初始化项目,由ModelHub XC社区提供模型
Model: laion/dev_set_part1_10k_glm_4_7_traces_jupiter_cleaned 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: apache-2.0
|
||||
base_model: Qwen/Qwen3-8B
|
||||
tags:
|
||||
- llama-factory
|
||||
- full
|
||||
- generated_from_trainer
|
||||
model-index:
|
||||
- name: dev_set_part1_10k_glm_4_7_traces_jupiter_cleaned
|
||||
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. -->
|
||||
|
||||
# dev_set_part1_10k_glm_4_7_traces_jupiter_cleaned
|
||||
|
||||
This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on the /data/cat/ws/befe330h-befe330h-otagent/huggingface/hub/datasets--DCAgent--dev_set_part1_10k_glm_4.7_traces_jupiter_cleaned/snapshots/094996d33f3310ba7da0ee9cbf487f5e5673de79_thinking_preprocessed dataset.
|
||||
|
||||
## Model description
|
||||
|
||||
More information needed
|
||||
|
||||
## Intended uses & limitations
|
||||
|
||||
More information needed
|
||||
|
||||
## Training and evaluation data
|
||||
|
||||
More information needed
|
||||
|
||||
## Training procedure
|
||||
|
||||
### Training hyperparameters
|
||||
|
||||
The following hyperparameters were used during training:
|
||||
- learning_rate: 4e-05
|
||||
- train_batch_size: 1
|
||||
- eval_batch_size: 8
|
||||
- seed: 42
|
||||
- distributed_type: multi-GPU
|
||||
- num_devices: 8
|
||||
- gradient_accumulation_steps: 2
|
||||
- total_train_batch_size: 16
|
||||
- total_eval_batch_size: 64
|
||||
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.98) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
||||
- lr_scheduler_type: cosine
|
||||
- lr_scheduler_warmup_ratio: 0.1
|
||||
- num_epochs: 7.0
|
||||
|
||||
### Training results
|
||||
|
||||
|
||||
|
||||
### Framework versions
|
||||
|
||||
- Transformers 4.57.6
|
||||
- Pytorch 2.9.0+cu128
|
||||
- Datasets 4.4.1
|
||||
- Tokenizers 0.22.2
|
||||
28
added_tokens.json
Normal file
28
added_tokens.json
Normal file
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"</think>": 151668,
|
||||
"</tool_call>": 151658,
|
||||
"</tool_response>": 151666,
|
||||
"<think>": 151667,
|
||||
"<tool_call>": 151657,
|
||||
"<tool_response>": 151665,
|
||||
"<|box_end|>": 151649,
|
||||
"<|box_start|>": 151648,
|
||||
"<|endoftext|>": 151643,
|
||||
"<|file_sep|>": 151664,
|
||||
"<|fim_middle|>": 151660,
|
||||
"<|fim_pad|>": 151662,
|
||||
"<|fim_prefix|>": 151659,
|
||||
"<|fim_suffix|>": 151661,
|
||||
"<|im_end|>": 151645,
|
||||
"<|im_start|>": 151644,
|
||||
"<|image_pad|>": 151655,
|
||||
"<|object_ref_end|>": 151647,
|
||||
"<|object_ref_start|>": 151646,
|
||||
"<|quad_end|>": 151651,
|
||||
"<|quad_start|>": 151650,
|
||||
"<|repo_name|>": 151663,
|
||||
"<|video_pad|>": 151656,
|
||||
"<|vision_end|>": 151653,
|
||||
"<|vision_pad|>": 151654,
|
||||
"<|vision_start|>": 151652
|
||||
}
|
||||
16
all_results.json
Normal file
16
all_results.json
Normal file
@@ -0,0 +1,16 @@
|
||||
{
|
||||
"achieved_tflops_per_gpu": 3.8806677213684275,
|
||||
"achieved_tflops_per_gpu_theoretical": 233.76541483479863,
|
||||
"epoch": 7.0,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.3018219769001007,
|
||||
"mfu_percent": 0.39238298497152957,
|
||||
"mfu_percent_theoretical": 23.636543461556993,
|
||||
"total_flos": 1.8215701044296417e+18,
|
||||
"train_loss": 0.2893604008122581,
|
||||
"train_runtime": 58674.5064,
|
||||
"train_samples_per_second": 1.1,
|
||||
"train_steps_per_second": 0.069,
|
||||
"valid_targets_mean": 9465.8,
|
||||
"valid_targets_min": 3229
|
||||
}
|
||||
89
chat_template.jinja
Normal file
89
chat_template.jinja
Normal file
@@ -0,0 +1,89 @@
|
||||
{%- if tools %}
|
||||
{{- '<|im_start|>system\n' }}
|
||||
{%- if messages[0].role == 'system' %}
|
||||
{{- messages[0].content + '\n\n' }}
|
||||
{%- endif %}
|
||||
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
||||
{%- for tool in tools %}
|
||||
{{- "\n" }}
|
||||
{{- tool | tojson }}
|
||||
{%- endfor %}
|
||||
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
||||
{%- else %}
|
||||
{%- if messages[0].role == 'system' %}
|
||||
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
||||
{%- for message in messages[::-1] %}
|
||||
{%- set index = (messages|length - 1) - loop.index0 %}
|
||||
{%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
||||
{%- set ns.multi_step_tool = false %}
|
||||
{%- set ns.last_query_index = index %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- for message in messages %}
|
||||
{%- if message.content is string %}
|
||||
{%- set content = message.content %}
|
||||
{%- else %}
|
||||
{%- set content = '' %}
|
||||
{%- endif %}
|
||||
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
||||
{%- elif message.role == "assistant" %}
|
||||
{%- set reasoning_content = '' %}
|
||||
{%- if message.reasoning_content is string %}
|
||||
{%- set reasoning_content = message.reasoning_content %}
|
||||
{%- else %}
|
||||
{%- if '</think>' in content %}
|
||||
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
||||
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- if loop.index0 > ns.last_query_index %}
|
||||
{%- if loop.last or (not loop.last and reasoning_content) %}
|
||||
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||
{%- endif %}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||
{%- endif %}
|
||||
{%- if message.tool_calls %}
|
||||
{%- for tool_call in message.tool_calls %}
|
||||
{%- if (loop.first and content) or (not loop.first) %}
|
||||
{{- '\n' }}
|
||||
{%- endif %}
|
||||
{%- if tool_call.function %}
|
||||
{%- set tool_call = tool_call.function %}
|
||||
{%- endif %}
|
||||
{{- '<tool_call>\n{"name": "' }}
|
||||
{{- tool_call.name }}
|
||||
{{- '", "arguments": ' }}
|
||||
{%- if tool_call.arguments is string %}
|
||||
{{- tool_call.arguments }}
|
||||
{%- else %}
|
||||
{{- tool_call.arguments | tojson }}
|
||||
{%- endif %}
|
||||
{{- '}\n</tool_call>' }}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- elif message.role == "tool" %}
|
||||
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
||||
{{- '<|im_start|>user' }}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_response>\n' }}
|
||||
{{- content }}
|
||||
{{- '\n</tool_response>' }}
|
||||
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- if add_generation_prompt %}
|
||||
{{- '<|im_start|>assistant\n' }}
|
||||
{%- if enable_thinking is defined and enable_thinking is false %}
|
||||
{{- '<think>\n\n</think>\n\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
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": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 12288,
|
||||
"layer_types": [
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention"
|
||||
],
|
||||
"max_position_embeddings": 40960,
|
||||
"max_window_layers": 36,
|
||||
"model_type": "qwen3",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 36,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 151643,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 1000000,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "4.57.6",
|
||||
"use_cache": false,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
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": 0.6,
|
||||
"top_k": 20,
|
||||
"top_p": 0.95,
|
||||
"transformers_version": "4.57.6"
|
||||
}
|
||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model-00001-of-00004.safetensors
Normal file
3
model-00001-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:201e8137f626cdd3b97fc3ebc29992415eeb5111e78c6717e7f515272038f5bc
|
||||
size 4902257696
|
||||
3
model-00002-of-00004.safetensors
Normal file
3
model-00002-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8c42f15401207fa818cb6829acb23927a861570a15eeb89d7c47ebe998a645b6
|
||||
size 4915960368
|
||||
3
model-00003-of-00004.safetensors
Normal file
3
model-00003-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2be48392d59b30ff24e79ec80e0a3d40c38a21ff0172730bcba0ccd20e9f6d28
|
||||
size 4983068496
|
||||
3
model-00004-of-00004.safetensors
Normal file
3
model-00004-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:78f5c0b01c714bf66ac03e55708b6faf7712ce5f8075bba6fb2888c9a096c521
|
||||
size 1580230264
|
||||
407
model.safetensors.index.json
Normal file
407
model.safetensors.index.json
Normal file
@@ -0,0 +1,407 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_parameters": 308224,
|
||||
"total_size": 16381470720
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00004-of-00004.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.norm.weight": "model-00004-of-00004.safetensors"
|
||||
}
|
||||
}
|
||||
12
run_summary.json
Normal file
12
run_summary.json
Normal file
@@ -0,0 +1,12 @@
|
||||
{
|
||||
"agent_name": "094996d33f3310ba7da0ee9cbf487f5e5673de79_thinking_preprocessed",
|
||||
"training_start": null,
|
||||
"training_end": null,
|
||||
"created_by": "DCAgent",
|
||||
"base_model_name": "Qwen/Qwen3-8B",
|
||||
"dataset_name": "/data/cat/ws/befe330h-befe330h-otagent/huggingface/hub/datasets--DCAgent--dev_set_part1_10k_glm_4.7_traces_jupiter_cleaned/snapshots/094996d33f3310ba7da0ee9cbf487f5e5673de79_thinking_preprocessed",
|
||||
"training_type": "SFT",
|
||||
"training_parameters": "https://huggingface.co/laion/dev_set_part1_10k_glm_4_7_traces_jupiter_cleaned/blob/main/config.json",
|
||||
"wandb_link": "https://wandb.ai/dogml/OpenThoughts-Agent/runs/sft_dev_set_part1_10k_glm_4-7_traces_jupiter_cleaned_Qwen3-8B",
|
||||
"traces_location_s3": null
|
||||
}
|
||||
31
special_tokens_map.json
Normal file
31
special_tokens_map.json
Normal file
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"eos_token": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
BIN
tokenizer.json
(Stored with Git LFS)
Normal file
BIN
tokenizer.json
(Stored with Git LFS)
Normal file
Binary file not shown.
240
tokenizer_config.json
Normal file
240
tokenizer_config.json
Normal file
@@ -0,0 +1,240 @@
|
||||
{
|
||||
"add_bos_token": false,
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"151643": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151644": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151645": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151646": {
|
||||
"content": "<|object_ref_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151647": {
|
||||
"content": "<|object_ref_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151648": {
|
||||
"content": "<|box_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151649": {
|
||||
"content": "<|box_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151650": {
|
||||
"content": "<|quad_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151651": {
|
||||
"content": "<|quad_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151652": {
|
||||
"content": "<|vision_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151653": {
|
||||
"content": "<|vision_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151654": {
|
||||
"content": "<|vision_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151655": {
|
||||
"content": "<|image_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151656": {
|
||||
"content": "<|video_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151657": {
|
||||
"content": "<tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151658": {
|
||||
"content": "</tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151659": {
|
||||
"content": "<|fim_prefix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151660": {
|
||||
"content": "<|fim_middle|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151661": {
|
||||
"content": "<|fim_suffix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151662": {
|
||||
"content": "<|fim_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151663": {
|
||||
"content": "<|repo_name|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151664": {
|
||||
"content": "<|file_sep|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151665": {
|
||||
"content": "<tool_response>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151666": {
|
||||
"content": "</tool_response>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151667": {
|
||||
"content": "<think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151668": {
|
||||
"content": "</think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"bos_token": null,
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": {},
|
||||
"model_max_length": 32768,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"padding_side": "right",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
16
train_results.json
Normal file
16
train_results.json
Normal file
@@ -0,0 +1,16 @@
|
||||
{
|
||||
"achieved_tflops_per_gpu": 3.8806677213684275,
|
||||
"achieved_tflops_per_gpu_theoretical": 233.76541483479863,
|
||||
"epoch": 7.0,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.3018219769001007,
|
||||
"mfu_percent": 0.39238298497152957,
|
||||
"mfu_percent_theoretical": 23.636543461556993,
|
||||
"total_flos": 1.8215701044296417e+18,
|
||||
"train_loss": 0.2893604008122581,
|
||||
"train_runtime": 58674.5064,
|
||||
"train_samples_per_second": 1.1,
|
||||
"train_steps_per_second": 0.069,
|
||||
"valid_targets_mean": 9465.8,
|
||||
"valid_targets_min": 3229
|
||||
}
|
||||
808
trainer_log.jsonl
Normal file
808
trainer_log.jsonl
Normal file
@@ -0,0 +1,808 @@
|
||||
{"current_steps": 5, "total_steps": 4039, "loss": 0.7839, "lr": 3.9603960396039606e-07, "epoch": 0.008673026886383347, "percentage": 0.12, "elapsed_time": "0:01:32", "remaining_time": "20:37:29"}
|
||||
{"current_steps": 10, "total_steps": 4039, "loss": 0.7411, "lr": 8.910891089108911e-07, "epoch": 0.017346053772766695, "percentage": 0.25, "elapsed_time": "0:02:49", "remaining_time": "19:00:45"}
|
||||
{"current_steps": 15, "total_steps": 4039, "loss": 0.7125, "lr": 1.3861386138613863e-06, "epoch": 0.026019080659150044, "percentage": 0.37, "elapsed_time": "0:04:01", "remaining_time": "18:00:24"}
|
||||
{"current_steps": 20, "total_steps": 4039, "loss": 0.6823, "lr": 1.8811881188118813e-06, "epoch": 0.03469210754553339, "percentage": 0.5, "elapsed_time": "0:05:16", "remaining_time": "17:40:08"}
|
||||
{"current_steps": 25, "total_steps": 4039, "loss": 0.6499, "lr": 2.3762376237623762e-06, "epoch": 0.04336513443191674, "percentage": 0.62, "elapsed_time": "0:06:38", "remaining_time": "17:45:30"}
|
||||
{"current_steps": 30, "total_steps": 4039, "loss": 0.6244, "lr": 2.8712871287128712e-06, "epoch": 0.05203816131830009, "percentage": 0.74, "elapsed_time": "0:07:57", "remaining_time": "17:43:26"}
|
||||
{"current_steps": 35, "total_steps": 4039, "loss": 0.6426, "lr": 3.3663366336633666e-06, "epoch": 0.060711188204683436, "percentage": 0.87, "elapsed_time": "0:09:11", "remaining_time": "17:32:27"}
|
||||
{"current_steps": 40, "total_steps": 4039, "loss": 0.5529, "lr": 3.861386138613862e-06, "epoch": 0.06938421509106678, "percentage": 0.99, "elapsed_time": "0:10:31", "remaining_time": "17:32:33"}
|
||||
{"current_steps": 45, "total_steps": 4039, "loss": 0.5473, "lr": 4.356435643564357e-06, "epoch": 0.07805724197745013, "percentage": 1.11, "elapsed_time": "0:11:45", "remaining_time": "17:23:02"}
|
||||
{"current_steps": 50, "total_steps": 4039, "loss": 0.548, "lr": 4.851485148514852e-06, "epoch": 0.08673026886383348, "percentage": 1.24, "elapsed_time": "0:13:06", "remaining_time": "17:26:04"}
|
||||
{"current_steps": 55, "total_steps": 4039, "loss": 0.5344, "lr": 5.346534653465347e-06, "epoch": 0.09540329575021683, "percentage": 1.36, "elapsed_time": "0:14:25", "remaining_time": "17:24:30"}
|
||||
{"current_steps": 60, "total_steps": 4039, "loss": 0.5223, "lr": 5.841584158415842e-06, "epoch": 0.10407632263660017, "percentage": 1.49, "elapsed_time": "0:15:42", "remaining_time": "17:21:37"}
|
||||
{"current_steps": 65, "total_steps": 4039, "loss": 0.505, "lr": 6.336633663366337e-06, "epoch": 0.11274934952298352, "percentage": 1.61, "elapsed_time": "0:16:42", "remaining_time": "17:01:57"}
|
||||
{"current_steps": 70, "total_steps": 4039, "loss": 0.5229, "lr": 6.831683168316833e-06, "epoch": 0.12142237640936687, "percentage": 1.73, "elapsed_time": "0:18:00", "remaining_time": "17:01:25"}
|
||||
{"current_steps": 75, "total_steps": 4039, "loss": 0.5147, "lr": 7.326732673267327e-06, "epoch": 0.13009540329575023, "percentage": 1.86, "elapsed_time": "0:19:14", "remaining_time": "16:57:23"}
|
||||
{"current_steps": 80, "total_steps": 4039, "loss": 0.5225, "lr": 7.821782178217822e-06, "epoch": 0.13876843018213356, "percentage": 1.98, "elapsed_time": "0:20:28", "remaining_time": "16:53:27"}
|
||||
{"current_steps": 85, "total_steps": 4039, "loss": 0.4848, "lr": 8.316831683168318e-06, "epoch": 0.1474414570685169, "percentage": 2.1, "elapsed_time": "0:21:36", "remaining_time": "16:45:21"}
|
||||
{"current_steps": 90, "total_steps": 4039, "loss": 0.5089, "lr": 8.811881188118812e-06, "epoch": 0.15611448395490027, "percentage": 2.23, "elapsed_time": "0:22:49", "remaining_time": "16:41:14"}
|
||||
{"current_steps": 95, "total_steps": 4039, "loss": 0.4503, "lr": 9.306930693069308e-06, "epoch": 0.1647875108412836, "percentage": 2.35, "elapsed_time": "0:24:06", "remaining_time": "16:40:38"}
|
||||
{"current_steps": 100, "total_steps": 4039, "loss": 0.4932, "lr": 9.801980198019802e-06, "epoch": 0.17346053772766695, "percentage": 2.48, "elapsed_time": "0:25:23", "remaining_time": "16:39:54"}
|
||||
{"current_steps": 105, "total_steps": 4039, "loss": 0.5149, "lr": 1.0297029702970298e-05, "epoch": 0.1821335646140503, "percentage": 2.6, "elapsed_time": "0:26:28", "remaining_time": "16:31:50"}
|
||||
{"current_steps": 110, "total_steps": 4039, "loss": 0.4453, "lr": 1.0792079207920793e-05, "epoch": 0.19080659150043366, "percentage": 2.72, "elapsed_time": "0:27:41", "remaining_time": "16:29:14"}
|
||||
{"current_steps": 115, "total_steps": 4039, "loss": 0.4548, "lr": 1.1287128712871288e-05, "epoch": 0.199479618386817, "percentage": 2.85, "elapsed_time": "0:28:53", "remaining_time": "16:25:40"}
|
||||
{"current_steps": 120, "total_steps": 4039, "loss": 0.4659, "lr": 1.1782178217821782e-05, "epoch": 0.20815264527320035, "percentage": 2.97, "elapsed_time": "0:30:10", "remaining_time": "16:25:40"}
|
||||
{"current_steps": 125, "total_steps": 4039, "loss": 0.5055, "lr": 1.2277227722772278e-05, "epoch": 0.2168256721595837, "percentage": 3.09, "elapsed_time": "0:31:22", "remaining_time": "16:22:22"}
|
||||
{"current_steps": 130, "total_steps": 4039, "loss": 0.4595, "lr": 1.2772277227722773e-05, "epoch": 0.22549869904596703, "percentage": 3.22, "elapsed_time": "0:32:42", "remaining_time": "16:23:28"}
|
||||
{"current_steps": 135, "total_steps": 4039, "loss": 0.4584, "lr": 1.326732673267327e-05, "epoch": 0.2341717259323504, "percentage": 3.34, "elapsed_time": "0:34:00", "remaining_time": "16:23:39"}
|
||||
{"current_steps": 140, "total_steps": 4039, "loss": 0.4346, "lr": 1.3762376237623762e-05, "epoch": 0.24284475281873374, "percentage": 3.47, "elapsed_time": "0:35:18", "remaining_time": "16:23:33"}
|
||||
{"current_steps": 145, "total_steps": 4039, "loss": 0.4406, "lr": 1.4257425742574257e-05, "epoch": 0.2515177797051171, "percentage": 3.59, "elapsed_time": "0:36:31", "remaining_time": "16:21:05"}
|
||||
{"current_steps": 150, "total_steps": 4039, "loss": 0.4349, "lr": 1.4752475247524753e-05, "epoch": 0.26019080659150046, "percentage": 3.71, "elapsed_time": "0:37:46", "remaining_time": "16:19:29"}
|
||||
{"current_steps": 155, "total_steps": 4039, "loss": 0.4405, "lr": 1.5247524752475249e-05, "epoch": 0.2688638334778838, "percentage": 3.84, "elapsed_time": "0:39:01", "remaining_time": "16:17:59"}
|
||||
{"current_steps": 160, "total_steps": 4039, "loss": 0.4378, "lr": 1.5742574257425743e-05, "epoch": 0.2775368603642671, "percentage": 3.96, "elapsed_time": "0:40:17", "remaining_time": "16:16:58"}
|
||||
{"current_steps": 165, "total_steps": 4039, "loss": 0.4039, "lr": 1.623762376237624e-05, "epoch": 0.2862098872506505, "percentage": 4.09, "elapsed_time": "0:41:28", "remaining_time": "16:13:37"}
|
||||
{"current_steps": 170, "total_steps": 4039, "loss": 0.4132, "lr": 1.6732673267326735e-05, "epoch": 0.2948829141370338, "percentage": 4.21, "elapsed_time": "0:42:42", "remaining_time": "16:12:10"}
|
||||
{"current_steps": 175, "total_steps": 4039, "loss": 0.3724, "lr": 1.722772277227723e-05, "epoch": 0.30355594102341715, "percentage": 4.33, "elapsed_time": "0:43:58", "remaining_time": "16:10:52"}
|
||||
{"current_steps": 180, "total_steps": 4039, "loss": 0.3781, "lr": 1.7722772277227723e-05, "epoch": 0.31222896790980054, "percentage": 4.46, "elapsed_time": "0:45:09", "remaining_time": "16:08:06"}
|
||||
{"current_steps": 185, "total_steps": 4039, "loss": 0.4346, "lr": 1.821782178217822e-05, "epoch": 0.32090199479618386, "percentage": 4.58, "elapsed_time": "0:46:23", "remaining_time": "16:06:18"}
|
||||
{"current_steps": 190, "total_steps": 4039, "loss": 0.4228, "lr": 1.8712871287128715e-05, "epoch": 0.3295750216825672, "percentage": 4.7, "elapsed_time": "0:47:37", "remaining_time": "16:04:38"}
|
||||
{"current_steps": 195, "total_steps": 4039, "loss": 0.4204, "lr": 1.920792079207921e-05, "epoch": 0.3382480485689506, "percentage": 4.83, "elapsed_time": "0:48:57", "remaining_time": "16:05:13"}
|
||||
{"current_steps": 200, "total_steps": 4039, "loss": 0.4351, "lr": 1.9702970297029703e-05, "epoch": 0.3469210754553339, "percentage": 4.95, "elapsed_time": "0:50:14", "remaining_time": "16:04:18"}
|
||||
{"current_steps": 205, "total_steps": 4039, "loss": 0.4462, "lr": 2.01980198019802e-05, "epoch": 0.35559410234171723, "percentage": 5.08, "elapsed_time": "0:51:29", "remaining_time": "16:02:59"}
|
||||
{"current_steps": 210, "total_steps": 4039, "loss": 0.3694, "lr": 2.0693069306930695e-05, "epoch": 0.3642671292281006, "percentage": 5.2, "elapsed_time": "0:52:43", "remaining_time": "16:01:28"}
|
||||
{"current_steps": 215, "total_steps": 4039, "loss": 0.4004, "lr": 2.1188118811881192e-05, "epoch": 0.37294015611448394, "percentage": 5.32, "elapsed_time": "0:54:03", "remaining_time": "16:01:33"}
|
||||
{"current_steps": 220, "total_steps": 4039, "loss": 0.414, "lr": 2.1683168316831686e-05, "epoch": 0.38161318300086733, "percentage": 5.45, "elapsed_time": "0:55:20", "remaining_time": "16:00:44"}
|
||||
{"current_steps": 225, "total_steps": 4039, "loss": 0.3989, "lr": 2.217821782178218e-05, "epoch": 0.39028620988725066, "percentage": 5.57, "elapsed_time": "0:56:28", "remaining_time": "15:57:25"}
|
||||
{"current_steps": 230, "total_steps": 4039, "loss": 0.3997, "lr": 2.2673267326732675e-05, "epoch": 0.398959236773634, "percentage": 5.69, "elapsed_time": "0:57:45", "remaining_time": "15:56:25"}
|
||||
{"current_steps": 235, "total_steps": 4039, "loss": 0.3699, "lr": 2.316831683168317e-05, "epoch": 0.40763226366001737, "percentage": 5.82, "elapsed_time": "0:58:54", "remaining_time": "15:53:37"}
|
||||
{"current_steps": 240, "total_steps": 4039, "loss": 0.3955, "lr": 2.3663366336633663e-05, "epoch": 0.4163052905464007, "percentage": 5.94, "elapsed_time": "1:00:08", "remaining_time": "15:52:05"}
|
||||
{"current_steps": 245, "total_steps": 4039, "loss": 0.3491, "lr": 2.415841584158416e-05, "epoch": 0.424978317432784, "percentage": 6.07, "elapsed_time": "1:01:15", "remaining_time": "15:48:36"}
|
||||
{"current_steps": 250, "total_steps": 4039, "loss": 0.4382, "lr": 2.4653465346534655e-05, "epoch": 0.4336513443191674, "percentage": 6.19, "elapsed_time": "1:02:34", "remaining_time": "15:48:20"}
|
||||
{"current_steps": 255, "total_steps": 4039, "loss": 0.4176, "lr": 2.5148514851485152e-05, "epoch": 0.44232437120555074, "percentage": 6.31, "elapsed_time": "1:03:50", "remaining_time": "15:47:18"}
|
||||
{"current_steps": 260, "total_steps": 4039, "loss": 0.3956, "lr": 2.5643564356435646e-05, "epoch": 0.45099739809193407, "percentage": 6.44, "elapsed_time": "1:04:59", "remaining_time": "15:44:34"}
|
||||
{"current_steps": 265, "total_steps": 4039, "loss": 0.3398, "lr": 2.613861386138614e-05, "epoch": 0.45967042497831745, "percentage": 6.56, "elapsed_time": "1:06:19", "remaining_time": "15:44:37"}
|
||||
{"current_steps": 270, "total_steps": 4039, "loss": 0.3799, "lr": 2.6633663366336638e-05, "epoch": 0.4683434518647008, "percentage": 6.68, "elapsed_time": "1:07:30", "remaining_time": "15:42:18"}
|
||||
{"current_steps": 275, "total_steps": 4039, "loss": 0.418, "lr": 2.7128712871287132e-05, "epoch": 0.4770164787510841, "percentage": 6.81, "elapsed_time": "1:08:50", "remaining_time": "15:42:15"}
|
||||
{"current_steps": 280, "total_steps": 4039, "loss": 0.3752, "lr": 2.7623762376237623e-05, "epoch": 0.4856895056374675, "percentage": 6.93, "elapsed_time": "1:10:03", "remaining_time": "15:40:37"}
|
||||
{"current_steps": 285, "total_steps": 4039, "loss": 0.4278, "lr": 2.811881188118812e-05, "epoch": 0.4943625325238508, "percentage": 7.06, "elapsed_time": "1:11:06", "remaining_time": "15:36:36"}
|
||||
{"current_steps": 290, "total_steps": 4039, "loss": 0.3708, "lr": 2.8613861386138614e-05, "epoch": 0.5030355594102341, "percentage": 7.18, "elapsed_time": "1:12:22", "remaining_time": "15:35:40"}
|
||||
{"current_steps": 295, "total_steps": 4039, "loss": 0.3743, "lr": 2.9108910891089112e-05, "epoch": 0.5117085862966175, "percentage": 7.3, "elapsed_time": "1:13:37", "remaining_time": "15:34:23"}
|
||||
{"current_steps": 300, "total_steps": 4039, "loss": 0.3921, "lr": 2.9603960396039606e-05, "epoch": 0.5203816131830009, "percentage": 7.43, "elapsed_time": "1:14:48", "remaining_time": "15:32:23"}
|
||||
{"current_steps": 305, "total_steps": 4039, "loss": 0.3685, "lr": 3.00990099009901e-05, "epoch": 0.5290546400693842, "percentage": 7.55, "elapsed_time": "1:16:05", "remaining_time": "15:31:31"}
|
||||
{"current_steps": 310, "total_steps": 4039, "loss": 0.3529, "lr": 3.0594059405940594e-05, "epoch": 0.5377276669557676, "percentage": 7.68, "elapsed_time": "1:17:21", "remaining_time": "15:30:34"}
|
||||
{"current_steps": 315, "total_steps": 4039, "loss": 0.3918, "lr": 3.1089108910891095e-05, "epoch": 0.546400693842151, "percentage": 7.8, "elapsed_time": "1:18:27", "remaining_time": "15:27:36"}
|
||||
{"current_steps": 320, "total_steps": 4039, "loss": 0.3152, "lr": 3.158415841584159e-05, "epoch": 0.5550737207285342, "percentage": 7.92, "elapsed_time": "1:19:48", "remaining_time": "15:27:28"}
|
||||
{"current_steps": 325, "total_steps": 4039, "loss": 0.3865, "lr": 3.2079207920792084e-05, "epoch": 0.5637467476149176, "percentage": 8.05, "elapsed_time": "1:20:57", "remaining_time": "15:25:09"}
|
||||
{"current_steps": 330, "total_steps": 4039, "loss": 0.3921, "lr": 3.257425742574258e-05, "epoch": 0.572419774501301, "percentage": 8.17, "elapsed_time": "1:22:08", "remaining_time": "15:23:17"}
|
||||
{"current_steps": 335, "total_steps": 4039, "loss": 0.3886, "lr": 3.306930693069307e-05, "epoch": 0.5810928013876843, "percentage": 8.29, "elapsed_time": "1:23:24", "remaining_time": "15:22:18"}
|
||||
{"current_steps": 340, "total_steps": 4039, "loss": 0.3575, "lr": 3.3564356435643566e-05, "epoch": 0.5897658282740676, "percentage": 8.42, "elapsed_time": "1:24:38", "remaining_time": "15:20:56"}
|
||||
{"current_steps": 345, "total_steps": 4039, "loss": 0.3283, "lr": 3.405940594059406e-05, "epoch": 0.598438855160451, "percentage": 8.54, "elapsed_time": "1:25:56", "remaining_time": "15:20:08"}
|
||||
{"current_steps": 350, "total_steps": 4039, "loss": 0.3755, "lr": 3.4554455445544554e-05, "epoch": 0.6071118820468343, "percentage": 8.67, "elapsed_time": "1:27:08", "remaining_time": "15:18:27"}
|
||||
{"current_steps": 355, "total_steps": 4039, "loss": 0.3077, "lr": 3.5049504950495055e-05, "epoch": 0.6157849089332177, "percentage": 8.79, "elapsed_time": "1:28:19", "remaining_time": "15:16:32"}
|
||||
{"current_steps": 360, "total_steps": 4039, "loss": 0.3502, "lr": 3.554455445544555e-05, "epoch": 0.6244579358196011, "percentage": 8.91, "elapsed_time": "1:29:38", "remaining_time": "15:16:05"}
|
||||
{"current_steps": 365, "total_steps": 4039, "loss": 0.3592, "lr": 3.6039603960396043e-05, "epoch": 0.6331309627059843, "percentage": 9.04, "elapsed_time": "1:30:59", "remaining_time": "15:15:50"}
|
||||
{"current_steps": 370, "total_steps": 4039, "loss": 0.3293, "lr": 3.653465346534654e-05, "epoch": 0.6418039895923677, "percentage": 9.16, "elapsed_time": "1:32:12", "remaining_time": "15:14:23"}
|
||||
{"current_steps": 375, "total_steps": 4039, "loss": 0.3475, "lr": 3.702970297029703e-05, "epoch": 0.6504770164787511, "percentage": 9.28, "elapsed_time": "1:33:19", "remaining_time": "15:11:54"}
|
||||
{"current_steps": 380, "total_steps": 4039, "loss": 0.3864, "lr": 3.7524752475247526e-05, "epoch": 0.6591500433651344, "percentage": 9.41, "elapsed_time": "1:34:30", "remaining_time": "15:09:57"}
|
||||
{"current_steps": 385, "total_steps": 4039, "loss": 0.362, "lr": 3.801980198019802e-05, "epoch": 0.6678230702515178, "percentage": 9.53, "elapsed_time": "1:35:39", "remaining_time": "15:07:54"}
|
||||
{"current_steps": 390, "total_steps": 4039, "loss": 0.3279, "lr": 3.8514851485148514e-05, "epoch": 0.6764960971379012, "percentage": 9.66, "elapsed_time": "1:36:48", "remaining_time": "15:05:49"}
|
||||
{"current_steps": 395, "total_steps": 4039, "loss": 0.418, "lr": 3.9009900990099015e-05, "epoch": 0.6851691240242844, "percentage": 9.78, "elapsed_time": "1:38:00", "remaining_time": "15:04:10"}
|
||||
{"current_steps": 400, "total_steps": 4039, "loss": 0.3255, "lr": 3.950495049504951e-05, "epoch": 0.6938421509106678, "percentage": 9.9, "elapsed_time": "1:39:11", "remaining_time": "15:02:19"}
|
||||
{"current_steps": 405, "total_steps": 4039, "loss": 0.3386, "lr": 4e-05, "epoch": 0.7025151777970512, "percentage": 10.03, "elapsed_time": "1:40:27", "remaining_time": "15:01:23"}
|
||||
{"current_steps": 410, "total_steps": 4039, "loss": 0.4236, "lr": 3.9999813263055716e-05, "epoch": 0.7111882046834345, "percentage": 10.15, "elapsed_time": "1:41:40", "remaining_time": "14:59:56"}
|
||||
{"current_steps": 415, "total_steps": 4039, "loss": 0.3035, "lr": 3.999925305570993e-05, "epoch": 0.7198612315698178, "percentage": 10.27, "elapsed_time": "1:42:55", "remaining_time": "14:58:45"}
|
||||
{"current_steps": 420, "total_steps": 4039, "loss": 0.3503, "lr": 3.999831938842379e-05, "epoch": 0.7285342584562012, "percentage": 10.4, "elapsed_time": "1:44:01", "remaining_time": "14:56:20"}
|
||||
{"current_steps": 425, "total_steps": 4039, "loss": 0.39, "lr": 3.99970122786323e-05, "epoch": 0.7372072853425846, "percentage": 10.52, "elapsed_time": "1:45:22", "remaining_time": "14:56:03"}
|
||||
{"current_steps": 430, "total_steps": 4039, "loss": 0.3287, "lr": 3.999533175074404e-05, "epoch": 0.7458803122289679, "percentage": 10.65, "elapsed_time": "1:46:32", "remaining_time": "14:54:13"}
|
||||
{"current_steps": 435, "total_steps": 4039, "loss": 0.3376, "lr": 3.999327783614067e-05, "epoch": 0.7545533391153513, "percentage": 10.77, "elapsed_time": "1:47:44", "remaining_time": "14:52:37"}
|
||||
{"current_steps": 440, "total_steps": 4039, "loss": 0.327, "lr": 3.9990850573176374e-05, "epoch": 0.7632263660017347, "percentage": 10.89, "elapsed_time": "1:49:03", "remaining_time": "14:52:00"}
|
||||
{"current_steps": 445, "total_steps": 4039, "loss": 0.3779, "lr": 3.9988050007177094e-05, "epoch": 0.7718993928881179, "percentage": 11.02, "elapsed_time": "1:50:10", "remaining_time": "14:49:51"}
|
||||
{"current_steps": 450, "total_steps": 4039, "loss": 0.339, "lr": 3.998487619043977e-05, "epoch": 0.7805724197745013, "percentage": 11.14, "elapsed_time": "1:51:26", "remaining_time": "14:48:45"}
|
||||
{"current_steps": 455, "total_steps": 4039, "loss": 0.2904, "lr": 3.9981329182231274e-05, "epoch": 0.7892454466608847, "percentage": 11.27, "elapsed_time": "1:52:35", "remaining_time": "14:46:49"}
|
||||
{"current_steps": 460, "total_steps": 4039, "loss": 0.3742, "lr": 3.9977409048787355e-05, "epoch": 0.797918473547268, "percentage": 11.39, "elapsed_time": "1:53:50", "remaining_time": "14:45:44"}
|
||||
{"current_steps": 465, "total_steps": 4039, "loss": 0.3339, "lr": 3.9973115863311375e-05, "epoch": 0.8065915004336514, "percentage": 11.51, "elapsed_time": "1:55:04", "remaining_time": "14:44:26"}
|
||||
{"current_steps": 470, "total_steps": 4039, "loss": 0.3559, "lr": 3.996844970597299e-05, "epoch": 0.8152645273200347, "percentage": 11.64, "elapsed_time": "1:56:15", "remaining_time": "14:42:48"}
|
||||
{"current_steps": 475, "total_steps": 4039, "loss": 0.3503, "lr": 3.996341066390659e-05, "epoch": 0.823937554206418, "percentage": 11.76, "elapsed_time": "1:57:30", "remaining_time": "14:41:43"}
|
||||
{"current_steps": 480, "total_steps": 4039, "loss": 0.3473, "lr": 3.9957998831209695e-05, "epoch": 0.8326105810928014, "percentage": 11.88, "elapsed_time": "1:58:51", "remaining_time": "14:41:14"}
|
||||
{"current_steps": 485, "total_steps": 4039, "loss": 0.343, "lr": 3.9952214308941225e-05, "epoch": 0.8412836079791848, "percentage": 12.01, "elapsed_time": "1:59:58", "remaining_time": "14:39:07"}
|
||||
{"current_steps": 490, "total_steps": 4039, "loss": 0.3211, "lr": 3.9946057205119575e-05, "epoch": 0.849956634865568, "percentage": 12.13, "elapsed_time": "2:01:12", "remaining_time": "14:37:52"}
|
||||
{"current_steps": 495, "total_steps": 4039, "loss": 0.3621, "lr": 3.993952763472063e-05, "epoch": 0.8586296617519514, "percentage": 12.26, "elapsed_time": "2:02:19", "remaining_time": "14:35:48"}
|
||||
{"current_steps": 500, "total_steps": 4039, "loss": 0.3445, "lr": 3.993262571967558e-05, "epoch": 0.8673026886383348, "percentage": 12.38, "elapsed_time": "2:03:34", "remaining_time": "14:34:39"}
|
||||
{"current_steps": 505, "total_steps": 4039, "loss": 0.3753, "lr": 3.9925351588868684e-05, "epoch": 0.8759757155247181, "percentage": 12.5, "elapsed_time": "2:04:42", "remaining_time": "14:32:40"}
|
||||
{"current_steps": 510, "total_steps": 4039, "loss": 0.3613, "lr": 3.9917705378134846e-05, "epoch": 0.8846487424111015, "percentage": 12.63, "elapsed_time": "2:05:42", "remaining_time": "14:29:53"}
|
||||
{"current_steps": 515, "total_steps": 4039, "loss": 0.3409, "lr": 3.9909687230257056e-05, "epoch": 0.8933217692974849, "percentage": 12.75, "elapsed_time": "2:07:02", "remaining_time": "14:29:20"}
|
||||
{"current_steps": 520, "total_steps": 4039, "loss": 0.3827, "lr": 3.990129729496376e-05, "epoch": 0.9019947961838681, "percentage": 12.87, "elapsed_time": "2:08:09", "remaining_time": "14:27:14"}
|
||||
{"current_steps": 525, "total_steps": 4039, "loss": 0.3405, "lr": 3.9892535728926055e-05, "epoch": 0.9106678230702515, "percentage": 13.0, "elapsed_time": "2:09:23", "remaining_time": "14:26:00"}
|
||||
{"current_steps": 530, "total_steps": 4039, "loss": 0.3325, "lr": 3.988340269575474e-05, "epoch": 0.9193408499566349, "percentage": 13.12, "elapsed_time": "2:10:43", "remaining_time": "14:25:27"}
|
||||
{"current_steps": 535, "total_steps": 4039, "loss": 0.3064, "lr": 3.987389836599728e-05, "epoch": 0.9280138768430182, "percentage": 13.25, "elapsed_time": "2:12:01", "remaining_time": "14:24:43"}
|
||||
{"current_steps": 540, "total_steps": 4039, "loss": 0.3428, "lr": 3.986402291713463e-05, "epoch": 0.9366869037294016, "percentage": 13.37, "elapsed_time": "2:13:20", "remaining_time": "14:24:02"}
|
||||
{"current_steps": 545, "total_steps": 4039, "loss": 0.3311, "lr": 3.985377653357791e-05, "epoch": 0.9453599306157849, "percentage": 13.49, "elapsed_time": "2:14:36", "remaining_time": "14:22:59"}
|
||||
{"current_steps": 550, "total_steps": 4039, "loss": 0.3614, "lr": 3.984315940666495e-05, "epoch": 0.9540329575021682, "percentage": 13.62, "elapsed_time": "2:15:44", "remaining_time": "14:21:04"}
|
||||
{"current_steps": 555, "total_steps": 4039, "loss": 0.3321, "lr": 3.983217173465674e-05, "epoch": 0.9627059843885516, "percentage": 13.74, "elapsed_time": "2:16:51", "remaining_time": "14:19:07"}
|
||||
{"current_steps": 560, "total_steps": 4039, "loss": 0.3421, "lr": 3.98208137227337e-05, "epoch": 0.971379011274935, "percentage": 13.86, "elapsed_time": "2:18:05", "remaining_time": "14:17:51"}
|
||||
{"current_steps": 565, "total_steps": 4039, "loss": 0.3823, "lr": 3.9809085582991877e-05, "epoch": 0.9800520381613183, "percentage": 13.99, "elapsed_time": "2:19:22", "remaining_time": "14:16:55"}
|
||||
{"current_steps": 570, "total_steps": 4039, "loss": 0.3032, "lr": 3.979698753443897e-05, "epoch": 0.9887250650477016, "percentage": 14.11, "elapsed_time": "2:20:37", "remaining_time": "14:15:52"}
|
||||
{"current_steps": 575, "total_steps": 4039, "loss": 0.3377, "lr": 3.978451980299024e-05, "epoch": 0.997398091934085, "percentage": 14.24, "elapsed_time": "2:21:50", "remaining_time": "14:14:29"}
|
||||
{"current_steps": 580, "total_steps": 4039, "loss": 0.3229, "lr": 3.97716826214643e-05, "epoch": 1.00520381613183, "percentage": 14.36, "elapsed_time": "2:22:52", "remaining_time": "14:12:05"}
|
||||
{"current_steps": 585, "total_steps": 4039, "loss": 0.311, "lr": 3.975847622957875e-05, "epoch": 1.0138768430182135, "percentage": 14.48, "elapsed_time": "2:24:06", "remaining_time": "14:10:48"}
|
||||
{"current_steps": 590, "total_steps": 4039, "loss": 0.2871, "lr": 3.974490087394571e-05, "epoch": 1.0225498699045967, "percentage": 14.61, "elapsed_time": "2:25:14", "remaining_time": "14:09:04"}
|
||||
{"current_steps": 595, "total_steps": 4039, "loss": 0.3321, "lr": 3.973095680806724e-05, "epoch": 1.03122289679098, "percentage": 14.73, "elapsed_time": "2:26:25", "remaining_time": "14:07:33"}
|
||||
{"current_steps": 600, "total_steps": 4039, "loss": 0.319, "lr": 3.9716644292330544e-05, "epoch": 1.0398959236773635, "percentage": 14.86, "elapsed_time": "2:27:36", "remaining_time": "14:06:00"}
|
||||
{"current_steps": 605, "total_steps": 4039, "loss": 0.298, "lr": 3.9701963594003185e-05, "epoch": 1.0485689505637468, "percentage": 14.98, "elapsed_time": "2:28:45", "remaining_time": "14:04:23"}
|
||||
{"current_steps": 610, "total_steps": 4039, "loss": 0.3459, "lr": 3.968691498722803e-05, "epoch": 1.05724197745013, "percentage": 15.1, "elapsed_time": "2:30:02", "remaining_time": "14:03:24"}
|
||||
{"current_steps": 615, "total_steps": 4039, "loss": 0.3273, "lr": 3.967149875301817e-05, "epoch": 1.0659150043365135, "percentage": 15.23, "elapsed_time": "2:31:14", "remaining_time": "14:02:04"}
|
||||
{"current_steps": 620, "total_steps": 4039, "loss": 0.3286, "lr": 3.9655715179251635e-05, "epoch": 1.0745880312228968, "percentage": 15.35, "elapsed_time": "2:32:21", "remaining_time": "14:00:08"}
|
||||
{"current_steps": 625, "total_steps": 4039, "loss": 0.3198, "lr": 3.963956456066608e-05, "epoch": 1.08326105810928, "percentage": 15.47, "elapsed_time": "2:33:37", "remaining_time": "13:59:11"}
|
||||
{"current_steps": 630, "total_steps": 4039, "loss": 0.3475, "lr": 3.962304719885321e-05, "epoch": 1.0919340849956636, "percentage": 15.6, "elapsed_time": "2:34:57", "remaining_time": "13:58:30"}
|
||||
{"current_steps": 635, "total_steps": 4039, "loss": 0.2966, "lr": 3.960616340225318e-05, "epoch": 1.1006071118820469, "percentage": 15.72, "elapsed_time": "2:36:07", "remaining_time": "13:56:56"}
|
||||
{"current_steps": 640, "total_steps": 4039, "loss": 0.3173, "lr": 3.958891348614888e-05, "epoch": 1.1092801387684301, "percentage": 15.85, "elapsed_time": "2:37:23", "remaining_time": "13:55:51"}
|
||||
{"current_steps": 645, "total_steps": 4039, "loss": 0.3462, "lr": 3.957129777265995e-05, "epoch": 1.1179531656548136, "percentage": 15.97, "elapsed_time": "2:38:40", "remaining_time": "13:54:59"}
|
||||
{"current_steps": 650, "total_steps": 4039, "loss": 0.305, "lr": 3.955331659073684e-05, "epoch": 1.126626192541197, "percentage": 16.09, "elapsed_time": "2:39:38", "remaining_time": "13:52:21"}
|
||||
{"current_steps": 655, "total_steps": 4039, "loss": 0.3637, "lr": 3.953497027615465e-05, "epoch": 1.1352992194275802, "percentage": 16.22, "elapsed_time": "2:40:42", "remaining_time": "13:50:19"}
|
||||
{"current_steps": 660, "total_steps": 4039, "loss": 0.2863, "lr": 3.9516259171506866e-05, "epoch": 1.1439722463139637, "percentage": 16.34, "elapsed_time": "2:41:48", "remaining_time": "13:48:24"}
|
||||
{"current_steps": 665, "total_steps": 4039, "loss": 0.2999, "lr": 3.9497183626198914e-05, "epoch": 1.152645273200347, "percentage": 16.46, "elapsed_time": "2:43:00", "remaining_time": "13:47:01"}
|
||||
{"current_steps": 670, "total_steps": 4039, "loss": 0.3832, "lr": 3.947774399644171e-05, "epoch": 1.1613183000867302, "percentage": 16.59, "elapsed_time": "2:44:11", "remaining_time": "13:45:36"}
|
||||
{"current_steps": 675, "total_steps": 4039, "loss": 0.3472, "lr": 3.945794064524497e-05, "epoch": 1.1699913269731137, "percentage": 16.71, "elapsed_time": "2:45:21", "remaining_time": "13:44:03"}
|
||||
{"current_steps": 680, "total_steps": 4039, "loss": 0.3315, "lr": 3.943777394241041e-05, "epoch": 1.178664353859497, "percentage": 16.84, "elapsed_time": "2:46:37", "remaining_time": "13:43:05"}
|
||||
{"current_steps": 685, "total_steps": 4039, "loss": 0.3294, "lr": 3.941724426452488e-05, "epoch": 1.1873373807458802, "percentage": 16.96, "elapsed_time": "2:47:57", "remaining_time": "13:42:23"}
|
||||
{"current_steps": 690, "total_steps": 4039, "loss": 0.3244, "lr": 3.939635199495331e-05, "epoch": 1.1960104076322637, "percentage": 17.08, "elapsed_time": "2:49:09", "remaining_time": "13:41:01"}
|
||||
{"current_steps": 695, "total_steps": 4039, "loss": 0.3242, "lr": 3.937509752383156e-05, "epoch": 1.204683434518647, "percentage": 17.21, "elapsed_time": "2:50:15", "remaining_time": "13:39:13"}
|
||||
{"current_steps": 700, "total_steps": 4039, "loss": 0.3162, "lr": 3.935348124805913e-05, "epoch": 1.2133564614050303, "percentage": 17.33, "elapsed_time": "2:51:28", "remaining_time": "13:37:55"}
|
||||
{"current_steps": 705, "total_steps": 4039, "loss": 0.319, "lr": 3.933150357129175e-05, "epoch": 1.2220294882914138, "percentage": 17.45, "elapsed_time": "2:52:39", "remaining_time": "13:36:31"}
|
||||
{"current_steps": 710, "total_steps": 4039, "loss": 0.3216, "lr": 3.930916490393383e-05, "epoch": 1.230702515177797, "percentage": 17.58, "elapsed_time": "2:53:52", "remaining_time": "13:35:13"}
|
||||
{"current_steps": 715, "total_steps": 4039, "loss": 0.3518, "lr": 3.9286465663130834e-05, "epoch": 1.2393755420641803, "percentage": 17.7, "elapsed_time": "2:54:58", "remaining_time": "13:33:28"}
|
||||
{"current_steps": 720, "total_steps": 4039, "loss": 0.2771, "lr": 3.926340627276143e-05, "epoch": 1.2480485689505638, "percentage": 17.83, "elapsed_time": "2:56:08", "remaining_time": "13:31:55"}
|
||||
{"current_steps": 725, "total_steps": 4039, "loss": 0.3161, "lr": 3.923998716342964e-05, "epoch": 1.256721595836947, "percentage": 17.95, "elapsed_time": "2:57:21", "remaining_time": "13:30:44"}
|
||||
{"current_steps": 730, "total_steps": 4039, "loss": 0.3462, "lr": 3.921620877245676e-05, "epoch": 1.2653946227233304, "percentage": 18.07, "elapsed_time": "2:58:32", "remaining_time": "13:29:18"}
|
||||
{"current_steps": 735, "total_steps": 4039, "loss": 0.2879, "lr": 3.919207154387318e-05, "epoch": 1.2740676496097139, "percentage": 18.2, "elapsed_time": "2:59:44", "remaining_time": "13:27:58"}
|
||||
{"current_steps": 740, "total_steps": 4039, "loss": 0.3292, "lr": 3.9167575928410146e-05, "epoch": 1.2827406764960971, "percentage": 18.32, "elapsed_time": "3:00:56", "remaining_time": "13:26:40"}
|
||||
{"current_steps": 745, "total_steps": 4039, "loss": 0.3337, "lr": 3.9142722383491294e-05, "epoch": 1.2914137033824804, "percentage": 18.45, "elapsed_time": "3:02:08", "remaining_time": "13:25:18"}
|
||||
{"current_steps": 750, "total_steps": 4039, "loss": 0.2884, "lr": 3.911751137322412e-05, "epoch": 1.300086730268864, "percentage": 18.57, "elapsed_time": "3:03:22", "remaining_time": "13:24:09"}
|
||||
{"current_steps": 755, "total_steps": 4039, "loss": 0.3047, "lr": 3.909194336839133e-05, "epoch": 1.3087597571552472, "percentage": 18.69, "elapsed_time": "3:04:40", "remaining_time": "13:23:18"}
|
||||
{"current_steps": 760, "total_steps": 4039, "loss": 0.3157, "lr": 3.906601884644203e-05, "epoch": 1.3174327840416304, "percentage": 18.82, "elapsed_time": "3:05:47", "remaining_time": "13:21:34"}
|
||||
{"current_steps": 765, "total_steps": 4039, "loss": 0.3002, "lr": 3.903973829148282e-05, "epoch": 1.326105810928014, "percentage": 18.94, "elapsed_time": "3:06:58", "remaining_time": "13:20:13"}
|
||||
{"current_steps": 770, "total_steps": 4039, "loss": 0.3359, "lr": 3.901310219426877e-05, "epoch": 1.3347788378143972, "percentage": 19.06, "elapsed_time": "3:08:06", "remaining_time": "13:18:36"}
|
||||
{"current_steps": 775, "total_steps": 4039, "loss": 0.2923, "lr": 3.89861110521942e-05, "epoch": 1.3434518647007807, "percentage": 19.19, "elapsed_time": "3:09:14", "remaining_time": "13:17:00"}
|
||||
{"current_steps": 780, "total_steps": 4039, "loss": 0.3348, "lr": 3.895876536928346e-05, "epoch": 1.352124891587164, "percentage": 19.31, "elapsed_time": "3:10:25", "remaining_time": "13:15:39"}
|
||||
{"current_steps": 785, "total_steps": 4039, "loss": 0.3169, "lr": 3.893106565618147e-05, "epoch": 1.3607979184735473, "percentage": 19.44, "elapsed_time": "3:11:36", "remaining_time": "13:14:15"}
|
||||
{"current_steps": 790, "total_steps": 4039, "loss": 0.3028, "lr": 3.890301243014421e-05, "epoch": 1.3694709453599305, "percentage": 19.56, "elapsed_time": "3:12:43", "remaining_time": "13:12:38"}
|
||||
{"current_steps": 795, "total_steps": 4039, "loss": 0.3291, "lr": 3.887460621502906e-05, "epoch": 1.378143972246314, "percentage": 19.68, "elapsed_time": "3:13:45", "remaining_time": "13:10:37"}
|
||||
{"current_steps": 800, "total_steps": 4039, "loss": 0.3339, "lr": 3.884584754128499e-05, "epoch": 1.3868169991326973, "percentage": 19.81, "elapsed_time": "3:14:52", "remaining_time": "13:09:02"}
|
||||
{"current_steps": 805, "total_steps": 4039, "loss": 0.2893, "lr": 3.881673694594269e-05, "epoch": 1.3954900260190808, "percentage": 19.93, "elapsed_time": "3:16:05", "remaining_time": "13:07:45"}
|
||||
{"current_steps": 810, "total_steps": 4039, "loss": 0.2864, "lr": 3.8787274972604514e-05, "epoch": 1.404163052905464, "percentage": 20.05, "elapsed_time": "3:17:16", "remaining_time": "13:06:26"}
|
||||
{"current_steps": 815, "total_steps": 4039, "loss": 0.2985, "lr": 3.875746217143436e-05, "epoch": 1.4128360797918473, "percentage": 20.18, "elapsed_time": "3:18:25", "remaining_time": "13:04:54"}
|
||||
{"current_steps": 820, "total_steps": 4039, "loss": 0.3218, "lr": 3.872729909914736e-05, "epoch": 1.4215091066782306, "percentage": 20.3, "elapsed_time": "3:19:42", "remaining_time": "13:04:00"}
|
||||
{"current_steps": 825, "total_steps": 4039, "loss": 0.3547, "lr": 3.869678631899952e-05, "epoch": 1.430182133564614, "percentage": 20.43, "elapsed_time": "3:20:58", "remaining_time": "13:02:55"}
|
||||
{"current_steps": 830, "total_steps": 4039, "loss": 0.2908, "lr": 3.866592440077716e-05, "epoch": 1.4388551604509974, "percentage": 20.55, "elapsed_time": "3:22:01", "remaining_time": "13:01:04"}
|
||||
{"current_steps": 835, "total_steps": 4039, "loss": 0.3116, "lr": 3.8634713920786315e-05, "epoch": 1.4475281873373809, "percentage": 20.67, "elapsed_time": "3:23:11", "remaining_time": "12:59:39"}
|
||||
{"current_steps": 840, "total_steps": 4039, "loss": 0.2706, "lr": 3.860315546184195e-05, "epoch": 1.4562012142237641, "percentage": 20.8, "elapsed_time": "3:24:31", "remaining_time": "12:58:52"}
|
||||
{"current_steps": 845, "total_steps": 4039, "loss": 0.2862, "lr": 3.857124961325709e-05, "epoch": 1.4648742411101474, "percentage": 20.92, "elapsed_time": "3:25:41", "remaining_time": "12:57:28"}
|
||||
{"current_steps": 850, "total_steps": 4039, "loss": 0.2908, "lr": 3.8538996970831794e-05, "epoch": 1.4735472679965307, "percentage": 21.04, "elapsed_time": "3:26:59", "remaining_time": "12:56:33"}
|
||||
{"current_steps": 855, "total_steps": 4039, "loss": 0.3056, "lr": 3.850639813684206e-05, "epoch": 1.4822202948829142, "percentage": 21.17, "elapsed_time": "3:28:16", "remaining_time": "12:55:35"}
|
||||
{"current_steps": 860, "total_steps": 4039, "loss": 0.3283, "lr": 3.847345372002854e-05, "epoch": 1.4908933217692975, "percentage": 21.29, "elapsed_time": "3:29:33", "remaining_time": "12:54:38"}
|
||||
{"current_steps": 865, "total_steps": 4039, "loss": 0.3372, "lr": 3.844016433558522e-05, "epoch": 1.499566348655681, "percentage": 21.42, "elapsed_time": "3:30:52", "remaining_time": "12:53:47"}
|
||||
{"current_steps": 870, "total_steps": 4039, "loss": 0.3097, "lr": 3.840653060514788e-05, "epoch": 1.5082393755420642, "percentage": 21.54, "elapsed_time": "3:32:08", "remaining_time": "12:52:45"}
|
||||
{"current_steps": 875, "total_steps": 4039, "loss": 0.3346, "lr": 3.8372553156782536e-05, "epoch": 1.5169124024284475, "percentage": 21.66, "elapsed_time": "3:33:12", "remaining_time": "12:50:59"}
|
||||
{"current_steps": 880, "total_steps": 4039, "loss": 0.2982, "lr": 3.833823262497367e-05, "epoch": 1.5255854293148308, "percentage": 21.79, "elapsed_time": "3:34:27", "remaining_time": "12:49:52"}
|
||||
{"current_steps": 885, "total_steps": 4039, "loss": 0.3235, "lr": 3.830356965061241e-05, "epoch": 1.5342584562012143, "percentage": 21.91, "elapsed_time": "3:35:39", "remaining_time": "12:48:35"}
|
||||
{"current_steps": 890, "total_steps": 4039, "loss": 0.3152, "lr": 3.8268564880984545e-05, "epoch": 1.5429314830875975, "percentage": 22.04, "elapsed_time": "3:36:52", "remaining_time": "12:47:20"}
|
||||
{"current_steps": 895, "total_steps": 4039, "loss": 0.3455, "lr": 3.823321896975844e-05, "epoch": 1.551604509973981, "percentage": 22.16, "elapsed_time": "3:38:03", "remaining_time": "12:46:00"}
|
||||
{"current_steps": 900, "total_steps": 4039, "loss": 0.3368, "lr": 3.819753257697285e-05, "epoch": 1.5602775368603643, "percentage": 22.28, "elapsed_time": "3:39:17", "remaining_time": "12:44:49"}
|
||||
{"current_steps": 905, "total_steps": 4039, "loss": 0.2837, "lr": 3.816150636902457e-05, "epoch": 1.5689505637467476, "percentage": 22.41, "elapsed_time": "3:40:25", "remaining_time": "12:43:19"}
|
||||
{"current_steps": 910, "total_steps": 4039, "loss": 0.3479, "lr": 3.8125141018655986e-05, "epoch": 1.5776235906331308, "percentage": 22.53, "elapsed_time": "3:41:28", "remaining_time": "12:41:32"}
|
||||
{"current_steps": 915, "total_steps": 4039, "loss": 0.3014, "lr": 3.808843720494255e-05, "epoch": 1.5862966175195143, "percentage": 22.65, "elapsed_time": "3:42:46", "remaining_time": "12:40:34"}
|
||||
{"current_steps": 920, "total_steps": 4039, "loss": 0.2952, "lr": 3.805139561328007e-05, "epoch": 1.5949696444058976, "percentage": 22.78, "elapsed_time": "3:43:55", "remaining_time": "12:39:09"}
|
||||
{"current_steps": 925, "total_steps": 4039, "loss": 0.3395, "lr": 3.801401693537189e-05, "epoch": 1.603642671292281, "percentage": 22.9, "elapsed_time": "3:45:10", "remaining_time": "12:38:02"}
|
||||
{"current_steps": 930, "total_steps": 4039, "loss": 0.3359, "lr": 3.797630186921603e-05, "epoch": 1.6123156981786644, "percentage": 23.03, "elapsed_time": "3:46:18", "remaining_time": "12:36:33"}
|
||||
{"current_steps": 935, "total_steps": 4039, "loss": 0.2944, "lr": 3.793825111909211e-05, "epoch": 1.6209887250650477, "percentage": 23.15, "elapsed_time": "3:47:25", "remaining_time": "12:35:00"}
|
||||
{"current_steps": 940, "total_steps": 4039, "loss": 0.2978, "lr": 3.789986539554822e-05, "epoch": 1.629661751951431, "percentage": 23.27, "elapsed_time": "3:48:29", "remaining_time": "12:33:18"}
|
||||
{"current_steps": 945, "total_steps": 4039, "loss": 0.3049, "lr": 3.786114541538762e-05, "epoch": 1.6383347788378144, "percentage": 23.4, "elapsed_time": "3:49:40", "remaining_time": "12:31:59"}
|
||||
{"current_steps": 950, "total_steps": 4039, "loss": 0.3094, "lr": 3.7822091901655385e-05, "epoch": 1.6470078057241977, "percentage": 23.52, "elapsed_time": "3:50:42", "remaining_time": "12:30:08"}
|
||||
{"current_steps": 955, "total_steps": 4039, "loss": 0.2922, "lr": 3.7782705583624905e-05, "epoch": 1.6556808326105812, "percentage": 23.64, "elapsed_time": "3:51:57", "remaining_time": "12:29:04"}
|
||||
{"current_steps": 960, "total_steps": 4039, "loss": 0.2811, "lr": 3.7742987196784245e-05, "epoch": 1.6643538594969645, "percentage": 23.77, "elapsed_time": "3:53:15", "remaining_time": "12:28:06"}
|
||||
{"current_steps": 965, "total_steps": 4039, "loss": 0.3389, "lr": 3.770293748282242e-05, "epoch": 1.6730268863833477, "percentage": 23.89, "elapsed_time": "3:54:34", "remaining_time": "12:27:15"}
|
||||
{"current_steps": 970, "total_steps": 4039, "loss": 0.3111, "lr": 3.7662557189615566e-05, "epoch": 1.681699913269731, "percentage": 24.02, "elapsed_time": "3:55:42", "remaining_time": "12:25:45"}
|
||||
{"current_steps": 975, "total_steps": 4039, "loss": 0.3069, "lr": 3.762184707121292e-05, "epoch": 1.6903729401561145, "percentage": 24.14, "elapsed_time": "3:57:00", "remaining_time": "12:24:49"}
|
||||
{"current_steps": 980, "total_steps": 4039, "loss": 0.2978, "lr": 3.7580807887822805e-05, "epoch": 1.699045967042498, "percentage": 24.26, "elapsed_time": "3:58:06", "remaining_time": "12:23:12"}
|
||||
{"current_steps": 985, "total_steps": 4039, "loss": 0.2834, "lr": 3.753944040579839e-05, "epoch": 1.7077189939288813, "percentage": 24.39, "elapsed_time": "3:59:20", "remaining_time": "12:22:04"}
|
||||
{"current_steps": 990, "total_steps": 4039, "loss": 0.3262, "lr": 3.749774539762339e-05, "epoch": 1.7163920208152645, "percentage": 24.51, "elapsed_time": "4:00:33", "remaining_time": "12:20:53"}
|
||||
{"current_steps": 995, "total_steps": 4039, "loss": 0.294, "lr": 3.745572364189764e-05, "epoch": 1.7250650477016478, "percentage": 24.63, "elapsed_time": "4:01:46", "remaining_time": "12:19:39"}
|
||||
{"current_steps": 1000, "total_steps": 4039, "loss": 0.2867, "lr": 3.741337592332258e-05, "epoch": 1.733738074588031, "percentage": 24.76, "elapsed_time": "4:02:54", "remaining_time": "12:18:10"}
|
||||
{"current_steps": 1005, "total_steps": 4039, "loss": 0.3144, "lr": 3.7370703032686554e-05, "epoch": 1.7424111014744146, "percentage": 24.88, "elapsed_time": "4:04:08", "remaining_time": "12:17:03"}
|
||||
{"current_steps": 1010, "total_steps": 4039, "loss": 0.2958, "lr": 3.732770576685009e-05, "epoch": 1.751084128360798, "percentage": 25.01, "elapsed_time": "4:05:24", "remaining_time": "12:15:58"}
|
||||
{"current_steps": 1015, "total_steps": 4039, "loss": 0.3312, "lr": 3.7284384928731e-05, "epoch": 1.7597571552471813, "percentage": 25.13, "elapsed_time": "4:06:41", "remaining_time": "12:14:58"}
|
||||
{"current_steps": 1020, "total_steps": 4039, "loss": 0.2785, "lr": 3.724074132728935e-05, "epoch": 1.7684301821335646, "percentage": 25.25, "elapsed_time": "4:07:56", "remaining_time": "12:13:52"}
|
||||
{"current_steps": 1025, "total_steps": 4039, "loss": 0.3005, "lr": 3.719677577751245e-05, "epoch": 1.777103209019948, "percentage": 25.38, "elapsed_time": "4:09:12", "remaining_time": "12:12:48"}
|
||||
{"current_steps": 1030, "total_steps": 4039, "loss": 0.2729, "lr": 3.715248910039952e-05, "epoch": 1.7857762359063312, "percentage": 25.5, "elapsed_time": "4:10:27", "remaining_time": "12:11:39"}
|
||||
{"current_steps": 1035, "total_steps": 4039, "loss": 0.3317, "lr": 3.710788212294644e-05, "epoch": 1.7944492627927147, "percentage": 25.63, "elapsed_time": "4:11:35", "remaining_time": "12:10:12"}
|
||||
{"current_steps": 1040, "total_steps": 4039, "loss": 0.3143, "lr": 3.706295567813028e-05, "epoch": 1.8031222896790982, "percentage": 25.75, "elapsed_time": "4:12:51", "remaining_time": "12:09:09"}
|
||||
{"current_steps": 1045, "total_steps": 4039, "loss": 0.2882, "lr": 3.7017710604893736e-05, "epoch": 1.8117953165654814, "percentage": 25.87, "elapsed_time": "4:14:10", "remaining_time": "12:08:13"}
|
||||
{"current_steps": 1050, "total_steps": 4039, "loss": 0.2931, "lr": 3.697214774812949e-05, "epoch": 1.8204683434518647, "percentage": 26.0, "elapsed_time": "4:15:24", "remaining_time": "12:07:03"}
|
||||
{"current_steps": 1055, "total_steps": 4039, "loss": 0.3261, "lr": 3.69262679586644e-05, "epoch": 1.829141370338248, "percentage": 26.12, "elapsed_time": "4:16:39", "remaining_time": "12:05:55"}
|
||||
{"current_steps": 1060, "total_steps": 4039, "loss": 0.3251, "lr": 3.688007209324363e-05, "epoch": 1.8378143972246312, "percentage": 26.24, "elapsed_time": "4:17:58", "remaining_time": "12:04:59"}
|
||||
{"current_steps": 1065, "total_steps": 4039, "loss": 0.2929, "lr": 3.683356101451467e-05, "epoch": 1.8464874241110147, "percentage": 26.37, "elapsed_time": "4:19:09", "remaining_time": "12:03:41"}
|
||||
{"current_steps": 1070, "total_steps": 4039, "loss": 0.3151, "lr": 3.6786735591011175e-05, "epoch": 1.8551604509973982, "percentage": 26.49, "elapsed_time": "4:20:20", "remaining_time": "12:02:23"}
|
||||
{"current_steps": 1075, "total_steps": 4039, "loss": 0.3061, "lr": 3.6739596697136805e-05, "epoch": 1.8638334778837815, "percentage": 26.62, "elapsed_time": "4:21:35", "remaining_time": "12:01:15"}
|
||||
{"current_steps": 1080, "total_steps": 4039, "loss": 0.2829, "lr": 3.669214521314886e-05, "epoch": 1.8725065047701648, "percentage": 26.74, "elapsed_time": "4:22:42", "remaining_time": "11:59:45"}
|
||||
{"current_steps": 1085, "total_steps": 4039, "loss": 0.3148, "lr": 3.664438202514184e-05, "epoch": 1.881179531656548, "percentage": 26.86, "elapsed_time": "4:23:56", "remaining_time": "11:58:36"}
|
||||
{"current_steps": 1090, "total_steps": 4039, "loss": 0.3124, "lr": 3.659630802503094e-05, "epoch": 1.8898525585429313, "percentage": 26.99, "elapsed_time": "4:25:07", "remaining_time": "11:57:18"}
|
||||
{"current_steps": 1095, "total_steps": 4039, "loss": 0.3278, "lr": 3.6547924110535335e-05, "epoch": 1.8985255854293148, "percentage": 27.11, "elapsed_time": "4:26:26", "remaining_time": "11:56:22"}
|
||||
{"current_steps": 1100, "total_steps": 4039, "loss": 0.2792, "lr": 3.6499231185161466e-05, "epoch": 1.9071986123156983, "percentage": 27.23, "elapsed_time": "4:27:40", "remaining_time": "11:55:10"}
|
||||
{"current_steps": 1105, "total_steps": 4039, "loss": 0.3002, "lr": 3.645023015818614e-05, "epoch": 1.9158716392020816, "percentage": 27.36, "elapsed_time": "4:28:51", "remaining_time": "11:53:52"}
|
||||
{"current_steps": 1110, "total_steps": 4039, "loss": 0.3311, "lr": 3.640092194463957e-05, "epoch": 1.9245446660884649, "percentage": 27.48, "elapsed_time": "4:30:00", "remaining_time": "11:52:28"}
|
||||
{"current_steps": 1115, "total_steps": 4039, "loss": 0.2905, "lr": 3.635130746528826e-05, "epoch": 1.9332176929748481, "percentage": 27.61, "elapsed_time": "4:31:08", "remaining_time": "11:51:01"}
|
||||
{"current_steps": 1120, "total_steps": 4039, "loss": 0.3008, "lr": 3.6301387646617826e-05, "epoch": 1.9418907198612314, "percentage": 27.73, "elapsed_time": "4:32:25", "remaining_time": "11:50:01"}
|
||||
{"current_steps": 1125, "total_steps": 4039, "loss": 0.2803, "lr": 3.625116342081573e-05, "epoch": 1.950563746747615, "percentage": 27.85, "elapsed_time": "4:33:40", "remaining_time": "11:48:51"}
|
||||
{"current_steps": 1130, "total_steps": 4039, "loss": 0.2935, "lr": 3.6200635725753804e-05, "epoch": 1.9592367736339984, "percentage": 27.98, "elapsed_time": "4:34:52", "remaining_time": "11:47:36"}
|
||||
{"current_steps": 1135, "total_steps": 4039, "loss": 0.3222, "lr": 3.6149805504970785e-05, "epoch": 1.9679098005203817, "percentage": 28.1, "elapsed_time": "4:36:06", "remaining_time": "11:46:28"}
|
||||
{"current_steps": 1140, "total_steps": 4039, "loss": 0.322, "lr": 3.6098673707654685e-05, "epoch": 1.976582827406765, "percentage": 28.22, "elapsed_time": "4:37:18", "remaining_time": "11:45:10"}
|
||||
{"current_steps": 1145, "total_steps": 4039, "loss": 0.3141, "lr": 3.6047241288625076e-05, "epoch": 1.9852558542931482, "percentage": 28.35, "elapsed_time": "4:38:22", "remaining_time": "11:43:35"}
|
||||
{"current_steps": 1150, "total_steps": 4039, "loss": 0.2629, "lr": 3.599550920831521e-05, "epoch": 1.9939288811795317, "percentage": 28.47, "elapsed_time": "4:39:42", "remaining_time": "11:42:39"}
|
||||
{"current_steps": 1155, "total_steps": 4039, "loss": 0.2875, "lr": 3.594347843275418e-05, "epoch": 2.0017346053772767, "percentage": 28.6, "elapsed_time": "4:40:51", "remaining_time": "11:41:17"}
|
||||
{"current_steps": 1160, "total_steps": 4039, "loss": 0.3026, "lr": 3.589114993354876e-05, "epoch": 2.01040763226366, "percentage": 28.72, "elapsed_time": "4:41:54", "remaining_time": "11:39:40"}
|
||||
{"current_steps": 1165, "total_steps": 4039, "loss": 0.2594, "lr": 3.583852468786536e-05, "epoch": 2.019080659150043, "percentage": 28.84, "elapsed_time": "4:42:56", "remaining_time": "11:37:59"}
|
||||
{"current_steps": 1170, "total_steps": 4039, "loss": 0.2907, "lr": 3.5785603678411733e-05, "epoch": 2.027753686036427, "percentage": 28.97, "elapsed_time": "4:44:09", "remaining_time": "11:36:47"}
|
||||
{"current_steps": 1175, "total_steps": 4039, "loss": 0.2666, "lr": 3.573238789341866e-05, "epoch": 2.03642671292281, "percentage": 29.09, "elapsed_time": "4:45:16", "remaining_time": "11:35:20"}
|
||||
{"current_steps": 1180, "total_steps": 4039, "loss": 0.2768, "lr": 3.567887832662143e-05, "epoch": 2.0450997398091935, "percentage": 29.22, "elapsed_time": "4:46:30", "remaining_time": "11:34:10"}
|
||||
{"current_steps": 1185, "total_steps": 4039, "loss": 0.3217, "lr": 3.5625075977241356e-05, "epoch": 2.0537727666955767, "percentage": 29.34, "elapsed_time": "4:47:47", "remaining_time": "11:33:07"}
|
||||
{"current_steps": 1190, "total_steps": 4039, "loss": 0.2723, "lr": 3.557098184996705e-05, "epoch": 2.06244579358196, "percentage": 29.46, "elapsed_time": "4:48:56", "remaining_time": "11:31:46"}
|
||||
{"current_steps": 1195, "total_steps": 4039, "loss": 0.3095, "lr": 3.551659695493573e-05, "epoch": 2.0711188204683433, "percentage": 29.59, "elapsed_time": "4:50:09", "remaining_time": "11:30:33"}
|
||||
{"current_steps": 1200, "total_steps": 4039, "loss": 0.308, "lr": 3.546192230771431e-05, "epoch": 2.079791847354727, "percentage": 29.71, "elapsed_time": "4:51:22", "remaining_time": "11:29:20"}
|
||||
{"current_steps": 1205, "total_steps": 4039, "loss": 0.2666, "lr": 3.5406958929280436e-05, "epoch": 2.0884648742411103, "percentage": 29.83, "elapsed_time": "4:52:38", "remaining_time": "11:28:14"}
|
||||
{"current_steps": 1210, "total_steps": 4039, "loss": 0.3098, "lr": 3.535170784600344e-05, "epoch": 2.0971379011274935, "percentage": 29.96, "elapsed_time": "4:53:55", "remaining_time": "11:27:12"}
|
||||
{"current_steps": 1215, "total_steps": 4039, "loss": 0.3068, "lr": 3.529617008962518e-05, "epoch": 2.105810928013877, "percentage": 30.08, "elapsed_time": "4:55:08", "remaining_time": "11:25:59"}
|
||||
{"current_steps": 1220, "total_steps": 4039, "loss": 0.2915, "lr": 3.5240346697240735e-05, "epoch": 2.11448395490026, "percentage": 30.21, "elapsed_time": "4:56:28", "remaining_time": "11:25:01"}
|
||||
{"current_steps": 1225, "total_steps": 4039, "loss": 0.2742, "lr": 3.518423871127909e-05, "epoch": 2.1231569817866434, "percentage": 30.33, "elapsed_time": "4:57:39", "remaining_time": "11:23:44"}
|
||||
{"current_steps": 1230, "total_steps": 4039, "loss": 0.2878, "lr": 3.512784717948361e-05, "epoch": 2.131830008673027, "percentage": 30.45, "elapsed_time": "4:58:50", "remaining_time": "11:22:27"}
|
||||
{"current_steps": 1235, "total_steps": 4039, "loss": 0.2828, "lr": 3.507117315489255e-05, "epoch": 2.1405030355594103, "percentage": 30.58, "elapsed_time": "5:00:00", "remaining_time": "11:21:08"}
|
||||
{"current_steps": 1240, "total_steps": 4039, "loss": 0.2762, "lr": 3.501421769581931e-05, "epoch": 2.1491760624457936, "percentage": 30.7, "elapsed_time": "5:01:19", "remaining_time": "11:20:09"}
|
||||
{"current_steps": 1245, "total_steps": 4039, "loss": 0.2951, "lr": 3.495698186583275e-05, "epoch": 2.157849089332177, "percentage": 30.82, "elapsed_time": "5:02:33", "remaining_time": "11:18:58"}
|
||||
{"current_steps": 1250, "total_steps": 4039, "loss": 0.2839, "lr": 3.489946673373724e-05, "epoch": 2.16652211621856, "percentage": 30.95, "elapsed_time": "5:03:44", "remaining_time": "11:17:41"}
|
||||
{"current_steps": 1255, "total_steps": 4039, "loss": 0.2434, "lr": 3.48416733735528e-05, "epoch": 2.1751951431049434, "percentage": 31.07, "elapsed_time": "5:04:48", "remaining_time": "11:16:10"}
|
||||
{"current_steps": 1260, "total_steps": 4039, "loss": 0.256, "lr": 3.4783602864494974e-05, "epoch": 2.183868169991327, "percentage": 31.2, "elapsed_time": "5:06:00", "remaining_time": "11:14:54"}
|
||||
{"current_steps": 1265, "total_steps": 4039, "loss": 0.2944, "lr": 3.472525629095471e-05, "epoch": 2.1925411968777104, "percentage": 31.32, "elapsed_time": "5:07:16", "remaining_time": "11:13:48"}
|
||||
{"current_steps": 1270, "total_steps": 4039, "loss": 0.2765, "lr": 3.466663474247809e-05, "epoch": 2.2012142237640937, "percentage": 31.44, "elapsed_time": "5:08:28", "remaining_time": "11:12:34"}
|
||||
{"current_steps": 1275, "total_steps": 4039, "loss": 0.2871, "lr": 3.460773931374599e-05, "epoch": 2.209887250650477, "percentage": 31.57, "elapsed_time": "5:09:36", "remaining_time": "11:11:11"}
|
||||
{"current_steps": 1280, "total_steps": 4039, "loss": 0.3199, "lr": 3.454857110455366e-05, "epoch": 2.2185602775368602, "percentage": 31.69, "elapsed_time": "5:10:46", "remaining_time": "11:09:51"}
|
||||
{"current_steps": 1285, "total_steps": 4039, "loss": 0.2921, "lr": 3.448913121979015e-05, "epoch": 2.2272333044232435, "percentage": 31.81, "elapsed_time": "5:12:01", "remaining_time": "11:08:44"}
|
||||
{"current_steps": 1290, "total_steps": 4039, "loss": 0.2793, "lr": 3.44294207694177e-05, "epoch": 2.2359063313096272, "percentage": 31.94, "elapsed_time": "5:13:11", "remaining_time": "11:07:25"}
|
||||
{"current_steps": 1295, "total_steps": 4039, "loss": 0.2884, "lr": 3.4369440868451035e-05, "epoch": 2.2445793581960105, "percentage": 32.06, "elapsed_time": "5:14:26", "remaining_time": "11:06:15"}
|
||||
{"current_steps": 1300, "total_steps": 4039, "loss": 0.267, "lr": 3.430919263693648e-05, "epoch": 2.253252385082394, "percentage": 32.19, "elapsed_time": "5:15:38", "remaining_time": "11:05:02"}
|
||||
{"current_steps": 1305, "total_steps": 4039, "loss": 0.2868, "lr": 3.42486771999311e-05, "epoch": 2.261925411968777, "percentage": 32.31, "elapsed_time": "5:16:58", "remaining_time": "11:04:03"}
|
||||
{"current_steps": 1310, "total_steps": 4039, "loss": 0.2851, "lr": 3.4187895687481686e-05, "epoch": 2.2705984388551603, "percentage": 32.43, "elapsed_time": "5:18:16", "remaining_time": "11:03:01"}
|
||||
{"current_steps": 1315, "total_steps": 4039, "loss": 0.2948, "lr": 3.412684923460362e-05, "epoch": 2.2792714657415436, "percentage": 32.56, "elapsed_time": "5:19:28", "remaining_time": "11:01:46"}
|
||||
{"current_steps": 1320, "total_steps": 4039, "loss": 0.284, "lr": 3.40655389812597e-05, "epoch": 2.2879444926279273, "percentage": 32.68, "elapsed_time": "5:20:40", "remaining_time": "11:00:32"}
|
||||
{"current_steps": 1325, "total_steps": 4039, "loss": 0.2584, "lr": 3.400396607233888e-05, "epoch": 2.2966175195143106, "percentage": 32.81, "elapsed_time": "5:21:47", "remaining_time": "10:59:07"}
|
||||
{"current_steps": 1330, "total_steps": 4039, "loss": 0.3005, "lr": 3.394213165763485e-05, "epoch": 2.305290546400694, "percentage": 32.93, "elapsed_time": "5:23:03", "remaining_time": "10:58:00"}
|
||||
{"current_steps": 1335, "total_steps": 4039, "loss": 0.305, "lr": 3.388003689182455e-05, "epoch": 2.313963573287077, "percentage": 33.05, "elapsed_time": "5:24:14", "remaining_time": "10:56:44"}
|
||||
{"current_steps": 1340, "total_steps": 4039, "loss": 0.2936, "lr": 3.381768293444668e-05, "epoch": 2.3226366001734604, "percentage": 33.18, "elapsed_time": "5:25:33", "remaining_time": "10:55:44"}
|
||||
{"current_steps": 1345, "total_steps": 4039, "loss": 0.3028, "lr": 3.375507094987998e-05, "epoch": 2.331309627059844, "percentage": 33.3, "elapsed_time": "5:26:44", "remaining_time": "10:54:27"}
|
||||
{"current_steps": 1350, "total_steps": 4039, "loss": 0.2781, "lr": 3.369220210732152e-05, "epoch": 2.3399826539462274, "percentage": 33.42, "elapsed_time": "5:28:02", "remaining_time": "10:53:24"}
|
||||
{"current_steps": 1355, "total_steps": 4039, "loss": 0.2762, "lr": 3.3629077580764864e-05, "epoch": 2.3486556808326107, "percentage": 33.55, "elapsed_time": "5:29:23", "remaining_time": "10:52:26"}
|
||||
{"current_steps": 1360, "total_steps": 4039, "loss": 0.3026, "lr": 3.356569854897811e-05, "epoch": 2.357328707718994, "percentage": 33.67, "elapsed_time": "5:30:38", "remaining_time": "10:51:19"}
|
||||
{"current_steps": 1365, "total_steps": 4039, "loss": 0.2959, "lr": 3.3502066195481956e-05, "epoch": 2.366001734605377, "percentage": 33.8, "elapsed_time": "5:31:57", "remaining_time": "10:50:18"}
|
||||
{"current_steps": 1370, "total_steps": 4039, "loss": 0.2779, "lr": 3.3438181708527505e-05, "epoch": 2.3746747614917605, "percentage": 33.92, "elapsed_time": "5:33:13", "remaining_time": "10:49:10"}
|
||||
{"current_steps": 1375, "total_steps": 4039, "loss": 0.2622, "lr": 3.3374046281074163e-05, "epoch": 2.3833477883781438, "percentage": 34.04, "elapsed_time": "5:34:28", "remaining_time": "10:48:00"}
|
||||
{"current_steps": 1380, "total_steps": 4039, "loss": 0.303, "lr": 3.3309661110767295e-05, "epoch": 2.3920208152645275, "percentage": 34.17, "elapsed_time": "5:35:30", "remaining_time": "10:46:27"}
|
||||
{"current_steps": 1385, "total_steps": 4039, "loss": 0.328, "lr": 3.32450273999159e-05, "epoch": 2.4006938421509108, "percentage": 34.29, "elapsed_time": "5:36:35", "remaining_time": "10:45:00"}
|
||||
{"current_steps": 1390, "total_steps": 4039, "loss": 0.3133, "lr": 3.318014635547013e-05, "epoch": 2.409366869037294, "percentage": 34.41, "elapsed_time": "5:37:50", "remaining_time": "10:43:50"}
|
||||
{"current_steps": 1395, "total_steps": 4039, "loss": 0.3208, "lr": 3.311501918899881e-05, "epoch": 2.4180398959236773, "percentage": 34.54, "elapsed_time": "5:38:56", "remaining_time": "10:42:24"}
|
||||
{"current_steps": 1400, "total_steps": 4039, "loss": 0.2933, "lr": 3.3049647116666725e-05, "epoch": 2.4267129228100606, "percentage": 34.66, "elapsed_time": "5:40:12", "remaining_time": "10:41:17"}
|
||||
{"current_steps": 1405, "total_steps": 4039, "loss": 0.284, "lr": 3.298403135921199e-05, "epoch": 2.4353859496964443, "percentage": 34.79, "elapsed_time": "5:41:25", "remaining_time": "10:40:05"}
|
||||
{"current_steps": 1410, "total_steps": 4039, "loss": 0.3055, "lr": 3.291817314192319e-05, "epoch": 2.4440589765828276, "percentage": 34.91, "elapsed_time": "5:42:41", "remaining_time": "10:38:57"}
|
||||
{"current_steps": 1415, "total_steps": 4039, "loss": 0.2591, "lr": 3.2852073694616575e-05, "epoch": 2.452732003469211, "percentage": 35.03, "elapsed_time": "5:43:51", "remaining_time": "10:37:40"}
|
||||
{"current_steps": 1420, "total_steps": 4039, "loss": 0.2509, "lr": 3.278573425161301e-05, "epoch": 2.461405030355594, "percentage": 35.16, "elapsed_time": "5:45:04", "remaining_time": "10:36:27"}
|
||||
{"current_steps": 1425, "total_steps": 4039, "loss": 0.3087, "lr": 3.271915605171499e-05, "epoch": 2.4700780572419774, "percentage": 35.28, "elapsed_time": "5:46:21", "remaining_time": "10:35:21"}
|
||||
{"current_steps": 1430, "total_steps": 4039, "loss": 0.2844, "lr": 3.265234033818347e-05, "epoch": 2.4787510841283606, "percentage": 35.4, "elapsed_time": "5:47:32", "remaining_time": "10:34:04"}
|
||||
{"current_steps": 1435, "total_steps": 4039, "loss": 0.3292, "lr": 3.2585288358714674e-05, "epoch": 2.487424111014744, "percentage": 35.53, "elapsed_time": "5:48:46", "remaining_time": "10:32:54"}
|
||||
{"current_steps": 1440, "total_steps": 4039, "loss": 0.3009, "lr": 3.251800136541677e-05, "epoch": 2.4960971379011276, "percentage": 35.65, "elapsed_time": "5:50:04", "remaining_time": "10:31:49"}
|
||||
{"current_steps": 1445, "total_steps": 4039, "loss": 0.2669, "lr": 3.245048061478652e-05, "epoch": 2.504770164787511, "percentage": 35.78, "elapsed_time": "5:51:17", "remaining_time": "10:30:37"}
|
||||
{"current_steps": 1450, "total_steps": 4039, "loss": 0.2852, "lr": 3.2382727367685765e-05, "epoch": 2.513443191673894, "percentage": 35.9, "elapsed_time": "5:52:27", "remaining_time": "10:29:18"}
|
||||
{"current_steps": 1455, "total_steps": 4039, "loss": 0.2585, "lr": 3.231474288931796e-05, "epoch": 2.5221162185602775, "percentage": 36.02, "elapsed_time": "5:53:41", "remaining_time": "10:28:08"}
|
||||
{"current_steps": 1460, "total_steps": 4039, "loss": 0.2907, "lr": 3.224652844920449e-05, "epoch": 2.5307892454466607, "percentage": 36.15, "elapsed_time": "5:54:48", "remaining_time": "10:26:44"}
|
||||
{"current_steps": 1465, "total_steps": 4039, "loss": 0.2829, "lr": 3.217808532116094e-05, "epoch": 2.5394622723330444, "percentage": 36.27, "elapsed_time": "5:56:02", "remaining_time": "10:25:33"}
|
||||
{"current_steps": 1470, "total_steps": 4039, "loss": 0.2537, "lr": 3.210941478327338e-05, "epoch": 2.5481352992194277, "percentage": 36.4, "elapsed_time": "5:57:18", "remaining_time": "10:24:26"}
|
||||
{"current_steps": 1475, "total_steps": 4039, "loss": 0.2958, "lr": 3.2040518117874455e-05, "epoch": 2.556808326105811, "percentage": 36.52, "elapsed_time": "5:58:30", "remaining_time": "10:23:11"}
|
||||
{"current_steps": 1480, "total_steps": 4039, "loss": 0.2706, "lr": 3.197139661151943e-05, "epoch": 2.5654813529921943, "percentage": 36.64, "elapsed_time": "5:59:48", "remaining_time": "10:22:08"}
|
||||
{"current_steps": 1485, "total_steps": 4039, "loss": 0.2662, "lr": 3.19020515549622e-05, "epoch": 2.5741543798785775, "percentage": 36.77, "elapsed_time": "6:00:57", "remaining_time": "10:20:47"}
|
||||
{"current_steps": 1490, "total_steps": 4039, "loss": 0.2858, "lr": 3.183248424313116e-05, "epoch": 2.582827406764961, "percentage": 36.89, "elapsed_time": "6:01:56", "remaining_time": "10:19:10"}
|
||||
{"current_steps": 1495, "total_steps": 4039, "loss": 0.3145, "lr": 3.176269597510503e-05, "epoch": 2.591500433651344, "percentage": 37.01, "elapsed_time": "6:03:12", "remaining_time": "10:18:03"}
|
||||
{"current_steps": 1500, "total_steps": 4039, "loss": 0.2898, "lr": 3.169268805408861e-05, "epoch": 2.600173460537728, "percentage": 37.14, "elapsed_time": "6:04:18", "remaining_time": "10:16:39"}
|
||||
{"current_steps": 1505, "total_steps": 4039, "loss": 0.2745, "lr": 3.162246178738843e-05, "epoch": 2.608846487424111, "percentage": 37.26, "elapsed_time": "6:06:00", "remaining_time": "10:16:15"}
|
||||
{"current_steps": 1510, "total_steps": 4039, "loss": 0.2988, "lr": 3.1552018486388315e-05, "epoch": 2.6175195143104943, "percentage": 37.39, "elapsed_time": "6:07:15", "remaining_time": "10:15:06"}
|
||||
{"current_steps": 1515, "total_steps": 4039, "loss": 0.2503, "lr": 3.148135946652496e-05, "epoch": 2.6261925411968776, "percentage": 37.51, "elapsed_time": "6:08:18", "remaining_time": "10:13:36"}
|
||||
{"current_steps": 1520, "total_steps": 4039, "loss": 0.2325, "lr": 3.14104860472633e-05, "epoch": 2.634865568083261, "percentage": 37.63, "elapsed_time": "6:09:37", "remaining_time": "10:12:32"}
|
||||
{"current_steps": 1525, "total_steps": 4039, "loss": 0.2835, "lr": 3.1339399552071915e-05, "epoch": 2.6435385949696446, "percentage": 37.76, "elapsed_time": "6:10:53", "remaining_time": "10:11:25"}
|
||||
{"current_steps": 1530, "total_steps": 4039, "loss": 0.3078, "lr": 3.1268101308398295e-05, "epoch": 2.652211621856028, "percentage": 37.88, "elapsed_time": "6:12:08", "remaining_time": "10:10:16"}
|
||||
{"current_steps": 1535, "total_steps": 4039, "loss": 0.2708, "lr": 3.119659264764405e-05, "epoch": 2.660884648742411, "percentage": 38.0, "elapsed_time": "6:13:25", "remaining_time": "10:09:09"}
|
||||
{"current_steps": 1540, "total_steps": 4039, "loss": 0.2743, "lr": 3.112487490514006e-05, "epoch": 2.6695576756287944, "percentage": 38.13, "elapsed_time": "6:14:37", "remaining_time": "10:07:54"}
|
||||
{"current_steps": 1545, "total_steps": 4039, "loss": 0.2919, "lr": 3.1052949420121535e-05, "epoch": 2.6782307025151777, "percentage": 38.25, "elapsed_time": "6:15:49", "remaining_time": "10:06:40"}
|
||||
{"current_steps": 1550, "total_steps": 4039, "loss": 0.3226, "lr": 3.098081753570301e-05, "epoch": 2.6869037294015614, "percentage": 38.38, "elapsed_time": "6:17:01", "remaining_time": "10:05:25"}
|
||||
{"current_steps": 1555, "total_steps": 4039, "loss": 0.2701, "lr": 3.090848059885325e-05, "epoch": 2.6955767562879442, "percentage": 38.5, "elapsed_time": "6:18:17", "remaining_time": "10:04:18"}
|
||||
{"current_steps": 1560, "total_steps": 4039, "loss": 0.2367, "lr": 3.083593996037011e-05, "epoch": 2.704249783174328, "percentage": 38.62, "elapsed_time": "6:19:31", "remaining_time": "10:03:05"}
|
||||
{"current_steps": 1565, "total_steps": 4039, "loss": 0.2944, "lr": 3.07631969748553e-05, "epoch": 2.7129228100607112, "percentage": 38.75, "elapsed_time": "6:20:44", "remaining_time": "10:01:53"}
|
||||
{"current_steps": 1570, "total_steps": 4039, "loss": 0.2943, "lr": 3.069025300068911e-05, "epoch": 2.7215958369470945, "percentage": 38.87, "elapsed_time": "6:21:56", "remaining_time": "10:00:39"}
|
||||
{"current_steps": 1575, "total_steps": 4039, "loss": 0.3063, "lr": 3.061710940000502e-05, "epoch": 2.7302688638334778, "percentage": 38.99, "elapsed_time": "6:23:09", "remaining_time": "9:59:25"}
|
||||
{"current_steps": 1580, "total_steps": 4039, "loss": 0.2726, "lr": 3.054376753866429e-05, "epoch": 2.738941890719861, "percentage": 39.12, "elapsed_time": "6:24:16", "remaining_time": "9:58:03"}
|
||||
{"current_steps": 1585, "total_steps": 4039, "loss": 0.2766, "lr": 3.0470228786230403e-05, "epoch": 2.7476149176062448, "percentage": 39.24, "elapsed_time": "6:25:13", "remaining_time": "9:56:25"}
|
||||
{"current_steps": 1590, "total_steps": 4039, "loss": 0.3213, "lr": 3.0396494515943577e-05, "epoch": 2.756287944492628, "percentage": 39.37, "elapsed_time": "6:26:22", "remaining_time": "9:55:07"}
|
||||
{"current_steps": 1595, "total_steps": 4039, "loss": 0.2803, "lr": 3.032256610469503e-05, "epoch": 2.7649609713790113, "percentage": 39.49, "elapsed_time": "6:27:37", "remaining_time": "9:53:57"}
|
||||
{"current_steps": 1600, "total_steps": 4039, "loss": 0.2693, "lr": 3.024844493300133e-05, "epoch": 2.7736339982653946, "percentage": 39.61, "elapsed_time": "6:28:44", "remaining_time": "9:52:35"}
|
||||
{"current_steps": 1605, "total_steps": 4039, "loss": 0.3093, "lr": 3.0174132384978576e-05, "epoch": 2.782307025151778, "percentage": 39.74, "elapsed_time": "6:29:51", "remaining_time": "9:51:12"}
|
||||
{"current_steps": 1610, "total_steps": 4039, "loss": 0.2813, "lr": 3.0099629848316597e-05, "epoch": 2.7909800520381616, "percentage": 39.86, "elapsed_time": "6:31:02", "remaining_time": "9:49:57"}
|
||||
{"current_steps": 1615, "total_steps": 4039, "loss": 0.2979, "lr": 3.0024938714252993e-05, "epoch": 2.7996530789245444, "percentage": 39.99, "elapsed_time": "6:32:16", "remaining_time": "9:48:46"}
|
||||
{"current_steps": 1620, "total_steps": 4039, "loss": 0.2902, "lr": 2.995006037754717e-05, "epoch": 2.808326105810928, "percentage": 40.11, "elapsed_time": "6:33:33", "remaining_time": "9:47:39"}
|
||||
{"current_steps": 1625, "total_steps": 4039, "loss": 0.2805, "lr": 2.9874996236454313e-05, "epoch": 2.8169991326973114, "percentage": 40.23, "elapsed_time": "6:34:43", "remaining_time": "9:46:22"}
|
||||
{"current_steps": 1630, "total_steps": 4039, "loss": 0.2851, "lr": 2.9799747692699252e-05, "epoch": 2.8256721595836947, "percentage": 40.36, "elapsed_time": "6:36:02", "remaining_time": "9:45:18"}
|
||||
{"current_steps": 1635, "total_steps": 4039, "loss": 0.2542, "lr": 2.97243161514503e-05, "epoch": 2.834345186470078, "percentage": 40.48, "elapsed_time": "6:37:15", "remaining_time": "9:44:06"}
|
||||
{"current_steps": 1640, "total_steps": 4039, "loss": 0.2978, "lr": 2.9648703021293017e-05, "epoch": 2.843018213356461, "percentage": 40.6, "elapsed_time": "6:38:22", "remaining_time": "9:42:45"}
|
||||
{"current_steps": 1645, "total_steps": 4039, "loss": 0.2881, "lr": 2.957290971420388e-05, "epoch": 2.851691240242845, "percentage": 40.73, "elapsed_time": "6:39:36", "remaining_time": "9:41:33"}
|
||||
{"current_steps": 1650, "total_steps": 4039, "loss": 0.2711, "lr": 2.9496937645523948e-05, "epoch": 2.860364267129228, "percentage": 40.85, "elapsed_time": "6:40:56", "remaining_time": "9:40:30"}
|
||||
{"current_steps": 1655, "total_steps": 4039, "loss": 0.3009, "lr": 2.9420788233932413e-05, "epoch": 2.8690372940156115, "percentage": 40.98, "elapsed_time": "6:42:05", "remaining_time": "9:39:11"}
|
||||
{"current_steps": 1660, "total_steps": 4039, "loss": 0.2873, "lr": 2.9344462901420133e-05, "epoch": 2.8777103209019947, "percentage": 41.1, "elapsed_time": "6:43:16", "remaining_time": "9:37:56"}
|
||||
{"current_steps": 1665, "total_steps": 4039, "loss": 0.2928, "lr": 2.9267963073263028e-05, "epoch": 2.886383347788378, "percentage": 41.22, "elapsed_time": "6:44:30", "remaining_time": "9:36:45"}
|
||||
{"current_steps": 1670, "total_steps": 4039, "loss": 0.293, "lr": 2.9191290177995516e-05, "epoch": 2.8950563746747617, "percentage": 41.35, "elapsed_time": "6:45:42", "remaining_time": "9:35:31"}
|
||||
{"current_steps": 1675, "total_steps": 4039, "loss": 0.2726, "lr": 2.9114445647383826e-05, "epoch": 2.9037294015611446, "percentage": 41.47, "elapsed_time": "6:47:02", "remaining_time": "9:34:27"}
|
||||
{"current_steps": 1680, "total_steps": 4039, "loss": 0.2812, "lr": 2.903743091639922e-05, "epoch": 2.9124024284475283, "percentage": 41.59, "elapsed_time": "6:48:14", "remaining_time": "9:33:13"}
|
||||
{"current_steps": 1685, "total_steps": 4039, "loss": 0.2964, "lr": 2.8960247423191273e-05, "epoch": 2.9210754553339116, "percentage": 41.72, "elapsed_time": "6:49:30", "remaining_time": "9:32:05"}
|
||||
{"current_steps": 1690, "total_steps": 4039, "loss": 0.2475, "lr": 2.8882896609060935e-05, "epoch": 2.929748482220295, "percentage": 41.84, "elapsed_time": "6:50:46", "remaining_time": "9:30:57"}
|
||||
{"current_steps": 1695, "total_steps": 4039, "loss": 0.3088, "lr": 2.880537991843369e-05, "epoch": 2.938421509106678, "percentage": 41.97, "elapsed_time": "6:51:57", "remaining_time": "9:29:41"}
|
||||
{"current_steps": 1700, "total_steps": 4039, "loss": 0.2797, "lr": 2.8727698798832508e-05, "epoch": 2.9470945359930614, "percentage": 42.09, "elapsed_time": "6:53:05", "remaining_time": "9:28:22"}
|
||||
{"current_steps": 1705, "total_steps": 4039, "loss": 0.2909, "lr": 2.8649854700850903e-05, "epoch": 2.955767562879445, "percentage": 42.21, "elapsed_time": "6:54:21", "remaining_time": "9:27:13"}
|
||||
{"current_steps": 1710, "total_steps": 4039, "loss": 0.3026, "lr": 2.8571849078125756e-05, "epoch": 2.9644405897658284, "percentage": 42.34, "elapsed_time": "6:55:32", "remaining_time": "9:25:57"}
|
||||
{"current_steps": 1715, "total_steps": 4039, "loss": 0.3212, "lr": 2.849368338731024e-05, "epoch": 2.9731136166522116, "percentage": 42.46, "elapsed_time": "6:56:49", "remaining_time": "9:24:50"}
|
||||
{"current_steps": 1720, "total_steps": 4039, "loss": 0.2651, "lr": 2.8415359088046578e-05, "epoch": 2.981786643538595, "percentage": 42.58, "elapsed_time": "6:58:02", "remaining_time": "9:23:37"}
|
||||
{"current_steps": 1725, "total_steps": 4039, "loss": 0.2811, "lr": 2.8336877642938804e-05, "epoch": 2.990459670424978, "percentage": 42.71, "elapsed_time": "6:59:16", "remaining_time": "9:22:26"}
|
||||
{"current_steps": 1730, "total_steps": 4039, "loss": 0.2805, "lr": 2.8258240517525438e-05, "epoch": 2.999132697311362, "percentage": 42.83, "elapsed_time": "7:00:31", "remaining_time": "9:21:15"}
|
||||
{"current_steps": 1735, "total_steps": 4039, "loss": 0.3004, "lr": 2.8179449180252122e-05, "epoch": 3.0069384215091066, "percentage": 42.96, "elapsed_time": "7:01:43", "remaining_time": "9:20:01"}
|
||||
{"current_steps": 1740, "total_steps": 4039, "loss": 0.3022, "lr": 2.810050510244423e-05, "epoch": 3.01561144839549, "percentage": 43.08, "elapsed_time": "7:02:55", "remaining_time": "9:18:47"}
|
||||
{"current_steps": 1745, "total_steps": 4039, "loss": 0.3141, "lr": 2.8021409758279338e-05, "epoch": 3.024284475281873, "percentage": 43.2, "elapsed_time": "7:04:12", "remaining_time": "9:17:40"}
|
||||
{"current_steps": 1750, "total_steps": 4039, "loss": 0.2869, "lr": 2.7942164624759728e-05, "epoch": 3.032957502168257, "percentage": 43.33, "elapsed_time": "7:05:25", "remaining_time": "9:16:26"}
|
||||
{"current_steps": 1755, "total_steps": 4039, "loss": 0.2602, "lr": 2.7862771181684824e-05, "epoch": 3.04163052905464, "percentage": 43.45, "elapsed_time": "7:06:42", "remaining_time": "9:15:20"}
|
||||
{"current_steps": 1760, "total_steps": 4039, "loss": 0.2813, "lr": 2.7783230911623503e-05, "epoch": 3.0503035559410234, "percentage": 43.58, "elapsed_time": "7:07:54", "remaining_time": "9:14:05"}
|
||||
{"current_steps": 1765, "total_steps": 4039, "loss": 0.2484, "lr": 2.7703545299886475e-05, "epoch": 3.0589765828274067, "percentage": 43.7, "elapsed_time": "7:09:03", "remaining_time": "9:12:48"}
|
||||
{"current_steps": 1770, "total_steps": 4039, "loss": 0.262, "lr": 2.762371583449851e-05, "epoch": 3.06764960971379, "percentage": 43.82, "elapsed_time": "7:10:17", "remaining_time": "9:11:35"}
|
||||
{"current_steps": 1775, "total_steps": 4039, "loss": 0.2796, "lr": 2.754374400617063e-05, "epoch": 3.0763226366001737, "percentage": 43.95, "elapsed_time": "7:11:33", "remaining_time": "9:10:26"}
|
||||
{"current_steps": 1780, "total_steps": 4039, "loss": 0.2568, "lr": 2.746363130827234e-05, "epoch": 3.084995663486557, "percentage": 44.07, "elapsed_time": "7:12:43", "remaining_time": "9:09:10"}
|
||||
{"current_steps": 1785, "total_steps": 4039, "loss": 0.2597, "lr": 2.738337923680367e-05, "epoch": 3.0936686903729402, "percentage": 44.19, "elapsed_time": "7:13:55", "remaining_time": "9:07:56"}
|
||||
{"current_steps": 1790, "total_steps": 4039, "loss": 0.2585, "lr": 2.730298929036728e-05, "epoch": 3.1023417172593235, "percentage": 44.32, "elapsed_time": "7:15:15", "remaining_time": "9:06:51"}
|
||||
{"current_steps": 1795, "total_steps": 4039, "loss": 0.2632, "lr": 2.7222462970140467e-05, "epoch": 3.111014744145707, "percentage": 44.44, "elapsed_time": "7:16:26", "remaining_time": "9:05:37"}
|
||||
{"current_steps": 1800, "total_steps": 4039, "loss": 0.2517, "lr": 2.7141801779847132e-05, "epoch": 3.11968777103209, "percentage": 44.57, "elapsed_time": "7:17:31", "remaining_time": "9:04:14"}
|
||||
{"current_steps": 1805, "total_steps": 4039, "loss": 0.2762, "lr": 2.7061007225729693e-05, "epoch": 3.1283607979184733, "percentage": 44.69, "elapsed_time": "7:18:39", "remaining_time": "9:02:54"}
|
||||
{"current_steps": 1810, "total_steps": 4039, "loss": 0.2834, "lr": 2.6980080816520962e-05, "epoch": 3.137033824804857, "percentage": 44.81, "elapsed_time": "7:19:55", "remaining_time": "9:01:46"}
|
||||
{"current_steps": 1815, "total_steps": 4039, "loss": 0.2704, "lr": 2.6899024063415975e-05, "epoch": 3.1457068516912403, "percentage": 44.94, "elapsed_time": "7:20:58", "remaining_time": "9:00:21"}
|
||||
{"current_steps": 1820, "total_steps": 4039, "loss": 0.2538, "lr": 2.681783848004378e-05, "epoch": 3.1543798785776236, "percentage": 45.06, "elapsed_time": "7:22:18", "remaining_time": "8:59:16"}
|
||||
{"current_steps": 1825, "total_steps": 4039, "loss": 0.2663, "lr": 2.6736525582439135e-05, "epoch": 3.163052905464007, "percentage": 45.18, "elapsed_time": "7:23:30", "remaining_time": "8:58:02"}
|
||||
{"current_steps": 1830, "total_steps": 4039, "loss": 0.2765, "lr": 2.665508688901427e-05, "epoch": 3.17172593235039, "percentage": 45.31, "elapsed_time": "7:24:40", "remaining_time": "8:56:46"}
|
||||
{"current_steps": 1835, "total_steps": 4039, "loss": 0.2677, "lr": 2.657352392053043e-05, "epoch": 3.180398959236774, "percentage": 45.43, "elapsed_time": "7:25:49", "remaining_time": "8:55:28"}
|
||||
{"current_steps": 1840, "total_steps": 4039, "loss": 0.2511, "lr": 2.649183820006959e-05, "epoch": 3.189071986123157, "percentage": 45.56, "elapsed_time": "7:27:03", "remaining_time": "8:54:17"}
|
||||
{"current_steps": 1845, "total_steps": 4039, "loss": 0.2955, "lr": 2.6410031253005913e-05, "epoch": 3.1977450130095404, "percentage": 45.68, "elapsed_time": "7:28:20", "remaining_time": "8:53:09"}
|
||||
{"current_steps": 1850, "total_steps": 4039, "loss": 0.2898, "lr": 2.6328104606977346e-05, "epoch": 3.2064180398959237, "percentage": 45.8, "elapsed_time": "7:29:35", "remaining_time": "8:51:58"}
|
||||
{"current_steps": 1855, "total_steps": 4039, "loss": 0.2521, "lr": 2.6246059791857032e-05, "epoch": 3.215091066782307, "percentage": 45.93, "elapsed_time": "7:30:42", "remaining_time": "8:50:39"}
|
||||
{"current_steps": 1860, "total_steps": 4039, "loss": 0.2756, "lr": 2.6163898339724796e-05, "epoch": 3.22376409366869, "percentage": 46.05, "elapsed_time": "7:31:55", "remaining_time": "8:49:25"}
|
||||
{"current_steps": 1865, "total_steps": 4039, "loss": 0.2971, "lr": 2.608162178483846e-05, "epoch": 3.232437120555074, "percentage": 46.17, "elapsed_time": "7:33:04", "remaining_time": "8:48:08"}
|
||||
{"current_steps": 1870, "total_steps": 4039, "loss": 0.2755, "lr": 2.5999231663605294e-05, "epoch": 3.241110147441457, "percentage": 46.3, "elapsed_time": "7:34:05", "remaining_time": "8:46:41"}
|
||||
{"current_steps": 1875, "total_steps": 4039, "loss": 0.2469, "lr": 2.591672951455323e-05, "epoch": 3.2497831743278405, "percentage": 46.42, "elapsed_time": "7:35:06", "remaining_time": "8:45:14"}
|
||||
{"current_steps": 1880, "total_steps": 4039, "loss": 0.254, "lr": 2.5834116878302203e-05, "epoch": 3.2584562012142237, "percentage": 46.55, "elapsed_time": "7:36:20", "remaining_time": "8:44:04"}
|
||||
{"current_steps": 1885, "total_steps": 4039, "loss": 0.2677, "lr": 2.5751395297535327e-05, "epoch": 3.267129228100607, "percentage": 46.67, "elapsed_time": "7:37:30", "remaining_time": "8:42:48"}
|
||||
{"current_steps": 1890, "total_steps": 4039, "loss": 0.2456, "lr": 2.5668566316970128e-05, "epoch": 3.2758022549869903, "percentage": 46.79, "elapsed_time": "7:38:50", "remaining_time": "8:41:43"}
|
||||
{"current_steps": 1895, "total_steps": 4039, "loss": 0.3015, "lr": 2.5585631483329677e-05, "epoch": 3.284475281873374, "percentage": 46.92, "elapsed_time": "7:40:03", "remaining_time": "8:40:30"}
|
||||
{"current_steps": 1900, "total_steps": 4039, "loss": 0.2597, "lr": 2.5502592345313723e-05, "epoch": 3.2931483087597573, "percentage": 47.04, "elapsed_time": "7:41:22", "remaining_time": "8:39:24"}
|
||||
{"current_steps": 1905, "total_steps": 4039, "loss": 0.2888, "lr": 2.5419450453569744e-05, "epoch": 3.3018213356461406, "percentage": 47.17, "elapsed_time": "7:42:40", "remaining_time": "8:38:17"}
|
||||
{"current_steps": 1910, "total_steps": 4039, "loss": 0.2978, "lr": 2.5336207360664022e-05, "epoch": 3.310494362532524, "percentage": 47.29, "elapsed_time": "7:43:50", "remaining_time": "8:37:01"}
|
||||
{"current_steps": 1915, "total_steps": 4039, "loss": 0.2596, "lr": 2.5252864621052643e-05, "epoch": 3.319167389418907, "percentage": 47.41, "elapsed_time": "7:45:07", "remaining_time": "8:35:52"}
|
||||
{"current_steps": 1920, "total_steps": 4039, "loss": 0.2853, "lr": 2.5169423791052455e-05, "epoch": 3.3278404163052904, "percentage": 47.54, "elapsed_time": "7:46:20", "remaining_time": "8:34:40"}
|
||||
{"current_steps": 1925, "total_steps": 4039, "loss": 0.2459, "lr": 2.5085886428812024e-05, "epoch": 3.3365134431916736, "percentage": 47.66, "elapsed_time": "7:47:33", "remaining_time": "8:33:27"}
|
||||
{"current_steps": 1930, "total_steps": 4039, "loss": 0.242, "lr": 2.500225409428252e-05, "epoch": 3.3451864700780574, "percentage": 47.78, "elapsed_time": "7:48:48", "remaining_time": "8:32:16"}
|
||||
{"current_steps": 1935, "total_steps": 4039, "loss": 0.2582, "lr": 2.4918528349188606e-05, "epoch": 3.3538594969644406, "percentage": 47.91, "elapsed_time": "7:50:02", "remaining_time": "8:31:06"}
|
||||
{"current_steps": 1940, "total_steps": 4039, "loss": 0.2693, "lr": 2.4834710756999263e-05, "epoch": 3.362532523850824, "percentage": 48.03, "elapsed_time": "7:51:15", "remaining_time": "8:29:53"}
|
||||
{"current_steps": 1945, "total_steps": 4039, "loss": 0.2767, "lr": 2.475080288289859e-05, "epoch": 3.371205550737207, "percentage": 48.16, "elapsed_time": "7:52:16", "remaining_time": "8:28:27"}
|
||||
{"current_steps": 1950, "total_steps": 4039, "loss": 0.267, "lr": 2.46668062937566e-05, "epoch": 3.3798785776235905, "percentage": 48.28, "elapsed_time": "7:53:27", "remaining_time": "8:27:12"}
|
||||
{"current_steps": 1955, "total_steps": 4039, "loss": 0.2704, "lr": 2.458272255809992e-05, "epoch": 3.388551604509974, "percentage": 48.4, "elapsed_time": "7:54:40", "remaining_time": "8:25:59"}
|
||||
{"current_steps": 1960, "total_steps": 4039, "loss": 0.26, "lr": 2.4498553246082537e-05, "epoch": 3.3972246313963574, "percentage": 48.53, "elapsed_time": "7:55:47", "remaining_time": "8:24:40"}
|
||||
{"current_steps": 1965, "total_steps": 4039, "loss": 0.3315, "lr": 2.441429992945647e-05, "epoch": 3.4058976582827407, "percentage": 48.65, "elapsed_time": "7:56:54", "remaining_time": "8:23:21"}
|
||||
{"current_steps": 1970, "total_steps": 4039, "loss": 0.3227, "lr": 2.4329964181542404e-05, "epoch": 3.414570685169124, "percentage": 48.77, "elapsed_time": "7:58:05", "remaining_time": "8:22:07"}
|
||||
{"current_steps": 1975, "total_steps": 4039, "loss": 0.248, "lr": 2.4245547577200328e-05, "epoch": 3.4232437120555073, "percentage": 48.9, "elapsed_time": "7:59:09", "remaining_time": "8:20:44"}
|
||||
{"current_steps": 1980, "total_steps": 4039, "loss": 0.2434, "lr": 2.416105169280011e-05, "epoch": 3.4319167389418905, "percentage": 49.02, "elapsed_time": "8:00:19", "remaining_time": "8:19:28"}
|
||||
{"current_steps": 1985, "total_steps": 4039, "loss": 0.2956, "lr": 2.407647810619208e-05, "epoch": 3.4405897658282742, "percentage": 49.15, "elapsed_time": "8:01:30", "remaining_time": "8:18:15"}
|
||||
{"current_steps": 1990, "total_steps": 4039, "loss": 0.2755, "lr": 2.3991828396677553e-05, "epoch": 3.4492627927146575, "percentage": 49.27, "elapsed_time": "8:02:45", "remaining_time": "8:17:03"}
|
||||
{"current_steps": 1995, "total_steps": 4039, "loss": 0.2892, "lr": 2.3907104144979333e-05, "epoch": 3.457935819601041, "percentage": 49.39, "elapsed_time": "8:04:00", "remaining_time": "8:15:53"}
|
||||
{"current_steps": 2000, "total_steps": 4039, "loss": 0.2395, "lr": 2.382230693321221e-05, "epoch": 3.466608846487424, "percentage": 49.52, "elapsed_time": "8:05:15", "remaining_time": "8:14:43"}
|
||||
{"current_steps": 2005, "total_steps": 4039, "loss": 0.2458, "lr": 2.3737438344853406e-05, "epoch": 3.4752818733738073, "percentage": 49.64, "elapsed_time": "8:06:25", "remaining_time": "8:13:27"}
|
||||
{"current_steps": 2010, "total_steps": 4039, "loss": 0.2844, "lr": 2.3652499964713e-05, "epoch": 3.4839549002601906, "percentage": 49.76, "elapsed_time": "8:07:36", "remaining_time": "8:12:12"}
|
||||
{"current_steps": 2015, "total_steps": 4039, "loss": 0.2665, "lr": 2.3567493378904355e-05, "epoch": 3.4926279271465743, "percentage": 49.89, "elapsed_time": "8:08:47", "remaining_time": "8:10:58"}
|
||||
{"current_steps": 2020, "total_steps": 4039, "loss": 0.2265, "lr": 2.348242017481448e-05, "epoch": 3.5013009540329576, "percentage": 50.01, "elapsed_time": "8:10:06", "remaining_time": "8:09:51"}
|
||||
{"current_steps": 2025, "total_steps": 4039, "loss": 0.2421, "lr": 2.339728194107439e-05, "epoch": 3.509973980919341, "percentage": 50.14, "elapsed_time": "8:11:24", "remaining_time": "8:08:44"}
|
||||
{"current_steps": 2030, "total_steps": 4039, "loss": 0.2551, "lr": 2.3312080267529443e-05, "epoch": 3.518647007805724, "percentage": 50.26, "elapsed_time": "8:12:30", "remaining_time": "8:07:24"}
|
||||
{"current_steps": 2035, "total_steps": 4039, "loss": 0.2699, "lr": 2.3226816745209653e-05, "epoch": 3.5273200346921074, "percentage": 50.38, "elapsed_time": "8:13:44", "remaining_time": "8:06:12"}
|
||||
{"current_steps": 2040, "total_steps": 4039, "loss": 0.2982, "lr": 2.3141492966299994e-05, "epoch": 3.535993061578491, "percentage": 50.51, "elapsed_time": "8:14:59", "remaining_time": "8:05:02"}
|
||||
{"current_steps": 2045, "total_steps": 4039, "loss": 0.2425, "lr": 2.3056110524110637e-05, "epoch": 3.544666088464874, "percentage": 50.63, "elapsed_time": "8:16:19", "remaining_time": "8:03:57"}
|
||||
{"current_steps": 2050, "total_steps": 4039, "loss": 0.2556, "lr": 2.29706710130472e-05, "epoch": 3.5533391153512577, "percentage": 50.76, "elapsed_time": "8:17:30", "remaining_time": "8:02:42"}
|
||||
{"current_steps": 2055, "total_steps": 4039, "loss": 0.301, "lr": 2.2885176028581023e-05, "epoch": 3.562012142237641, "percentage": 50.88, "elapsed_time": "8:18:45", "remaining_time": "8:01:31"}
|
||||
{"current_steps": 2060, "total_steps": 4039, "loss": 0.2525, "lr": 2.279962716721932e-05, "epoch": 3.5706851691240242, "percentage": 51.0, "elapsed_time": "8:19:59", "remaining_time": "8:00:19"}
|
||||
{"current_steps": 2065, "total_steps": 4039, "loss": 0.2536, "lr": 2.271402602647538e-05, "epoch": 3.5793581960104075, "percentage": 51.13, "elapsed_time": "8:21:10", "remaining_time": "7:59:05"}
|
||||
{"current_steps": 2070, "total_steps": 4039, "loss": 0.2439, "lr": 2.2628374204838747e-05, "epoch": 3.5880312228967908, "percentage": 51.25, "elapsed_time": "8:22:18", "remaining_time": "7:57:48"}
|
||||
{"current_steps": 2075, "total_steps": 4039, "loss": 0.281, "lr": 2.2542673301745374e-05, "epoch": 3.5967042497831745, "percentage": 51.37, "elapsed_time": "8:23:29", "remaining_time": "7:56:33"}
|
||||
{"current_steps": 2080, "total_steps": 4039, "loss": 0.2751, "lr": 2.2456924917547733e-05, "epoch": 3.6053772766695578, "percentage": 51.5, "elapsed_time": "8:24:47", "remaining_time": "7:55:25"}
|
||||
{"current_steps": 2085, "total_steps": 4039, "loss": 0.2798, "lr": 2.237113065348495e-05, "epoch": 3.614050303555941, "percentage": 51.62, "elapsed_time": "8:26:05", "remaining_time": "7:54:17"}
|
||||
{"current_steps": 2090, "total_steps": 4039, "loss": 0.2637, "lr": 2.2285292111652884e-05, "epoch": 3.6227233304423243, "percentage": 51.75, "elapsed_time": "8:27:17", "remaining_time": "7:53:03"}
|
||||
{"current_steps": 2095, "total_steps": 4039, "loss": 0.287, "lr": 2.2199410894974257e-05, "epoch": 3.6313963573287076, "percentage": 51.87, "elapsed_time": "8:28:33", "remaining_time": "7:51:54"}
|
||||
{"current_steps": 2100, "total_steps": 4039, "loss": 0.2689, "lr": 2.2113488607168644e-05, "epoch": 3.6400693842150913, "percentage": 51.99, "elapsed_time": "8:29:52", "remaining_time": "7:50:47"}
|
||||
{"current_steps": 2105, "total_steps": 4039, "loss": 0.2718, "lr": 2.2027526852722606e-05, "epoch": 3.6487424111014746, "percentage": 52.12, "elapsed_time": "8:31:11", "remaining_time": "7:49:40"}
|
||||
{"current_steps": 2110, "total_steps": 4039, "loss": 0.3016, "lr": 2.1941527236859683e-05, "epoch": 3.657415437987858, "percentage": 52.24, "elapsed_time": "8:32:15", "remaining_time": "7:48:19"}
|
||||
{"current_steps": 2115, "total_steps": 4039, "loss": 0.2978, "lr": 2.1855491365510404e-05, "epoch": 3.666088464874241, "percentage": 52.36, "elapsed_time": "8:33:21", "remaining_time": "7:47:00"}
|
||||
{"current_steps": 2120, "total_steps": 4039, "loss": 0.2593, "lr": 2.176942084528236e-05, "epoch": 3.6747614917606244, "percentage": 52.49, "elapsed_time": "8:34:34", "remaining_time": "7:45:47"}
|
||||
{"current_steps": 2125, "total_steps": 4039, "loss": 0.2733, "lr": 2.168331728343013e-05, "epoch": 3.6834345186470077, "percentage": 52.61, "elapsed_time": "8:35:45", "remaining_time": "7:44:33"}
|
||||
{"current_steps": 2130, "total_steps": 4039, "loss": 0.2471, "lr": 2.159718228782532e-05, "epoch": 3.692107545533391, "percentage": 52.74, "elapsed_time": "8:37:03", "remaining_time": "7:43:24"}
|
||||
{"current_steps": 2135, "total_steps": 4039, "loss": 0.2351, "lr": 2.151101746692653e-05, "epoch": 3.7007805724197746, "percentage": 52.86, "elapsed_time": "8:38:17", "remaining_time": "7:42:12"}
|
||||
{"current_steps": 2140, "total_steps": 4039, "loss": 0.2626, "lr": 2.142482442974928e-05, "epoch": 3.709453599306158, "percentage": 52.98, "elapsed_time": "8:39:33", "remaining_time": "7:41:02"}
|
||||
{"current_steps": 2145, "total_steps": 4039, "loss": 0.2727, "lr": 2.1338604785836013e-05, "epoch": 3.718126626192541, "percentage": 53.11, "elapsed_time": "8:40:43", "remaining_time": "7:39:47"}
|
||||
{"current_steps": 2150, "total_steps": 4039, "loss": 0.2558, "lr": 2.1252360145226022e-05, "epoch": 3.7267996530789245, "percentage": 53.23, "elapsed_time": "8:41:52", "remaining_time": "7:38:31"}
|
||||
{"current_steps": 2155, "total_steps": 4039, "loss": 0.2963, "lr": 2.1166092118425355e-05, "epoch": 3.7354726799653077, "percentage": 53.35, "elapsed_time": "8:43:05", "remaining_time": "7:37:18"}
|
||||
{"current_steps": 2160, "total_steps": 4039, "loss": 0.2795, "lr": 2.1079802316376797e-05, "epoch": 3.7441457068516915, "percentage": 53.48, "elapsed_time": "8:44:20", "remaining_time": "7:36:07"}
|
||||
{"current_steps": 2165, "total_steps": 4039, "loss": 0.2819, "lr": 2.0993492350429737e-05, "epoch": 3.7528187337380747, "percentage": 53.6, "elapsed_time": "8:45:29", "remaining_time": "7:34:51"}
|
||||
{"current_steps": 2170, "total_steps": 4039, "loss": 0.253, "lr": 2.090716383231012e-05, "epoch": 3.761491760624458, "percentage": 53.73, "elapsed_time": "8:46:45", "remaining_time": "7:33:41"}
|
||||
{"current_steps": 2175, "total_steps": 4039, "loss": 0.2891, "lr": 2.082081837409029e-05, "epoch": 3.7701647875108413, "percentage": 53.85, "elapsed_time": "8:47:48", "remaining_time": "7:32:20"}
|
||||
{"current_steps": 2180, "total_steps": 4039, "loss": 0.27, "lr": 2.0734457588158965e-05, "epoch": 3.7788378143972245, "percentage": 53.97, "elapsed_time": "8:49:02", "remaining_time": "7:31:08"}
|
||||
{"current_steps": 2185, "total_steps": 4039, "loss": 0.2785, "lr": 2.064808308719107e-05, "epoch": 3.787510841283608, "percentage": 54.1, "elapsed_time": "8:50:18", "remaining_time": "7:29:58"}
|
||||
{"current_steps": 2190, "total_steps": 4039, "loss": 0.2302, "lr": 2.0561696484117638e-05, "epoch": 3.796183868169991, "percentage": 54.22, "elapsed_time": "8:51:33", "remaining_time": "7:28:47"}
|
||||
{"current_steps": 2195, "total_steps": 4039, "loss": 0.2364, "lr": 2.0475299392095703e-05, "epoch": 3.804856895056375, "percentage": 54.35, "elapsed_time": "8:52:46", "remaining_time": "7:27:35"}
|
||||
{"current_steps": 2200, "total_steps": 4039, "loss": 0.2779, "lr": 2.0388893424478152e-05, "epoch": 3.813529921942758, "percentage": 54.47, "elapsed_time": "8:53:50", "remaining_time": "7:26:14"}
|
||||
{"current_steps": 2205, "total_steps": 4039, "loss": 0.2677, "lr": 2.030248019478364e-05, "epoch": 3.8222029488291414, "percentage": 54.59, "elapsed_time": "8:55:05", "remaining_time": "7:25:03"}
|
||||
{"current_steps": 2210, "total_steps": 4039, "loss": 0.2624, "lr": 2.0216061316666386e-05, "epoch": 3.8308759757155246, "percentage": 54.72, "elapsed_time": "8:56:16", "remaining_time": "7:23:49"}
|
||||
{"current_steps": 2215, "total_steps": 4039, "loss": 0.2895, "lr": 2.012963840388613e-05, "epoch": 3.839549002601908, "percentage": 54.84, "elapsed_time": "8:57:29", "remaining_time": "7:22:36"}
|
||||
{"current_steps": 2220, "total_steps": 4039, "loss": 0.2779, "lr": 2.004321307027793e-05, "epoch": 3.8482220294882916, "percentage": 54.96, "elapsed_time": "8:58:31", "remaining_time": "7:21:15"}
|
||||
{"current_steps": 2225, "total_steps": 4039, "loss": 0.2755, "lr": 1.9956786929722072e-05, "epoch": 3.856895056374675, "percentage": 55.09, "elapsed_time": "8:59:44", "remaining_time": "7:20:02"}
|
||||
{"current_steps": 2230, "total_steps": 4039, "loss": 0.242, "lr": 1.9870361596113872e-05, "epoch": 3.865568083261058, "percentage": 55.21, "elapsed_time": "9:00:59", "remaining_time": "7:18:51"}
|
||||
{"current_steps": 2235, "total_steps": 4039, "loss": 0.2597, "lr": 1.9783938683333618e-05, "epoch": 3.8742411101474414, "percentage": 55.34, "elapsed_time": "9:02:12", "remaining_time": "7:17:39"}
|
||||
{"current_steps": 2240, "total_steps": 4039, "loss": 0.2797, "lr": 1.9697519805216375e-05, "epoch": 3.8829141370338247, "percentage": 55.46, "elapsed_time": "9:03:31", "remaining_time": "7:16:31"}
|
||||
{"current_steps": 2245, "total_steps": 4039, "loss": 0.2407, "lr": 1.9611106575521844e-05, "epoch": 3.8915871639202084, "percentage": 55.58, "elapsed_time": "9:04:46", "remaining_time": "7:15:19"}
|
||||
{"current_steps": 2250, "total_steps": 4039, "loss": 0.2442, "lr": 1.95247006079043e-05, "epoch": 3.9002601908065913, "percentage": 55.71, "elapsed_time": "9:05:54", "remaining_time": "7:14:03"}
|
||||
{"current_steps": 2255, "total_steps": 4039, "loss": 0.2964, "lr": 1.943830351588237e-05, "epoch": 3.908933217692975, "percentage": 55.83, "elapsed_time": "9:07:08", "remaining_time": "7:12:51"}
|
||||
{"current_steps": 2260, "total_steps": 4039, "loss": 0.2645, "lr": 1.9351916912808936e-05, "epoch": 3.9176062445793582, "percentage": 55.95, "elapsed_time": "9:08:23", "remaining_time": "7:11:40"}
|
||||
{"current_steps": 2265, "total_steps": 4039, "loss": 0.2534, "lr": 1.926554241184104e-05, "epoch": 3.9262792714657415, "percentage": 56.08, "elapsed_time": "9:09:33", "remaining_time": "7:10:25"}
|
||||
{"current_steps": 2270, "total_steps": 4039, "loss": 0.2765, "lr": 1.9179181625909717e-05, "epoch": 3.934952298352125, "percentage": 56.2, "elapsed_time": "9:10:44", "remaining_time": "7:09:11"}
|
||||
{"current_steps": 2275, "total_steps": 4039, "loss": 0.2821, "lr": 1.9092836167689887e-05, "epoch": 3.943625325238508, "percentage": 56.33, "elapsed_time": "9:11:57", "remaining_time": "7:07:58"}
|
||||
{"current_steps": 2280, "total_steps": 4039, "loss": 0.2856, "lr": 1.9006507649570266e-05, "epoch": 3.952298352124892, "percentage": 56.45, "elapsed_time": "9:13:07", "remaining_time": "7:06:43"}
|
||||
{"current_steps": 2285, "total_steps": 4039, "loss": 0.2942, "lr": 1.8920197683623203e-05, "epoch": 3.960971379011275, "percentage": 56.57, "elapsed_time": "9:14:20", "remaining_time": "7:05:30"}
|
||||
{"current_steps": 2290, "total_steps": 4039, "loss": 0.2655, "lr": 1.8833907881574648e-05, "epoch": 3.9696444058976583, "percentage": 56.7, "elapsed_time": "9:15:28", "remaining_time": "7:04:14"}
|
||||
{"current_steps": 2295, "total_steps": 4039, "loss": 0.2554, "lr": 1.874763985477399e-05, "epoch": 3.9783174327840416, "percentage": 56.82, "elapsed_time": "9:16:37", "remaining_time": "7:02:59"}
|
||||
{"current_steps": 2300, "total_steps": 4039, "loss": 0.2683, "lr": 1.866139521416399e-05, "epoch": 3.986990459670425, "percentage": 56.94, "elapsed_time": "9:17:57", "remaining_time": "7:01:51"}
|
||||
{"current_steps": 2305, "total_steps": 4039, "loss": 0.2586, "lr": 1.8575175570250728e-05, "epoch": 3.9956634865568086, "percentage": 57.07, "elapsed_time": "9:19:10", "remaining_time": "7:00:39"}
|
||||
{"current_steps": 2310, "total_steps": 4039, "loss": 0.2666, "lr": 1.8488982533073483e-05, "epoch": 4.003469210754553, "percentage": 57.19, "elapsed_time": "9:20:15", "remaining_time": "6:59:20"}
|
||||
{"current_steps": 2315, "total_steps": 4039, "loss": 0.2368, "lr": 1.840281771217468e-05, "epoch": 4.012142237640937, "percentage": 57.32, "elapsed_time": "9:21:27", "remaining_time": "6:58:07"}
|
||||
{"current_steps": 2320, "total_steps": 4039, "loss": 0.2812, "lr": 1.8316682716569878e-05, "epoch": 4.02081526452732, "percentage": 57.44, "elapsed_time": "9:22:39", "remaining_time": "6:56:54"}
|
||||
{"current_steps": 2325, "total_steps": 4039, "loss": 0.2585, "lr": 1.8230579154717653e-05, "epoch": 4.029488291413704, "percentage": 57.56, "elapsed_time": "9:23:48", "remaining_time": "6:55:38"}
|
||||
{"current_steps": 2330, "total_steps": 4039, "loss": 0.2307, "lr": 1.8144508634489603e-05, "epoch": 4.038161318300086, "percentage": 57.69, "elapsed_time": "9:25:03", "remaining_time": "6:54:27"}
|
||||
{"current_steps": 2335, "total_steps": 4039, "loss": 0.2537, "lr": 1.8058472763140324e-05, "epoch": 4.04683434518647, "percentage": 57.81, "elapsed_time": "9:26:18", "remaining_time": "6:53:16"}
|
||||
{"current_steps": 2340, "total_steps": 4039, "loss": 0.288, "lr": 1.7972473147277394e-05, "epoch": 4.055507372072854, "percentage": 57.94, "elapsed_time": "9:27:27", "remaining_time": "6:52:00"}
|
||||
{"current_steps": 2345, "total_steps": 4039, "loss": 0.2362, "lr": 1.788651139283136e-05, "epoch": 4.064180398959237, "percentage": 58.06, "elapsed_time": "9:28:34", "remaining_time": "6:50:43"}
|
||||
{"current_steps": 2350, "total_steps": 4039, "loss": 0.2699, "lr": 1.7800589105025757e-05, "epoch": 4.07285342584562, "percentage": 58.18, "elapsed_time": "9:29:44", "remaining_time": "6:49:29"}
|
||||
{"current_steps": 2355, "total_steps": 4039, "loss": 0.257, "lr": 1.771470788834712e-05, "epoch": 4.081526452732003, "percentage": 58.31, "elapsed_time": "9:31:00", "remaining_time": "6:48:18"}
|
||||
{"current_steps": 2360, "total_steps": 4039, "loss": 0.2476, "lr": 1.762886934651506e-05, "epoch": 4.090199479618387, "percentage": 58.43, "elapsed_time": "9:32:04", "remaining_time": "6:46:59"}
|
||||
{"current_steps": 2365, "total_steps": 4039, "loss": 0.2733, "lr": 1.7543075082452277e-05, "epoch": 4.09887250650477, "percentage": 58.55, "elapsed_time": "9:33:11", "remaining_time": "6:45:42"}
|
||||
{"current_steps": 2370, "total_steps": 4039, "loss": 0.2465, "lr": 1.745732669825463e-05, "epoch": 4.1075455333911535, "percentage": 58.68, "elapsed_time": "9:34:28", "remaining_time": "6:44:33"}
|
||||
{"current_steps": 2375, "total_steps": 4039, "loss": 0.2397, "lr": 1.737162579516126e-05, "epoch": 4.116218560277537, "percentage": 58.8, "elapsed_time": "9:35:41", "remaining_time": "6:43:21"}
|
||||
{"current_steps": 2380, "total_steps": 4039, "loss": 0.3036, "lr": 1.728597397352463e-05, "epoch": 4.12489158716392, "percentage": 58.93, "elapsed_time": "9:36:47", "remaining_time": "6:42:03"}
|
||||
{"current_steps": 2385, "total_steps": 4039, "loss": 0.2803, "lr": 1.7200372832780685e-05, "epoch": 4.133564614050304, "percentage": 59.05, "elapsed_time": "9:38:02", "remaining_time": "6:40:52"}
|
||||
{"current_steps": 2390, "total_steps": 4039, "loss": 0.2591, "lr": 1.711482397141898e-05, "epoch": 4.142237640936687, "percentage": 59.17, "elapsed_time": "9:39:19", "remaining_time": "6:39:42"}
|
||||
{"current_steps": 2395, "total_steps": 4039, "loss": 0.2567, "lr": 1.7029328986952805e-05, "epoch": 4.15091066782307, "percentage": 59.3, "elapsed_time": "9:40:33", "remaining_time": "6:38:30"}
|
||||
{"current_steps": 2400, "total_steps": 4039, "loss": 0.2544, "lr": 1.6943889475889373e-05, "epoch": 4.159583694709454, "percentage": 59.42, "elapsed_time": "9:41:51", "remaining_time": "6:37:21"}
|
||||
{"current_steps": 2405, "total_steps": 4039, "loss": 0.2351, "lr": 1.6858507033700013e-05, "epoch": 4.168256721595837, "percentage": 59.54, "elapsed_time": "9:43:05", "remaining_time": "6:36:09"}
|
||||
{"current_steps": 2410, "total_steps": 4039, "loss": 0.2598, "lr": 1.6773183254790347e-05, "epoch": 4.1769297484822205, "percentage": 59.67, "elapsed_time": "9:44:17", "remaining_time": "6:34:56"}
|
||||
{"current_steps": 2415, "total_steps": 4039, "loss": 0.2457, "lr": 1.6687919732470564e-05, "epoch": 4.185602775368603, "percentage": 59.79, "elapsed_time": "9:45:33", "remaining_time": "6:33:45"}
|
||||
{"current_steps": 2420, "total_steps": 4039, "loss": 0.2235, "lr": 1.660271805892562e-05, "epoch": 4.194275802254987, "percentage": 59.92, "elapsed_time": "9:46:44", "remaining_time": "6:32:32"}
|
||||
{"current_steps": 2425, "total_steps": 4039, "loss": 0.2996, "lr": 1.651757982518552e-05, "epoch": 4.20294882914137, "percentage": 60.04, "elapsed_time": "9:48:01", "remaining_time": "6:31:22"}
|
||||
{"current_steps": 2430, "total_steps": 4039, "loss": 0.2669, "lr": 1.643250662109565e-05, "epoch": 4.211621856027754, "percentage": 60.16, "elapsed_time": "9:49:08", "remaining_time": "6:30:05"}
|
||||
{"current_steps": 2435, "total_steps": 4039, "loss": 0.2454, "lr": 1.634750003528701e-05, "epoch": 4.220294882914137, "percentage": 60.29, "elapsed_time": "9:50:12", "remaining_time": "6:28:46"}
|
||||
{"current_steps": 2440, "total_steps": 4039, "loss": 0.283, "lr": 1.62625616551466e-05, "epoch": 4.22896790980052, "percentage": 60.41, "elapsed_time": "9:51:23", "remaining_time": "6:27:33"}
|
||||
{"current_steps": 2445, "total_steps": 4039, "loss": 0.2713, "lr": 1.61776930667878e-05, "epoch": 4.237640936686904, "percentage": 60.53, "elapsed_time": "9:52:42", "remaining_time": "6:26:25"}
|
||||
{"current_steps": 2450, "total_steps": 4039, "loss": 0.2659, "lr": 1.609289585502067e-05, "epoch": 4.246313963573287, "percentage": 60.66, "elapsed_time": "9:53:54", "remaining_time": "6:25:11"}
|
||||
{"current_steps": 2455, "total_steps": 4039, "loss": 0.2602, "lr": 1.6008171603322453e-05, "epoch": 4.25498699045967, "percentage": 60.78, "elapsed_time": "9:55:07", "remaining_time": "6:23:59"}
|
||||
{"current_steps": 2460, "total_steps": 4039, "loss": 0.2682, "lr": 1.5923521893807928e-05, "epoch": 4.263660017346054, "percentage": 60.91, "elapsed_time": "9:56:24", "remaining_time": "6:22:48"}
|
||||
{"current_steps": 2465, "total_steps": 4039, "loss": 0.2227, "lr": 1.5838948307199896e-05, "epoch": 4.272333044232437, "percentage": 61.03, "elapsed_time": "9:57:38", "remaining_time": "6:21:36"}
|
||||
{"current_steps": 2470, "total_steps": 4039, "loss": 0.2362, "lr": 1.575445242279968e-05, "epoch": 4.281006071118821, "percentage": 61.15, "elapsed_time": "9:58:57", "remaining_time": "6:20:28"}
|
||||
{"current_steps": 2475, "total_steps": 4039, "loss": 0.2475, "lr": 1.5670035818457603e-05, "epoch": 4.2896790980052035, "percentage": 61.28, "elapsed_time": "10:00:08", "remaining_time": "6:19:14"}
|
||||
{"current_steps": 2480, "total_steps": 4039, "loss": 0.2518, "lr": 1.5585700070543535e-05, "epoch": 4.298352124891587, "percentage": 61.4, "elapsed_time": "10:01:25", "remaining_time": "6:18:04"}
|
||||
{"current_steps": 2485, "total_steps": 4039, "loss": 0.2602, "lr": 1.550144675391747e-05, "epoch": 4.307025151777971, "percentage": 61.53, "elapsed_time": "10:02:31", "remaining_time": "6:16:47"}
|
||||
{"current_steps": 2490, "total_steps": 4039, "loss": 0.2436, "lr": 1.5417277441900086e-05, "epoch": 4.315698178664354, "percentage": 61.65, "elapsed_time": "10:03:38", "remaining_time": "6:15:31"}
|
||||
{"current_steps": 2495, "total_steps": 4039, "loss": 0.226, "lr": 1.5333193706243405e-05, "epoch": 4.3243712055507375, "percentage": 61.77, "elapsed_time": "10:04:54", "remaining_time": "6:14:20"}
|
||||
{"current_steps": 2500, "total_steps": 4039, "loss": 0.2803, "lr": 1.5249197117101414e-05, "epoch": 4.33304423243712, "percentage": 61.9, "elapsed_time": "10:06:04", "remaining_time": "6:13:05"}
|
||||
{"current_steps": 2505, "total_steps": 4039, "loss": 0.2418, "lr": 1.5165289243000739e-05, "epoch": 4.341717259323504, "percentage": 62.02, "elapsed_time": "10:07:14", "remaining_time": "6:11:51"}
|
||||
{"current_steps": 2510, "total_steps": 4039, "loss": 0.2237, "lr": 1.5081471650811399e-05, "epoch": 4.350390286209887, "percentage": 62.14, "elapsed_time": "10:08:28", "remaining_time": "6:10:39"}
|
||||
{"current_steps": 2515, "total_steps": 4039, "loss": 0.233, "lr": 1.4997745905717489e-05, "epoch": 4.359063313096271, "percentage": 62.27, "elapsed_time": "10:09:44", "remaining_time": "6:09:28"}
|
||||
{"current_steps": 2520, "total_steps": 4039, "loss": 0.2745, "lr": 1.491411357118798e-05, "epoch": 4.367736339982654, "percentage": 62.39, "elapsed_time": "10:10:59", "remaining_time": "6:08:17"}
|
||||
{"current_steps": 2525, "total_steps": 4039, "loss": 0.2573, "lr": 1.4830576208947549e-05, "epoch": 4.376409366869037, "percentage": 62.52, "elapsed_time": "10:12:17", "remaining_time": "6:07:07"}
|
||||
{"current_steps": 2530, "total_steps": 4039, "loss": 0.2773, "lr": 1.4747135378947366e-05, "epoch": 4.385082393755421, "percentage": 62.64, "elapsed_time": "10:13:30", "remaining_time": "6:05:55"}
|
||||
{"current_steps": 2535, "total_steps": 4039, "loss": 0.2525, "lr": 1.4663792639335981e-05, "epoch": 4.393755420641804, "percentage": 62.76, "elapsed_time": "10:14:32", "remaining_time": "6:04:36"}
|
||||
{"current_steps": 2540, "total_steps": 4039, "loss": 0.2486, "lr": 1.4580549546430263e-05, "epoch": 4.402428447528187, "percentage": 62.89, "elapsed_time": "10:15:50", "remaining_time": "6:03:26"}
|
||||
{"current_steps": 2545, "total_steps": 4039, "loss": 0.2149, "lr": 1.4497407654686283e-05, "epoch": 4.41110147441457, "percentage": 63.01, "elapsed_time": "10:17:00", "remaining_time": "6:02:12"}
|
||||
{"current_steps": 2550, "total_steps": 4039, "loss": 0.2255, "lr": 1.4414368516670326e-05, "epoch": 4.419774501300954, "percentage": 63.13, "elapsed_time": "10:18:08", "remaining_time": "6:00:56"}
|
||||
{"current_steps": 2555, "total_steps": 4039, "loss": 0.2516, "lr": 1.4331433683029879e-05, "epoch": 4.428447528187338, "percentage": 63.26, "elapsed_time": "10:19:21", "remaining_time": "5:59:44"}
|
||||
{"current_steps": 2560, "total_steps": 4039, "loss": 0.2862, "lr": 1.4248604702464674e-05, "epoch": 4.4371205550737205, "percentage": 63.38, "elapsed_time": "10:20:34", "remaining_time": "5:58:31"}
|
||||
{"current_steps": 2565, "total_steps": 4039, "loss": 0.3068, "lr": 1.41658831216978e-05, "epoch": 4.445793581960104, "percentage": 63.51, "elapsed_time": "10:21:47", "remaining_time": "5:57:18"}
|
||||
{"current_steps": 2570, "total_steps": 4039, "loss": 0.2136, "lr": 1.4083270485446772e-05, "epoch": 4.454466608846487, "percentage": 63.63, "elapsed_time": "10:22:49", "remaining_time": "5:56:00"}
|
||||
{"current_steps": 2575, "total_steps": 4039, "loss": 0.2624, "lr": 1.4000768336394707e-05, "epoch": 4.463139635732871, "percentage": 63.75, "elapsed_time": "10:24:03", "remaining_time": "5:54:48"}
|
||||
{"current_steps": 2580, "total_steps": 4039, "loss": 0.2836, "lr": 1.3918378215161541e-05, "epoch": 4.4718126626192545, "percentage": 63.88, "elapsed_time": "10:25:20", "remaining_time": "5:53:37"}
|
||||
{"current_steps": 2585, "total_steps": 4039, "loss": 0.2915, "lr": 1.3836101660275215e-05, "epoch": 4.480485689505637, "percentage": 64.0, "elapsed_time": "10:26:34", "remaining_time": "5:52:25"}
|
||||
{"current_steps": 2590, "total_steps": 4039, "loss": 0.2724, "lr": 1.3753940208142966e-05, "epoch": 4.489158716392021, "percentage": 64.12, "elapsed_time": "10:27:53", "remaining_time": "5:51:16"}
|
||||
{"current_steps": 2595, "total_steps": 4039, "loss": 0.2925, "lr": 1.3671895393022659e-05, "epoch": 4.497831743278404, "percentage": 64.25, "elapsed_time": "10:29:03", "remaining_time": "5:50:02"}
|
||||
{"current_steps": 2600, "total_steps": 4039, "loss": 0.2559, "lr": 1.3589968746994095e-05, "epoch": 4.506504770164788, "percentage": 64.37, "elapsed_time": "10:30:16", "remaining_time": "5:48:50"}
|
||||
{"current_steps": 2605, "total_steps": 4039, "loss": 0.3043, "lr": 1.3508161799930416e-05, "epoch": 4.515177797051171, "percentage": 64.5, "elapsed_time": "10:31:36", "remaining_time": "5:47:41"}
|
||||
{"current_steps": 2610, "total_steps": 4039, "loss": 0.2341, "lr": 1.3426476079469577e-05, "epoch": 4.523850823937554, "percentage": 64.62, "elapsed_time": "10:32:48", "remaining_time": "5:46:28"}
|
||||
{"current_steps": 2615, "total_steps": 4039, "loss": 0.2446, "lr": 1.334491311098574e-05, "epoch": 4.532523850823938, "percentage": 64.74, "elapsed_time": "10:33:54", "remaining_time": "5:45:11"}
|
||||
{"current_steps": 2620, "total_steps": 4039, "loss": 0.2796, "lr": 1.3263474417560866e-05, "epoch": 4.541196877710321, "percentage": 64.87, "elapsed_time": "10:35:08", "remaining_time": "5:43:59"}
|
||||
{"current_steps": 2625, "total_steps": 4039, "loss": 0.2274, "lr": 1.3182161519956227e-05, "epoch": 4.549869904596704, "percentage": 64.99, "elapsed_time": "10:36:19", "remaining_time": "5:42:45"}
|
||||
{"current_steps": 2630, "total_steps": 4039, "loss": 0.2764, "lr": 1.3100975936584025e-05, "epoch": 4.558542931483087, "percentage": 65.12, "elapsed_time": "10:37:34", "remaining_time": "5:41:34"}
|
||||
{"current_steps": 2635, "total_steps": 4039, "loss": 0.2428, "lr": 1.3019919183479043e-05, "epoch": 4.567215958369471, "percentage": 65.24, "elapsed_time": "10:38:43", "remaining_time": "5:40:20"}
|
||||
{"current_steps": 2640, "total_steps": 4039, "loss": 0.268, "lr": 1.2938992774270316e-05, "epoch": 4.575888985255855, "percentage": 65.36, "elapsed_time": "10:39:57", "remaining_time": "5:39:07"}
|
||||
{"current_steps": 2645, "total_steps": 4039, "loss": 0.2155, "lr": 1.2858198220152872e-05, "epoch": 4.5845620121422375, "percentage": 65.49, "elapsed_time": "10:41:07", "remaining_time": "5:37:53"}
|
||||
{"current_steps": 2650, "total_steps": 4039, "loss": 0.2339, "lr": 1.2777537029859536e-05, "epoch": 4.593235039028621, "percentage": 65.61, "elapsed_time": "10:42:22", "remaining_time": "5:36:41"}
|
||||
{"current_steps": 2655, "total_steps": 4039, "loss": 0.2599, "lr": 1.2697010709632729e-05, "epoch": 4.601908065915004, "percentage": 65.73, "elapsed_time": "10:43:29", "remaining_time": "5:35:26"}
|
||||
{"current_steps": 2660, "total_steps": 4039, "loss": 0.2397, "lr": 1.2616620763196337e-05, "epoch": 4.610581092801388, "percentage": 65.86, "elapsed_time": "10:44:40", "remaining_time": "5:34:12"}
|
||||
{"current_steps": 2665, "total_steps": 4039, "loss": 0.2686, "lr": 1.2536368691727669e-05, "epoch": 4.6192541196877706, "percentage": 65.98, "elapsed_time": "10:45:46", "remaining_time": "5:32:56"}
|
||||
{"current_steps": 2670, "total_steps": 4039, "loss": 0.2185, "lr": 1.2456255993829371e-05, "epoch": 4.627927146574154, "percentage": 66.11, "elapsed_time": "10:46:50", "remaining_time": "5:31:39"}
|
||||
{"current_steps": 2675, "total_steps": 4039, "loss": 0.2329, "lr": 1.23762841655015e-05, "epoch": 4.636600173460538, "percentage": 66.23, "elapsed_time": "10:48:01", "remaining_time": "5:30:25"}
|
||||
{"current_steps": 2680, "total_steps": 4039, "loss": 0.2587, "lr": 1.2296454700113526e-05, "epoch": 4.645273200346921, "percentage": 66.35, "elapsed_time": "10:49:20", "remaining_time": "5:29:16"}
|
||||
{"current_steps": 2685, "total_steps": 4039, "loss": 0.2067, "lr": 1.22167690883765e-05, "epoch": 4.6539462272333045, "percentage": 66.48, "elapsed_time": "10:50:27", "remaining_time": "5:28:01"}
|
||||
{"current_steps": 2690, "total_steps": 4039, "loss": 0.2717, "lr": 1.2137228818315182e-05, "epoch": 4.662619254119688, "percentage": 66.6, "elapsed_time": "10:51:42", "remaining_time": "5:26:49"}
|
||||
{"current_steps": 2695, "total_steps": 4039, "loss": 0.273, "lr": 1.2057835375240277e-05, "epoch": 4.671292281006071, "percentage": 66.72, "elapsed_time": "10:52:44", "remaining_time": "5:25:31"}
|
||||
{"current_steps": 2700, "total_steps": 4039, "loss": 0.26, "lr": 1.1978590241720669e-05, "epoch": 4.679965307892455, "percentage": 66.85, "elapsed_time": "10:53:57", "remaining_time": "5:24:18"}
|
||||
{"current_steps": 2705, "total_steps": 4039, "loss": 0.2841, "lr": 1.189949489755578e-05, "epoch": 4.688638334778838, "percentage": 66.97, "elapsed_time": "10:55:15", "remaining_time": "5:23:08"}
|
||||
{"current_steps": 2710, "total_steps": 4039, "loss": 0.2381, "lr": 1.1820550819747885e-05, "epoch": 4.697311361665221, "percentage": 67.1, "elapsed_time": "10:56:21", "remaining_time": "5:21:52"}
|
||||
{"current_steps": 2715, "total_steps": 4039, "loss": 0.2721, "lr": 1.174175948247457e-05, "epoch": 4.705984388551604, "percentage": 67.22, "elapsed_time": "10:57:35", "remaining_time": "5:20:41"}
|
||||
{"current_steps": 2720, "total_steps": 4039, "loss": 0.2318, "lr": 1.1663122357061205e-05, "epoch": 4.714657415437988, "percentage": 67.34, "elapsed_time": "10:58:45", "remaining_time": "5:19:27"}
|
||||
{"current_steps": 2725, "total_steps": 4039, "loss": 0.2887, "lr": 1.1584640911953429e-05, "epoch": 4.723330442324372, "percentage": 67.47, "elapsed_time": "11:00:00", "remaining_time": "5:18:15"}
|
||||
{"current_steps": 2730, "total_steps": 4039, "loss": 0.2666, "lr": 1.1506316612689763e-05, "epoch": 4.732003469210754, "percentage": 67.59, "elapsed_time": "11:01:15", "remaining_time": "5:17:03"}
|
||||
{"current_steps": 2735, "total_steps": 4039, "loss": 0.2601, "lr": 1.1428150921874251e-05, "epoch": 4.740676496097138, "percentage": 67.71, "elapsed_time": "11:02:19", "remaining_time": "5:15:47"}
|
||||
{"current_steps": 2740, "total_steps": 4039, "loss": 0.2508, "lr": 1.1350145299149102e-05, "epoch": 4.749349522983521, "percentage": 67.84, "elapsed_time": "11:03:35", "remaining_time": "5:14:36"}
|
||||
{"current_steps": 2745, "total_steps": 4039, "loss": 0.2546, "lr": 1.1272301201167494e-05, "epoch": 4.758022549869905, "percentage": 67.96, "elapsed_time": "11:04:55", "remaining_time": "5:13:26"}
|
||||
{"current_steps": 2750, "total_steps": 4039, "loss": 0.2586, "lr": 1.1194620081566323e-05, "epoch": 4.7666955767562875, "percentage": 68.09, "elapsed_time": "11:06:05", "remaining_time": "5:12:12"}
|
||||
{"current_steps": 2755, "total_steps": 4039, "loss": 0.2709, "lr": 1.1117103390939064e-05, "epoch": 4.775368603642671, "percentage": 68.21, "elapsed_time": "11:07:21", "remaining_time": "5:11:01"}
|
||||
{"current_steps": 2760, "total_steps": 4039, "loss": 0.2427, "lr": 1.1039752576808733e-05, "epoch": 4.784041630529055, "percentage": 68.33, "elapsed_time": "11:08:34", "remaining_time": "5:09:49"}
|
||||
{"current_steps": 2765, "total_steps": 4039, "loss": 0.2373, "lr": 1.0962569083600782e-05, "epoch": 4.792714657415438, "percentage": 68.46, "elapsed_time": "11:09:50", "remaining_time": "5:08:38"}
|
||||
{"current_steps": 2770, "total_steps": 4039, "loss": 0.2426, "lr": 1.088555435261618e-05, "epoch": 4.8013876843018215, "percentage": 68.58, "elapsed_time": "11:11:07", "remaining_time": "5:07:27"}
|
||||
{"current_steps": 2775, "total_steps": 4039, "loss": 0.2714, "lr": 1.0808709822004486e-05, "epoch": 4.810060711188204, "percentage": 68.71, "elapsed_time": "11:12:23", "remaining_time": "5:06:16"}
|
||||
{"current_steps": 2780, "total_steps": 4039, "loss": 0.2598, "lr": 1.0732036926736979e-05, "epoch": 4.818733738074588, "percentage": 68.83, "elapsed_time": "11:13:40", "remaining_time": "5:05:05"}
|
||||
{"current_steps": 2785, "total_steps": 4039, "loss": 0.2358, "lr": 1.0655537098579869e-05, "epoch": 4.827406764960972, "percentage": 68.95, "elapsed_time": "11:14:54", "remaining_time": "5:03:53"}
|
||||
{"current_steps": 2790, "total_steps": 4039, "loss": 0.3009, "lr": 1.0579211766067586e-05, "epoch": 4.836079791847355, "percentage": 69.08, "elapsed_time": "11:16:04", "remaining_time": "5:02:39"}
|
||||
{"current_steps": 2795, "total_steps": 4039, "loss": 0.2486, "lr": 1.0503062354476059e-05, "epoch": 4.844752818733738, "percentage": 69.2, "elapsed_time": "11:17:15", "remaining_time": "5:01:25"}
|
||||
{"current_steps": 2800, "total_steps": 4039, "loss": 0.2542, "lr": 1.0427090285796123e-05, "epoch": 4.853425845620121, "percentage": 69.32, "elapsed_time": "11:18:26", "remaining_time": "5:00:12"}
|
||||
{"current_steps": 2805, "total_steps": 4039, "loss": 0.2691, "lr": 1.0351296978706986e-05, "epoch": 4.862098872506505, "percentage": 69.45, "elapsed_time": "11:19:42", "remaining_time": "4:59:01"}
|
||||
{"current_steps": 2810, "total_steps": 4039, "loss": 0.274, "lr": 1.0275683848549703e-05, "epoch": 4.870771899392889, "percentage": 69.57, "elapsed_time": "11:20:54", "remaining_time": "4:57:48"}
|
||||
{"current_steps": 2815, "total_steps": 4039, "loss": 0.2548, "lr": 1.0200252307300758e-05, "epoch": 4.879444926279271, "percentage": 69.7, "elapsed_time": "11:21:53", "remaining_time": "4:56:29"}
|
||||
{"current_steps": 2820, "total_steps": 4039, "loss": 0.2941, "lr": 1.0125003763545699e-05, "epoch": 4.888117953165655, "percentage": 69.82, "elapsed_time": "11:23:11", "remaining_time": "4:55:19"}
|
||||
{"current_steps": 2825, "total_steps": 4039, "loss": 0.248, "lr": 1.0049939622452837e-05, "epoch": 4.896790980052038, "percentage": 69.94, "elapsed_time": "11:24:26", "remaining_time": "4:54:07"}
|
||||
{"current_steps": 2830, "total_steps": 4039, "loss": 0.237, "lr": 9.97506128574702e-06, "epoch": 4.905464006938422, "percentage": 70.07, "elapsed_time": "11:25:38", "remaining_time": "4:52:54"}
|
||||
{"current_steps": 2835, "total_steps": 4039, "loss": 0.2441, "lr": 9.900370151683412e-06, "epoch": 4.9141370338248045, "percentage": 70.19, "elapsed_time": "11:26:57", "remaining_time": "4:51:44"}
|
||||
{"current_steps": 2840, "total_steps": 4039, "loss": 0.2419, "lr": 9.825867615021428e-06, "epoch": 4.922810060711188, "percentage": 70.31, "elapsed_time": "11:28:15", "remaining_time": "4:50:34"}
|
||||
{"current_steps": 2845, "total_steps": 4039, "loss": 0.2427, "lr": 9.751555066998678e-06, "epoch": 4.931483087597572, "percentage": 70.44, "elapsed_time": "11:29:26", "remaining_time": "4:49:20"}
|
||||
{"current_steps": 2850, "total_steps": 4039, "loss": 0.2321, "lr": 9.67743389530497e-06, "epoch": 4.940156114483955, "percentage": 70.56, "elapsed_time": "11:30:42", "remaining_time": "4:48:09"}
|
||||
{"current_steps": 2855, "total_steps": 4039, "loss": 0.2317, "lr": 9.603505484056428e-06, "epoch": 4.9488291413703385, "percentage": 70.69, "elapsed_time": "11:31:54", "remaining_time": "4:46:56"}
|
||||
{"current_steps": 2860, "total_steps": 4039, "loss": 0.2614, "lr": 9.5297712137696e-06, "epoch": 4.957502168256721, "percentage": 70.81, "elapsed_time": "11:33:12", "remaining_time": "4:45:45"}
|
||||
{"current_steps": 2865, "total_steps": 4039, "loss": 0.2157, "lr": 9.456232461335717e-06, "epoch": 4.966175195143105, "percentage": 70.93, "elapsed_time": "11:34:20", "remaining_time": "4:44:31"}
|
||||
{"current_steps": 2870, "total_steps": 4039, "loss": 0.2409, "lr": 9.382890599994982e-06, "epoch": 4.974848222029488, "percentage": 71.06, "elapsed_time": "11:35:35", "remaining_time": "4:43:19"}
|
||||
{"current_steps": 2875, "total_steps": 4039, "loss": 0.2541, "lr": 9.309746999310898e-06, "epoch": 4.983521248915872, "percentage": 71.18, "elapsed_time": "11:36:46", "remaining_time": "4:42:06"}
|
||||
{"current_steps": 2880, "total_steps": 4039, "loss": 0.2512, "lr": 9.236803025144703e-06, "epoch": 4.992194275802255, "percentage": 71.3, "elapsed_time": "11:37:59", "remaining_time": "4:40:53"}
|
||||
{"current_steps": 2885, "total_steps": 4039, "loss": 0.2907, "lr": 9.164060039629897e-06, "epoch": 5.0, "percentage": 71.43, "elapsed_time": "11:39:06", "remaining_time": "4:39:38"}
|
||||
{"current_steps": 2890, "total_steps": 4039, "loss": 0.2425, "lr": 9.091519401146755e-06, "epoch": 5.008673026886384, "percentage": 71.55, "elapsed_time": "11:40:17", "remaining_time": "4:38:25"}
|
||||
{"current_steps": 2895, "total_steps": 4039, "loss": 0.2646, "lr": 9.019182464296989e-06, "epoch": 5.0173460537727665, "percentage": 71.68, "elapsed_time": "11:41:32", "remaining_time": "4:37:13"}
|
||||
{"current_steps": 2900, "total_steps": 4039, "loss": 0.2547, "lr": 8.947050579878467e-06, "epoch": 5.02601908065915, "percentage": 71.8, "elapsed_time": "11:42:47", "remaining_time": "4:36:01"}
|
||||
{"current_steps": 2905, "total_steps": 4039, "loss": 0.2749, "lr": 8.875125094859942e-06, "epoch": 5.034692107545533, "percentage": 71.92, "elapsed_time": "11:43:55", "remaining_time": "4:34:46"}
|
||||
{"current_steps": 2910, "total_steps": 4039, "loss": 0.2922, "lr": 8.803407352355957e-06, "epoch": 5.043365134431917, "percentage": 72.05, "elapsed_time": "11:45:11", "remaining_time": "4:33:35"}
|
||||
{"current_steps": 2915, "total_steps": 4039, "loss": 0.2293, "lr": 8.731898691601712e-06, "epoch": 5.0520381613183005, "percentage": 72.17, "elapsed_time": "11:46:28", "remaining_time": "4:32:24"}
|
||||
{"current_steps": 2920, "total_steps": 4039, "loss": 0.2714, "lr": 8.660600447928085e-06, "epoch": 5.060711188204683, "percentage": 72.3, "elapsed_time": "11:47:21", "remaining_time": "4:31:04"}
|
||||
{"current_steps": 2925, "total_steps": 4039, "loss": 0.2561, "lr": 8.589513952736701e-06, "epoch": 5.069384215091067, "percentage": 72.42, "elapsed_time": "11:48:41", "remaining_time": "4:29:54"}
|
||||
{"current_steps": 2930, "total_steps": 4039, "loss": 0.2313, "lr": 8.518640533475044e-06, "epoch": 5.07805724197745, "percentage": 72.54, "elapsed_time": "11:49:57", "remaining_time": "4:28:43"}
|
||||
{"current_steps": 2935, "total_steps": 4039, "loss": 0.246, "lr": 8.447981513611683e-06, "epoch": 5.086730268863834, "percentage": 72.67, "elapsed_time": "11:51:11", "remaining_time": "4:27:30"}
|
||||
{"current_steps": 2940, "total_steps": 4039, "loss": 0.2242, "lr": 8.377538212611573e-06, "epoch": 5.095403295750216, "percentage": 72.79, "elapsed_time": "11:52:24", "remaining_time": "4:26:18"}
|
||||
{"current_steps": 2945, "total_steps": 4039, "loss": 0.2198, "lr": 8.30731194591139e-06, "epoch": 5.1040763226366, "percentage": 72.91, "elapsed_time": "11:53:37", "remaining_time": "4:25:05"}
|
||||
{"current_steps": 2950, "total_steps": 4039, "loss": 0.2596, "lr": 8.237304024894972e-06, "epoch": 5.112749349522984, "percentage": 73.04, "elapsed_time": "11:54:47", "remaining_time": "4:23:52"}
|
||||
{"current_steps": 2955, "total_steps": 4039, "loss": 0.2842, "lr": 8.167515756868845e-06, "epoch": 5.121422376409367, "percentage": 73.16, "elapsed_time": "11:56:00", "remaining_time": "4:22:39"}
|
||||
{"current_steps": 2960, "total_steps": 4039, "loss": 0.2369, "lr": 8.09794844503781e-06, "epoch": 5.13009540329575, "percentage": 73.29, "elapsed_time": "11:57:14", "remaining_time": "4:21:27"}
|
||||
{"current_steps": 2965, "total_steps": 4039, "loss": 0.2527, "lr": 8.02860338848058e-06, "epoch": 5.138768430182133, "percentage": 73.41, "elapsed_time": "11:58:33", "remaining_time": "4:20:16"}
|
||||
{"current_steps": 2970, "total_steps": 4039, "loss": 0.2477, "lr": 7.95948188212556e-06, "epoch": 5.147441457068517, "percentage": 73.53, "elapsed_time": "11:59:42", "remaining_time": "4:19:02"}
|
||||
{"current_steps": 2975, "total_steps": 4039, "loss": 0.293, "lr": 7.890585216726625e-06, "epoch": 5.156114483954901, "percentage": 73.66, "elapsed_time": "12:00:59", "remaining_time": "4:17:51"}
|
||||
{"current_steps": 2980, "total_steps": 4039, "loss": 0.2373, "lr": 7.821914678839067e-06, "epoch": 5.1647875108412835, "percentage": 73.78, "elapsed_time": "12:02:13", "remaining_time": "4:16:39"}
|
||||
{"current_steps": 2985, "total_steps": 4039, "loss": 0.247, "lr": 7.753471550795519e-06, "epoch": 5.173460537727667, "percentage": 73.9, "elapsed_time": "12:03:16", "remaining_time": "4:15:23"}
|
||||
{"current_steps": 2990, "total_steps": 4039, "loss": 0.2485, "lr": 7.685257110682036e-06, "epoch": 5.18213356461405, "percentage": 74.03, "elapsed_time": "12:04:33", "remaining_time": "4:14:12"}
|
||||
{"current_steps": 2995, "total_steps": 4039, "loss": 0.2524, "lr": 7.617272632314239e-06, "epoch": 5.190806591500434, "percentage": 74.15, "elapsed_time": "12:05:36", "remaining_time": "4:12:55"}
|
||||
{"current_steps": 3000, "total_steps": 4039, "loss": 0.2477, "lr": 7.549519385213497e-06, "epoch": 5.199479618386817, "percentage": 74.28, "elapsed_time": "12:06:51", "remaining_time": "4:11:44"}
|
||||
{"current_steps": 3005, "total_steps": 4039, "loss": 0.2478, "lr": 7.481998634583236e-06, "epoch": 5.2081526452732, "percentage": 74.4, "elapsed_time": "12:08:44", "remaining_time": "4:10:45"}
|
||||
{"current_steps": 3010, "total_steps": 4039, "loss": 0.2642, "lr": 7.414711641285335e-06, "epoch": 5.216825672159584, "percentage": 74.52, "elapsed_time": "12:09:52", "remaining_time": "4:09:30"}
|
||||
{"current_steps": 3015, "total_steps": 4039, "loss": 0.228, "lr": 7.347659661816533e-06, "epoch": 5.225498699045967, "percentage": 74.65, "elapsed_time": "12:11:12", "remaining_time": "4:08:20"}
|
||||
{"current_steps": 3020, "total_steps": 4039, "loss": 0.2473, "lr": 7.280843948285017e-06, "epoch": 5.234171725932351, "percentage": 74.77, "elapsed_time": "12:12:23", "remaining_time": "4:07:07"}
|
||||
{"current_steps": 3025, "total_steps": 4039, "loss": 0.238, "lr": 7.214265748386997e-06, "epoch": 5.242844752818733, "percentage": 74.89, "elapsed_time": "12:13:37", "remaining_time": "4:05:55"}
|
||||
{"current_steps": 3030, "total_steps": 4039, "loss": 0.2575, "lr": 7.1479263053834304e-06, "epoch": 5.251517779705117, "percentage": 75.02, "elapsed_time": "12:14:44", "remaining_time": "4:04:40"}
|
||||
{"current_steps": 3035, "total_steps": 4039, "loss": 0.2697, "lr": 7.081826858076814e-06, "epoch": 5.260190806591501, "percentage": 75.14, "elapsed_time": "12:15:56", "remaining_time": "4:03:27"}
|
||||
{"current_steps": 3040, "total_steps": 4039, "loss": 0.2522, "lr": 7.015968640788024e-06, "epoch": 5.268863833477884, "percentage": 75.27, "elapsed_time": "12:17:14", "remaining_time": "4:02:16"}
|
||||
{"current_steps": 3045, "total_steps": 4039, "loss": 0.2586, "lr": 6.95035288333328e-06, "epoch": 5.277536860364267, "percentage": 75.39, "elapsed_time": "12:18:23", "remaining_time": "4:01:02"}
|
||||
{"current_steps": 3050, "total_steps": 4039, "loss": 0.2435, "lr": 6.884980811001196e-06, "epoch": 5.28620988725065, "percentage": 75.51, "elapsed_time": "12:19:37", "remaining_time": "3:59:49"}
|
||||
{"current_steps": 3055, "total_steps": 4039, "loss": 0.2638, "lr": 6.819853644529875e-06, "epoch": 5.294882914137034, "percentage": 75.64, "elapsed_time": "12:20:48", "remaining_time": "3:58:36"}
|
||||
{"current_steps": 3060, "total_steps": 4039, "loss": 0.2397, "lr": 6.754972600084109e-06, "epoch": 5.303555941023417, "percentage": 75.76, "elapsed_time": "12:21:58", "remaining_time": "3:57:23"}
|
||||
{"current_steps": 3065, "total_steps": 4039, "loss": 0.2349, "lr": 6.6903388892327105e-06, "epoch": 5.3122289679098005, "percentage": 75.89, "elapsed_time": "12:23:12", "remaining_time": "3:56:10"}
|
||||
{"current_steps": 3070, "total_steps": 4039, "loss": 0.235, "lr": 6.625953718925837e-06, "epoch": 5.320901994796184, "percentage": 76.01, "elapsed_time": "12:24:30", "remaining_time": "3:54:59"}
|
||||
{"current_steps": 3075, "total_steps": 4039, "loss": 0.2091, "lr": 6.561818291472493e-06, "epoch": 5.329575021682567, "percentage": 76.13, "elapsed_time": "12:25:41", "remaining_time": "3:53:46"}
|
||||
{"current_steps": 3080, "total_steps": 4039, "loss": 0.2877, "lr": 6.497933804518048e-06, "epoch": 5.338248048568951, "percentage": 76.26, "elapsed_time": "12:26:59", "remaining_time": "3:52:35"}
|
||||
{"current_steps": 3085, "total_steps": 4039, "loss": 0.2655, "lr": 6.434301451021891e-06, "epoch": 5.346921075455334, "percentage": 76.38, "elapsed_time": "12:28:00", "remaining_time": "3:51:18"}
|
||||
{"current_steps": 3090, "total_steps": 4039, "loss": 0.2269, "lr": 6.370922419235142e-06, "epoch": 5.355594102341717, "percentage": 76.5, "elapsed_time": "12:29:17", "remaining_time": "3:50:07"}
|
||||
{"current_steps": 3095, "total_steps": 4039, "loss": 0.2185, "lr": 6.307797892678482e-06, "epoch": 5.364267129228101, "percentage": 76.63, "elapsed_time": "12:30:19", "remaining_time": "3:48:51"}
|
||||
{"current_steps": 3100, "total_steps": 4039, "loss": 0.2591, "lr": 6.244929050120026e-06, "epoch": 5.372940156114484, "percentage": 76.75, "elapsed_time": "12:31:34", "remaining_time": "3:47:39"}
|
||||
{"current_steps": 3105, "total_steps": 4039, "loss": 0.2628, "lr": 6.1823170655533315e-06, "epoch": 5.3816131830008676, "percentage": 76.88, "elapsed_time": "12:32:48", "remaining_time": "3:46:26"}
|
||||
{"current_steps": 3110, "total_steps": 4039, "loss": 0.2357, "lr": 6.119963108175464e-06, "epoch": 5.39028620988725, "percentage": 77.0, "elapsed_time": "12:33:57", "remaining_time": "3:45:13"}
|
||||
{"current_steps": 3115, "total_steps": 4039, "loss": 0.2565, "lr": 6.057868342365163e-06, "epoch": 5.398959236773634, "percentage": 77.12, "elapsed_time": "12:35:05", "remaining_time": "3:43:58"}
|
||||
{"current_steps": 3120, "total_steps": 4039, "loss": 0.2492, "lr": 5.996033927661124e-06, "epoch": 5.407632263660018, "percentage": 77.25, "elapsed_time": "12:36:12", "remaining_time": "3:42:44"}
|
||||
{"current_steps": 3125, "total_steps": 4039, "loss": 0.2447, "lr": 5.9344610187403e-06, "epoch": 5.416305290546401, "percentage": 77.37, "elapsed_time": "12:37:30", "remaining_time": "3:41:33"}
|
||||
{"current_steps": 3130, "total_steps": 4039, "loss": 0.2597, "lr": 5.873150765396389e-06, "epoch": 5.424978317432784, "percentage": 77.49, "elapsed_time": "12:38:44", "remaining_time": "3:40:21"}
|
||||
{"current_steps": 3135, "total_steps": 4039, "loss": 0.2557, "lr": 5.812104312518325e-06, "epoch": 5.433651344319167, "percentage": 77.62, "elapsed_time": "12:39:58", "remaining_time": "3:39:08"}
|
||||
{"current_steps": 3140, "total_steps": 4039, "loss": 0.2545, "lr": 5.751322800068904e-06, "epoch": 5.442324371205551, "percentage": 77.74, "elapsed_time": "12:41:13", "remaining_time": "3:37:56"}
|
||||
{"current_steps": 3145, "total_steps": 4039, "loss": 0.2657, "lr": 5.690807363063529e-06, "epoch": 5.450997398091934, "percentage": 77.87, "elapsed_time": "12:42:22", "remaining_time": "3:36:42"}
|
||||
{"current_steps": 3150, "total_steps": 4039, "loss": 0.2424, "lr": 5.6305591315489765e-06, "epoch": 5.4596704249783174, "percentage": 77.99, "elapsed_time": "12:43:31", "remaining_time": "3:35:29"}
|
||||
{"current_steps": 3155, "total_steps": 4039, "loss": 0.2339, "lr": 5.5705792305823e-06, "epoch": 5.468343451864701, "percentage": 78.11, "elapsed_time": "12:44:46", "remaining_time": "3:34:16"}
|
||||
{"current_steps": 3160, "total_steps": 4039, "loss": 0.2293, "lr": 5.510868780209859e-06, "epoch": 5.477016478751084, "percentage": 78.24, "elapsed_time": "12:45:45", "remaining_time": "3:33:00"}
|
||||
{"current_steps": 3165, "total_steps": 4039, "loss": 0.2602, "lr": 5.451428895446351e-06, "epoch": 5.485689505637468, "percentage": 78.36, "elapsed_time": "12:46:47", "remaining_time": "3:31:44"}
|
||||
{"current_steps": 3170, "total_steps": 4039, "loss": 0.2686, "lr": 5.392260686254014e-06, "epoch": 5.4943625325238505, "percentage": 78.48, "elapsed_time": "12:48:04", "remaining_time": "3:30:33"}
|
||||
{"current_steps": 3175, "total_steps": 4039, "loss": 0.2234, "lr": 5.333365257521916e-06, "epoch": 5.503035559410234, "percentage": 78.61, "elapsed_time": "12:49:24", "remaining_time": "3:29:22"}
|
||||
{"current_steps": 3180, "total_steps": 4039, "loss": 0.2847, "lr": 5.274743709045289e-06, "epoch": 5.511708586296617, "percentage": 78.73, "elapsed_time": "12:50:37", "remaining_time": "3:28:09"}
|
||||
{"current_steps": 3185, "total_steps": 4039, "loss": 0.2925, "lr": 5.216397135505025e-06, "epoch": 5.520381613183001, "percentage": 78.86, "elapsed_time": "12:51:55", "remaining_time": "3:26:58"}
|
||||
{"current_steps": 3190, "total_steps": 4039, "loss": 0.2065, "lr": 5.1583266264472055e-06, "epoch": 5.5290546400693845, "percentage": 78.98, "elapsed_time": "12:53:06", "remaining_time": "3:25:45"}
|
||||
{"current_steps": 3195, "total_steps": 4039, "loss": 0.2575, "lr": 5.100533266262764e-06, "epoch": 5.537727666955767, "percentage": 79.1, "elapsed_time": "12:54:24", "remaining_time": "3:24:34"}
|
||||
{"current_steps": 3200, "total_steps": 4039, "loss": 0.2242, "lr": 5.043018134167262e-06, "epoch": 5.546400693842151, "percentage": 79.23, "elapsed_time": "12:55:42", "remaining_time": "3:23:22"}
|
||||
{"current_steps": 3205, "total_steps": 4039, "loss": 0.2672, "lr": 4.985782304180693e-06, "epoch": 5.555073720728534, "percentage": 79.35, "elapsed_time": "12:56:51", "remaining_time": "3:22:09"}
|
||||
{"current_steps": 3210, "total_steps": 4039, "loss": 0.2188, "lr": 4.928826845107453e-06, "epoch": 5.563746747614918, "percentage": 79.48, "elapsed_time": "12:58:05", "remaining_time": "3:20:56"}
|
||||
{"current_steps": 3215, "total_steps": 4039, "loss": 0.2513, "lr": 4.8721528205163895e-06, "epoch": 5.572419774501301, "percentage": 79.6, "elapsed_time": "12:59:12", "remaining_time": "3:19:42"}
|
||||
{"current_steps": 3220, "total_steps": 4039, "loss": 0.263, "lr": 4.815761288720919e-06, "epoch": 5.581092801387684, "percentage": 79.72, "elapsed_time": "13:00:23", "remaining_time": "3:18:29"}
|
||||
{"current_steps": 3225, "total_steps": 4039, "loss": 0.2611, "lr": 4.759653302759264e-06, "epoch": 5.589765828274068, "percentage": 79.85, "elapsed_time": "13:01:37", "remaining_time": "3:17:17"}
|
||||
{"current_steps": 3230, "total_steps": 4039, "loss": 0.2083, "lr": 4.703829910374824e-06, "epoch": 5.598438855160451, "percentage": 79.97, "elapsed_time": "13:02:45", "remaining_time": "3:16:03"}
|
||||
{"current_steps": 3235, "total_steps": 4039, "loss": 0.2351, "lr": 4.648292153996563e-06, "epoch": 5.607111882046834, "percentage": 80.09, "elapsed_time": "13:03:58", "remaining_time": "3:14:50"}
|
||||
{"current_steps": 3240, "total_steps": 4039, "loss": 0.2315, "lr": 4.593041070719573e-06, "epoch": 5.615784908933218, "percentage": 80.22, "elapsed_time": "13:05:07", "remaining_time": "3:13:36"}
|
||||
{"current_steps": 3245, "total_steps": 4039, "loss": 0.2252, "lr": 4.538077692285694e-06, "epoch": 5.624457935819601, "percentage": 80.34, "elapsed_time": "13:06:23", "remaining_time": "3:12:25"}
|
||||
{"current_steps": 3250, "total_steps": 4039, "loss": 0.2705, "lr": 4.483403045064272e-06, "epoch": 5.633130962705985, "percentage": 80.47, "elapsed_time": "13:07:37", "remaining_time": "3:11:12"}
|
||||
{"current_steps": 3255, "total_steps": 4039, "loss": 0.229, "lr": 4.429018150032956e-06, "epoch": 5.6418039895923675, "percentage": 80.59, "elapsed_time": "13:08:46", "remaining_time": "3:09:59"}
|
||||
{"current_steps": 3260, "total_steps": 4039, "loss": 0.2352, "lr": 4.374924022758657e-06, "epoch": 5.650477016478751, "percentage": 80.71, "elapsed_time": "13:10:05", "remaining_time": "3:08:47"}
|
||||
{"current_steps": 3265, "total_steps": 4039, "loss": 0.245, "lr": 4.321121673378572e-06, "epoch": 5.659150043365134, "percentage": 80.84, "elapsed_time": "13:11:14", "remaining_time": "3:07:34"}
|
||||
{"current_steps": 3270, "total_steps": 4039, "loss": 0.2254, "lr": 4.267612106581347e-06, "epoch": 5.667823070251518, "percentage": 80.96, "elapsed_time": "13:12:26", "remaining_time": "3:06:21"}
|
||||
{"current_steps": 3275, "total_steps": 4039, "loss": 0.2411, "lr": 4.214396321588272e-06, "epoch": 5.6764960971379015, "percentage": 81.08, "elapsed_time": "13:13:29", "remaining_time": "3:05:06"}
|
||||
{"current_steps": 3280, "total_steps": 4039, "loss": 0.2233, "lr": 4.16147531213465e-06, "epoch": 5.685169124024284, "percentage": 81.21, "elapsed_time": "13:14:49", "remaining_time": "3:03:55"}
|
||||
{"current_steps": 3285, "total_steps": 4039, "loss": 0.261, "lr": 4.108850066451256e-06, "epoch": 5.693842150910668, "percentage": 81.33, "elapsed_time": "13:16:07", "remaining_time": "3:02:43"}
|
||||
{"current_steps": 3290, "total_steps": 4039, "loss": 0.2274, "lr": 4.056521567245828e-06, "epoch": 5.702515177797051, "percentage": 81.46, "elapsed_time": "13:17:19", "remaining_time": "3:01:31"}
|
||||
{"current_steps": 3295, "total_steps": 4039, "loss": 0.2454, "lr": 4.004490791684788e-06, "epoch": 5.711188204683435, "percentage": 81.58, "elapsed_time": "13:18:34", "remaining_time": "3:00:18"}
|
||||
{"current_steps": 3300, "total_steps": 4039, "loss": 0.2695, "lr": 3.952758711374931e-06, "epoch": 5.719861231569817, "percentage": 81.7, "elapsed_time": "13:19:37", "remaining_time": "2:59:03"}
|
||||
{"current_steps": 3305, "total_steps": 4039, "loss": 0.2753, "lr": 3.901326292345314e-06, "epoch": 5.728534258456201, "percentage": 81.83, "elapsed_time": "13:20:51", "remaining_time": "2:57:51"}
|
||||
{"current_steps": 3310, "total_steps": 4039, "loss": 0.2419, "lr": 3.8501944950292184e-06, "epoch": 5.737207285342585, "percentage": 81.95, "elapsed_time": "13:22:07", "remaining_time": "2:56:39"}
|
||||
{"current_steps": 3315, "total_steps": 4039, "loss": 0.2532, "lr": 3.7993642742462043e-06, "epoch": 5.745880312228968, "percentage": 82.07, "elapsed_time": "13:23:05", "remaining_time": "2:55:23"}
|
||||
{"current_steps": 3320, "total_steps": 4039, "loss": 0.2431, "lr": 3.748836579184274e-06, "epoch": 5.754553339115351, "percentage": 82.2, "elapsed_time": "13:24:17", "remaining_time": "2:54:10"}
|
||||
{"current_steps": 3325, "total_steps": 4039, "loss": 0.231, "lr": 3.698612353382176e-06, "epoch": 5.763226366001735, "percentage": 82.32, "elapsed_time": "13:25:28", "remaining_time": "2:52:57"}
|
||||
{"current_steps": 3330, "total_steps": 4039, "loss": 0.2122, "lr": 3.648692534711751e-06, "epoch": 5.771899392888118, "percentage": 82.45, "elapsed_time": "13:26:33", "remaining_time": "2:51:43"}
|
||||
{"current_steps": 3335, "total_steps": 4039, "loss": 0.2549, "lr": 3.599078055360432e-06, "epoch": 5.780572419774502, "percentage": 82.57, "elapsed_time": "13:27:38", "remaining_time": "2:50:29"}
|
||||
{"current_steps": 3340, "total_steps": 4039, "loss": 0.257, "lr": 3.5497698418138573e-06, "epoch": 5.7892454466608845, "percentage": 82.69, "elapsed_time": "13:28:48", "remaining_time": "2:49:16"}
|
||||
{"current_steps": 3345, "total_steps": 4039, "loss": 0.2122, "lr": 3.500768814838531e-06, "epoch": 5.797918473547268, "percentage": 82.82, "elapsed_time": "13:30:05", "remaining_time": "2:48:04"}
|
||||
{"current_steps": 3350, "total_steps": 4039, "loss": 0.2207, "lr": 3.4520758894646654e-06, "epoch": 5.806591500433651, "percentage": 82.94, "elapsed_time": "13:31:20", "remaining_time": "2:46:52"}
|
||||
{"current_steps": 3355, "total_steps": 4039, "loss": 0.288, "lr": 3.4036919749690654e-06, "epoch": 5.815264527320035, "percentage": 83.07, "elapsed_time": "13:32:37", "remaining_time": "2:45:40"}
|
||||
{"current_steps": 3360, "total_steps": 4039, "loss": 0.2623, "lr": 3.3556179748581586e-06, "epoch": 5.8239375542064185, "percentage": 83.19, "elapsed_time": "13:33:52", "remaining_time": "2:44:28"}
|
||||
{"current_steps": 3365, "total_steps": 4039, "loss": 0.2123, "lr": 3.3078547868511455e-06, "epoch": 5.832610581092801, "percentage": 83.31, "elapsed_time": "13:35:05", "remaining_time": "2:43:15"}
|
||||
{"current_steps": 3370, "total_steps": 4039, "loss": 0.2414, "lr": 3.2604033028632e-06, "epoch": 5.841283607979185, "percentage": 83.44, "elapsed_time": "13:36:14", "remaining_time": "2:42:02"}
|
||||
{"current_steps": 3375, "total_steps": 4039, "loss": 0.2447, "lr": 3.2132644089888253e-06, "epoch": 5.849956634865568, "percentage": 83.56, "elapsed_time": "13:37:33", "remaining_time": "2:40:50"}
|
||||
{"current_steps": 3380, "total_steps": 4039, "loss": 0.2163, "lr": 3.166438985485334e-06, "epoch": 5.8586296617519515, "percentage": 83.68, "elapsed_time": "13:38:48", "remaining_time": "2:39:38"}
|
||||
{"current_steps": 3385, "total_steps": 4039, "loss": 0.2509, "lr": 3.1199279067563706e-06, "epoch": 5.867302688638334, "percentage": 83.81, "elapsed_time": "13:39:56", "remaining_time": "2:38:25"}
|
||||
{"current_steps": 3390, "total_steps": 4039, "loss": 0.2474, "lr": 3.0737320413356063e-06, "epoch": 5.875975715524718, "percentage": 83.93, "elapsed_time": "13:41:10", "remaining_time": "2:37:12"}
|
||||
{"current_steps": 3395, "total_steps": 4039, "loss": 0.2393, "lr": 3.0278522518705177e-06, "epoch": 5.884648742411102, "percentage": 84.06, "elapsed_time": "13:42:24", "remaining_time": "2:36:00"}
|
||||
{"current_steps": 3400, "total_steps": 4039, "loss": 0.2438, "lr": 2.9822893951062658e-06, "epoch": 5.893321769297485, "percentage": 84.18, "elapsed_time": "13:43:41", "remaining_time": "2:34:48"}
|
||||
{"current_steps": 3405, "total_steps": 4039, "loss": 0.2397, "lr": 2.9370443218697264e-06, "epoch": 5.901994796183868, "percentage": 84.3, "elapsed_time": "13:44:58", "remaining_time": "2:33:36"}
|
||||
{"current_steps": 3410, "total_steps": 4039, "loss": 0.234, "lr": 2.8921178770535687e-06, "epoch": 5.910667823070251, "percentage": 84.43, "elapsed_time": "13:46:12", "remaining_time": "2:32:23"}
|
||||
{"current_steps": 3415, "total_steps": 4039, "loss": 0.2583, "lr": 2.847510899600485e-06, "epoch": 5.919340849956635, "percentage": 84.55, "elapsed_time": "13:47:24", "remaining_time": "2:31:11"}
|
||||
{"current_steps": 3420, "total_steps": 4039, "loss": 0.2667, "lr": 2.8032242224875573e-06, "epoch": 5.928013876843018, "percentage": 84.67, "elapsed_time": "13:48:40", "remaining_time": "2:29:59"}
|
||||
{"current_steps": 3425, "total_steps": 4039, "loss": 0.259, "lr": 2.7592586727106517e-06, "epoch": 5.936686903729401, "percentage": 84.8, "elapsed_time": "13:49:51", "remaining_time": "2:28:46"}
|
||||
{"current_steps": 3430, "total_steps": 4039, "loss": 0.2646, "lr": 2.715615071269009e-06, "epoch": 5.945359930615785, "percentage": 84.92, "elapsed_time": "13:50:57", "remaining_time": "2:27:32"}
|
||||
{"current_steps": 3435, "total_steps": 4039, "loss": 0.2488, "lr": 2.6722942331499125e-06, "epoch": 5.954032957502168, "percentage": 85.05, "elapsed_time": "13:52:03", "remaining_time": "2:26:18"}
|
||||
{"current_steps": 3440, "total_steps": 4039, "loss": 0.2242, "lr": 2.6292969673134527e-06, "epoch": 5.962705984388552, "percentage": 85.17, "elapsed_time": "13:53:22", "remaining_time": "2:25:06"}
|
||||
{"current_steps": 3445, "total_steps": 4039, "loss": 0.2544, "lr": 2.5866240766774265e-06, "epoch": 5.971379011274935, "percentage": 85.29, "elapsed_time": "13:54:30", "remaining_time": "2:23:53"}
|
||||
{"current_steps": 3450, "total_steps": 4039, "loss": 0.2173, "lr": 2.5442763581023664e-06, "epoch": 5.980052038161318, "percentage": 85.42, "elapsed_time": "13:55:36", "remaining_time": "2:22:39"}
|
||||
{"current_steps": 3455, "total_steps": 4039, "loss": 0.1968, "lr": 2.5022546023766192e-06, "epoch": 5.988725065047702, "percentage": 85.54, "elapsed_time": "13:56:38", "remaining_time": "2:21:25"}
|
||||
{"current_steps": 3460, "total_steps": 4039, "loss": 0.2547, "lr": 2.460559594201617e-06, "epoch": 5.997398091934085, "percentage": 85.66, "elapsed_time": "13:57:48", "remaining_time": "2:20:11"}
|
||||
{"current_steps": 3465, "total_steps": 4039, "loss": 0.2973, "lr": 2.4191921121772e-06, "epoch": 6.00520381613183, "percentage": 85.79, "elapsed_time": "13:58:45", "remaining_time": "2:18:56"}
|
||||
{"current_steps": 3470, "total_steps": 4039, "loss": 0.2283, "lr": 2.3781529287870786e-06, "epoch": 6.013876843018213, "percentage": 85.91, "elapsed_time": "14:00:00", "remaining_time": "2:17:44"}
|
||||
{"current_steps": 3475, "total_steps": 4039, "loss": 0.2239, "lr": 2.337442810384436e-06, "epoch": 6.022549869904597, "percentage": 86.04, "elapsed_time": "14:01:17", "remaining_time": "2:16:32"}
|
||||
{"current_steps": 3480, "total_steps": 4039, "loss": 0.2414, "lr": 2.2970625171775774e-06, "epoch": 6.03122289679098, "percentage": 86.16, "elapsed_time": "14:02:19", "remaining_time": "2:15:18"}
|
||||
{"current_steps": 3485, "total_steps": 4039, "loss": 0.2267, "lr": 2.2570128032157568e-06, "epoch": 6.0398959236773635, "percentage": 86.28, "elapsed_time": "14:03:29", "remaining_time": "2:14:05"}
|
||||
{"current_steps": 3490, "total_steps": 4039, "loss": 0.207, "lr": 2.2172944163750975e-06, "epoch": 6.048568950563746, "percentage": 86.41, "elapsed_time": "14:04:41", "remaining_time": "2:12:52"}
|
||||
{"current_steps": 3495, "total_steps": 4039, "loss": 0.2408, "lr": 2.177908098344621e-06, "epoch": 6.05724197745013, "percentage": 86.53, "elapsed_time": "14:06:00", "remaining_time": "2:11:40"}
|
||||
{"current_steps": 3500, "total_steps": 4039, "loss": 0.2629, "lr": 2.1388545846123866e-06, "epoch": 6.065915004336514, "percentage": 86.66, "elapsed_time": "14:07:15", "remaining_time": "2:10:28"}
|
||||
{"current_steps": 3505, "total_steps": 4039, "loss": 0.2005, "lr": 2.1001346044517847e-06, "epoch": 6.074588031222897, "percentage": 86.78, "elapsed_time": "14:08:30", "remaining_time": "2:09:16"}
|
||||
{"current_steps": 3510, "total_steps": 4039, "loss": 0.2344, "lr": 2.061748880907888e-06, "epoch": 6.08326105810928, "percentage": 86.9, "elapsed_time": "14:09:43", "remaining_time": "2:08:03"}
|
||||
{"current_steps": 3515, "total_steps": 4039, "loss": 0.2176, "lr": 2.023698130783971e-06, "epoch": 6.091934084995663, "percentage": 87.03, "elapsed_time": "14:10:48", "remaining_time": "2:06:50"}
|
||||
{"current_steps": 3520, "total_steps": 4039, "loss": 0.2255, "lr": 1.985983064628114e-06, "epoch": 6.100607111882047, "percentage": 87.15, "elapsed_time": "14:11:58", "remaining_time": "2:05:37"}
|
||||
{"current_steps": 3525, "total_steps": 4039, "loss": 0.2201, "lr": 1.948604386719939e-06, "epoch": 6.109280138768431, "percentage": 87.27, "elapsed_time": "14:13:06", "remaining_time": "2:04:23"}
|
||||
{"current_steps": 3530, "total_steps": 4039, "loss": 0.2266, "lr": 1.9115627950574533e-06, "epoch": 6.117953165654813, "percentage": 87.4, "elapsed_time": "14:14:24", "remaining_time": "2:03:12"}
|
||||
{"current_steps": 3535, "total_steps": 4039, "loss": 0.2236, "lr": 1.8748589813440165e-06, "epoch": 6.126626192541197, "percentage": 87.52, "elapsed_time": "14:15:33", "remaining_time": "2:01:58"}
|
||||
{"current_steps": 3540, "total_steps": 4039, "loss": 0.2368, "lr": 1.8384936309754375e-06, "epoch": 6.13529921942758, "percentage": 87.65, "elapsed_time": "14:16:42", "remaining_time": "2:00:45"}
|
||||
{"current_steps": 3545, "total_steps": 4039, "loss": 0.213, "lr": 1.8024674230271544e-06, "epoch": 6.143972246313964, "percentage": 87.77, "elapsed_time": "14:17:47", "remaining_time": "1:59:32"}
|
||||
{"current_steps": 3550, "total_steps": 4039, "loss": 0.2317, "lr": 1.7667810302415666e-06, "epoch": 6.152645273200347, "percentage": 87.89, "elapsed_time": "14:18:59", "remaining_time": "1:58:19"}
|
||||
{"current_steps": 3555, "total_steps": 4039, "loss": 0.2296, "lr": 1.7314351190154633e-06, "epoch": 6.16131830008673, "percentage": 88.02, "elapsed_time": "14:20:11", "remaining_time": "1:57:06"}
|
||||
{"current_steps": 3560, "total_steps": 4039, "loss": 0.2366, "lr": 1.6964303493875966e-06, "epoch": 6.169991326973114, "percentage": 88.14, "elapsed_time": "14:21:21", "remaining_time": "1:55:53"}
|
||||
{"current_steps": 3565, "total_steps": 4039, "loss": 0.2874, "lr": 1.661767375026333e-06, "epoch": 6.178664353859497, "percentage": 88.26, "elapsed_time": "14:22:39", "remaining_time": "1:54:41"}
|
||||
{"current_steps": 3570, "total_steps": 4039, "loss": 0.2621, "lr": 1.6274468432174707e-06, "epoch": 6.1873373807458805, "percentage": 88.39, "elapsed_time": "14:23:46", "remaining_time": "1:53:28"}
|
||||
{"current_steps": 3575, "total_steps": 4039, "loss": 0.2278, "lr": 1.5934693948521251e-06, "epoch": 6.196010407632263, "percentage": 88.51, "elapsed_time": "14:24:56", "remaining_time": "1:52:15"}
|
||||
{"current_steps": 3580, "total_steps": 4039, "loss": 0.2293, "lr": 1.5598356644147883e-06, "epoch": 6.204683434518647, "percentage": 88.64, "elapsed_time": "14:26:16", "remaining_time": "1:51:04"}
|
||||
{"current_steps": 3585, "total_steps": 4039, "loss": 0.2505, "lr": 1.5265462799714659e-06, "epoch": 6.213356461405031, "percentage": 88.76, "elapsed_time": "14:27:28", "remaining_time": "1:49:51"}
|
||||
{"current_steps": 3590, "total_steps": 4039, "loss": 0.2173, "lr": 1.4936018631579497e-06, "epoch": 6.222029488291414, "percentage": 88.88, "elapsed_time": "14:28:40", "remaining_time": "1:48:38"}
|
||||
{"current_steps": 3595, "total_steps": 4039, "loss": 0.2626, "lr": 1.461003029168211e-06, "epoch": 6.230702515177797, "percentage": 89.01, "elapsed_time": "14:29:52", "remaining_time": "1:47:26"}
|
||||
{"current_steps": 3600, "total_steps": 4039, "loss": 0.2382, "lr": 1.4287503867429165e-06, "epoch": 6.23937554206418, "percentage": 89.13, "elapsed_time": "14:30:54", "remaining_time": "1:46:12"}
|
||||
{"current_steps": 3605, "total_steps": 4039, "loss": 0.2449, "lr": 1.3968445381580554e-06, "epoch": 6.248048568950564, "percentage": 89.25, "elapsed_time": "14:32:12", "remaining_time": "1:45:00"}
|
||||
{"current_steps": 3610, "total_steps": 4039, "loss": 0.2875, "lr": 1.3652860792136902e-06, "epoch": 6.256721595836947, "percentage": 89.38, "elapsed_time": "14:33:29", "remaining_time": "1:43:48"}
|
||||
{"current_steps": 3615, "total_steps": 4039, "loss": 0.2494, "lr": 1.334075599222846e-06, "epoch": 6.26539462272333, "percentage": 89.5, "elapsed_time": "14:34:31", "remaining_time": "1:42:34"}
|
||||
{"current_steps": 3620, "total_steps": 4039, "loss": 0.2366, "lr": 1.3032136810004881e-06, "epoch": 6.274067649609714, "percentage": 89.63, "elapsed_time": "14:35:40", "remaining_time": "1:41:21"}
|
||||
{"current_steps": 3625, "total_steps": 4039, "loss": 0.2541, "lr": 1.2727009008526414e-06, "epoch": 6.282740676496097, "percentage": 89.75, "elapsed_time": "14:36:58", "remaining_time": "1:40:09"}
|
||||
{"current_steps": 3630, "total_steps": 4039, "loss": 0.2517, "lr": 1.2425378285656464e-06, "epoch": 6.291413703382481, "percentage": 89.87, "elapsed_time": "14:38:01", "remaining_time": "1:38:55"}
|
||||
{"current_steps": 3635, "total_steps": 4039, "loss": 0.2292, "lr": 1.2127250273954893e-06, "epoch": 6.3000867302688635, "percentage": 90.0, "elapsed_time": "14:39:12", "remaining_time": "1:37:42"}
|
||||
{"current_steps": 3640, "total_steps": 4039, "loss": 0.2702, "lr": 1.1832630540573176e-06, "epoch": 6.308759757155247, "percentage": 90.12, "elapsed_time": "14:40:25", "remaining_time": "1:36:30"}
|
||||
{"current_steps": 3645, "total_steps": 4039, "loss": 0.2626, "lr": 1.1541524587150165e-06, "epoch": 6.317432784041631, "percentage": 90.25, "elapsed_time": "14:41:45", "remaining_time": "1:35:18"}
|
||||
{"current_steps": 3650, "total_steps": 4039, "loss": 0.2511, "lr": 1.1253937849709428e-06, "epoch": 6.326105810928014, "percentage": 90.37, "elapsed_time": "14:42:52", "remaining_time": "1:34:05"}
|
||||
{"current_steps": 3655, "total_steps": 4039, "loss": 0.2574, "lr": 1.0969875698557874e-06, "epoch": 6.334778837814397, "percentage": 90.49, "elapsed_time": "14:44:03", "remaining_time": "1:32:52"}
|
||||
{"current_steps": 3660, "total_steps": 4039, "loss": 0.2459, "lr": 1.0689343438185328e-06, "epoch": 6.34345186470078, "percentage": 90.62, "elapsed_time": "14:45:18", "remaining_time": "1:31:40"}
|
||||
{"current_steps": 3665, "total_steps": 4039, "loss": 0.2648, "lr": 1.041234630716541e-06, "epoch": 6.352124891587164, "percentage": 90.74, "elapsed_time": "14:46:30", "remaining_time": "1:30:27"}
|
||||
{"current_steps": 3670, "total_steps": 4039, "loss": 0.2199, "lr": 1.0138889478058013e-06, "epoch": 6.360797918473548, "percentage": 90.86, "elapsed_time": "14:47:35", "remaining_time": "1:29:14"}
|
||||
{"current_steps": 3675, "total_steps": 4039, "loss": 0.2533, "lr": 9.868978057312328e-07, "epoch": 6.3694709453599305, "percentage": 90.99, "elapsed_time": "14:48:51", "remaining_time": "1:28:02"}
|
||||
{"current_steps": 3680, "total_steps": 4039, "loss": 0.2321, "lr": 9.602617085171784e-07, "epoch": 6.378143972246314, "percentage": 91.11, "elapsed_time": "14:50:06", "remaining_time": "1:26:50"}
|
||||
{"current_steps": 3685, "total_steps": 4039, "loss": 0.2345, "lr": 9.339811535579768e-07, "epoch": 6.386816999132697, "percentage": 91.24, "elapsed_time": "14:51:22", "remaining_time": "1:25:37"}
|
||||
{"current_steps": 3690, "total_steps": 4039, "loss": 0.2425, "lr": 9.08056631608678e-07, "epoch": 6.395490026019081, "percentage": 91.36, "elapsed_time": "14:52:35", "remaining_time": "1:24:25"}
|
||||
{"current_steps": 3695, "total_steps": 4039, "loss": 0.2711, "lr": 8.824886267758881e-07, "epoch": 6.404163052905464, "percentage": 91.48, "elapsed_time": "14:53:53", "remaining_time": "1:23:13"}
|
||||
{"current_steps": 3700, "total_steps": 4039, "loss": 0.271, "lr": 8.572776165087137e-07, "epoch": 6.412836079791847, "percentage": 91.61, "elapsed_time": "14:55:10", "remaining_time": "1:22:01"}
|
||||
{"current_steps": 3705, "total_steps": 4039, "loss": 0.2232, "lr": 8.324240715898568e-07, "epoch": 6.421509106678231, "percentage": 91.73, "elapsed_time": "14:56:20", "remaining_time": "1:20:48"}
|
||||
{"current_steps": 3710, "total_steps": 4039, "loss": 0.2733, "lr": 8.079284561268208e-07, "epoch": 6.430182133564614, "percentage": 91.85, "elapsed_time": "14:57:32", "remaining_time": "1:19:35"}
|
||||
{"current_steps": 3715, "total_steps": 4039, "loss": 0.2536, "lr": 7.837912275432469e-07, "epoch": 6.438855160450998, "percentage": 91.98, "elapsed_time": "14:58:44", "remaining_time": "1:18:22"}
|
||||
{"current_steps": 3720, "total_steps": 4039, "loss": 0.2314, "lr": 7.600128365703608e-07, "epoch": 6.44752818733738, "percentage": 92.1, "elapsed_time": "14:59:53", "remaining_time": "1:17:10"}
|
||||
{"current_steps": 3725, "total_steps": 4039, "loss": 0.2381, "lr": 7.365937272385726e-07, "epoch": 6.456201214223764, "percentage": 92.23, "elapsed_time": "15:01:07", "remaining_time": "1:15:57"}
|
||||
{"current_steps": 3730, "total_steps": 4039, "loss": 0.2329, "lr": 7.13534336869175e-07, "epoch": 6.464874241110148, "percentage": 92.35, "elapsed_time": "15:02:18", "remaining_time": "1:14:44"}
|
||||
{"current_steps": 3735, "total_steps": 4039, "loss": 0.2523, "lr": 6.908350960661713e-07, "epoch": 6.473547267996531, "percentage": 92.47, "elapsed_time": "15:03:26", "remaining_time": "1:13:31"}
|
||||
{"current_steps": 3740, "total_steps": 4039, "loss": 0.2488, "lr": 6.684964287082562e-07, "epoch": 6.482220294882914, "percentage": 92.6, "elapsed_time": "15:04:36", "remaining_time": "1:12:19"}
|
||||
{"current_steps": 3745, "total_steps": 4039, "loss": 0.24, "lr": 6.4651875194087e-07, "epoch": 6.490893321769297, "percentage": 92.72, "elapsed_time": "15:05:46", "remaining_time": "1:11:06"}
|
||||
{"current_steps": 3750, "total_steps": 4039, "loss": 0.2528, "lr": 6.249024761684408e-07, "epoch": 6.499566348655681, "percentage": 92.84, "elapsed_time": "15:07:02", "remaining_time": "1:09:54"}
|
||||
{"current_steps": 3755, "total_steps": 4039, "loss": 0.2402, "lr": 6.036480050466931e-07, "epoch": 6.508239375542065, "percentage": 92.97, "elapsed_time": "15:08:19", "remaining_time": "1:08:41"}
|
||||
{"current_steps": 3760, "total_steps": 4039, "loss": 0.2229, "lr": 5.827557354751223e-07, "epoch": 6.5169124024284475, "percentage": 93.09, "elapsed_time": "15:09:33", "remaining_time": "1:07:29"}
|
||||
{"current_steps": 3765, "total_steps": 4039, "loss": 0.2359, "lr": 5.622260575895944e-07, "epoch": 6.525585429314831, "percentage": 93.22, "elapsed_time": "15:10:49", "remaining_time": "1:06:17"}
|
||||
{"current_steps": 3770, "total_steps": 4039, "loss": 0.2636, "lr": 5.420593547550334e-07, "epoch": 6.534258456201214, "percentage": 93.34, "elapsed_time": "15:11:57", "remaining_time": "1:05:04"}
|
||||
{"current_steps": 3775, "total_steps": 4039, "loss": 0.286, "lr": 5.22256003558288e-07, "epoch": 6.542931483087598, "percentage": 93.46, "elapsed_time": "15:13:08", "remaining_time": "1:03:51"}
|
||||
{"current_steps": 3780, "total_steps": 4039, "loss": 0.2247, "lr": 5.028163738010917e-07, "epoch": 6.551604509973981, "percentage": 93.59, "elapsed_time": "15:14:17", "remaining_time": "1:02:38"}
|
||||
{"current_steps": 3785, "total_steps": 4039, "loss": 0.2083, "lr": 4.837408284931444e-07, "epoch": 6.560277536860364, "percentage": 93.71, "elapsed_time": "15:15:28", "remaining_time": "1:01:26"}
|
||||
{"current_steps": 3790, "total_steps": 4039, "loss": 0.2507, "lr": 4.650297238453516e-07, "epoch": 6.568950563746748, "percentage": 93.84, "elapsed_time": "15:16:44", "remaining_time": "1:00:13"}
|
||||
{"current_steps": 3795, "total_steps": 4039, "loss": 0.2675, "lr": 4.4668340926316446e-07, "epoch": 6.577623590633131, "percentage": 93.96, "elapsed_time": "15:17:54", "remaining_time": "0:59:01"}
|
||||
{"current_steps": 3800, "total_steps": 4039, "loss": 0.2603, "lr": 4.287022273400565e-07, "epoch": 6.586296617519515, "percentage": 94.08, "elapsed_time": "15:19:11", "remaining_time": "0:57:48"}
|
||||
{"current_steps": 3805, "total_steps": 4039, "loss": 0.235, "lr": 4.110865138511244e-07, "epoch": 6.594969644405897, "percentage": 94.21, "elapsed_time": "15:20:30", "remaining_time": "0:56:36"}
|
||||
{"current_steps": 3810, "total_steps": 4039, "loss": 0.2438, "lr": 3.938365977468173e-07, "epoch": 6.603642671292281, "percentage": 94.33, "elapsed_time": "15:21:37", "remaining_time": "0:55:23"}
|
||||
{"current_steps": 3815, "total_steps": 4039, "loss": 0.2503, "lr": 3.769528011467993e-07, "epoch": 6.612315698178664, "percentage": 94.45, "elapsed_time": "15:22:47", "remaining_time": "0:54:10"}
|
||||
{"current_steps": 3820, "total_steps": 4039, "loss": 0.2811, "lr": 3.604354393339238e-07, "epoch": 6.620988725065048, "percentage": 94.58, "elapsed_time": "15:23:59", "remaining_time": "0:52:58"}
|
||||
{"current_steps": 3825, "total_steps": 4039, "loss": 0.231, "lr": 3.4428482074836623e-07, "epoch": 6.629661751951431, "percentage": 94.7, "elapsed_time": "15:25:18", "remaining_time": "0:51:46"}
|
||||
{"current_steps": 3830, "total_steps": 4039, "loss": 0.2425, "lr": 3.2850124698183827e-07, "epoch": 6.638334778837814, "percentage": 94.83, "elapsed_time": "15:26:33", "remaining_time": "0:50:33"}
|
||||
{"current_steps": 3835, "total_steps": 4039, "loss": 0.266, "lr": 3.1308501277197203e-07, "epoch": 6.647007805724198, "percentage": 94.95, "elapsed_time": "15:27:47", "remaining_time": "0:49:21"}
|
||||
{"current_steps": 3840, "total_steps": 4039, "loss": 0.2642, "lr": 2.9803640599681995e-07, "epoch": 6.655680832610581, "percentage": 95.07, "elapsed_time": "15:29:05", "remaining_time": "0:48:08"}
|
||||
{"current_steps": 3845, "total_steps": 4039, "loss": 0.2689, "lr": 2.833557076694571e-07, "epoch": 6.6643538594969645, "percentage": 95.2, "elapsed_time": "15:30:24", "remaining_time": "0:46:56"}
|
||||
{"current_steps": 3850, "total_steps": 4039, "loss": 0.2807, "lr": 2.690431919327674e-07, "epoch": 6.673026886383347, "percentage": 95.32, "elapsed_time": "15:31:37", "remaining_time": "0:45:44"}
|
||||
{"current_steps": 3855, "total_steps": 4039, "loss": 0.2457, "lr": 2.5509912605429233e-07, "epoch": 6.681699913269731, "percentage": 95.44, "elapsed_time": "15:32:49", "remaining_time": "0:44:31"}
|
||||
{"current_steps": 3860, "total_steps": 4039, "loss": 0.2452, "lr": 2.41523770421257e-07, "epoch": 6.690372940156115, "percentage": 95.57, "elapsed_time": "15:34:03", "remaining_time": "0:43:18"}
|
||||
{"current_steps": 3865, "total_steps": 4039, "loss": 0.2434, "lr": 2.2831737853570513e-07, "epoch": 6.6990459670424976, "percentage": 95.69, "elapsed_time": "15:35:22", "remaining_time": "0:42:06"}
|
||||
{"current_steps": 3870, "total_steps": 4039, "loss": 0.2298, "lr": 2.1548019700976308e-07, "epoch": 6.707718993928881, "percentage": 95.82, "elapsed_time": "15:36:28", "remaining_time": "0:40:53"}
|
||||
{"current_steps": 3875, "total_steps": 4039, "loss": 0.2505, "lr": 2.0301246556103437e-07, "epoch": 6.716392020815265, "percentage": 95.94, "elapsed_time": "15:37:35", "remaining_time": "0:39:40"}
|
||||
{"current_steps": 3880, "total_steps": 4039, "loss": 0.2672, "lr": 1.9091441700813008e-07, "epoch": 6.725065047701648, "percentage": 96.06, "elapsed_time": "15:38:49", "remaining_time": "0:38:28"}
|
||||
{"current_steps": 3885, "total_steps": 4039, "loss": 0.2611, "lr": 1.7918627726630777e-07, "epoch": 6.7337380745880315, "percentage": 96.19, "elapsed_time": "15:40:06", "remaining_time": "0:37:15"}
|
||||
{"current_steps": 3890, "total_steps": 4039, "loss": 0.2367, "lr": 1.6782826534326835e-07, "epoch": 6.742411101474414, "percentage": 96.31, "elapsed_time": "15:41:25", "remaining_time": "0:36:03"}
|
||||
{"current_steps": 3895, "total_steps": 4039, "loss": 0.1902, "lr": 1.5684059333505254e-07, "epoch": 6.751084128360798, "percentage": 96.43, "elapsed_time": "15:42:44", "remaining_time": "0:34:51"}
|
||||
{"current_steps": 3900, "total_steps": 4039, "loss": 0.2232, "lr": 1.4622346642209295e-07, "epoch": 6.759757155247181, "percentage": 96.56, "elapsed_time": "15:44:02", "remaining_time": "0:33:38"}
|
||||
{"current_steps": 3905, "total_steps": 4039, "loss": 0.2387, "lr": 1.359770828653728e-07, "epoch": 6.768430182133565, "percentage": 96.68, "elapsed_time": "15:45:08", "remaining_time": "0:32:25"}
|
||||
{"current_steps": 3910, "total_steps": 4039, "loss": 0.2365, "lr": 1.2610163400272657e-07, "epoch": 6.777103209019948, "percentage": 96.81, "elapsed_time": "15:46:16", "remaining_time": "0:31:13"}
|
||||
{"current_steps": 3915, "total_steps": 4039, "loss": 0.2348, "lr": 1.1659730424526949e-07, "epoch": 6.785776235906331, "percentage": 96.93, "elapsed_time": "15:47:33", "remaining_time": "0:30:00"}
|
||||
{"current_steps": 3920, "total_steps": 4039, "loss": 0.2399, "lr": 1.0746427107395151e-07, "epoch": 6.794449262792715, "percentage": 97.05, "elapsed_time": "15:48:52", "remaining_time": "0:28:48"}
|
||||
{"current_steps": 3925, "total_steps": 4039, "loss": 0.2355, "lr": 9.87027050362399e-08, "epoch": 6.803122289679098, "percentage": 97.18, "elapsed_time": "15:50:04", "remaining_time": "0:27:35"}
|
||||
{"current_steps": 3930, "total_steps": 4039, "loss": 0.2719, "lr": 9.031276974294622e-08, "epoch": 6.811795316565481, "percentage": 97.3, "elapsed_time": "15:51:24", "remaining_time": "0:26:23"}
|
||||
{"current_steps": 3935, "total_steps": 4039, "loss": 0.2081, "lr": 8.229462186515769e-08, "epoch": 6.820468343451864, "percentage": 97.43, "elapsed_time": "15:52:30", "remaining_time": "0:25:10"}
|
||||
{"current_steps": 3940, "total_steps": 4039, "loss": 0.2117, "lr": 7.464841113131504e-08, "epoch": 6.829141370338248, "percentage": 97.55, "elapsed_time": "15:53:42", "remaining_time": "0:23:57"}
|
||||
{"current_steps": 3945, "total_steps": 4039, "loss": 0.2581, "lr": 6.737428032442372e-08, "epoch": 6.837814397224632, "percentage": 97.67, "elapsed_time": "15:54:58", "remaining_time": "0:22:45"}
|
||||
{"current_steps": 3950, "total_steps": 4039, "loss": 0.2386, "lr": 6.047236527937594e-08, "epoch": 6.8464874241110145, "percentage": 97.8, "elapsed_time": "15:56:07", "remaining_time": "0:21:32"}
|
||||
{"current_steps": 3955, "total_steps": 4039, "loss": 0.2404, "lr": 5.394279488042831e-08, "epoch": 6.855160450997398, "percentage": 97.92, "elapsed_time": "15:57:22", "remaining_time": "0:20:20"}
|
||||
{"current_steps": 3960, "total_steps": 4039, "loss": 0.2151, "lr": 4.7785691058781505e-08, "epoch": 6.863833477883781, "percentage": 98.04, "elapsed_time": "15:58:38", "remaining_time": "0:19:07"}
|
||||
{"current_steps": 3965, "total_steps": 4039, "loss": 0.2525, "lr": 4.200116879031102e-08, "epoch": 6.872506504770165, "percentage": 98.17, "elapsed_time": "15:59:57", "remaining_time": "0:17:54"}
|
||||
{"current_steps": 3970, "total_steps": 4039, "loss": 0.2346, "lr": 3.658933609341775e-08, "epoch": 6.8811795316565485, "percentage": 98.29, "elapsed_time": "16:01:16", "remaining_time": "0:16:42"}
|
||||
{"current_steps": 3975, "total_steps": 4039, "loss": 0.2365, "lr": 3.155029402701182e-08, "epoch": 6.889852558542931, "percentage": 98.42, "elapsed_time": "16:02:27", "remaining_time": "0:15:29"}
|
||||
{"current_steps": 3980, "total_steps": 4039, "loss": 0.2933, "lr": 2.6884136688625218e-08, "epoch": 6.898525585429315, "percentage": 98.54, "elapsed_time": "16:03:39", "remaining_time": "0:14:17"}
|
||||
{"current_steps": 3985, "total_steps": 4039, "loss": 0.2367, "lr": 2.259095121265542e-08, "epoch": 6.907198612315698, "percentage": 98.66, "elapsed_time": "16:04:51", "remaining_time": "0:13:04"}
|
||||
{"current_steps": 3990, "total_steps": 4039, "loss": 0.2095, "lr": 1.8670817768733364e-08, "epoch": 6.915871639202082, "percentage": 98.79, "elapsed_time": "16:06:05", "remaining_time": "0:11:51"}
|
||||
{"current_steps": 3995, "total_steps": 4039, "loss": 0.2266, "lr": 1.5123809560233516e-08, "epoch": 6.924544666088465, "percentage": 98.91, "elapsed_time": "16:07:09", "remaining_time": "0:10:39"}
|
||||
{"current_steps": 4000, "total_steps": 4039, "loss": 0.2251, "lr": 1.194999282290832e-08, "epoch": 6.933217692974848, "percentage": 99.03, "elapsed_time": "16:08:21", "remaining_time": "0:09:26"}
|
||||
{"current_steps": 4005, "total_steps": 4039, "loss": 0.2256, "lr": 9.149426823633622e-09, "epoch": 6.941890719861232, "percentage": 99.16, "elapsed_time": "16:09:30", "remaining_time": "0:08:13"}
|
||||
{"current_steps": 4010, "total_steps": 4039, "loss": 0.2563, "lr": 6.722163859329556e-09, "epoch": 6.950563746747615, "percentage": 99.28, "elapsed_time": "16:10:38", "remaining_time": "0:07:01"}
|
||||
{"current_steps": 4015, "total_steps": 4039, "loss": 0.2209, "lr": 4.668249255961321e-09, "epoch": 6.959236773633998, "percentage": 99.41, "elapsed_time": "16:11:47", "remaining_time": "0:05:48"}
|
||||
{"current_steps": 4020, "total_steps": 4039, "loss": 0.2422, "lr": 2.98772136770209e-09, "epoch": 6.967909800520381, "percentage": 99.53, "elapsed_time": "16:12:57", "remaining_time": "0:04:35"}
|
||||
{"current_steps": 4025, "total_steps": 4039, "loss": 0.2171, "lr": 1.6806115762135754e-09, "epoch": 6.976582827406765, "percentage": 99.65, "elapsed_time": "16:14:05", "remaining_time": "0:03:23"}
|
||||
{"current_steps": 4030, "total_steps": 4039, "loss": 0.216, "lr": 7.469442900687185e-10, "epoch": 6.985255854293149, "percentage": 99.78, "elapsed_time": "16:15:12", "remaining_time": "0:02:10"}
|
||||
{"current_steps": 4035, "total_steps": 4039, "loss": 0.2716, "lr": 1.867369442853928e-10, "epoch": 6.9939288811795315, "percentage": 99.9, "elapsed_time": "16:16:19", "remaining_time": "0:00:58"}
|
||||
{"current_steps": 4039, "total_steps": 4039, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "16:17:49", "remaining_time": "0:00:00"}
|
||||
8924
trainer_state.json
Normal file
8924
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 sha256:3cd9e92642a9ea91ad3f69fb96b3a62bd343a2ca3a9addeb0bf73f0546857513
|
||||
size 8657
|
||||
BIN
training_loss.png
Normal file
BIN
training_loss.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 48 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