0.7876, "lr": 4.7667634751910006e-05, "epoch": 0.22490863086870957, "percentage": 22.49, "elapsed_time": "1:10:37", "remaining_time": "4:03:23"}
|
||||
{"current_steps": 2210, "total_steps": 9782, "loss": 0.775, "lr": 4.762986091288482e-05, "epoch": 0.22593094282720372, "percentage": 22.59, "elapsed_time": "1:10:59", "remaining_time": "4:03:12"}
|
||||
{"current_steps": 2220, "total_steps": 9782, "loss": 0.7872, "lr": 4.759179885674543e-05, "epoch": 0.22695325478569786, "percentage": 22.69, "elapsed_time": "1:11:20", "remaining_time": "4:02:59"}
|
||||
{"current_steps": 2230, "total_steps": 9782, "loss": 0.7732, "lr": 4.7553449068255574e-05, "epoch": 0.22797556674419198, "percentage": 22.8, "elapsed_time": "1:11:41", "remaining_time": "4:02:47"}
|
||||
{"current_steps": 2240, "total_steps": 9782, "loss": 0.7789, "lr": 4.75148120358436e-05, "epoch": 0.22899787870268612, "percentage": 22.9, "elapsed_time": "1:12:03", "remaining_time": "4:02:37"}
|
||||
{"current_steps": 2250, "total_steps": 9782, "loss": 0.7793, "lr": 4.747588825159622e-05, "epoch": 0.23002019066118026, "percentage": 23.0, "elapsed_time": "1:12:26", "remaining_time": "4:02:30"}
|
||||
{"current_steps": 2260, "total_steps": 9782, "loss": 0.7809, "lr": 4.7436678211252266e-05, "epoch": 0.2310425026196744, "percentage": 23.1, "elapsed_time": "1:12:49", "remaining_time": "4:02:21"}
|
||||
{"current_steps": 2270, "total_steps": 9782, "loss": 0.7801, "lr": 4.739718241419636e-05, "epoch": 0.23206481457816852, "percentage": 23.21, "elapsed_time": "1:13:11", "remaining_time": "4:02:12"}
|
||||
{"current_steps": 2280, "total_steps": 9782, "loss": 0.7934, "lr": 4.735740136345258e-05, "epoch": 0.23308712653666266, "percentage": 23.31, "elapsed_time": "1:13:33", "remaining_time": "4:02:02"}
|
||||
{"current_steps": 2290, "total_steps": 9782, "loss": 0.7804, "lr": 4.731733556567801e-05, "epoch": 0.2341094384951568, "percentage": 23.41, "elapsed_time": "1:13:53", "remaining_time": "4:01:45"}
|
||||
{"current_steps": 2300, "total_steps": 9782, "loss": 0.7681, "lr": 4.727698553115634e-05, "epoch": 0.23513175045365092, "percentage": 23.51, "elapsed_time": "1:14:15", "remaining_time": "4:01:33"}
|
||||
{"current_steps": 2310, "total_steps": 9782, "loss": 0.7878, "lr": 4.723635177379131e-05, "epoch": 0.23615406241214507, "percentage": 23.61, "elapsed_time": "1:14:36", "remaining_time": "4:01:20"}
|
||||
{"current_steps": 2320, "total_steps": 9782, "loss": 0.7771, "lr": 4.719543481110022e-05, "epoch": 0.2371763743706392, "percentage": 23.72, "elapsed_time": "1:14:59", "remaining_time": "4:01:12"}
|
||||
{"current_steps": 2330, "total_steps": 9782, "loss": 0.7764, "lr": 4.7154235164207304e-05, "epoch": 0.23819868632913332, "percentage": 23.82, "elapsed_time": "1:15:23", "remaining_time": "4:01:08"}
|
||||
{"current_steps": 2340, "total_steps": 9782, "loss": 0.7701, "lr": 4.711275335783709e-05, "epoch": 0.23922099828762747, "percentage": 23.92, "elapsed_time": "1:15:45", "remaining_time": "4:00:57"}
|
||||
{"current_steps": 2350, "total_steps": 9782, "loss": 0.7771, "lr": 4.707098992030775e-05, "epoch": 0.2402433102461216, "percentage": 24.02, "elapsed_time": "1:16:07", "remaining_time": "4:00:45"}
|
||||
{"current_steps": 2360, "total_steps": 9782, "loss": 0.7769, "lr": 4.702894538352434e-05, "epoch": 0.24126562220461573, "percentage": 24.13, "elapsed_time": "1:16:28", "remaining_time": "4:00:31"}
|
||||
{"current_steps": 2370, "total_steps": 9782, "loss": 0.7773, "lr": 4.6986620282972034e-05, "epoch": 0.24228793416310987, "percentage": 24.23, "elapsed_time": "1:16:50", "remaining_time": "4:00:20"}
|
||||
{"current_steps": 2380, "total_steps": 9782, "loss": 0.7773, "lr": 4.6944015157709306e-05, "epoch": 0.243310246121604, "percentage": 24.33, "elapsed_time": "1:17:11", "remaining_time": "4:00:04"}
|
||||
{"current_steps": 2390, "total_steps": 9782, "loss": 0.7802, "lr": 4.690113055036106e-05, "epoch": 0.24433255808009816, "percentage": 24.43, "elapsed_time": "1:17:35", "remaining_time": "3:59:57"}
|
||||
{"current_steps": 2400, "total_steps": 9782, "loss": 0.7703, "lr": 4.685796700711175e-05, "epoch": 0.24535487003859227, "percentage": 24.53, "elapsed_time": "1:17:57", "remaining_time": "3:59:46"}
|
||||
{"current_steps": 2410, "total_steps": 9782, "loss": 0.7563, "lr": 4.6814525077698365e-05, "epoch": 0.24637718199708641, "percentage": 24.64, "elapsed_time": "1:18:20", "remaining_time": "3:59:37"}
|
||||
{"current_steps": 2420, "total_steps": 9782, "loss": 0.7686, "lr": 4.677080531540347e-05, "epoch": 0.24739949395558056, "percentage": 24.74, "elapsed_time": "1:18:42", "remaining_time": "3:59:26"}
|
||||
{"current_steps": 2430, "total_steps": 9782, "loss": 0.76, "lr": 4.672680827704815e-05, "epoch": 0.24842180591407467, "percentage": 24.84, "elapsed_time": "1:19:06", "remaining_time": "3:59:20"}
|
||||
{"current_steps": 2440, "total_steps": 9782, "loss": 0.7692, "lr": 4.668253452298492e-05, "epoch": 0.24944411787256882, "percentage": 24.94, "elapsed_time": "1:19:29", "remaining_time": "3:59:10"}
|
||||
{"current_steps": 2450, "total_steps": 9782, "loss": 0.7642, "lr": 4.663798461709059e-05, "epoch": 0.25046642983106293, "percentage": 25.05, "elapsed_time": "1:19:52", "remaining_time": "3:59:01"}
|
||||
{"current_steps": 2460, "total_steps": 9782, "loss": 0.7676, "lr": 4.6593159126759064e-05, "epoch": 0.2514887417895571, "percentage": 25.15, "elapsed_time": "1:20:15", "remaining_time": "3:58:52"}
|
||||
{"current_steps": 2470, "total_steps": 9782, "loss": 0.7643, "lr": 4.654805862289414e-05, "epoch": 0.2525110537480512, "percentage": 25.25, "elapsed_time": "1:20:38", "remaining_time": "3:58:43"}
|
||||
{"current_steps": 2480, "total_steps": 9782, "loss": 0.7607, "lr": 4.650268367990222e-05, "epoch": 0.25353336570654533, "percentage": 25.35, "elapsed_time": "1:20:59", "remaining_time": "3:58:29"}
|
||||
{"current_steps": 2490, "total_steps": 9782, "loss": 0.7689, "lr": 4.6457034875685e-05, "epoch": 0.2545556776650395, "percentage": 25.45, "elapsed_time": "1:21:23", "remaining_time": "3:58:21"}
|
||||
{"current_steps": 2500, "total_steps": 9782, "loss": 0.7667, "lr": 4.641111279163214e-05, "epoch": 0.2555779896235336, "percentage": 25.56, "elapsed_time": "1:21:45", "remaining_time": "3:58:09"}
|
||||
{"current_steps": 2510, "total_steps": 9782, "loss": 0.7643, "lr": 4.636491801261379e-05, "epoch": 0.25660030158202773, "percentage": 25.66, "elapsed_time": "1:22:09", "remaining_time": "3:58:01"}
|
||||
{"current_steps": 2520, "total_steps": 9782, "loss": 0.7686, "lr": 4.631845112697319e-05, "epoch": 0.2576226135405219, "percentage": 25.76, "elapsed_time": "1:22:30", "remaining_time": "3:57:45"}
|
||||
{"current_steps": 2530, "total_steps": 9782, "loss": 0.7645, "lr": 4.62717127265192e-05, "epoch": 0.258644925499016, "percentage": 25.86, "elapsed_time": "1:22:51", "remaining_time": "3:57:30"}
|
||||
{"current_steps": 2540, "total_steps": 9782, "loss": 0.7635, "lr": 4.62247034065187e-05, "epoch": 0.25966723745751014, "percentage": 25.97, "elapsed_time": "1:23:14", "remaining_time": "3:57:20"}
|
||||
{"current_steps": 2550, "total_steps": 9782, "loss": 0.7671, "lr": 4.6177423765689045e-05, "epoch": 0.2606895494160043, "percentage": 26.07, "elapsed_time": "1:23:36", "remaining_time": "3:57:06"}
|
||||
{"current_steps": 2560, "total_steps": 9782, "loss": 0.7633, "lr": 4.612987440619044e-05, "epoch": 0.2617118613744984, "percentage": 26.17, "elapsed_time": "1:23:58", "remaining_time": "3:56:54"}
|
||||
{"current_steps": 2570, "total_steps": 9782, "loss": 0.7559, "lr": 4.6082055933618255e-05, "epoch": 0.26273417333299254, "percentage": 26.27, "elapsed_time": "1:24:22", "remaining_time": "3:56:45"}
|
||||
{"current_steps": 2580, "total_steps": 9782, "loss": 0.7486, "lr": 4.6033968956995346e-05, "epoch": 0.2637564852914867, "percentage": 26.37, "elapsed_time": "1:24:42", "remaining_time": "3:56:26"}
|
||||
{"current_steps": 2590, "total_steps": 9782, "loss": 0.7611, "lr": 4.598561408876425e-05, "epoch": 0.2647787972499808, "percentage": 26.48, "elapsed_time": "1:25:05", "remaining_time": "3:56:16"}
|
||||
{"current_steps": 2600, "total_steps": 9782, "loss": 0.7591, "lr": 4.593699194477943e-05, "epoch": 0.26580110920847494, "percentage": 26.58, "elapsed_time": "1:25:27", "remaining_time": "3:56:02"}
|
||||
{"current_steps": 2610, "total_steps": 9782, "loss": 0.7498, "lr": 4.5888103144299374e-05, "epoch": 0.2668234211669691, "percentage": 26.68, "elapsed_time": "1:25:50", "remaining_time": "3:55:53"}
|
||||
{"current_steps": 2620, "total_steps": 9782, "loss": 0.7443, "lr": 4.583894830997879e-05, "epoch": 0.2678457331254632, "percentage": 26.78, "elapsed_time": "1:26:15", "remaining_time": "3:55:47"}
|
||||
{"current_steps": 2630, "total_steps": 9782, "loss": 0.7413, "lr": 4.578952806786061e-05, "epoch": 0.2688680450839574, "percentage": 26.89, "elapsed_time": "1:26:38", "remaining_time": "3:55:35"}
|
||||
{"current_steps": 2640, "total_steps": 9782, "loss": 0.7472, "lr": 4.573984304736804e-05, "epoch": 0.2698903570424515, "percentage": 26.99, "elapsed_time": "1:27:02", "remaining_time": "3:55:27"}
|
||||
{"current_steps": 2650, "total_steps": 9782, "loss": 0.7555, "lr": 4.568989388129652e-05, "epoch": 0.2709126690009456, "percentage": 27.09, "elapsed_time": "1:27:27", "remaining_time": "3:55:21"}
|
||||
{"current_steps": 2660, "total_steps": 9782, "loss": 0.7561, "lr": 4.563968120580573e-05, "epoch": 0.2719349809594398, "percentage": 27.19, "elapsed_time": "1:27:49", "remaining_time": "3:55:08"}
|
||||
{"current_steps": 2670, "total_steps": 9782, "loss": 0.7537, "lr": 4.5589205660411397e-05, "epoch": 0.2729572929179339, "percentage": 27.3, "elapsed_time": "1:28:13", "remaining_time": "3:55:00"}
|
||||
{"current_steps": 2680, "total_steps": 9782, "loss": 0.7575, "lr": 4.553846788797723e-05, "epoch": 0.27397960487642803, "percentage": 27.4, "elapsed_time": "1:28:36", "remaining_time": "3:54:49"}
|
||||
{"current_steps": 2690, "total_steps": 9782, "loss": 0.7558, "lr": 4.5487468534706685e-05, "epoch": 0.2750019168349222, "percentage": 27.5, "elapsed_time": "1:28:58", "remaining_time": "3:54:34"}
|
||||
{"current_steps": 2700, "total_steps": 9782, "loss": 0.7441, "lr": 4.5436208250134744e-05, "epoch": 0.2760242287934163, "percentage": 27.6, "elapsed_time": "1:29:22", "remaining_time": "3:54:25"}
|
||||
{"current_steps": 2710, "total_steps": 9782, "loss": 0.743, "lr": 4.5384687687119656e-05, "epoch": 0.27704654075191043, "percentage": 27.7, "elapsed_time": "1:29:44", "remaining_time": "3:54:10"}
|
||||
{"current_steps": 2720, "total_steps": 9782, "loss": 0.7465, "lr": 4.533290750183461e-05, "epoch": 0.2780688527104046, "percentage": 27.81, "elapsed_time": "1:30:06", "remaining_time": "3:53:58"}
|
||||
{"current_steps": 2730, "total_steps": 9782, "loss": 0.7505, "lr": 4.5280868353759375e-05, "epoch": 0.2790911646688987, "percentage": 27.91, "elapsed_time": "1:30:28", "remaining_time": "3:53:43"}
|
||||
{"current_steps": 2740, "total_steps": 9782, "loss": 0.7389, "lr": 4.522857090567193e-05, "epoch": 0.28011347662739283, "percentage": 28.01, "elapsed_time": "1:30:51", "remaining_time": "3:53:30"}
|
||||
{"current_steps": 2750, "total_steps": 9782, "loss": 0.7501, "lr": 4.517601582363995e-05, "epoch": 0.281135788585887, "percentage": 28.11, "elapsed_time": "1:31:15", "remaining_time": "3:53:20"}
|
||||
{"current_steps": 2760, "total_steps": 9782, "loss": 0.75, "lr": 4.512320377701244e-05, "epoch": 0.2821581005443811, "percentage": 28.22, "elapsed_time": "1:31:38", "remaining_time": "3:53:10"}
|
||||
{"current_steps": 2770, "total_steps": 9782, "loss": 0.7401, "lr": 4.507013543841109e-05, "epoch": 0.28318041250287523, "percentage": 28.32, "elapsed_time": "1:32:02", "remaining_time": "3:53:00"}
|
||||
{"current_steps": 2780, "total_steps": 9782, "loss": 0.7354, "lr": 4.501681148372177e-05, "epoch": 0.2842027244613694, "percentage": 28.42, "elapsed_time": "1:32:26", "remaining_time": "3:52:49"}
|
||||
{"current_steps": 2790, "total_steps": 9782, "loss": 0.7539, "lr": 4.496323259208592e-05, "epoch": 0.2852250364198635, "percentage": 28.52, "elapsed_time": "1:32:49", "remaining_time": "3:52:37"}
|
||||
{"current_steps": 2800, "total_steps": 9782, "loss": 0.7515, "lr": 4.490939944589192e-05, "epoch": 0.28624734837835764, "percentage": 28.62, "elapsed_time": "1:33:11", "remaining_time": "3:52:23"}
|
||||
{"current_steps": 2810, "total_steps": 9782, "loss": 0.7414, "lr": 4.485531273076632e-05, "epoch": 0.2872696603368518, "percentage": 28.73, "elapsed_time": "1:33:34", "remaining_time": "3:52:10"}
|
||||
{"current_steps": 2820, "total_steps": 9782, "loss": 0.7409, "lr": 4.48009731355652e-05, "epoch": 0.2882919722953459, "percentage": 28.83, "elapsed_time": "1:33:57", "remaining_time": "3:51:58"}
|
||||
{"current_steps": 2830, "total_steps": 9782, "loss": 0.7489, "lr": 4.474638135236533e-05, "epoch": 0.28931428425384004, "percentage": 28.93, "elapsed_time": "1:34:21", "remaining_time": "3:51:48"}
|
||||
{"current_steps": 2840, "total_steps": 9782, "loss": 0.7349, "lr": 4.46915380764554e-05, "epoch": 0.2903365962123342, "percentage": 29.03, "elapsed_time": "1:34:43", "remaining_time": "3:51:33"}
|
||||
{"current_steps": 2850, "total_steps": 9782, "loss": 0.7364, "lr": 4.463644400632714e-05, "epoch": 0.2913589081708283, "percentage": 29.14, "elapsed_time": "1:35:06", "remaining_time": "3:51:19"}
|
||||
{"current_steps": 2860, "total_steps": 9782, "loss": 0.7512, "lr": 4.458109984366643e-05, "epoch": 0.29238122012932244, "percentage": 29.24, "elapsed_time": "1:35:28", "remaining_time": "3:51:04"}
|
||||
{"current_steps": 2870, "total_steps": 9782, "loss": 0.734, "lr": 4.4525506293344364e-05, "epoch": 0.2934035320878166, "percentage": 29.34, "elapsed_time": "1:35:52", "remaining_time": "3:50:54"}
|
||||
{"current_steps": 2880, "total_steps": 9782, "loss": 0.7396, "lr": 4.4469664063408284e-05, "epoch": 0.2944258440463107, "percentage": 29.44, "elapsed_time": "1:36:15", "remaining_time": "3:50:40"}
|
||||
{"current_steps": 2890, "total_steps": 9782, "loss": 0.7414, "lr": 4.4413573865072734e-05, "epoch": 0.29544815600480484, "percentage": 29.54, "elapsed_time": "1:36:37", "remaining_time": "3:50:25"}
|
||||
{"current_steps": 2900, "total_steps": 9782, "loss": 0.7395, "lr": 4.4357236412710415e-05, "epoch": 0.296470467963299, "percentage": 29.65, "elapsed_time": "1:37:00", "remaining_time": "3:50:12"}
|
||||
{"current_steps": 2910, "total_steps": 9782, "loss": 0.741, "lr": 4.430065242384311e-05, "epoch": 0.2974927799217931, "percentage": 29.75, "elapsed_time": "1:37:21", "remaining_time": "3:49:55"}
|
||||
{"current_steps": 2920, "total_steps": 9782, "loss": 0.7292, "lr": 4.424382261913254e-05, "epoch": 0.29851509188028724, "percentage": 29.85, "elapsed_time": "1:37:44", "remaining_time": "3:49:42"}
|
||||
{"current_steps": 2930, "total_steps": 9782, "loss": 0.7329, "lr": 4.41867477223711e-05, "epoch": 0.2995374038387814, "percentage": 29.95, "elapsed_time": "1:38:07", "remaining_time": "3:49:27"}
|
||||
{"current_steps": 2940, "total_steps": 9782, "loss": 0.7315, "lr": 4.41294284604728e-05, "epoch": 0.30055971579727553, "percentage": 30.06, "elapsed_time": "1:38:30", "remaining_time": "3:49:16"}
|
||||
{"current_steps": 2950, "total_steps": 9782, "loss": 0.7457, "lr": 4.407186556346385e-05, "epoch": 0.3015820277557697, "percentage": 30.16, "elapsed_time": "1:38:54", "remaining_time": "3:49:03"}
|
||||
{"current_steps": 2960, "total_steps": 9782, "loss": 0.7351, "lr": 4.401405976447349e-05, "epoch": 0.3026043397142638, "percentage": 30.26, "elapsed_time": "1:39:16", "remaining_time": "3:48:46"}
|
||||
{"current_steps": 2970, "total_steps": 9782, "loss": 0.7275, "lr": 4.395601179972454e-05, "epoch": 0.30362665167275793, "percentage": 30.36, "elapsed_time": "1:39:40", "remaining_time": "3:48:36"}
|
||||
{"current_steps": 2980, "total_steps": 9782, "loss": 0.7252, "lr": 4.389772240852412e-05, "epoch": 0.3046489636312521, "percentage": 30.46, "elapsed_time": "1:40:03", "remaining_time": "3:48:23"}
|
||||
{"current_steps": 2990, "total_steps": 9782, "loss": 0.7234, "lr": 4.383919233325415e-05, "epoch": 0.3056712755897462, "percentage": 30.57, "elapsed_time": "1:40:28", "remaining_time": "3:48:14"}
|
||||
{"current_steps": 3000, "total_steps": 9782, "loss": 0.7155, "lr": 4.3780422319361994e-05, "epoch": 0.30669358754824033, "percentage": 30.67, "elapsed_time": "1:40:56", "remaining_time": "3:48:11"}
|
||||
{"current_steps": 3010, "total_steps": 9782, "loss": 0.6982, "lr": 4.372141311535083e-05, "epoch": 0.3077158995067345, "percentage": 30.77, "elapsed_time": "1:42:00", "remaining_time": "3:49:30"}
|
||||
{"current_steps": 3020, "total_steps": 9782, "loss": 0.7027, "lr": 4.3662165472770275e-05, "epoch": 0.3087382114652286, "percentage": 30.87, "elapsed_time": "1:42:28", "remaining_time": "3:49:27"}
|
||||
{"current_steps": 3030, "total_steps": 9782, "loss": 0.7012, "lr": 4.360268014620669e-05, "epoch": 0.30976052342372273, "percentage": 30.98, "elapsed_time": "1:42:57", "remaining_time": "3:49:25"}
|
||||
{"current_steps": 3040, "total_steps": 9782, "loss": 0.6926, "lr": 4.35429578932736e-05, "epoch": 0.3107828353822169, "percentage": 31.08, "elapsed_time": "1:43:24", "remaining_time": "3:49:20"}
|
||||
{"current_steps": 3050, "total_steps": 9782, "loss": 0.6965, "lr": 4.3482999474602116e-05, "epoch": 0.311805147340711, "percentage": 31.18, "elapsed_time": "1:43:52", "remaining_time": "3:49:15"}
|
||||
{"current_steps": 3060, "total_steps": 9782, "loss": 0.6902, "lr": 4.342280565383111e-05, "epoch": 0.31282745929920514, "percentage": 31.28, "elapsed_time": "1:44:20", "remaining_time": "3:49:12"}
|
||||
{"current_steps": 3070, "total_steps": 9782, "loss": 0.6972, "lr": 4.336237719759764e-05, "epoch": 0.3138497712576993, "percentage": 31.38, "elapsed_time": "1:44:48", "remaining_time": "3:49:08"}
|
||||
{"current_steps": 3080, "total_steps": 9782, "loss": 0.6864, "lr": 4.330171487552708e-05, "epoch": 0.3148720832161934, "percentage": 31.49, "elapsed_time": "1:45:16", "remaining_time": "3:49:03"}
|
||||
{"current_steps": 3090, "total_steps": 9782, "loss": 0.6806, "lr": 4.324081946022334e-05, "epoch": 0.31589439517468754, "percentage": 31.59, "elapsed_time": "1:45:43", "remaining_time": "3:48:58"}
|
||||
{"current_steps": 3100, "total_steps": 9782, "loss": 0.6837, "lr": 4.317969172725907e-05, "epoch": 0.3169167071331817, "percentage": 31.69, "elapsed_time": "1:46:11", "remaining_time": "3:48:54"}
|
||||
{"current_steps": 3110, "total_steps": 9782, "loss": 0.6872, "lr": 4.3118332455165735e-05, "epoch": 0.3179390190916758, "percentage": 31.79, "elapsed_time": "1:46:39", "remaining_time": "3:48:49"}
|
||||
{"current_steps": 3120, "total_steps": 9782, "loss": 0.6818, "lr": 4.3056742425423706e-05, "epoch": 0.31896133105016994, "percentage": 31.9, "elapsed_time": "1:47:08", "remaining_time": "3:48:46"}
|
||||
{"current_steps": 3130, "total_steps": 9782, "loss": 0.6856, "lr": 4.299492242245235e-05, "epoch": 0.3199836430086641, "percentage": 32.0, "elapsed_time": "1:47:36", "remaining_time": "3:48:41"}
|
||||
{"current_steps": 3140, "total_steps": 9782, "loss": 0.682, "lr": 4.293287323359995e-05, "epoch": 0.3210059549671582, "percentage": 32.1, "elapsed_time": "1:48:03", "remaining_time": "3:48:35"}
|
||||
{"current_steps": 3150, "total_steps": 9782, "loss": 0.6852, "lr": 4.2870595649133784e-05, "epoch": 0.32202826692565234, "percentage": 32.2, "elapsed_time": "1:48:32", "remaining_time": "3:48:30"}
|
||||
{"current_steps": 3160, "total_steps": 9782, "loss": 0.6815, "lr": 4.2808090462229986e-05, "epoch": 0.3230505788841465, "percentage": 32.3, "elapsed_time": "1:48:59", "remaining_time": "3:48:24"}
|
||||
{"current_steps": 3170, "total_steps": 9782, "loss": 0.6792, "lr": 4.274535846896348e-05, "epoch": 0.3240728908426406, "percentage": 32.41, "elapsed_time": "1:49:28", "remaining_time": "3:48:20"}
|
||||
{"current_steps": 3180, "total_steps": 9782, "loss": 0.6819, "lr": 4.268240046829781e-05, "epoch": 0.32509520280113474, "percentage": 32.51, "elapsed_time": "1:49:56", "remaining_time": "3:48:14"}
|
||||
{"current_steps": 3190, "total_steps": 9782, "loss": 0.685, "lr": 4.2619217262074975e-05, "epoch": 0.3261175147596289, "percentage": 32.61, "elapsed_time": "1:50:24", "remaining_time": "3:48:08"}
|
||||
{"current_steps": 3200, "total_steps": 9782, "loss": 0.6768, "lr": 4.255580965500526e-05, "epoch": 0.32713982671812303, "percentage": 32.71, "elapsed_time": "1:50:52", "remaining_time": "3:48:03"}
|
||||
{"current_steps": 3210, "total_steps": 9782, "loss": 0.6712, "lr": 4.249217845465694e-05, "epoch": 0.32816213867661714, "percentage": 32.82, "elapsed_time": "1:51:21", "remaining_time": "3:47:58"}
|
||||
{"current_steps": 3220, "total_steps": 9782, "loss": 0.6745, "lr": 4.242832447144597e-05, "epoch": 0.3291844506351113, "percentage": 32.92, "elapsed_time": "1:51:49", "remaining_time": "3:47:53"}
|
||||
{"current_steps": 3230, "total_steps": 9782, "loss": 0.6831, "lr": 4.236424851862574e-05, "epoch": 0.33020676259360543, "percentage": 33.02, "elapsed_time": "1:52:17", "remaining_time": "3:47:46"}
|
||||
{"current_steps": 3240, "total_steps": 9782, "loss": 0.6787, "lr": 4.229995141227665e-05, "epoch": 0.3312290745520996, "percentage": 33.12, "elapsed_time": "1:52:45", "remaining_time": "3:47:39"}
|
||||
{"current_steps": 3250, "total_steps": 9782, "loss": 0.6796, "lr": 4.223543397129577e-05, "epoch": 0.3322513865105937, "percentage": 33.22, "elapsed_time": "1:53:12", "remaining_time": "3:47:30"}
|
||||
{"current_steps": 3260, "total_steps": 9782, "loss": 0.6755, "lr": 4.2170697017386365e-05, "epoch": 0.33327369846908783, "percentage": 33.33, "elapsed_time": "1:53:40", "remaining_time": "3:47:24"}
|
||||
{"current_steps": 3270, "total_steps": 9782, "loss": 0.8193, "lr": 4.210574137504744e-05, "epoch": 0.334296010427582, "percentage": 33.43, "elapsed_time": "1:53:53", "remaining_time": "3:46:49"}
|
||||
{"current_steps": 3280, "total_steps": 9782, "loss": 0.8628, "lr": 4.204056787156326e-05, "epoch": 0.3353183223860761, "percentage": 33.53, "elapsed_time": "1:54:07", "remaining_time": "3:46:13"}
|
||||
{"current_steps": 3290, "total_steps": 9782, "loss": 0.8978, "lr": 4.197517733699281e-05, "epoch": 0.33634063434457023, "percentage": 33.63, "elapsed_time": "1:54:21", "remaining_time": "3:45:39"}
|
||||
{"current_steps": 3300, "total_steps": 9782, "loss": 0.9052, "lr": 4.1909570604159186e-05, "epoch": 0.3373629463030644, "percentage": 33.74, "elapsed_time": "1:54:35", "remaining_time": "3:45:04"}
|
||||
{"current_steps": 3310, "total_steps": 9782, "loss": 0.9197, "lr": 4.1843748508639035e-05, "epoch": 0.3383852582615585, "percentage": 33.84, "elapsed_time": "1:54:49", "remaining_time": "3:44:31"}
|
||||
{"current_steps": 3320, "total_steps": 9782, "loss": 1.0064, "lr": 4.17777118887519e-05, "epoch": 0.33940757022005263, "percentage": 33.94, "elapsed_time": "1:55:04", "remaining_time": "3:43:57"}
|
||||
{"current_steps": 3330, "total_steps": 9782, "loss": 0.935, "lr": 4.171146158554951e-05, "epoch": 0.3404298821785468, "percentage": 34.04, "elapsed_time": "1:55:18", "remaining_time": "3:43:24"}
|
||||
{"current_steps": 3340, "total_steps": 9782, "loss": 0.9026, "lr": 4.1644998442805114e-05, "epoch": 0.3414521941370409, "percentage": 34.14, "elapsed_time": "1:55:33", "remaining_time": "3:42:53"}
|
||||
{"current_steps": 3350, "total_steps": 9782, "loss": 0.8654, "lr": 4.157832330700272e-05, "epoch": 0.34247450609553504, "percentage": 34.25, "elapsed_time": "1:55:49", "remaining_time": "3:42:22"}
|
||||
{"current_steps": 3360, "total_steps": 9782, "loss": 0.9811, "lr": 4.1511437027326304e-05, "epoch": 0.3434968180540292, "percentage": 34.35, "elapsed_time": "1:56:02", "remaining_time": "3:41:47"}
|
||||
{"current_steps": 3370, "total_steps": 9782, "loss": 0.9688, "lr": 4.1444340455648995e-05, "epoch": 0.3445191300125233, "percentage": 34.45, "elapsed_time": "1:56:16", "remaining_time": "3:41:14"}
|
||||
{"current_steps": 3380, "total_steps": 9782, "loss": 0.9601, "lr": 4.137703444652223e-05, "epoch": 0.34554144197101744, "percentage": 34.55, "elapsed_time": "1:56:30", "remaining_time": "3:40:41"}
|
||||
{"current_steps": 3390, "total_steps": 9782, "loss": 1.0296, "lr": 4.130951985716488e-05, "epoch": 0.3465637539295116, "percentage": 34.66, "elapsed_time": "1:56:44", "remaining_time": "3:40:06"}
|
||||
{"current_steps": 3400, "total_steps": 9782, "loss": 0.9131, "lr": 4.1241797547452316e-05, "epoch": 0.3475860658880057, "percentage": 34.76, "elapsed_time": "1:56:58", "remaining_time": "3:39:34"}
|
||||
{"current_steps": 3410, "total_steps": 9782, "loss": 0.9109, "lr": 4.117386837990547e-05, "epoch": 0.34860837784649984, "percentage": 34.86, "elapsed_time": "1:57:13", "remaining_time": "3:39:03"}
|
||||
{"current_steps": 3420, "total_steps": 9782, "loss": 0.9349, "lr": 4.1105733219679844e-05, "epoch": 0.349630689804994, "percentage": 34.96, "elapsed_time": "1:57:28", "remaining_time": "3:38:31"}
|
||||
{"current_steps": 3430, "total_steps": 9782, "loss": 0.9001, "lr": 4.103739293455449e-05, "epoch": 0.3506530017634881, "percentage": 35.06, "elapsed_time": "1:57:44", "remaining_time": "3:38:02"}
|
||||
{"current_steps": 3440, "total_steps": 9782, "loss": 0.9077, "lr": 4.096884839492095e-05, "epoch": 0.35167531372198224, "percentage": 35.17, "elapsed_time": "1:57:59", "remaining_time": "3:37:31"}
|
||||
{"current_steps": 3450, "total_steps": 9782, "loss": 0.8612, "lr": 4.0900100473772204e-05, "epoch": 0.3526976256804764, "percentage": 35.27, "elapsed_time": "1:58:14", "remaining_time": "3:37:01"}
|
||||
{"current_steps": 3460, "total_steps": 9782, "loss": 0.8622, "lr": 4.083115004669151e-05, "epoch": 0.3537199376389705, "percentage": 35.37, "elapsed_time": "1:58:30", "remaining_time": "3:36:32"}
|
||||
{"current_steps": 3470, "total_steps": 9782, "loss": 0.8206, "lr": 4.076199799184127e-05, "epoch": 0.35474224959746464, "percentage": 35.47, "elapsed_time": "1:58:46", "remaining_time": "3:36:03"}
|
||||
{"current_steps": 3480, "total_steps": 9782, "loss": 0.9132, "lr": 4.0692645189951855e-05, "epoch": 0.3557645615559588, "percentage": 35.58, "elapsed_time": "1:59:03", "remaining_time": "3:35:36"}
|
||||
{"current_steps": 3490, "total_steps": 9782, "loss": 0.9233, "lr": 4.062309252431037e-05, "epoch": 0.35678687351445293, "percentage": 35.68, "elapsed_time": "1:59:18", "remaining_time": "3:35:05"}
|
||||
{"current_steps": 3500, "total_steps": 9782, "loss": 0.8194, "lr": 4.0553340880749425e-05, "epoch": 0.35780918547294704, "percentage": 35.78, "elapsed_time": "1:59:34", "remaining_time": "3:34:37"}
|
||||
{"current_steps": 3510, "total_steps": 9782, "loss": 0.8394, "lr": 4.048339114763582e-05, "epoch": 0.3588314974314412, "percentage": 35.88, "elapsed_time": "1:59:51", "remaining_time": "3:34:10"}
|
||||
{"current_steps": 3520, "total_steps": 9782, "loss": 0.782, "lr": 4.041324421585928e-05, "epoch": 0.35985380938993533, "percentage": 35.98, "elapsed_time": "2:00:07", "remaining_time": "3:33:42"}
|
||||
{"current_steps": 3530, "total_steps": 9782, "loss": 0.7677, "lr": 4.034290097882105e-05, "epoch": 0.36087612134842945, "percentage": 36.09, "elapsed_time": "2:00:25", "remaining_time": "3:33:16"}
|
||||
{"current_steps": 3540, "total_steps": 9782, "loss": 0.7844, "lr": 4.027236233242257e-05, "epoch": 0.3618984333069236, "percentage": 36.19, "elapsed_time": "2:00:42", "remaining_time": "3:32:50"}
|
||||
{"current_steps": 3550, "total_steps": 9782, "loss": 0.8085, "lr": 4.020162917505403e-05, "epoch": 0.36292074526541773, "percentage": 36.29, "elapsed_time": "2:00:58", "remaining_time": "3:32:22"}
|
||||
{"current_steps": 3560, "total_steps": 9782, "loss": 0.77, "lr": 4.013070240758294e-05, "epoch": 0.3639430572239119, "percentage": 36.39, "elapsed_time": "2:01:15", "remaining_time": "3:31:55"}
|
||||
{"current_steps": 3570, "total_steps": 9782, "loss": 0.8105, "lr": 4.0059582933342666e-05, "epoch": 0.364965369182406, "percentage": 36.5, "elapsed_time": "2:01:33", "remaining_time": "3:31:30"}
|
||||
{"current_steps": 3580, "total_steps": 9782, "loss": 0.7977, "lr": 3.99882716581209e-05, "epoch": 0.36598768114090013, "percentage": 36.6, "elapsed_time": "2:01:50", "remaining_time": "3:31:03"}
|
||||
{"current_steps": 3590, "total_steps": 9782, "loss": 0.7906, "lr": 3.991676949014814e-05, "epoch": 0.3670099930993943, "percentage": 36.7, "elapsed_time": "2:02:06", "remaining_time": "3:30:36"}
|
||||
{"current_steps": 3600, "total_steps": 9782, "loss": 0.7578, "lr": 3.984507734008614e-05, "epoch": 0.3680323050578884, "percentage": 36.8, "elapsed_time": "2:02:23", "remaining_time": "3:30:10"}
|
||||
{"current_steps": 3610, "total_steps": 9782, "loss": 0.803, "lr": 3.9773196121016264e-05, "epoch": 0.36905461701638254, "percentage": 36.9, "elapsed_time": "2:02:39", "remaining_time": "3:29:41"}
|
||||
{"current_steps": 3620, "total_steps": 9782, "loss": 0.7424, "lr": 3.970112674842791e-05, "epoch": 0.3700769289748767, "percentage": 37.01, "elapsed_time": "2:02:57", "remaining_time": "3:29:17"}
|
||||
{"current_steps": 3630, "total_steps": 9782, "loss": 0.7438, "lr": 3.962887014020681e-05, "epoch": 0.3710992409333708, "percentage": 37.11, "elapsed_time": "2:03:15", "remaining_time": "3:28:54"}
|
||||
{"current_steps": 3640, "total_steps": 9782, "loss": 0.7917, "lr": 3.955642721662336e-05, "epoch": 0.37212155289186494, "percentage": 37.21, "elapsed_time": "2:03:32", "remaining_time": "3:28:28"}
|
||||
{"current_steps": 3650, "total_steps": 9782, "loss": 0.7571, "lr": 3.94837989003209e-05, "epoch": 0.3731438648503591, "percentage": 37.31, "elapsed_time": "2:03:50", "remaining_time": "3:28:03"}
|
||||
{"current_steps": 3660, "total_steps": 9782, "loss": 0.7683, "lr": 3.941098611630396e-05, "epoch": 0.3741661768088532, "percentage": 37.42, "elapsed_time": "2:04:07", "remaining_time": "3:27:37"}
|
||||
{"current_steps": 3670, "total_steps": 9782, "loss": 0.7227, "lr": 3.9337989791926466e-05, "epoch": 0.37518848876734734, "percentage": 37.52, "elapsed_time": "2:04:25", "remaining_time": "3:27:12"}
|
||||
{"current_steps": 3680, "total_steps": 9782, "loss": 0.7608, "lr": 3.926481085687994e-05, "epoch": 0.3762108007258415, "percentage": 37.62, "elapsed_time": "2:04:43", "remaining_time": "3:26:49"}
|
||||
{"current_steps": 3690, "total_steps": 9782, "loss": 0.695, "lr": 3.919145024318168e-05, "epoch": 0.3772331126843356, "percentage": 37.72, "elapsed_time": "2:05:02", "remaining_time": "3:26:25"}
|
||||
{"current_steps": 3700, "total_steps": 9782, "loss": 0.7274, "lr": 3.9117908885162836e-05, "epoch": 0.37825542464282974, "percentage": 37.82, "elapsed_time": "2:05:19", "remaining_time": "3:26:00"}
|
||||
{"current_steps": 3710, "total_steps": 9782, "loss": 0.7259, "lr": 3.904418771945658e-05, "epoch": 0.3792777366013239, "percentage": 37.93, "elapsed_time": "2:05:37", "remaining_time": "3:25:36"}
|
||||
{"current_steps": 3720, "total_steps": 9782, "loss": 0.7152, "lr": 3.8970287684986105e-05, "epoch": 0.380300048559818, "percentage": 38.03, "elapsed_time": "2:05:58", "remaining_time": "3:25:16"}
|
||||
{"current_steps": 3730, "total_steps": 9782, "loss": 0.7628, "lr": 3.8896209722952724e-05, "epoch": 0.38132236051831214, "percentage": 38.13, "elapsed_time": "2:06:15", "remaining_time": "3:24:51"}
|
||||
{"current_steps": 3740, "total_steps": 9782, "loss": 0.7508, "lr": 3.882195477682386e-05, "epoch": 0.3823446724768063, "percentage": 38.23, "elapsed_time": "2:06:32", "remaining_time": "3:24:26"}
|
||||
{"current_steps": 3750, "total_steps": 9782, "loss": 0.7239, "lr": 3.874752379232102e-05, "epoch": 0.38336698443530043, "percentage": 38.34, "elapsed_time": "2:06:51", "remaining_time": "3:24:03"}
|
||||
{"current_steps": 3760, "total_steps": 9782, "loss": 0.7371, "lr": 3.867291771740776e-05, "epoch": 0.38438929639379454, "percentage": 38.44, "elapsed_time": "2:07:09", "remaining_time": "3:23:40"}
|
||||
{"current_steps": 3770, "total_steps": 9782, "loss": 0.732, "lr": 3.8598137502277636e-05, "epoch": 0.3854116083522887, "percentage": 38.54, "elapsed_time": "2:07:28", "remaining_time": "3:23:16"}
|
||||
{"current_steps": 3780, "total_steps": 9782, "loss": 0.7107, "lr": 3.8523184099342044e-05, "epoch": 0.38643392031078283, "percentage": 38.64, "elapsed_time": "2:07:46", "remaining_time": "3:22:52"}
|
||||
{"current_steps": 3790, "total_steps": 9782, "loss": 0.7076, "lr": 3.844805846321815e-05, "epoch": 0.38745623226927695, "percentage": 38.74, "elapsed_time": "2:08:04", "remaining_time": "3:22:29"}
|
||||
{"current_steps": 3800, "total_steps": 9782, "loss": 0.7157, "lr": 3.83727615507167e-05, "epoch": 0.3884785442277711, "percentage": 38.85, "elapsed_time": "2:08:22", "remaining_time": "3:22:06"}
|
||||
{"current_steps": 3810, "total_steps": 9782, "loss": 0.7167, "lr": 3.829729432082982e-05, "epoch": 0.38950085618626523, "percentage": 38.95, "elapsed_time": "2:08:40", "remaining_time": "3:21:41"}
|
||||
{"current_steps": 3820, "total_steps": 9782, "loss": 0.7399, "lr": 3.8221657734718855e-05, "epoch": 0.39052316814475935, "percentage": 39.05, "elapsed_time": "2:08:58", "remaining_time": "3:21:18"}
|
||||
{"current_steps": 3830, "total_steps": 9782, "loss": 0.7077, "lr": 3.814585275570209e-05, "epoch": 0.3915454801032535, "percentage": 39.15, "elapsed_time": "2:09:17", "remaining_time": "3:20:54"}
|
||||
{"current_steps": 3840, "total_steps": 9782, "loss": 0.7028, "lr": 3.8069880349242457e-05, "epoch": 0.39256779206174763, "percentage": 39.26, "elapsed_time": "2:09:35", "remaining_time": "3:20:32"}
|
||||
{"current_steps": 3850, "total_steps": 9782, "loss": 0.7084, "lr": 3.7993741482935293e-05, "epoch": 0.3935901040202418, "percentage": 39.36, "elapsed_time": "2:09:54", "remaining_time": "3:20:09"}
|
||||
{"current_steps": 3860, "total_steps": 9782, "loss": 0.704, "lr": 3.791743712649598e-05, "epoch": 0.3946124159787359, "percentage": 39.46, "elapsed_time": "2:10:12", "remaining_time": "3:19:45"}
|
||||
{"current_steps": 3870, "total_steps": 9782, "loss": 0.6932, "lr": 3.784096825174762e-05, "epoch": 0.39563472793723004, "percentage": 39.56, "elapsed_time": "2:10:30", "remaining_time": "3:19:22"}
|
||||
{"current_steps": 3880, "total_steps": 9782, "loss": 0.6952, "lr": 3.776433583260863e-05, "epoch": 0.3966570398957242, "percentage": 39.66, "elapsed_time": "2:10:50", "remaining_time": "3:19:01"}
|
||||
{"current_steps": 3890, "total_steps": 9782, "loss": 0.6886, "lr": 3.768754084508036e-05, "epoch": 0.3976793518542183, "percentage": 39.77, "elapsed_time": "2:11:09", "remaining_time": "3:18:38"}
|
||||
{"current_steps": 3900, "total_steps": 9782, "loss": 0.6923, "lr": 3.761058426723463e-05, "epoch": 0.39870166381271244, "percentage": 39.87, "elapsed_time": "2:11:27", "remaining_time": "3:18:16"}
|
||||
{"current_steps": 3910, "total_steps": 9782, "loss": 0.6944, "lr": 3.753346707920134e-05, "epoch": 0.3997239757712066, "percentage": 39.97, "elapsed_time": "2:11:47", "remaining_time": "3:17:55"}
|
||||
{"current_steps": 3920, "total_steps": 9782, "loss": 0.7191, "lr": 3.745619026315591e-05, "epoch": 0.4007462877297007, "percentage": 40.07, "elapsed_time": "2:12:05", "remaining_time": "3:17:31"}
|
||||
{"current_steps": 3930, "total_steps": 9782, "loss": 0.6887, "lr": 3.737875480330681e-05, "epoch": 0.40176859968819484, "percentage": 40.18, "elapsed_time": "2:12:25", "remaining_time": "3:17:10"}
|
||||
{"current_steps": 3940, "total_steps": 9782, "loss": 0.6788, "lr": 3.7301161685883046e-05, "epoch": 0.402790911646689, "percentage": 40.28, "elapsed_time": "2:12:44", "remaining_time": "3:16:48"}
|
||||
{"current_steps": 3950, "total_steps": 9782, "loss": 0.6841, "lr": 3.7223411899121527e-05, "epoch": 0.4038132236051831, "percentage": 40.38, "elapsed_time": "2:13:03", "remaining_time": "3:16:27"}
|
||||
{"current_steps": 3960, "total_steps": 9782, "loss": 0.6791, "lr": 3.714550643325458e-05, "epoch": 0.40483553556367724, "percentage": 40.48, "elapsed_time": "2:13:24", "remaining_time": "3:16:07"}
|
||||
{"current_steps": 3970, "total_steps": 9782, "loss": 0.6964, "lr": 3.7067446280497227e-05, "epoch": 0.4058578475221714, "percentage": 40.58, "elapsed_time": "2:13:43", "remaining_time": "3:15:45"}
|
||||
{"current_steps": 3980, "total_steps": 9782, "loss": 0.6751, "lr": 3.698923243503464e-05, "epoch": 0.4068801594806655, "percentage": 40.69, "elapsed_time": "2:14:03", "remaining_time": "3:15:26"}
|
||||
{"current_steps": 3990, "total_steps": 9782, "loss": 0.6709, "lr": 3.6910865893009445e-05, "epoch": 0.40790247143915964, "percentage": 40.79, "elapsed_time": "2:14:22", "remaining_time": "3:15:03"}
|
||||
{"current_steps": 4000, "total_steps": 9782, "loss": 0.6693, "lr": 3.6832347652509003e-05, "epoch": 0.4089247833976538, "percentage": 40.89, "elapsed_time": "2:14:41", "remaining_time": "3:14:41"}
|
||||
{"current_steps": 4010, "total_steps": 9782, "loss": 0.6668, "lr": 3.6753678713552766e-05, "epoch": 0.40994709535614793, "percentage": 40.99, "elapsed_time": "2:15:01", "remaining_time": "3:14:20"}
|
||||
{"current_steps": 4020, "total_steps": 9782, "loss": 0.672, "lr": 3.6674860078079464e-05, "epoch": 0.41096940731464204, "percentage": 41.1, "elapsed_time": "2:15:20", "remaining_time": "3:13:58"}
|
||||
{"current_steps": 4030, "total_steps": 9782, "loss": 0.6732, "lr": 3.659589274993442e-05, "epoch": 0.4119917192731362, "percentage": 41.2, "elapsed_time": "2:15:39", "remaining_time": "3:13:37"}
|
||||
{"current_steps": 4040, "total_steps": 9782, "loss": 0.6563, "lr": 3.651677773485671e-05, "epoch": 0.41301403123163033, "percentage": 41.3, "elapsed_time": "2:16:00", "remaining_time": "3:13:17"}
|
||||
{"current_steps": 4050, "total_steps": 9782, "loss": 0.6692, "lr": 3.643751604046637e-05, "epoch": 0.41403634319012445, "percentage": 41.4, "elapsed_time": "2:16:19", "remaining_time": "3:12:57"}
|
||||
{"current_steps": 4060, "total_steps": 9782, "loss": 0.6637, "lr": 3.6358108676251564e-05, "epoch": 0.4150586551486186, "percentage": 41.5, "elapsed_time": "2:16:39", "remaining_time": "3:12:35"}
|
||||
{"current_steps": 4070, "total_steps": 9782, "loss": 0.6664, "lr": 3.627855665355574e-05, "epoch": 0.41608096710711273, "percentage": 41.61, "elapsed_time": "2:16:59", "remaining_time": "3:12:15"}
|
||||
{"current_steps": 4080, "total_steps": 9782, "loss": 0.6661, "lr": 3.619886098556471e-05, "epoch": 0.41710327906560685, "percentage": 41.71, "elapsed_time": "2:17:19", "remaining_time": "3:11:54"}
|
||||
{"current_steps": 4090, "total_steps": 9782, "loss": 0.6784, "lr": 3.6119022687293814e-05, "epoch": 0.418125591024101, "percentage": 41.81, "elapsed_time": "2:17:38", "remaining_time": "3:11:33"}
|
||||
{"current_steps": 4100, "total_steps": 9782, "loss": 0.6633, "lr": 3.603904277557491e-05, "epoch": 0.41914790298259513, "percentage": 41.91, "elapsed_time": "2:17:59", "remaining_time": "3:11:14"}
|
||||
{"current_steps": 4110, "total_steps": 9782, "loss": 0.6519, "lr": 3.5958922269043494e-05, "epoch": 0.42017021494108925, "percentage": 42.02, "elapsed_time": "2:18:19", "remaining_time": "3:10:53"}
|
||||
{"current_steps": 4120, "total_steps": 9782, "loss": 0.6659, "lr": 3.587866218812568e-05, "epoch": 0.4211925268995834, "percentage": 42.12, "elapsed_time": "2:18:38", "remaining_time": "3:10:32"}
|
||||
{"current_steps": 4130, "total_steps": 9782, "loss": 0.6647, "lr": 3.579826355502522e-05, "epoch": 0.42221483885807753, "percentage": 42.22, "elapsed_time": "2:18:59", "remaining_time": "3:10:12"}
|
||||
{"current_steps": 4140, "total_steps": 9782, "loss": 0.6668, "lr": 3.571772739371053e-05, "epoch": 0.42323715081657165, "percentage": 42.32, "elapsed_time": "2:19:19", "remaining_time": "3:09:51"}
|
||||
{"current_steps": 4150, "total_steps": 9782, "loss": 0.669, "lr": 3.563705472990152e-05, "epoch": 0.4242594627750658, "percentage": 42.42, "elapsed_time": "2:19:39", "remaining_time": "3:09:32"}
|
||||
{"current_steps": 4160, "total_steps": 9782, "loss": 0.6523, "lr": 3.55562465910567e-05, "epoch": 0.42528177473355994, "percentage": 42.53, "elapsed_time": "2:20:00", "remaining_time": "3:09:12"}
|
||||
{"current_steps": 4170, "total_steps": 9782, "loss": 0.6547, "lr": 3.547530400635996e-05, "epoch": 0.4263040866920541, "percentage": 42.63, "elapsed_time": "2:20:20", "remaining_time": "3:08:52"}
|
||||
{"current_steps": 4180, "total_steps": 9782, "loss": 0.6475, "lr": 3.5394228006707516e-05, "epoch": 0.4273263986505482, "percentage": 42.73, "elapsed_time": "2:20:41", "remaining_time": "3:08:33"}
|
||||
{"current_steps": 4190, "total_steps": 9782, "loss": 0.6531, "lr": 3.53130196246948e-05, "epoch": 0.42834871060904234, "percentage": 42.83, "elapsed_time": "2:21:01", "remaining_time": "3:08:13"}
|
||||
{"current_steps": 4200, "total_steps": 9782, "loss": 0.6489, "lr": 3.523167989460325e-05, "epoch": 0.4293710225675365, "percentage": 42.94, "elapsed_time": "2:21:22", "remaining_time": "3:07:53"}
|
||||
{"current_steps": 4210, "total_steps": 9782, "loss": 0.6544, "lr": 3.515020985238721e-05, "epoch": 0.4303933345260306, "percentage": 43.04, "elapsed_time": "2:21:43", "remaining_time": "3:07:33"}
|
||||
{"current_steps": 4220, "total_steps": 9782, "loss": 0.654, "lr": 3.5068610535660674e-05, "epoch": 0.43141564648452474, "percentage": 43.14, "elapsed_time": "2:22:03", "remaining_time": "3:07:13"}
|
||||
{"current_steps": 4230, "total_steps": 9782, "loss": 0.6492, "lr": 3.4986882983684094e-05, "epoch": 0.4324379584430189, "percentage": 43.24, "elapsed_time": "2:22:24", "remaining_time": "3:06:54"}
|
||||
{"current_steps": 4240, "total_steps": 9782, "loss": 0.6457, "lr": 3.490502823735115e-05, "epoch": 0.433460270401513, "percentage": 43.34, "elapsed_time": "2:22:44", "remaining_time": "3:06:34"}
|
||||
{"current_steps": 4250, "total_steps": 9782, "loss": 0.645, "lr": 3.482304733917548e-05, "epoch": 0.43448258236000714, "percentage": 43.45, "elapsed_time": "2:23:06", "remaining_time": "3:06:16"}
|
||||
{"current_steps": 4260, "total_steps": 9782, "loss": 0.6456, "lr": 3.474094133327743e-05, "epoch": 0.4355048943185013, "percentage": 43.55, "elapsed_time": "2:23:27", "remaining_time": "3:05:57"}
|
||||
{"current_steps": 4270, "total_steps": 9782, "loss": 0.6396, "lr": 3.465871126537072e-05, "epoch": 0.4365272062769954, "percentage": 43.65, "elapsed_time": "2:23:48", "remaining_time": "3:05:37"}
|
||||
{"current_steps": 4280, "total_steps": 9782, "loss": 0.6573, "lr": 3.457635818274912e-05, "epoch": 0.43754951823548954, "percentage": 43.75, "elapsed_time": "2:24:07", "remaining_time": "3:05:16"}
|
||||
{"current_steps": 4290, "total_steps": 9782, "loss": 0.6419, "lr": 3.449388313427319e-05, "epoch": 0.4385718301939837, "percentage": 43.86, "elapsed_time": "2:24:28", "remaining_time": "3:04:56"}
|
||||
{"current_steps": 4300, "total_steps": 9782, "loss": 0.6326, "lr": 3.441128717035681e-05, "epoch": 0.43959414215247783, "percentage": 43.96, "elapsed_time": "2:24:48", "remaining_time": "3:04:37"}
|
||||
{"current_steps": 4310, "total_steps": 9782, "loss": 0.6501, "lr": 3.432857134295387e-05, "epoch": 0.44061645411097194, "percentage": 44.06, "elapsed_time": "2:25:09", "remaining_time": "3:04:17"}
|
||||
{"current_steps": 4320, "total_steps": 9782, "loss": 0.6517, "lr": 3.42457367055449e-05, "epoch": 0.4416387660694661, "percentage": 44.16, "elapsed_time": "2:25:28", "remaining_time": "3:03:56"}
|
||||
{"current_steps": 4330, "total_steps": 9782, "loss": 0.6474, "lr": 3.4162784313123524e-05, "epoch": 0.44266107802796023, "percentage": 44.26, "elapsed_time": "2:25:50", "remaining_time": "3:03:37"}
|
||||
{"current_steps": 4340, "total_steps": 9782, "loss": 0.6451, "lr": 3.40797152221832e-05, "epoch": 0.44368338998645435, "percentage": 44.37, "elapsed_time": "2:26:11", "remaining_time": "3:03:18"}
|
||||
{"current_steps": 4350, "total_steps": 9782, "loss": 0.651, "lr": 3.399653049070363e-05, "epoch": 0.4447057019449485, "percentage": 44.47, "elapsed_time": "2:26:32", "remaining_time": "3:03:00"}
|
||||
{"current_steps": 4360, "total_steps": 9782, "loss": 0.6485, "lr": 3.3913231178137335e-05, "epoch": 0.44572801390344263, "percentage": 44.57, "elapsed_time": "2:26:52", "remaining_time": "3:02:39"}
|
||||
{"current_steps": 4370, "total_steps": 9782, "loss": 0.6447, "lr": 3.382981834539615e-05, "epoch": 0.44675032586193675, "percentage": 44.67, "elapsed_time": "2:27:13", "remaining_time": "3:02:19"}
|
||||
{"current_steps": 4380, "total_steps": 9782, "loss": 0.6408, "lr": 3.3746293054837746e-05, "epoch": 0.4477726378204309, "percentage": 44.78, "elapsed_time": "2:27:33", "remaining_time": "3:01:59"}
|
||||
{"current_steps": 4390, "total_steps": 9782, "loss": 0.6328, "lr": 3.3662656370252045e-05, "epoch": 0.44879494977892503, "percentage": 44.88, "elapsed_time": "2:27:55", "remaining_time": "3:01:40"}
|
||||
{"current_steps": 4400, "total_steps": 9782, "loss": 0.6449, "lr": 3.357890935684771e-05, "epoch": 0.44981726173741915, "percentage": 44.98, "elapsed_time": "2:28:16", "remaining_time": "3:01:22"}
|
||||
{"current_steps": 4410, "total_steps": 9782, "loss": 0.6375, "lr": 3.3495053081238566e-05, "epoch": 0.4508395736959133, "percentage": 45.08, "elapsed_time": "2:28:35", "remaining_time": "3:01:00"}
|
||||
{"current_steps": 4420, "total_steps": 9782, "loss": 0.6425, "lr": 3.341108861143002e-05, "epoch": 0.45186188565440744, "percentage": 45.19, "elapsed_time": "2:28:57", "remaining_time": "3:00:42"}
|
||||
{"current_steps": 4430, "total_steps": 9782, "loss": 0.6353, "lr": 3.332701701680546e-05, "epoch": 0.45288419761290155, "percentage": 45.29, "elapsed_time": "2:29:20", "remaining_time": "3:00:25"}
|
||||
{"current_steps": 4440, "total_steps": 9782, "loss": 0.6355, "lr": 3.3242839368112604e-05, "epoch": 0.4539065095713957, "percentage": 45.39, "elapsed_time": "2:29:43", "remaining_time": "3:00:08"}
|
||||
{"current_steps": 4450, "total_steps": 9782, "loss": 0.6322, "lr": 3.315855673744994e-05, "epoch": 0.45492882152988984, "percentage": 45.49, "elapsed_time": "2:30:05", "remaining_time": "2:59:50"}
|
||||
{"current_steps": 4460, "total_steps": 9782, "loss": 0.6299, "lr": 3.307417019825296e-05, "epoch": 0.45595113348838395, "percentage": 45.59, "elapsed_time": "2:30:27", "remaining_time": "2:59:31"}
|
||||
{"current_steps": 4470, "total_steps": 9782, "loss": 0.6309, "lr": 3.2989680825280605e-05, "epoch": 0.4569734454468781, "percentage": 45.7, "elapsed_time": "2:30:49", "remaining_time": "2:59:13"}
|
||||
{"current_steps": 4480, "total_steps": 9782, "loss": 0.6363, "lr": 3.290508969460149e-05, "epoch": 0.45799575740537224, "percentage": 45.8, "elapsed_time": "2:31:10", "remaining_time": "2:58:54"}
|
||||
{"current_steps": 4490, "total_steps": 9782, "loss": 0.6365, "lr": 3.2820397883580224e-05, "epoch": 0.4590180693638664, "percentage": 45.9, "elapsed_time": "2:31:33", "remaining_time": "2:58:37"}
|
||||
{"current_steps": 4500, "total_steps": 9782, "loss": 0.636, "lr": 3.273560647086373e-05, "epoch": 0.4600403813223605, "percentage": 46.0, "elapsed_time": "2:31:53", "remaining_time": "2:58:17"}
|
||||
{"current_steps": 4510, "total_steps": 9782, "loss": 0.6175, "lr": 3.265071653636744e-05, "epoch": 0.46106269328085464, "percentage": 46.11, "elapsed_time": "2:32:14", "remaining_time": "2:57:58"}
|
||||
{"current_steps": 4520, "total_steps": 9782, "loss": 0.6262, "lr": 3.256572916126158e-05, "epoch": 0.4620850052393488, "percentage": 46.21, "elapsed_time": "2:32:36", "remaining_time": "2:57:39"}
|
||||
{"current_steps": 4530, "total_steps": 9782, "loss": 0.6304, "lr": 3.248064542795741e-05, "epoch": 0.4631073171978429, "percentage": 46.31, "elapsed_time": "2:32:57", "remaining_time": "2:57:20"}
|
||||
{"current_steps": 4540, "total_steps": 9782, "loss": 0.6345, "lr": 3.239546642009341e-05, "epoch": 0.46412962915633704, "percentage": 46.41, "elapsed_time": "2:33:17", "remaining_time": "2:56:59"}
|
||||
{"current_steps": 4550, "total_steps": 9782, "loss": 0.6363, "lr": 3.231019322252148e-05, "epoch": 0.4651519411148312, "percentage": 46.51, "elapsed_time": "2:33:38", "remaining_time": "2:56:40"}
|
||||
{"current_steps": 4560, "total_steps": 9782, "loss": 0.624, "lr": 3.222482692129315e-05, "epoch": 0.46617425307332533, "percentage": 46.62, "elapsed_time": "2:34:00", "remaining_time": "2:56:22"}
|
||||
{"current_steps": 4570, "total_steps": 9782, "loss": 0.6309, "lr": 3.213936860364572e-05, "epoch": 0.46719656503181944, "percentage": 46.72, "elapsed_time": "2:34:21", "remaining_time": "2:56:02"}
|
||||
{"current_steps": 4580, "total_steps": 9782, "loss": 0.6211, "lr": 3.2053819357988446e-05, "epoch": 0.4682188769903136, "percentage": 46.82, "elapsed_time": "2:34:41", "remaining_time": "2:55:42"}
|
||||
{"current_steps": 4590, "total_steps": 9782, "loss": 0.6228, "lr": 3.196818027388861e-05, "epoch": 0.46924118894880773, "percentage": 46.92, "elapsed_time": "2:35:02", "remaining_time": "2:55:22"}
|
||||
{"current_steps": 4600, "total_steps": 9782, "loss": 0.6186, "lr": 3.188245244205774e-05, "epoch": 0.47026350090730185, "percentage": 47.03, "elapsed_time": "2:35:22", "remaining_time": "2:55:02"}
|
||||
{"current_steps": 4610, "total_steps": 9782, "loss": 0.6226, "lr": 3.179663695433764e-05, "epoch": 0.471285812865796, "percentage": 47.13, "elapsed_time": "2:35:44", "remaining_time": "2:54:43"}
|
||||
{"current_steps": 4620, "total_steps": 9782, "loss": 0.6404, "lr": 3.171073490368651e-05, "epoch": 0.47230812482429013, "percentage": 47.23, "elapsed_time": "2:36:05", "remaining_time": "2:54:24"}
|
||||
{"current_steps": 4630, "total_steps": 9782, "loss": 0.6333, "lr": 3.162474738416506e-05, "epoch": 0.47333043678278425, "percentage": 47.33, "elapsed_time": "2:36:27", "remaining_time": "2:54:05"}
|
||||
{"current_steps": 4640, "total_steps": 9782, "loss": 0.6127, "lr": 3.153867549092249e-05, "epoch": 0.4743527487412784, "percentage": 47.43, "elapsed_time": "2:36:50", "remaining_time": "2:53:48"}
|
||||
{"current_steps": 4650, "total_steps": 9782, "loss": 0.6239, "lr": 3.145252032018264e-05, "epoch": 0.47537506069977253, "percentage": 47.54, "elapsed_time": "2:37:13", "remaining_time": "2:53:31"}
|
||||
{"current_steps": 4660, "total_steps": 9782, "loss": 0.6347, "lr": 3.136628296922997e-05, "epoch": 0.47639737265826665, "percentage": 47.64, "elapsed_time": "2:37:36", "remaining_time": "2:53:14"}
|
||||
{"current_steps": 4670, "total_steps": 9782, "loss": 0.6276, "lr": 3.127996453639559e-05, "epoch": 0.4774196846167608, "percentage": 47.74, "elapsed_time": "2:37:58", "remaining_time": "2:52:55"}
|
||||
{"current_steps": 4680, "total_steps": 9782, "loss": 0.6254, "lr": 3.119356612104329e-05, "epoch": 0.47844199657525494, "percentage": 47.84, "elapsed_time": "2:38:20", "remaining_time": "2:52:36"}
|
||||
{"current_steps": 4690, "total_steps": 9782, "loss": 0.6275, "lr": 3.110708882355553e-05, "epoch": 0.47946430853374905, "percentage": 47.95, "elapsed_time": "2:38:42", "remaining_time": "2:52:18"}
|
||||
{"current_steps": 4700, "total_steps": 9782, "loss": 0.6356, "lr": 3.102053374531941e-05, "epoch": 0.4804866204922432, "percentage": 48.05, "elapsed_time": "2:39:04", "remaining_time": "2:52:00"}
|
||||
{"current_steps": 4710, "total_steps": 9782, "loss": 0.6159, "lr": 3.0933901988712694e-05, "epoch": 0.48150893245073734, "percentage": 48.15, "elapsed_time": "2:39:28", "remaining_time": "2:51:43"}
|
||||
{"current_steps": 4720, "total_steps": 9782, "loss": 0.636, "lr": 3.084719465708967e-05, "epoch": 0.48253124440923145, "percentage": 48.25, "elapsed_time": "2:39:50", "remaining_time": "2:51:25"}
|
||||
{"current_steps": 4730, "total_steps": 9782, "loss": 0.6117, "lr": 3.076041285476722e-05, "epoch": 0.4835535563677256, "percentage": 48.35, "elapsed_time": "2:40:11", "remaining_time": "2:51:06"}
|
||||
{"current_steps": 4740, "total_steps": 9782, "loss": 0.6151, "lr": 3.067355768701067e-05, "epoch": 0.48457586832621974, "percentage": 48.46, "elapsed_time": "2:40:33", "remaining_time": "2:50:47"}
|
||||
{"current_steps": 4750, "total_steps": 9782, "loss": 0.6126, "lr": 3.0586630260019726e-05, "epoch": 0.48559818028471385, "percentage": 48.56, "elapsed_time": "2:40:54", "remaining_time": "2:50:28"}
|
||||
{"current_steps": 4760, "total_steps": 9782, "loss": 0.619, "lr": 3.049963168091443e-05, "epoch": 0.486620492243208, "percentage": 48.66, "elapsed_time": "2:41:15", "remaining_time": "2:50:08"}
|
||||
{"current_steps": 4770, "total_steps": 9782, "loss": 0.6103, "lr": 3.0412563057720995e-05, "epoch": 0.48764280420170214, "percentage": 48.76, "elapsed_time": "2:41:37", "remaining_time": "2:49:49"}
|
||||
{"current_steps": 4780, "total_steps": 9782, "loss": 0.6148, "lr": 3.032542549935775e-05, "epoch": 0.4886651161601963, "percentage": 48.87, "elapsed_time": "2:41:59", "remaining_time": "2:49:31"}
|
||||
{"current_steps": 4790, "total_steps": 9782, "loss": 0.6154, "lr": 3.0238220115620976e-05, "epoch": 0.4896874281186904, "percentage": 48.97, "elapsed_time": "2:42:21", "remaining_time": "2:49:12"}
|
||||
{"current_steps": 4800, "total_steps": 9782, "loss": 0.6166, "lr": 3.015094801717079e-05, "epoch": 0.49070974007718454, "percentage": 49.07, "elapsed_time": "2:42:44", "remaining_time": "2:48:54"}
|
||||
{"current_steps": 4810, "total_steps": 9782, "loss": 0.6206, "lr": 3.0063610315517003e-05, "epoch": 0.4917320520356787, "percentage": 49.17, "elapsed_time": "2:43:06", "remaining_time": "2:48:36"}
|
||||
{"current_steps": 4820, "total_steps": 9782, "loss": 0.6209, "lr": 2.997620812300496e-05, "epoch": 0.49275436399417283, "percentage": 49.27, "elapsed_time": "2:43:30", "remaining_time": "2:48:19"}
|
||||
{"current_steps": 4830, "total_steps": 9782, "loss": 0.618, "lr": 2.9888742552801358e-05, "epoch": 0.49377667595266694, "percentage": 49.38, "elapsed_time": "2:43:52", "remaining_time": "2:48:01"}
|
||||
{"current_steps": 4840, "total_steps": 9782, "loss": 0.6153, "lr": 2.9801214718880095e-05, "epoch": 0.4947989879111611, "percentage": 49.48, "elapsed_time": "2:44:14", "remaining_time": "2:47:41"}
|
||||
{"current_steps": 4850, "total_steps": 9782, "loss": 0.6158, "lr": 2.971362573600806e-05, "epoch": 0.49582129986965523, "percentage": 49.58, "elapsed_time": "2:44:35", "remaining_time": "2:47:22"}
|
||||
{"current_steps": 4860, "total_steps": 9782, "loss": 0.6118, "lr": 2.9625976719730948e-05, "epoch": 0.49684361182814935, "percentage": 49.68, "elapsed_time": "2:44:57", "remaining_time": "2:47:03"}
|
||||
{"current_steps": 4870, "total_steps": 9782, "loss": 0.618, "lr": 2.9538268786359046e-05, "epoch": 0.4978659237866435, "percentage": 49.79, "elapsed_time": "2:45:19", "remaining_time": "2:46:45"}
|
||||
{"current_steps": 4880, "total_steps": 9782, "loss": 0.624, "lr": 2.9450503052953004e-05, "epoch": 0.49888823574513763, "percentage": 49.89, "elapsed_time": "2:45:40", "remaining_time": "2:46:25"}
|
||||
{"current_steps": 4890, "total_steps": 9782, "loss": 0.6117, "lr": 2.9362680637309664e-05, "epoch": 0.49991054770363175, "percentage": 49.99, "elapsed_time": "2:46:02", "remaining_time": "2:46:06"}
|
||||
{"current_steps": 4900, "total_steps": 9782, "loss": 0.6167, "lr": 2.9274802657947724e-05, "epoch": 0.5009328596621259, "percentage": 50.09, "elapsed_time": "2:46:24", "remaining_time": "2:45:47"}
|
||||
{"current_steps": 4910, "total_steps": 9782, "loss": 0.6133, "lr": 2.9186870234093592e-05, "epoch": 0.50195517162062, "percentage": 50.19, "elapsed_time": "2:46:45", "remaining_time": "2:45:28"}
|
||||
{"current_steps": 4920, "total_steps": 9782, "loss": 0.6117, "lr": 2.909888448566708e-05, "epoch": 0.5029774835791142, "percentage": 50.3, "elapsed_time": "2:47:10", "remaining_time": "2:45:11"}
|
||||
{"current_steps": 4930, "total_steps": 9782, "loss": 0.6132, "lr": 2.9010846533267118e-05, "epoch": 0.5039997955376083, "percentage": 50.4, "elapsed_time": "2:47:32", "remaining_time": "2:44:53"}
|
||||
{"current_steps": 4940, "total_steps": 9782, "loss": 0.6191, "lr": 2.8922757498157572e-05, "epoch": 0.5050221074961024, "percentage": 50.5, "elapsed_time": "2:47:57", "remaining_time": "2:44:37"}
|
||||
{"current_steps": 4950, "total_steps": 9782, "loss": 0.6144, "lr": 2.883461850225284e-05, "epoch": 0.5060444194545966, "percentage": 50.6, "elapsed_time": "2:48:20", "remaining_time": "2:44:19"}
|
||||
{"current_steps": 4960, "total_steps": 9782, "loss": 0.6108, "lr": 2.874643066810368e-05, "epoch": 0.5070667314130907, "percentage": 50.71, "elapsed_time": "2:48:43", "remaining_time": "2:44:02"}
|
||||
{"current_steps": 4970, "total_steps": 9782, "loss": 0.617, "lr": 2.8658195118882835e-05, "epoch": 0.5080890433715849, "percentage": 50.81, "elapsed_time": "2:49:05", "remaining_time": "2:43:42"}
|
||||
{"current_steps": 4980, "total_steps": 9782, "loss": 0.6143, "lr": 2.856991297837076e-05, "epoch": 0.509111355330079, "percentage": 50.91, "elapsed_time": "2:49:28", "remaining_time": "2:43:25"}
|
||||
{"current_steps": 4990, "total_steps": 9782, "loss": 0.6086, "lr": 2.8481585370941295e-05, "epoch": 0.5101336672885731, "percentage": 51.01, "elapsed_time": "2:49:52", "remaining_time": "2:43:07"}
|
||||
{"current_steps": 5000, "total_steps": 9782, "loss": 0.6048, "lr": 2.8393213421547366e-05, "epoch": 0.5111559792470672, "percentage": 51.11, "elapsed_time": "2:50:14", "remaining_time": "2:42:49"}
|
||||
{"current_steps": 5010, "total_steps": 9782, "loss": 0.6103, "lr": 2.830479825570663e-05, "epoch": 0.5121782912055614, "percentage": 51.22, "elapsed_time": "2:50:37", "remaining_time": "2:42:31"}
|
||||
{"current_steps": 5020, "total_steps": 9782, "loss": 0.613, "lr": 2.8216340999487184e-05, "epoch": 0.5132006031640555, "percentage": 51.32, "elapsed_time": "2:51:00", "remaining_time": "2:42:13"}
|
||||
{"current_steps": 5030, "total_steps": 9782, "loss": 0.6211, "lr": 2.8127842779493152e-05, "epoch": 0.5142229151225497, "percentage": 51.42, "elapsed_time": "2:51:23", "remaining_time": "2:41:55"}
|
||||
{"current_steps": 5040, "total_steps": 9782, "loss": 0.609, "lr": 2.8039304722850408e-05, "epoch": 0.5152452270810438, "percentage": 51.52, "elapsed_time": "2:51:46", "remaining_time": "2:41:37"}
|
||||
{"current_steps": 5050, "total_steps": 9782, "loss": 0.6101, "lr": 2.795072795719219e-05, "epoch": 0.5162675390395379, "percentage": 51.63, "elapsed_time": "2:52:10", "remaining_time": "2:41:19"}
|
||||
{"current_steps": 5060, "total_steps": 9782, "loss": 0.5994, "lr": 2.7862113610644715e-05, "epoch": 0.517289850998032, "percentage": 51.73, "elapsed_time": "2:52:32", "remaining_time": "2:41:01"}
|
||||
{"current_steps": 5070, "total_steps": 9782, "loss": 0.6125, "lr": 2.7773462811812877e-05, "epoch": 0.5183121629565262, "percentage": 51.83, "elapsed_time": "2:52:55", "remaining_time": "2:40:43"}
|
||||
{"current_steps": 5080, "total_steps": 9782, "loss": 0.6051, "lr": 2.768477668976579e-05, "epoch": 0.5193344749150203, "percentage": 51.93, "elapsed_time": "2:53:19", "remaining_time": "2:40:25"}
|
||||
{"current_steps": 5090, "total_steps": 9782, "loss": 0.5927, "lr": 2.7596056374022473e-05, "epoch": 0.5203567868735145, "percentage": 52.03, "elapsed_time": "2:53:42", "remaining_time": "2:40:07"}
|
||||
{"current_steps": 5100, "total_steps": 9782, "loss": 0.6042, "lr": 2.7507302994537432e-05, "epoch": 0.5213790988320086, "percentage": 52.14, "elapsed_time": "2:54:05", "remaining_time": "2:39:49"}
|
||||
{"current_steps": 5110, "total_steps": 9782, "loss": 0.604, "lr": 2.7418517681686283e-05, "epoch": 0.5224014107905027, "percentage": 52.24, "elapsed_time": "2:54:28", "remaining_time": "2:39:31"}
|
||||
{"current_steps": 5120, "total_steps": 9782, "loss": 0.6002, "lr": 2.7329701566251354e-05, "epoch": 0.5234237227489968, "percentage": 52.34, "elapsed_time": "2:54:51", "remaining_time": "2:39:13"}
|
||||
{"current_steps": 5130, "total_steps": 9782, "loss": 0.5997, "lr": 2.724085577940726e-05, "epoch": 0.524446034707491, "percentage": 52.44, "elapsed_time": "2:55:15", "remaining_time": "2:38:55"}
|
||||
{"current_steps": 5140, "total_steps": 9782, "loss": 0.6054, "lr": 2.7151981452706525e-05, "epoch": 0.5254683466659851, "percentage": 52.55, "elapsed_time": "2:55:38", "remaining_time": "2:38:37"}
|
||||
{"current_steps": 5150, "total_steps": 9782, "loss": 0.6071, "lr": 2.7063079718065182e-05, "epoch": 0.5264906586244793, "percentage": 52.65, "elapsed_time": "2:56:00", "remaining_time": "2:38:18"}
|
||||
{"current_steps": 5160, "total_steps": 9782, "loss": 0.6083, "lr": 2.6974151707748302e-05, "epoch": 0.5275129705829734, "percentage": 52.75, "elapsed_time": "2:56:24", "remaining_time": "2:38:00"}
|
||||
{"current_steps": 5170, "total_steps": 9782, "loss": 0.6008, "lr": 2.688519855435563e-05, "epoch": 0.5285352825414675, "percentage": 52.85, "elapsed_time": "2:56:48", "remaining_time": "2:37:43"}
|
||||
{"current_steps": 5180, "total_steps": 9782, "loss": 0.6038, "lr": 2.6796221390807117e-05, "epoch": 0.5295575944999616, "percentage": 52.95, "elapsed_time": "2:57:12", "remaining_time": "2:37:26"}
|
||||
{"current_steps": 5190, "total_steps": 9782, "loss": 0.6123, "lr": 2.6707221350328526e-05, "epoch": 0.5305799064584558, "percentage": 53.06, "elapsed_time": "2:57:36", "remaining_time": "2:37:08"}
|
||||
{"current_steps": 5200, "total_steps": 9782, "loss": 0.6132, "lr": 2.6618199566436993e-05, "epoch": 0.5316022184169499, "percentage": 53.16, "elapsed_time": "2:58:00", "remaining_time": "2:36:50"}
|
||||
{"current_steps": 5210, "total_steps": 9782, "loss": 0.6043, "lr": 2.6529157172926546e-05, "epoch": 0.5326245303754441, "percentage": 53.26, "elapsed_time": "2:58:22", "remaining_time": "2:36:32"}
|
||||
{"current_steps": 5220, "total_steps": 9782, "loss": 0.6024, "lr": 2.644009530385374e-05, "epoch": 0.5336468423339382, "percentage": 53.36, "elapsed_time": "2:58:46", "remaining_time": "2:36:14"}
|
||||
{"current_steps": 5230, "total_steps": 9782, "loss": 0.6052, "lr": 2.6351015093523147e-05, "epoch": 0.5346691542924323, "percentage": 53.47, "elapsed_time": "2:59:10", "remaining_time": "2:35:56"}
|
||||
{"current_steps": 5240, "total_steps": 9782, "loss": 0.597, "lr": 2.6261917676472946e-05, "epoch": 0.5356914662509265, "percentage": 53.57, "elapsed_time": "2:59:34", "remaining_time": "2:35:39"}
|
||||
{"current_steps": 5250, "total_steps": 9782, "loss": 0.5985, "lr": 2.6172804187460465e-05, "epoch": 0.5367137782094206, "percentage": 53.67, "elapsed_time": "2:59:57", "remaining_time": "2:35:21"}
|
||||
{"current_steps": 5260, "total_steps": 9782, "loss": 0.596, "lr": 2.6083675761447712e-05, "epoch": 0.5377360901679148, "percentage": 53.77, "elapsed_time": "3:00:21", "remaining_time": "2:35:02"}
|
||||
{"current_steps": 5270, "total_steps": 9782, "loss": 0.6019, "lr": 2.5994533533586955e-05, "epoch": 0.5387584021264089, "percentage": 53.87, "elapsed_time": "3:00:44", "remaining_time": "2:34:45"}
|
||||
{"current_steps": 5280, "total_steps": 9782, "loss": 0.5928, "lr": 2.5905378639206242e-05, "epoch": 0.539780714084903, "percentage": 53.98, "elapsed_time": "3:01:08", "remaining_time": "2:34:26"}
|
||||
{"current_steps": 5290, "total_steps": 9782, "loss": 0.6035, "lr": 2.5816212213794926e-05, "epoch": 0.5408030260433971, "percentage": 54.08, "elapsed_time": "3:01:31", "remaining_time": "2:34:08"}
|
||||
{"current_steps": 5300, "total_steps": 9782, "loss": 0.6076, "lr": 2.5727035392989235e-05, "epoch": 0.5418253380018913, "percentage": 54.18, "elapsed_time": "3:01:55", "remaining_time": "2:33:50"}
|
||||
{"current_steps": 5310, "total_steps": 9782, "loss": 0.6014, "lr": 2.5637849312557795e-05, "epoch": 0.5428476499603854, "percentage": 54.28, "elapsed_time": "3:02:19", "remaining_time": "2:33:32"}
|
||||
{"current_steps": 5320, "total_steps": 9782, "loss": 0.609, "lr": 2.5548655108387144e-05, "epoch": 0.5438699619188796, "percentage": 54.39, "elapsed_time": "3:02:44", "remaining_time": "2:33:15"}
|
||||
{"current_steps": 5330, "total_steps": 9782, "loss": 0.606, "lr": 2.545945391646733e-05, "epoch": 0.5448922738773737, "percentage": 54.49, "elapsed_time": "3:03:07", "remaining_time": "2:32:57"}
|
||||
{"current_steps": 5340, "total_steps": 9782, "loss": 0.5994, "lr": 2.537024687287734e-05, "epoch": 0.5459145858358678, "percentage": 54.59, "elapsed_time": "3:03:29", "remaining_time": "2:32:38"}
|
||||
{"current_steps": 5350, "total_steps": 9782, "loss": 0.5942, "lr": 2.5281035113770734e-05, "epoch": 0.5469368977943619, "percentage": 54.69, "elapsed_time": "3:03:54", "remaining_time": "2:32:20"}
|
||||
{"current_steps": 5360, "total_steps": 9782, "loss": 0.6103, "lr": 2.519181977536111e-05, "epoch": 0.5479592097528561, "percentage": 54.79, "elapsed_time": "3:04:16", "remaining_time": "2:32:01"}
|
||||
{"current_steps": 5370, "total_steps": 9782, "loss": 0.5969, "lr": 2.510260199390765e-05, "epoch": 0.5489815217113502, "percentage": 54.9, "elapsed_time": "3:04:40", "remaining_time": "2:31:43"}
|
||||
{"current_steps": 5380, "total_steps": 9782, "loss": 0.5939, "lr": 2.5013382905700673e-05, "epoch": 0.5500038336698444, "percentage": 55.0, "elapsed_time": "3:05:02", "remaining_time": "2:31:24"}
|
||||
{"current_steps": 5390, "total_steps": 9782, "loss": 0.5981, "lr": 2.4924163647047103e-05, "epoch": 0.5510261456283385, "percentage": 55.1, "elapsed_time": "3:05:27", "remaining_time": "2:31:07"}
|
||||
{"current_steps": 5400, "total_steps": 9782, "loss": 0.5921, "lr": 2.483494535425607e-05, "epoch": 0.5520484575868326, "percentage": 55.2, "elapsed_time": "3:05:50", "remaining_time": "2:30:48"}
|
||||
{"current_steps": 5410, "total_steps": 9782, "loss": 0.5889, "lr": 2.4745729163624382e-05, "epoch": 0.5530707695453267, "percentage": 55.31, "elapsed_time": "3:06:14", "remaining_time": "2:30:30"}
|
||||
{"current_steps": 5420, "total_steps": 9782, "loss": 0.6031, "lr": 2.4656516211422084e-05, "epoch": 0.5540930815038209, "percentage": 55.41, "elapsed_time": "3:06:38", "remaining_time": "2:30:12"}
|
||||
{"current_steps": 5430, "total_steps": 9782, "loss": 0.588, "lr": 2.456730763387799e-05, "epoch": 0.555115393462315, "percentage": 55.51, "elapsed_time": "3:07:02", "remaining_time": "2:29:54"}
|
||||
{"current_steps": 5440, "total_steps": 9782, "loss": 0.5949, "lr": 2.4478104567165143e-05, "epoch": 0.5561377054208092, "percentage": 55.61, "elapsed_time": "3:07:25", "remaining_time": "2:29:35"}
|
||||
{"current_steps": 5450, "total_steps": 9782, "loss": 0.5976, "lr": 2.438890814738647e-05, "epoch": 0.5571600173793033, "percentage": 55.71, "elapsed_time": "3:07:49", "remaining_time": "2:29:17"}
|
||||
{"current_steps": 5460, "total_steps": 9782, "loss": 0.5888, "lr": 2.4299719510560184e-05, "epoch": 0.5581823293377974, "percentage": 55.82, "elapsed_time": "3:08:14", "remaining_time": "2:29:00"}
|
||||
{"current_steps": 5470, "total_steps": 9782, "loss": 0.5984, "lr": 2.421053979260541e-05, "epoch": 0.5592046412962915, "percentage": 55.92, "elapsed_time": "3:08:38", "remaining_time": "2:28:42"}
|
||||
{"current_steps": 5480, "total_steps": 9782, "loss": 0.5937, "lr": 2.4121370129327688e-05, "epoch": 0.5602269532547857, "percentage": 56.02, "elapsed_time": "3:09:01", "remaining_time": "2:28:23"}
|
||||
{"current_steps": 5490, "total_steps": 9782, "loss": 0.5938, "lr": 2.4032211656404442e-05, "epoch": 0.5612492652132798, "percentage": 56.12, "elapsed_time": "3:09:25", "remaining_time": "2:28:05"}
|
||||
{"current_steps": 5500, "total_steps": 9782, "loss": 0.597, "lr": 2.394306550937063e-05, "epoch": 0.562271577171774, "percentage": 56.23, "elapsed_time": "3:09:48", "remaining_time": "2:27:46"}
|
||||
{"current_steps": 5510, "total_steps": 9782, "loss": 0.5974, "lr": 2.3853932823604212e-05, "epoch": 0.5632938891302681, "percentage": 56.33, "elapsed_time": "3:10:13", "remaining_time": "2:27:28"}
|
||||
{"current_steps": 5520, "total_steps": 9782, "loss": 0.593, "lr": 2.376481473431171e-05, "epoch": 0.5643162010887622, "percentage": 56.43, "elapsed_time": "3:10:37", "remaining_time": "2:27:11"}
|
||||
{"current_steps": 5530, "total_steps": 9782, "loss": 0.5966, "lr": 2.367571237651371e-05, "epoch": 0.5653385130472564, "percentage": 56.53, "elapsed_time": "3:11:00", "remaining_time": "2:26:51"}
|
||||
{"current_steps": 5540, "total_steps": 9782, "loss": 0.5997, "lr": 2.3586626885030472e-05, "epoch": 0.5663608250057505, "percentage": 56.63, "elapsed_time": "3:11:23", "remaining_time": "2:26:33"}
|
||||
{"current_steps": 5550, "total_steps": 9782, "loss": 0.5916, "lr": 2.3497559394467443e-05, "epoch": 0.5673831369642447, "percentage": 56.74, "elapsed_time": "3:11:48", "remaining_time": "2:26:15"}
|
||||
{"current_steps": 5560, "total_steps": 9782, "loss": 0.5949, "lr": 2.3408511039200784e-05, "epoch": 0.5684054489227388, "percentage": 56.84, "elapsed_time": "3:12:12", "remaining_time": "2:25:56"}
|
||||
{"current_steps": 5570, "total_steps": 9782, "loss": 0.5886, "lr": 2.3319482953362982e-05, "epoch": 0.5694277608812329, "percentage": 56.94, "elapsed_time": "3:12:36", "remaining_time": "2:25:38"}
|
||||
{"current_steps": 5580, "total_steps": 9782, "loss": 0.5913, "lr": 2.3230476270828334e-05, "epoch": 0.570450072839727, "percentage": 57.04, "elapsed_time": "3:12:58", "remaining_time": "2:25:19"}
|
||||
{"current_steps": 5590, "total_steps": 9782, "loss": 0.599, "lr": 2.3141492125198554e-05, "epoch": 0.5714723847982212, "percentage": 57.15, "elapsed_time": "3:13:21", "remaining_time": "2:25:00"}
|
||||
{"current_steps": 5600, "total_steps": 9782, "loss": 0.5904, "lr": 2.3052531649788337e-05, "epoch": 0.5724946967567153, "percentage": 57.25, "elapsed_time": "3:13:45", "remaining_time": "2:24:41"}
|
||||
{"current_steps": 5610, "total_steps": 9782, "loss": 0.584, "lr": 2.2963595977610907e-05, "epoch": 0.5735170087152095, "percentage": 57.35, "elapsed_time": "3:14:09", "remaining_time": "2:24:23"}
|
||||
{"current_steps": 5620, "total_steps": 9782, "loss": 0.5949, "lr": 2.2874686241363558e-05, "epoch": 0.5745393206737036, "percentage": 57.45, "elapsed_time": "3:14:32", "remaining_time": "2:24:04"}
|
||||
{"current_steps": 5630, "total_steps": 9782, "loss": 0.5981, "lr": 2.2785803573413302e-05, "epoch": 0.5755616326321977, "percentage": 57.55, "elapsed_time": "3:14:56", "remaining_time": "2:23:46"}
|
||||
{"current_steps": 5640, "total_steps": 9782, "loss": 0.588, "lr": 2.269694910578238e-05, "epoch": 0.5765839445906918, "percentage": 57.66, "elapsed_time": "3:15:20", "remaining_time": "2:23:27"}
|
||||
{"current_steps": 5650, "total_steps": 9782, "loss": 0.5889, "lr": 2.2608123970133893e-05, "epoch": 0.577606256549186, "percentage": 57.76, "elapsed_time": "3:15:42", "remaining_time": "2:23:07"}
|
||||
{"current_steps": 5660, "total_steps": 9782, "loss": 0.5909, "lr": 2.251932929775734e-05, "epoch": 0.5786285685076801, "percentage": 57.86, "elapsed_time": "3:16:07", "remaining_time": "2:22:49"}
|
||||
{"current_steps": 5670, "total_steps": 9782, "loss": 0.5859, "lr": 2.243056621955424e-05, "epoch": 0.5796508804661743, "percentage": 57.96, "elapsed_time": "3:16:31", "remaining_time": "2:22:31"}
|
||||
{"current_steps": 5680, "total_steps": 9782, "loss": 0.5915, "lr": 2.2341835866023744e-05, "epoch": 0.5806731924246684, "percentage": 58.07, "elapsed_time": "3:16:56", "remaining_time": "2:22:13"}
|
||||
{"current_steps": 5690, "total_steps": 9782, "loss": 0.5831, "lr": 2.2253139367248192e-05, "epoch": 0.5816955043831625, "percentage": 58.17, "elapsed_time": "3:17:20", "remaining_time": "2:21:55"}
|
||||
{"current_steps": 5700, "total_steps": 9782, "loss": 0.5893, "lr": 2.216447785287878e-05, "epoch": 0.5827178163416566, "percentage": 58.27, "elapsed_time": "3:17:44", "remaining_time": "2:21:36"}
|
||||
{"current_steps": 5710, "total_steps": 9782, "loss": 0.586, "lr": 2.2075852452121083e-05, "epoch": 0.5837401283001508, "percentage": 58.37, "elapsed_time": "3:18:09", "remaining_time": "2:21:18"}
|
||||
{"current_steps": 5720, "total_steps": 9782, "loss": 0.5915, "lr": 2.1987264293720774e-05, "epoch": 0.5847624402586449, "percentage": 58.47, "elapsed_time": "3:18:32", "remaining_time": "2:20:59"}
|
||||
{"current_steps": 5730, "total_steps": 9782, "loss": 0.5896, "lr": 2.189871450594919e-05, "epoch": 0.5857847522171391, "percentage": 58.58, "elapsed_time": "3:18:57", "remaining_time": "2:20:41"}
|
||||
{"current_steps": 5740, "total_steps": 9782, "loss": 0.5755, "lr": 2.1810204216588975e-05, "epoch": 0.5868070641756332, "percentage": 58.68, "elapsed_time": "3:19:21", "remaining_time": "2:20:22"}
|
||||
{"current_steps": 5750, "total_steps": 9782, "loss": 0.578, "lr": 2.172173455291969e-05, "epoch": 0.5878293761341273, "percentage": 58.78, "elapsed_time": "3:19:45", "remaining_time": "2:20:04"}
|
||||
{"current_steps": 5760, "total_steps": 9782, "loss": 0.5877, "lr": 2.163330664170353e-05, "epoch": 0.5888516880926215, "percentage": 58.88, "elapsed_time": "3:20:10", "remaining_time": "2:19:46"}
|
||||
{"current_steps": 5770, "total_steps": 9782, "loss": 0.5852, "lr": 2.154492160917088e-05, "epoch": 0.5898740000511156, "percentage": 58.99, "elapsed_time": "3:20:32", "remaining_time": "2:19:26"}
|
||||
{"current_steps": 5780, "total_steps": 9782, "loss": 0.5794, "lr": 2.1456580581006047e-05, "epoch": 0.5908963120096097, "percentage": 59.09, "elapsed_time": "3:20:56", "remaining_time": "2:19:07"}
|
||||
{"current_steps": 5790, "total_steps": 9782, "loss": 0.5848, "lr": 2.136828468233288e-05, "epoch": 0.5919186239681039, "percentage": 59.19, "elapsed_time": "3:21:21", "remaining_time": "2:18:49"}
|
||||
{"current_steps": 5800, "total_steps": 9782, "loss": 0.5894, "lr": 2.1280035037700436e-05, "epoch": 0.592940935926598, "percentage": 59.29, "elapsed_time": "3:21:46", "remaining_time": "2:18:31"}
|
||||
{"current_steps": 5810, "total_steps": 9782, "loss": 0.5835, "lr": 2.1191832771068705e-05, "epoch": 0.5939632478850921, "percentage": 59.39, "elapsed_time": "3:22:10", "remaining_time": "2:18:12"}
|
||||
{"current_steps": 5820, "total_steps": 9782, "loss": 0.5817, "lr": 2.110367900579424e-05, "epoch": 0.5949855598435863, "percentage": 59.5, "elapsed_time": "3:22:34", "remaining_time": "2:17:54"}
|
||||
{"current_steps": 5830, "total_steps": 9782, "loss": 0.5821, "lr": 2.1015574864615896e-05, "epoch": 0.5960078718020804, "percentage": 59.6, "elapsed_time": "3:22:58", "remaining_time": "2:17:35"}
|
||||
{"current_steps": 5840, "total_steps": 9782, "loss": 0.5824, "lr": 2.092752146964048e-05, "epoch": 0.5970301837605745, "percentage": 59.7, "elapsed_time": "3:23:21", "remaining_time": "2:17:16"}
|
||||
{"current_steps": 5850, "total_steps": 9782, "loss": 0.5841, "lr": 2.0839519942328512e-05, "epoch": 0.5980524957190687, "percentage": 59.8, "elapsed_time": "3:23:45", "remaining_time": "2:16:57"}
|
||||
{"current_steps": 5860, "total_steps": 9782, "loss": 0.5873, "lr": 2.0751571403479906e-05, "epoch": 0.5990748076775628, "percentage": 59.91, "elapsed_time": "3:24:10", "remaining_time": "2:16:38"}
|
||||
{"current_steps": 5870, "total_steps": 9782, "loss": 0.5817, "lr": 2.066367697321971e-05, "epoch": 0.6000971196360569, "percentage": 60.01, "elapsed_time": "3:24:34", "remaining_time": "2:16:20"}
|
||||
{"current_steps": 5880, "total_steps": 9782, "loss": 0.5916, "lr": 2.057583777098385e-05, "epoch": 0.6011194315945511, "percentage": 60.11, "elapsed_time": "3:24:58", "remaining_time": "2:16:01"}
|
||||
{"current_steps": 5890, "total_steps": 9782, "loss": 0.5928, "lr": 2.048805491550484e-05, "epoch": 0.6021417435530452, "percentage": 60.21, "elapsed_time": "3:25:24", "remaining_time": "2:15:43"}
|
||||
{"current_steps": 5900, "total_steps": 9782, "loss": 0.5822, "lr": 2.0400329524797553e-05, "epoch": 0.6031640555115394, "percentage": 60.31, "elapsed_time": "3:25:49", "remaining_time": "2:15:25"}
|
||||
{"current_steps": 5910, "total_steps": 9782, "loss": 0.5784, "lr": 2.0312662716145004e-05, "epoch": 0.6041863674700335, "percentage": 60.42, "elapsed_time": "3:26:13", "remaining_time": "2:15:06"}
|
||||
{"current_steps": 5920, "total_steps": 9782, "loss": 0.5819, "lr": 2.022505560608409e-05, "epoch": 0.6052086794285276, "percentage": 60.52, "elapsed_time": "3:26:37", "remaining_time": "2:14:47"}
|
||||
{"current_steps": 5930, "total_steps": 9782, "loss": 0.581, "lr": 2.0137509310391357e-05, "epoch": 0.6062309913870217, "percentage": 60.62, "elapsed_time": "3:27:01", "remaining_time": "2:14:28"}
|
||||
{"current_steps": 5940, "total_steps": 9782, "loss": 0.5798, "lr": 2.0050024944068847e-05, "epoch": 0.6072533033455159, "percentage": 60.72, "elapsed_time": "3:27:25", "remaining_time": "2:14:09"}
|
||||
{"current_steps": 5950, "total_steps": 9782, "loss": 0.5798, "lr": 1.9962603621329823e-05, "epoch": 0.60827561530401, "percentage": 60.83, "elapsed_time": "3:27:49", "remaining_time": "2:13:51"}
|
||||
{"current_steps": 5960, "total_steps": 9782, "loss": 0.5749, "lr": 1.9875246455584658e-05, "epoch": 0.6092979272625042, "percentage": 60.93, "elapsed_time": "3:28:14", "remaining_time": "2:13:32"}
|
||||
{"current_steps": 5970, "total_steps": 9782, "loss": 0.5891, "lr": 1.9787954559426574e-05, "epoch": 0.6103202392209983, "percentage": 61.03, "elapsed_time": "3:28:39", "remaining_time": "2:13:13"}
|
||||
{"current_steps": 5980, "total_steps": 9782, "loss": 0.5786, "lr": 1.9700729044617523e-05, "epoch": 0.6113425511794924, "percentage": 61.13, "elapsed_time": "3:29:03", "remaining_time": "2:12:54"}
|
||||
{"current_steps": 5990, "total_steps": 9782, "loss": 0.5809, "lr": 1.961357102207403e-05, "epoch": 0.6123648631379865, "percentage": 61.23, "elapsed_time": "3:29:29", "remaining_time": "2:12:37"}
|
||||
{"current_steps": 6000, "total_steps": 9782, "loss": 0.5908, "lr": 1.9526481601853004e-05, "epoch": 0.6133871750964807, "percentage": 61.34, "elapsed_time": "3:29:54", "remaining_time": "2:12:18"}
|
||||
{"current_steps": 6010, "total_steps": 9782, "loss": 0.5897, "lr": 1.9439461893137654e-05, "epoch": 0.6144094870549748, "percentage": 61.44, "elapsed_time": "3:30:55", "remaining_time": "2:12:22"}
|
||||
{"current_steps": 6020, "total_steps": 9782, "loss": 0.5807, "lr": 1.93525130042233e-05, "epoch": 0.615431799013469, "percentage": 61.54, "elapsed_time": "3:31:20", "remaining_time": "2:12:04"}
|
||||
{"current_steps": 6030, "total_steps": 9782, "loss": 0.5806, "lr": 1.926563604250331e-05, "epoch": 0.6164541109719631, "percentage": 61.64, "elapsed_time": "3:31:44", "remaining_time": "2:11:44"}
|
||||
{"current_steps": 6040, "total_steps": 9782, "loss": 0.5831, "lr": 1.9178832114454982e-05, "epoch": 0.6174764229304572, "percentage": 61.75, "elapsed_time": "3:32:08", "remaining_time": "2:11:25"}
|
||||
{"current_steps": 6050, "total_steps": 9782, "loss": 0.5801, "lr": 1.9092102325625447e-05, "epoch": 0.6184987348889514, "percentage": 61.85, "elapsed_time": "3:32:31", "remaining_time": "2:11:06"}
|
||||
{"current_steps": 6060, "total_steps": 9782, "loss": 0.5832, "lr": 1.900544778061756e-05, "epoch": 0.6195210468474455, "percentage": 61.95, "elapsed_time": "3:32:56", "remaining_time": "2:10:47"}
|
||||
{"current_steps": 6070, "total_steps": 9782, "loss": 0.5906, "lr": 1.8918869583075893e-05, "epoch": 0.6205433588059396, "percentage": 62.05, "elapsed_time": "3:33:19", "remaining_time": "2:10:27"}
|
||||
{"current_steps": 6080, "total_steps": 9782, "loss": 0.5827, "lr": 1.883236883567263e-05, "epoch": 0.6215656707644338, "percentage": 62.15, "elapsed_time": "3:33:43", "remaining_time": "2:10:07"}
|
||||
{"current_steps": 6090, "total_steps": 9782, "loss": 0.5738, "lr": 1.8745946640093554e-05, "epoch": 0.6225879827229279, "percentage": 62.26, "elapsed_time": "3:34:07", "remaining_time": "2:09:48"}
|
||||
{"current_steps": 6100, "total_steps": 9782, "loss": 0.5789, "lr": 1.8659604097023986e-05, "epoch": 0.623610294681422, "percentage": 62.36, "elapsed_time": "3:34:30", "remaining_time": "2:09:28"}
|
||||
{"current_steps": 6110, "total_steps": 9782, "loss": 0.5818, "lr": 1.857334230613477e-05, "epoch": 0.6246326066399162, "percentage": 62.46, "elapsed_time": "3:34:55", "remaining_time": "2:09:09"}
|
||||
{"current_steps": 6120, "total_steps": 9782, "loss": 0.5746, "lr": 1.848716236606831e-05, "epoch": 0.6256549185984103, "percentage": 62.56, "elapsed_time": "3:35:19", "remaining_time": "2:08:50"}
|
||||
{"current_steps": 6130, "total_steps": 9782, "loss": 0.5809, "lr": 1.8401065374424524e-05, "epoch": 0.6266772305569044, "percentage": 62.67, "elapsed_time": "3:35:44", "remaining_time": "2:08:31"}
|
||||
{"current_steps": 6140, "total_steps": 9782, "loss": 0.5771, "lr": 1.8315052427746907e-05, "epoch": 0.6276995425153986, "percentage": 62.77, "elapsed_time": "3:36:09", "remaining_time": "2:08:13"}
|
||||
{"current_steps": 6150, "total_steps": 9782, "loss": 0.5784, "lr": 1.8229124621508514e-05, "epoch": 0.6287218544738927, "percentage": 62.87, "elapsed_time": "3:36:35", "remaining_time": "2:07:54"}
|
||||
{"current_steps": 6160, "total_steps": 9782, "loss": 0.578, "lr": 1.8143283050098058e-05, "epoch": 0.6297441664323868, "percentage": 62.97, "elapsed_time": "3:36:59", "remaining_time": "2:07:35"}
|
||||
{"current_steps": 6170, "total_steps": 9782, "loss": 0.5653, "lr": 1.8057528806805968e-05, "epoch": 0.630766478390881, "percentage": 63.08, "elapsed_time": "3:37:25", "remaining_time": "2:07:17"}
|
||||
{"current_steps": 6180, "total_steps": 9782, "loss": 0.5745, "lr": 1.7971862983810414e-05, "epoch": 0.6317887903493751, "percentage": 63.18, "elapsed_time": "3:37:50", "remaining_time": "2:06:57"}
|
||||
{"current_steps": 6190, "total_steps": 9782, "loss": 0.5763, "lr": 1.7886286672163477e-05, "epoch": 0.6328111023078693, "percentage": 63.28, "elapsed_time": "3:38:14", "remaining_time": "2:06:38"}
|
||||
{"current_steps": 6200, "total_steps": 9782, "loss": 0.5793, "lr": 1.7800800961777164e-05, "epoch": 0.6338334142663634, "percentage": 63.38, "elapsed_time": "3:38:39", "remaining_time": "2:06:19"}
|
||||
{"current_steps": 6210, "total_steps": 9782, "loss": 0.5726, "lr": 1.771540694140959e-05, "epoch": 0.6348557262248575, "percentage": 63.48, "elapsed_time": "3:39:04", "remaining_time": "2:06:00"}
|
||||
{"current_steps": 6220, "total_steps": 9782, "loss": 0.5787, "lr": 1.763010569865111e-05, "epoch": 0.6358780381833516, "percentage": 63.59, "elapsed_time": "3:39:28", "remaining_time": "2:05:41"}
|
||||
{"current_steps": 6230, "total_steps": 9782, "loss": 0.5692, "lr": 1.7544898319910436e-05, "epoch": 0.6369003501418458, "percentage": 63.69, "elapsed_time": "3:39:54", "remaining_time": "2:05:22"}
|
||||
{"current_steps": 6240, "total_steps": 9782, "loss": 0.5806, "lr": 1.7459785890400794e-05, "epoch": 0.6379226621003399, "percentage": 63.79, "elapsed_time": "3:40:19", "remaining_time": "2:05:03"}
|
||||
{"current_steps": 6250, "total_steps": 9782, "loss": 0.5764, "lr": 1.7374769494126157e-05, "epoch": 0.6389449740588341, "percentage": 63.89, "elapsed_time": "3:40:47", "remaining_time": "2:04:46"}
|
||||
{"current_steps": 6260, "total_steps": 9782, "loss": 0.5756, "lr": 1.7289850213867388e-05, "epoch": 0.6399672860173282, "percentage": 64.0, "elapsed_time": "3:41:15", "remaining_time": "2:04:28"}
|
||||
{"current_steps": 6270, "total_steps": 9782, "loss": 0.5746, "lr": 1.7205029131168478e-05, "epoch": 0.6409895979758223, "percentage": 64.1, "elapsed_time": "3:41:43", "remaining_time": "2:04:11"}
|
||||
{"current_steps": 6280, "total_steps": 9782, "loss": 0.569, "lr": 1.7120307326322738e-05, "epoch": 0.6420119099343164, "percentage": 64.2, "elapsed_time": "3:42:10", "remaining_time": "2:03:53"}
|
||||
{"current_steps": 6290, "total_steps": 9782, "loss": 0.564, "lr": 1.7035685878359074e-05, "epoch": 0.6430342218928106, "percentage": 64.3, "elapsed_time": "3:42:39", "remaining_time": "2:03:36"}
|
||||
{"current_steps": 6300, "total_steps": 9782, "loss": 0.5697, "lr": 1.6951165865028253e-05, "epoch": 0.6440565338513047, "percentage": 64.4, "elapsed_time": "3:43:07", "remaining_time": "2:03:19"}
|
||||
{"current_steps": 6310, "total_steps": 9782, "loss": 0.5692, "lr": 1.6866748362789114e-05, "epoch": 0.6450788458097989, "percentage": 64.51, "elapsed_time": "3:43:35", "remaining_time": "2:03:01"}
|
||||
{"current_steps": 6320, "total_steps": 9782, "loss": 0.568, "lr": 1.678243444679495e-05, "epoch": 0.646101157768293, "percentage": 64.61, "elapsed_time": "3:44:03", "remaining_time": "2:02:44"}
|
||||
{"current_steps": 6330, "total_steps": 9782, "loss": 0.5621, "lr": 1.669822519087972e-05, "epoch": 0.6471234697267871, "percentage": 64.71, "elapsed_time": "3:44:32", "remaining_time": "2:02:27"}
|
||||
{"current_steps": 6340, "total_steps": 9782, "loss": 0.5613, "lr": 1.661412166754443e-05, "epoch": 0.6481457816852813, "percentage": 64.81, "elapsed_time": "3:45:00", "remaining_time": "2:02:09"}
|
||||
{"current_steps": 6350, "total_steps": 9782, "loss": 0.5606, "lr": 1.653012494794348e-05, "epoch": 0.6491680936437754, "percentage": 64.92, "elapsed_time": "3:45:28", "remaining_time": "2:01:51"}
|
||||
{"current_steps": 6360, "total_steps": 9782, "loss": 0.5677, "lr": 1.6446236101871e-05, "epoch": 0.6501904056022695, "percentage": 65.02, "elapsed_time": "3:45:57", "remaining_time": "2:01:34"}
|
||||
{"current_steps": 6370, "total_steps": 9782, "loss": 0.572, "lr": 1.6362456197747185e-05, "epoch": 0.6512127175607637, "percentage": 65.12, "elapsed_time": "3:46:25", "remaining_time": "2:01:16"}
|
||||
{"current_steps": 6380, "total_steps": 9782, "loss": 0.5617, "lr": 1.6278786302604786e-05, "epoch": 0.6522350295192578, "percentage": 65.22, "elapsed_time": "3:46:52", "remaining_time": "2:00:58"}
|
||||
{"current_steps": 6390, "total_steps": 9782, "loss": 0.5646, "lr": 1.619522748207543e-05, "epoch": 0.6532573414777519, "percentage": 65.32, "elapsed_time": "3:47:20", "remaining_time": "2:00:41"}
|
||||
{"current_steps": 6400, "total_steps": 9782, "loss": 0.5625, "lr": 1.6111780800376098e-05, "epoch": 0.6542796534362461, "percentage": 65.43, "elapsed_time": "3:47:48", "remaining_time": "2:00:22"}
|
||||
{"current_steps": 6410, "total_steps": 9782, "loss": 0.5604, "lr": 1.6028447320295554e-05, "epoch": 0.6553019653947402, "percentage": 65.53, "elapsed_time": "3:48:16", "remaining_time": "2:00:05"}
|
||||
{"current_steps": 6420, "total_steps": 9782, "loss": 0.5665, "lr": 1.594522810318078e-05, "epoch": 0.6563242773532343, "percentage": 65.63, "elapsed_time": "3:48:45", "remaining_time": "1:59:47"}
|
||||
{"current_steps": 6430, "total_steps": 9782, "loss": 0.5633, "lr": 1.586212420892354e-05, "epoch": 0.6573465893117285, "percentage": 65.73, "elapsed_time": "3:49:13", "remaining_time": "1:59:29"}
|
||||
{"current_steps": 6440, "total_steps": 9782, "loss": 0.5688, "lr": 1.577913669594679e-05, "epoch": 0.6583689012702226, "percentage": 65.84, "elapsed_time": "3:49:41", "remaining_time": "1:59:11"}
|
||||
{"current_steps": 6450, "total_steps": 9782, "loss": 0.5593, "lr": 1.569626662119126e-05, "epoch": 0.6593912132287167, "percentage": 65.94, "elapsed_time": "3:50:09", "remaining_time": "1:58:53"}
|
||||
{"current_steps": 6460, "total_steps": 9782, "loss": 0.5537, "lr": 1.561351504010195e-05, "epoch": 0.6604135251872109, "percentage": 66.04, "elapsed_time": "3:50:37", "remaining_time": "1:58:35"}
|
||||
{"current_steps": 6470, "total_steps": 9782, "loss": 0.5647, "lr": 1.553088300661472e-05, "epoch": 0.661435837145705, "percentage": 66.14, "elapsed_time": "3:51:05", "remaining_time": "1:58:17"}
|
||||
{"current_steps": 6480, "total_steps": 9782, "loss": 0.5609, "lr": 1.544837157314287e-05, "epoch": 0.6624581491041992, "percentage": 66.24, "elapsed_time": "3:51:34", "remaining_time": "1:57:59"}
|
||||
{"current_steps": 6490, "total_steps": 9782, "loss": 0.5596, "lr": 1.5365981790563676e-05, "epoch": 0.6634804610626933, "percentage": 66.35, "elapsed_time": "3:52:02", "remaining_time": "1:57:42"}
|
||||
{"current_steps": 6500, "total_steps": 9782, "loss": 0.5601, "lr": 1.528371470820511e-05, "epoch": 0.6645027730211874, "percentage": 66.45, "elapsed_time": "3:52:30", "remaining_time": "1:57:23"}
|
||||
{"current_steps": 6510, "total_steps": 9782, "loss": 0.5632, "lr": 1.5201571373832368e-05, "epoch": 0.6655250849796815, "percentage": 66.55, "elapsed_time": "3:52:58", "remaining_time": "1:57:05"}
|
||||
{"current_steps": 6520, "total_steps": 9782, "loss": 0.5608, "lr": 1.5119552833634592e-05, "epoch": 0.6665473969381757, "percentage": 66.65, "elapsed_time": "3:53:26", "remaining_time": "1:56:47"}
|
||||
{"current_steps": 6530, "total_steps": 9782, "loss": 0.4508, "lr": 1.503766013221154e-05, "epoch": 0.6675697088966698, "percentage": 66.76, "elapsed_time": "3:53:50", "remaining_time": "1:56:27"}
|
||||
{"current_steps": 6540, "total_steps": 9782, "loss": 0.438, "lr": 1.4955894312560254e-05, "epoch": 0.668592020855164, "percentage": 66.86, "elapsed_time": "3:54:13", "remaining_time": "1:56:06"}
|
||||
{"current_steps": 6550, "total_steps": 9782, "loss": 0.436, "lr": 1.4874256416061783e-05, "epoch": 0.6696143328136581, "percentage": 66.96, "elapsed_time": "3:54:37", "remaining_time": "1:55:46"}
|
||||
{"current_steps": 6560, "total_steps": 9782, "loss": 0.4405, "lr": 1.4792747482467953e-05, "epoch": 0.6706366447721522, "percentage": 67.06, "elapsed_time": "3:54:59", "remaining_time": "1:55:24"}
|
||||
{"current_steps": 6570, "total_steps": 9782, "loss": 0.4479, "lr": 1.4711368549888082e-05, "epoch": 0.6716589567306464, "percentage": 67.16, "elapsed_time": "3:55:20", "remaining_time": "1:55:03"}
|
||||
{"current_steps": 6580, "total_steps": 9782, "loss": 0.4365, "lr": 1.46301206547758e-05, "epoch": 0.6726812686891405, "percentage": 67.27, "elapsed_time": "3:55:41", "remaining_time": "1:54:41"}
|
||||
{"current_steps": 6590, "total_steps": 9782, "loss": 0.4374, "lr": 1.4549004831915786e-05, "epoch": 0.6737035806476346, "percentage": 67.37, "elapsed_time": "3:56:03", "remaining_time": "1:54:20"}
|
||||
{"current_steps": 6600, "total_steps": 9782, "loss": 0.4403, "lr": 1.4468022114410663e-05, "epoch": 0.6747258926061288, "percentage": 67.47, "elapsed_time": "3:56:23", "remaining_time": "1:53:58"}
|
||||
{"current_steps": 6610, "total_steps": 9782, "loss": 0.4496, "lr": 1.4387173533667785e-05, "epoch": 0.6757482045646229, "percentage": 67.57, "elapsed_time": "3:56:46", "remaining_time": "1:53:37"}
|
||||
{"current_steps": 6620, "total_steps": 9782, "loss": 0.4433, "lr": 1.430646011938614e-05, "epoch": 0.676770516523117, "percentage": 67.68, "elapsed_time": "3:57:09", "remaining_time": "1:53:16"}
|
||||
{"current_steps": 6630, "total_steps": 9782, "loss": 0.453, "lr": 1.4225882899543194e-05, "epoch": 0.6777928284816112, "percentage": 67.78, "elapsed_time": "3:57:33", "remaining_time": "1:52:56"}
|
||||
{"current_steps": 6640, "total_steps": 9782, "loss": 0.4344, "lr": 1.4145442900381839e-05, "epoch": 0.6788151404401053, "percentage": 67.88, "elapsed_time": "3:57:54", "remaining_time": "1:52:34"}
|
||||
{"current_steps": 6650, "total_steps": 9782, "loss": 0.4396, "lr": 1.4065141146397298e-05, "epoch": 0.6798374523985994, "percentage": 67.98, "elapsed_time": "3:58:16", "remaining_time": "1:52:13"}
|
||||
{"current_steps": 6660, "total_steps": 9782, "loss": 0.448, "lr": 1.3984978660324077e-05, "epoch": 0.6808597643570936, "percentage": 68.08, "elapsed_time": "3:58:37", "remaining_time": "1:51:51"}
|
||||
{"current_steps": 6670, "total_steps": 9782, "loss": 0.4547, "lr": 1.3904956463122982e-05, "epoch": 0.6818820763155877, "percentage": 68.19, "elapsed_time": "3:59:00", "remaining_time": "1:51:30"}
|
||||
{"current_steps": 6680, "total_steps": 9782, "loss": 0.4502, "lr": 1.3825075573968018e-05, "epoch": 0.6829043882740818, "percentage": 68.29, "elapsed_time": "3:59:21", "remaining_time": "1:51:09"}
|
||||
{"current_steps": 6690, "total_steps": 9782, "loss": 0.4587, "lr": 1.3745337010233511e-05, "epoch": 0.683926700232576, "percentage": 68.39, "elapsed_time": "3:59:44", "remaining_time": "1:50:48"}
|
||||
{"current_steps": 6700, "total_steps": 9782, "loss": 0.4466, "lr": 1.3665741787481121e-05, "epoch": 0.6849490121910701, "percentage": 68.49, "elapsed_time": "4:00:07", "remaining_time": "1:50:27"}
|
||||
{"current_steps": 6710, "total_steps": 9782, "loss": 0.4449, "lr": 1.358629091944687e-05, "epoch": 0.6859713241495642, "percentage": 68.6, "elapsed_time": "4:00:29", "remaining_time": "1:50:06"}
|
||||
{"current_steps": 6720, "total_steps": 9782, "loss": 0.4425, "lr": 1.3506985418028268e-05, "epoch": 0.6869936361080584, "percentage": 68.7, "elapsed_time": "4:00:50", "remaining_time": "1:49:44"}
|
||||
{"current_steps": 6730, "total_steps": 9782, "loss": 0.4447, "lr": 1.3427826293271417e-05, "epoch": 0.6880159480665525, "percentage": 68.8, "elapsed_time": "4:01:12", "remaining_time": "1:49:22"}
|
||||
{"current_steps": 6740, "total_steps": 9782, "loss": 0.4557, "lr": 1.3348814553358139e-05, "epoch": 0.6890382600250466, "percentage": 68.9, "elapsed_time": "4:01:33", "remaining_time": "1:49:01"}
|
||||
{"current_steps": 6750, "total_steps": 9782, "loss": 0.4581, "lr": 1.326995120459315e-05, "epoch": 0.6900605719835408, "percentage": 69.0, "elapsed_time": "4:01:54", "remaining_time": "1:48:39"}
|
||||
{"current_steps": 6760, "total_steps": 9782, "loss": 0.4467, "lr": 1.3191237251391228e-05, "epoch": 0.6910828839420349, "percentage": 69.11, "elapsed_time": "4:02:17", "remaining_time": "1:48:19"}
|
||||
{"current_steps": 6770, "total_steps": 9782, "loss": 0.4452, "lr": 1.3112673696264432e-05, "epoch": 0.692105195900529, "percentage": 69.21, "elapsed_time": "4:02:40", "remaining_time": "1:47:57"}
|
||||
{"current_steps": 6780, "total_steps": 9782, "loss": 0.4511, "lr": 1.3034261539809333e-05, "epoch": 0.6931275078590232, "percentage": 69.31, "elapsed_time": "4:03:02", "remaining_time": "1:47:36"}
|
||||
{"current_steps": 6790, "total_steps": 9782, "loss": 0.4476, "lr": 1.2956001780694249e-05, "epoch": 0.6941498198175173, "percentage": 69.41, "elapsed_time": "4:03:23", "remaining_time": "1:47:15"}
|
||||
{"current_steps": 6800, "total_steps": 9782, "loss": 0.4541, "lr": 1.2877895415646584e-05, "epoch": 0.6951721317760114, "percentage": 69.52, "elapsed_time": "4:03:45", "remaining_time": "1:46:53"}
|
||||
{"current_steps": 6810, "total_steps": 9782, "loss": 0.4521, "lr": 1.2799943439440048e-05, "epoch": 0.6961944437345056, "percentage": 69.62, "elapsed_time": "4:04:07", "remaining_time": "1:46:32"}
|
||||
{"current_steps": 6820, "total_steps": 9782, "loss": 0.451, "lr": 1.2722146844882043e-05, "epoch": 0.6972167556929997, "percentage": 69.72, "elapsed_time": "4:04:29", "remaining_time": "1:46:10"}
|
||||
{"current_steps": 6830, "total_steps": 9782, "loss": 0.4486, "lr": 1.264450662280104e-05, "epoch": 0.6982390676514939, "percentage": 69.82, "elapsed_time": "4:04:51", "remaining_time": "1:45:49"}
|
||||
{"current_steps": 6840, "total_steps": 9782, "loss": 0.4512, "lr": 1.2567023762033897e-05, "epoch": 0.699261379609988, "percentage": 69.92, "elapsed_time": "4:05:13", "remaining_time": "1:45:28"}
|
||||
{"current_steps": 6850, "total_steps": 9782, "loss": 0.4502, "lr": 1.2489699249413302e-05, "epoch": 0.7002836915684821, "percentage": 70.03, "elapsed_time": "4:05:36", "remaining_time": "1:45:07"}
|
||||
{"current_steps": 6860, "total_steps": 9782, "loss": 0.4421, "lr": 1.2412534069755204e-05, "epoch": 0.7013060035269763, "percentage": 70.13, "elapsed_time": "4:05:59", "remaining_time": "1:44:46"}
|
||||
{"current_steps": 6870, "total_steps": 9782, "loss": 0.4456, "lr": 1.233552920584626e-05, "epoch": 0.7023283154854704, "percentage": 70.23, "elapsed_time": "4:06:20", "remaining_time": "1:44:25"}
|
||||
{"current_steps": 6880, "total_steps": 9782, "loss": 0.4521, "lr": 1.2258685638431325e-05, "epoch": 0.7033506274439645, "percentage": 70.33, "elapsed_time": "4:06:43", "remaining_time": "1:44:03"}
|
||||
{"current_steps": 6890, "total_steps": 9782, "loss": 0.4508, "lr": 1.2182004346200958e-05, "epoch": 0.7043729394024587, "percentage": 70.44, "elapsed_time": "4:07:05", "remaining_time": "1:43:42"}
|
||||
{"current_steps": 6900, "total_steps": 9782, "loss": 0.451, "lr": 1.2105486305778965e-05, "epoch": 0.7053952513609528, "percentage": 70.54, "elapsed_time": "4:07:27", "remaining_time": "1:43:21"}
|
||||
{"current_steps": 6910, "total_steps": 9782, "loss": 0.4431, "lr": 1.2029132491709938e-05, "epoch": 0.7064175633194469, "percentage": 70.64, "elapsed_time": "4:07:48", "remaining_time": "1:42:59"}
|
||||
{"current_steps": 6920, "total_steps": 9782, "loss": 0.4453, "lr": 1.1952943876446867e-05, "epoch": 0.707439875277941, "percentage": 70.74, "elapsed_time": "4:08:10", "remaining_time": "1:42:38"}
|
||||
{"current_steps": 6930, "total_steps": 9782, "loss": 0.4474, "lr": 1.1876921430338764e-05, "epoch": 0.7084621872364352, "percentage": 70.84, "elapsed_time": "4:08:31", "remaining_time": "1:42:16"}
|
||||
{"current_steps": 6940, "total_steps": 9782, "loss": 0.4441, "lr": 1.1801066121618273e-05, "epoch": 0.7094844991949293, "percentage": 70.95, "elapsed_time": "4:08:53", "remaining_time": "1:41:55"}
|
||||
{"current_steps": 6950, "total_steps": 9782, "loss": 0.4516, "lr": 1.172537891638932e-05, "epoch": 0.7105068111534235, "percentage": 71.05, "elapsed_time": "4:09:16", "remaining_time": "1:41:34"}
|
||||
{"current_steps": 6960, "total_steps": 9782, "loss": 0.4544, "lr": 1.1649860778614905e-05, "epoch": 0.7115291231119176, "percentage": 71.15, "elapsed_time": "4:09:38", "remaining_time": "1:41:13"}
|
||||
{"current_steps": 6970, "total_steps": 9782, "loss": 0.4369, "lr": 1.1574512670104714e-05, "epoch": 0.7125514350704117, "percentage": 71.25, "elapsed_time": "4:09:59", "remaining_time": "1:40:51"}
|
||||
{"current_steps": 6980, "total_steps": 9782, "loss": 0.44, "lr": 1.1499335550502936e-05, "epoch": 0.7135737470289059, "percentage": 71.36, "elapsed_time": "4:10:21", "remaining_time": "1:40:30"}
|
||||
{"current_steps": 6990, "total_steps": 9782, "loss": 0.4533, "lr": 1.142433037727601e-05, "epoch": 0.7145960589874, "percentage": 71.46, "elapsed_time": "4:10:43", "remaining_time": "1:40:08"}
|
||||
{"current_steps": 7000, "total_steps": 9782, "loss": 0.4494, "lr": 1.1349498105700449e-05, "epoch": 0.7156183709458941, "percentage": 71.56, "elapsed_time": "4:11:06", "remaining_time": "1:39:47"}
|
||||
{"current_steps": 7010, "total_steps": 9782, "loss": 0.4454, "lr": 1.1274839688850663e-05, "epoch": 0.7166406829043883, "percentage": 71.66, "elapsed_time": "4:11:28", "remaining_time": "1:39:26"}
|
||||
{"current_steps": 7020, "total_steps": 9782, "loss": 0.4446, "lr": 1.1200356077586819e-05, "epoch": 0.7176629948628824, "percentage": 71.76, "elapsed_time": "4:11:50", "remaining_time": "1:39:05"}
|
||||
{"current_steps": 7030, "total_steps": 9782, "loss": 0.4492, "lr": 1.1126048220542764e-05, "epoch": 0.7186853068213765, "percentage": 71.87, "elapsed_time": "4:12:12", "remaining_time": "1:38:43"}
|
||||
{"current_steps": 7040, "total_steps": 9782, "loss": 0.4526, "lr": 1.1051917064113867e-05, "epoch": 0.7197076187798707, "percentage": 71.97, "elapsed_time": "4:12:33", "remaining_time": "1:38:22"}
|
||||
{"current_steps": 7050, "total_steps": 9782, "loss": 0.4396, "lr": 1.0977963552445037e-05, "epoch": 0.7207299307383648, "percentage": 72.07, "elapsed_time": "4:12:55", "remaining_time": "1:38:00"}
|
||||
{"current_steps": 7060, "total_steps": 9782, "loss": 0.4461, "lr": 1.090418862741869e-05, "epoch": 0.7217522426968589, "percentage": 72.17, "elapsed_time": "4:13:19", "remaining_time": "1:37:40"}
|
||||
{"current_steps": 7070, "total_steps": 9782, "loss": 0.4502, "lr": 1.0830593228642724e-05, "epoch": 0.7227745546553531, "percentage": 72.28, "elapsed_time": "4:13:41", "remaining_time": "1:37:18"}
|
||||
{"current_steps": 7080, "total_steps": 9782, "loss": 0.4411, "lr": 1.0757178293438536e-05, "epoch": 0.7237968666138472, "percentage": 72.38, "elapsed_time": "4:14:03", "remaining_time": "1:36:57"}
|
||||
{"current_steps": 7090, "total_steps": 9782, "loss": 0.4448, "lr": 1.0683944756829168e-05, "epoch": 0.7248191785723413, "percentage": 72.48, "elapsed_time": "4:14:25", "remaining_time": "1:36:36"}
|
||||
{"current_steps": 7100, "total_steps": 9782, "loss": 0.4462, "lr": 1.0610893551527304e-05, "epoch": 0.7258414905308355, "percentage": 72.58, "elapsed_time": "4:14:47", "remaining_time": "1:36:14"}
|
||||
{"current_steps": 7110, "total_steps": 9782, "loss": 0.442, "lr": 1.0538025607923444e-05, "epoch": 0.7268638024893296, "percentage": 72.68, "elapsed_time": "4:15:08", "remaining_time": "1:35:53"}
|
||||
{"current_steps": 7120, "total_steps": 9782, "loss": 0.4397, "lr": 1.0465341854074043e-05, "epoch": 0.7278861144478238, "percentage": 72.79, "elapsed_time": "4:15:31", "remaining_time": "1:35:32"}
|
||||
{"current_steps": 7130, "total_steps": 9782, "loss": 0.4469, "lr": 1.039284321568968e-05, "epoch": 0.7289084264063179, "percentage": 72.89, "elapsed_time": "4:15:52", "remaining_time": "1:35:10"}
|
||||
{"current_steps": 7140, "total_steps": 9782, "loss": 0.4439, "lr": 1.032053061612329e-05, "epoch": 0.729930738364812, "percentage": 72.99, "elapsed_time": "4:16:13", "remaining_time": "1:34:48"}
|
||||
{"current_steps": 7150, "total_steps": 9782, "loss": 0.4551, "lr": 1.0248404976358369e-05, "epoch": 0.7309530503233062, "percentage": 73.09, "elapsed_time": "4:16:36", "remaining_time": "1:34:27"}
|
||||
{"current_steps": 7160, "total_steps": 9782, "loss": 0.4493, "lr": 1.0176467214997312e-05, "epoch": 0.7319753622818003, "percentage": 73.2, "elapsed_time": "4:16:58", "remaining_time": "1:34:06"}
|
||||
{"current_steps": 7170, "total_steps": 9782, "loss": 0.4448, "lr": 1.0104718248249611e-05, "epoch": 0.7329976742402944, "percentage": 73.3, "elapsed_time": "4:17:21", "remaining_time": "1:33:45"}
|
||||
{"current_steps": 7180, "total_steps": 9782, "loss": 0.4482, "lr": 1.0033158989920271e-05, "epoch": 0.7340199861987886, "percentage": 73.4, "elapsed_time": "4:17:44", "remaining_time": "1:33:24"}
|
||||
{"current_steps": 7190, "total_steps": 9782, "loss": 0.4392, "lr": 9.96179035139816e-06, "epoch": 0.7350422981572827, "percentage": 73.5, "elapsed_time": "4:18:06", "remaining_time": "1:33:02"}
|
||||
{"current_steps": 7200, "total_steps": 9782, "loss": 0.4388, "lr": 9.890613241644367e-06, "epoch": 0.7360646101157768, "percentage": 73.6, "elapsed_time": "4:18:28", "remaining_time": "1:32:41"}
|
||||
{"current_steps": 7210, "total_steps": 9782, "loss": 0.4461, "lr": 9.819628567180617e-06, "epoch": 0.737086922074271, "percentage": 73.71, "elapsed_time": "4:18:51", "remaining_time": "1:32:20"}
|
||||
{"current_steps": 7220, "total_steps": 9782, "loss": 0.447, "lr": 9.748837232077807e-06, "epoch": 0.7381092340327651, "percentage": 73.81, "elapsed_time": "4:19:13", "remaining_time": "1:31:59"}
|
||||
{"current_steps": 7230, "total_steps": 9782, "loss": 0.4475, "lr": 9.6782401379444e-06, "epoch": 0.7391315459912592, "percentage": 73.91, "elapsed_time": "4:19:36", "remaining_time": "1:31:37"}
|
||||
{"current_steps": 7240, "total_steps": 9782, "loss": 0.444, "lr": 9.607838183914989e-06, "epoch": 0.7401538579497534, "percentage": 74.01, "elapsed_time": "4:19:59", "remaining_time": "1:31:17"}
|
||||
{"current_steps": 7250, "total_steps": 9782, "loss": 0.4447, "lr": 9.537632266638829e-06, "epoch": 0.7411761699082475, "percentage": 74.12, "elapsed_time": "4:20:21", "remaining_time": "1:30:55"}
|
||||
{"current_steps": 7260, "total_steps": 9782, "loss": 0.4358, "lr": 9.467623280268432e-06, "epoch": 0.7421984818667416, "percentage": 74.22, "elapsed_time": "4:20:41", "remaining_time": "1:30:33"}
|
||||
{"current_steps": 7270, "total_steps": 9782, "loss": 0.4471, "lr": 9.39781211644816e-06, "epoch": 0.7432207938252358, "percentage": 74.32, "elapsed_time": "4:21:04", "remaining_time": "1:30:12"}
|
||||
{"current_steps": 7280, "total_steps": 9782, "loss": 0.4443, "lr": 9.32819966430288e-06, "epoch": 0.7442431057837299, "percentage": 74.42, "elapsed_time": "4:21:27", "remaining_time": "1:29:51"}
|
||||
{"current_steps": 7290, "total_steps": 9782, "loss": 0.4483, "lr": 9.25878681042667e-06, "epoch": 0.745265417742224, "percentage": 74.52, "elapsed_time": "4:21:51", "remaining_time": "1:29:30"}
|
||||
{"current_steps": 7300, "total_steps": 9782, "loss": 0.4433, "lr": 9.189574438871443e-06, "epoch": 0.7462877297007182, "percentage": 74.63, "elapsed_time": "4:22:12", "remaining_time": "1:29:09"}
|
||||
{"current_steps": 7310, "total_steps": 9782, "loss": 0.4477, "lr": 9.120563431135765e-06, "epoch": 0.7473100416592123, "percentage": 74.73, "elapsed_time": "4:22:33", "remaining_time": "1:28:47"}
|
||||
{"current_steps": 7320, "total_steps": 9782, "loss": 0.444, "lr": 9.051754666153625e-06, "epoch": 0.7483323536177064, "percentage": 74.83, "elapsed_time": "4:22:57", "remaining_time": "1:28:26"}
|
||||
{"current_steps": 7330, "total_steps": 9782, "loss": 0.4523, "lr": 8.983149020283191e-06, "epoch": 0.7493546655762006, "percentage": 74.93, "elapsed_time": "4:23:18", "remaining_time": "1:28:05"}
|
||||
{"current_steps": 7340, "total_steps": 9782, "loss": 0.4461, "lr": 8.91474736729569e-06, "epoch": 0.7503769775346947, "percentage": 75.04, "elapsed_time": "4:23:40", "remaining_time": "1:27:43"}
|
||||
{"current_steps": 7350, "total_steps": 9782, "loss": 0.4404, "lr": 8.84655057836426e-06, "epoch": 0.7513992894931888, "percentage": 75.14, "elapsed_time": "4:24:01", "remaining_time": "1:27:21"}
|
||||
{"current_steps": 7360, "total_steps": 9782, "loss": 0.448, "lr": 8.77855952205287e-06, "epoch": 0.752421601451683, "percentage": 75.24, "elapsed_time": "4:24:23", "remaining_time": "1:27:00"}
|
||||
{"current_steps": 7370, "total_steps": 9782, "loss": 0.4424, "lr": 8.71077506430524e-06, "epoch": 0.7534439134101771, "percentage": 75.34, "elapsed_time": "4:24:44", "remaining_time": "1:26:38"}
|
||||
{"current_steps": 7380, "total_steps": 9782, "loss": 0.4543, "lr": 8.643198068433828e-06, "epoch": 0.7544662253686713, "percentage": 75.44, "elapsed_time": "4:25:05", "remaining_time": "1:26:16"}
|
||||
{"current_steps": 7390, "total_steps": 9782, "loss": 0.4319, "lr": 8.575829395108826e-06, "epoch": 0.7554885373271654, "percentage": 75.55, "elapsed_time": "4:25:25", "remaining_time": "1:25:54"}
|
||||
{"current_steps": 7400, "total_steps": 9782, "loss": 0.4363, "lr": 8.508669902347196e-06, "epoch": 0.7565108492856595, "percentage": 75.65, "elapsed_time": "4:25:46", "remaining_time": "1:25:33"}
|
||||
{"current_steps": 7410, "total_steps": 9782, "loss": 0.4415, "lr": 8.44172044550175e-06, "epoch": 0.7575331612441537, "percentage": 75.75, "elapsed_time": "4:26:08", "remaining_time": "1:25:11"}
|
||||
{"current_steps": 7420, "total_steps": 9782, "loss": 0.4368, "lr": 8.374981877250277e-06, "epoch": 0.7585554732026478, "percentage": 75.85, "elapsed_time": "4:26:31", "remaining_time": "1:24:50"}
|
||||
{"current_steps": 7430, "total_steps": 9782, "loss": 0.4337, "lr": 8.308455047584607e-06, "epoch": 0.7595777851611419, "percentage": 75.96, "elapsed_time": "4:26:53", "remaining_time": "1:24:29"}
|
||||
{"current_steps": 7440, "total_steps": 9782, "loss": 0.4419, "lr": 8.242140803799872e-06, "epoch": 0.760600097119636, "percentage": 76.06, "elapsed_time": "4:27:15", "remaining_time": "1:24:07"}
|
||||
{"current_steps": 7450, "total_steps": 9782, "loss": 0.4432, "lr": 8.176039990483689e-06, "epoch": 0.7616224090781302, "percentage": 76.16, "elapsed_time": "4:27:37", "remaining_time": "1:23:46"}
|
||||
{"current_steps": 7460, "total_steps": 9782, "loss": 0.4461, "lr": 8.110153449505368e-06, "epoch": 0.7626447210366243, "percentage": 76.26, "elapsed_time": "4:28:00", "remaining_time": "1:23:25"}
|
||||
{"current_steps": 7470, "total_steps": 9782, "loss": 0.4395, "lr": 8.044482020005234e-06, "epoch": 0.7636670329951185, "percentage": 76.36, "elapsed_time": "4:28:22", "remaining_time": "1:23:03"}
|
||||
{"current_steps": 7480, "total_steps": 9782, "loss": 0.4411, "lr": 7.97902653838391e-06, "epoch": 0.7646893449536126, "percentage": 76.47, "elapsed_time": "4:28:43", "remaining_time": "1:22:42"}
|
||||
{"current_steps": 7490, "total_steps": 9782, "loss": 0.4403, "lr": 7.913787838291686e-06, "epoch": 0.7657116569121067, "percentage": 76.57, "elapsed_time": "4:29:04", "remaining_time": "1:22:20"}
|
||||
{"current_steps": 7500, "total_steps": 9782, "loss": 0.4445, "lr": 7.84876675061789e-06, "epoch": 0.7667339688706009, "percentage": 76.67, "elapsed_time": "4:29:28", "remaining_time": "1:21:59"}
|
||||
{"current_steps": 7510, "total_steps": 9782, "loss": 0.4372, "lr": 7.783964103480296e-06, "epoch": 0.767756280829095, "percentage": 76.77, "elapsed_time": "4:29:50", "remaining_time": "1:21:38"}
|
||||
{"current_steps": 7520, "total_steps": 9782, "loss": 0.4366, "lr": 7.719380722214605e-06, "epoch": 0.7687785927875891, "percentage": 76.88, "elapsed_time": "4:30:11", "remaining_time": "1:21:16"}
|
||||
{"current_steps": 7530, "total_steps": 9782, "loss": 0.4435, "lr": 7.655017429363908e-06, "epoch": 0.7698009047460833, "percentage": 76.98, "elapsed_time": "4:30:34", "remaining_time": "1:20:55"}
|
||||
{"current_steps": 7540, "total_steps": 9782, "loss": 0.4425, "lr": 7.590875044668213e-06, "epoch": 0.7708232167045774, "percentage": 77.08, "elapsed_time": "4:30:55", "remaining_time": "1:20:33"}
|
||||
{"current_steps": 7550, "total_steps": 9782, "loss": 0.4358, "lr": 7.526954385054031e-06, "epoch": 0.7718455286630715, "percentage": 77.18, "elapsed_time": "4:31:17", "remaining_time": "1:20:12"}
|
||||
{"current_steps": 7560, "total_steps": 9782, "loss": 0.4425, "lr": 7.463256264623939e-06, "epoch": 0.7728678406215657, "percentage": 77.28, "elapsed_time": "4:31:39", "remaining_time": "1:19:50"}
|
||||
{"current_steps": 7570, "total_steps": 9782, "loss": 0.427, "lr": 7.399781494646196e-06, "epoch": 0.7738901525800598, "percentage": 77.39, "elapsed_time": "4:32:01", "remaining_time": "1:19:29"}
|
||||
{"current_steps": 7580, "total_steps": 9782, "loss": 0.4361, "lr": 7.33653088354449e-06, "epoch": 0.7749124645385539, "percentage": 77.49, "elapsed_time": "4:32:25", "remaining_time": "1:19:08"}
|
||||
{"current_steps": 7590, "total_steps": 9782, "loss": 0.4231, "lr": 7.273505236887554e-06, "epoch": 0.7759347764970481, "percentage": 77.59, "elapsed_time": "4:32:44", "remaining_time": "1:18:46"}
|
||||
{"current_steps": 7600, "total_steps": 9782, "loss": 0.4318, "lr": 7.2107053573789525e-06, "epoch": 0.7769570884555422, "percentage": 77.69, "elapsed_time": "4:33:06", "remaining_time": "1:18:24"}
|
||||
{"current_steps": 7610, "total_steps": 9782, "loss": 0.4454, "lr": 7.14813204484685e-06, "epoch": 0.7779794004140363, "percentage": 77.8, "elapsed_time": "4:33:28", "remaining_time": "1:18:03"}
|
||||
{"current_steps": 7620, "total_steps": 9782, "loss": 0.445, "lr": 7.085786096233813e-06, "epoch": 0.7790017123725305, "percentage": 77.9, "elapsed_time": "4:33:49", "remaining_time": "1:17:41"}
|
||||
{"current_steps": 7630, "total_steps": 9782, "loss": 0.4402, "lr": 7.023668305586678e-06, "epoch": 0.7800240243310246, "percentage": 78.0, "elapsed_time": "4:34:11", "remaining_time": "1:17:19"}
|
||||
{"current_steps": 7640, "total_steps": 9782, "loss": 0.4368, "lr": 6.961779464046417e-06, "epoch": 0.7810463362895187, "percentage": 78.1, "elapsed_time": "4:34:34", "remaining_time": "1:16:58"}
|
||||
{"current_steps": 7650, "total_steps": 9782, "loss": 0.446, "lr": 6.900120359838108e-06, "epoch": 0.7820686482480129, "percentage": 78.2, "elapsed_time": "4:34:57", "remaining_time": "1:16:37"}
|
||||
{"current_steps": 7660, "total_steps": 9782, "loss": 0.4424, "lr": 6.838691778260808e-06, "epoch": 0.783090960206507, "percentage": 78.31, "elapsed_time": "4:35:19", "remaining_time": "1:16:16"}
|
||||
{"current_steps": 7670, "total_steps": 9782, "loss": 0.4367, "lr": 6.777494501677639e-06, "epoch": 0.7841132721650012, "percentage": 78.41, "elapsed_time": "4:35:41", "remaining_time": "1:15:54"}
|
||||
{"current_steps": 7680, "total_steps": 9782, "loss": 0.4338, "lr": 6.716529309505801e-06, "epoch": 0.7851355841234953, "percentage": 78.51, "elapsed_time": "4:36:02", "remaining_time": "1:15:33"}
|
||||
{"current_steps": 7690, "total_steps": 9782, "loss": 0.4544, "lr": 6.6557969782066105e-06, "epoch": 0.7861578960819894, "percentage": 78.61, "elapsed_time": "4:36:24", "remaining_time": "1:15:11"}
|
||||
{"current_steps": 7700, "total_steps": 9782, "loss": 0.4401, "lr": 6.595298281275625e-06, "epoch": 0.7871802080404836, "percentage": 78.72, "elapsed_time": "4:36:45", "remaining_time": "1:14:49"}
|
||||
{"current_steps": 7710, "total_steps": 9782, "loss": 0.4326, "lr": 6.535033989232839e-06, "epoch": 0.7882025199989777, "percentage": 78.82, "elapsed_time": "4:37:10", "remaining_time": "1:14:29"}
|
||||
{"current_steps": 7720, "total_steps": 9782, "loss": 0.4297, "lr": 6.475004869612805e-06, "epoch": 0.7892248319574718, "percentage": 78.92, "elapsed_time": "4:37:31", "remaining_time": "1:14:07"}
|
||||
{"current_steps": 7730, "total_steps": 9782, "loss": 0.4372, "lr": 6.415211686954894e-06, "epoch": 0.790247143915966, "percentage": 79.02, "elapsed_time": "4:37:52", "remaining_time": "1:13:45"}
|
||||
{"current_steps": 7740, "total_steps": 9782, "loss": 0.4336, "lr": 6.35565520279355e-06, "epoch": 0.7912694558744601, "percentage": 79.12, "elapsed_time": "4:38:14", "remaining_time": "1:13:24"}
|
||||
{"current_steps": 7750, "total_steps": 9782, "loss": 0.4323, "lr": 6.296336175648592e-06, "epoch": 0.7922917678329542, "percentage": 79.23, "elapsed_time": "4:38:34", "remaining_time": "1:13:02"}
|
||||
{"current_steps": 7760, "total_steps": 9782, "loss": 0.436, "lr": 6.237255361015554e-06, "epoch": 0.7933140797914484, "percentage": 79.33, "elapsed_time": "4:38:57", "remaining_time": "1:12:41"}
|
||||
{"current_steps": 7770, "total_steps": 9782, "loss": 0.4406, "lr": 6.1784135113560516e-06, "epoch": 0.7943363917499425, "percentage": 79.43, "elapsed_time": "4:39:18", "remaining_time": "1:12:19"}
|
||||
{"current_steps": 7780, "total_steps": 9782, "loss": 0.4428, "lr": 6.119811376088239e-06, "epoch": 0.7953587037084366, "percentage": 79.53, "elapsed_time": "4:39:41", "remaining_time": "1:11:58"}
|
||||
{"current_steps": 7790, "total_steps": 9782, "loss": 0.4366, "lr": 6.06144970157719e-06, "epoch": 0.7963810156669308, "percentage": 79.64, "elapsed_time": "4:40:04", "remaining_time": "1:11:37"}
|
||||
{"current_steps": 7800, "total_steps": 9782, "loss": 0.4439, "lr": 6.00332923112546e-06, "epoch": 0.7974033276254249, "percentage": 79.74, "elapsed_time": "4:40:26", "remaining_time": "1:11:15"}
|
||||
{"current_steps": 7810, "total_steps": 9782, "loss": 0.4455, "lr": 5.945450704963604e-06, "epoch": 0.798425639583919, "percentage": 79.84, "elapsed_time": "4:40:47", "remaining_time": "1:10:54"}
|
||||
{"current_steps": 7820, "total_steps": 9782, "loss": 0.4367, "lr": 5.887814860240737e-06, "epoch": 0.7994479515424132, "percentage": 79.94, "elapsed_time": "4:41:09", "remaining_time": "1:10:32"}
|
||||
{"current_steps": 7830, "total_steps": 9782, "loss": 0.4336, "lr": 5.830422431015112e-06, "epoch": 0.8004702635009073, "percentage": 80.04, "elapsed_time": "4:41:31", "remaining_time": "1:10:10"}
|
||||
{"current_steps": 7840, "total_steps": 9782, "loss": 0.4456, "lr": 5.773274148244867e-06, "epoch": 0.8014925754594014, "percentage": 80.15, "elapsed_time": "4:41:53", "remaining_time": "1:09:49"}
|
||||
{"current_steps": 7850, "total_steps": 9782, "loss": 0.4339, "lr": 5.716370739778612e-06, "epoch": 0.8025148874178956, "percentage": 80.25, "elapsed_time": "4:42:15", "remaining_time": "1:09:27"}
|
||||
{"current_steps": 7860, "total_steps": 9782, "loss": 0.4407, "lr": 5.659712930346225e-06, "epoch": 0.8035371993763897, "percentage": 80.35, "elapsed_time": "4:42:35", "remaining_time": "1:09:06"}
|
||||
{"current_steps": 7870, "total_steps": 9782, "loss": 0.4381, "lr": 5.603301441549585e-06, "epoch": 0.8045595113348838, "percentage": 80.45, "elapsed_time": "4:42:57", "remaining_time": "1:08:44"}
|
||||
{"current_steps": 7880, "total_steps": 9782, "loss": 0.4426, "lr": 5.5471369918534135e-06, "epoch": 0.805581823293378, "percentage": 80.56, "elapsed_time": "4:43:18", "remaining_time": "1:08:23"}
|
||||
{"current_steps": 7890, "total_steps": 9782, "loss": 0.4337, "lr": 5.491220296576088e-06, "epoch": 0.8066041352518721, "percentage": 80.66, "elapsed_time": "4:43:41", "remaining_time": "1:08:01"}
|
||||
{"current_steps": 7900, "total_steps": 9782, "loss": 0.4348, "lr": 5.435552067880562e-06, "epoch": 0.8076264472103662, "percentage": 80.76, "elapsed_time": "4:44:03", "remaining_time": "1:07:40"}
|
||||
{"current_steps": 7910, "total_steps": 9782, "loss": 0.4395, "lr": 5.380133014765296e-06, "epoch": 0.8086487591688604, "percentage": 80.86, "elapsed_time": "4:44:25", "remaining_time": "1:07:18"}
|
||||
{"current_steps": 7920, "total_steps": 9782, "loss": 0.4309, "lr": 5.3249638430551834e-06, "epoch": 0.8096710711273545, "percentage": 80.97, "elapsed_time": "4:44:48", "remaining_time": "1:06:57"}
|
||||
{"current_steps": 7930, "total_steps": 9782, "loss": 0.4348, "lr": 5.270045255392608e-06, "epoch": 0.8106933830858486, "percentage": 81.07, "elapsed_time": "4:45:11", "remaining_time": "1:06:36"}
|
||||
{"current_steps": 7940, "total_steps": 9782, "loss": 0.4333, "lr": 5.215377951228501e-06, "epoch": 0.8117156950443428, "percentage": 81.17, "elapsed_time": "4:45:33", "remaining_time": "1:06:14"}
|
||||
{"current_steps": 7950, "total_steps": 9782, "loss": 0.4349, "lr": 5.160962626813379e-06, "epoch": 0.8127380070028369, "percentage": 81.27, "elapsed_time": "4:45:57", "remaining_time": "1:05:53"}
|
||||
{"current_steps": 7960, "total_steps": 9782, "loss": 0.4346, "lr": 5.106799975188523e-06, "epoch": 0.813760318961331, "percentage": 81.37, "elapsed_time": "4:46:18", "remaining_time": "1:05:32"}
|
||||
{"current_steps": 7970, "total_steps": 9782, "loss": 0.4281, "lr": 5.052890686177139e-06, "epoch": 0.8147826309198252, "percentage": 81.48, "elapsed_time": "4:46:40", "remaining_time": "1:05:10"}
|
||||
{"current_steps": 7980, "total_steps": 9782, "loss": 0.4348, "lr": 4.999235446375566e-06, "epoch": 0.8158049428783193, "percentage": 81.58, "elapsed_time": "4:47:03", "remaining_time": "1:04:49"}
|
||||
{"current_steps": 7990, "total_steps": 9782, "loss": 0.4337, "lr": 4.945834939144539e-06, "epoch": 0.8168272548368134, "percentage": 81.68, "elapsed_time": "4:47:25", "remaining_time": "1:04:27"}
|
||||
{"current_steps": 8000, "total_steps": 9782, "loss": 0.4337, "lr": 4.892689844600484e-06, "epoch": 0.8178495667953076, "percentage": 81.78, "elapsed_time": "4:47:48", "remaining_time": "1:04:06"}
|
||||
{"current_steps": 8010, "total_steps": 9782, "loss": 0.4304, "lr": 4.839800839606851e-06, "epoch": 0.8188718787538017, "percentage": 81.89, "elapsed_time": "4:48:11", "remaining_time": "1:03:45"}
|
||||
{"current_steps": 8020, "total_steps": 9782, "loss": 0.4395, "lr": 4.787168597765501e-06, "epoch": 0.8198941907122959, "percentage": 81.99, "elapsed_time": "4:48:33", "remaining_time": "1:03:23"}
|
||||
{"current_steps": 8030, "total_steps": 9782, "loss": 0.4314, "lr": 4.734793789408115e-06, "epoch": 0.82091650267079, "percentage": 82.09, "elapsed_time": "4:48:56", "remaining_time": "1:03:02"}
|
||||
{"current_steps": 8040, "total_steps": 9782, "loss": 0.4376, "lr": 4.682677081587691e-06, "epoch": 0.8219388146292841, "percentage": 82.19, "elapsed_time": "4:49:18", "remaining_time": "1:02:41"}
|
||||
{"current_steps": 8050, "total_steps": 9782, "loss": 0.4407, "lr": 4.630819138069983e-06, "epoch": 0.8229611265877783, "percentage": 82.29, "elapsed_time": "4:49:40", "remaining_time": "1:02:19"}
|
||||
{"current_steps": 8060, "total_steps": 9782, "loss": 0.4277, "lr": 4.579220619325106e-06, "epoch": 0.8239834385462724, "percentage": 82.4, "elapsed_time": "4:50:00", "remaining_time": "1:01:57"}
|
||||
{"current_steps": 8070, "total_steps": 9782, "loss": 0.4348, "lr": 4.527882182519114e-06, "epoch": 0.8250057505047665, "percentage": 82.5, "elapsed_time": "4:50:23", "remaining_time": "1:01:36"}
|
||||
{"current_steps": 8080, "total_steps": 9782, "loss": 0.4277, "lr": 4.476804481505609e-06, "epoch": 0.8260280624632607, "percentage": 82.6, "elapsed_time": "4:50:46", "remaining_time": "1:01:14"}
|
||||
{"current_steps": 8090, "total_steps": 9782, "loss": 0.4353, "lr": 4.425988166817422e-06, "epoch": 0.8270503744217548, "percentage": 82.7, "elapsed_time": "4:51:09", "remaining_time": "1:00:53"}
|
||||
{"current_steps": 8100, "total_steps": 9782, "loss": 0.4304, "lr": 4.3754338856583365e-06, "epoch": 0.8280726863802489, "percentage": 82.81, "elapsed_time": "4:51:33", "remaining_time": "1:00:32"}
|
||||
{"current_steps": 8110, "total_steps": 9782, "loss": 0.4357, "lr": 4.325142281894837e-06, "epoch": 0.8290949983387431, "percentage": 82.91, "elapsed_time": "4:51:56", "remaining_time": "1:00:11"}
|
||||
{"current_steps": 8120, "total_steps": 9782, "loss": 0.4332, "lr": 4.275113996047916e-06, "epoch": 0.8301173102972372, "percentage": 83.01, "elapsed_time": "4:52:18", "remaining_time": "0:59:49"}
|
||||
{"current_steps": 8130, "total_steps": 9782, "loss": 0.4328, "lr": 4.225349665284908e-06, "epoch": 0.8311396222557313, "percentage": 83.11, "elapsed_time": "4:52:40", "remaining_time": "0:59:28"}
|
||||
{"current_steps": 8140, "total_steps": 9782, "loss": 0.4261, "lr": 4.175849923411379e-06, "epoch": 0.8321619342142255, "percentage": 83.21, "elapsed_time": "4:53:02", "remaining_time": "0:59:06"}
|
||||
{"current_steps": 8150, "total_steps": 9782, "loss": 0.4273, "lr": 4.126615400863054e-06, "epoch": 0.8331842461727196, "percentage": 83.32, "elapsed_time": "4:53:24", "remaining_time": "0:58:45"}
|
||||
{"current_steps": 8160, "total_steps": 9782, "loss": 0.4274, "lr": 4.077646724697778e-06, "epoch": 0.8342065581312137, "percentage": 83.42, "elapsed_time": "4:53:46", "remaining_time": "0:58:23"}
|
||||
{"current_steps": 8170, "total_steps": 9782, "loss": 0.4321, "lr": 4.02894451858756e-06, "epoch": 0.8352288700897079, "percentage": 83.52, "elapsed_time": "4:54:09", "remaining_time": "0:58:02"}
|
||||
{"current_steps": 8180, "total_steps": 9782, "loss": 0.4328, "lr": 3.980509402810598e-06, "epoch": 0.836251182048202, "percentage": 83.62, "elapsed_time": "4:54:32", "remaining_time": "0:57:40"}
|
||||
{"current_steps": 8190, "total_steps": 9782, "loss": 0.4277, "lr": 3.932341994243366e-06, "epoch": 0.8372734940066962, "percentage": 83.73, "elapsed_time": "4:54:55", "remaining_time": "0:57:19"}
|
||||
{"current_steps": 8200, "total_steps": 9782, "loss": 0.4329, "lr": 3.884442906352826e-06, "epoch": 0.8382958059651903, "percentage": 83.83, "elapsed_time": "4:55:18", "remaining_time": "0:56:58"}
|
||||
{"current_steps": 8210, "total_steps": 9782, "loss": 0.4298, "lr": 3.836812749188534e-06, "epoch": 0.8393181179236844, "percentage": 83.93, "elapsed_time": "4:55:41", "remaining_time": "0:56:37"}
|
||||
{"current_steps": 8220, "total_steps": 9782, "loss": 0.4275, "lr": 3.7894521293749207e-06, "epoch": 0.8403404298821785, "percentage": 84.03, "elapsed_time": "4:56:03", "remaining_time": "0:56:15"}
|
||||
{"current_steps": 8230, "total_steps": 9782, "loss": 0.4299, "lr": 3.742361650103554e-06, "epoch": 0.8413627418406727, "percentage": 84.13, "elapsed_time": "4:56:25", "remaining_time": "0:55:54"}
|
||||
{"current_steps": 8240, "total_steps": 9782, "loss": 0.4321, "lr": 3.6955419111254415e-06, "epoch": 0.8423850537991668, "percentage": 84.24, "elapsed_time": "4:56:48", "remaining_time": "0:55:32"}
|
||||
{"current_steps": 8250, "total_steps": 9782, "loss": 0.4261, "lr": 3.6489935087434144e-06, "epoch": 0.843407365757661, "percentage": 84.34, "elapsed_time": "4:57:10", "remaining_time": "0:55:11"}
|
||||
{"current_steps": 8260, "total_steps": 9782, "loss": 0.4299, "lr": 3.6027170358045148e-06, "epoch": 0.8444296777161551, "percentage": 84.44, "elapsed_time": "4:57:32", "remaining_time": "0:54:49"}
|
||||
{"current_steps": 8270, "total_steps": 9782, "loss": 0.4293, "lr": 3.55671308169247e-06, "epoch": 0.8454519896746492, "percentage": 84.54, "elapsed_time": "4:57:52", "remaining_time": "0:54:27"}
|
||||
{"current_steps": 8280, "total_steps": 9782, "loss": 0.4264, "lr": 3.5109822323201423e-06, "epoch": 0.8464743016331433, "percentage": 84.65, "elapsed_time": "4:58:14", "remaining_time": "0:54:06"}
|
||||
{"current_steps": 8290, "total_steps": 9782, "loss": 0.4258, "lr": 3.465525070122108e-06, "epoch": 0.8474966135916375, "percentage": 84.75, "elapsed_time": "4:58:36", "remaining_time": "0:53:44"}
|
||||
{"current_steps": 8300, "total_steps": 9782, "loss": 0.4283, "lr": 3.4203421740472365e-06, "epoch": 0.8485189255501316, "percentage": 84.85, "elapsed_time": "4:58:58", "remaining_time": "0:53:23"}
|
||||
{"current_steps": 8310, "total_steps": 9782, "loss": 0.4335, "lr": 3.375434119551285e-06, "epoch": 0.8495412375086258, "percentage": 84.95, "elapsed_time": "4:59:22", "remaining_time": "0:53:01"}
|
||||
{"current_steps": 8320, "total_steps": 9782, "loss": 0.4377, "lr": 3.3308014785895904e-06, "epoch": 0.8505635494671199, "percentage": 85.05, "elapsed_time": "4:59:45", "remaining_time": "0:52:40"}
|
||||
{"current_steps": 8330, "total_steps": 9782, "loss": 0.4328, "lr": 3.286444819609799e-06, "epoch": 0.851585861425614, "percentage": 85.16, "elapsed_time": "5:00:08", "remaining_time": "0:52:19"}
|
||||
{"current_steps": 8340, "total_steps": 9782, "loss": 0.4251, "lr": 3.242364707544601e-06, "epoch": 0.8526081733841082, "percentage": 85.26, "elapsed_time": "5:00:30", "remaining_time": "0:51:57"}
|
||||
{"current_steps": 8350, "total_steps": 9782, "loss": 0.4249, "lr": 3.1985617038045477e-06, "epoch": 0.8536304853426023, "percentage": 85.36, "elapsed_time": "5:00:51", "remaining_time": "0:51:35"}
|
||||
{"current_steps": 8360, "total_steps": 9782, "loss": 0.4221, "lr": 3.1550363662708996e-06, "epoch": 0.8546527973010964, "percentage": 85.46, "elapsed_time": "5:01:14", "remaining_time": "0:51:14"}
|
||||
{"current_steps": 8370, "total_steps": 9782, "loss": 0.4308, "lr": 3.1117892492885188e-06, "epoch": 0.8556751092595906, "percentage": 85.57, "elapsed_time": "5:01:36", "remaining_time": "0:50:52"}
|
||||
{"current_steps": 8380, "total_steps": 9782, "loss": 0.433, "lr": 3.0688209036588174e-06, "epoch": 0.8566974212180847, "percentage": 85.67, "elapsed_time": "5:02:00", "remaining_time": "0:50:31"}
|
||||
{"current_steps": 8390, "total_steps": 9782, "loss": 0.4281, "lr": 3.0261318766327206e-06, "epoch": 0.8577197331765788, "percentage": 85.77, "elapsed_time": "5:02:22", "remaining_time": "0:50:10"}
|
||||
{"current_steps": 8400, "total_steps": 9782, "loss": 0.4329, "lr": 2.983722711903747e-06, "epoch": 0.858742045135073, "percentage": 85.87, "elapsed_time": "5:02:45", "remaining_time": "0:49:48"}
|
||||
{"current_steps": 8410, "total_steps": 9782, "loss": 0.4312, "lr": 2.941593949601007e-06, "epoch": 0.8597643570935671, "percentage": 85.97, "elapsed_time": "5:03:05", "remaining_time": "0:49:26"}
|
||||
{"current_steps": 8420, "total_steps": 9782, "loss": 0.4324, "lr": 2.8997461262823823e-06, "epoch": 0.8607866690520612, "percentage": 86.08, "elapsed_time": "5:03:27", "remaining_time": "0:49:05"}
|
||||
{"current_steps": 8430, "total_steps": 9782, "loss": 0.4232, "lr": 2.8581797749276914e-06, "epoch": 0.8618089810105554, "percentage": 86.18, "elapsed_time": "5:03:48", "remaining_time": "0:48:43"}
|
||||
{"current_steps": 8440, "total_steps": 9782, "loss": 0.4205, "lr": 2.816895424931873e-06, "epoch": 0.8628312929690495, "percentage": 86.28, "elapsed_time": "5:04:09", "remaining_time": "0:48:21"}
|
||||
{"current_steps": 8450, "total_steps": 9782, "loss": 0.4235, "lr": 2.7758936020982425e-06, "epoch": 0.8638536049275436, "percentage": 86.38, "elapsed_time": "5:04:32", "remaining_time": "0:48:00"}
|
||||
{"current_steps": 8460, "total_steps": 9782, "loss": 0.4228, "lr": 2.735174828631837e-06, "epoch": 0.8648759168860378, "percentage": 86.49, "elapsed_time": "5:04:53", "remaining_time": "0:47:38"}
|
||||
{"current_steps": 8470, "total_steps": 9782, "loss": 0.4356, "lr": 2.694739623132722e-06, "epoch": 0.8658982288445319, "percentage": 86.59, "elapsed_time": "5:05:15", "remaining_time": "0:47:17"}
|
||||
{"current_steps": 8480, "total_steps": 9782, "loss": 0.4222, "lr": 2.654588500589397e-06, "epoch": 0.866920540803026, "percentage": 86.69, "elapsed_time": "5:05:37", "remaining_time": "0:46:55"}
|
||||
{"current_steps": 8490, "total_steps": 9782, "loss": 0.4262, "lr": 2.614721972372247e-06, "epoch": 0.8679428527615202, "percentage": 86.79, "elapsed_time": "5:06:00", "remaining_time": "0:46:34"}
|
||||
{"current_steps": 8500, "total_steps": 9782, "loss": 0.4207, "lr": 2.5751405462270286e-06, "epoch": 0.8689651647200143, "percentage": 86.89, "elapsed_time": "5:06:22", "remaining_time": "0:46:12"}
|
||||
{"current_steps": 8510, "total_steps": 9782, "loss": 0.4348, "lr": 2.5358447262683855e-06, "epoch": 0.8699874766785084, "percentage": 87.0, "elapsed_time": "5:06:45", "remaining_time": "0:45:51"}
|
||||
{"current_steps": 8520, "total_steps": 9782, "loss": 0.4247, "lr": 2.4968350129734445e-06, "epoch": 0.8710097886370026, "percentage": 87.1, "elapsed_time": "5:07:07", "remaining_time": "0:45:29"}
|
||||
{"current_steps": 8530, "total_steps": 9782, "loss": 0.4289, "lr": 2.4581119031754556e-06, "epoch": 0.8720321005954967, "percentage": 87.2, "elapsed_time": "5:07:29", "remaining_time": "0:45:07"}
|
||||
{"current_steps": 8540, "total_steps": 9782, "loss": 0.4205, "lr": 2.4196758900574156e-06, "epoch": 0.8730544125539909, "percentage": 87.3, "elapsed_time": "5:07:52", "remaining_time": "0:44:46"}
|
||||
{"current_steps": 8550, "total_steps": 9782, "loss": 0.4244, "lr": 2.381527463145833e-06, "epoch": 0.874076724512485, "percentage": 87.41, "elapsed_time": "5:08:13", "remaining_time": "0:44:24"}
|
||||
{"current_steps": 8560, "total_steps": 9782, "loss": 0.425, "lr": 2.343667108304484e-06, "epoch": 0.8750990364709791, "percentage": 87.51, "elapsed_time": "5:08:35", "remaining_time": "0:44:03"}
|
||||
{"current_steps": 8570, "total_steps": 9782, "loss": 0.4197, "lr": 2.3060953077282068e-06, "epoch": 0.8761213484294732, "percentage": 87.61, "elapsed_time": "5:08:58", "remaining_time": "0:43:41"}
|
||||
{"current_steps": 8580, "total_steps": 9782, "loss": 0.4235, "lr": 2.2688125399367766e-06, "epoch": 0.8771436603879674, "percentage": 87.71, "elapsed_time": "5:09:19", "remaining_time": "0:43:20"}
|
||||
{"current_steps": 8590, "total_steps": 9782, "loss": 0.4269, "lr": 2.231819279768807e-06, "epoch": 0.8781659723464615, "percentage": 87.81, "elapsed_time": "5:09:40", "remaining_time": "0:42:58"}
|
||||
{"current_steps": 8600, "total_steps": 9782, "loss": 0.4313, "lr": 2.1951159983756936e-06, "epoch": 0.8791882843049557, "percentage": 87.92, "elapsed_time": "5:10:02", "remaining_time": "0:42:36"}
|
||||
{"current_steps": 8610, "total_steps": 9782, "loss": 0.4298, "lr": 2.1587031632156363e-06, "epoch": 0.8802105962634498, "percentage": 88.02, "elapsed_time": "5:10:24", "remaining_time": "0:42:15"}
|
||||
{"current_steps": 8620, "total_steps": 9782, "loss": 0.4324, "lr": 2.122581238047652e-06, "epoch": 0.8812329082219439, "percentage": 88.12, "elapsed_time": "5:10:47", "remaining_time": "0:41:53"}
|
||||
{"current_steps": 8630, "total_steps": 9782, "loss": 0.4173, "lr": 2.086750682925706e-06, "epoch": 0.8822552201804381, "percentage": 88.22, "elapsed_time": "5:11:08", "remaining_time": "0:41:31"}
|
||||
{"current_steps": 8640, "total_steps": 9782, "loss": 0.432, "lr": 2.0512119541928164e-06, "epoch": 0.8832775321389322, "percentage": 88.33, "elapsed_time": "5:11:30", "remaining_time": "0:41:10"}
|
||||
{"current_steps": 8650, "total_steps": 9782, "loss": 0.4269, "lr": 2.0159655044752673e-06, "epoch": 0.8842998440974263, "percentage": 88.43, "elapsed_time": "5:11:53", "remaining_time": "0:40:48"}
|
||||
{"current_steps": 8660, "total_steps": 9782, "loss": 0.4364, "lr": 1.981011782676842e-06, "epoch": 0.8853221560559205, "percentage": 88.53, "elapsed_time": "5:12:14", "remaining_time": "0:40:27"}
|
||||
{"current_steps": 8670, "total_steps": 9782, "loss": 0.425, "lr": 1.9463512339730873e-06, "epoch": 0.8863444680144146, "percentage": 88.63, "elapsed_time": "5:12:37", "remaining_time": "0:40:05"}
|
||||
{"current_steps": 8680, "total_steps": 9782, "loss": 0.4306, "lr": 1.911984299805658e-06, "epoch": 0.8873667799729087, "percentage": 88.73, "elapsed_time": "5:13:01", "remaining_time": "0:39:44"}
|
||||
{"current_steps": 8690, "total_steps": 9782, "loss": 0.4274, "lr": 1.8779114178767016e-06, "epoch": 0.8883890919314029, "percentage": 88.84, "elapsed_time": "5:13:23", "remaining_time": "0:39:22"}
|
||||
{"current_steps": 8700, "total_steps": 9782, "loss": 0.429, "lr": 1.8441330221432684e-06, "epoch": 0.889411403889897, "percentage": 88.94, "elapsed_time": "5:13:47", "remaining_time": "0:39:01"}
|
||||
{"current_steps": 8710, "total_steps": 9782, "loss": 0.4288, "lr": 1.8106495428117902e-06, "epoch": 0.8904337158483911, "percentage": 89.04, "elapsed_time": "5:14:10", "remaining_time": "0:38:40"}
|
||||
{"current_steps": 8720, "total_steps": 9782, "loss": 0.4236, "lr": 1.7774614063326005e-06, "epoch": 0.8914560278068853, "percentage": 89.14, "elapsed_time": "5:14:32", "remaining_time": "0:38:18"}
|
||||
{"current_steps": 8730, "total_steps": 9782, "loss": 0.424, "lr": 1.7445690353945109e-06, "epoch": 0.8924783397653794, "percentage": 89.25, "elapsed_time": "5:14:53", "remaining_time": "0:37:56"}
|
||||
{"current_steps": 8740, "total_steps": 9782, "loss": 0.4308, "lr": 1.711972848919416e-06, "epoch": 0.8935006517238735, "percentage": 89.35, "elapsed_time": "5:15:15", "remaining_time": "0:37:35"}
|
||||
{"current_steps": 8750, "total_steps": 9782, "loss": 0.4352, "lr": 1.6796732620569606e-06, "epoch": 0.8945229636823677, "percentage": 89.45, "elapsed_time": "5:15:39", "remaining_time": "0:37:13"}
|
||||
{"current_steps": 8760, "total_steps": 9782, "loss": 0.4361, "lr": 1.6476706861792617e-06, "epoch": 0.8955452756408618, "percentage": 89.55, "elapsed_time": "5:16:01", "remaining_time": "0:36:52"}
|
||||
{"current_steps": 8770, "total_steps": 9782, "loss": 0.4223, "lr": 1.6159655288756599e-06, "epoch": 0.896567587599356, "percentage": 89.65, "elapsed_time": "5:16:25", "remaining_time": "0:36:30"}
|
||||
{"current_steps": 8780, "total_steps": 9782, "loss": 0.4268, "lr": 1.5845581939475219e-06, "epoch": 0.8975898995578501, "percentage": 89.76, "elapsed_time": "5:16:47", "remaining_time": "0:36:09"}
|
||||
{"current_steps": 8790, "total_steps": 9782, "loss": 0.4239, "lr": 1.5534490814031245e-06, "epoch": 0.8986122115163442, "percentage": 89.86, "elapsed_time": "5:17:11", "remaining_time": "0:35:47"}
|
||||
{"current_steps": 8800, "total_steps": 9782, "loss": 0.4348, "lr": 1.5226385874525324e-06, "epoch": 0.8996345234748383, "percentage": 89.96, "elapsed_time": "5:17:33", "remaining_time": "0:35:26"}
|
||||
{"current_steps": 8810, "total_steps": 9782, "loss": 0.425, "lr": 1.4921271045025499e-06, "epoch": 0.9006568354333325, "percentage": 90.06, "elapsed_time": "5:17:54", "remaining_time": "0:35:04"}
|
||||
{"current_steps": 8820, "total_steps": 9782, "loss": 0.417, "lr": 1.4619150211517552e-06, "epoch": 0.9016791473918266, "percentage": 90.17, "elapsed_time": "5:18:16", "remaining_time": "0:34:42"}
|
||||
{"current_steps": 8830, "total_steps": 9782, "loss": 0.4177, "lr": 1.4320027221855186e-06, "epoch": 0.9027014593503208, "percentage": 90.27, "elapsed_time": "5:18:37", "remaining_time": "0:34:21"}
|
||||
{"current_steps": 8840, "total_steps": 9782, "loss": 0.4288, "lr": 1.4023905885711148e-06, "epoch": 0.9037237713088149, "percentage": 90.37, "elapsed_time": "5:19:00", "remaining_time": "0:33:59"}
|
||||
{"current_steps": 8850, "total_steps": 9782, "loss": 0.4305, "lr": 1.3730789974528784e-06, "epoch": 0.904746083267309, "percentage": 90.47, "elapsed_time": "5:19:23", "remaining_time": "0:33:38"}
|
||||
{"current_steps": 8860, "total_steps": 9782, "loss": 0.4254, "lr": 1.3440683221473793e-06, "epoch": 0.9057683952258031, "percentage": 90.57, "elapsed_time": "5:19:45", "remaining_time": "0:33:16"}
|
||||
{"current_steps": 8870, "total_steps": 9782, "loss": 0.4136, "lr": 1.315358932138691e-06, "epoch": 0.9067907071842973, "percentage": 90.68, "elapsed_time": "5:20:07", "remaining_time": "0:32:54"}
|
||||
{"current_steps": 8880, "total_steps": 9782, "loss": 0.4185, "lr": 1.2869511930736684e-06, "epoch": 0.9078130191427914, "percentage": 90.78, "elapsed_time": "5:20:29", "remaining_time": "0:32:33"}
|
||||
{"current_steps": 8890, "total_steps": 9782, "loss": 0.4315, "lr": 1.258845466757308e-06, "epoch": 0.9088353311012856, "percentage": 90.88, "elapsed_time": "5:20:52", "remaining_time": "0:32:11"}
|
||||
{"current_steps": 8900, "total_steps": 9782, "loss": 0.4299, "lr": 1.2310421111481146e-06, "epoch": 0.9098576430597797, "percentage": 90.98, "elapsed_time": "5:21:14", "remaining_time": "0:31:50"}
|
||||
{"current_steps": 8910, "total_steps": 9782, "loss": 0.4254, "lr": 1.2035414803535623e-06, "epoch": 0.9108799550182738, "percentage": 91.09, "elapsed_time": "5:21:35", "remaining_time": "0:31:28"}
|
||||
{"current_steps": 8920, "total_steps": 9782, "loss": 0.4288, "lr": 1.1763439246255835e-06, "epoch": 0.9119022669767679, "percentage": 91.19, "elapsed_time": "5:21:57", "remaining_time": "0:31:06"}
|
||||
{"current_steps": 8930, "total_steps": 9782, "loss": 0.4292, "lr": 1.149449790356108e-06, "epoch": 0.9129245789352621, "percentage": 91.29, "elapsed_time": "5:22:22", "remaining_time": "0:30:45"}
|
||||
{"current_steps": 8940, "total_steps": 9782, "loss": 0.4277, "lr": 1.1228594200726223e-06, "epoch": 0.9139468908937562, "percentage": 91.39, "elapsed_time": "5:22:44", "remaining_time": "0:30:23"}
|
||||
{"current_steps": 8950, "total_steps": 9782, "loss": 0.4266, "lr": 1.0965731524338634e-06, "epoch": 0.9149692028522504, "percentage": 91.49, "elapsed_time": "5:23:06", "remaining_time": "0:30:02"}
|
||||
{"current_steps": 8960, "total_steps": 9782, "loss": 0.4202, "lr": 1.070591322225456e-06, "epoch": 0.9159915148107445, "percentage": 91.6, "elapsed_time": "5:23:28", "remaining_time": "0:29:40"}
|
||||
{"current_steps": 8970, "total_steps": 9782, "loss": 0.4298, "lr": 1.0449142603556672e-06, "epoch": 0.9170138267692386, "percentage": 91.7, "elapsed_time": "5:23:48", "remaining_time": "0:29:18"}
|
||||
{"current_steps": 8980, "total_steps": 9782, "loss": 0.4312, "lr": 1.0195422938511973e-06, "epoch": 0.9180361387277328, "percentage": 91.8, "elapsed_time": "5:24:11", "remaining_time": "0:28:57"}
|
||||
{"current_steps": 8990, "total_steps": 9782, "loss": 0.4267, "lr": 9.944757458530047e-07, "epoch": 0.9190584506862269, "percentage": 91.9, "elapsed_time": "5:24:32", "remaining_time": "0:28:35"}
|
||||
{"current_steps": 9000, "total_steps": 9782, "loss": 0.4255, "lr": 9.697149356121927e-07, "epoch": 0.920080762644721, "percentage": 92.01, "elapsed_time": "5:24:55", "remaining_time": "0:28:13"}
|
||||
{"current_steps": 9010, "total_steps": 9782, "loss": 0.4264, "lr": 9.452601784859516e-07, "epoch": 0.9211030746032152, "percentage": 92.11, "elapsed_time": "5:25:54", "remaining_time": "0:27:55"}
|
||||
{"current_steps": 9020, "total_steps": 9782, "loss": 0.4171, "lr": 9.211117859335344e-07, "epoch": 0.9221253865617093, "percentage": 92.21, "elapsed_time": "5:26:16", "remaining_time": "0:27:33"}
|
||||
{"current_steps": 9030, "total_steps": 9782, "loss": 0.421, "lr": 8.972700655122817e-07, "epoch": 0.9231476985202034, "percentage": 92.31, "elapsed_time": "5:26:39", "remaining_time": "0:27:12"}
|
||||
{"current_steps": 9040, "total_steps": 9782, "loss": 0.4255, "lr": 8.737353208737281e-07, "epoch": 0.9241700104786976, "percentage": 92.41, "elapsed_time": "5:26:59", "remaining_time": "0:26:50"}
|
||||
{"current_steps": 9050, "total_steps": 9782, "loss": 0.4126, "lr": 8.505078517597131e-07, "epoch": 0.9251923224371917, "percentage": 92.52, "elapsed_time": "5:27:22", "remaining_time": "0:26:28"}
|
||||
{"current_steps": 9060, "total_steps": 9782, "loss": 0.4249, "lr": 8.275879539985765e-07, "epoch": 0.9262146343956859, "percentage": 92.62, "elapsed_time": "5:27:45", "remaining_time": "0:26:07"}
|
||||
{"current_steps": 9070, "total_steps": 9782, "loss": 0.426, "lr": 8.049759195013773e-07, "epoch": 0.92723694635418, "percentage": 92.72, "elapsed_time": "5:28:09", "remaining_time": "0:25:45"}
|
||||
{"current_steps": 9080, "total_steps": 9782, "loss": 0.4249, "lr": 7.826720362581946e-07, "epoch": 0.9282592583126741, "percentage": 92.82, "elapsed_time": "5:28:31", "remaining_time": "0:25:23"}
|
||||
{"current_steps": 9090, "total_steps": 9782, "loss": 0.4296, "lr": 7.606765883344441e-07, "epoch": 0.9292815702711682, "percentage": 92.93, "elapsed_time": "5:28:55", "remaining_time": "0:25:02"}
|
||||
{"current_steps": 9100, "total_steps": 9782, "loss": 0.4227, "lr": 7.389898558672642e-07, "epoch": 0.9303038822296624, "percentage": 93.03, "elapsed_time": "5:29:18", "remaining_time": "0:24:40"}
|
||||
{"current_steps": 9110, "total_steps": 9782, "loss": 0.4226, "lr": 7.176121150619524e-07, "epoch": 0.9313261941881565, "percentage": 93.13, "elapsed_time": "5:29:41", "remaining_time": "0:24:19"}
|
||||
{"current_steps": 9120, "total_steps": 9782, "loss": 0.419, "lr": 6.96543638188446e-07, "epoch": 0.9323485061466507, "percentage": 93.23, "elapsed_time": "5:30:03", "remaining_time": "0:23:57"}
|
||||
{"current_steps": 9130, "total_steps": 9782, "loss": 0.4142, "lr": 6.757846935778495e-07, "epoch": 0.9333708181051448, "percentage": 93.33, "elapsed_time": "5:30:26", "remaining_time": "0:23:35"}
|
||||
{"current_steps": 9140, "total_steps": 9782, "loss": 0.4336, "lr": 6.55335545619018e-07, "epoch": 0.9343931300636389, "percentage": 93.44, "elapsed_time": "5:30:47", "remaining_time": "0:23:14"}
|
||||
{"current_steps": 9150, "total_steps": 9782, "loss": 0.4285, "lr": 6.351964547552048e-07, "epoch": 0.935415442022133, "percentage": 93.54, "elapsed_time": "5:31:10", "remaining_time": "0:22:52"}
|
||||
{"current_steps": 9160, "total_steps": 9782, "loss": 0.4318, "lr": 6.153676774807188e-07, "epoch": 0.9364377539806272, "percentage": 93.64, "elapsed_time": "5:31:32", "remaining_time": "0:22:30"}
|
||||
{"current_steps": 9170, "total_steps": 9782, "loss": 0.4197, "lr": 5.958494663376751e-07, "epoch": 0.9374600659391213, "percentage": 93.74, "elapsed_time": "5:31:54", "remaining_time": "0:22:09"}
|
||||
{"current_steps": 9180, "total_steps": 9782, "loss": 0.4218, "lr": 5.766420699127778e-07, "epoch": 0.9384823778976155, "percentage": 93.85, "elapsed_time": "5:32:16", "remaining_time": "0:21:47"}
|
||||
{"current_steps": 9190, "total_steps": 9782, "loss": 0.4295, "lr": 5.577457328341529e-07, "epoch": 0.9395046898561096, "percentage": 93.95, "elapsed_time": "5:32:40", "remaining_time": "0:21:25"}
|
||||
{"current_steps": 9200, "total_steps": 9782, "loss": 0.4245, "lr": 5.391606957682149e-07, "epoch": 0.9405270018146037, "percentage": 94.05, "elapsed_time": "5:33:01", "remaining_time": "0:21:04"}
|
||||
{"current_steps": 9210, "total_steps": 9782, "loss": 0.4265, "lr": 5.208871954166389e-07, "epoch": 0.9415493137730978, "percentage": 94.15, "elapsed_time": "5:33:23", "remaining_time": "0:20:42"}
|
||||
{"current_steps": 9220, "total_steps": 9782, "loss": 0.4272, "lr": 5.029254645133097e-07, "epoch": 0.942571625731592, "percentage": 94.25, "elapsed_time": "5:33:48", "remaining_time": "0:20:20"}
|
||||
{"current_steps": 9230, "total_steps": 9782, "loss": 0.4172, "lr": 4.852757318213775e-07, "epoch": 0.9435939376900861, "percentage": 94.36, "elapsed_time": "5:34:10", "remaining_time": "0:19:59"}
|
||||
{"current_steps": 9240, "total_steps": 9782, "loss": 0.4246, "lr": 4.6793822213033466e-07, "epoch": 0.9446162496485803, "percentage": 94.46, "elapsed_time": "5:34:33", "remaining_time": "0:19:37"}
|
||||
{"current_steps": 9250, "total_steps": 9782, "loss": 0.4227, "lr": 4.50913156253166e-07, "epoch": 0.9456385616070744, "percentage": 94.56, "elapsed_time": "5:34:54", "remaining_time": "0:19:15"}
|
||||
{"current_steps": 9260, "total_steps": 9782, "loss": 0.4259, "lr": 4.3420075102351965e-07, "epoch": 0.9466608735655685, "percentage": 94.66, "elapsed_time": "5:35:18", "remaining_time": "0:18:54"}
|
||||
{"current_steps": 9270, "total_steps": 9782, "loss": 0.4292, "lr": 4.1780121929295426e-07, "epoch": 0.9476831855240627, "percentage": 94.77, "elapsed_time": "5:35:40", "remaining_time": "0:18:32"}
|
||||
{"current_steps": 9280, "total_steps": 9782, "loss": 0.4256, "lr": 4.0171476992823255e-07, "epoch": 0.9487054974825568, "percentage": 94.87, "elapsed_time": "5:36:02", "remaining_time": "0:18:10"}
|
||||
{"current_steps": 9290, "total_steps": 9782, "loss": 0.4196, "lr": 3.859416078086486e-07, "epoch": 0.949727809441051, "percentage": 94.97, "elapsed_time": "5:36:23", "remaining_time": "0:17:48"}
|
||||
{"current_steps": 9300, "total_steps": 9782, "loss": 0.4198, "lr": 3.7048193382343e-07, "epoch": 0.9507501213995451, "percentage": 95.07, "elapsed_time": "5:36:44", "remaining_time": "0:17:27"}
|
||||
{"current_steps": 9310, "total_steps": 9782, "loss": 0.4252, "lr": 3.553359448691784e-07, "epoch": 0.9517724333580392, "percentage": 95.17, "elapsed_time": "5:37:04", "remaining_time": "0:17:05"}
|
||||
{"current_steps": 9320, "total_steps": 9782, "loss": 0.4258, "lr": 3.4050383384735264e-07, "epoch": 0.9527947453165333, "percentage": 95.28, "elapsed_time": "5:37:26", "remaining_time": "0:16:43"}
|
||||
{"current_steps": 9330, "total_steps": 9782, "loss": 0.4206, "lr": 3.259857896618174e-07, "epoch": 0.9538170572750275, "percentage": 95.38, "elapsed_time": "5:37:49", "remaining_time": "0:16:21"}
|
||||
{"current_steps": 9340, "total_steps": 9782, "loss": 0.4173, "lr": 3.1178199721644264e-07, "epoch": 0.9548393692335216, "percentage": 95.48, "elapsed_time": "5:38:12", "remaining_time": "0:16:00"}
|
||||
{"current_steps": 9350, "total_steps": 9782, "loss": 0.4191, "lr": 2.978926374127389e-07, "epoch": 0.9558616811920158, "percentage": 95.58, "elapsed_time": "5:38:35", "remaining_time": "0:15:38"}
|
||||
{"current_steps": 9360, "total_steps": 9782, "loss": 0.4348, "lr": 2.8431788714756437e-07, "epoch": 0.9568839931505099, "percentage": 95.69, "elapsed_time": "5:38:57", "remaining_time": "0:15:16"}
|
||||
{"current_steps": 9370, "total_steps": 9782, "loss": 0.4265, "lr": 2.7105791931085475e-07, "epoch": 0.957906305109004, "percentage": 95.79, "elapsed_time": "5:39:20", "remaining_time": "0:14:55"}
|
||||
{"current_steps": 9380, "total_steps": 9782, "loss": 0.4238, "lr": 2.5811290278344446e-07, "epoch": 0.9589286170674981, "percentage": 95.89, "elapsed_time": "5:39:43", "remaining_time": "0:14:33"}
|
||||
{"current_steps": 9390, "total_steps": 9782, "loss": 0.4212, "lr": 2.4548300243489306e-07, "epoch": 0.9599509290259923, "percentage": 95.99, "elapsed_time": "5:40:05", "remaining_time": "0:14:11"}
|
||||
{"current_steps": 9400, "total_steps": 9782, "loss": 0.4183, "lr": 2.33168379121404e-07, "epoch": 0.9609732409844864, "percentage": 96.09, "elapsed_time": "5:40:25", "remaining_time": "0:13:50"}
|
||||
{"current_steps": 9410, "total_steps": 9782, "loss": 0.4272, "lr": 2.2116918968376476e-07, "epoch": 0.9619955529429806, "percentage": 96.2, "elapsed_time": "5:40:48", "remaining_time": "0:13:28"}
|
||||
{"current_steps": 9420, "total_steps": 9782, "loss": 0.4263, "lr": 2.094855869453488e-07, "epoch": 0.9630178649014747, "percentage": 96.3, "elapsed_time": "5:41:11", "remaining_time": "0:13:06"}
|
||||
{"current_steps": 9430, "total_steps": 9782, "loss": 0.4275, "lr": 1.9811771971017523e-07, "epoch": 0.9640401768599688, "percentage": 96.4, "elapsed_time": "5:41:34", "remaining_time": "0:12:45"}
|
||||
{"current_steps": 9440, "total_steps": 9782, "loss": 0.4189, "lr": 1.870657327610159e-07, "epoch": 0.9650624888184629, "percentage": 96.5, "elapsed_time": "5:41:56", "remaining_time": "0:12:23"}
|
||||
{"current_steps": 9450, "total_steps": 9782, "loss": 0.4267, "lr": 1.7632976685753866e-07, "epoch": 0.9660848007769571, "percentage": 96.61, "elapsed_time": "5:42:18", "remaining_time": "0:12:01"}
|
||||
{"current_steps": 9460, "total_steps": 9782, "loss": 0.4319, "lr": 1.659099587345281e-07, "epoch": 0.9671071127354512, "percentage": 96.71, "elapsed_time": "5:42:42", "remaining_time": "0:11:39"}
|
||||
{"current_steps": 9470, "total_steps": 9782, "loss": 0.4276, "lr": 1.558064411001342e-07, "epoch": 0.9681294246939454, "percentage": 96.81, "elapsed_time": "5:43:04", "remaining_time": "0:11:18"}
|
||||
{"current_steps": 9480, "total_steps": 9782, "loss": 0.4208, "lr": 1.460193426341877e-07, "epoch": 0.9691517366524395, "percentage": 96.91, "elapsed_time": "5:43:26", "remaining_time": "0:10:56"}
|
||||
{"current_steps": 9490, "total_steps": 9782, "loss": 0.4242, "lr": 1.3654878798656512e-07, "epoch": 0.9701740486109336, "percentage": 97.01, "elapsed_time": "5:43:47", "remaining_time": "0:10:34"}
|
||||
{"current_steps": 9500, "total_steps": 9782, "loss": 0.423, "lr": 1.273948977755901e-07, "epoch": 0.9711963605694277, "percentage": 97.12, "elapsed_time": "5:44:10", "remaining_time": "0:10:12"}
|
||||
{"current_steps": 9510, "total_steps": 9782, "loss": 0.4239, "lr": 1.1855778858650412e-07, "epoch": 0.9722186725279219, "percentage": 97.22, "elapsed_time": "5:44:31", "remaining_time": "0:09:51"}
|
||||
{"current_steps": 9520, "total_steps": 9782, "loss": 0.4186, "lr": 1.100375729699843e-07, "epoch": 0.973240984486416, "percentage": 97.32, "elapsed_time": "5:44:54", "remaining_time": "0:09:29"}
|
||||
{"current_steps": 9530, "total_steps": 9782, "loss": 0.4298, "lr": 1.0183435944070007e-07, "epoch": 0.9742632964449102, "percentage": 97.42, "elapsed_time": "5:45:16", "remaining_time": "0:09:07"}
|
||||
{"current_steps": 9540, "total_steps": 9782, "loss": 0.4281, "lr": 9.394825247594219e-08, "epoch": 0.9752856084034043, "percentage": 97.53, "elapsed_time": "5:45:37", "remaining_time": "0:08:46"}
|
||||
{"current_steps": 9550, "total_steps": 9782, "loss": 0.4274, "lr": 8.637935251428753e-08, "epoch": 0.9763079203618984, "percentage": 97.63, "elapsed_time": "5:45:59", "remaining_time": "0:08:24"}
|
||||
{"current_steps": 9560, "total_steps": 9782, "loss": 0.4235, "lr": 7.912775595431687e-08, "epoch": 0.9773302323203926, "percentage": 97.73, "elapsed_time": "5:46:21", "remaining_time": "0:08:02"}
|
||||
{"current_steps": 9570, "total_steps": 9782, "loss": 0.4255, "lr": 7.219355515339088e-08, "epoch": 0.9783525442788867, "percentage": 97.83, "elapsed_time": "5:46:41", "remaining_time": "0:07:40"}
|
||||
{"current_steps": 9580, "total_steps": 9782, "loss": 0.4216, "lr": 6.5576838426476e-08, "epoch": 0.9793748562373809, "percentage": 97.93, "elapsed_time": "5:47:04", "remaining_time": "0:07:19"}
|
||||
{"current_steps": 9590, "total_steps": 9782, "loss": 0.4244, "lr": 5.927769004501205e-08, "epoch": 0.980397168195875, "percentage": 98.04, "elapsed_time": "5:47:28", "remaining_time": "0:06:57"}
|
||||
{"current_steps": 9600, "total_steps": 9782, "loss": 0.4294, "lr": 5.329619023584087e-08, "epoch": 0.9814194801543691, "percentage": 98.14, "elapsed_time": "5:47:50", "remaining_time": "0:06:35"}
|
||||
{"current_steps": 9610, "total_steps": 9782, "loss": 0.4231, "lr": 4.7632415180198784e-08, "epoch": 0.9824417921128632, "percentage": 98.24, "elapsed_time": "5:48:11", "remaining_time": "0:06:13"}
|
||||
{"current_steps": 9620, "total_steps": 9782, "loss": 0.421, "lr": 4.228643701272017e-08, "epoch": 0.9834641040713574, "percentage": 98.34, "elapsed_time": "5:48:32", "remaining_time": "0:05:52"}
|
||||
{"current_steps": 9630, "total_steps": 9782, "loss": 0.4253, "lr": 3.72583238205465e-08, "epoch": 0.9844864160298515, "percentage": 98.45, "elapsed_time": "5:48:55", "remaining_time": "0:05:30"}
|
||||
{"current_steps": 9640, "total_steps": 9782, "loss": 0.4233, "lr": 3.254813964243542e-08, "epoch": 0.9855087279883457, "percentage": 98.55, "elapsed_time": "5:49:16", "remaining_time": "0:05:08"}
|
||||
{"current_steps": 9650, "total_steps": 9782, "loss": 0.4286, "lr": 2.8155944467961327e-08, "epoch": 0.9865310399468398, "percentage": 98.65, "elapsed_time": "5:49:39", "remaining_time": "0:04:46"}
|
||||
{"current_steps": 9660, "total_steps": 9782, "loss": 0.4212, "lr": 2.4081794236743837e-08, "epoch": 0.9875533519053339, "percentage": 98.75, "elapsed_time": "5:50:02", "remaining_time": "0:04:25"}
|
||||
{"current_steps": 9670, "total_steps": 9782, "loss": 0.4253, "lr": 2.032574083773997e-08, "epoch": 0.988575663863828, "percentage": 98.86, "elapsed_time": "5:50:25", "remaining_time": "0:04:03"}
|
||||
{"current_steps": 9680, "total_steps": 9782, "loss": 0.4254, "lr": 1.6887832108572476e-08, "epoch": 0.9895979758223222, "percentage": 98.96, "elapsed_time": "5:50:48", "remaining_time": "0:03:41"}
|
||||
{"current_steps": 9690, "total_steps": 9782, "loss": 0.4226, "lr": 1.3768111834938645e-08, "epoch": 0.9906202877808163, "percentage": 99.06, "elapsed_time": "5:51:08", "remaining_time": "0:03:20"}
|
||||
{"current_steps": 9700, "total_steps": 9782, "loss": 0.4315, "lr": 1.0966619750035768e-08, "epoch": 0.9916425997393105, "percentage": 99.16, "elapsed_time": "5:51:31", "remaining_time": "0:02:58"}
|
||||
{"current_steps": 9710, "total_steps": 9782, "loss": 0.4177, "lr": 8.4833915340643e-09, "epoch": 0.9926649116978046, "percentage": 99.26, "elapsed_time": "5:51:52", "remaining_time": "0:02:36"}
|
||||
{"current_steps": 9720, "total_steps": 9782, "loss": 0.4257, "lr": 6.318458813769912e-09, "epoch": 0.9936872236562987, "percentage": 99.37, "elapsed_time": "5:52:15", "remaining_time": "0:02:14"}
|
||||
{"current_steps": 9730, "total_steps": 9782, "loss": 0.4293, "lr": 4.471849162043795e-09, "epoch": 0.9947095356147928, "percentage": 99.47, "elapsed_time": "5:52:39", "remaining_time": "0:01:53"}
|
||||
{"current_steps": 9740, "total_steps": 9782, "loss": 0.4272, "lr": 2.943586097567397e-09, "epoch": 0.995731847573287, "percentage": 99.57, "elapsed_time": "5:53:03", "remaining_time": "0:01:31"}
|
||||
{"current_steps": 9750, "total_steps": 9782, "loss": 0.4224, "lr": 1.733689084515433e-09, "epoch": 0.9967541595317811, "percentage": 99.67, "elapsed_time": "5:53:26", "remaining_time": "0:01:09"}
|
||||
{"current_steps": 9760, "total_steps": 9782, "loss": 0.4265, "lr": 8.421735323060897e-10, "epoch": 0.9977764714902753, "percentage": 99.78, "elapsed_time": "5:53:50", "remaining_time": "0:00:47"}
|
||||
{"current_steps": 9770, "total_steps": 9782, "loss": 0.4271, "lr": 2.6905079540950894e-10, "epoch": 0.9987987834487694, "percentage": 99.88, "elapsed_time": "5:54:12", "remaining_time": "0:00:26"}
|
||||
{"current_steps": 9780, "total_steps": 9782, "loss": 0.4183, "lr": 1.4328173200683915e-11, "epoch": 0.9998210954072635, "percentage": 99.98, "elapsed_time": "5:54:34", "remaining_time": "0:00:04"}
|
||||
{"current_steps": 9782, "total_steps": 9782, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "5:55:14", "remaining_time": "0:00:00"}
|
||||
6889
trainer_state.json
Normal file
6889
trainer_state.json
Normal file
File diff suppressed because it is too large
Load Diff
3
training_args.bin
Normal file
3
training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:fb9f019ed50297ff3b4ccffea5cd1759dcb09a1a1c2395e73d5c082049effddf
|
||||
size 7889
|
||||
BIN
training_loss.png
Normal file
BIN
training_loss.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 28 KiB |
1
vocab.json
Normal file
1
vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user