初始化项目,由ModelHub XC社区提供模型
Model: laion/exp_tas_timeout_multiplier_0_25_traces 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: exp_tas_timeout_multiplier_0_25_traces
|
||||
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. -->
|
||||
|
||||
# exp_tas_timeout_multiplier_0_25_traces
|
||||
|
||||
This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on the DCAgent/exp_tas_timeout_multiplier_0.25_traces 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 4.57.3
|
||||
- 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": 4.371088632174594,
|
||||
"achieved_tflops_per_gpu_theoretical": 1399.2045844459683,
|
||||
"epoch": 7.0,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.3092809319496155,
|
||||
"mfu_percent": 0.44197053914808837,
|
||||
"mfu_percent_theoretical": 141.47670216844978,
|
||||
"total_flos": 3.5061492931887104e+17,
|
||||
"train_loss": 0.4353422062565001,
|
||||
"train_runtime": 10026.5334,
|
||||
"train_samples_per_second": 6.605,
|
||||
"train_steps_per_second": 0.413,
|
||||
"valid_targets_mean": 1015.2,
|
||||
"valid_targets_min": 532
|
||||
}
|
||||
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": "4.57.3",
|
||||
"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": "4.57.3"
|
||||
}
|
||||
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:d3269fab3a2180d3a9702405fde1077338161a7c78192388d5bd57498c1d46a6
|
||||
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 sha256:17e347a74361b95868a8cc7e1e6ec2a62cb09e4091fbecef570c9929ecc61c49
|
||||
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 sha256:4da5b78c2428b8783fcfd6ab3313a7ce40a4ca9a5903f85b8284e366b0a76b7b
|
||||
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:ad684f81d25593dd72c3b718ca156bdd5c5abfce3dd9fd952e950b1fa78235b5
|
||||
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": "terminus-2",
|
||||
"training_start": null,
|
||||
"training_end": null,
|
||||
"created_by": "DCAgent",
|
||||
"base_model_name": "Qwen/Qwen3-8B",
|
||||
"dataset_name": "DCAgent/exp_tas_timeout_multiplier_0.25_traces",
|
||||
"training_type": "SFT",
|
||||
"training_parameters": "https://huggingface.co/laion/exp_tas_timeout_multiplier_0_25_traces/blob/main/config.json",
|
||||
"wandb_link": "https://wandb.ai/dogml/OpenThoughts-Agent/runs/sft_exp_tas_timeout_multiplier_0-25_traces_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
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
||||
size 11422654
|
||||
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": 4.371088632174594,
|
||||
"achieved_tflops_per_gpu_theoretical": 1399.2045844459683,
|
||||
"epoch": 7.0,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.3092809319496155,
|
||||
"mfu_percent": 0.44197053914808837,
|
||||
"mfu_percent_theoretical": 141.47670216844978,
|
||||
"total_flos": 3.5061492931887104e+17,
|
||||
"train_loss": 0.4353422062565001,
|
||||
"train_runtime": 10026.5334,
|
||||
"train_samples_per_second": 6.605,
|
||||
"train_steps_per_second": 0.413,
|
||||
"valid_targets_mean": 1015.2,
|
||||
"valid_targets_min": 532
|
||||
}
|
||||
829
trainer_log.jsonl
Normal file
829
trainer_log.jsonl
Normal file
@@ -0,0 +1,829 @@
|
||||
{"current_steps": 5, "total_steps": 4144, "loss": 1.1892, "lr": 3.855421686746989e-07, "epoch": 0.0084530853761623, "percentage": 0.12, "elapsed_time": "0:00:23", "remaining_time": "5:18:12"}
|
||||
{"current_steps": 10, "total_steps": 4144, "loss": 1.1909, "lr": 8.674698795180723e-07, "epoch": 0.0169061707523246, "percentage": 0.24, "elapsed_time": "0:00:37", "remaining_time": "4:20:54"}
|
||||
{"current_steps": 15, "total_steps": 4144, "loss": 1.2099, "lr": 1.349397590361446e-06, "epoch": 0.0253592561284869, "percentage": 0.36, "elapsed_time": "0:00:52", "remaining_time": "4:01:19"}
|
||||
{"current_steps": 20, "total_steps": 4144, "loss": 1.1232, "lr": 1.8313253012048193e-06, "epoch": 0.0338123415046492, "percentage": 0.48, "elapsed_time": "0:01:08", "remaining_time": "3:55:47"}
|
||||
{"current_steps": 25, "total_steps": 4144, "loss": 1.1038, "lr": 2.313253012048193e-06, "epoch": 0.042265426880811495, "percentage": 0.6, "elapsed_time": "0:01:23", "remaining_time": "3:48:48"}
|
||||
{"current_steps": 30, "total_steps": 4144, "loss": 1.0545, "lr": 2.7951807228915666e-06, "epoch": 0.0507185122569738, "percentage": 0.72, "elapsed_time": "0:01:39", "remaining_time": "3:46:58"}
|
||||
{"current_steps": 35, "total_steps": 4144, "loss": 1.0262, "lr": 3.2771084337349403e-06, "epoch": 0.05917159763313609, "percentage": 0.84, "elapsed_time": "0:01:53", "remaining_time": "3:42:16"}
|
||||
{"current_steps": 40, "total_steps": 4144, "loss": 1.015, "lr": 3.7590361445783136e-06, "epoch": 0.0676246830092984, "percentage": 0.97, "elapsed_time": "0:02:09", "remaining_time": "3:40:41"}
|
||||
{"current_steps": 45, "total_steps": 4144, "loss": 0.931, "lr": 4.240963855421687e-06, "epoch": 0.0760777683854607, "percentage": 1.09, "elapsed_time": "0:02:23", "remaining_time": "3:37:39"}
|
||||
{"current_steps": 50, "total_steps": 4144, "loss": 0.9053, "lr": 4.7228915662650606e-06, "epoch": 0.08453085376162299, "percentage": 1.21, "elapsed_time": "0:02:37", "remaining_time": "3:34:34"}
|
||||
{"current_steps": 55, "total_steps": 4144, "loss": 0.8944, "lr": 5.204819277108434e-06, "epoch": 0.09298393913778528, "percentage": 1.33, "elapsed_time": "0:02:50", "remaining_time": "3:30:53"}
|
||||
{"current_steps": 60, "total_steps": 4144, "loss": 0.8293, "lr": 5.686746987951808e-06, "epoch": 0.1014370245139476, "percentage": 1.45, "elapsed_time": "0:03:02", "remaining_time": "3:27:24"}
|
||||
{"current_steps": 65, "total_steps": 4144, "loss": 0.8331, "lr": 6.168674698795182e-06, "epoch": 0.10989010989010989, "percentage": 1.57, "elapsed_time": "0:03:16", "remaining_time": "3:25:35"}
|
||||
{"current_steps": 70, "total_steps": 4144, "loss": 0.7559, "lr": 6.6506024096385545e-06, "epoch": 0.11834319526627218, "percentage": 1.69, "elapsed_time": "0:03:28", "remaining_time": "3:22:26"}
|
||||
{"current_steps": 75, "total_steps": 4144, "loss": 0.7641, "lr": 7.132530120481929e-06, "epoch": 0.12679628064243448, "percentage": 1.81, "elapsed_time": "0:03:41", "remaining_time": "3:20:09"}
|
||||
{"current_steps": 80, "total_steps": 4144, "loss": 0.7635, "lr": 7.614457831325302e-06, "epoch": 0.1352493660185968, "percentage": 1.93, "elapsed_time": "0:03:54", "remaining_time": "3:18:48"}
|
||||
{"current_steps": 85, "total_steps": 4144, "loss": 0.7347, "lr": 8.096385542168676e-06, "epoch": 0.1437024513947591, "percentage": 2.05, "elapsed_time": "0:04:10", "remaining_time": "3:19:05"}
|
||||
{"current_steps": 90, "total_steps": 4144, "loss": 0.7447, "lr": 8.57831325301205e-06, "epoch": 0.1521555367709214, "percentage": 2.17, "elapsed_time": "0:04:22", "remaining_time": "3:17:05"}
|
||||
{"current_steps": 95, "total_steps": 4144, "loss": 0.6786, "lr": 9.060240963855423e-06, "epoch": 0.16060862214708369, "percentage": 2.29, "elapsed_time": "0:04:35", "remaining_time": "3:15:41"}
|
||||
{"current_steps": 100, "total_steps": 4144, "loss": 0.6916, "lr": 9.542168674698796e-06, "epoch": 0.16906170752324598, "percentage": 2.41, "elapsed_time": "0:04:48", "remaining_time": "3:14:26"}
|
||||
{"current_steps": 105, "total_steps": 4144, "loss": 0.7096, "lr": 1.002409638554217e-05, "epoch": 0.17751479289940827, "percentage": 2.53, "elapsed_time": "0:05:00", "remaining_time": "3:12:26"}
|
||||
{"current_steps": 110, "total_steps": 4144, "loss": 0.7169, "lr": 1.0506024096385542e-05, "epoch": 0.18596787827557057, "percentage": 2.65, "elapsed_time": "0:05:13", "remaining_time": "3:11:45"}
|
||||
{"current_steps": 115, "total_steps": 4144, "loss": 0.6696, "lr": 1.0987951807228916e-05, "epoch": 0.1944209636517329, "percentage": 2.78, "elapsed_time": "0:05:26", "remaining_time": "3:10:39"}
|
||||
{"current_steps": 120, "total_steps": 4144, "loss": 0.7062, "lr": 1.146987951807229e-05, "epoch": 0.2028740490278952, "percentage": 2.9, "elapsed_time": "0:05:40", "remaining_time": "3:10:20"}
|
||||
{"current_steps": 125, "total_steps": 4144, "loss": 0.6603, "lr": 1.1951807228915664e-05, "epoch": 0.21132713440405748, "percentage": 3.02, "elapsed_time": "0:05:53", "remaining_time": "3:09:31"}
|
||||
{"current_steps": 130, "total_steps": 4144, "loss": 0.6573, "lr": 1.2433734939759037e-05, "epoch": 0.21978021978021978, "percentage": 3.14, "elapsed_time": "0:06:05", "remaining_time": "3:08:10"}
|
||||
{"current_steps": 135, "total_steps": 4144, "loss": 0.6899, "lr": 1.291566265060241e-05, "epoch": 0.22823330515638207, "percentage": 3.26, "elapsed_time": "0:06:17", "remaining_time": "3:06:56"}
|
||||
{"current_steps": 140, "total_steps": 4144, "loss": 0.7076, "lr": 1.3397590361445785e-05, "epoch": 0.23668639053254437, "percentage": 3.38, "elapsed_time": "0:06:29", "remaining_time": "3:05:38"}
|
||||
{"current_steps": 145, "total_steps": 4144, "loss": 0.6918, "lr": 1.3879518072289157e-05, "epoch": 0.2451394759087067, "percentage": 3.5, "elapsed_time": "0:06:41", "remaining_time": "3:04:36"}
|
||||
{"current_steps": 150, "total_steps": 4144, "loss": 0.6942, "lr": 1.436144578313253e-05, "epoch": 0.25359256128486896, "percentage": 3.62, "elapsed_time": "0:06:53", "remaining_time": "3:03:23"}
|
||||
{"current_steps": 155, "total_steps": 4144, "loss": 0.6837, "lr": 1.4843373493975905e-05, "epoch": 0.26204564666103125, "percentage": 3.74, "elapsed_time": "0:07:06", "remaining_time": "3:02:56"}
|
||||
{"current_steps": 160, "total_steps": 4144, "loss": 0.6325, "lr": 1.532530120481928e-05, "epoch": 0.2704987320371936, "percentage": 3.86, "elapsed_time": "0:07:18", "remaining_time": "3:01:47"}
|
||||
{"current_steps": 165, "total_steps": 4144, "loss": 0.6327, "lr": 1.580722891566265e-05, "epoch": 0.2789518174133559, "percentage": 3.98, "elapsed_time": "0:07:29", "remaining_time": "3:00:46"}
|
||||
{"current_steps": 170, "total_steps": 4144, "loss": 0.6693, "lr": 1.6289156626506025e-05, "epoch": 0.2874049027895182, "percentage": 4.1, "elapsed_time": "0:07:41", "remaining_time": "2:59:39"}
|
||||
{"current_steps": 175, "total_steps": 4144, "loss": 0.6323, "lr": 1.67710843373494e-05, "epoch": 0.2958579881656805, "percentage": 4.22, "elapsed_time": "0:07:53", "remaining_time": "2:59:07"}
|
||||
{"current_steps": 180, "total_steps": 4144, "loss": 0.6363, "lr": 1.725301204819277e-05, "epoch": 0.3043110735418428, "percentage": 4.34, "elapsed_time": "0:08:06", "remaining_time": "2:58:42"}
|
||||
{"current_steps": 185, "total_steps": 4144, "loss": 0.627, "lr": 1.7734939759036146e-05, "epoch": 0.3127641589180051, "percentage": 4.46, "elapsed_time": "0:08:20", "remaining_time": "2:58:21"}
|
||||
{"current_steps": 190, "total_steps": 4144, "loss": 0.6267, "lr": 1.821686746987952e-05, "epoch": 0.32121724429416737, "percentage": 4.58, "elapsed_time": "0:08:32", "remaining_time": "2:57:48"}
|
||||
{"current_steps": 195, "total_steps": 4144, "loss": 0.6428, "lr": 1.8698795180722893e-05, "epoch": 0.32967032967032966, "percentage": 4.71, "elapsed_time": "0:08:44", "remaining_time": "2:57:11"}
|
||||
{"current_steps": 200, "total_steps": 4144, "loss": 0.6355, "lr": 1.9180722891566265e-05, "epoch": 0.33812341504649196, "percentage": 4.83, "elapsed_time": "0:08:56", "remaining_time": "2:56:24"}
|
||||
{"current_steps": 205, "total_steps": 4144, "loss": 0.6567, "lr": 1.966265060240964e-05, "epoch": 0.34657650042265425, "percentage": 4.95, "elapsed_time": "0:09:07", "remaining_time": "2:55:22"}
|
||||
{"current_steps": 210, "total_steps": 4144, "loss": 0.6746, "lr": 2.0144578313253014e-05, "epoch": 0.35502958579881655, "percentage": 5.07, "elapsed_time": "0:09:18", "remaining_time": "2:54:28"}
|
||||
{"current_steps": 215, "total_steps": 4144, "loss": 0.614, "lr": 2.062650602409639e-05, "epoch": 0.36348267117497884, "percentage": 5.19, "elapsed_time": "0:09:30", "remaining_time": "2:53:45"}
|
||||
{"current_steps": 220, "total_steps": 4144, "loss": 0.6562, "lr": 2.110843373493976e-05, "epoch": 0.37193575655114114, "percentage": 5.31, "elapsed_time": "0:09:43", "remaining_time": "2:53:28"}
|
||||
{"current_steps": 225, "total_steps": 4144, "loss": 0.6531, "lr": 2.1590361445783136e-05, "epoch": 0.3803888419273035, "percentage": 5.43, "elapsed_time": "0:09:56", "remaining_time": "2:53:07"}
|
||||
{"current_steps": 230, "total_steps": 4144, "loss": 0.6191, "lr": 2.207228915662651e-05, "epoch": 0.3888419273034658, "percentage": 5.55, "elapsed_time": "0:10:10", "remaining_time": "2:53:01"}
|
||||
{"current_steps": 235, "total_steps": 4144, "loss": 0.6637, "lr": 2.255421686746988e-05, "epoch": 0.3972950126796281, "percentage": 5.67, "elapsed_time": "0:10:21", "remaining_time": "2:52:13"}
|
||||
{"current_steps": 240, "total_steps": 4144, "loss": 0.6531, "lr": 2.3036144578313254e-05, "epoch": 0.4057480980557904, "percentage": 5.79, "elapsed_time": "0:10:35", "remaining_time": "2:52:13"}
|
||||
{"current_steps": 245, "total_steps": 4144, "loss": 0.6481, "lr": 2.351807228915663e-05, "epoch": 0.41420118343195267, "percentage": 5.91, "elapsed_time": "0:10:50", "remaining_time": "2:52:25"}
|
||||
{"current_steps": 250, "total_steps": 4144, "loss": 0.6625, "lr": 2.4e-05, "epoch": 0.42265426880811496, "percentage": 6.03, "elapsed_time": "0:11:01", "remaining_time": "2:51:50"}
|
||||
{"current_steps": 255, "total_steps": 4144, "loss": 0.6333, "lr": 2.4481927710843376e-05, "epoch": 0.43110735418427726, "percentage": 6.15, "elapsed_time": "0:11:14", "remaining_time": "2:51:21"}
|
||||
{"current_steps": 260, "total_steps": 4144, "loss": 0.5766, "lr": 2.496385542168675e-05, "epoch": 0.43956043956043955, "percentage": 6.27, "elapsed_time": "0:11:26", "remaining_time": "2:50:57"}
|
||||
{"current_steps": 265, "total_steps": 4144, "loss": 0.6231, "lr": 2.5445783132530122e-05, "epoch": 0.44801352493660185, "percentage": 6.39, "elapsed_time": "0:11:39", "remaining_time": "2:50:38"}
|
||||
{"current_steps": 270, "total_steps": 4144, "loss": 0.6109, "lr": 2.5927710843373497e-05, "epoch": 0.45646661031276414, "percentage": 6.52, "elapsed_time": "0:11:52", "remaining_time": "2:50:25"}
|
||||
{"current_steps": 275, "total_steps": 4144, "loss": 0.6267, "lr": 2.640963855421687e-05, "epoch": 0.46491969568892644, "percentage": 6.64, "elapsed_time": "0:12:04", "remaining_time": "2:49:55"}
|
||||
{"current_steps": 280, "total_steps": 4144, "loss": 0.6215, "lr": 2.6891566265060244e-05, "epoch": 0.47337278106508873, "percentage": 6.76, "elapsed_time": "0:12:15", "remaining_time": "2:49:05"}
|
||||
{"current_steps": 285, "total_steps": 4144, "loss": 0.6087, "lr": 2.737349397590362e-05, "epoch": 0.4818258664412511, "percentage": 6.88, "elapsed_time": "0:12:27", "remaining_time": "2:48:46"}
|
||||
{"current_steps": 290, "total_steps": 4144, "loss": 0.5679, "lr": 2.7855421686746987e-05, "epoch": 0.4902789518174134, "percentage": 7.0, "elapsed_time": "0:12:40", "remaining_time": "2:48:26"}
|
||||
{"current_steps": 295, "total_steps": 4144, "loss": 0.6338, "lr": 2.8337349397590365e-05, "epoch": 0.4987320371935757, "percentage": 7.12, "elapsed_time": "0:12:52", "remaining_time": "2:48:01"}
|
||||
{"current_steps": 300, "total_steps": 4144, "loss": 0.6199, "lr": 2.881927710843374e-05, "epoch": 0.5071851225697379, "percentage": 7.24, "elapsed_time": "0:13:04", "remaining_time": "2:47:31"}
|
||||
{"current_steps": 305, "total_steps": 4144, "loss": 0.6221, "lr": 2.9301204819277108e-05, "epoch": 0.5156382079459002, "percentage": 7.36, "elapsed_time": "0:13:15", "remaining_time": "2:46:55"}
|
||||
{"current_steps": 310, "total_steps": 4144, "loss": 0.6265, "lr": 2.9783132530120483e-05, "epoch": 0.5240912933220625, "percentage": 7.48, "elapsed_time": "0:13:29", "remaining_time": "2:46:55"}
|
||||
{"current_steps": 315, "total_steps": 4144, "loss": 0.6513, "lr": 3.0265060240963858e-05, "epoch": 0.5325443786982249, "percentage": 7.6, "elapsed_time": "0:13:41", "remaining_time": "2:46:21"}
|
||||
{"current_steps": 320, "total_steps": 4144, "loss": 0.5937, "lr": 3.074698795180723e-05, "epoch": 0.5409974640743872, "percentage": 7.72, "elapsed_time": "0:13:52", "remaining_time": "2:45:47"}
|
||||
{"current_steps": 325, "total_steps": 4144, "loss": 0.5974, "lr": 3.122891566265061e-05, "epoch": 0.5494505494505495, "percentage": 7.84, "elapsed_time": "0:14:04", "remaining_time": "2:45:24"}
|
||||
{"current_steps": 330, "total_steps": 4144, "loss": 0.5939, "lr": 3.171084337349398e-05, "epoch": 0.5579036348267118, "percentage": 7.96, "elapsed_time": "0:14:17", "remaining_time": "2:45:15"}
|
||||
{"current_steps": 335, "total_steps": 4144, "loss": 0.5841, "lr": 3.219277108433735e-05, "epoch": 0.5663567202028741, "percentage": 8.08, "elapsed_time": "0:14:29", "remaining_time": "2:44:48"}
|
||||
{"current_steps": 340, "total_steps": 4144, "loss": 0.6166, "lr": 3.267469879518072e-05, "epoch": 0.5748098055790364, "percentage": 8.2, "elapsed_time": "0:14:42", "remaining_time": "2:44:31"}
|
||||
{"current_steps": 345, "total_steps": 4144, "loss": 0.613, "lr": 3.31566265060241e-05, "epoch": 0.5832628909551987, "percentage": 8.33, "elapsed_time": "0:14:55", "remaining_time": "2:44:19"}
|
||||
{"current_steps": 350, "total_steps": 4144, "loss": 0.6287, "lr": 3.363855421686747e-05, "epoch": 0.591715976331361, "percentage": 8.45, "elapsed_time": "0:15:06", "remaining_time": "2:43:46"}
|
||||
{"current_steps": 355, "total_steps": 4144, "loss": 0.6111, "lr": 3.4120481927710844e-05, "epoch": 0.6001690617075233, "percentage": 8.57, "elapsed_time": "0:15:18", "remaining_time": "2:43:23"}
|
||||
{"current_steps": 360, "total_steps": 4144, "loss": 0.5737, "lr": 3.460240963855422e-05, "epoch": 0.6086221470836856, "percentage": 8.69, "elapsed_time": "0:15:29", "remaining_time": "2:42:54"}
|
||||
{"current_steps": 365, "total_steps": 4144, "loss": 0.5936, "lr": 3.5084337349397594e-05, "epoch": 0.6170752324598479, "percentage": 8.81, "elapsed_time": "0:15:41", "remaining_time": "2:42:26"}
|
||||
{"current_steps": 370, "total_steps": 4144, "loss": 0.6079, "lr": 3.5566265060240966e-05, "epoch": 0.6255283178360102, "percentage": 8.93, "elapsed_time": "0:15:52", "remaining_time": "2:41:59"}
|
||||
{"current_steps": 375, "total_steps": 4144, "loss": 0.5999, "lr": 3.604819277108434e-05, "epoch": 0.6339814032121724, "percentage": 9.05, "elapsed_time": "0:16:04", "remaining_time": "2:41:38"}
|
||||
{"current_steps": 380, "total_steps": 4144, "loss": 0.5842, "lr": 3.6530120481927716e-05, "epoch": 0.6424344885883347, "percentage": 9.17, "elapsed_time": "0:16:17", "remaining_time": "2:41:23"}
|
||||
{"current_steps": 385, "total_steps": 4144, "loss": 0.5815, "lr": 3.701204819277109e-05, "epoch": 0.650887573964497, "percentage": 9.29, "elapsed_time": "0:16:29", "remaining_time": "2:41:00"}
|
||||
{"current_steps": 390, "total_steps": 4144, "loss": 0.5935, "lr": 3.749397590361446e-05, "epoch": 0.6593406593406593, "percentage": 9.41, "elapsed_time": "0:16:41", "remaining_time": "2:40:36"}
|
||||
{"current_steps": 395, "total_steps": 4144, "loss": 0.5798, "lr": 3.797590361445784e-05, "epoch": 0.6677937447168216, "percentage": 9.53, "elapsed_time": "0:16:53", "remaining_time": "2:40:16"}
|
||||
{"current_steps": 400, "total_steps": 4144, "loss": 0.6184, "lr": 3.845783132530121e-05, "epoch": 0.6762468300929839, "percentage": 9.65, "elapsed_time": "0:17:07", "remaining_time": "2:40:13"}
|
||||
{"current_steps": 405, "total_steps": 4144, "loss": 0.5632, "lr": 3.893975903614458e-05, "epoch": 0.6846999154691462, "percentage": 9.77, "elapsed_time": "0:17:18", "remaining_time": "2:39:51"}
|
||||
{"current_steps": 410, "total_steps": 4144, "loss": 0.5849, "lr": 3.942168674698795e-05, "epoch": 0.6931530008453085, "percentage": 9.89, "elapsed_time": "0:17:30", "remaining_time": "2:39:26"}
|
||||
{"current_steps": 415, "total_steps": 4144, "loss": 0.5874, "lr": 3.990361445783133e-05, "epoch": 0.7016060862214708, "percentage": 10.01, "elapsed_time": "0:17:41", "remaining_time": "2:39:01"}
|
||||
{"current_steps": 420, "total_steps": 4144, "loss": 0.5888, "lr": 3.999988643760311e-05, "epoch": 0.7100591715976331, "percentage": 10.14, "elapsed_time": "0:17:54", "remaining_time": "2:38:48"}
|
||||
{"current_steps": 425, "total_steps": 4144, "loss": 0.6278, "lr": 3.999942509257603e-05, "epoch": 0.7185122569737954, "percentage": 10.26, "elapsed_time": "0:18:07", "remaining_time": "2:38:36"}
|
||||
{"current_steps": 430, "total_steps": 4144, "loss": 0.598, "lr": 3.9998608875448804e-05, "epoch": 0.7269653423499577, "percentage": 10.38, "elapsed_time": "0:18:19", "remaining_time": "2:38:19"}
|
||||
{"current_steps": 435, "total_steps": 4144, "loss": 0.5662, "lr": 3.9997437800704486e-05, "epoch": 0.73541842772612, "percentage": 10.5, "elapsed_time": "0:18:32", "remaining_time": "2:38:02"}
|
||||
{"current_steps": 440, "total_steps": 4144, "loss": 0.612, "lr": 3.9995911889122764e-05, "epoch": 0.7438715131022823, "percentage": 10.62, "elapsed_time": "0:18:45", "remaining_time": "2:37:56"}
|
||||
{"current_steps": 445, "total_steps": 4144, "loss": 0.5787, "lr": 3.999403116777959e-05, "epoch": 0.7523245984784447, "percentage": 10.74, "elapsed_time": "0:18:56", "remaining_time": "2:37:28"}
|
||||
{"current_steps": 450, "total_steps": 4144, "loss": 0.5681, "lr": 3.999179567004669e-05, "epoch": 0.760777683854607, "percentage": 10.86, "elapsed_time": "0:19:08", "remaining_time": "2:37:07"}
|
||||
{"current_steps": 455, "total_steps": 4144, "loss": 0.61, "lr": 3.998920543559101e-05, "epoch": 0.7692307692307693, "percentage": 10.98, "elapsed_time": "0:19:20", "remaining_time": "2:36:51"}
|
||||
{"current_steps": 460, "total_steps": 4144, "loss": 0.6054, "lr": 3.998626051037396e-05, "epoch": 0.7776838546069316, "percentage": 11.1, "elapsed_time": "0:19:34", "remaining_time": "2:36:48"}
|
||||
{"current_steps": 465, "total_steps": 4144, "loss": 0.567, "lr": 3.998296094665062e-05, "epoch": 0.7861369399830939, "percentage": 11.22, "elapsed_time": "0:19:47", "remaining_time": "2:36:33"}
|
||||
{"current_steps": 470, "total_steps": 4144, "loss": 0.5849, "lr": 3.9979306802968845e-05, "epoch": 0.7945900253592562, "percentage": 11.34, "elapsed_time": "0:20:00", "remaining_time": "2:36:21"}
|
||||
{"current_steps": 475, "total_steps": 4144, "loss": 0.5722, "lr": 3.997529814416818e-05, "epoch": 0.8030431107354185, "percentage": 11.46, "elapsed_time": "0:20:13", "remaining_time": "2:36:13"}
|
||||
{"current_steps": 480, "total_steps": 4144, "loss": 0.6183, "lr": 3.997093504137872e-05, "epoch": 0.8114961961115807, "percentage": 11.58, "elapsed_time": "0:20:25", "remaining_time": "2:35:53"}
|
||||
{"current_steps": 485, "total_steps": 4144, "loss": 0.5773, "lr": 3.996621757201986e-05, "epoch": 0.819949281487743, "percentage": 11.7, "elapsed_time": "0:20:35", "remaining_time": "2:35:23"}
|
||||
{"current_steps": 490, "total_steps": 4144, "loss": 0.5949, "lr": 3.996114581979893e-05, "epoch": 0.8284023668639053, "percentage": 11.82, "elapsed_time": "0:20:47", "remaining_time": "2:35:05"}
|
||||
{"current_steps": 495, "total_steps": 4144, "loss": 0.5959, "lr": 3.995571987470968e-05, "epoch": 0.8368554522400676, "percentage": 11.94, "elapsed_time": "0:20:59", "remaining_time": "2:34:45"}
|
||||
{"current_steps": 500, "total_steps": 4144, "loss": 0.5792, "lr": 3.99499398330307e-05, "epoch": 0.8453085376162299, "percentage": 12.07, "elapsed_time": "0:21:11", "remaining_time": "2:34:29"}
|
||||
{"current_steps": 505, "total_steps": 4144, "loss": 0.5905, "lr": 3.994380579732372e-05, "epoch": 0.8537616229923922, "percentage": 12.19, "elapsed_time": "0:21:22", "remaining_time": "2:34:02"}
|
||||
{"current_steps": 510, "total_steps": 4144, "loss": 0.5441, "lr": 3.993731787643178e-05, "epoch": 0.8622147083685545, "percentage": 12.31, "elapsed_time": "0:21:36", "remaining_time": "2:34:01"}
|
||||
{"current_steps": 515, "total_steps": 4144, "loss": 0.5838, "lr": 3.9930476185477286e-05, "epoch": 0.8706677937447168, "percentage": 12.43, "elapsed_time": "0:21:48", "remaining_time": "2:33:37"}
|
||||
{"current_steps": 520, "total_steps": 4144, "loss": 0.5815, "lr": 3.992328084585999e-05, "epoch": 0.8791208791208791, "percentage": 12.55, "elapsed_time": "0:21:59", "remaining_time": "2:33:16"}
|
||||
{"current_steps": 525, "total_steps": 4144, "loss": 0.5448, "lr": 3.991573198525484e-05, "epoch": 0.8875739644970414, "percentage": 12.67, "elapsed_time": "0:22:11", "remaining_time": "2:32:57"}
|
||||
{"current_steps": 530, "total_steps": 4144, "loss": 0.5556, "lr": 3.9907829737609664e-05, "epoch": 0.8960270498732037, "percentage": 12.79, "elapsed_time": "0:22:23", "remaining_time": "2:32:40"}
|
||||
{"current_steps": 535, "total_steps": 4144, "loss": 0.587, "lr": 3.989957424314287e-05, "epoch": 0.904480135249366, "percentage": 12.91, "elapsed_time": "0:22:36", "remaining_time": "2:32:28"}
|
||||
{"current_steps": 540, "total_steps": 4144, "loss": 0.587, "lr": 3.98909656483409e-05, "epoch": 0.9129332206255283, "percentage": 13.03, "elapsed_time": "0:22:47", "remaining_time": "2:32:05"}
|
||||
{"current_steps": 545, "total_steps": 4144, "loss": 0.5533, "lr": 3.988200410595564e-05, "epoch": 0.9213863060016906, "percentage": 13.15, "elapsed_time": "0:22:59", "remaining_time": "2:31:47"}
|
||||
{"current_steps": 550, "total_steps": 4144, "loss": 0.5688, "lr": 3.9872689775001745e-05, "epoch": 0.9298393913778529, "percentage": 13.27, "elapsed_time": "0:23:10", "remaining_time": "2:31:25"}
|
||||
{"current_steps": 555, "total_steps": 4144, "loss": 0.5317, "lr": 3.986302282075377e-05, "epoch": 0.9382924767540152, "percentage": 13.39, "elapsed_time": "0:23:22", "remaining_time": "2:31:07"}
|
||||
{"current_steps": 560, "total_steps": 4144, "loss": 0.5451, "lr": 3.985300341474325e-05, "epoch": 0.9467455621301775, "percentage": 13.51, "elapsed_time": "0:23:34", "remaining_time": "2:30:54"}
|
||||
{"current_steps": 565, "total_steps": 4144, "loss": 0.5423, "lr": 3.9842631734755696e-05, "epoch": 0.9551986475063398, "percentage": 13.63, "elapsed_time": "0:23:47", "remaining_time": "2:30:42"}
|
||||
{"current_steps": 570, "total_steps": 4144, "loss": 0.5919, "lr": 3.9831907964827386e-05, "epoch": 0.9636517328825022, "percentage": 13.75, "elapsed_time": "0:23:58", "remaining_time": "2:30:17"}
|
||||
{"current_steps": 575, "total_steps": 4144, "loss": 0.6039, "lr": 3.982083229524213e-05, "epoch": 0.9721048182586645, "percentage": 13.88, "elapsed_time": "0:24:09", "remaining_time": "2:29:59"}
|
||||
{"current_steps": 580, "total_steps": 4144, "loss": 0.5927, "lr": 3.9809404922527865e-05, "epoch": 0.9805579036348268, "percentage": 14.0, "elapsed_time": "0:24:22", "remaining_time": "2:29:48"}
|
||||
{"current_steps": 585, "total_steps": 4144, "loss": 0.5799, "lr": 3.979762604945324e-05, "epoch": 0.989010989010989, "percentage": 14.12, "elapsed_time": "0:24:36", "remaining_time": "2:29:40"}
|
||||
{"current_steps": 590, "total_steps": 4144, "loss": 0.5604, "lr": 3.97854958850239e-05, "epoch": 0.9974640743871513, "percentage": 14.24, "elapsed_time": "0:24:49", "remaining_time": "2:29:32"}
|
||||
{"current_steps": 595, "total_steps": 4144, "loss": 0.5785, "lr": 3.97730146444789e-05, "epoch": 1.0050718512256973, "percentage": 14.36, "elapsed_time": "0:25:00", "remaining_time": "2:29:11"}
|
||||
{"current_steps": 600, "total_steps": 4144, "loss": 0.5621, "lr": 3.97601825492868e-05, "epoch": 1.0135249366018597, "percentage": 14.48, "elapsed_time": "0:25:13", "remaining_time": "2:28:58"}
|
||||
{"current_steps": 605, "total_steps": 4144, "loss": 0.5452, "lr": 3.974699982714178e-05, "epoch": 1.021978021978022, "percentage": 14.6, "elapsed_time": "0:25:25", "remaining_time": "2:28:41"}
|
||||
{"current_steps": 610, "total_steps": 4144, "loss": 0.518, "lr": 3.973346671195958e-05, "epoch": 1.0304311073541843, "percentage": 14.72, "elapsed_time": "0:25:37", "remaining_time": "2:28:24"}
|
||||
{"current_steps": 615, "total_steps": 4144, "loss": 0.5522, "lr": 3.971958344387335e-05, "epoch": 1.0388841927303465, "percentage": 14.84, "elapsed_time": "0:25:49", "remaining_time": "2:28:09"}
|
||||
{"current_steps": 620, "total_steps": 4144, "loss": 0.5562, "lr": 3.9705350269229386e-05, "epoch": 1.047337278106509, "percentage": 14.96, "elapsed_time": "0:26:00", "remaining_time": "2:27:48"}
|
||||
{"current_steps": 625, "total_steps": 4144, "loss": 0.5368, "lr": 3.9690767440582784e-05, "epoch": 1.055790363482671, "percentage": 15.08, "elapsed_time": "0:26:12", "remaining_time": "2:27:36"}
|
||||
{"current_steps": 630, "total_steps": 4144, "loss": 0.5019, "lr": 3.967583521669294e-05, "epoch": 1.0642434488588335, "percentage": 15.2, "elapsed_time": "0:26:24", "remaining_time": "2:27:15"}
|
||||
{"current_steps": 635, "total_steps": 4144, "loss": 0.5136, "lr": 3.966055386251895e-05, "epoch": 1.072696534234996, "percentage": 15.32, "elapsed_time": "0:26:35", "remaining_time": "2:26:57"}
|
||||
{"current_steps": 640, "total_steps": 4144, "loss": 0.5326, "lr": 3.9644923649214915e-05, "epoch": 1.081149619611158, "percentage": 15.44, "elapsed_time": "0:26:47", "remaining_time": "2:26:38"}
|
||||
{"current_steps": 645, "total_steps": 4144, "loss": 0.5457, "lr": 3.9628944854125144e-05, "epoch": 1.0896027049873203, "percentage": 15.56, "elapsed_time": "0:26:58", "remaining_time": "2:26:20"}
|
||||
{"current_steps": 650, "total_steps": 4144, "loss": 0.5591, "lr": 3.961261776077922e-05, "epoch": 1.0980557903634827, "percentage": 15.69, "elapsed_time": "0:27:10", "remaining_time": "2:26:03"}
|
||||
{"current_steps": 655, "total_steps": 4144, "loss": 0.5389, "lr": 3.9595942658886946e-05, "epoch": 1.106508875739645, "percentage": 15.81, "elapsed_time": "0:27:22", "remaining_time": "2:25:46"}
|
||||
{"current_steps": 660, "total_steps": 4144, "loss": 0.5209, "lr": 3.957891984433327e-05, "epoch": 1.1149619611158073, "percentage": 15.93, "elapsed_time": "0:27:33", "remaining_time": "2:25:26"}
|
||||
{"current_steps": 665, "total_steps": 4144, "loss": 0.5245, "lr": 3.956154961917297e-05, "epoch": 1.1234150464919697, "percentage": 16.05, "elapsed_time": "0:27:44", "remaining_time": "2:25:08"}
|
||||
{"current_steps": 670, "total_steps": 4144, "loss": 0.5121, "lr": 3.954383229162531e-05, "epoch": 1.1318681318681318, "percentage": 16.17, "elapsed_time": "0:27:56", "remaining_time": "2:24:51"}
|
||||
{"current_steps": 675, "total_steps": 4144, "loss": 0.5199, "lr": 3.952576817606859e-05, "epoch": 1.1403212172442942, "percentage": 16.29, "elapsed_time": "0:28:08", "remaining_time": "2:24:35"}
|
||||
{"current_steps": 680, "total_steps": 4144, "loss": 0.5409, "lr": 3.950735759303456e-05, "epoch": 1.1487743026204564, "percentage": 16.41, "elapsed_time": "0:28:19", "remaining_time": "2:24:17"}
|
||||
{"current_steps": 685, "total_steps": 4144, "loss": 0.5298, "lr": 3.948860086920273e-05, "epoch": 1.1572273879966188, "percentage": 16.53, "elapsed_time": "0:28:30", "remaining_time": "2:23:59"}
|
||||
{"current_steps": 690, "total_steps": 4144, "loss": 0.5228, "lr": 3.9469498337394555e-05, "epoch": 1.165680473372781, "percentage": 16.65, "elapsed_time": "0:28:42", "remaining_time": "2:23:41"}
|
||||
{"current_steps": 695, "total_steps": 4144, "loss": 0.5045, "lr": 3.945005033656756e-05, "epoch": 1.1741335587489434, "percentage": 16.77, "elapsed_time": "0:28:54", "remaining_time": "2:23:29"}
|
||||
{"current_steps": 700, "total_steps": 4144, "loss": 0.5396, "lr": 3.9430257211809306e-05, "epoch": 1.1825866441251056, "percentage": 16.89, "elapsed_time": "0:29:06", "remaining_time": "2:23:13"}
|
||||
{"current_steps": 705, "total_steps": 4144, "loss": 0.5574, "lr": 3.941011931433129e-05, "epoch": 1.191039729501268, "percentage": 17.01, "elapsed_time": "0:29:18", "remaining_time": "2:22:57"}
|
||||
{"current_steps": 710, "total_steps": 4144, "loss": 0.5278, "lr": 3.9389637001462664e-05, "epoch": 1.1994928148774302, "percentage": 17.13, "elapsed_time": "0:29:32", "remaining_time": "2:22:53"}
|
||||
{"current_steps": 715, "total_steps": 4144, "loss": 0.501, "lr": 3.936881063664395e-05, "epoch": 1.2079459002535926, "percentage": 17.25, "elapsed_time": "0:29:44", "remaining_time": "2:22:35"}
|
||||
{"current_steps": 720, "total_steps": 4144, "loss": 0.4902, "lr": 3.934764058942058e-05, "epoch": 1.2163989856297548, "percentage": 17.37, "elapsed_time": "0:29:56", "remaining_time": "2:22:22"}
|
||||
{"current_steps": 725, "total_steps": 4144, "loss": 0.5602, "lr": 3.932612723543628e-05, "epoch": 1.2248520710059172, "percentage": 17.5, "elapsed_time": "0:30:08", "remaining_time": "2:22:10"}
|
||||
{"current_steps": 730, "total_steps": 4144, "loss": 0.5213, "lr": 3.93042709564265e-05, "epoch": 1.2333051563820794, "percentage": 17.62, "elapsed_time": "0:30:20", "remaining_time": "2:21:53"}
|
||||
{"current_steps": 735, "total_steps": 4144, "loss": 0.5359, "lr": 3.928207214021156e-05, "epoch": 1.2417582417582418, "percentage": 17.74, "elapsed_time": "0:30:32", "remaining_time": "2:21:40"}
|
||||
{"current_steps": 740, "total_steps": 4144, "loss": 0.4942, "lr": 3.9259531180689804e-05, "epoch": 1.2502113271344042, "percentage": 17.86, "elapsed_time": "0:30:44", "remaining_time": "2:21:24"}
|
||||
{"current_steps": 745, "total_steps": 4144, "loss": 0.4902, "lr": 3.9236648477830626e-05, "epoch": 1.2586644125105664, "percentage": 17.98, "elapsed_time": "0:30:56", "remaining_time": "2:21:08"}
|
||||
{"current_steps": 750, "total_steps": 4144, "loss": 0.559, "lr": 3.921342443766733e-05, "epoch": 1.2671174978867286, "percentage": 18.1, "elapsed_time": "0:31:07", "remaining_time": "2:20:50"}
|
||||
{"current_steps": 755, "total_steps": 4144, "loss": 0.5342, "lr": 3.9189859472289956e-05, "epoch": 1.275570583262891, "percentage": 18.22, "elapsed_time": "0:31:18", "remaining_time": "2:20:33"}
|
||||
{"current_steps": 760, "total_steps": 4144, "loss": 0.5328, "lr": 3.916595399983796e-05, "epoch": 1.2840236686390534, "percentage": 18.34, "elapsed_time": "0:31:29", "remaining_time": "2:20:15"}
|
||||
{"current_steps": 765, "total_steps": 4144, "loss": 0.4986, "lr": 3.91417084444928e-05, "epoch": 1.2924767540152156, "percentage": 18.46, "elapsed_time": "0:31:42", "remaining_time": "2:20:01"}
|
||||
{"current_steps": 770, "total_steps": 4144, "loss": 0.5048, "lr": 3.91171232364704e-05, "epoch": 1.3009298393913777, "percentage": 18.58, "elapsed_time": "0:31:54", "remaining_time": "2:19:48"}
|
||||
{"current_steps": 775, "total_steps": 4144, "loss": 0.4943, "lr": 3.9092198812013515e-05, "epoch": 1.3093829247675401, "percentage": 18.7, "elapsed_time": "0:32:06", "remaining_time": "2:19:33"}
|
||||
{"current_steps": 780, "total_steps": 4144, "loss": 0.5023, "lr": 3.9066935613384004e-05, "epoch": 1.3178360101437026, "percentage": 18.82, "elapsed_time": "0:32:19", "remaining_time": "2:19:22"}
|
||||
{"current_steps": 785, "total_steps": 4144, "loss": 0.5419, "lr": 3.9041334088854984e-05, "epoch": 1.3262890955198647, "percentage": 18.94, "elapsed_time": "0:32:30", "remaining_time": "2:19:05"}
|
||||
{"current_steps": 790, "total_steps": 4144, "loss": 0.5153, "lr": 3.901539469270283e-05, "epoch": 1.334742180896027, "percentage": 19.06, "elapsed_time": "0:32:41", "remaining_time": "2:18:48"}
|
||||
{"current_steps": 795, "total_steps": 4144, "loss": 0.5364, "lr": 3.8989117885199184e-05, "epoch": 1.3431952662721893, "percentage": 19.18, "elapsed_time": "0:32:54", "remaining_time": "2:18:39"}
|
||||
{"current_steps": 800, "total_steps": 4144, "loss": 0.5061, "lr": 3.896250413260273e-05, "epoch": 1.3516483516483517, "percentage": 19.31, "elapsed_time": "0:33:06", "remaining_time": "2:18:24"}
|
||||
{"current_steps": 805, "total_steps": 4144, "loss": 0.5383, "lr": 3.8935553907150974e-05, "epoch": 1.360101437024514, "percentage": 19.43, "elapsed_time": "0:33:18", "remaining_time": "2:18:11"}
|
||||
{"current_steps": 810, "total_steps": 4144, "loss": 0.526, "lr": 3.8908267687051806e-05, "epoch": 1.3685545224006763, "percentage": 19.55, "elapsed_time": "0:33:30", "remaining_time": "2:17:54"}
|
||||
{"current_steps": 815, "total_steps": 4144, "loss": 0.5069, "lr": 3.8880645956475064e-05, "epoch": 1.3770076077768385, "percentage": 19.67, "elapsed_time": "0:33:42", "remaining_time": "2:17:43"}
|
||||
{"current_steps": 820, "total_steps": 4144, "loss": 0.5089, "lr": 3.88526892055439e-05, "epoch": 1.385460693153001, "percentage": 19.79, "elapsed_time": "0:33:55", "remaining_time": "2:17:29"}
|
||||
{"current_steps": 825, "total_steps": 4144, "loss": 0.5299, "lr": 3.882439793032614e-05, "epoch": 1.393913778529163, "percentage": 19.91, "elapsed_time": "0:34:06", "remaining_time": "2:17:12"}
|
||||
{"current_steps": 830, "total_steps": 4144, "loss": 0.5354, "lr": 3.8795772632825405e-05, "epoch": 1.4023668639053255, "percentage": 20.03, "elapsed_time": "0:34:18", "remaining_time": "2:16:57"}
|
||||
{"current_steps": 835, "total_steps": 4144, "loss": 0.5106, "lr": 3.8766813820972276e-05, "epoch": 1.4108199492814877, "percentage": 20.15, "elapsed_time": "0:34:30", "remaining_time": "2:16:43"}
|
||||
{"current_steps": 840, "total_steps": 4144, "loss": 0.5126, "lr": 3.8737522008615247e-05, "epoch": 1.41927303465765, "percentage": 20.27, "elapsed_time": "0:34:43", "remaining_time": "2:16:33"}
|
||||
{"current_steps": 845, "total_steps": 4144, "loss": 0.5388, "lr": 3.87078977155116e-05, "epoch": 1.4277261200338123, "percentage": 20.39, "elapsed_time": "0:34:54", "remaining_time": "2:16:16"}
|
||||
{"current_steps": 850, "total_steps": 4144, "loss": 0.5573, "lr": 3.867794146731822e-05, "epoch": 1.4361792054099747, "percentage": 20.51, "elapsed_time": "0:35:05", "remaining_time": "2:15:58"}
|
||||
{"current_steps": 855, "total_steps": 4144, "loss": 0.5282, "lr": 3.864765379558219e-05, "epoch": 1.4446322907861369, "percentage": 20.63, "elapsed_time": "0:35:18", "remaining_time": "2:15:48"}
|
||||
{"current_steps": 860, "total_steps": 4144, "loss": 0.5003, "lr": 3.861703523773146e-05, "epoch": 1.4530853761622993, "percentage": 20.75, "elapsed_time": "0:35:29", "remaining_time": "2:15:32"}
|
||||
{"current_steps": 865, "total_steps": 4144, "loss": 0.5406, "lr": 3.858608633706525e-05, "epoch": 1.4615384615384617, "percentage": 20.87, "elapsed_time": "0:35:41", "remaining_time": "2:15:17"}
|
||||
{"current_steps": 870, "total_steps": 4144, "loss": 0.5505, "lr": 3.855480764274441e-05, "epoch": 1.4699915469146239, "percentage": 20.99, "elapsed_time": "0:35:52", "remaining_time": "2:15:02"}
|
||||
{"current_steps": 875, "total_steps": 4144, "loss": 0.5153, "lr": 3.852319970978168e-05, "epoch": 1.478444632290786, "percentage": 21.11, "elapsed_time": "0:36:04", "remaining_time": "2:14:47"}
|
||||
{"current_steps": 880, "total_steps": 4144, "loss": 0.5124, "lr": 3.8491263099031874e-05, "epoch": 1.4868977176669484, "percentage": 21.24, "elapsed_time": "0:36:15", "remaining_time": "2:14:30"}
|
||||
{"current_steps": 885, "total_steps": 4144, "loss": 0.5308, "lr": 3.845899837718188e-05, "epoch": 1.4953508030431109, "percentage": 21.36, "elapsed_time": "0:36:28", "remaining_time": "2:14:19"}
|
||||
{"current_steps": 890, "total_steps": 4144, "loss": 0.5386, "lr": 3.842640611674064e-05, "epoch": 1.503803888419273, "percentage": 21.48, "elapsed_time": "0:36:40", "remaining_time": "2:14:05"}
|
||||
{"current_steps": 895, "total_steps": 4144, "loss": 0.5086, "lr": 3.839348689602897e-05, "epoch": 1.5122569737954352, "percentage": 21.6, "elapsed_time": "0:36:51", "remaining_time": "2:13:47"}
|
||||
{"current_steps": 900, "total_steps": 4144, "loss": 0.5522, "lr": 3.836024129916931e-05, "epoch": 1.5207100591715976, "percentage": 21.72, "elapsed_time": "0:37:03", "remaining_time": "2:13:35"}
|
||||
{"current_steps": 905, "total_steps": 4144, "loss": 0.5241, "lr": 3.832666991607536e-05, "epoch": 1.52916314454776, "percentage": 21.84, "elapsed_time": "0:37:15", "remaining_time": "2:13:19"}
|
||||
{"current_steps": 910, "total_steps": 4144, "loss": 0.5006, "lr": 3.82927733424416e-05, "epoch": 1.5376162299239222, "percentage": 21.96, "elapsed_time": "0:37:27", "remaining_time": "2:13:06"}
|
||||
{"current_steps": 915, "total_steps": 4144, "loss": 0.511, "lr": 3.8258552179732736e-05, "epoch": 1.5460693153000844, "percentage": 22.08, "elapsed_time": "0:37:38", "remaining_time": "2:12:49"}
|
||||
{"current_steps": 920, "total_steps": 4144, "loss": 0.52, "lr": 3.822400703517301e-05, "epoch": 1.5545224006762468, "percentage": 22.2, "elapsed_time": "0:37:50", "remaining_time": "2:12:36"}
|
||||
{"current_steps": 925, "total_steps": 4144, "loss": 0.5468, "lr": 3.8189138521735454e-05, "epoch": 1.5629754860524092, "percentage": 22.32, "elapsed_time": "0:38:02", "remaining_time": "2:12:21"}
|
||||
{"current_steps": 930, "total_steps": 4144, "loss": 0.5113, "lr": 3.8153947258130976e-05, "epoch": 1.5714285714285714, "percentage": 22.44, "elapsed_time": "0:38:13", "remaining_time": "2:12:07"}
|
||||
{"current_steps": 935, "total_steps": 4144, "loss": 0.5643, "lr": 3.8118433868797406e-05, "epoch": 1.5798816568047336, "percentage": 22.56, "elapsed_time": "0:38:27", "remaining_time": "2:12:00"}
|
||||
{"current_steps": 940, "total_steps": 4144, "loss": 0.4803, "lr": 3.8082598983888414e-05, "epoch": 1.588334742180896, "percentage": 22.68, "elapsed_time": "0:38:39", "remaining_time": "2:11:45"}
|
||||
{"current_steps": 945, "total_steps": 4144, "loss": 0.5492, "lr": 3.804644323926232e-05, "epoch": 1.5967878275570584, "percentage": 22.8, "elapsed_time": "0:38:51", "remaining_time": "2:11:33"}
|
||||
{"current_steps": 950, "total_steps": 4144, "loss": 0.5258, "lr": 3.800996727647081e-05, "epoch": 1.6052409129332206, "percentage": 22.92, "elapsed_time": "0:39:02", "remaining_time": "2:11:17"}
|
||||
{"current_steps": 955, "total_steps": 4144, "loss": 0.5135, "lr": 3.7973171742747584e-05, "epoch": 1.6136939983093828, "percentage": 23.05, "elapsed_time": "0:39:15", "remaining_time": "2:11:05"}
|
||||
{"current_steps": 960, "total_steps": 4144, "loss": 0.5126, "lr": 3.793605729099681e-05, "epoch": 1.6221470836855452, "percentage": 23.17, "elapsed_time": "0:39:27", "remaining_time": "2:10:52"}
|
||||
{"current_steps": 965, "total_steps": 4144, "loss": 0.511, "lr": 3.7898624579781586e-05, "epoch": 1.6306001690617076, "percentage": 23.29, "elapsed_time": "0:39:39", "remaining_time": "2:10:37"}
|
||||
{"current_steps": 970, "total_steps": 4144, "loss": 0.5241, "lr": 3.786087427331226e-05, "epoch": 1.63905325443787, "percentage": 23.41, "elapsed_time": "0:39:50", "remaining_time": "2:10:22"}
|
||||
{"current_steps": 975, "total_steps": 4144, "loss": 0.5324, "lr": 3.7822807041434615e-05, "epoch": 1.6475063398140322, "percentage": 23.53, "elapsed_time": "0:40:03", "remaining_time": "2:10:10"}
|
||||
{"current_steps": 980, "total_steps": 4144, "loss": 0.5135, "lr": 3.7784423559617985e-05, "epoch": 1.6559594251901943, "percentage": 23.65, "elapsed_time": "0:40:14", "remaining_time": "2:09:56"}
|
||||
{"current_steps": 985, "total_steps": 4144, "loss": 0.4934, "lr": 3.774572450894329e-05, "epoch": 1.6644125105663568, "percentage": 23.77, "elapsed_time": "0:40:26", "remaining_time": "2:09:41"}
|
||||
{"current_steps": 990, "total_steps": 4144, "loss": 0.5391, "lr": 3.7706710576090936e-05, "epoch": 1.6728655959425192, "percentage": 23.89, "elapsed_time": "0:40:38", "remaining_time": "2:09:29"}
|
||||
{"current_steps": 995, "total_steps": 4144, "loss": 0.5225, "lr": 3.766738245332865e-05, "epoch": 1.6813186813186813, "percentage": 24.01, "elapsed_time": "0:40:50", "remaining_time": "2:09:15"}
|
||||
{"current_steps": 1000, "total_steps": 4144, "loss": 0.5054, "lr": 3.762774083849915e-05, "epoch": 1.6897717666948435, "percentage": 24.13, "elapsed_time": "0:41:01", "remaining_time": "2:08:59"}
|
||||
{"current_steps": 1005, "total_steps": 4144, "loss": 0.5428, "lr": 3.7587786435007825e-05, "epoch": 1.698224852071006, "percentage": 24.25, "elapsed_time": "0:41:12", "remaining_time": "2:08:42"}
|
||||
{"current_steps": 1010, "total_steps": 4144, "loss": 0.5208, "lr": 3.7547519951810196e-05, "epoch": 1.7066779374471683, "percentage": 24.37, "elapsed_time": "0:41:24", "remaining_time": "2:08:29"}
|
||||
{"current_steps": 1015, "total_steps": 4144, "loss": 0.5325, "lr": 3.7506942103399385e-05, "epoch": 1.7151310228233305, "percentage": 24.49, "elapsed_time": "0:41:36", "remaining_time": "2:08:15"}
|
||||
{"current_steps": 1020, "total_steps": 4144, "loss": 0.533, "lr": 3.74660536097934e-05, "epoch": 1.7235841081994927, "percentage": 24.61, "elapsed_time": "0:41:48", "remaining_time": "2:08:02"}
|
||||
{"current_steps": 1025, "total_steps": 4144, "loss": 0.5009, "lr": 3.7424855196522376e-05, "epoch": 1.732037193575655, "percentage": 24.73, "elapsed_time": "0:41:59", "remaining_time": "2:07:47"}
|
||||
{"current_steps": 1030, "total_steps": 4144, "loss": 0.5331, "lr": 3.738334759461569e-05, "epoch": 1.7404902789518175, "percentage": 24.86, "elapsed_time": "0:42:11", "remaining_time": "2:07:32"}
|
||||
{"current_steps": 1035, "total_steps": 4144, "loss": 0.4781, "lr": 3.734153154058902e-05, "epoch": 1.7489433643279797, "percentage": 24.98, "elapsed_time": "0:42:22", "remaining_time": "2:07:15"}
|
||||
{"current_steps": 1040, "total_steps": 4144, "loss": 0.5219, "lr": 3.7299407776431236e-05, "epoch": 1.7573964497041419, "percentage": 25.1, "elapsed_time": "0:42:32", "remaining_time": "2:06:59"}
|
||||
{"current_steps": 1045, "total_steps": 4144, "loss": 0.5433, "lr": 3.7256977049591255e-05, "epoch": 1.7658495350803043, "percentage": 25.22, "elapsed_time": "0:42:45", "remaining_time": "2:06:46"}
|
||||
{"current_steps": 1050, "total_steps": 4144, "loss": 0.5343, "lr": 3.7214240112964776e-05, "epoch": 1.7743026204564667, "percentage": 25.34, "elapsed_time": "0:42:56", "remaining_time": "2:06:33"}
|
||||
{"current_steps": 1055, "total_steps": 4144, "loss": 0.496, "lr": 3.7171197724880916e-05, "epoch": 1.7827557058326289, "percentage": 25.46, "elapsed_time": "0:43:09", "remaining_time": "2:06:21"}
|
||||
{"current_steps": 1060, "total_steps": 4144, "loss": 0.4876, "lr": 3.712785064908877e-05, "epoch": 1.791208791208791, "percentage": 25.58, "elapsed_time": "0:43:23", "remaining_time": "2:06:13"}
|
||||
{"current_steps": 1065, "total_steps": 4144, "loss": 0.5446, "lr": 3.708419965474384e-05, "epoch": 1.7996618765849535, "percentage": 25.7, "elapsed_time": "0:43:34", "remaining_time": "2:05:57"}
|
||||
{"current_steps": 1070, "total_steps": 4144, "loss": 0.5088, "lr": 3.704024551639438e-05, "epoch": 1.8081149619611159, "percentage": 25.82, "elapsed_time": "0:43:45", "remaining_time": "2:05:43"}
|
||||
{"current_steps": 1075, "total_steps": 4144, "loss": 0.5087, "lr": 3.6995989013967695e-05, "epoch": 1.816568047337278, "percentage": 25.94, "elapsed_time": "0:43:57", "remaining_time": "2:05:30"}
|
||||
{"current_steps": 1080, "total_steps": 4144, "loss": 0.4746, "lr": 3.695143093275625e-05, "epoch": 1.8250211327134402, "percentage": 26.06, "elapsed_time": "0:44:09", "remaining_time": "2:05:17"}
|
||||
{"current_steps": 1085, "total_steps": 4144, "loss": 0.4817, "lr": 3.690657206340375e-05, "epoch": 1.8334742180896026, "percentage": 26.18, "elapsed_time": "0:44:22", "remaining_time": "2:05:06"}
|
||||
{"current_steps": 1090, "total_steps": 4144, "loss": 0.5437, "lr": 3.686141320189116e-05, "epoch": 1.841927303465765, "percentage": 26.3, "elapsed_time": "0:44:34", "remaining_time": "2:04:53"}
|
||||
{"current_steps": 1095, "total_steps": 4144, "loss": 0.5124, "lr": 3.6815955149522496e-05, "epoch": 1.8503803888419275, "percentage": 26.42, "elapsed_time": "0:44:47", "remaining_time": "2:04:42"}
|
||||
{"current_steps": 1100, "total_steps": 4144, "loss": 0.4856, "lr": 3.677019871291068e-05, "epoch": 1.8588334742180896, "percentage": 26.54, "elapsed_time": "0:44:59", "remaining_time": "2:04:31"}
|
||||
{"current_steps": 1105, "total_steps": 4144, "loss": 0.5111, "lr": 3.6724144703963184e-05, "epoch": 1.8672865595942518, "percentage": 26.67, "elapsed_time": "0:45:10", "remaining_time": "2:04:15"}
|
||||
{"current_steps": 1110, "total_steps": 4144, "loss": 0.5161, "lr": 3.667779393986765e-05, "epoch": 1.8757396449704142, "percentage": 26.79, "elapsed_time": "0:45:22", "remaining_time": "2:04:02"}
|
||||
{"current_steps": 1115, "total_steps": 4144, "loss": 0.5303, "lr": 3.663114724307735e-05, "epoch": 1.8841927303465766, "percentage": 26.91, "elapsed_time": "0:45:34", "remaining_time": "2:03:48"}
|
||||
{"current_steps": 1120, "total_steps": 4144, "loss": 0.5047, "lr": 3.6584205441296666e-05, "epoch": 1.8926458157227388, "percentage": 27.03, "elapsed_time": "0:45:47", "remaining_time": "2:03:38"}
|
||||
{"current_steps": 1125, "total_steps": 4144, "loss": 0.4995, "lr": 3.6536969367466306e-05, "epoch": 1.901098901098901, "percentage": 27.15, "elapsed_time": "0:46:00", "remaining_time": "2:03:27"}
|
||||
{"current_steps": 1130, "total_steps": 4144, "loss": 0.5111, "lr": 3.6489439859748616e-05, "epoch": 1.9095519864750634, "percentage": 27.27, "elapsed_time": "0:46:11", "remaining_time": "2:03:11"}
|
||||
{"current_steps": 1135, "total_steps": 4144, "loss": 0.5261, "lr": 3.6441617761512645e-05, "epoch": 1.9180050718512258, "percentage": 27.39, "elapsed_time": "0:46:22", "remaining_time": "2:02:57"}
|
||||
{"current_steps": 1140, "total_steps": 4144, "loss": 0.546, "lr": 3.6393503921319205e-05, "epoch": 1.926458157227388, "percentage": 27.51, "elapsed_time": "0:46:34", "remaining_time": "2:02:43"}
|
||||
{"current_steps": 1145, "total_steps": 4144, "loss": 0.5119, "lr": 3.6345099192905814e-05, "epoch": 1.9349112426035502, "percentage": 27.63, "elapsed_time": "0:46:45", "remaining_time": "2:02:28"}
|
||||
{"current_steps": 1150, "total_steps": 4144, "loss": 0.52, "lr": 3.629640443517154e-05, "epoch": 1.9433643279797126, "percentage": 27.75, "elapsed_time": "0:46:57", "remaining_time": "2:02:15"}
|
||||
{"current_steps": 1155, "total_steps": 4144, "loss": 0.4967, "lr": 3.6247420512161774e-05, "epoch": 1.951817413355875, "percentage": 27.87, "elapsed_time": "0:47:08", "remaining_time": "2:02:00"}
|
||||
{"current_steps": 1160, "total_steps": 4144, "loss": 0.514, "lr": 3.6198148293052874e-05, "epoch": 1.9602704987320372, "percentage": 27.99, "elapsed_time": "0:47:21", "remaining_time": "2:01:49"}
|
||||
{"current_steps": 1165, "total_steps": 4144, "loss": 0.5208, "lr": 3.614858865213678e-05, "epoch": 1.9687235841081994, "percentage": 28.11, "elapsed_time": "0:47:33", "remaining_time": "2:01:36"}
|
||||
{"current_steps": 1170, "total_steps": 4144, "loss": 0.4911, "lr": 3.609874246880545e-05, "epoch": 1.9771766694843618, "percentage": 28.23, "elapsed_time": "0:47:44", "remaining_time": "2:01:21"}
|
||||
{"current_steps": 1175, "total_steps": 4144, "loss": 0.4609, "lr": 3.6048610627535296e-05, "epoch": 1.9856297548605242, "percentage": 28.35, "elapsed_time": "0:47:56", "remaining_time": "2:01:07"}
|
||||
{"current_steps": 1180, "total_steps": 4144, "loss": 0.5301, "lr": 3.599819401787148e-05, "epoch": 1.9940828402366864, "percentage": 28.47, "elapsed_time": "0:48:08", "remaining_time": "2:00:54"}
|
||||
{"current_steps": 1185, "total_steps": 4144, "loss": 0.5156, "lr": 3.594749353441213e-05, "epoch": 2.0016906170752327, "percentage": 28.6, "elapsed_time": "0:48:19", "remaining_time": "2:00:40"}
|
||||
{"current_steps": 1190, "total_steps": 4144, "loss": 0.4641, "lr": 3.589651007679246e-05, "epoch": 2.0101437024513946, "percentage": 28.72, "elapsed_time": "0:48:30", "remaining_time": "2:00:25"}
|
||||
{"current_steps": 1195, "total_steps": 4144, "loss": 0.4628, "lr": 3.58452445496688e-05, "epoch": 2.018596787827557, "percentage": 28.84, "elapsed_time": "0:48:42", "remaining_time": "2:00:13"}
|
||||
{"current_steps": 1200, "total_steps": 4144, "loss": 0.4816, "lr": 3.579369786270257e-05, "epoch": 2.0270498732037194, "percentage": 28.96, "elapsed_time": "0:48:53", "remaining_time": "1:59:57"}
|
||||
{"current_steps": 1205, "total_steps": 4144, "loss": 0.4932, "lr": 3.574187093054411e-05, "epoch": 2.035502958579882, "percentage": 29.08, "elapsed_time": "0:49:05", "remaining_time": "1:59:44"}
|
||||
{"current_steps": 1210, "total_steps": 4144, "loss": 0.4477, "lr": 3.5689764672816464e-05, "epoch": 2.043956043956044, "percentage": 29.2, "elapsed_time": "0:49:17", "remaining_time": "1:59:31"}
|
||||
{"current_steps": 1215, "total_steps": 4144, "loss": 0.451, "lr": 3.563738001409908e-05, "epoch": 2.052409129332206, "percentage": 29.32, "elapsed_time": "0:49:29", "remaining_time": "1:59:17"}
|
||||
{"current_steps": 1220, "total_steps": 4144, "loss": 0.462, "lr": 3.558471788391136e-05, "epoch": 2.0608622147083686, "percentage": 29.44, "elapsed_time": "0:49:42", "remaining_time": "1:59:09"}
|
||||
{"current_steps": 1225, "total_steps": 4144, "loss": 0.4573, "lr": 3.5531779216696195e-05, "epoch": 2.069315300084531, "percentage": 29.56, "elapsed_time": "0:49:54", "remaining_time": "1:58:54"}
|
||||
{"current_steps": 1230, "total_steps": 4144, "loss": 0.4392, "lr": 3.54785649518034e-05, "epoch": 2.077768385460693, "percentage": 29.68, "elapsed_time": "0:50:06", "remaining_time": "1:58:42"}
|
||||
{"current_steps": 1235, "total_steps": 4144, "loss": 0.4548, "lr": 3.5425076033473e-05, "epoch": 2.0862214708368554, "percentage": 29.8, "elapsed_time": "0:50:18", "remaining_time": "1:58:29"}
|
||||
{"current_steps": 1240, "total_steps": 4144, "loss": 0.453, "lr": 3.537131341081854e-05, "epoch": 2.094674556213018, "percentage": 29.92, "elapsed_time": "0:50:29", "remaining_time": "1:58:14"}
|
||||
{"current_steps": 1245, "total_steps": 4144, "loss": 0.4638, "lr": 3.531727803781016e-05, "epoch": 2.10312764158918, "percentage": 30.04, "elapsed_time": "0:50:40", "remaining_time": "1:58:00"}
|
||||
{"current_steps": 1250, "total_steps": 4144, "loss": 0.4734, "lr": 3.5262970873257754e-05, "epoch": 2.111580726965342, "percentage": 30.16, "elapsed_time": "0:50:53", "remaining_time": "1:57:50"}
|
||||
{"current_steps": 1255, "total_steps": 4144, "loss": 0.4657, "lr": 3.520839288079388e-05, "epoch": 2.1200338123415046, "percentage": 30.28, "elapsed_time": "0:51:05", "remaining_time": "1:57:37"}
|
||||
{"current_steps": 1260, "total_steps": 4144, "loss": 0.4837, "lr": 3.515354502885673e-05, "epoch": 2.128486897717667, "percentage": 30.41, "elapsed_time": "0:51:17", "remaining_time": "1:57:24"}
|
||||
{"current_steps": 1265, "total_steps": 4144, "loss": 0.4525, "lr": 3.50984282906729e-05, "epoch": 2.1369399830938294, "percentage": 30.53, "elapsed_time": "0:51:29", "remaining_time": "1:57:10"}
|
||||
{"current_steps": 1270, "total_steps": 4144, "loss": 0.4652, "lr": 3.5043043644240135e-05, "epoch": 2.145393068469992, "percentage": 30.65, "elapsed_time": "0:51:41", "remaining_time": "1:56:58"}
|
||||
{"current_steps": 1275, "total_steps": 4144, "loss": 0.4385, "lr": 3.4987392072309964e-05, "epoch": 2.1538461538461537, "percentage": 30.77, "elapsed_time": "0:51:52", "remaining_time": "1:56:44"}
|
||||
{"current_steps": 1280, "total_steps": 4144, "loss": 0.4507, "lr": 3.493147456237029e-05, "epoch": 2.162299239222316, "percentage": 30.89, "elapsed_time": "0:52:04", "remaining_time": "1:56:31"}
|
||||
{"current_steps": 1285, "total_steps": 4144, "loss": 0.4457, "lr": 3.487529210662784e-05, "epoch": 2.1707523245984786, "percentage": 31.01, "elapsed_time": "0:52:16", "remaining_time": "1:56:18"}
|
||||
{"current_steps": 1290, "total_steps": 4144, "loss": 0.4641, "lr": 3.481884570199058e-05, "epoch": 2.1792054099746405, "percentage": 31.13, "elapsed_time": "0:52:30", "remaining_time": "1:56:09"}
|
||||
{"current_steps": 1295, "total_steps": 4144, "loss": 0.4701, "lr": 3.476213635005001e-05, "epoch": 2.187658495350803, "percentage": 31.25, "elapsed_time": "0:52:41", "remaining_time": "1:55:54"}
|
||||
{"current_steps": 1300, "total_steps": 4144, "loss": 0.4792, "lr": 3.470516505706339e-05, "epoch": 2.1961115807269653, "percentage": 31.37, "elapsed_time": "0:52:52", "remaining_time": "1:55:40"}
|
||||
{"current_steps": 1305, "total_steps": 4144, "loss": 0.4607, "lr": 3.46479328339359e-05, "epoch": 2.2045646661031277, "percentage": 31.49, "elapsed_time": "0:53:04", "remaining_time": "1:55:27"}
|
||||
{"current_steps": 1310, "total_steps": 4144, "loss": 0.4339, "lr": 3.459044069620269e-05, "epoch": 2.21301775147929, "percentage": 31.61, "elapsed_time": "0:53:15", "remaining_time": "1:55:13"}
|
||||
{"current_steps": 1315, "total_steps": 4144, "loss": 0.4513, "lr": 3.453268966401087e-05, "epoch": 2.221470836855452, "percentage": 31.73, "elapsed_time": "0:53:27", "remaining_time": "1:55:01"}
|
||||
{"current_steps": 1320, "total_steps": 4144, "loss": 0.4651, "lr": 3.44746807621014e-05, "epoch": 2.2299239222316145, "percentage": 31.85, "elapsed_time": "0:53:39", "remaining_time": "1:54:47"}
|
||||
{"current_steps": 1325, "total_steps": 4144, "loss": 0.4663, "lr": 3.4416415019790924e-05, "epoch": 2.238377007607777, "percentage": 31.97, "elapsed_time": "0:53:50", "remaining_time": "1:54:33"}
|
||||
{"current_steps": 1330, "total_steps": 4144, "loss": 0.4577, "lr": 3.4357893470953455e-05, "epoch": 2.2468300929839393, "percentage": 32.09, "elapsed_time": "0:54:02", "remaining_time": "1:54:20"}
|
||||
{"current_steps": 1335, "total_steps": 4144, "loss": 0.4353, "lr": 3.42991171540021e-05, "epoch": 2.2552831783601013, "percentage": 32.22, "elapsed_time": "0:54:14", "remaining_time": "1:54:08"}
|
||||
{"current_steps": 1340, "total_steps": 4144, "loss": 0.463, "lr": 3.42400871118706e-05, "epoch": 2.2637362637362637, "percentage": 32.34, "elapsed_time": "0:54:27", "remaining_time": "1:53:57"}
|
||||
{"current_steps": 1345, "total_steps": 4144, "loss": 0.4712, "lr": 3.4180804391994794e-05, "epoch": 2.272189349112426, "percentage": 32.46, "elapsed_time": "0:54:38", "remaining_time": "1:53:42"}
|
||||
{"current_steps": 1350, "total_steps": 4144, "loss": 0.4518, "lr": 3.4121270046294104e-05, "epoch": 2.2806424344885885, "percentage": 32.58, "elapsed_time": "0:54:50", "remaining_time": "1:53:31"}
|
||||
{"current_steps": 1355, "total_steps": 4144, "loss": 0.4791, "lr": 3.4061485131152804e-05, "epoch": 2.2890955198647505, "percentage": 32.7, "elapsed_time": "0:55:02", "remaining_time": "1:53:17"}
|
||||
{"current_steps": 1360, "total_steps": 4144, "loss": 0.4331, "lr": 3.400145070740131e-05, "epoch": 2.297548605240913, "percentage": 32.82, "elapsed_time": "0:55:15", "remaining_time": "1:53:07"}
|
||||
{"current_steps": 1365, "total_steps": 4144, "loss": 0.4689, "lr": 3.394116784029733e-05, "epoch": 2.3060016906170753, "percentage": 32.94, "elapsed_time": "0:55:27", "remaining_time": "1:52:55"}
|
||||
{"current_steps": 1370, "total_steps": 4144, "loss": 0.4577, "lr": 3.388063759950701e-05, "epoch": 2.3144547759932377, "percentage": 33.06, "elapsed_time": "0:55:39", "remaining_time": "1:52:41"}
|
||||
{"current_steps": 1375, "total_steps": 4144, "loss": 0.4517, "lr": 3.381986105908591e-05, "epoch": 2.3229078613693996, "percentage": 33.18, "elapsed_time": "0:55:51", "remaining_time": "1:52:28"}
|
||||
{"current_steps": 1380, "total_steps": 4144, "loss": 0.4206, "lr": 3.375883929745995e-05, "epoch": 2.331360946745562, "percentage": 33.3, "elapsed_time": "0:56:02", "remaining_time": "1:52:13"}
|
||||
{"current_steps": 1385, "total_steps": 4144, "loss": 0.4527, "lr": 3.369757339740629e-05, "epoch": 2.3398140321217245, "percentage": 33.42, "elapsed_time": "0:56:13", "remaining_time": "1:51:59"}
|
||||
{"current_steps": 1390, "total_steps": 4144, "loss": 0.4725, "lr": 3.363606444603411e-05, "epoch": 2.348267117497887, "percentage": 33.54, "elapsed_time": "0:56:25", "remaining_time": "1:51:47"}
|
||||
{"current_steps": 1395, "total_steps": 4144, "loss": 0.4505, "lr": 3.357431353476532e-05, "epoch": 2.3567202028740493, "percentage": 33.66, "elapsed_time": "0:56:38", "remaining_time": "1:51:36"}
|
||||
{"current_steps": 1400, "total_steps": 4144, "loss": 0.4692, "lr": 3.3512321759315196e-05, "epoch": 2.3651732882502112, "percentage": 33.78, "elapsed_time": "0:56:49", "remaining_time": "1:51:23"}
|
||||
{"current_steps": 1405, "total_steps": 4144, "loss": 0.4241, "lr": 3.345009021967294e-05, "epoch": 2.3736263736263736, "percentage": 33.9, "elapsed_time": "0:57:01", "remaining_time": "1:51:10"}
|
||||
{"current_steps": 1410, "total_steps": 4144, "loss": 0.4604, "lr": 3.3387620020082155e-05, "epoch": 2.382079459002536, "percentage": 34.03, "elapsed_time": "0:57:13", "remaining_time": "1:50:57"}
|
||||
{"current_steps": 1415, "total_steps": 4144, "loss": 0.4466, "lr": 3.332491226902124e-05, "epoch": 2.390532544378698, "percentage": 34.15, "elapsed_time": "0:57:26", "remaining_time": "1:50:47"}
|
||||
{"current_steps": 1420, "total_steps": 4144, "loss": 0.4726, "lr": 3.3261968079183744e-05, "epoch": 2.3989856297548604, "percentage": 34.27, "elapsed_time": "0:57:37", "remaining_time": "1:50:33"}
|
||||
{"current_steps": 1425, "total_steps": 4144, "loss": 0.4465, "lr": 3.319878856745862e-05, "epoch": 2.407438715131023, "percentage": 34.39, "elapsed_time": "0:57:48", "remaining_time": "1:50:18"}
|
||||
{"current_steps": 1430, "total_steps": 4144, "loss": 0.4328, "lr": 3.31353748549104e-05, "epoch": 2.415891800507185, "percentage": 34.51, "elapsed_time": "0:57:59", "remaining_time": "1:50:04"}
|
||||
{"current_steps": 1435, "total_steps": 4144, "loss": 0.4599, "lr": 3.307172806675929e-05, "epoch": 2.4243448858833476, "percentage": 34.63, "elapsed_time": "0:58:11", "remaining_time": "1:49:51"}
|
||||
{"current_steps": 1440, "total_steps": 4144, "loss": 0.4344, "lr": 3.3007849332361214e-05, "epoch": 2.4327979712595096, "percentage": 34.75, "elapsed_time": "0:58:23", "remaining_time": "1:49:38"}
|
||||
{"current_steps": 1445, "total_steps": 4144, "loss": 0.4696, "lr": 3.29437397851878e-05, "epoch": 2.441251056635672, "percentage": 34.87, "elapsed_time": "0:58:34", "remaining_time": "1:49:24"}
|
||||
{"current_steps": 1450, "total_steps": 4144, "loss": 0.4547, "lr": 3.2879400562806226e-05, "epoch": 2.4497041420118344, "percentage": 34.99, "elapsed_time": "0:58:47", "remaining_time": "1:49:13"}
|
||||
{"current_steps": 1455, "total_steps": 4144, "loss": 0.4612, "lr": 3.281483280685906e-05, "epoch": 2.458157227387997, "percentage": 35.11, "elapsed_time": "0:58:59", "remaining_time": "1:49:01"}
|
||||
{"current_steps": 1460, "total_steps": 4144, "loss": 0.4683, "lr": 3.2750037663043985e-05, "epoch": 2.4666103127641588, "percentage": 35.23, "elapsed_time": "0:59:12", "remaining_time": "1:48:50"}
|
||||
{"current_steps": 1465, "total_steps": 4144, "loss": 0.4645, "lr": 3.2685016281093494e-05, "epoch": 2.475063398140321, "percentage": 35.35, "elapsed_time": "0:59:23", "remaining_time": "1:48:36"}
|
||||
{"current_steps": 1470, "total_steps": 4144, "loss": 0.4456, "lr": 3.2619769814754464e-05, "epoch": 2.4835164835164836, "percentage": 35.47, "elapsed_time": "0:59:35", "remaining_time": "1:48:23"}
|
||||
{"current_steps": 1475, "total_steps": 4144, "loss": 0.4369, "lr": 3.2554299421767715e-05, "epoch": 2.491969568892646, "percentage": 35.59, "elapsed_time": "0:59:47", "remaining_time": "1:48:11"}
|
||||
{"current_steps": 1480, "total_steps": 4144, "loss": 0.4901, "lr": 3.2488606263847425e-05, "epoch": 2.5004226542688084, "percentage": 35.71, "elapsed_time": "0:59:59", "remaining_time": "1:47:59"}
|
||||
{"current_steps": 1485, "total_steps": 4144, "loss": 0.4931, "lr": 3.242269150666054e-05, "epoch": 2.5088757396449703, "percentage": 35.83, "elapsed_time": "1:00:10", "remaining_time": "1:47:45"}
|
||||
{"current_steps": 1490, "total_steps": 4144, "loss": 0.4713, "lr": 3.2356556319806106e-05, "epoch": 2.5173288250211328, "percentage": 35.96, "elapsed_time": "1:00:21", "remaining_time": "1:47:31"}
|
||||
{"current_steps": 1495, "total_steps": 4144, "loss": 0.4524, "lr": 3.2290201876794494e-05, "epoch": 2.525781910397295, "percentage": 36.08, "elapsed_time": "1:00:34", "remaining_time": "1:47:19"}
|
||||
{"current_steps": 1500, "total_steps": 4144, "loss": 0.4547, "lr": 3.222362935502656e-05, "epoch": 2.534234995773457, "percentage": 36.2, "elapsed_time": "1:00:45", "remaining_time": "1:47:05"}
|
||||
{"current_steps": 1505, "total_steps": 4144, "loss": 0.4361, "lr": 3.2156839935772805e-05, "epoch": 2.5426880811496195, "percentage": 36.32, "elapsed_time": "1:01:34", "remaining_time": "1:47:57"}
|
||||
{"current_steps": 1510, "total_steps": 4144, "loss": 0.4389, "lr": 3.2089834804152364e-05, "epoch": 2.551141166525782, "percentage": 36.44, "elapsed_time": "1:01:46", "remaining_time": "1:47:44"}
|
||||
{"current_steps": 1515, "total_steps": 4144, "loss": 0.4626, "lr": 3.2022615149112e-05, "epoch": 2.5595942519019443, "percentage": 36.56, "elapsed_time": "1:01:58", "remaining_time": "1:47:31"}
|
||||
{"current_steps": 1520, "total_steps": 4144, "loss": 0.4482, "lr": 3.195518216340501e-05, "epoch": 2.5680473372781067, "percentage": 36.68, "elapsed_time": "1:02:10", "remaining_time": "1:47:19"}
|
||||
{"current_steps": 1525, "total_steps": 4144, "loss": 0.4638, "lr": 3.1887537043570044e-05, "epoch": 2.5765004226542687, "percentage": 36.8, "elapsed_time": "1:02:23", "remaining_time": "1:47:09"}
|
||||
{"current_steps": 1530, "total_steps": 4144, "loss": 0.4592, "lr": 3.181968098990991e-05, "epoch": 2.584953508030431, "percentage": 36.92, "elapsed_time": "1:02:35", "remaining_time": "1:46:56"}
|
||||
{"current_steps": 1535, "total_steps": 4144, "loss": 0.4691, "lr": 3.175161520647022e-05, "epoch": 2.5934065934065935, "percentage": 37.04, "elapsed_time": "1:02:47", "remaining_time": "1:46:43"}
|
||||
{"current_steps": 1540, "total_steps": 4144, "loss": 0.4566, "lr": 3.168334090101806e-05, "epoch": 2.6018596787827555, "percentage": 37.16, "elapsed_time": "1:02:59", "remaining_time": "1:46:30"}
|
||||
{"current_steps": 1545, "total_steps": 4144, "loss": 0.475, "lr": 3.1614859285020585e-05, "epoch": 2.610312764158918, "percentage": 37.28, "elapsed_time": "1:03:11", "remaining_time": "1:46:17"}
|
||||
{"current_steps": 1550, "total_steps": 4144, "loss": 0.4474, "lr": 3.1546171573623445e-05, "epoch": 2.6187658495350803, "percentage": 37.4, "elapsed_time": "1:03:22", "remaining_time": "1:46:04"}
|
||||
{"current_steps": 1555, "total_steps": 4144, "loss": 0.4463, "lr": 3.147727898562931e-05, "epoch": 2.6272189349112427, "percentage": 37.52, "elapsed_time": "1:03:34", "remaining_time": "1:45:51"}
|
||||
{"current_steps": 1560, "total_steps": 4144, "loss": 0.4613, "lr": 3.140818274347618e-05, "epoch": 2.635672020287405, "percentage": 37.64, "elapsed_time": "1:03:46", "remaining_time": "1:45:38"}
|
||||
{"current_steps": 1565, "total_steps": 4144, "loss": 0.4554, "lr": 3.133888407321574e-05, "epoch": 2.644125105663567, "percentage": 37.77, "elapsed_time": "1:03:59", "remaining_time": "1:45:26"}
|
||||
{"current_steps": 1570, "total_steps": 4144, "loss": 0.4569, "lr": 3.126938420449155e-05, "epoch": 2.6525781910397295, "percentage": 37.89, "elapsed_time": "1:04:10", "remaining_time": "1:45:13"}
|
||||
{"current_steps": 1575, "total_steps": 4144, "loss": 0.4703, "lr": 3.119968437051729e-05, "epoch": 2.661031276415892, "percentage": 38.01, "elapsed_time": "1:04:22", "remaining_time": "1:45:00"}
|
||||
{"current_steps": 1580, "total_steps": 4144, "loss": 0.4722, "lr": 3.1129785808054836e-05, "epoch": 2.669484361792054, "percentage": 38.13, "elapsed_time": "1:04:35", "remaining_time": "1:44:48"}
|
||||
{"current_steps": 1585, "total_steps": 4144, "loss": 0.4523, "lr": 3.105968975739232e-05, "epoch": 2.6779374471682162, "percentage": 38.25, "elapsed_time": "1:04:47", "remaining_time": "1:44:36"}
|
||||
{"current_steps": 1590, "total_steps": 4144, "loss": 0.4853, "lr": 3.098939746232212e-05, "epoch": 2.6863905325443787, "percentage": 38.37, "elapsed_time": "1:04:58", "remaining_time": "1:44:21"}
|
||||
{"current_steps": 1595, "total_steps": 4144, "loss": 0.4633, "lr": 3.091891017011883e-05, "epoch": 2.694843617920541, "percentage": 38.49, "elapsed_time": "1:05:09", "remaining_time": "1:44:08"}
|
||||
{"current_steps": 1600, "total_steps": 4144, "loss": 0.4795, "lr": 3.084822913151706e-05, "epoch": 2.7032967032967035, "percentage": 38.61, "elapsed_time": "1:05:21", "remaining_time": "1:43:54"}
|
||||
{"current_steps": 1605, "total_steps": 4144, "loss": 0.4509, "lr": 3.077735560068928e-05, "epoch": 2.711749788672866, "percentage": 38.73, "elapsed_time": "1:05:32", "remaining_time": "1:43:40"}
|
||||
{"current_steps": 1610, "total_steps": 4144, "loss": 0.4659, "lr": 3.070629083522361e-05, "epoch": 2.720202874049028, "percentage": 38.85, "elapsed_time": "1:05:43", "remaining_time": "1:43:27"}
|
||||
{"current_steps": 1615, "total_steps": 4144, "loss": 0.4465, "lr": 3.0635036096101396e-05, "epoch": 2.7286559594251902, "percentage": 38.97, "elapsed_time": "1:05:54", "remaining_time": "1:43:12"}
|
||||
{"current_steps": 1620, "total_steps": 4144, "loss": 0.4854, "lr": 3.056359264767494e-05, "epoch": 2.7371090448013526, "percentage": 39.09, "elapsed_time": "1:06:06", "remaining_time": "1:42:59"}
|
||||
{"current_steps": 1625, "total_steps": 4144, "loss": 0.445, "lr": 3.0491961757645003e-05, "epoch": 2.7455621301775146, "percentage": 39.21, "elapsed_time": "1:06:18", "remaining_time": "1:42:47"}
|
||||
{"current_steps": 1630, "total_steps": 4144, "loss": 0.457, "lr": 3.042014469703836e-05, "epoch": 2.754015215553677, "percentage": 39.33, "elapsed_time": "1:06:31", "remaining_time": "1:42:35"}
|
||||
{"current_steps": 1635, "total_steps": 4144, "loss": 0.4693, "lr": 3.0348142740185172e-05, "epoch": 2.7624683009298394, "percentage": 39.45, "elapsed_time": "1:06:42", "remaining_time": "1:42:21"}
|
||||
{"current_steps": 1640, "total_steps": 4144, "loss": 0.4542, "lr": 3.027595716469647e-05, "epoch": 2.770921386306002, "percentage": 39.58, "elapsed_time": "1:06:53", "remaining_time": "1:42:07"}
|
||||
{"current_steps": 1645, "total_steps": 4144, "loss": 0.4598, "lr": 3.02035892514414e-05, "epoch": 2.7793744716821642, "percentage": 39.7, "elapsed_time": "1:07:05", "remaining_time": "1:41:55"}
|
||||
{"current_steps": 1650, "total_steps": 4144, "loss": 0.4427, "lr": 3.0131040284524543e-05, "epoch": 2.787827557058326, "percentage": 39.82, "elapsed_time": "1:07:17", "remaining_time": "1:41:42"}
|
||||
{"current_steps": 1655, "total_steps": 4144, "loss": 0.4701, "lr": 3.0058311551263116e-05, "epoch": 2.7962806424344886, "percentage": 39.94, "elapsed_time": "1:07:28", "remaining_time": "1:41:28"}
|
||||
{"current_steps": 1660, "total_steps": 4144, "loss": 0.4343, "lr": 2.9985404342164136e-05, "epoch": 2.804733727810651, "percentage": 40.06, "elapsed_time": "1:07:41", "remaining_time": "1:41:17"}
|
||||
{"current_steps": 1665, "total_steps": 4144, "loss": 0.4955, "lr": 2.9912319950901498e-05, "epoch": 2.813186813186813, "percentage": 40.18, "elapsed_time": "1:07:54", "remaining_time": "1:41:06"}
|
||||
{"current_steps": 1670, "total_steps": 4144, "loss": 0.4727, "lr": 2.9839059674293058e-05, "epoch": 2.8216398985629754, "percentage": 40.3, "elapsed_time": "1:08:06", "remaining_time": "1:40:53"}
|
||||
{"current_steps": 1675, "total_steps": 4144, "loss": 0.4621, "lr": 2.97656248122776e-05, "epoch": 2.8300929839391378, "percentage": 40.42, "elapsed_time": "1:08:17", "remaining_time": "1:40:39"}
|
||||
{"current_steps": 1680, "total_steps": 4144, "loss": 0.4515, "lr": 2.969201666789176e-05, "epoch": 2.8385460693153, "percentage": 40.54, "elapsed_time": "1:08:29", "remaining_time": "1:40:27"}
|
||||
{"current_steps": 1685, "total_steps": 4144, "loss": 0.4374, "lr": 2.961823654724692e-05, "epoch": 2.8469991546914626, "percentage": 40.66, "elapsed_time": "1:08:42", "remaining_time": "1:40:15"}
|
||||
{"current_steps": 1690, "total_steps": 4144, "loss": 0.443, "lr": 2.954428575950603e-05, "epoch": 2.8554522400676245, "percentage": 40.78, "elapsed_time": "1:08:53", "remaining_time": "1:40:02"}
|
||||
{"current_steps": 1695, "total_steps": 4144, "loss": 0.4674, "lr": 2.9470165616860386e-05, "epoch": 2.863905325443787, "percentage": 40.9, "elapsed_time": "1:09:05", "remaining_time": "1:39:49"}
|
||||
{"current_steps": 1700, "total_steps": 4144, "loss": 0.4524, "lr": 2.9395877434506314e-05, "epoch": 2.8723584108199494, "percentage": 41.02, "elapsed_time": "1:09:17", "remaining_time": "1:39:36"}
|
||||
{"current_steps": 1705, "total_steps": 4144, "loss": 0.4784, "lr": 2.9321422530621883e-05, "epoch": 2.8808114961961113, "percentage": 41.14, "elapsed_time": "1:09:29", "remaining_time": "1:39:23"}
|
||||
{"current_steps": 1710, "total_steps": 4144, "loss": 0.463, "lr": 2.9246802226343468e-05, "epoch": 2.8892645815722737, "percentage": 41.26, "elapsed_time": "1:09:41", "remaining_time": "1:39:11"}
|
||||
{"current_steps": 1715, "total_steps": 4144, "loss": 0.4523, "lr": 2.9172017845742338e-05, "epoch": 2.897717666948436, "percentage": 41.39, "elapsed_time": "1:09:53", "remaining_time": "1:38:59"}
|
||||
{"current_steps": 1720, "total_steps": 4144, "loss": 0.4703, "lr": 2.9097070715801138e-05, "epoch": 2.9061707523245985, "percentage": 41.51, "elapsed_time": "1:10:05", "remaining_time": "1:38:46"}
|
||||
{"current_steps": 1725, "total_steps": 4144, "loss": 0.4651, "lr": 2.9021962166390377e-05, "epoch": 2.914623837700761, "percentage": 41.63, "elapsed_time": "1:10:17", "remaining_time": "1:38:34"}
|
||||
{"current_steps": 1730, "total_steps": 4144, "loss": 0.454, "lr": 2.8946693530244796e-05, "epoch": 2.9230769230769234, "percentage": 41.75, "elapsed_time": "1:10:28", "remaining_time": "1:38:21"}
|
||||
{"current_steps": 1735, "total_steps": 4144, "loss": 0.4588, "lr": 2.8871266142939737e-05, "epoch": 2.9315300084530853, "percentage": 41.87, "elapsed_time": "1:10:40", "remaining_time": "1:38:08"}
|
||||
{"current_steps": 1740, "total_steps": 4144, "loss": 0.4305, "lr": 2.8795681342867432e-05, "epoch": 2.9399830938292477, "percentage": 41.99, "elapsed_time": "1:10:52", "remaining_time": "1:37:55"}
|
||||
{"current_steps": 1745, "total_steps": 4144, "loss": 0.4591, "lr": 2.871994047121328e-05, "epoch": 2.94843617920541, "percentage": 42.11, "elapsed_time": "1:11:03", "remaining_time": "1:37:41"}
|
||||
{"current_steps": 1750, "total_steps": 4144, "loss": 0.4617, "lr": 2.8644044871932015e-05, "epoch": 2.956889264581572, "percentage": 42.23, "elapsed_time": "1:11:15", "remaining_time": "1:37:28"}
|
||||
{"current_steps": 1755, "total_steps": 4144, "loss": 0.4764, "lr": 2.856799589172389e-05, "epoch": 2.9653423499577345, "percentage": 42.35, "elapsed_time": "1:11:28", "remaining_time": "1:37:17"}
|
||||
{"current_steps": 1760, "total_steps": 4144, "loss": 0.467, "lr": 2.8491794880010756e-05, "epoch": 2.973795435333897, "percentage": 42.47, "elapsed_time": "1:11:40", "remaining_time": "1:37:04"}
|
||||
{"current_steps": 1765, "total_steps": 4144, "loss": 0.488, "lr": 2.841544318891214e-05, "epoch": 2.9822485207100593, "percentage": 42.59, "elapsed_time": "1:11:52", "remaining_time": "1:36:52"}
|
||||
{"current_steps": 1770, "total_steps": 4144, "loss": 0.4701, "lr": 2.833894217322123e-05, "epoch": 2.9907016060862217, "percentage": 42.71, "elapsed_time": "1:12:03", "remaining_time": "1:36:38"}
|
||||
{"current_steps": 1775, "total_steps": 4144, "loss": 0.4608, "lr": 2.8262293190380843e-05, "epoch": 2.9991546914623837, "percentage": 42.83, "elapsed_time": "1:12:15", "remaining_time": "1:36:26"}
|
||||
{"current_steps": 1780, "total_steps": 4144, "loss": 0.3924, "lr": 2.8185497600459368e-05, "epoch": 3.0067624683009297, "percentage": 42.95, "elapsed_time": "1:12:26", "remaining_time": "1:36:12"}
|
||||
{"current_steps": 1785, "total_steps": 4144, "loss": 0.4144, "lr": 2.8108556766126573e-05, "epoch": 3.015215553677092, "percentage": 43.07, "elapsed_time": "1:12:37", "remaining_time": "1:35:59"}
|
||||
{"current_steps": 1790, "total_steps": 4144, "loss": 0.3917, "lr": 2.8031472052629482e-05, "epoch": 3.0236686390532546, "percentage": 43.19, "elapsed_time": "1:12:49", "remaining_time": "1:35:46"}
|
||||
{"current_steps": 1795, "total_steps": 4144, "loss": 0.4169, "lr": 2.7954244827768133e-05, "epoch": 3.0321217244294165, "percentage": 43.32, "elapsed_time": "1:13:00", "remaining_time": "1:35:32"}
|
||||
{"current_steps": 1800, "total_steps": 4144, "loss": 0.3809, "lr": 2.7876876461871262e-05, "epoch": 3.040574809805579, "percentage": 43.44, "elapsed_time": "1:13:14", "remaining_time": "1:35:22"}
|
||||
{"current_steps": 1805, "total_steps": 4144, "loss": 0.4117, "lr": 2.7799368327772083e-05, "epoch": 3.0490278951817413, "percentage": 43.56, "elapsed_time": "1:13:25", "remaining_time": "1:35:09"}
|
||||
{"current_steps": 1810, "total_steps": 4144, "loss": 0.4049, "lr": 2.7721721800783837e-05, "epoch": 3.0574809805579037, "percentage": 43.68, "elapsed_time": "1:13:38", "remaining_time": "1:34:57"}
|
||||
{"current_steps": 1815, "total_steps": 4144, "loss": 0.3933, "lr": 2.7643938258675434e-05, "epoch": 3.065934065934066, "percentage": 43.8, "elapsed_time": "1:13:50", "remaining_time": "1:34:44"}
|
||||
{"current_steps": 1820, "total_steps": 4144, "loss": 0.3988, "lr": 2.7566019081647e-05, "epoch": 3.074387151310228, "percentage": 43.92, "elapsed_time": "1:14:01", "remaining_time": "1:34:31"}
|
||||
{"current_steps": 1825, "total_steps": 4144, "loss": 0.3942, "lr": 2.748796565230536e-05, "epoch": 3.0828402366863905, "percentage": 44.04, "elapsed_time": "1:14:13", "remaining_time": "1:34:18"}
|
||||
{"current_steps": 1830, "total_steps": 4144, "loss": 0.4066, "lr": 2.7409779355639572e-05, "epoch": 3.091293322062553, "percentage": 44.16, "elapsed_time": "1:14:24", "remaining_time": "1:34:05"}
|
||||
{"current_steps": 1835, "total_steps": 4144, "loss": 0.4096, "lr": 2.733146157899626e-05, "epoch": 3.0997464074387153, "percentage": 44.28, "elapsed_time": "1:14:36", "remaining_time": "1:33:52"}
|
||||
{"current_steps": 1840, "total_steps": 4144, "loss": 0.4064, "lr": 2.725301371205507e-05, "epoch": 3.1081994928148773, "percentage": 44.4, "elapsed_time": "1:14:48", "remaining_time": "1:33:39"}
|
||||
{"current_steps": 1845, "total_steps": 4144, "loss": 0.3751, "lr": 2.717443714680399e-05, "epoch": 3.1166525781910397, "percentage": 44.52, "elapsed_time": "1:14:59", "remaining_time": "1:33:27"}
|
||||
{"current_steps": 1850, "total_steps": 4144, "loss": 0.3897, "lr": 2.7095733277514623e-05, "epoch": 3.125105663567202, "percentage": 44.64, "elapsed_time": "1:15:11", "remaining_time": "1:33:14"}
|
||||
{"current_steps": 1855, "total_steps": 4144, "loss": 0.4255, "lr": 2.7016903500717483e-05, "epoch": 3.1335587489433645, "percentage": 44.76, "elapsed_time": "1:15:23", "remaining_time": "1:33:01"}
|
||||
{"current_steps": 1860, "total_steps": 4144, "loss": 0.4245, "lr": 2.6937949215177206e-05, "epoch": 3.1420118343195265, "percentage": 44.88, "elapsed_time": "1:15:35", "remaining_time": "1:32:49"}
|
||||
{"current_steps": 1865, "total_steps": 4144, "loss": 0.412, "lr": 2.6858871821867722e-05, "epoch": 3.150464919695689, "percentage": 45.0, "elapsed_time": "1:15:47", "remaining_time": "1:32:36"}
|
||||
{"current_steps": 1870, "total_steps": 4144, "loss": 0.3968, "lr": 2.6779672723947392e-05, "epoch": 3.1589180050718513, "percentage": 45.13, "elapsed_time": "1:15:59", "remaining_time": "1:32:24"}
|
||||
{"current_steps": 1875, "total_steps": 4144, "loss": 0.39, "lr": 2.6700353326734117e-05, "epoch": 3.1673710904480137, "percentage": 45.25, "elapsed_time": "1:16:12", "remaining_time": "1:32:13"}
|
||||
{"current_steps": 1880, "total_steps": 4144, "loss": 0.4183, "lr": 2.662091503768042e-05, "epoch": 3.1758241758241756, "percentage": 45.37, "elapsed_time": "1:16:23", "remaining_time": "1:32:00"}
|
||||
{"current_steps": 1885, "total_steps": 4144, "loss": 0.3903, "lr": 2.6541359266348437e-05, "epoch": 3.184277261200338, "percentage": 45.49, "elapsed_time": "1:16:37", "remaining_time": "1:31:49"}
|
||||
{"current_steps": 1890, "total_steps": 4144, "loss": 0.4284, "lr": 2.6461687424384925e-05, "epoch": 3.1927303465765005, "percentage": 45.61, "elapsed_time": "1:16:48", "remaining_time": "1:31:36"}
|
||||
{"current_steps": 1895, "total_steps": 4144, "loss": 0.4045, "lr": 2.6381900925496227e-05, "epoch": 3.201183431952663, "percentage": 45.73, "elapsed_time": "1:17:01", "remaining_time": "1:31:24"}
|
||||
{"current_steps": 1900, "total_steps": 4144, "loss": 0.3893, "lr": 2.6302001185423152e-05, "epoch": 3.209636517328825, "percentage": 45.85, "elapsed_time": "1:17:13", "remaining_time": "1:31:12"}
|
||||
{"current_steps": 1905, "total_steps": 4144, "loss": 0.4138, "lr": 2.622198962191588e-05, "epoch": 3.2180896027049872, "percentage": 45.97, "elapsed_time": "1:17:25", "remaining_time": "1:30:59"}
|
||||
{"current_steps": 1910, "total_steps": 4144, "loss": 0.4188, "lr": 2.6141867654708805e-05, "epoch": 3.2265426880811496, "percentage": 46.09, "elapsed_time": "1:17:35", "remaining_time": "1:30:45"}
|
||||
{"current_steps": 1915, "total_steps": 4144, "loss": 0.4036, "lr": 2.606163670549533e-05, "epoch": 3.234995773457312, "percentage": 46.21, "elapsed_time": "1:17:47", "remaining_time": "1:30:32"}
|
||||
{"current_steps": 1920, "total_steps": 4144, "loss": 0.3801, "lr": 2.5981298197902644e-05, "epoch": 3.2434488588334744, "percentage": 46.33, "elapsed_time": "1:17:58", "remaining_time": "1:30:19"}
|
||||
{"current_steps": 1925, "total_steps": 4144, "loss": 0.3973, "lr": 2.590085355746649e-05, "epoch": 3.2519019442096364, "percentage": 46.45, "elapsed_time": "1:18:10", "remaining_time": "1:30:06"}
|
||||
{"current_steps": 1930, "total_steps": 4144, "loss": 0.4077, "lr": 2.58203042116058e-05, "epoch": 3.260355029585799, "percentage": 46.57, "elapsed_time": "1:18:22", "remaining_time": "1:29:53"}
|
||||
{"current_steps": 1935, "total_steps": 4144, "loss": 0.4179, "lr": 2.573965158959746e-05, "epoch": 3.268808114961961, "percentage": 46.69, "elapsed_time": "1:18:34", "remaining_time": "1:29:41"}
|
||||
{"current_steps": 1940, "total_steps": 4144, "loss": 0.3779, "lr": 2.5658897122550852e-05, "epoch": 3.277261200338123, "percentage": 46.81, "elapsed_time": "1:18:46", "remaining_time": "1:29:29"}
|
||||
{"current_steps": 1945, "total_steps": 4144, "loss": 0.3837, "lr": 2.5578042243382547e-05, "epoch": 3.2857142857142856, "percentage": 46.94, "elapsed_time": "1:18:58", "remaining_time": "1:29:17"}
|
||||
{"current_steps": 1950, "total_steps": 4144, "loss": 0.4305, "lr": 2.5497088386790816e-05, "epoch": 3.294167371090448, "percentage": 47.06, "elapsed_time": "1:19:10", "remaining_time": "1:29:05"}
|
||||
{"current_steps": 1955, "total_steps": 4144, "loss": 0.4029, "lr": 2.5416036989230223e-05, "epoch": 3.3026204564666104, "percentage": 47.18, "elapsed_time": "1:19:21", "remaining_time": "1:28:51"}
|
||||
{"current_steps": 1960, "total_steps": 4144, "loss": 0.3881, "lr": 2.5334889488886062e-05, "epoch": 3.311073541842773, "percentage": 47.3, "elapsed_time": "1:19:34", "remaining_time": "1:28:40"}
|
||||
{"current_steps": 1965, "total_steps": 4144, "loss": 0.399, "lr": 2.5253647325648945e-05, "epoch": 3.3195266272189348, "percentage": 47.42, "elapsed_time": "1:19:46", "remaining_time": "1:28:27"}
|
||||
{"current_steps": 1970, "total_steps": 4144, "loss": 0.4149, "lr": 2.5172311941089152e-05, "epoch": 3.327979712595097, "percentage": 47.54, "elapsed_time": "1:19:57", "remaining_time": "1:28:14"}
|
||||
{"current_steps": 1975, "total_steps": 4144, "loss": 0.4007, "lr": 2.5090884778431105e-05, "epoch": 3.3364327979712596, "percentage": 47.66, "elapsed_time": "1:20:09", "remaining_time": "1:28:02"}
|
||||
{"current_steps": 1980, "total_steps": 4144, "loss": 0.4284, "lr": 2.500936728252775e-05, "epoch": 3.344885883347422, "percentage": 47.78, "elapsed_time": "1:20:21", "remaining_time": "1:27:49"}
|
||||
{"current_steps": 1985, "total_steps": 4144, "loss": 0.4035, "lr": 2.492776089983492e-05, "epoch": 3.353338968723584, "percentage": 47.9, "elapsed_time": "1:20:32", "remaining_time": "1:27:36"}
|
||||
{"current_steps": 1990, "total_steps": 4144, "loss": 0.4409, "lr": 2.4846067078385648e-05, "epoch": 3.3617920540997464, "percentage": 48.02, "elapsed_time": "1:20:46", "remaining_time": "1:27:25"}
|
||||
{"current_steps": 1995, "total_steps": 4144, "loss": 0.4024, "lr": 2.476428726776451e-05, "epoch": 3.3702451394759088, "percentage": 48.14, "elapsed_time": "1:20:57", "remaining_time": "1:27:12"}
|
||||
{"current_steps": 2000, "total_steps": 4144, "loss": 0.384, "lr": 2.468242291908188e-05, "epoch": 3.378698224852071, "percentage": 48.26, "elapsed_time": "1:21:09", "remaining_time": "1:27:00"}
|
||||
{"current_steps": 2005, "total_steps": 4144, "loss": 0.4255, "lr": 2.4600475484948176e-05, "epoch": 3.387151310228233, "percentage": 48.38, "elapsed_time": "1:21:20", "remaining_time": "1:26:46"}
|
||||
{"current_steps": 2010, "total_steps": 4144, "loss": 0.3961, "lr": 2.4518446419448095e-05, "epoch": 3.3956043956043955, "percentage": 48.5, "elapsed_time": "1:21:32", "remaining_time": "1:26:34"}
|
||||
{"current_steps": 2015, "total_steps": 4144, "loss": 0.3926, "lr": 2.4436337178114816e-05, "epoch": 3.404057480980558, "percentage": 48.62, "elapsed_time": "1:21:44", "remaining_time": "1:26:21"}
|
||||
{"current_steps": 2020, "total_steps": 4144, "loss": 0.3952, "lr": 2.4354149217904174e-05, "epoch": 3.4125105663567203, "percentage": 48.75, "elapsed_time": "1:21:57", "remaining_time": "1:26:11"}
|
||||
{"current_steps": 2025, "total_steps": 4144, "loss": 0.4227, "lr": 2.4271883997168775e-05, "epoch": 3.4209636517328823, "percentage": 48.87, "elapsed_time": "1:22:09", "remaining_time": "1:25:58"}
|
||||
{"current_steps": 2030, "total_steps": 4144, "loss": 0.4225, "lr": 2.418954297563218e-05, "epoch": 3.4294167371090447, "percentage": 48.99, "elapsed_time": "1:22:21", "remaining_time": "1:25:45"}
|
||||
{"current_steps": 2035, "total_steps": 4144, "loss": 0.3958, "lr": 2.4107127614362943e-05, "epoch": 3.437869822485207, "percentage": 49.11, "elapsed_time": "1:22:32", "remaining_time": "1:25:32"}
|
||||
{"current_steps": 2040, "total_steps": 4144, "loss": 0.4226, "lr": 2.402463937574871e-05, "epoch": 3.4463229078613695, "percentage": 49.23, "elapsed_time": "1:22:44", "remaining_time": "1:25:20"}
|
||||
{"current_steps": 2045, "total_steps": 4144, "loss": 0.4051, "lr": 2.394207972347029e-05, "epoch": 3.454775993237532, "percentage": 49.35, "elapsed_time": "1:22:56", "remaining_time": "1:25:07"}
|
||||
{"current_steps": 2050, "total_steps": 4144, "loss": 0.3822, "lr": 2.3859450122475652e-05, "epoch": 3.463229078613694, "percentage": 49.47, "elapsed_time": "1:23:08", "remaining_time": "1:24:55"}
|
||||
{"current_steps": 2055, "total_steps": 4144, "loss": 0.3952, "lr": 2.3776752038953932e-05, "epoch": 3.4716821639898563, "percentage": 49.59, "elapsed_time": "1:23:19", "remaining_time": "1:24:42"}
|
||||
{"current_steps": 2060, "total_steps": 4144, "loss": 0.4482, "lr": 2.3693986940309458e-05, "epoch": 3.4801352493660187, "percentage": 49.71, "elapsed_time": "1:23:30", "remaining_time": "1:24:29"}
|
||||
{"current_steps": 2065, "total_steps": 4144, "loss": 0.3951, "lr": 2.361115629513565e-05, "epoch": 3.4885883347421807, "percentage": 49.83, "elapsed_time": "1:23:43", "remaining_time": "1:24:17"}
|
||||
{"current_steps": 2070, "total_steps": 4144, "loss": 0.4234, "lr": 2.352826157318901e-05, "epoch": 3.497041420118343, "percentage": 49.95, "elapsed_time": "1:23:55", "remaining_time": "1:24:05"}
|
||||
{"current_steps": 2075, "total_steps": 4144, "loss": 0.3826, "lr": 2.3445304245363024e-05, "epoch": 3.5054945054945055, "percentage": 50.07, "elapsed_time": "1:24:06", "remaining_time": "1:23:52"}
|
||||
{"current_steps": 2080, "total_steps": 4144, "loss": 0.401, "lr": 2.336228578366207e-05, "epoch": 3.513947590870668, "percentage": 50.19, "elapsed_time": "1:24:18", "remaining_time": "1:23:39"}
|
||||
{"current_steps": 2085, "total_steps": 4144, "loss": 0.4168, "lr": 2.3279207661175275e-05, "epoch": 3.5224006762468303, "percentage": 50.31, "elapsed_time": "1:24:29", "remaining_time": "1:23:26"}
|
||||
{"current_steps": 2090, "total_steps": 4144, "loss": 0.4031, "lr": 2.319607135205041e-05, "epoch": 3.5308537616229922, "percentage": 50.43, "elapsed_time": "1:24:41", "remaining_time": "1:23:13"}
|
||||
{"current_steps": 2095, "total_steps": 4144, "loss": 0.4126, "lr": 2.31128783314677e-05, "epoch": 3.5393068469991547, "percentage": 50.56, "elapsed_time": "1:24:53", "remaining_time": "1:23:01"}
|
||||
{"current_steps": 2100, "total_steps": 4144, "loss": 0.4156, "lr": 2.3029630075613692e-05, "epoch": 3.547759932375317, "percentage": 50.68, "elapsed_time": "1:25:05", "remaining_time": "1:22:48"}
|
||||
{"current_steps": 2105, "total_steps": 4144, "loss": 0.4308, "lr": 2.2946328061655007e-05, "epoch": 3.556213017751479, "percentage": 50.8, "elapsed_time": "1:25:17", "remaining_time": "1:22:36"}
|
||||
{"current_steps": 2110, "total_steps": 4144, "loss": 0.394, "lr": 2.2862973767712165e-05, "epoch": 3.5646661031276414, "percentage": 50.92, "elapsed_time": "1:25:29", "remaining_time": "1:22:24"}
|
||||
{"current_steps": 2115, "total_steps": 4144, "loss": 0.4104, "lr": 2.2779568672833348e-05, "epoch": 3.573119188503804, "percentage": 51.04, "elapsed_time": "1:25:40", "remaining_time": "1:22:11"}
|
||||
{"current_steps": 2120, "total_steps": 4144, "loss": 0.4267, "lr": 2.269611425696817e-05, "epoch": 3.5815722738799662, "percentage": 51.16, "elapsed_time": "1:25:52", "remaining_time": "1:21:58"}
|
||||
{"current_steps": 2125, "total_steps": 4144, "loss": 0.4231, "lr": 2.2612612000941366e-05, "epoch": 3.5900253592561286, "percentage": 51.28, "elapsed_time": "1:26:04", "remaining_time": "1:21:46"}
|
||||
{"current_steps": 2130, "total_steps": 4144, "loss": 0.4085, "lr": 2.2529063386426598e-05, "epoch": 3.598478444632291, "percentage": 51.4, "elapsed_time": "1:26:17", "remaining_time": "1:21:35"}
|
||||
{"current_steps": 2135, "total_steps": 4144, "loss": 0.4241, "lr": 2.2445469895920086e-05, "epoch": 3.606931530008453, "percentage": 51.52, "elapsed_time": "1:26:28", "remaining_time": "1:21:21"}
|
||||
{"current_steps": 2140, "total_steps": 4144, "loss": 0.4317, "lr": 2.2361833012714348e-05, "epoch": 3.6153846153846154, "percentage": 51.64, "elapsed_time": "1:26:39", "remaining_time": "1:21:09"}
|
||||
{"current_steps": 2145, "total_steps": 4144, "loss": 0.3962, "lr": 2.227815422087185e-05, "epoch": 3.623837700760778, "percentage": 51.76, "elapsed_time": "1:26:51", "remaining_time": "1:20:56"}
|
||||
{"current_steps": 2150, "total_steps": 4144, "loss": 0.409, "lr": 2.219443500519872e-05, "epoch": 3.63229078613694, "percentage": 51.88, "elapsed_time": "1:27:02", "remaining_time": "1:20:43"}
|
||||
{"current_steps": 2155, "total_steps": 4144, "loss": 0.3956, "lr": 2.211067685121835e-05, "epoch": 3.640743871513102, "percentage": 52.0, "elapsed_time": "1:27:14", "remaining_time": "1:20:30"}
|
||||
{"current_steps": 2160, "total_steps": 4144, "loss": 0.4219, "lr": 2.202688124514506e-05, "epoch": 3.6491969568892646, "percentage": 52.12, "elapsed_time": "1:27:25", "remaining_time": "1:20:18"}
|
||||
{"current_steps": 2165, "total_steps": 4144, "loss": 0.4016, "lr": 2.194304967385772e-05, "epoch": 3.657650042265427, "percentage": 52.24, "elapsed_time": "1:27:37", "remaining_time": "1:20:05"}
|
||||
{"current_steps": 2170, "total_steps": 4144, "loss": 0.4026, "lr": 2.185918362487339e-05, "epoch": 3.6661031276415894, "percentage": 52.36, "elapsed_time": "1:27:49", "remaining_time": "1:19:53"}
|
||||
{"current_steps": 2175, "total_steps": 4144, "loss": 0.3886, "lr": 2.1775284586320883e-05, "epoch": 3.6745562130177514, "percentage": 52.49, "elapsed_time": "1:28:01", "remaining_time": "1:19:41"}
|
||||
{"current_steps": 2180, "total_steps": 4144, "loss": 0.395, "lr": 2.1691354046914405e-05, "epoch": 3.6830092983939138, "percentage": 52.61, "elapsed_time": "1:28:13", "remaining_time": "1:19:28"}
|
||||
{"current_steps": 2185, "total_steps": 4144, "loss": 0.4094, "lr": 2.1607393495927088e-05, "epoch": 3.691462383770076, "percentage": 52.73, "elapsed_time": "1:28:24", "remaining_time": "1:19:15"}
|
||||
{"current_steps": 2190, "total_steps": 4144, "loss": 0.4109, "lr": 2.1523404423164625e-05, "epoch": 3.699915469146238, "percentage": 52.85, "elapsed_time": "1:28:35", "remaining_time": "1:19:03"}
|
||||
{"current_steps": 2195, "total_steps": 4144, "loss": 0.3985, "lr": 2.1439388318938778e-05, "epoch": 3.7083685545224006, "percentage": 52.97, "elapsed_time": "1:28:47", "remaining_time": "1:18:50"}
|
||||
{"current_steps": 2200, "total_steps": 4144, "loss": 0.4198, "lr": 2.1355346674040974e-05, "epoch": 3.716821639898563, "percentage": 53.09, "elapsed_time": "1:28:59", "remaining_time": "1:18:37"}
|
||||
{"current_steps": 2205, "total_steps": 4144, "loss": 0.4296, "lr": 2.127128097971583e-05, "epoch": 3.7252747252747254, "percentage": 53.21, "elapsed_time": "1:29:12", "remaining_time": "1:18:26"}
|
||||
{"current_steps": 2210, "total_steps": 4144, "loss": 0.4002, "lr": 2.1187192727634693e-05, "epoch": 3.7337278106508878, "percentage": 53.33, "elapsed_time": "1:29:25", "remaining_time": "1:18:15"}
|
||||
{"current_steps": 2215, "total_steps": 4144, "loss": 0.4213, "lr": 2.1103083409869195e-05, "epoch": 3.7421808960270497, "percentage": 53.45, "elapsed_time": "1:29:36", "remaining_time": "1:18:02"}
|
||||
{"current_steps": 2220, "total_steps": 4144, "loss": 0.4399, "lr": 2.1018954518864744e-05, "epoch": 3.750633981403212, "percentage": 53.57, "elapsed_time": "1:29:49", "remaining_time": "1:17:50"}
|
||||
{"current_steps": 2225, "total_steps": 4144, "loss": 0.3958, "lr": 2.093480754741406e-05, "epoch": 3.7590870667793745, "percentage": 53.69, "elapsed_time": "1:30:00", "remaining_time": "1:17:38"}
|
||||
{"current_steps": 2230, "total_steps": 4144, "loss": 0.3999, "lr": 2.085064398863068e-05, "epoch": 3.7675401521555365, "percentage": 53.81, "elapsed_time": "1:30:14", "remaining_time": "1:17:26"}
|
||||
{"current_steps": 2235, "total_steps": 4144, "loss": 0.4266, "lr": 2.076646533592249e-05, "epoch": 3.775993237531699, "percentage": 53.93, "elapsed_time": "1:30:25", "remaining_time": "1:17:14"}
|
||||
{"current_steps": 2240, "total_steps": 4144, "loss": 0.3903, "lr": 2.0682273082965186e-05, "epoch": 3.7844463229078613, "percentage": 54.05, "elapsed_time": "1:30:37", "remaining_time": "1:17:01"}
|
||||
{"current_steps": 2245, "total_steps": 4144, "loss": 0.4148, "lr": 2.0598068723675783e-05, "epoch": 3.7928994082840237, "percentage": 54.17, "elapsed_time": "1:30:49", "remaining_time": "1:16:49"}
|
||||
{"current_steps": 2250, "total_steps": 4144, "loss": 0.3877, "lr": 2.0513853752186133e-05, "epoch": 3.801352493660186, "percentage": 54.3, "elapsed_time": "1:31:00", "remaining_time": "1:16:36"}
|
||||
{"current_steps": 2255, "total_steps": 4144, "loss": 0.4097, "lr": 2.0429629662816377e-05, "epoch": 3.8098055790363485, "percentage": 54.42, "elapsed_time": "1:31:13", "remaining_time": "1:16:25"}
|
||||
{"current_steps": 2260, "total_steps": 4144, "loss": 0.4218, "lr": 2.0345397950048446e-05, "epoch": 3.8182586644125105, "percentage": 54.54, "elapsed_time": "1:31:24", "remaining_time": "1:16:12"}
|
||||
{"current_steps": 2265, "total_steps": 4144, "loss": 0.4468, "lr": 2.026116010849954e-05, "epoch": 3.826711749788673, "percentage": 54.66, "elapsed_time": "1:31:36", "remaining_time": "1:15:59"}
|
||||
{"current_steps": 2270, "total_steps": 4144, "loss": 0.417, "lr": 2.0176917632895625e-05, "epoch": 3.8351648351648353, "percentage": 54.78, "elapsed_time": "1:31:48", "remaining_time": "1:15:47"}
|
||||
{"current_steps": 2275, "total_steps": 4144, "loss": 0.4007, "lr": 2.009267201804487e-05, "epoch": 3.8436179205409973, "percentage": 54.9, "elapsed_time": "1:31:59", "remaining_time": "1:15:34"}
|
||||
{"current_steps": 2280, "total_steps": 4144, "loss": 0.4113, "lr": 2.0008424758811164e-05, "epoch": 3.8520710059171597, "percentage": 55.02, "elapsed_time": "1:32:10", "remaining_time": "1:15:21"}
|
||||
{"current_steps": 2285, "total_steps": 4144, "loss": 0.4096, "lr": 1.992417735008757e-05, "epoch": 3.860524091293322, "percentage": 55.14, "elapsed_time": "1:32:22", "remaining_time": "1:15:09"}
|
||||
{"current_steps": 2290, "total_steps": 4144, "loss": 0.405, "lr": 1.9839931286769795e-05, "epoch": 3.8689771766694845, "percentage": 55.26, "elapsed_time": "1:32:34", "remaining_time": "1:14:56"}
|
||||
{"current_steps": 2295, "total_steps": 4144, "loss": 0.3991, "lr": 1.9755688063729693e-05, "epoch": 3.877430262045647, "percentage": 55.38, "elapsed_time": "1:32:46", "remaining_time": "1:14:44"}
|
||||
{"current_steps": 2300, "total_steps": 4144, "loss": 0.3784, "lr": 1.9671449175788698e-05, "epoch": 3.885883347421809, "percentage": 55.5, "elapsed_time": "1:32:59", "remaining_time": "1:14:32"}
|
||||
{"current_steps": 2305, "total_steps": 4144, "loss": 0.4323, "lr": 1.9587216117691333e-05, "epoch": 3.8943364327979713, "percentage": 55.62, "elapsed_time": "1:33:10", "remaining_time": "1:14:19"}
|
||||
{"current_steps": 2310, "total_steps": 4144, "loss": 0.3894, "lr": 1.9502990384078676e-05, "epoch": 3.9027895181741337, "percentage": 55.74, "elapsed_time": "1:33:22", "remaining_time": "1:14:07"}
|
||||
{"current_steps": 2315, "total_steps": 4144, "loss": 0.4093, "lr": 1.941877346946183e-05, "epoch": 3.9112426035502956, "percentage": 55.86, "elapsed_time": "1:33:34", "remaining_time": "1:13:55"}
|
||||
{"current_steps": 2320, "total_steps": 4144, "loss": 0.413, "lr": 1.9334566868195425e-05, "epoch": 3.919695688926458, "percentage": 55.98, "elapsed_time": "1:33:45", "remaining_time": "1:13:43"}
|
||||
{"current_steps": 2325, "total_steps": 4144, "loss": 0.4005, "lr": 1.9250372074451084e-05, "epoch": 3.9281487743026204, "percentage": 56.11, "elapsed_time": "1:33:58", "remaining_time": "1:13:31"}
|
||||
{"current_steps": 2330, "total_steps": 4144, "loss": 0.415, "lr": 1.9166190582190907e-05, "epoch": 3.936601859678783, "percentage": 56.23, "elapsed_time": "1:34:10", "remaining_time": "1:13:19"}
|
||||
{"current_steps": 2335, "total_steps": 4144, "loss": 0.452, "lr": 1.908202388514099e-05, "epoch": 3.9450549450549453, "percentage": 56.35, "elapsed_time": "1:34:23", "remaining_time": "1:13:07"}
|
||||
{"current_steps": 2340, "total_steps": 4144, "loss": 0.3993, "lr": 1.8997873476764884e-05, "epoch": 3.953508030431107, "percentage": 56.47, "elapsed_time": "1:34:35", "remaining_time": "1:12:55"}
|
||||
{"current_steps": 2345, "total_steps": 4144, "loss": 0.378, "lr": 1.891374085023711e-05, "epoch": 3.9619611158072696, "percentage": 56.59, "elapsed_time": "1:34:47", "remaining_time": "1:12:42"}
|
||||
{"current_steps": 2350, "total_steps": 4144, "loss": 0.3829, "lr": 1.8829627498416698e-05, "epoch": 3.970414201183432, "percentage": 56.71, "elapsed_time": "1:34:59", "remaining_time": "1:12:30"}
|
||||
{"current_steps": 2355, "total_steps": 4144, "loss": 0.4106, "lr": 1.874553491382062e-05, "epoch": 3.978867286559594, "percentage": 56.83, "elapsed_time": "1:35:11", "remaining_time": "1:12:18"}
|
||||
{"current_steps": 2360, "total_steps": 4144, "loss": 0.4099, "lr": 1.8661464588597373e-05, "epoch": 3.9873203719357564, "percentage": 56.95, "elapsed_time": "1:35:22", "remaining_time": "1:12:06"}
|
||||
{"current_steps": 2365, "total_steps": 4144, "loss": 0.4164, "lr": 1.8577418014500505e-05, "epoch": 3.995773457311919, "percentage": 57.07, "elapsed_time": "1:35:33", "remaining_time": "1:11:53"}
|
||||
{"current_steps": 2370, "total_steps": 4144, "loss": 0.3884, "lr": 1.8493396682862066e-05, "epoch": 4.003381234150465, "percentage": 57.19, "elapsed_time": "1:35:44", "remaining_time": "1:11:40"}
|
||||
{"current_steps": 2375, "total_steps": 4144, "loss": 0.3461, "lr": 1.8409402084566254e-05, "epoch": 4.011834319526627, "percentage": 57.31, "elapsed_time": "1:35:56", "remaining_time": "1:11:27"}
|
||||
{"current_steps": 2380, "total_steps": 4144, "loss": 0.3621, "lr": 1.8325435710022886e-05, "epoch": 4.020287404902789, "percentage": 57.43, "elapsed_time": "1:36:08", "remaining_time": "1:11:15"}
|
||||
{"current_steps": 2385, "total_steps": 4144, "loss": 0.3607, "lr": 1.824149904914096e-05, "epoch": 4.028740490278952, "percentage": 57.55, "elapsed_time": "1:36:21", "remaining_time": "1:11:03"}
|
||||
{"current_steps": 2390, "total_steps": 4144, "loss": 0.3751, "lr": 1.8157593591302253e-05, "epoch": 4.037193575655114, "percentage": 57.67, "elapsed_time": "1:36:33", "remaining_time": "1:10:52"}
|
||||
{"current_steps": 2395, "total_steps": 4144, "loss": 0.371, "lr": 1.8073720825334874e-05, "epoch": 4.0456466610312765, "percentage": 57.79, "elapsed_time": "1:36:45", "remaining_time": "1:10:39"}
|
||||
{"current_steps": 2400, "total_steps": 4144, "loss": 0.3767, "lr": 1.798988223948682e-05, "epoch": 4.054099746407439, "percentage": 57.92, "elapsed_time": "1:36:57", "remaining_time": "1:10:27"}
|
||||
{"current_steps": 2405, "total_steps": 4144, "loss": 0.3434, "lr": 1.79060793213996e-05, "epoch": 4.062552831783601, "percentage": 58.04, "elapsed_time": "1:37:10", "remaining_time": "1:10:15"}
|
||||
{"current_steps": 2410, "total_steps": 4144, "loss": 0.3515, "lr": 1.782231355808186e-05, "epoch": 4.071005917159764, "percentage": 58.16, "elapsed_time": "1:37:21", "remaining_time": "1:10:03"}
|
||||
{"current_steps": 2415, "total_steps": 4144, "loss": 0.3683, "lr": 1.7738586435882916e-05, "epoch": 4.079459002535925, "percentage": 58.28, "elapsed_time": "1:37:34", "remaining_time": "1:09:51"}
|
||||
{"current_steps": 2420, "total_steps": 4144, "loss": 0.3411, "lr": 1.7654899440466477e-05, "epoch": 4.087912087912088, "percentage": 58.4, "elapsed_time": "1:37:45", "remaining_time": "1:09:38"}
|
||||
{"current_steps": 2425, "total_steps": 4144, "loss": 0.3479, "lr": 1.757125405678421e-05, "epoch": 4.09636517328825, "percentage": 58.52, "elapsed_time": "1:37:58", "remaining_time": "1:09:26"}
|
||||
{"current_steps": 2430, "total_steps": 4144, "loss": 0.3744, "lr": 1.748765176904943e-05, "epoch": 4.104818258664412, "percentage": 58.64, "elapsed_time": "1:38:10", "remaining_time": "1:09:14"}
|
||||
{"current_steps": 2435, "total_steps": 4144, "loss": 0.3731, "lr": 1.7404094060710753e-05, "epoch": 4.113271344040575, "percentage": 58.76, "elapsed_time": "1:38:22", "remaining_time": "1:09:02"}
|
||||
{"current_steps": 2440, "total_steps": 4144, "loss": 0.3515, "lr": 1.7320582414425766e-05, "epoch": 4.121724429416737, "percentage": 58.88, "elapsed_time": "1:38:33", "remaining_time": "1:08:49"}
|
||||
{"current_steps": 2445, "total_steps": 4144, "loss": 0.3525, "lr": 1.723711831203474e-05, "epoch": 4.1301775147929, "percentage": 59.0, "elapsed_time": "1:38:45", "remaining_time": "1:08:37"}
|
||||
{"current_steps": 2450, "total_steps": 4144, "loss": 0.3663, "lr": 1.7153703234534302e-05, "epoch": 4.138630600169062, "percentage": 59.12, "elapsed_time": "1:38:56", "remaining_time": "1:08:24"}
|
||||
{"current_steps": 2455, "total_steps": 4144, "loss": 0.3398, "lr": 1.7070338662051186e-05, "epoch": 4.147083685545224, "percentage": 59.24, "elapsed_time": "1:39:08", "remaining_time": "1:08:12"}
|
||||
{"current_steps": 2460, "total_steps": 4144, "loss": 0.3334, "lr": 1.6987026073815956e-05, "epoch": 4.155536770921386, "percentage": 59.36, "elapsed_time": "1:39:20", "remaining_time": "1:08:00"}
|
||||
{"current_steps": 2465, "total_steps": 4144, "loss": 0.3548, "lr": 1.6903766948136785e-05, "epoch": 4.163989856297548, "percentage": 59.48, "elapsed_time": "1:39:32", "remaining_time": "1:07:48"}
|
||||
{"current_steps": 2470, "total_steps": 4144, "loss": 0.3656, "lr": 1.6820562762373155e-05, "epoch": 4.172442941673711, "percentage": 59.6, "elapsed_time": "1:39:43", "remaining_time": "1:07:35"}
|
||||
{"current_steps": 2475, "total_steps": 4144, "loss": 0.3549, "lr": 1.673741499290972e-05, "epoch": 4.180896027049873, "percentage": 59.72, "elapsed_time": "1:39:55", "remaining_time": "1:07:22"}
|
||||
{"current_steps": 2480, "total_steps": 4144, "loss": 0.369, "lr": 1.6654325115130076e-05, "epoch": 4.189349112426036, "percentage": 59.85, "elapsed_time": "1:40:08", "remaining_time": "1:07:11"}
|
||||
{"current_steps": 2485, "total_steps": 4144, "loss": 0.3686, "lr": 1.6571294603390566e-05, "epoch": 4.197802197802198, "percentage": 59.97, "elapsed_time": "1:40:19", "remaining_time": "1:06:58"}
|
||||
{"current_steps": 2490, "total_steps": 4144, "loss": 0.3762, "lr": 1.6488324930994148e-05, "epoch": 4.20625528317836, "percentage": 60.09, "elapsed_time": "1:40:31", "remaining_time": "1:06:46"}
|
||||
{"current_steps": 2495, "total_steps": 4144, "loss": 0.362, "lr": 1.6405417570164244e-05, "epoch": 4.214708368554523, "percentage": 60.21, "elapsed_time": "1:40:42", "remaining_time": "1:06:33"}
|
||||
{"current_steps": 2500, "total_steps": 4144, "loss": 0.3498, "lr": 1.632257399201859e-05, "epoch": 4.223161453930684, "percentage": 60.33, "elapsed_time": "1:40:54", "remaining_time": "1:06:21"}
|
||||
{"current_steps": 2505, "total_steps": 4144, "loss": 0.3415, "lr": 1.6239795666543182e-05, "epoch": 4.231614539306847, "percentage": 60.45, "elapsed_time": "1:41:06", "remaining_time": "1:06:09"}
|
||||
{"current_steps": 2510, "total_steps": 4144, "loss": 0.3642, "lr": 1.615708406256614e-05, "epoch": 4.240067624683009, "percentage": 60.57, "elapsed_time": "1:41:18", "remaining_time": "1:05:57"}
|
||||
{"current_steps": 2515, "total_steps": 4144, "loss": 0.3433, "lr": 1.6074440647731688e-05, "epoch": 4.2485207100591715, "percentage": 60.69, "elapsed_time": "1:41:30", "remaining_time": "1:05:44"}
|
||||
{"current_steps": 2520, "total_steps": 4144, "loss": 0.3306, "lr": 1.59918668884741e-05, "epoch": 4.256973795435334, "percentage": 60.81, "elapsed_time": "1:41:41", "remaining_time": "1:05:32"}
|
||||
{"current_steps": 2525, "total_steps": 4144, "loss": 0.3624, "lr": 1.5909364249991643e-05, "epoch": 4.265426880811496, "percentage": 60.93, "elapsed_time": "1:41:53", "remaining_time": "1:05:19"}
|
||||
{"current_steps": 2530, "total_steps": 4144, "loss": 0.365, "lr": 1.5826934196220636e-05, "epoch": 4.273879966187659, "percentage": 61.05, "elapsed_time": "1:42:05", "remaining_time": "1:05:07"}
|
||||
{"current_steps": 2535, "total_steps": 4144, "loss": 0.3643, "lr": 1.5744578189809446e-05, "epoch": 4.282333051563821, "percentage": 61.17, "elapsed_time": "1:42:17", "remaining_time": "1:04:55"}
|
||||
{"current_steps": 2540, "total_steps": 4144, "loss": 0.3375, "lr": 1.566229769209251e-05, "epoch": 4.290786136939984, "percentage": 61.29, "elapsed_time": "1:42:28", "remaining_time": "1:04:42"}
|
||||
{"current_steps": 2545, "total_steps": 4144, "loss": 0.3705, "lr": 1.558009416306446e-05, "epoch": 4.299239222316145, "percentage": 61.41, "elapsed_time": "1:42:40", "remaining_time": "1:04:30"}
|
||||
{"current_steps": 2550, "total_steps": 4144, "loss": 0.3449, "lr": 1.5497969061354176e-05, "epoch": 4.3076923076923075, "percentage": 61.53, "elapsed_time": "1:42:53", "remaining_time": "1:04:19"}
|
||||
{"current_steps": 2555, "total_steps": 4144, "loss": 0.3771, "lr": 1.541592384419891e-05, "epoch": 4.31614539306847, "percentage": 61.66, "elapsed_time": "1:43:04", "remaining_time": "1:04:06"}
|
||||
{"current_steps": 2560, "total_steps": 4144, "loss": 0.3699, "lr": 1.5333959967418423e-05, "epoch": 4.324598478444632, "percentage": 61.78, "elapsed_time": "1:43:18", "remaining_time": "1:03:55"}
|
||||
{"current_steps": 2565, "total_steps": 4144, "loss": 0.3471, "lr": 1.5252078885389195e-05, "epoch": 4.333051563820795, "percentage": 61.9, "elapsed_time": "1:43:30", "remaining_time": "1:03:43"}
|
||||
{"current_steps": 2570, "total_steps": 4144, "loss": 0.3471, "lr": 1.5170282051018555e-05, "epoch": 4.341504649196957, "percentage": 62.02, "elapsed_time": "1:43:42", "remaining_time": "1:03:30"}
|
||||
{"current_steps": 2575, "total_steps": 4144, "loss": 0.3697, "lr": 1.5088570915718952e-05, "epoch": 4.3499577345731195, "percentage": 62.14, "elapsed_time": "1:43:54", "remaining_time": "1:03:18"}
|
||||
{"current_steps": 2580, "total_steps": 4144, "loss": 0.3601, "lr": 1.500694692938217e-05, "epoch": 4.358410819949281, "percentage": 62.26, "elapsed_time": "1:44:07", "remaining_time": "1:03:07"}
|
||||
{"current_steps": 2585, "total_steps": 4144, "loss": 0.3455, "lr": 1.4925411540353611e-05, "epoch": 4.366863905325443, "percentage": 62.38, "elapsed_time": "1:44:19", "remaining_time": "1:02:54"}
|
||||
{"current_steps": 2590, "total_steps": 4144, "loss": 0.3465, "lr": 1.4843966195406605e-05, "epoch": 4.375316990701606, "percentage": 62.5, "elapsed_time": "1:44:30", "remaining_time": "1:02:42"}
|
||||
{"current_steps": 2595, "total_steps": 4144, "loss": 0.3669, "lr": 1.476261233971673e-05, "epoch": 4.383770076077768, "percentage": 62.62, "elapsed_time": "1:44:43", "remaining_time": "1:02:30"}
|
||||
{"current_steps": 2600, "total_steps": 4144, "loss": 0.3738, "lr": 1.4681351416836149e-05, "epoch": 4.392223161453931, "percentage": 62.74, "elapsed_time": "1:44:55", "remaining_time": "1:02:18"}
|
||||
{"current_steps": 2605, "total_steps": 4144, "loss": 0.3464, "lr": 1.4600184868668041e-05, "epoch": 4.400676246830093, "percentage": 62.86, "elapsed_time": "1:45:07", "remaining_time": "1:02:06"}
|
||||
{"current_steps": 2610, "total_steps": 4144, "loss": 0.3741, "lr": 1.4519114135440964e-05, "epoch": 4.4091293322062555, "percentage": 62.98, "elapsed_time": "1:45:19", "remaining_time": "1:01:54"}
|
||||
{"current_steps": 2615, "total_steps": 4144, "loss": 0.3369, "lr": 1.4438140655683343e-05, "epoch": 4.417582417582418, "percentage": 63.1, "elapsed_time": "1:45:32", "remaining_time": "1:01:42"}
|
||||
{"current_steps": 2620, "total_steps": 4144, "loss": 0.3582, "lr": 1.435726586619793e-05, "epoch": 4.42603550295858, "percentage": 63.22, "elapsed_time": "1:45:45", "remaining_time": "1:01:31"}
|
||||
{"current_steps": 2625, "total_steps": 4144, "loss": 0.3728, "lr": 1.4276491202036277e-05, "epoch": 4.434488588334742, "percentage": 63.34, "elapsed_time": "1:45:57", "remaining_time": "1:01:19"}
|
||||
{"current_steps": 2630, "total_steps": 4144, "loss": 0.359, "lr": 1.4195818096473329e-05, "epoch": 4.442941673710904, "percentage": 63.47, "elapsed_time": "1:46:09", "remaining_time": "1:01:06"}
|
||||
{"current_steps": 2635, "total_steps": 4144, "loss": 0.3491, "lr": 1.411524798098196e-05, "epoch": 4.451394759087067, "percentage": 63.59, "elapsed_time": "1:46:20", "remaining_time": "1:00:53"}
|
||||
{"current_steps": 2640, "total_steps": 4144, "loss": 0.3576, "lr": 1.403478228520756e-05, "epoch": 4.459847844463229, "percentage": 63.71, "elapsed_time": "1:46:31", "remaining_time": "1:00:41"}
|
||||
{"current_steps": 2645, "total_steps": 4144, "loss": 0.3462, "lr": 1.3954422436942696e-05, "epoch": 4.468300929839391, "percentage": 63.83, "elapsed_time": "1:46:43", "remaining_time": "1:00:29"}
|
||||
{"current_steps": 2650, "total_steps": 4144, "loss": 0.3621, "lr": 1.3874169862101774e-05, "epoch": 4.476754015215554, "percentage": 63.95, "elapsed_time": "1:46:54", "remaining_time": "1:00:16"}
|
||||
{"current_steps": 2655, "total_steps": 4144, "loss": 0.3522, "lr": 1.3794025984695698e-05, "epoch": 4.485207100591716, "percentage": 64.07, "elapsed_time": "1:47:05", "remaining_time": "1:00:03"}
|
||||
{"current_steps": 2660, "total_steps": 4144, "loss": 0.3886, "lr": 1.371399222680666e-05, "epoch": 4.493660185967879, "percentage": 64.19, "elapsed_time": "1:47:18", "remaining_time": "0:59:51"}
|
||||
{"current_steps": 2665, "total_steps": 4144, "loss": 0.3811, "lr": 1.3634070008562878e-05, "epoch": 4.50211327134404, "percentage": 64.31, "elapsed_time": "1:47:31", "remaining_time": "0:59:40"}
|
||||
{"current_steps": 2670, "total_steps": 4144, "loss": 0.3618, "lr": 1.3554260748113372e-05, "epoch": 4.510566356720203, "percentage": 64.43, "elapsed_time": "1:47:43", "remaining_time": "0:59:28"}
|
||||
{"current_steps": 2675, "total_steps": 4144, "loss": 0.365, "lr": 1.3474565861602851e-05, "epoch": 4.519019442096365, "percentage": 64.55, "elapsed_time": "1:47:56", "remaining_time": "0:59:16"}
|
||||
{"current_steps": 2680, "total_steps": 4144, "loss": 0.3688, "lr": 1.3394986763146556e-05, "epoch": 4.527472527472527, "percentage": 64.67, "elapsed_time": "1:48:08", "remaining_time": "0:59:04"}
|
||||
{"current_steps": 2685, "total_steps": 4144, "loss": 0.3461, "lr": 1.3315524864805163e-05, "epoch": 4.53592561284869, "percentage": 64.79, "elapsed_time": "1:48:20", "remaining_time": "0:58:52"}
|
||||
{"current_steps": 2690, "total_steps": 4144, "loss": 0.3485, "lr": 1.3236181576559739e-05, "epoch": 4.544378698224852, "percentage": 64.91, "elapsed_time": "1:48:32", "remaining_time": "0:58:40"}
|
||||
{"current_steps": 2695, "total_steps": 4144, "loss": 0.3714, "lr": 1.3156958306286715e-05, "epoch": 4.552831783601015, "percentage": 65.03, "elapsed_time": "1:48:44", "remaining_time": "0:58:28"}
|
||||
{"current_steps": 2700, "total_steps": 4144, "loss": 0.3442, "lr": 1.3077856459732923e-05, "epoch": 4.561284868977177, "percentage": 65.15, "elapsed_time": "1:48:56", "remaining_time": "0:58:15"}
|
||||
{"current_steps": 2705, "total_steps": 4144, "loss": 0.3659, "lr": 1.2998877440490637e-05, "epoch": 4.569737954353339, "percentage": 65.28, "elapsed_time": "1:49:07", "remaining_time": "0:58:03"}
|
||||
{"current_steps": 2710, "total_steps": 4144, "loss": 0.3662, "lr": 1.2920022649972643e-05, "epoch": 4.578191039729501, "percentage": 65.4, "elapsed_time": "1:49:18", "remaining_time": "0:57:50"}
|
||||
{"current_steps": 2715, "total_steps": 4144, "loss": 0.3746, "lr": 1.284129348738743e-05, "epoch": 4.586644125105663, "percentage": 65.52, "elapsed_time": "1:49:32", "remaining_time": "0:57:39"}
|
||||
{"current_steps": 2720, "total_steps": 4144, "loss": 0.3671, "lr": 1.2762691349714325e-05, "epoch": 4.595097210481826, "percentage": 65.64, "elapsed_time": "1:49:43", "remaining_time": "0:57:26"}
|
||||
{"current_steps": 2725, "total_steps": 4144, "loss": 0.3727, "lr": 1.2684217631678684e-05, "epoch": 4.603550295857988, "percentage": 65.76, "elapsed_time": "1:49:55", "remaining_time": "0:57:14"}
|
||||
{"current_steps": 2730, "total_steps": 4144, "loss": 0.362, "lr": 1.2605873725727203e-05, "epoch": 4.6120033812341505, "percentage": 65.88, "elapsed_time": "1:50:08", "remaining_time": "0:57:02"}
|
||||
{"current_steps": 2735, "total_steps": 4144, "loss": 0.3622, "lr": 1.2527661022003169e-05, "epoch": 4.620456466610313, "percentage": 66.0, "elapsed_time": "1:50:19", "remaining_time": "0:56:50"}
|
||||
{"current_steps": 2740, "total_steps": 4144, "loss": 0.3746, "lr": 1.2449580908321778e-05, "epoch": 4.628909551986475, "percentage": 66.12, "elapsed_time": "1:50:31", "remaining_time": "0:56:38"}
|
||||
{"current_steps": 2745, "total_steps": 4144, "loss": 0.3763, "lr": 1.2371634770145566e-05, "epoch": 4.637362637362637, "percentage": 66.24, "elapsed_time": "1:50:42", "remaining_time": "0:56:25"}
|
||||
{"current_steps": 2750, "total_steps": 4144, "loss": 0.3472, "lr": 1.2293823990559784e-05, "epoch": 4.645815722738799, "percentage": 66.36, "elapsed_time": "1:50:54", "remaining_time": "0:56:13"}
|
||||
{"current_steps": 2755, "total_steps": 4144, "loss": 0.3685, "lr": 1.221614995024784e-05, "epoch": 4.654268808114962, "percentage": 66.48, "elapsed_time": "1:51:06", "remaining_time": "0:56:00"}
|
||||
{"current_steps": 2760, "total_steps": 4144, "loss": 0.3623, "lr": 1.2138614027466854e-05, "epoch": 4.662721893491124, "percentage": 66.6, "elapsed_time": "1:51:17", "remaining_time": "0:55:48"}
|
||||
{"current_steps": 2765, "total_steps": 4144, "loss": 0.3452, "lr": 1.2061217598023164e-05, "epoch": 4.6711749788672865, "percentage": 66.72, "elapsed_time": "1:51:28", "remaining_time": "0:55:35"}
|
||||
{"current_steps": 2770, "total_steps": 4144, "loss": 0.3634, "lr": 1.1983962035247911e-05, "epoch": 4.679628064243449, "percentage": 66.84, "elapsed_time": "1:51:40", "remaining_time": "0:55:23"}
|
||||
{"current_steps": 2775, "total_steps": 4144, "loss": 0.3759, "lr": 1.1906848709972705e-05, "epoch": 4.688081149619611, "percentage": 66.96, "elapsed_time": "1:51:53", "remaining_time": "0:55:11"}
|
||||
{"current_steps": 2780, "total_steps": 4144, "loss": 0.3466, "lr": 1.1829878990505244e-05, "epoch": 4.696534234995774, "percentage": 67.08, "elapsed_time": "1:52:04", "remaining_time": "0:54:59"}
|
||||
{"current_steps": 2785, "total_steps": 4144, "loss": 0.3589, "lr": 1.1753054242605098e-05, "epoch": 4.704987320371936, "percentage": 67.21, "elapsed_time": "1:52:16", "remaining_time": "0:54:47"}
|
||||
{"current_steps": 2790, "total_steps": 4144, "loss": 0.3743, "lr": 1.1676375829459437e-05, "epoch": 4.7134404057480985, "percentage": 67.33, "elapsed_time": "1:52:27", "remaining_time": "0:54:34"}
|
||||
{"current_steps": 2795, "total_steps": 4144, "loss": 0.3582, "lr": 1.1599845111658834e-05, "epoch": 4.72189349112426, "percentage": 67.45, "elapsed_time": "1:52:39", "remaining_time": "0:54:22"}
|
||||
{"current_steps": 2800, "total_steps": 4144, "loss": 0.3685, "lr": 1.1523463447173167e-05, "epoch": 4.7303465765004225, "percentage": 67.57, "elapsed_time": "1:52:50", "remaining_time": "0:54:09"}
|
||||
{"current_steps": 2805, "total_steps": 4144, "loss": 0.3583, "lr": 1.1447232191327475e-05, "epoch": 4.738799661876585, "percentage": 67.69, "elapsed_time": "1:53:02", "remaining_time": "0:53:57"}
|
||||
{"current_steps": 2810, "total_steps": 4144, "loss": 0.3539, "lr": 1.137115269677793e-05, "epoch": 4.747252747252747, "percentage": 67.81, "elapsed_time": "1:53:14", "remaining_time": "0:53:45"}
|
||||
{"current_steps": 2815, "total_steps": 4144, "loss": 0.359, "lr": 1.129522631348783e-05, "epoch": 4.75570583262891, "percentage": 67.93, "elapsed_time": "1:53:26", "remaining_time": "0:53:33"}
|
||||
{"current_steps": 2820, "total_steps": 4144, "loss": 0.3795, "lr": 1.1219454388703683e-05, "epoch": 4.764158918005072, "percentage": 68.05, "elapsed_time": "1:53:37", "remaining_time": "0:53:20"}
|
||||
{"current_steps": 2825, "total_steps": 4144, "loss": 0.3589, "lr": 1.114383826693121e-05, "epoch": 4.7726120033812345, "percentage": 68.17, "elapsed_time": "1:53:48", "remaining_time": "0:53:08"}
|
||||
{"current_steps": 2830, "total_steps": 4144, "loss": 0.3437, "lr": 1.10683792899116e-05, "epoch": 4.781065088757396, "percentage": 68.29, "elapsed_time": "1:54:00", "remaining_time": "0:52:56"}
|
||||
{"current_steps": 2835, "total_steps": 4144, "loss": 0.3656, "lr": 1.0993078796597614e-05, "epoch": 4.789518174133558, "percentage": 68.41, "elapsed_time": "1:54:12", "remaining_time": "0:52:43"}
|
||||
{"current_steps": 2840, "total_steps": 4144, "loss": 0.3535, "lr": 1.0917938123129873e-05, "epoch": 4.797971259509721, "percentage": 68.53, "elapsed_time": "1:54:23", "remaining_time": "0:52:31"}
|
||||
{"current_steps": 2845, "total_steps": 4144, "loss": 0.3789, "lr": 1.0842958602813121e-05, "epoch": 4.806424344885883, "percentage": 68.65, "elapsed_time": "1:54:36", "remaining_time": "0:52:19"}
|
||||
{"current_steps": 2850, "total_steps": 4144, "loss": 0.3771, "lr": 1.0768141566092622e-05, "epoch": 4.814877430262046, "percentage": 68.77, "elapsed_time": "1:54:47", "remaining_time": "0:52:07"}
|
||||
{"current_steps": 2855, "total_steps": 4144, "loss": 0.3667, "lr": 1.069348834053045e-05, "epoch": 4.823330515638208, "percentage": 68.89, "elapsed_time": "1:54:59", "remaining_time": "0:51:55"}
|
||||
{"current_steps": 2860, "total_steps": 4144, "loss": 0.336, "lr": 1.0619000250782059e-05, "epoch": 4.83178360101437, "percentage": 69.02, "elapsed_time": "1:55:11", "remaining_time": "0:51:42"}
|
||||
{"current_steps": 2865, "total_steps": 4144, "loss": 0.3887, "lr": 1.054467861857267e-05, "epoch": 4.840236686390533, "percentage": 69.14, "elapsed_time": "1:55:22", "remaining_time": "0:51:30"}
|
||||
{"current_steps": 2870, "total_steps": 4144, "loss": 0.3715, "lr": 1.0470524762673881e-05, "epoch": 4.848689771766695, "percentage": 69.26, "elapsed_time": "1:55:33", "remaining_time": "0:51:17"}
|
||||
{"current_steps": 2875, "total_steps": 4144, "loss": 0.3864, "lr": 1.0396539998880243e-05, "epoch": 4.857142857142857, "percentage": 69.38, "elapsed_time": "1:55:45", "remaining_time": "0:51:05"}
|
||||
{"current_steps": 2880, "total_steps": 4144, "loss": 0.3686, "lr": 1.0322725639985908e-05, "epoch": 4.865595942519019, "percentage": 69.5, "elapsed_time": "1:55:56", "remaining_time": "0:50:53"}
|
||||
{"current_steps": 2885, "total_steps": 4144, "loss": 0.3604, "lr": 1.0249082995761374e-05, "epoch": 4.874049027895182, "percentage": 69.62, "elapsed_time": "1:56:08", "remaining_time": "0:50:40"}
|
||||
{"current_steps": 2890, "total_steps": 4144, "loss": 0.3733, "lr": 1.0175613372930184e-05, "epoch": 4.882502113271344, "percentage": 69.74, "elapsed_time": "1:56:20", "remaining_time": "0:50:29"}
|
||||
{"current_steps": 2895, "total_steps": 4144, "loss": 0.3761, "lr": 1.0102318075145779e-05, "epoch": 4.890955198647506, "percentage": 69.86, "elapsed_time": "1:56:33", "remaining_time": "0:50:17"}
|
||||
{"current_steps": 2900, "total_steps": 4144, "loss": 0.3527, "lr": 1.0029198402968347e-05, "epoch": 4.899408284023669, "percentage": 69.98, "elapsed_time": "1:56:45", "remaining_time": "0:50:05"}
|
||||
{"current_steps": 2905, "total_steps": 4144, "loss": 0.3481, "lr": 9.956255653841793e-06, "epoch": 4.907861369399831, "percentage": 70.1, "elapsed_time": "1:56:58", "remaining_time": "0:49:53"}
|
||||
{"current_steps": 2910, "total_steps": 4144, "loss": 0.357, "lr": 9.883491122070617e-06, "epoch": 4.916314454775994, "percentage": 70.22, "elapsed_time": "1:57:09", "remaining_time": "0:49:40"}
|
||||
{"current_steps": 2915, "total_steps": 4144, "loss": 0.3768, "lr": 9.810906098797067e-06, "epoch": 4.924767540152155, "percentage": 70.34, "elapsed_time": "1:57:21", "remaining_time": "0:49:28"}
|
||||
{"current_steps": 2920, "total_steps": 4144, "loss": 0.3466, "lr": 9.738501871978138e-06, "epoch": 4.9332206255283175, "percentage": 70.46, "elapsed_time": "1:57:32", "remaining_time": "0:49:16"}
|
||||
{"current_steps": 2925, "total_steps": 4144, "loss": 0.3711, "lr": 9.666279726362769e-06, "epoch": 4.94167371090448, "percentage": 70.58, "elapsed_time": "1:57:43", "remaining_time": "0:49:03"}
|
||||
{"current_steps": 2930, "total_steps": 4144, "loss": 0.364, "lr": 9.594240943469008e-06, "epoch": 4.950126796280642, "percentage": 70.7, "elapsed_time": "1:57:54", "remaining_time": "0:48:51"}
|
||||
{"current_steps": 2935, "total_steps": 4144, "loss": 0.3614, "lr": 9.522386801561334e-06, "epoch": 4.958579881656805, "percentage": 70.83, "elapsed_time": "1:58:05", "remaining_time": "0:48:38"}
|
||||
{"current_steps": 2940, "total_steps": 4144, "loss": 0.3418, "lr": 9.45071857562788e-06, "epoch": 4.967032967032967, "percentage": 70.95, "elapsed_time": "1:58:18", "remaining_time": "0:48:26"}
|
||||
{"current_steps": 2945, "total_steps": 4144, "loss": 0.3645, "lr": 9.379237537357913e-06, "epoch": 4.97548605240913, "percentage": 71.07, "elapsed_time": "1:58:30", "remaining_time": "0:48:15"}
|
||||
{"current_steps": 2950, "total_steps": 4144, "loss": 0.3716, "lr": 9.307944955119193e-06, "epoch": 4.983939137785292, "percentage": 71.19, "elapsed_time": "1:58:42", "remaining_time": "0:48:02"}
|
||||
{"current_steps": 2955, "total_steps": 4144, "loss": 0.37, "lr": 9.236842093935508e-06, "epoch": 4.992392223161454, "percentage": 71.31, "elapsed_time": "1:58:53", "remaining_time": "0:47:50"}
|
||||
{"current_steps": 2960, "total_steps": 4144, "loss": 0.3813, "lr": 9.165930215464203e-06, "epoch": 5.0, "percentage": 71.43, "elapsed_time": "1:59:04", "remaining_time": "0:47:37"}
|
||||
{"current_steps": 2965, "total_steps": 4144, "loss": 0.3254, "lr": 9.095210577973814e-06, "epoch": 5.008453085376162, "percentage": 71.55, "elapsed_time": "1:59:16", "remaining_time": "0:47:25"}
|
||||
{"current_steps": 2970, "total_steps": 4144, "loss": 0.3231, "lr": 9.024684436321716e-06, "epoch": 5.016906170752325, "percentage": 71.67, "elapsed_time": "1:59:28", "remaining_time": "0:47:13"}
|
||||
{"current_steps": 2975, "total_steps": 4144, "loss": 0.3243, "lr": 8.954353041931905e-06, "epoch": 5.025359256128487, "percentage": 71.79, "elapsed_time": "1:59:41", "remaining_time": "0:47:01"}
|
||||
{"current_steps": 2980, "total_steps": 4144, "loss": 0.3271, "lr": 8.884217642772704e-06, "epoch": 5.03381234150465, "percentage": 71.91, "elapsed_time": "1:59:52", "remaining_time": "0:46:49"}
|
||||
{"current_steps": 2985, "total_steps": 4144, "loss": 0.3112, "lr": 8.81427948333473e-06, "epoch": 5.042265426880811, "percentage": 72.03, "elapsed_time": "2:00:03", "remaining_time": "0:46:36"}
|
||||
{"current_steps": 2990, "total_steps": 4144, "loss": 0.3183, "lr": 8.744539804608727e-06, "epoch": 5.0507185122569735, "percentage": 72.15, "elapsed_time": "2:00:14", "remaining_time": "0:46:24"}
|
||||
{"current_steps": 2995, "total_steps": 4144, "loss": 0.3104, "lr": 8.674999844063576e-06, "epoch": 5.059171597633136, "percentage": 72.27, "elapsed_time": "2:00:27", "remaining_time": "0:46:12"}
|
||||
{"current_steps": 3000, "total_steps": 4144, "loss": 0.3151, "lr": 8.605660835624332e-06, "epoch": 5.067624683009298, "percentage": 72.39, "elapsed_time": "2:00:39", "remaining_time": "0:46:00"}
|
||||
{"current_steps": 3005, "total_steps": 4144, "loss": 0.3373, "lr": 8.536524009650352e-06, "epoch": 5.076077768385461, "percentage": 72.51, "elapsed_time": "2:01:30", "remaining_time": "0:46:03"}
|
||||
{"current_steps": 3010, "total_steps": 4144, "loss": 0.3336, "lr": 8.46759059291343e-06, "epoch": 5.084530853761623, "percentage": 72.64, "elapsed_time": "2:01:41", "remaining_time": "0:45:50"}
|
||||
{"current_steps": 3015, "total_steps": 4144, "loss": 0.3249, "lr": 8.39886180857604e-06, "epoch": 5.092983939137786, "percentage": 72.76, "elapsed_time": "2:01:52", "remaining_time": "0:45:38"}
|
||||
{"current_steps": 3020, "total_steps": 4144, "loss": 0.3503, "lr": 8.330338876169638e-06, "epoch": 5.101437024513948, "percentage": 72.88, "elapsed_time": "2:02:04", "remaining_time": "0:45:26"}
|
||||
{"current_steps": 3025, "total_steps": 4144, "loss": 0.3184, "lr": 8.26202301157302e-06, "epoch": 5.1098901098901095, "percentage": 73.0, "elapsed_time": "2:02:16", "remaining_time": "0:45:14"}
|
||||
{"current_steps": 3030, "total_steps": 4144, "loss": 0.3183, "lr": 8.19391542699076e-06, "epoch": 5.118343195266272, "percentage": 73.12, "elapsed_time": "2:02:27", "remaining_time": "0:45:01"}
|
||||
{"current_steps": 3035, "total_steps": 4144, "loss": 0.3102, "lr": 8.126017330931666e-06, "epoch": 5.126796280642434, "percentage": 73.24, "elapsed_time": "2:02:38", "remaining_time": "0:44:48"}
|
||||
{"current_steps": 3040, "total_steps": 4144, "loss": 0.3315, "lr": 8.058329928187372e-06, "epoch": 5.135249366018597, "percentage": 73.36, "elapsed_time": "2:02:50", "remaining_time": "0:44:36"}
|
||||
{"current_steps": 3045, "total_steps": 4144, "loss": 0.3288, "lr": 7.990854419810939e-06, "epoch": 5.143702451394759, "percentage": 73.48, "elapsed_time": "2:03:01", "remaining_time": "0:44:24"}
|
||||
{"current_steps": 3050, "total_steps": 4144, "loss": 0.2958, "lr": 7.923592003095551e-06, "epoch": 5.1521555367709215, "percentage": 73.6, "elapsed_time": "2:03:15", "remaining_time": "0:44:12"}
|
||||
{"current_steps": 3055, "total_steps": 4144, "loss": 0.3041, "lr": 7.856543871553261e-06, "epoch": 5.160608622147084, "percentage": 73.72, "elapsed_time": "2:03:27", "remaining_time": "0:44:00"}
|
||||
{"current_steps": 3060, "total_steps": 4144, "loss": 0.3101, "lr": 7.789711214893857e-06, "epoch": 5.169061707523246, "percentage": 73.84, "elapsed_time": "2:03:39", "remaining_time": "0:43:48"}
|
||||
{"current_steps": 3065, "total_steps": 4144, "loss": 0.323, "lr": 7.723095219003659e-06, "epoch": 5.177514792899408, "percentage": 73.96, "elapsed_time": "2:03:51", "remaining_time": "0:43:36"}
|
||||
{"current_steps": 3070, "total_steps": 4144, "loss": 0.3214, "lr": 7.65669706592458e-06, "epoch": 5.18596787827557, "percentage": 74.08, "elapsed_time": "2:04:02", "remaining_time": "0:43:23"}
|
||||
{"current_steps": 3075, "total_steps": 4144, "loss": 0.317, "lr": 7.590517933833088e-06, "epoch": 5.194420963651733, "percentage": 74.2, "elapsed_time": "2:04:14", "remaining_time": "0:43:11"}
|
||||
{"current_steps": 3080, "total_steps": 4144, "loss": 0.3285, "lr": 7.524558997019313e-06, "epoch": 5.202874049027895, "percentage": 74.32, "elapsed_time": "2:04:26", "remaining_time": "0:42:59"}
|
||||
{"current_steps": 3085, "total_steps": 4144, "loss": 0.3411, "lr": 7.458821425866216e-06, "epoch": 5.2113271344040575, "percentage": 74.44, "elapsed_time": "2:04:37", "remaining_time": "0:42:46"}
|
||||
{"current_steps": 3090, "total_steps": 4144, "loss": 0.3152, "lr": 7.393306386828842e-06, "epoch": 5.21978021978022, "percentage": 74.57, "elapsed_time": "2:04:49", "remaining_time": "0:42:34"}
|
||||
{"current_steps": 3095, "total_steps": 4144, "loss": 0.3168, "lr": 7.328015042413556e-06, "epoch": 5.228233305156382, "percentage": 74.69, "elapsed_time": "2:05:02", "remaining_time": "0:42:22"}
|
||||
{"current_steps": 3100, "total_steps": 4144, "loss": 0.3415, "lr": 7.2629485511575075e-06, "epoch": 5.236686390532545, "percentage": 74.81, "elapsed_time": "2:05:13", "remaining_time": "0:42:10"}
|
||||
{"current_steps": 3105, "total_steps": 4144, "loss": 0.3267, "lr": 7.198108067607996e-06, "epoch": 5.245139475908707, "percentage": 74.93, "elapsed_time": "2:05:25", "remaining_time": "0:41:58"}
|
||||
{"current_steps": 3110, "total_steps": 4144, "loss": 0.3156, "lr": 7.133494742302025e-06, "epoch": 5.253592561284869, "percentage": 75.05, "elapsed_time": "2:05:37", "remaining_time": "0:41:46"}
|
||||
{"current_steps": 3115, "total_steps": 4144, "loss": 0.3303, "lr": 7.069109721745864e-06, "epoch": 5.262045646661031, "percentage": 75.17, "elapsed_time": "2:05:49", "remaining_time": "0:41:33"}
|
||||
{"current_steps": 3120, "total_steps": 4144, "loss": 0.3483, "lr": 7.0049541483947495e-06, "epoch": 5.270498732037193, "percentage": 75.29, "elapsed_time": "2:06:00", "remaining_time": "0:41:21"}
|
||||
{"current_steps": 3125, "total_steps": 4144, "loss": 0.3297, "lr": 6.941029160632529e-06, "epoch": 5.278951817413356, "percentage": 75.41, "elapsed_time": "2:06:13", "remaining_time": "0:41:09"}
|
||||
{"current_steps": 3130, "total_steps": 4144, "loss": 0.3019, "lr": 6.87733589275156e-06, "epoch": 5.287404902789518, "percentage": 75.53, "elapsed_time": "2:06:24", "remaining_time": "0:40:57"}
|
||||
{"current_steps": 3135, "total_steps": 4144, "loss": 0.3233, "lr": 6.813875474932512e-06, "epoch": 5.295857988165681, "percentage": 75.65, "elapsed_time": "2:06:36", "remaining_time": "0:40:44"}
|
||||
{"current_steps": 3140, "total_steps": 4144, "loss": 0.336, "lr": 6.7506490332243414e-06, "epoch": 5.304311073541843, "percentage": 75.77, "elapsed_time": "2:06:47", "remaining_time": "0:40:32"}
|
||||
{"current_steps": 3145, "total_steps": 4144, "loss": 0.3179, "lr": 6.6876576895243054e-06, "epoch": 5.3127641589180055, "percentage": 75.89, "elapsed_time": "2:06:59", "remaining_time": "0:40:20"}
|
||||
{"current_steps": 3150, "total_steps": 4144, "loss": 0.3445, "lr": 6.624902561558044e-06, "epoch": 5.321217244294167, "percentage": 76.01, "elapsed_time": "2:07:11", "remaining_time": "0:40:08"}
|
||||
{"current_steps": 3155, "total_steps": 4144, "loss": 0.3085, "lr": 6.562384762859788e-06, "epoch": 5.329670329670329, "percentage": 76.13, "elapsed_time": "2:07:25", "remaining_time": "0:39:56"}
|
||||
{"current_steps": 3160, "total_steps": 4144, "loss": 0.3204, "lr": 6.500105402752541e-06, "epoch": 5.338123415046492, "percentage": 76.25, "elapsed_time": "2:07:37", "remaining_time": "0:39:44"}
|
||||
{"current_steps": 3165, "total_steps": 4144, "loss": 0.333, "lr": 6.438065586328437e-06, "epoch": 5.346576500422654, "percentage": 76.38, "elapsed_time": "2:07:49", "remaining_time": "0:39:32"}
|
||||
{"current_steps": 3170, "total_steps": 4144, "loss": 0.3245, "lr": 6.376266414429108e-06, "epoch": 5.355029585798817, "percentage": 76.5, "elapsed_time": "2:08:01", "remaining_time": "0:39:20"}
|
||||
{"current_steps": 3175, "total_steps": 4144, "loss": 0.3553, "lr": 6.3147089836261945e-06, "epoch": 5.363482671174979, "percentage": 76.62, "elapsed_time": "2:08:14", "remaining_time": "0:39:08"}
|
||||
{"current_steps": 3180, "total_steps": 4144, "loss": 0.3203, "lr": 6.2533943862018055e-06, "epoch": 5.371935756551141, "percentage": 76.74, "elapsed_time": "2:08:26", "remaining_time": "0:38:56"}
|
||||
{"current_steps": 3185, "total_steps": 4144, "loss": 0.2985, "lr": 6.192323710129229e-06, "epoch": 5.380388841927304, "percentage": 76.86, "elapsed_time": "2:08:38", "remaining_time": "0:38:44"}
|
||||
{"current_steps": 3190, "total_steps": 4144, "loss": 0.3173, "lr": 6.131498039053567e-06, "epoch": 5.388841927303465, "percentage": 76.98, "elapsed_time": "2:08:50", "remaining_time": "0:38:31"}
|
||||
{"current_steps": 3195, "total_steps": 4144, "loss": 0.3066, "lr": 6.070918452272523e-06, "epoch": 5.397295012679628, "percentage": 77.1, "elapsed_time": "2:09:01", "remaining_time": "0:38:19"}
|
||||
{"current_steps": 3200, "total_steps": 4144, "loss": 0.3255, "lr": 6.010586024717249e-06, "epoch": 5.40574809805579, "percentage": 77.22, "elapsed_time": "2:09:13", "remaining_time": "0:38:07"}
|
||||
{"current_steps": 3205, "total_steps": 4144, "loss": 0.3372, "lr": 5.950501826933301e-06, "epoch": 5.414201183431953, "percentage": 77.34, "elapsed_time": "2:09:25", "remaining_time": "0:37:55"}
|
||||
{"current_steps": 3210, "total_steps": 4144, "loss": 0.3209, "lr": 5.890666925061576e-06, "epoch": 5.422654268808115, "percentage": 77.46, "elapsed_time": "2:09:37", "remaining_time": "0:37:42"}
|
||||
{"current_steps": 3215, "total_steps": 4144, "loss": 0.3179, "lr": 5.8310823808194815e-06, "epoch": 5.431107354184277, "percentage": 77.58, "elapsed_time": "2:09:48", "remaining_time": "0:37:30"}
|
||||
{"current_steps": 3220, "total_steps": 4144, "loss": 0.311, "lr": 5.771749251481999e-06, "epoch": 5.43956043956044, "percentage": 77.7, "elapsed_time": "2:10:00", "remaining_time": "0:37:18"}
|
||||
{"current_steps": 3225, "total_steps": 4144, "loss": 0.3323, "lr": 5.712668589863024e-06, "epoch": 5.448013524936602, "percentage": 77.82, "elapsed_time": "2:10:11", "remaining_time": "0:37:05"}
|
||||
{"current_steps": 3230, "total_steps": 4144, "loss": 0.3271, "lr": 5.6538414442966106e-06, "epoch": 5.456466610312765, "percentage": 77.94, "elapsed_time": "2:10:23", "remaining_time": "0:36:53"}
|
||||
{"current_steps": 3235, "total_steps": 4144, "loss": 0.3249, "lr": 5.5952688586183924e-06, "epoch": 5.464919695688926, "percentage": 78.06, "elapsed_time": "2:10:35", "remaining_time": "0:36:41"}
|
||||
{"current_steps": 3240, "total_steps": 4144, "loss": 0.324, "lr": 5.536951872147069e-06, "epoch": 5.4733727810650885, "percentage": 78.19, "elapsed_time": "2:10:46", "remaining_time": "0:36:29"}
|
||||
{"current_steps": 3245, "total_steps": 4144, "loss": 0.3463, "lr": 5.478891519665972e-06, "epoch": 5.481825866441251, "percentage": 78.31, "elapsed_time": "2:10:58", "remaining_time": "0:36:17"}
|
||||
{"current_steps": 3250, "total_steps": 4144, "loss": 0.3138, "lr": 5.4210888314046635e-06, "epoch": 5.490278951817413, "percentage": 78.43, "elapsed_time": "2:11:10", "remaining_time": "0:36:05"}
|
||||
{"current_steps": 3255, "total_steps": 4144, "loss": 0.3112, "lr": 5.363544833020704e-06, "epoch": 5.498732037193576, "percentage": 78.55, "elapsed_time": "2:11:22", "remaining_time": "0:35:52"}
|
||||
{"current_steps": 3260, "total_steps": 4144, "loss": 0.3195, "lr": 5.306260545581414e-06, "epoch": 5.507185122569738, "percentage": 78.67, "elapsed_time": "2:11:34", "remaining_time": "0:35:40"}
|
||||
{"current_steps": 3265, "total_steps": 4144, "loss": 0.3094, "lr": 5.249236985545783e-06, "epoch": 5.5156382079459005, "percentage": 78.79, "elapsed_time": "2:11:46", "remaining_time": "0:35:28"}
|
||||
{"current_steps": 3270, "total_steps": 4144, "loss": 0.3315, "lr": 5.192475164746429e-06, "epoch": 5.524091293322062, "percentage": 78.91, "elapsed_time": "2:11:57", "remaining_time": "0:35:16"}
|
||||
{"current_steps": 3275, "total_steps": 4144, "loss": 0.3259, "lr": 5.135976090371626e-06, "epoch": 5.5325443786982245, "percentage": 79.03, "elapsed_time": "2:12:08", "remaining_time": "0:35:03"}
|
||||
{"current_steps": 3280, "total_steps": 4144, "loss": 0.3243, "lr": 5.079740764947454e-06, "epoch": 5.540997464074387, "percentage": 79.15, "elapsed_time": "2:12:20", "remaining_time": "0:34:51"}
|
||||
{"current_steps": 3285, "total_steps": 4144, "loss": 0.3266, "lr": 5.02377018631999e-06, "epoch": 5.549450549450549, "percentage": 79.27, "elapsed_time": "2:12:33", "remaining_time": "0:34:39"}
|
||||
{"current_steps": 3290, "total_steps": 4144, "loss": 0.3505, "lr": 4.968065347637636e-06, "epoch": 5.557903634826712, "percentage": 79.39, "elapsed_time": "2:12:47", "remaining_time": "0:34:28"}
|
||||
{"current_steps": 3295, "total_steps": 4144, "loss": 0.3222, "lr": 4.912627237333443e-06, "epoch": 5.566356720202874, "percentage": 79.51, "elapsed_time": "2:12:59", "remaining_time": "0:34:15"}
|
||||
{"current_steps": 3300, "total_steps": 4144, "loss": 0.3229, "lr": 4.857456839107633e-06, "epoch": 5.5748098055790365, "percentage": 79.63, "elapsed_time": "2:13:10", "remaining_time": "0:34:03"}
|
||||
{"current_steps": 3305, "total_steps": 4144, "loss": 0.3476, "lr": 4.802555131910096e-06, "epoch": 5.583262890955199, "percentage": 79.75, "elapsed_time": "2:13:21", "remaining_time": "0:33:51"}
|
||||
{"current_steps": 3310, "total_steps": 4144, "loss": 0.3142, "lr": 4.747923089923041e-06, "epoch": 5.591715976331361, "percentage": 79.87, "elapsed_time": "2:13:33", "remaining_time": "0:33:39"}
|
||||
{"current_steps": 3315, "total_steps": 4144, "loss": 0.3493, "lr": 4.693561682543706e-06, "epoch": 5.600169061707524, "percentage": 80.0, "elapsed_time": "2:13:46", "remaining_time": "0:33:27"}
|
||||
{"current_steps": 3320, "total_steps": 4144, "loss": 0.3262, "lr": 4.6394718743671605e-06, "epoch": 5.608622147083685, "percentage": 80.12, "elapsed_time": "2:13:58", "remaining_time": "0:33:14"}
|
||||
{"current_steps": 3325, "total_steps": 4144, "loss": 0.3196, "lr": 4.5856546251691805e-06, "epoch": 5.617075232459848, "percentage": 80.24, "elapsed_time": "2:14:08", "remaining_time": "0:33:02"}
|
||||
{"current_steps": 3330, "total_steps": 4144, "loss": 0.3189, "lr": 4.532110889889243e-06, "epoch": 5.62552831783601, "percentage": 80.36, "elapsed_time": "2:14:20", "remaining_time": "0:32:50"}
|
||||
{"current_steps": 3335, "total_steps": 4144, "loss": 0.3077, "lr": 4.478841618613526e-06, "epoch": 5.6339814032121724, "percentage": 80.48, "elapsed_time": "2:14:32", "remaining_time": "0:32:38"}
|
||||
{"current_steps": 3340, "total_steps": 4144, "loss": 0.3335, "lr": 4.425847756558126e-06, "epoch": 5.642434488588335, "percentage": 80.6, "elapsed_time": "2:14:44", "remaining_time": "0:32:26"}
|
||||
{"current_steps": 3345, "total_steps": 4144, "loss": 0.3361, "lr": 4.3731302440522235e-06, "epoch": 5.650887573964497, "percentage": 80.72, "elapsed_time": "2:14:55", "remaining_time": "0:32:13"}
|
||||
{"current_steps": 3350, "total_steps": 4144, "loss": 0.3191, "lr": 4.320690016521427e-06, "epoch": 5.65934065934066, "percentage": 80.84, "elapsed_time": "2:15:08", "remaining_time": "0:32:01"}
|
||||
{"current_steps": 3355, "total_steps": 4144, "loss": 0.3357, "lr": 4.2685280044711615e-06, "epoch": 5.667793744716821, "percentage": 80.96, "elapsed_time": "2:15:21", "remaining_time": "0:31:49"}
|
||||
{"current_steps": 3360, "total_steps": 4144, "loss": 0.3464, "lr": 4.216645133470188e-06, "epoch": 5.676246830092984, "percentage": 81.08, "elapsed_time": "2:15:32", "remaining_time": "0:31:37"}
|
||||
{"current_steps": 3365, "total_steps": 4144, "loss": 0.3359, "lr": 4.165042324134116e-06, "epoch": 5.684699915469146, "percentage": 81.2, "elapsed_time": "2:15:43", "remaining_time": "0:31:25"}
|
||||
{"current_steps": 3370, "total_steps": 4144, "loss": 0.329, "lr": 4.113720492109152e-06, "epoch": 5.693153000845308, "percentage": 81.32, "elapsed_time": "2:15:54", "remaining_time": "0:31:12"}
|
||||
{"current_steps": 3375, "total_steps": 4144, "loss": 0.3423, "lr": 4.062680548055782e-06, "epoch": 5.701606086221471, "percentage": 81.44, "elapsed_time": "2:16:05", "remaining_time": "0:31:00"}
|
||||
{"current_steps": 3380, "total_steps": 4144, "loss": 0.3256, "lr": 4.011923397632644e-06, "epoch": 5.710059171597633, "percentage": 81.56, "elapsed_time": "2:16:16", "remaining_time": "0:30:48"}
|
||||
{"current_steps": 3385, "total_steps": 4144, "loss": 0.3281, "lr": 3.961449941480455e-06, "epoch": 5.718512256973796, "percentage": 81.68, "elapsed_time": "2:16:29", "remaining_time": "0:30:36"}
|
||||
{"current_steps": 3390, "total_steps": 4144, "loss": 0.3302, "lr": 3.911261075206036e-06, "epoch": 5.726965342349958, "percentage": 81.81, "elapsed_time": "2:16:40", "remaining_time": "0:30:24"}
|
||||
{"current_steps": 3395, "total_steps": 4144, "loss": 0.3231, "lr": 3.8613576893664e-06, "epoch": 5.73541842772612, "percentage": 81.93, "elapsed_time": "2:16:52", "remaining_time": "0:30:11"}
|
||||
{"current_steps": 3400, "total_steps": 4144, "loss": 0.3577, "lr": 3.8117406694529702e-06, "epoch": 5.743871513102282, "percentage": 82.05, "elapsed_time": "2:17:03", "remaining_time": "0:29:59"}
|
||||
{"current_steps": 3405, "total_steps": 4144, "loss": 0.311, "lr": 3.762410895875854e-06, "epoch": 5.752324598478444, "percentage": 82.17, "elapsed_time": "2:17:14", "remaining_time": "0:29:47"}
|
||||
{"current_steps": 3410, "total_steps": 4144, "loss": 0.3248, "lr": 3.713369243948226e-06, "epoch": 5.760777683854607, "percentage": 82.29, "elapsed_time": "2:17:26", "remaining_time": "0:29:35"}
|
||||
{"current_steps": 3415, "total_steps": 4144, "loss": 0.3395, "lr": 3.664616583870819e-06, "epoch": 5.769230769230769, "percentage": 82.41, "elapsed_time": "2:17:38", "remaining_time": "0:29:22"}
|
||||
{"current_steps": 3420, "total_steps": 4144, "loss": 0.348, "lr": 3.6161537807164203e-06, "epoch": 5.777683854606932, "percentage": 82.53, "elapsed_time": "2:17:50", "remaining_time": "0:29:10"}
|
||||
{"current_steps": 3425, "total_steps": 4144, "loss": 0.3296, "lr": 3.5679816944145996e-06, "epoch": 5.786136939983094, "percentage": 82.65, "elapsed_time": "2:18:02", "remaining_time": "0:28:58"}
|
||||
{"current_steps": 3430, "total_steps": 4144, "loss": 0.3382, "lr": 3.520101179736399e-06, "epoch": 5.794590025359256, "percentage": 82.77, "elapsed_time": "2:18:14", "remaining_time": "0:28:46"}
|
||||
{"current_steps": 3435, "total_steps": 4144, "loss": 0.3557, "lr": 3.4725130862791766e-06, "epoch": 5.803043110735419, "percentage": 82.89, "elapsed_time": "2:18:25", "remaining_time": "0:28:34"}
|
||||
{"current_steps": 3440, "total_steps": 4144, "loss": 0.3307, "lr": 3.4252182584515327e-06, "epoch": 5.81149619611158, "percentage": 83.01, "elapsed_time": "2:18:36", "remaining_time": "0:28:22"}
|
||||
{"current_steps": 3445, "total_steps": 4144, "loss": 0.3281, "lr": 3.3782175354583523e-06, "epoch": 5.819949281487743, "percentage": 83.13, "elapsed_time": "2:18:48", "remaining_time": "0:28:09"}
|
||||
{"current_steps": 3450, "total_steps": 4144, "loss": 0.3235, "lr": 3.3315117512858518e-06, "epoch": 5.828402366863905, "percentage": 83.25, "elapsed_time": "2:19:02", "remaining_time": "0:27:58"}
|
||||
{"current_steps": 3455, "total_steps": 4144, "loss": 0.312, "lr": 3.285101734686855e-06, "epoch": 5.8368554522400675, "percentage": 83.37, "elapsed_time": "2:19:13", "remaining_time": "0:27:45"}
|
||||
{"current_steps": 3460, "total_steps": 4144, "loss": 0.329, "lr": 3.2389883091660312e-06, "epoch": 5.84530853761623, "percentage": 83.49, "elapsed_time": "2:19:25", "remaining_time": "0:27:33"}
|
||||
{"current_steps": 3465, "total_steps": 4144, "loss": 0.3224, "lr": 3.1931722929653097e-06, "epoch": 5.853761622992392, "percentage": 83.61, "elapsed_time": "2:19:37", "remaining_time": "0:27:21"}
|
||||
{"current_steps": 3470, "total_steps": 4144, "loss": 0.3268, "lr": 3.147654499049346e-06, "epoch": 5.862214708368555, "percentage": 83.74, "elapsed_time": "2:19:50", "remaining_time": "0:27:09"}
|
||||
{"current_steps": 3475, "total_steps": 4144, "loss": 0.3446, "lr": 3.1024357350911317e-06, "epoch": 5.870667793744717, "percentage": 83.86, "elapsed_time": "2:20:02", "remaining_time": "0:26:57"}
|
||||
{"current_steps": 3480, "total_steps": 4144, "loss": 0.3443, "lr": 3.0575168034575964e-06, "epoch": 5.8791208791208796, "percentage": 83.98, "elapsed_time": "2:20:13", "remaining_time": "0:26:45"}
|
||||
{"current_steps": 3485, "total_steps": 4144, "loss": 0.3043, "lr": 3.012898501195447e-06, "epoch": 5.887573964497041, "percentage": 84.1, "elapsed_time": "2:20:24", "remaining_time": "0:26:33"}
|
||||
{"current_steps": 3490, "total_steps": 4144, "loss": 0.322, "lr": 2.9685816200169683e-06, "epoch": 5.8960270498732035, "percentage": 84.22, "elapsed_time": "2:20:36", "remaining_time": "0:26:20"}
|
||||
{"current_steps": 3495, "total_steps": 4144, "loss": 0.3221, "lr": 2.9245669462859982e-06, "epoch": 5.904480135249366, "percentage": 84.34, "elapsed_time": "2:20:48", "remaining_time": "0:26:08"}
|
||||
{"current_steps": 3500, "total_steps": 4144, "loss": 0.3244, "lr": 2.8808552610039718e-06, "epoch": 5.912933220625528, "percentage": 84.46, "elapsed_time": "2:21:01", "remaining_time": "0:25:56"}
|
||||
{"current_steps": 3505, "total_steps": 4144, "loss": 0.3189, "lr": 2.8374473397960645e-06, "epoch": 5.921386306001691, "percentage": 84.58, "elapsed_time": "2:21:14", "remaining_time": "0:25:44"}
|
||||
{"current_steps": 3510, "total_steps": 4144, "loss": 0.3415, "lr": 2.794343952897418e-06, "epoch": 5.929839391377853, "percentage": 84.7, "elapsed_time": "2:21:26", "remaining_time": "0:25:32"}
|
||||
{"current_steps": 3515, "total_steps": 4144, "loss": 0.345, "lr": 2.751545865139502e-06, "epoch": 5.9382924767540155, "percentage": 84.82, "elapsed_time": "2:21:39", "remaining_time": "0:25:20"}
|
||||
{"current_steps": 3520, "total_steps": 4144, "loss": 0.3214, "lr": 2.7090538359365016e-06, "epoch": 5.946745562130177, "percentage": 84.94, "elapsed_time": "2:21:51", "remaining_time": "0:25:08"}
|
||||
{"current_steps": 3525, "total_steps": 4144, "loss": 0.3159, "lr": 2.6668686192718764e-06, "epoch": 5.955198647506339, "percentage": 85.06, "elapsed_time": "2:22:02", "remaining_time": "0:24:56"}
|
||||
{"current_steps": 3530, "total_steps": 4144, "loss": 0.309, "lr": 2.6249909636849615e-06, "epoch": 5.963651732882502, "percentage": 85.18, "elapsed_time": "2:22:15", "remaining_time": "0:24:44"}
|
||||
{"current_steps": 3535, "total_steps": 4144, "loss": 0.3378, "lr": 2.583421612257695e-06, "epoch": 5.972104818258664, "percentage": 85.3, "elapsed_time": "2:22:27", "remaining_time": "0:24:32"}
|
||||
{"current_steps": 3540, "total_steps": 4144, "loss": 0.3079, "lr": 2.542161302601438e-06, "epoch": 5.980557903634827, "percentage": 85.42, "elapsed_time": "2:22:38", "remaining_time": "0:24:20"}
|
||||
{"current_steps": 3545, "total_steps": 4144, "loss": 0.3215, "lr": 2.501210766843871e-06, "epoch": 5.989010989010989, "percentage": 85.55, "elapsed_time": "2:22:51", "remaining_time": "0:24:08"}
|
||||
{"current_steps": 3550, "total_steps": 4144, "loss": 0.3178, "lr": 2.460570731616012e-06, "epoch": 5.9974640743871515, "percentage": 85.67, "elapsed_time": "2:23:02", "remaining_time": "0:23:56"}
|
||||
{"current_steps": 3555, "total_steps": 4144, "loss": 0.3057, "lr": 2.4202419180393167e-06, "epoch": 6.005071851225697, "percentage": 85.79, "elapsed_time": "2:23:13", "remaining_time": "0:23:43"}
|
||||
{"current_steps": 3560, "total_steps": 4144, "loss": 0.2941, "lr": 2.3802250417129067e-06, "epoch": 6.0135249366018595, "percentage": 85.91, "elapsed_time": "2:23:26", "remaining_time": "0:23:31"}
|
||||
{"current_steps": 3565, "total_steps": 4144, "loss": 0.3009, "lr": 2.340520812700824e-06, "epoch": 6.021978021978022, "percentage": 86.03, "elapsed_time": "2:23:38", "remaining_time": "0:23:19"}
|
||||
{"current_steps": 3570, "total_steps": 4144, "loss": 0.2949, "lr": 2.3011299355194948e-06, "epoch": 6.030431107354184, "percentage": 86.15, "elapsed_time": "2:23:51", "remaining_time": "0:23:07"}
|
||||
{"current_steps": 3575, "total_steps": 4144, "loss": 0.3236, "lr": 2.2620531091251597e-06, "epoch": 6.038884192730347, "percentage": 86.27, "elapsed_time": "2:24:02", "remaining_time": "0:22:55"}
|
||||
{"current_steps": 3580, "total_steps": 4144, "loss": 0.2817, "lr": 2.223291026901533e-06, "epoch": 6.047337278106509, "percentage": 86.39, "elapsed_time": "2:24:13", "remaining_time": "0:22:43"}
|
||||
{"current_steps": 3585, "total_steps": 4144, "loss": 0.2866, "lr": 2.184844376647457e-06, "epoch": 6.0557903634826715, "percentage": 86.51, "elapsed_time": "2:24:24", "remaining_time": "0:22:31"}
|
||||
{"current_steps": 3590, "total_steps": 4144, "loss": 0.3092, "lr": 2.1467138405647227e-06, "epoch": 6.064243448858833, "percentage": 86.63, "elapsed_time": "2:24:36", "remaining_time": "0:22:18"}
|
||||
{"current_steps": 3595, "total_steps": 4144, "loss": 0.3013, "lr": 2.1089000952459427e-06, "epoch": 6.0726965342349954, "percentage": 86.75, "elapsed_time": "2:24:47", "remaining_time": "0:22:06"}
|
||||
{"current_steps": 3600, "total_steps": 4144, "loss": 0.3142, "lr": 2.0714038116625756e-06, "epoch": 6.081149619611158, "percentage": 86.87, "elapsed_time": "2:24:59", "remaining_time": "0:21:54"}
|
||||
{"current_steps": 3605, "total_steps": 4144, "loss": 0.3186, "lr": 2.034225655152979e-06, "epoch": 6.08960270498732, "percentage": 86.99, "elapsed_time": "2:25:10", "remaining_time": "0:21:42"}
|
||||
{"current_steps": 3610, "total_steps": 4144, "loss": 0.2938, "lr": 1.9973662854106514e-06, "epoch": 6.098055790363483, "percentage": 87.11, "elapsed_time": "2:25:23", "remaining_time": "0:21:30"}
|
||||
{"current_steps": 3615, "total_steps": 4144, "loss": 0.2933, "lr": 1.960826356472485e-06, "epoch": 6.106508875739645, "percentage": 87.23, "elapsed_time": "2:25:35", "remaining_time": "0:21:18"}
|
||||
{"current_steps": 3620, "total_steps": 4144, "loss": 0.3021, "lr": 1.9246065167071858e-06, "epoch": 6.1149619611158075, "percentage": 87.36, "elapsed_time": "2:25:47", "remaining_time": "0:21:06"}
|
||||
{"current_steps": 3625, "total_steps": 4144, "loss": 0.2925, "lr": 1.8887074088037517e-06, "epoch": 6.12341504649197, "percentage": 87.48, "elapsed_time": "2:25:59", "remaining_time": "0:20:54"}
|
||||
{"current_steps": 3630, "total_steps": 4144, "loss": 0.2985, "lr": 1.8531296697600965e-06, "epoch": 6.131868131868132, "percentage": 87.6, "elapsed_time": "2:26:10", "remaining_time": "0:20:41"}
|
||||
{"current_steps": 3635, "total_steps": 4144, "loss": 0.3099, "lr": 1.8178739308717075e-06, "epoch": 6.140321217244294, "percentage": 87.72, "elapsed_time": "2:26:22", "remaining_time": "0:20:29"}
|
||||
{"current_steps": 3640, "total_steps": 4144, "loss": 0.2826, "lr": 1.7829408177204732e-06, "epoch": 6.148774302620456, "percentage": 87.84, "elapsed_time": "2:26:34", "remaining_time": "0:20:17"}
|
||||
{"current_steps": 3645, "total_steps": 4144, "loss": 0.3049, "lr": 1.7483309501635725e-06, "epoch": 6.157227387996619, "percentage": 87.96, "elapsed_time": "2:26:46", "remaining_time": "0:20:05"}
|
||||
{"current_steps": 3650, "total_steps": 4144, "loss": 0.3331, "lr": 1.714044942322477e-06, "epoch": 6.165680473372781, "percentage": 88.08, "elapsed_time": "2:26:58", "remaining_time": "0:19:53"}
|
||||
{"current_steps": 3655, "total_steps": 4144, "loss": 0.2971, "lr": 1.6800834025720614e-06, "epoch": 6.174133558748943, "percentage": 88.2, "elapsed_time": "2:27:09", "remaining_time": "0:19:41"}
|
||||
{"current_steps": 3660, "total_steps": 4144, "loss": 0.3046, "lr": 1.6464469335297883e-06, "epoch": 6.182586644125106, "percentage": 88.32, "elapsed_time": "2:27:20", "remaining_time": "0:19:29"}
|
||||
{"current_steps": 3665, "total_steps": 4144, "loss": 0.3091, "lr": 1.613136132045039e-06, "epoch": 6.191039729501268, "percentage": 88.44, "elapsed_time": "2:27:32", "remaining_time": "0:19:16"}
|
||||
{"current_steps": 3670, "total_steps": 4144, "loss": 0.3101, "lr": 1.5801515891885055e-06, "epoch": 6.199492814877431, "percentage": 88.56, "elapsed_time": "2:27:44", "remaining_time": "0:19:04"}
|
||||
{"current_steps": 3675, "total_steps": 4144, "loss": 0.3233, "lr": 1.5474938902417113e-06, "epoch": 6.207945900253592, "percentage": 88.68, "elapsed_time": "2:27:56", "remaining_time": "0:18:52"}
|
||||
{"current_steps": 3680, "total_steps": 4144, "loss": 0.3106, "lr": 1.5151636146866234e-06, "epoch": 6.216398985629755, "percentage": 88.8, "elapsed_time": "2:28:08", "remaining_time": "0:18:40"}
|
||||
{"current_steps": 3685, "total_steps": 4144, "loss": 0.3221, "lr": 1.48316133619538e-06, "epoch": 6.224852071005917, "percentage": 88.92, "elapsed_time": "2:28:20", "remaining_time": "0:18:28"}
|
||||
{"current_steps": 3690, "total_steps": 4144, "loss": 0.296, "lr": 1.4514876226200802e-06, "epoch": 6.233305156382079, "percentage": 89.04, "elapsed_time": "2:28:32", "remaining_time": "0:18:16"}
|
||||
{"current_steps": 3695, "total_steps": 4144, "loss": 0.318, "lr": 1.4201430359827506e-06, "epoch": 6.241758241758242, "percentage": 89.17, "elapsed_time": "2:28:44", "remaining_time": "0:18:04"}
|
||||
{"current_steps": 3700, "total_steps": 4144, "loss": 0.2983, "lr": 1.3891281324653427e-06, "epoch": 6.250211327134404, "percentage": 89.29, "elapsed_time": "2:28:56", "remaining_time": "0:17:52"}
|
||||
{"current_steps": 3705, "total_steps": 4144, "loss": 0.3037, "lr": 1.358443462399872e-06, "epoch": 6.258664412510567, "percentage": 89.41, "elapsed_time": "2:29:07", "remaining_time": "0:17:40"}
|
||||
{"current_steps": 3710, "total_steps": 4144, "loss": 0.3056, "lr": 1.3280895702586505e-06, "epoch": 6.267117497886729, "percentage": 89.53, "elapsed_time": "2:29:19", "remaining_time": "0:17:28"}
|
||||
{"current_steps": 3715, "total_steps": 4144, "loss": 0.3249, "lr": 1.2980669946446444e-06, "epoch": 6.2755705832628905, "percentage": 89.65, "elapsed_time": "2:29:32", "remaining_time": "0:17:16"}
|
||||
{"current_steps": 3720, "total_steps": 4144, "loss": 0.3022, "lr": 1.2683762682818768e-06, "epoch": 6.284023668639053, "percentage": 89.77, "elapsed_time": "2:29:44", "remaining_time": "0:17:04"}
|
||||
{"current_steps": 3725, "total_steps": 4144, "loss": 0.2977, "lr": 1.2390179180060246e-06, "epoch": 6.292476754015215, "percentage": 89.89, "elapsed_time": "2:29:56", "remaining_time": "0:16:51"}
|
||||
{"current_steps": 3730, "total_steps": 4144, "loss": 0.3057, "lr": 1.2099924647550253e-06, "epoch": 6.300929839391378, "percentage": 90.01, "elapsed_time": "2:30:07", "remaining_time": "0:16:39"}
|
||||
{"current_steps": 3735, "total_steps": 4144, "loss": 0.2967, "lr": 1.1813004235598657e-06, "epoch": 6.30938292476754, "percentage": 90.13, "elapsed_time": "2:30:19", "remaining_time": "0:16:27"}
|
||||
{"current_steps": 3740, "total_steps": 4144, "loss": 0.2998, "lr": 1.1529423035354204e-06, "epoch": 6.3178360101437026, "percentage": 90.25, "elapsed_time": "2:30:31", "remaining_time": "0:16:15"}
|
||||
{"current_steps": 3745, "total_steps": 4144, "loss": 0.3204, "lr": 1.1249186078714437e-06, "epoch": 6.326289095519865, "percentage": 90.37, "elapsed_time": "2:30:44", "remaining_time": "0:16:03"}
|
||||
{"current_steps": 3750, "total_steps": 4144, "loss": 0.3058, "lr": 1.0972298338236055e-06, "epoch": 6.334742180896027, "percentage": 90.49, "elapsed_time": "2:30:56", "remaining_time": "0:15:51"}
|
||||
{"current_steps": 3755, "total_steps": 4144, "loss": 0.3258, "lr": 1.069876472704705e-06, "epoch": 6.34319526627219, "percentage": 90.61, "elapsed_time": "2:31:08", "remaining_time": "0:15:39"}
|
||||
{"current_steps": 3760, "total_steps": 4144, "loss": 0.3194, "lr": 1.0428590098759317e-06, "epoch": 6.351648351648351, "percentage": 90.73, "elapsed_time": "2:31:20", "remaining_time": "0:15:27"}
|
||||
{"current_steps": 3765, "total_steps": 4144, "loss": 0.2993, "lr": 1.0161779247382486e-06, "epoch": 6.360101437024514, "percentage": 90.85, "elapsed_time": "2:31:32", "remaining_time": "0:15:15"}
|
||||
{"current_steps": 3770, "total_steps": 4144, "loss": 0.3078, "lr": 9.898336907239047e-07, "epoch": 6.368554522400676, "percentage": 90.97, "elapsed_time": "2:31:43", "remaining_time": "0:15:03"}
|
||||
{"current_steps": 3775, "total_steps": 4144, "loss": 0.2911, "lr": 9.638267752880147e-07, "epoch": 6.3770076077768385, "percentage": 91.1, "elapsed_time": "2:31:55", "remaining_time": "0:14:50"}
|
||||
{"current_steps": 3780, "total_steps": 4144, "loss": 0.2865, "lr": 9.381576399002856e-07, "epoch": 6.385460693153001, "percentage": 91.22, "elapsed_time": "2:32:07", "remaining_time": "0:14:38"}
|
||||
{"current_steps": 3785, "total_steps": 4144, "loss": 0.3197, "lr": 9.128267400368052e-07, "epoch": 6.393913778529163, "percentage": 91.34, "elapsed_time": "2:32:18", "remaining_time": "0:14:26"}
|
||||
{"current_steps": 3790, "total_steps": 4144, "loss": 0.3279, "lr": 8.878345251719777e-07, "epoch": 6.402366863905326, "percentage": 91.46, "elapsed_time": "2:32:28", "remaining_time": "0:14:14"}
|
||||
{"current_steps": 3795, "total_steps": 4144, "loss": 0.3204, "lr": 8.63181438770535e-07, "epoch": 6.410819949281488, "percentage": 91.58, "elapsed_time": "2:32:40", "remaining_time": "0:14:02"}
|
||||
{"current_steps": 3800, "total_steps": 4144, "loss": 0.2972, "lr": 8.388679182796888e-07, "epoch": 6.41927303465765, "percentage": 91.7, "elapsed_time": "2:32:52", "remaining_time": "0:13:50"}
|
||||
{"current_steps": 3805, "total_steps": 4144, "loss": 0.2759, "lr": 8.148943951213306e-07, "epoch": 6.427726120033812, "percentage": 91.82, "elapsed_time": "2:33:03", "remaining_time": "0:13:38"}
|
||||
{"current_steps": 3810, "total_steps": 4144, "loss": 0.3091, "lr": 7.912612946844245e-07, "epoch": 6.4361792054099745, "percentage": 91.94, "elapsed_time": "2:33:14", "remaining_time": "0:13:25"}
|
||||
{"current_steps": 3815, "total_steps": 4144, "loss": 0.3039, "lr": 7.679690363174197e-07, "epoch": 6.444632290786137, "percentage": 92.06, "elapsed_time": "2:33:26", "remaining_time": "0:13:13"}
|
||||
{"current_steps": 3820, "total_steps": 4144, "loss": 0.3014, "lr": 7.450180333208301e-07, "epoch": 6.453085376162299, "percentage": 92.18, "elapsed_time": "2:33:37", "remaining_time": "0:13:01"}
|
||||
{"current_steps": 3825, "total_steps": 4144, "loss": 0.3016, "lr": 7.224086929398932e-07, "epoch": 6.461538461538462, "percentage": 92.3, "elapsed_time": "2:33:49", "remaining_time": "0:12:49"}
|
||||
{"current_steps": 3830, "total_steps": 4144, "loss": 0.3143, "lr": 7.001414163573494e-07, "epoch": 6.469991546914624, "percentage": 92.42, "elapsed_time": "2:34:01", "remaining_time": "0:12:37"}
|
||||
{"current_steps": 3835, "total_steps": 4144, "loss": 0.3053, "lr": 6.782165986863098e-07, "epoch": 6.4784446322907865, "percentage": 92.54, "elapsed_time": "2:34:12", "remaining_time": "0:12:25"}
|
||||
{"current_steps": 3840, "total_steps": 4144, "loss": 0.3167, "lr": 6.566346289632686e-07, "epoch": 6.486897717666949, "percentage": 92.66, "elapsed_time": "2:34:24", "remaining_time": "0:12:13"}
|
||||
{"current_steps": 3845, "total_steps": 4144, "loss": 0.3267, "lr": 6.35395890141175e-07, "epoch": 6.49535080304311, "percentage": 92.78, "elapsed_time": "2:34:35", "remaining_time": "0:12:01"}
|
||||
{"current_steps": 3850, "total_steps": 4144, "loss": 0.3228, "lr": 6.145007590826591e-07, "epoch": 6.503803888419273, "percentage": 92.91, "elapsed_time": "2:34:47", "remaining_time": "0:11:49"}
|
||||
{"current_steps": 3855, "total_steps": 4144, "loss": 0.3056, "lr": 5.939496065533279e-07, "epoch": 6.512256973795435, "percentage": 93.03, "elapsed_time": "2:34:59", "remaining_time": "0:11:37"}
|
||||
{"current_steps": 3860, "total_steps": 4144, "loss": 0.3049, "lr": 5.737427972151999e-07, "epoch": 6.520710059171598, "percentage": 93.15, "elapsed_time": "2:35:11", "remaining_time": "0:11:25"}
|
||||
{"current_steps": 3865, "total_steps": 4144, "loss": 0.3235, "lr": 5.538806896202186e-07, "epoch": 6.52916314454776, "percentage": 93.27, "elapsed_time": "2:35:23", "remaining_time": "0:11:13"}
|
||||
{"current_steps": 3870, "total_steps": 4144, "loss": 0.3304, "lr": 5.34363636203914e-07, "epoch": 6.537616229923922, "percentage": 93.39, "elapsed_time": "2:35:34", "remaining_time": "0:11:00"}
|
||||
{"current_steps": 3875, "total_steps": 4144, "loss": 0.3329, "lr": 5.151919832791219e-07, "epoch": 6.546069315300085, "percentage": 93.51, "elapsed_time": "2:35:47", "remaining_time": "0:10:48"}
|
||||
{"current_steps": 3880, "total_steps": 4144, "loss": 0.3206, "lr": 4.963660710298613e-07, "epoch": 6.554522400676246, "percentage": 93.63, "elapsed_time": "2:35:59", "remaining_time": "0:10:36"}
|
||||
{"current_steps": 3885, "total_steps": 4144, "loss": 0.3, "lr": 4.77886233505287e-07, "epoch": 6.562975486052409, "percentage": 93.75, "elapsed_time": "2:36:11", "remaining_time": "0:10:24"}
|
||||
{"current_steps": 3890, "total_steps": 4144, "loss": 0.318, "lr": 4.5975279861375733e-07, "epoch": 6.571428571428571, "percentage": 93.87, "elapsed_time": "2:36:25", "remaining_time": "0:10:12"}
|
||||
{"current_steps": 3895, "total_steps": 4144, "loss": 0.34, "lr": 4.4196608811702954e-07, "epoch": 6.579881656804734, "percentage": 93.99, "elapsed_time": "2:36:37", "remaining_time": "0:10:00"}
|
||||
{"current_steps": 3900, "total_steps": 4144, "loss": 0.2829, "lr": 4.245264176245445e-07, "epoch": 6.588334742180896, "percentage": 94.11, "elapsed_time": "2:36:49", "remaining_time": "0:09:48"}
|
||||
{"current_steps": 3905, "total_steps": 4144, "loss": 0.3242, "lr": 4.0743409658781765e-07, "epoch": 6.596787827557058, "percentage": 94.23, "elapsed_time": "2:37:01", "remaining_time": "0:09:36"}
|
||||
{"current_steps": 3910, "total_steps": 4144, "loss": 0.2944, "lr": 3.906894282949636e-07, "epoch": 6.605240912933221, "percentage": 94.35, "elapsed_time": "2:37:12", "remaining_time": "0:09:24"}
|
||||
{"current_steps": 3915, "total_steps": 4144, "loss": 0.3204, "lr": 3.7429270986530263e-07, "epoch": 6.613693998309383, "percentage": 94.47, "elapsed_time": "2:37:25", "remaining_time": "0:09:12"}
|
||||
{"current_steps": 3920, "total_steps": 4144, "loss": 0.3083, "lr": 3.5824423224409156e-07, "epoch": 6.622147083685546, "percentage": 94.59, "elapsed_time": "2:37:38", "remaining_time": "0:09:00"}
|
||||
{"current_steps": 3925, "total_steps": 4144, "loss": 0.3185, "lr": 3.4254428019736774e-07, "epoch": 6.630600169061708, "percentage": 94.72, "elapsed_time": "2:37:49", "remaining_time": "0:08:48"}
|
||||
{"current_steps": 3930, "total_steps": 4144, "loss": 0.3179, "lr": 3.2719313230687997e-07, "epoch": 6.6390532544378695, "percentage": 94.84, "elapsed_time": "2:38:01", "remaining_time": "0:08:36"}
|
||||
{"current_steps": 3935, "total_steps": 4144, "loss": 0.3178, "lr": 3.1219106096517014e-07, "epoch": 6.647506339814032, "percentage": 94.96, "elapsed_time": "2:38:13", "remaining_time": "0:08:24"}
|
||||
{"current_steps": 3940, "total_steps": 4144, "loss": 0.3013, "lr": 2.975383323707148e-07, "epoch": 6.655959425190194, "percentage": 95.08, "elapsed_time": "2:38:24", "remaining_time": "0:08:12"}
|
||||
{"current_steps": 3945, "total_steps": 4144, "loss": 0.308, "lr": 2.83235206523218e-07, "epoch": 6.664412510566357, "percentage": 95.2, "elapsed_time": "2:38:35", "remaining_time": "0:07:59"}
|
||||
{"current_steps": 3950, "total_steps": 4144, "loss": 0.3034, "lr": 2.692819372189859e-07, "epoch": 6.672865595942519, "percentage": 95.32, "elapsed_time": "2:38:46", "remaining_time": "0:07:47"}
|
||||
{"current_steps": 3955, "total_steps": 4144, "loss": 0.3082, "lr": 2.5567877204644156e-07, "epoch": 6.681318681318682, "percentage": 95.44, "elapsed_time": "2:38:57", "remaining_time": "0:07:35"}
|
||||
{"current_steps": 3960, "total_steps": 4144, "loss": 0.2955, "lr": 2.4242595238170853e-07, "epoch": 6.689771766694844, "percentage": 95.56, "elapsed_time": "2:39:09", "remaining_time": "0:07:23"}
|
||||
{"current_steps": 3965, "total_steps": 4144, "loss": 0.3168, "lr": 2.295237133843453e-07, "epoch": 6.6982248520710055, "percentage": 95.68, "elapsed_time": "2:39:20", "remaining_time": "0:07:11"}
|
||||
{"current_steps": 3970, "total_steps": 4144, "loss": 0.2962, "lr": 2.1697228399316428e-07, "epoch": 6.706677937447168, "percentage": 95.8, "elapsed_time": "2:39:31", "remaining_time": "0:06:59"}
|
||||
{"current_steps": 3975, "total_steps": 4144, "loss": 0.2798, "lr": 2.0477188692217487e-07, "epoch": 6.71513102282333, "percentage": 95.92, "elapsed_time": "2:39:42", "remaining_time": "0:06:47"}
|
||||
{"current_steps": 3980, "total_steps": 4144, "loss": 0.3194, "lr": 1.929227386566246e-07, "epoch": 6.723584108199493, "percentage": 96.04, "elapsed_time": "2:39:55", "remaining_time": "0:06:35"}
|
||||
{"current_steps": 3985, "total_steps": 4144, "loss": 0.3095, "lr": 1.8142504944916428e-07, "epoch": 6.732037193575655, "percentage": 96.16, "elapsed_time": "2:40:07", "remaining_time": "0:06:23"}
|
||||
{"current_steps": 3990, "total_steps": 4144, "loss": 0.3237, "lr": 1.7027902331611557e-07, "epoch": 6.7404902789518175, "percentage": 96.28, "elapsed_time": "2:40:19", "remaining_time": "0:06:11"}
|
||||
{"current_steps": 3995, "total_steps": 4144, "loss": 0.309, "lr": 1.5948485803384483e-07, "epoch": 6.74894336432798, "percentage": 96.4, "elapsed_time": "2:40:30", "remaining_time": "0:05:59"}
|
||||
{"current_steps": 4000, "total_steps": 4144, "loss": 0.3069, "lr": 1.490427451352683e-07, "epoch": 6.757396449704142, "percentage": 96.53, "elapsed_time": "2:40:42", "remaining_time": "0:05:47"}
|
||||
{"current_steps": 4005, "total_steps": 4144, "loss": 0.2844, "lr": 1.3895286990643686e-07, "epoch": 6.765849535080305, "percentage": 96.65, "elapsed_time": "2:40:55", "remaining_time": "0:05:35"}
|
||||
{"current_steps": 4010, "total_steps": 4144, "loss": 0.2933, "lr": 1.2921541138325445e-07, "epoch": 6.774302620456466, "percentage": 96.77, "elapsed_time": "2:41:07", "remaining_time": "0:05:23"}
|
||||
{"current_steps": 4015, "total_steps": 4144, "loss": 0.2947, "lr": 1.1983054234830925e-07, "epoch": 6.782755705832629, "percentage": 96.89, "elapsed_time": "2:41:18", "remaining_time": "0:05:10"}
|
||||
{"current_steps": 4020, "total_steps": 4144, "loss": 0.2873, "lr": 1.1079842932779417e-07, "epoch": 6.791208791208791, "percentage": 97.01, "elapsed_time": "2:41:30", "remaining_time": "0:04:58"}
|
||||
{"current_steps": 4025, "total_steps": 4144, "loss": 0.3166, "lr": 1.021192325885667e-07, "epoch": 6.7996618765849535, "percentage": 97.13, "elapsed_time": "2:41:42", "remaining_time": "0:04:46"}
|
||||
{"current_steps": 4030, "total_steps": 4144, "loss": 0.2985, "lr": 9.379310613528925e-08, "epoch": 6.808114961961116, "percentage": 97.25, "elapsed_time": "2:41:53", "remaining_time": "0:04:34"}
|
||||
{"current_steps": 4035, "total_steps": 4144, "loss": 0.3307, "lr": 8.582019770770667e-08, "epoch": 6.816568047337278, "percentage": 97.37, "elapsed_time": "2:42:04", "remaining_time": "0:04:22"}
|
||||
{"current_steps": 4040, "total_steps": 4144, "loss": 0.3275, "lr": 7.820064877802624e-08, "epoch": 6.825021132713441, "percentage": 97.49, "elapsed_time": "2:42:15", "remaining_time": "0:04:10"}
|
||||
{"current_steps": 4045, "total_steps": 4144, "loss": 0.316, "lr": 7.093459454839746e-08, "epoch": 6.833474218089603, "percentage": 97.61, "elapsed_time": "2:42:28", "remaining_time": "0:03:58"}
|
||||
{"current_steps": 4050, "total_steps": 4144, "loss": 0.3048, "lr": 6.402216394852723e-08, "epoch": 6.841927303465765, "percentage": 97.73, "elapsed_time": "2:42:40", "remaining_time": "0:03:46"}
|
||||
{"current_steps": 4055, "total_steps": 4144, "loss": 0.3031, "lr": 5.746347963337506e-08, "epoch": 6.850380388841927, "percentage": 97.85, "elapsed_time": "2:42:52", "remaining_time": "0:03:34"}
|
||||
{"current_steps": 4060, "total_steps": 4144, "loss": 0.3238, "lr": 5.125865798099483e-08, "epoch": 6.858833474218089, "percentage": 97.97, "elapsed_time": "2:43:05", "remaining_time": "0:03:22"}
|
||||
{"current_steps": 4065, "total_steps": 4144, "loss": 0.3085, "lr": 4.5407809090449726e-08, "epoch": 6.867286559594252, "percentage": 98.09, "elapsed_time": "2:43:18", "remaining_time": "0:03:10"}
|
||||
{"current_steps": 4070, "total_steps": 4144, "loss": 0.316, "lr": 3.991103677988273e-08, "epoch": 6.875739644970414, "percentage": 98.21, "elapsed_time": "2:43:30", "remaining_time": "0:02:58"}
|
||||
{"current_steps": 4075, "total_steps": 4144, "loss": 0.3049, "lr": 3.476843858464918e-08, "epoch": 6.884192730346577, "percentage": 98.33, "elapsed_time": "2:43:42", "remaining_time": "0:02:46"}
|
||||
{"current_steps": 4080, "total_steps": 4144, "loss": 0.2902, "lr": 2.998010575560484e-08, "epoch": 6.892645815722739, "percentage": 98.46, "elapsed_time": "2:43:54", "remaining_time": "0:02:34"}
|
||||
{"current_steps": 4085, "total_steps": 4144, "loss": 0.2744, "lr": 2.5546123257478295e-08, "epoch": 6.9010989010989015, "percentage": 98.58, "elapsed_time": "2:44:06", "remaining_time": "0:02:22"}
|
||||
{"current_steps": 4090, "total_steps": 4144, "loss": 0.3208, "lr": 2.1466569767365496e-08, "epoch": 6.909551986475064, "percentage": 98.7, "elapsed_time": "2:44:17", "remaining_time": "0:02:10"}
|
||||
{"current_steps": 4095, "total_steps": 4144, "loss": 0.3263, "lr": 1.7741517673333098e-08, "epoch": 6.918005071851225, "percentage": 98.82, "elapsed_time": "2:44:28", "remaining_time": "0:01:58"}
|
||||
{"current_steps": 4100, "total_steps": 4144, "loss": 0.3094, "lr": 1.4371033073132812e-08, "epoch": 6.926458157227388, "percentage": 98.94, "elapsed_time": "2:44:41", "remaining_time": "0:01:46"}
|
||||
{"current_steps": 4105, "total_steps": 4144, "loss": 0.3125, "lr": 1.1355175773033467e-08, "epoch": 6.93491124260355, "percentage": 99.06, "elapsed_time": "2:44:53", "remaining_time": "0:01:33"}
|
||||
{"current_steps": 4110, "total_steps": 4144, "loss": 0.3001, "lr": 8.693999286752964e-09, "epoch": 6.943364327979713, "percentage": 99.18, "elapsed_time": "2:45:04", "remaining_time": "0:01:21"}
|
||||
{"current_steps": 4115, "total_steps": 4144, "loss": 0.31, "lr": 6.387550834512368e-09, "epoch": 6.951817413355875, "percentage": 99.3, "elapsed_time": "2:45:16", "remaining_time": "0:01:09"}
|
||||
{"current_steps": 4120, "total_steps": 4144, "loss": 0.2957, "lr": 4.435871342196585e-09, "epoch": 6.960270498732037, "percentage": 99.42, "elapsed_time": "2:45:27", "remaining_time": "0:00:57"}
|
||||
{"current_steps": 4125, "total_steps": 4144, "loss": 0.2918, "lr": 2.838995440637149e-09, "epoch": 6.9687235841082, "percentage": 99.54, "elapsed_time": "2:45:41", "remaining_time": "0:00:45"}
|
||||
{"current_steps": 4130, "total_steps": 4144, "loss": 0.3058, "lr": 1.5969514649771812e-09, "epoch": 6.977176669484361, "percentage": 99.66, "elapsed_time": "2:45:53", "remaining_time": "0:00:33"}
|
||||
{"current_steps": 4135, "total_steps": 4144, "loss": 0.3055, "lr": 7.097614541917708e-10, "epoch": 6.985629754860524, "percentage": 99.78, "elapsed_time": "2:46:05", "remaining_time": "0:00:21"}
|
||||
{"current_steps": 4140, "total_steps": 4144, "loss": 0.3111, "lr": 1.7744115068163424e-10, "epoch": 6.994082840236686, "percentage": 99.9, "elapsed_time": "2:46:16", "remaining_time": "0:00:09"}
|
||||
{"current_steps": 4144, "total_steps": 4144, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "2:47:03", "remaining_time": "0:00:00"}
|
||||
9155
trainer_state.json
Normal file
9155
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 sha256:845931ec6c1d1108766ee64a4dbdf4a5a879b06c1c20c3824a89753cb92e7152
|
||||
size 8657
|
||||
BIN
training_loss.png
Normal file
BIN
training_loss.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 40 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