初始化项目，由ModelHub XC社区提供模型
Model: laion/nemotron-terminal-security__Qwen3-8B Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -0,0 +1,36 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
61
README.md
Normal file
61
README.md
Normal file
@@ -0,0 +1,61 @@
|
||||
---
|
||||
library_name: transformers
|
||||
license: other
|
||||
base_model: Qwen/Qwen3-8B
|
||||
tags:
|
||||
- llama-factory
|
||||
- full
|
||||
- generated_from_trainer
|
||||
model-index:
|
||||
- name: nemotron-security__Qwen3-8B
|
||||
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. -->
|
||||
|
||||
# nemotron-security__Qwen3-8B
|
||||
|
||||
This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on the /e/data1/datasets/playground/ot/hf_hub/datasets--laion--nemotron-terminal-security/snapshots/8197195aee4bbc8978dde76cfe00adba811bc764_thinking_preprocessed dataset.
|
||||
|
||||
## Model description
|
||||
|
||||
More information needed
|
||||
|
||||
## Intended uses & limitations
|
||||
|
||||
More information needed
|
||||
|
||||
## Training and evaluation data
|
||||
|
||||
More information needed
|
||||
|
||||
## Training procedure
|
||||
|
||||
### Training hyperparameters
|
||||
|
||||
The following hyperparameters were used during training:
|
||||
- learning_rate: 4e-05
|
||||
- train_batch_size: 1
|
||||
- eval_batch_size: 8
|
||||
- seed: 42
|
||||
- distributed_type: multi-GPU
|
||||
- num_devices: 32
|
||||
- gradient_accumulation_steps: 3
|
||||
- total_train_batch_size: 96
|
||||
- total_eval_batch_size: 256
|
||||
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.98) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
||||
- lr_scheduler_type: cosine
|
||||
- lr_scheduler_warmup_ratio: 0.1
|
||||
- num_epochs: 7.0
|
||||
|
||||
### Training results
|
||||
|
||||
|
||||
|
||||
### Framework versions
|
||||
|
||||
- Transformers 4.57.6
|
||||
- Pytorch 2.9.1+cu130
|
||||
- Datasets 4.7.0
|
||||
- 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": 137488.10509998802,
|
||||
"achieved_tflops_per_gpu_theoretical": 3652289.8590967623,
|
||||
"epoch": 7.0,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.38367757201194763,
|
||||
"mfu_percent": 9716.473858656398,
|
||||
"mfu_percent_theoretical": 258112.3575333401,
|
||||
"total_flos": 5.085080059986117e+18,
|
||||
"train_loss": 0.0,
|
||||
"train_runtime": 1.1558,
|
||||
"train_samples_per_second": 103019.289,
|
||||
"train_steps_per_second": 1078.038,
|
||||
"valid_targets_mean": 8619.6,
|
||||
"valid_targets_min": 321
|
||||
}
|
||||
89
chat_template.jinja
Normal file
89
chat_template.jinja
Normal file
@@ -0,0 +1,89 @@
|
||||
{%- if tools %}
|
||||
{{- '<|im_start|>system\n' }}
|
||||
{%- if messages[0].role == 'system' %}
|
||||
{{- messages[0].content + '\n\n' }}
|
||||
{%- endif %}
|
||||
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
||||
{%- for tool in tools %}
|
||||
{{- "\n" }}
|
||||
{{- tool | tojson }}
|
||||
{%- endfor %}
|
||||
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
||||
{%- else %}
|
||||
{%- if messages[0].role == 'system' %}
|
||||
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
||||
{%- for message in messages[::-1] %}
|
||||
{%- set index = (messages|length - 1) - loop.index0 %}
|
||||
{%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
||||
{%- set ns.multi_step_tool = false %}
|
||||
{%- set ns.last_query_index = index %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- for message in messages %}
|
||||
{%- if message.content is string %}
|
||||
{%- set content = message.content %}
|
||||
{%- else %}
|
||||
{%- set content = '' %}
|
||||
{%- endif %}
|
||||
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
||||
{%- elif message.role == "assistant" %}
|
||||
{%- set reasoning_content = '' %}
|
||||
{%- if message.reasoning_content is string %}
|
||||
{%- set reasoning_content = message.reasoning_content %}
|
||||
{%- else %}
|
||||
{%- if '</think>' in content %}
|
||||
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
||||
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- if loop.index0 > ns.last_query_index %}
|
||||
{%- if loop.last or (not loop.last and reasoning_content) %}
|
||||
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||
{%- endif %}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||
{%- endif %}
|
||||
{%- if message.tool_calls %}
|
||||
{%- for tool_call in message.tool_calls %}
|
||||
{%- if (loop.first and content) or (not loop.first) %}
|
||||
{{- '\n' }}
|
||||
{%- endif %}
|
||||
{%- if tool_call.function %}
|
||||
{%- set tool_call = tool_call.function %}
|
||||
{%- endif %}
|
||||
{{- '<tool_call>\n{"name": "' }}
|
||||
{{- tool_call.name }}
|
||||
{{- '", "arguments": ' }}
|
||||
{%- if tool_call.arguments is string %}
|
||||
{{- tool_call.arguments }}
|
||||
{%- else %}
|
||||
{{- tool_call.arguments | tojson }}
|
||||
{%- endif %}
|
||||
{{- '}\n</tool_call>' }}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- elif message.role == "tool" %}
|
||||
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
||||
{{- '<|im_start|>user' }}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_response>\n' }}
|
||||
{{- content }}
|
||||
{{- '\n</tool_response>' }}
|
||||
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- if add_generation_prompt %}
|
||||
{{- '<|im_start|>assistant\n' }}
|
||||
{%- if enable_thinking is defined and enable_thinking is false %}
|
||||
{{- '<think>\n\n</think>\n\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
68
config.json
Normal file
68
config.json
Normal file
@@ -0,0 +1,68 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen3ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 151645,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 12288,
|
||||
"layer_types": [
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention"
|
||||
],
|
||||
"max_position_embeddings": 40960,
|
||||
"max_window_layers": 36,
|
||||
"model_type": "qwen3",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 36,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 151643,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 1000000,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "4.57.6",
|
||||
"use_cache": false,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
12
generation_config.json
Normal file
12
generation_config.json
Normal file
@@ -0,0 +1,12 @@
|
||||
{
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"pad_token_id": 151643,
|
||||
"temperature": 0.6,
|
||||
"top_k": 20,
|
||||
"top_p": 0.95,
|
||||
"transformers_version": "4.57.6"
|
||||
}
|
||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model-00001-of-00004.safetensors
Normal file
3
model-00001-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:67b68b7e542c87c87924a4df64d6c1c6d45b85b9166ce6bb04abd85edd5a9117
|
||||
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 sha256:86a23a04650e019aea6098575f3da217f69748f2526962452aa1b99157db1b3d
|
||||
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:e85a12555f5841cd058f89ae941cfffaa22f65ecdc6cc7a2257c114cee55e699
|
||||
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 sha256:1a6336371cfa5e232c77cb368e7514fad1968030404e0dfc6d80b042ad86c69d
|
||||
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": "8197195aee4bbc8978dde76cfe00adba811bc764_thinking_preprocessed",
|
||||
"training_start": null,
|
||||
"training_end": null,
|
||||
"created_by": "DCAgent",
|
||||
"base_model_name": "Qwen/Qwen3-8B",
|
||||
"dataset_name": "/e/data1/datasets/playground/ot/hf_hub/datasets--laion--nemotron-terminal-security/snapshots/8197195aee4bbc8978dde76cfe00adba811bc764_thinking_preprocessed",
|
||||
"training_type": "SFT",
|
||||
"training_parameters": "https://huggingface.co/laion/nemotron-terminal-security__Qwen3-8B/blob/main/config.json",
|
||||
"wandb_link": null,
|
||||
"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
|
||||
}
|
||||
12
train_results.json
Normal file
12
train_results.json
Normal file
@@ -0,0 +1,12 @@
|
||||
{
|
||||
"achieved_tflops_per_gpu": 137488.10509998802,
|
||||
"achieved_tflops_per_gpu_theoretical": 3652289.8590967623,
|
||||
"epoch": 7.0,
|
||||
"mfu_percent": 9716.473858656398,
|
||||
"mfu_percent_theoretical": 258112.3575333401,
|
||||
"total_flos": 5.085080059986117e+18,
|
||||
"train_loss": 0.0,
|
||||
"train_runtime": 1.1558,
|
||||
"train_samples_per_second": 103019.289,
|
||||
"train_steps_per_second": 1078.038
|
||||
}
|
||||
255
trainer_log.jsonl
Normal file
255
trainer_log.jsonl
Normal file
@@ -0,0 +1,255 @@
|
||||
{"current_steps": 5, "total_steps": 1246, "loss": 0.9036, "lr": 1.28e-06, "epoch": 0.02819548872180451, "percentage": 0.4, "elapsed_time": "0:02:09", "remaining_time": "8:53:38"}
|
||||
{"current_steps": 10, "total_steps": 1246, "loss": 0.8814, "lr": 2.88e-06, "epoch": 0.05639097744360902, "percentage": 0.8, "elapsed_time": "0:04:14", "remaining_time": "8:44:35"}
|
||||
{"current_steps": 15, "total_steps": 1246, "loss": 0.8293, "lr": 4.48e-06, "epoch": 0.08458646616541353, "percentage": 1.2, "elapsed_time": "0:06:19", "remaining_time": "8:38:24"}
|
||||
{"current_steps": 20, "total_steps": 1246, "loss": 0.7689, "lr": 6.08e-06, "epoch": 0.11278195488721804, "percentage": 1.61, "elapsed_time": "0:08:21", "remaining_time": "8:32:26"}
|
||||
{"current_steps": 25, "total_steps": 1246, "loss": 0.7462, "lr": 7.680000000000001e-06, "epoch": 0.14097744360902256, "percentage": 2.01, "elapsed_time": "0:10:33", "remaining_time": "8:35:52"}
|
||||
{"current_steps": 30, "total_steps": 1246, "loss": 0.7089, "lr": 9.280000000000001e-06, "epoch": 0.16917293233082706, "percentage": 2.41, "elapsed_time": "0:12:30", "remaining_time": "8:27:11"}
|
||||
{"current_steps": 35, "total_steps": 1246, "loss": 0.678, "lr": 1.0880000000000001e-05, "epoch": 0.19736842105263158, "percentage": 2.81, "elapsed_time": "0:14:37", "remaining_time": "8:26:09"}
|
||||
{"current_steps": 40, "total_steps": 1246, "loss": 0.6568, "lr": 1.248e-05, "epoch": 0.22556390977443608, "percentage": 3.21, "elapsed_time": "0:16:41", "remaining_time": "8:23:23"}
|
||||
{"current_steps": 45, "total_steps": 1246, "loss": 0.6408, "lr": 1.408e-05, "epoch": 0.25375939849624063, "percentage": 3.61, "elapsed_time": "0:18:51", "remaining_time": "8:23:05"}
|
||||
{"current_steps": 50, "total_steps": 1246, "loss": 0.6238, "lr": 1.5680000000000002e-05, "epoch": 0.2819548872180451, "percentage": 4.01, "elapsed_time": "0:20:47", "remaining_time": "8:17:12"}
|
||||
{"current_steps": 55, "total_steps": 1246, "loss": 0.6053, "lr": 1.728e-05, "epoch": 0.3101503759398496, "percentage": 4.41, "elapsed_time": "0:22:47", "remaining_time": "8:13:26"}
|
||||
{"current_steps": 60, "total_steps": 1246, "loss": 0.5907, "lr": 1.8880000000000002e-05, "epoch": 0.3383458646616541, "percentage": 4.82, "elapsed_time": "0:24:53", "remaining_time": "8:11:57"}
|
||||
{"current_steps": 65, "total_steps": 1246, "loss": 0.5641, "lr": 2.048e-05, "epoch": 0.36654135338345867, "percentage": 5.22, "elapsed_time": "0:26:57", "remaining_time": "8:09:43"}
|
||||
{"current_steps": 70, "total_steps": 1246, "loss": 0.5576, "lr": 2.2080000000000002e-05, "epoch": 0.39473684210526316, "percentage": 5.62, "elapsed_time": "0:28:54", "remaining_time": "8:05:31"}
|
||||
{"current_steps": 75, "total_steps": 1246, "loss": 0.5446, "lr": 2.368e-05, "epoch": 0.42293233082706766, "percentage": 6.02, "elapsed_time": "0:30:59", "remaining_time": "8:03:51"}
|
||||
{"current_steps": 80, "total_steps": 1246, "loss": 0.5433, "lr": 2.5280000000000002e-05, "epoch": 0.45112781954887216, "percentage": 6.42, "elapsed_time": "0:33:03", "remaining_time": "8:01:51"}
|
||||
{"current_steps": 85, "total_steps": 1246, "loss": 0.5308, "lr": 2.6880000000000004e-05, "epoch": 0.4793233082706767, "percentage": 6.82, "elapsed_time": "0:35:05", "remaining_time": "7:59:20"}
|
||||
{"current_steps": 90, "total_steps": 1246, "loss": 0.5262, "lr": 2.8480000000000002e-05, "epoch": 0.5075187969924813, "percentage": 7.22, "elapsed_time": "0:37:05", "remaining_time": "7:56:19"}
|
||||
{"current_steps": 95, "total_steps": 1246, "loss": 0.5173, "lr": 3.0080000000000003e-05, "epoch": 0.5357142857142857, "percentage": 7.62, "elapsed_time": "0:39:05", "remaining_time": "7:53:43"}
|
||||
{"current_steps": 100, "total_steps": 1246, "loss": 0.5054, "lr": 3.168e-05, "epoch": 0.5639097744360902, "percentage": 8.03, "elapsed_time": "0:41:08", "remaining_time": "7:51:30"}
|
||||
{"current_steps": 105, "total_steps": 1246, "loss": 0.4985, "lr": 3.328e-05, "epoch": 0.5921052631578947, "percentage": 8.43, "elapsed_time": "0:43:17", "remaining_time": "7:50:28"}
|
||||
{"current_steps": 110, "total_steps": 1246, "loss": 0.4935, "lr": 3.4880000000000005e-05, "epoch": 0.6203007518796992, "percentage": 8.83, "elapsed_time": "0:45:09", "remaining_time": "7:46:23"}
|
||||
{"current_steps": 115, "total_steps": 1246, "loss": 0.4863, "lr": 3.648e-05, "epoch": 0.6484962406015038, "percentage": 9.23, "elapsed_time": "0:47:09", "remaining_time": "7:43:43"}
|
||||
{"current_steps": 120, "total_steps": 1246, "loss": 0.4853, "lr": 3.808e-05, "epoch": 0.6766917293233082, "percentage": 9.63, "elapsed_time": "0:49:15", "remaining_time": "7:42:15"}
|
||||
{"current_steps": 125, "total_steps": 1246, "loss": 0.4774, "lr": 3.9680000000000006e-05, "epoch": 0.7048872180451128, "percentage": 10.03, "elapsed_time": "0:56:58", "remaining_time": "8:30:59"}
|
||||
{"current_steps": 130, "total_steps": 1246, "loss": 0.4779, "lr": 3.9998743380036454e-05, "epoch": 0.7330827067669173, "percentage": 10.43, "elapsed_time": "0:59:01", "remaining_time": "8:26:45"}
|
||||
{"current_steps": 135, "total_steps": 1246, "loss": 0.4714, "lr": 3.999363863206902e-05, "epoch": 0.7612781954887218, "percentage": 10.83, "elapsed_time": "1:01:05", "remaining_time": "8:22:42"}
|
||||
{"current_steps": 140, "total_steps": 1246, "loss": 0.4789, "lr": 3.9984608218874315e-05, "epoch": 0.7894736842105263, "percentage": 11.24, "elapsed_time": "1:03:02", "remaining_time": "8:17:57"}
|
||||
{"current_steps": 145, "total_steps": 1246, "loss": 0.468, "lr": 3.997165391353524e-05, "epoch": 0.8176691729323309, "percentage": 11.64, "elapsed_time": "1:05:05", "remaining_time": "8:14:15"}
|
||||
{"current_steps": 150, "total_steps": 1246, "loss": 0.4555, "lr": 3.995477825957412e-05, "epoch": 0.8458646616541353, "percentage": 12.04, "elapsed_time": "1:07:07", "remaining_time": "8:10:29"}
|
||||
{"current_steps": 155, "total_steps": 1246, "loss": 0.4551, "lr": 3.9933984570453255e-05, "epoch": 0.8740601503759399, "percentage": 12.44, "elapsed_time": "1:09:14", "remaining_time": "8:07:19"}
|
||||
{"current_steps": 160, "total_steps": 1246, "loss": 0.4576, "lr": 3.990927692892435e-05, "epoch": 0.9022556390977443, "percentage": 12.84, "elapsed_time": "1:11:20", "remaining_time": "8:04:16"}
|
||||
{"current_steps": 165, "total_steps": 1246, "loss": 0.4587, "lr": 3.9880660186226905e-05, "epoch": 0.9304511278195489, "percentage": 13.24, "elapsed_time": "1:13:25", "remaining_time": "8:00:59"}
|
||||
{"current_steps": 170, "total_steps": 1246, "loss": 0.4559, "lr": 3.9848139961135647e-05, "epoch": 0.9586466165413534, "percentage": 13.64, "elapsed_time": "1:15:21", "remaining_time": "7:56:55"}
|
||||
{"current_steps": 175, "total_steps": 1246, "loss": 0.4576, "lr": 3.981172263885736e-05, "epoch": 0.9868421052631579, "percentage": 14.04, "elapsed_time": "1:17:18", "remaining_time": "7:53:07"}
|
||||
{"current_steps": 180, "total_steps": 1246, "loss": 0.4489, "lr": 3.977141536977713e-05, "epoch": 1.0112781954887218, "percentage": 14.45, "elapsed_time": "1:19:04", "remaining_time": "7:48:19"}
|
||||
{"current_steps": 185, "total_steps": 1246, "loss": 0.4386, "lr": 3.972722606805445e-05, "epoch": 1.0394736842105263, "percentage": 14.85, "elapsed_time": "1:21:11", "remaining_time": "7:45:36"}
|
||||
{"current_steps": 190, "total_steps": 1246, "loss": 0.4524, "lr": 3.967916341006925e-05, "epoch": 1.0676691729323309, "percentage": 15.25, "elapsed_time": "1:23:13", "remaining_time": "7:42:34"}
|
||||
{"current_steps": 195, "total_steps": 1246, "loss": 0.4476, "lr": 3.962723683271837e-05, "epoch": 1.0958646616541354, "percentage": 15.65, "elapsed_time": "1:25:17", "remaining_time": "7:39:39"}
|
||||
{"current_steps": 200, "total_steps": 1246, "loss": 0.4506, "lr": 3.957145653156265e-05, "epoch": 1.1240601503759398, "percentage": 16.05, "elapsed_time": "1:27:22", "remaining_time": "7:36:56"}
|
||||
{"current_steps": 205, "total_steps": 1246, "loss": 0.4416, "lr": 3.9511833458825076e-05, "epoch": 1.1522556390977443, "percentage": 16.45, "elapsed_time": "1:29:19", "remaining_time": "7:33:37"}
|
||||
{"current_steps": 210, "total_steps": 1246, "loss": 0.4442, "lr": 3.944837932124036e-05, "epoch": 1.1804511278195489, "percentage": 16.85, "elapsed_time": "1:31:13", "remaining_time": "7:30:02"}
|
||||
{"current_steps": 215, "total_steps": 1246, "loss": 0.4487, "lr": 3.9381106577756374e-05, "epoch": 1.2086466165413534, "percentage": 17.26, "elapsed_time": "1:33:08", "remaining_time": "7:26:38"}
|
||||
{"current_steps": 220, "total_steps": 1246, "loss": 0.4455, "lr": 3.931002843708788e-05, "epoch": 1.236842105263158, "percentage": 17.66, "elapsed_time": "1:35:10", "remaining_time": "7:23:53"}
|
||||
{"current_steps": 225, "total_steps": 1246, "loss": 0.4401, "lr": 3.923515885512307e-05, "epoch": 1.2650375939849625, "percentage": 18.06, "elapsed_time": "1:37:18", "remaining_time": "7:21:35"}
|
||||
{"current_steps": 230, "total_steps": 1246, "loss": 0.4401, "lr": 3.9156512532183384e-05, "epoch": 1.2932330827067668, "percentage": 18.46, "elapsed_time": "1:39:22", "remaining_time": "7:18:58"}
|
||||
{"current_steps": 235, "total_steps": 1246, "loss": 0.4364, "lr": 3.907410491013714e-05, "epoch": 1.3214285714285714, "percentage": 18.86, "elapsed_time": "1:41:17", "remaining_time": "7:15:47"}
|
||||
{"current_steps": 240, "total_steps": 1246, "loss": 0.436, "lr": 3.898795216936763e-05, "epoch": 1.349624060150376, "percentage": 19.26, "elapsed_time": "1:43:16", "remaining_time": "7:12:54"}
|
||||
{"current_steps": 245, "total_steps": 1246, "loss": 0.4335, "lr": 3.889807122559614e-05, "epoch": 1.3778195488721805, "percentage": 19.66, "elapsed_time": "1:45:22", "remaining_time": "7:10:32"}
|
||||
{"current_steps": 250, "total_steps": 1246, "loss": 0.4383, "lr": 3.8804479726560644e-05, "epoch": 1.4060150375939848, "percentage": 20.06, "elapsed_time": "1:47:29", "remaining_time": "7:08:16"}
|
||||
{"current_steps": 255, "total_steps": 1246, "loss": 0.4279, "lr": 3.870719604855071e-05, "epoch": 1.4342105263157894, "percentage": 20.47, "elapsed_time": "1:49:33", "remaining_time": "7:05:46"}
|
||||
{"current_steps": 260, "total_steps": 1246, "loss": 0.4301, "lr": 3.860623929279946e-05, "epoch": 1.462406015037594, "percentage": 20.87, "elapsed_time": "1:51:34", "remaining_time": "7:03:06"}
|
||||
{"current_steps": 265, "total_steps": 1246, "loss": 0.4407, "lr": 3.850162928173303e-05, "epoch": 1.4906015037593985, "percentage": 21.27, "elapsed_time": "1:53:36", "remaining_time": "7:00:33"}
|
||||
{"current_steps": 270, "total_steps": 1246, "loss": 0.4342, "lr": 3.839338655507861e-05, "epoch": 1.518796992481203, "percentage": 21.67, "elapsed_time": "1:55:41", "remaining_time": "6:58:11"}
|
||||
{"current_steps": 275, "total_steps": 1246, "loss": 0.4401, "lr": 3.828153236583152e-05, "epoch": 1.5469924812030076, "percentage": 22.07, "elapsed_time": "1:57:44", "remaining_time": "6:55:43"}
|
||||
{"current_steps": 280, "total_steps": 1246, "loss": 0.4293, "lr": 3.816608867608227e-05, "epoch": 1.5751879699248121, "percentage": 22.47, "elapsed_time": "1:59:46", "remaining_time": "6:53:14"}
|
||||
{"current_steps": 285, "total_steps": 1246, "loss": 0.4347, "lr": 3.80470781527044e-05, "epoch": 1.6033834586466167, "percentage": 22.87, "elapsed_time": "2:01:45", "remaining_time": "6:50:33"}
|
||||
{"current_steps": 290, "total_steps": 1246, "loss": 0.4354, "lr": 3.792452416290393e-05, "epoch": 1.631578947368421, "percentage": 23.27, "elapsed_time": "2:03:49", "remaining_time": "6:48:12"}
|
||||
{"current_steps": 295, "total_steps": 1246, "loss": 0.4319, "lr": 3.779845076963136e-05, "epoch": 1.6597744360902256, "percentage": 23.68, "elapsed_time": "2:05:49", "remaining_time": "6:45:39"}
|
||||
{"current_steps": 300, "total_steps": 1246, "loss": 0.4255, "lr": 3.766888272685693e-05, "epoch": 1.6879699248120301, "percentage": 24.08, "elapsed_time": "2:07:47", "remaining_time": "6:42:58"}
|
||||
{"current_steps": 305, "total_steps": 1246, "loss": 0.4271, "lr": 3.753584547471036e-05, "epoch": 1.7161654135338344, "percentage": 24.48, "elapsed_time": "2:09:57", "remaining_time": "6:40:56"}
|
||||
{"current_steps": 310, "total_steps": 1246, "loss": 0.4202, "lr": 3.739936513448573e-05, "epoch": 1.744360902255639, "percentage": 24.88, "elapsed_time": "2:12:01", "remaining_time": "6:38:38"}
|
||||
{"current_steps": 315, "total_steps": 1246, "loss": 0.4274, "lr": 3.725946850351272e-05, "epoch": 1.7725563909774436, "percentage": 25.28, "elapsed_time": "2:13:52", "remaining_time": "6:35:41"}
|
||||
{"current_steps": 320, "total_steps": 1246, "loss": 0.4233, "lr": 3.7116183049895054e-05, "epoch": 1.800751879699248, "percentage": 25.68, "elapsed_time": "2:15:47", "remaining_time": "6:32:56"}
|
||||
{"current_steps": 325, "total_steps": 1246, "loss": 0.4139, "lr": 3.6969536907117234e-05, "epoch": 1.8289473684210527, "percentage": 26.08, "elapsed_time": "2:17:45", "remaining_time": "6:30:24"}
|
||||
{"current_steps": 330, "total_steps": 1246, "loss": 0.4206, "lr": 3.681955886852069e-05, "epoch": 1.8571428571428572, "percentage": 26.48, "elapsed_time": "2:19:41", "remaining_time": "6:27:44"}
|
||||
{"current_steps": 335, "total_steps": 1246, "loss": 0.4206, "lr": 3.66662783816503e-05, "epoch": 1.8853383458646618, "percentage": 26.89, "elapsed_time": "2:21:37", "remaining_time": "6:25:08"}
|
||||
{"current_steps": 340, "total_steps": 1246, "loss": 0.4211, "lr": 3.6509725542472516e-05, "epoch": 1.9135338345864663, "percentage": 27.29, "elapsed_time": "2:23:31", "remaining_time": "6:22:27"}
|
||||
{"current_steps": 345, "total_steps": 1246, "loss": 0.4154, "lr": 3.6349931089466114e-05, "epoch": 1.9417293233082706, "percentage": 27.69, "elapsed_time": "2:25:22", "remaining_time": "6:19:40"}
|
||||
{"current_steps": 350, "total_steps": 1246, "loss": 0.4224, "lr": 3.6186926397586866e-05, "epoch": 1.9699248120300752, "percentage": 28.09, "elapsed_time": "2:27:26", "remaining_time": "6:17:26"}
|
||||
{"current_steps": 355, "total_steps": 1246, "loss": 0.4214, "lr": 3.602074347210717e-05, "epoch": 1.9981203007518797, "percentage": 28.49, "elapsed_time": "2:29:36", "remaining_time": "6:15:29"}
|
||||
{"current_steps": 360, "total_steps": 1246, "loss": 0.4123, "lr": 3.5851414942331986e-05, "epoch": 2.0225563909774436, "percentage": 28.89, "elapsed_time": "2:31:22", "remaining_time": "6:12:32"}
|
||||
{"current_steps": 365, "total_steps": 1246, "loss": 0.4121, "lr": 3.5678974055192176e-05, "epoch": 2.050751879699248, "percentage": 29.29, "elapsed_time": "2:33:26", "remaining_time": "6:10:21"}
|
||||
{"current_steps": 370, "total_steps": 1246, "loss": 0.4133, "lr": 3.550345466871662e-05, "epoch": 2.0789473684210527, "percentage": 29.7, "elapsed_time": "2:35:19", "remaining_time": "6:07:45"}
|
||||
{"current_steps": 375, "total_steps": 1246, "loss": 0.4109, "lr": 3.5324891245384354e-05, "epoch": 2.107142857142857, "percentage": 30.1, "elapsed_time": "2:37:17", "remaining_time": "6:05:19"}
|
||||
{"current_steps": 380, "total_steps": 1246, "loss": 0.4197, "lr": 3.5143318845358006e-05, "epoch": 2.1353383458646618, "percentage": 30.5, "elapsed_time": "2:39:05", "remaining_time": "6:02:34"}
|
||||
{"current_steps": 385, "total_steps": 1246, "loss": 0.4108, "lr": 3.4958773119599874e-05, "epoch": 2.1635338345864663, "percentage": 30.9, "elapsed_time": "2:41:07", "remaining_time": "6:00:20"}
|
||||
{"current_steps": 390, "total_steps": 1246, "loss": 0.4062, "lr": 3.4771290302872e-05, "epoch": 2.191729323308271, "percentage": 31.3, "elapsed_time": "2:43:05", "remaining_time": "5:57:57"}
|
||||
{"current_steps": 395, "total_steps": 1246, "loss": 0.4192, "lr": 3.458090720662167e-05, "epoch": 2.219924812030075, "percentage": 31.7, "elapsed_time": "2:45:01", "remaining_time": "5:55:32"}
|
||||
{"current_steps": 400, "total_steps": 1246, "loss": 0.403, "lr": 3.438766121175361e-05, "epoch": 2.2481203007518795, "percentage": 32.1, "elapsed_time": "2:47:03", "remaining_time": "5:53:19"}
|
||||
{"current_steps": 405, "total_steps": 1246, "loss": 0.4067, "lr": 3.4191590261290405e-05, "epoch": 2.276315789473684, "percentage": 32.5, "elapsed_time": "2:49:05", "remaining_time": "5:51:08"}
|
||||
{"current_steps": 410, "total_steps": 1246, "loss": 0.4129, "lr": 3.399273285292258e-05, "epoch": 2.3045112781954886, "percentage": 32.91, "elapsed_time": "2:51:06", "remaining_time": "5:48:54"}
|
||||
{"current_steps": 415, "total_steps": 1246, "loss": 0.4145, "lr": 3.379112803144971e-05, "epoch": 2.332706766917293, "percentage": 33.31, "elapsed_time": "2:53:05", "remaining_time": "5:46:35"}
|
||||
{"current_steps": 420, "total_steps": 1246, "loss": 0.4172, "lr": 3.358681538111415e-05, "epoch": 2.3609022556390977, "percentage": 33.71, "elapsed_time": "2:55:13", "remaining_time": "5:44:36"}
|
||||
{"current_steps": 425, "total_steps": 1246, "loss": 0.4157, "lr": 3.3379835017828855e-05, "epoch": 2.3890977443609023, "percentage": 34.11, "elapsed_time": "2:57:20", "remaining_time": "5:42:35"}
|
||||
{"current_steps": 430, "total_steps": 1246, "loss": 0.4146, "lr": 3.317022758130078e-05, "epoch": 2.417293233082707, "percentage": 34.51, "elapsed_time": "2:59:23", "remaining_time": "5:40:26"}
|
||||
{"current_steps": 435, "total_steps": 1246, "loss": 0.4137, "lr": 3.295803422705143e-05, "epoch": 2.4454887218045114, "percentage": 34.91, "elapsed_time": "3:01:21", "remaining_time": "5:38:06"}
|
||||
{"current_steps": 440, "total_steps": 1246, "loss": 0.4132, "lr": 3.27432966183362e-05, "epoch": 2.473684210526316, "percentage": 35.31, "elapsed_time": "3:03:20", "remaining_time": "5:35:51"}
|
||||
{"current_steps": 445, "total_steps": 1246, "loss": 0.4104, "lr": 3.25260569179639e-05, "epoch": 2.5018796992481205, "percentage": 35.71, "elapsed_time": "3:05:30", "remaining_time": "5:33:54"}
|
||||
{"current_steps": 450, "total_steps": 1246, "loss": 0.4017, "lr": 3.230635778001836e-05, "epoch": 2.530075187969925, "percentage": 36.12, "elapsed_time": "3:07:32", "remaining_time": "5:31:44"}
|
||||
{"current_steps": 455, "total_steps": 1246, "loss": 0.3996, "lr": 3.208424234148338e-05, "epoch": 2.5582706766917296, "percentage": 36.52, "elapsed_time": "3:09:30", "remaining_time": "5:29:26"}
|
||||
{"current_steps": 460, "total_steps": 1246, "loss": 0.4088, "lr": 3.185975421377307e-05, "epoch": 2.5864661654135337, "percentage": 36.92, "elapsed_time": "3:11:30", "remaining_time": "5:27:13"}
|
||||
{"current_steps": 465, "total_steps": 1246, "loss": 0.4118, "lr": 3.1632937474168855e-05, "epoch": 2.6146616541353382, "percentage": 37.32, "elapsed_time": "3:13:25", "remaining_time": "5:24:52"}
|
||||
{"current_steps": 470, "total_steps": 1246, "loss": 0.396, "lr": 3.140383665716512e-05, "epoch": 2.642857142857143, "percentage": 37.72, "elapsed_time": "3:15:30", "remaining_time": "5:22:47"}
|
||||
{"current_steps": 475, "total_steps": 1246, "loss": 0.409, "lr": 3.1172496745725085e-05, "epoch": 2.6710526315789473, "percentage": 38.12, "elapsed_time": "3:17:26", "remaining_time": "5:20:29"}
|
||||
{"current_steps": 480, "total_steps": 1246, "loss": 0.4046, "lr": 3.093896316244855e-05, "epoch": 2.699248120300752, "percentage": 38.52, "elapsed_time": "3:19:24", "remaining_time": "5:18:12"}
|
||||
{"current_steps": 485, "total_steps": 1246, "loss": 0.4083, "lr": 3.0703281760653336e-05, "epoch": 2.7274436090225564, "percentage": 38.92, "elapsed_time": "3:21:18", "remaining_time": "5:15:51"}
|
||||
{"current_steps": 490, "total_steps": 1246, "loss": 0.4031, "lr": 3.0465498815372285e-05, "epoch": 2.755639097744361, "percentage": 39.33, "elapsed_time": "3:23:16", "remaining_time": "5:13:37"}
|
||||
{"current_steps": 495, "total_steps": 1246, "loss": 0.4025, "lr": 3.0225661014267255e-05, "epoch": 2.7838345864661656, "percentage": 39.73, "elapsed_time": "3:25:09", "remaining_time": "5:11:16"}
|
||||
{"current_steps": 500, "total_steps": 1246, "loss": 0.4072, "lr": 2.9983815448462245e-05, "epoch": 2.8120300751879697, "percentage": 40.13, "elapsed_time": "3:27:08", "remaining_time": "5:09:03"}
|
||||
{"current_steps": 505, "total_steps": 1246, "loss": 0.4127, "lr": 2.9740009603297236e-05, "epoch": 2.840225563909774, "percentage": 40.53, "elapsed_time": "3:29:05", "remaining_time": "5:06:47"}
|
||||
{"current_steps": 510, "total_steps": 1246, "loss": 0.4017, "lr": 2.949429134900468e-05, "epoch": 2.8684210526315788, "percentage": 40.93, "elapsed_time": "3:31:14", "remaining_time": "5:04:51"}
|
||||
{"current_steps": 515, "total_steps": 1246, "loss": 0.4039, "lr": 2.924670893131033e-05, "epoch": 2.8966165413533833, "percentage": 41.33, "elapsed_time": "3:33:19", "remaining_time": "5:02:47"}
|
||||
{"current_steps": 520, "total_steps": 1246, "loss": 0.4065, "lr": 2.8997310961960456e-05, "epoch": 2.924812030075188, "percentage": 41.73, "elapsed_time": "3:35:18", "remaining_time": "5:00:35"}
|
||||
{"current_steps": 525, "total_steps": 1246, "loss": 0.4017, "lr": 2.8746146409177112e-05, "epoch": 2.9530075187969924, "percentage": 42.13, "elapsed_time": "3:37:18", "remaining_time": "4:58:25"}
|
||||
{"current_steps": 530, "total_steps": 1246, "loss": 0.4079, "lr": 2.849326458804341e-05, "epoch": 2.981203007518797, "percentage": 42.54, "elapsed_time": "3:39:21", "remaining_time": "4:56:20"}
|
||||
{"current_steps": 535, "total_steps": 1246, "loss": 0.3958, "lr": 2.8238715150820764e-05, "epoch": 3.005639097744361, "percentage": 42.94, "elapsed_time": "3:41:04", "remaining_time": "4:53:47"}
|
||||
{"current_steps": 540, "total_steps": 1246, "loss": 0.3961, "lr": 2.7982548077199853e-05, "epoch": 3.0338345864661656, "percentage": 43.34, "elapsed_time": "3:43:09", "remaining_time": "4:51:45"}
|
||||
{"current_steps": 545, "total_steps": 1246, "loss": 0.4004, "lr": 2.7724813664487323e-05, "epoch": 3.06203007518797, "percentage": 43.74, "elapsed_time": "3:45:10", "remaining_time": "4:49:37"}
|
||||
{"current_steps": 550, "total_steps": 1246, "loss": 0.3946, "lr": 2.7465562517730132e-05, "epoch": 3.090225563909774, "percentage": 44.14, "elapsed_time": "3:47:11", "remaining_time": "4:47:30"}
|
||||
{"current_steps": 555, "total_steps": 1246, "loss": 0.4026, "lr": 2.7204845539779468e-05, "epoch": 3.1184210526315788, "percentage": 44.54, "elapsed_time": "3:49:07", "remaining_time": "4:45:16"}
|
||||
{"current_steps": 560, "total_steps": 1246, "loss": 0.3974, "lr": 2.6942713921296186e-05, "epoch": 3.1466165413533833, "percentage": 44.94, "elapsed_time": "3:51:05", "remaining_time": "4:43:04"}
|
||||
{"current_steps": 565, "total_steps": 1246, "loss": 0.4, "lr": 2.6679219130699747e-05, "epoch": 3.174812030075188, "percentage": 45.35, "elapsed_time": "3:53:09", "remaining_time": "4:41:02"}
|
||||
{"current_steps": 570, "total_steps": 1246, "loss": 0.4012, "lr": 2.641441290406261e-05, "epoch": 3.2030075187969924, "percentage": 45.75, "elapsed_time": "3:55:04", "remaining_time": "4:38:47"}
|
||||
{"current_steps": 575, "total_steps": 1246, "loss": 0.3962, "lr": 2.614834723495208e-05, "epoch": 3.231203007518797, "percentage": 46.15, "elapsed_time": "3:57:04", "remaining_time": "4:36:39"}
|
||||
{"current_steps": 580, "total_steps": 1246, "loss": 0.3926, "lr": 2.5881074364221593e-05, "epoch": 3.2593984962406015, "percentage": 46.55, "elapsed_time": "3:58:58", "remaining_time": "4:34:24"}
|
||||
{"current_steps": 585, "total_steps": 1246, "loss": 0.3984, "lr": 2.5612646769753454e-05, "epoch": 3.287593984962406, "percentage": 46.95, "elapsed_time": "4:01:00", "remaining_time": "4:32:19"}
|
||||
{"current_steps": 590, "total_steps": 1246, "loss": 0.395, "lr": 2.5343117156154994e-05, "epoch": 3.3157894736842106, "percentage": 47.35, "elapsed_time": "4:02:51", "remaining_time": "4:30:01"}
|
||||
{"current_steps": 595, "total_steps": 1246, "loss": 0.3913, "lr": 2.507253844441031e-05, "epoch": 3.343984962406015, "percentage": 47.75, "elapsed_time": "4:04:45", "remaining_time": "4:27:47"}
|
||||
{"current_steps": 600, "total_steps": 1246, "loss": 0.4003, "lr": 2.480096376148941e-05, "epoch": 3.3721804511278197, "percentage": 48.15, "elapsed_time": "4:06:40", "remaining_time": "4:25:35"}
|
||||
{"current_steps": 605, "total_steps": 1246, "loss": 0.3988, "lr": 2.4528446429916973e-05, "epoch": 3.4003759398496243, "percentage": 48.56, "elapsed_time": "4:08:44", "remaining_time": "4:23:33"}
|
||||
{"current_steps": 610, "total_steps": 1246, "loss": 0.3978, "lr": 2.4255039957302692e-05, "epoch": 3.4285714285714284, "percentage": 48.96, "elapsed_time": "4:10:51", "remaining_time": "4:21:33"}
|
||||
{"current_steps": 615, "total_steps": 1246, "loss": 0.3966, "lr": 2.3980798025835298e-05, "epoch": 3.456766917293233, "percentage": 49.36, "elapsed_time": "4:12:51", "remaining_time": "4:19:25"}
|
||||
{"current_steps": 620, "total_steps": 1246, "loss": 0.3954, "lr": 2.370577448174229e-05, "epoch": 3.4849624060150375, "percentage": 49.76, "elapsed_time": "4:14:49", "remaining_time": "4:17:17"}
|
||||
{"current_steps": 625, "total_steps": 1246, "loss": 0.3894, "lr": 2.3430023324717443e-05, "epoch": 3.513157894736842, "percentage": 50.16, "elapsed_time": "4:16:54", "remaining_time": "4:15:15"}
|
||||
{"current_steps": 630, "total_steps": 1246, "loss": 0.4027, "lr": 2.3153598697318237e-05, "epoch": 3.5413533834586466, "percentage": 50.56, "elapsed_time": "4:18:53", "remaining_time": "4:13:07"}
|
||||
{"current_steps": 635, "total_steps": 1246, "loss": 0.3926, "lr": 2.2876554874335124e-05, "epoch": 3.569548872180451, "percentage": 50.96, "elapsed_time": "4:20:53", "remaining_time": "4:11:01"}
|
||||
{"current_steps": 640, "total_steps": 1246, "loss": 0.4018, "lr": 2.2598946252135017e-05, "epoch": 3.5977443609022557, "percentage": 51.36, "elapsed_time": "4:22:48", "remaining_time": "4:08:50"}
|
||||
{"current_steps": 645, "total_steps": 1246, "loss": 0.3914, "lr": 2.2320827337980676e-05, "epoch": 3.6259398496240602, "percentage": 51.77, "elapsed_time": "4:24:42", "remaining_time": "4:06:39"}
|
||||
{"current_steps": 650, "total_steps": 1246, "loss": 0.3946, "lr": 2.204225273932855e-05, "epoch": 3.654135338345865, "percentage": 52.17, "elapsed_time": "4:26:42", "remaining_time": "4:04:33"}
|
||||
{"current_steps": 655, "total_steps": 1246, "loss": 0.3916, "lr": 2.176327715310673e-05, "epoch": 3.682330827067669, "percentage": 52.57, "elapsed_time": "4:28:41", "remaining_time": "4:02:26"}
|
||||
{"current_steps": 660, "total_steps": 1246, "loss": 0.3968, "lr": 2.1483955354975557e-05, "epoch": 3.7105263157894735, "percentage": 52.97, "elapsed_time": "4:30:42", "remaining_time": "4:00:21"}
|
||||
{"current_steps": 665, "total_steps": 1246, "loss": 0.3949, "lr": 2.120434218857254e-05, "epoch": 3.738721804511278, "percentage": 53.37, "elapsed_time": "4:32:39", "remaining_time": "3:58:13"}
|
||||
{"current_steps": 670, "total_steps": 1246, "loss": 0.3946, "lr": 2.0924492554744145e-05, "epoch": 3.7669172932330826, "percentage": 53.77, "elapsed_time": "4:34:30", "remaining_time": "3:55:59"}
|
||||
{"current_steps": 675, "total_steps": 1246, "loss": 0.3958, "lr": 2.0644461400766174e-05, "epoch": 3.795112781954887, "percentage": 54.17, "elapsed_time": "4:36:26", "remaining_time": "3:53:50"}
|
||||
{"current_steps": 680, "total_steps": 1246, "loss": 0.3893, "lr": 2.036430370955514e-05, "epoch": 3.8233082706766917, "percentage": 54.57, "elapsed_time": "4:38:27", "remaining_time": "3:51:46"}
|
||||
{"current_steps": 685, "total_steps": 1246, "loss": 0.3942, "lr": 2.0084074488872606e-05, "epoch": 3.851503759398496, "percentage": 54.98, "elapsed_time": "4:40:29", "remaining_time": "3:49:43"}
|
||||
{"current_steps": 690, "total_steps": 1246, "loss": 0.3928, "lr": 1.9803828760524627e-05, "epoch": 3.8796992481203008, "percentage": 55.38, "elapsed_time": "4:42:38", "remaining_time": "3:47:45"}
|
||||
{"current_steps": 695, "total_steps": 1246, "loss": 0.3918, "lr": 1.952362154955848e-05, "epoch": 3.9078947368421053, "percentage": 55.78, "elapsed_time": "4:44:40", "remaining_time": "3:45:41"}
|
||||
{"current_steps": 700, "total_steps": 1246, "loss": 0.3943, "lr": 1.9243507873458717e-05, "epoch": 3.93609022556391, "percentage": 56.18, "elapsed_time": "4:46:41", "remaining_time": "3:43:37"}
|
||||
{"current_steps": 705, "total_steps": 1246, "loss": 0.3905, "lr": 1.896354273134472e-05, "epoch": 3.9642857142857144, "percentage": 56.58, "elapsed_time": "4:48:41", "remaining_time": "3:41:32"}
|
||||
{"current_steps": 710, "total_steps": 1246, "loss": 0.3884, "lr": 1.8683781093171846e-05, "epoch": 3.992481203007519, "percentage": 56.98, "elapsed_time": "4:50:46", "remaining_time": "3:39:30"}
|
||||
{"current_steps": 715, "total_steps": 1246, "loss": 0.3899, "lr": 1.8404277888938337e-05, "epoch": 4.0169172932330826, "percentage": 57.38, "elapsed_time": "4:52:30", "remaining_time": "3:37:14"}
|
||||
{"current_steps": 720, "total_steps": 1246, "loss": 0.386, "lr": 1.8125087997900054e-05, "epoch": 4.045112781954887, "percentage": 57.78, "elapsed_time": "4:54:33", "remaining_time": "3:35:11"}
|
||||
{"current_steps": 725, "total_steps": 1246, "loss": 0.3907, "lr": 1.784626623779512e-05, "epoch": 4.073308270676692, "percentage": 58.19, "elapsed_time": "4:56:23", "remaining_time": "3:32:59"}
|
||||
{"current_steps": 730, "total_steps": 1246, "loss": 0.3793, "lr": 1.7567867354080766e-05, "epoch": 4.101503759398496, "percentage": 58.59, "elapsed_time": "4:58:21", "remaining_time": "3:30:53"}
|
||||
{"current_steps": 735, "total_steps": 1246, "loss": 0.3889, "lr": 1.7289946009184217e-05, "epoch": 4.129699248120301, "percentage": 58.99, "elapsed_time": "5:00:19", "remaining_time": "3:28:47"}
|
||||
{"current_steps": 740, "total_steps": 1246, "loss": 0.3857, "lr": 1.701255677177004e-05, "epoch": 4.157894736842105, "percentage": 59.39, "elapsed_time": "5:02:11", "remaining_time": "3:26:38"}
|
||||
{"current_steps": 745, "total_steps": 1246, "loss": 0.3856, "lr": 1.6735754106025747e-05, "epoch": 4.18609022556391, "percentage": 59.79, "elapsed_time": "5:04:05", "remaining_time": "3:24:29"}
|
||||
{"current_steps": 750, "total_steps": 1246, "loss": 0.3837, "lr": 1.6459592360968036e-05, "epoch": 4.214285714285714, "percentage": 60.19, "elapsed_time": "5:05:59", "remaining_time": "3:22:22"}
|
||||
{"current_steps": 755, "total_steps": 1246, "loss": 0.3798, "lr": 1.618412575977156e-05, "epoch": 4.242481203007519, "percentage": 60.59, "elapsed_time": "5:08:01", "remaining_time": "3:20:19"}
|
||||
{"current_steps": 760, "total_steps": 1246, "loss": 0.39, "lr": 1.5909408389122473e-05, "epoch": 4.2706766917293235, "percentage": 61.0, "elapsed_time": "5:09:57", "remaining_time": "3:18:12"}
|
||||
{"current_steps": 765, "total_steps": 1246, "loss": 0.3892, "lr": 1.5635494188598713e-05, "epoch": 4.298872180451128, "percentage": 61.4, "elapsed_time": "5:12:06", "remaining_time": "3:16:14"}
|
||||
{"current_steps": 770, "total_steps": 1246, "loss": 0.3841, "lr": 1.5362436940079194e-05, "epoch": 4.327067669172933, "percentage": 61.8, "elapsed_time": "5:14:09", "remaining_time": "3:14:12"}
|
||||
{"current_steps": 775, "total_steps": 1246, "loss": 0.3938, "lr": 1.5090290257184019e-05, "epoch": 4.355263157894737, "percentage": 62.2, "elapsed_time": "5:16:06", "remaining_time": "3:12:07"}
|
||||
{"current_steps": 780, "total_steps": 1246, "loss": 0.3869, "lr": 1.481910757474759e-05, "epoch": 4.383458646616542, "percentage": 62.6, "elapsed_time": "5:18:04", "remaining_time": "3:10:01"}
|
||||
{"current_steps": 785, "total_steps": 1246, "loss": 0.3875, "lr": 1.4548942138326978e-05, "epoch": 4.411654135338346, "percentage": 63.0, "elapsed_time": "5:20:03", "remaining_time": "3:07:57"}
|
||||
{"current_steps": 790, "total_steps": 1246, "loss": 0.3859, "lr": 1.4279846993747342e-05, "epoch": 4.43984962406015, "percentage": 63.4, "elapsed_time": "5:22:04", "remaining_time": "3:05:54"}
|
||||
{"current_steps": 795, "total_steps": 1246, "loss": 0.3842, "lr": 1.4011874976686648e-05, "epoch": 4.4680451127819545, "percentage": 63.8, "elapsed_time": "5:24:06", "remaining_time": "3:03:51"}
|
||||
{"current_steps": 800, "total_steps": 1246, "loss": 0.3855, "lr": 1.3745078702301569e-05, "epoch": 4.496240601503759, "percentage": 64.21, "elapsed_time": "5:26:04", "remaining_time": "3:01:47"}
|
||||
{"current_steps": 805, "total_steps": 1246, "loss": 0.3877, "lr": 1.3479510554896762e-05, "epoch": 4.524436090225564, "percentage": 64.61, "elapsed_time": "5:28:01", "remaining_time": "2:59:42"}
|
||||
{"current_steps": 810, "total_steps": 1246, "loss": 0.3862, "lr": 1.3215222677639394e-05, "epoch": 4.552631578947368, "percentage": 65.01, "elapsed_time": "5:29:58", "remaining_time": "2:57:36"}
|
||||
{"current_steps": 815, "total_steps": 1246, "loss": 0.391, "lr": 1.2952266962321106e-05, "epoch": 4.580827067669173, "percentage": 65.41, "elapsed_time": "5:31:59", "remaining_time": "2:55:33"}
|
||||
{"current_steps": 820, "total_steps": 1246, "loss": 0.3929, "lr": 1.2690695039169231e-05, "epoch": 4.609022556390977, "percentage": 65.81, "elapsed_time": "5:34:01", "remaining_time": "2:53:31"}
|
||||
{"current_steps": 825, "total_steps": 1246, "loss": 0.3849, "lr": 1.2430558266709451e-05, "epoch": 4.637218045112782, "percentage": 66.21, "elapsed_time": "5:36:04", "remaining_time": "2:51:29"}
|
||||
{"current_steps": 830, "total_steps": 1246, "loss": 0.383, "lr": 1.2171907721681755e-05, "epoch": 4.665413533834586, "percentage": 66.61, "elapsed_time": "5:37:58", "remaining_time": "2:49:23"}
|
||||
{"current_steps": 835, "total_steps": 1246, "loss": 0.3786, "lr": 1.1914794189011767e-05, "epoch": 4.693609022556391, "percentage": 67.01, "elapsed_time": "5:40:01", "remaining_time": "2:47:21"}
|
||||
{"current_steps": 840, "total_steps": 1246, "loss": 0.3851, "lr": 1.1659268151839305e-05, "epoch": 4.7218045112781954, "percentage": 67.42, "elapsed_time": "5:41:58", "remaining_time": "2:45:17"}
|
||||
{"current_steps": 845, "total_steps": 1246, "loss": 0.3874, "lr": 1.1405379781606264e-05, "epoch": 4.75, "percentage": 67.82, "elapsed_time": "5:43:53", "remaining_time": "2:43:11"}
|
||||
{"current_steps": 850, "total_steps": 1246, "loss": 0.3912, "lr": 1.115317892820564e-05, "epoch": 4.7781954887218046, "percentage": 68.22, "elapsed_time": "5:45:57", "remaining_time": "2:41:10"}
|
||||
{"current_steps": 855, "total_steps": 1246, "loss": 0.3883, "lr": 1.0902715110193758e-05, "epoch": 4.806390977443609, "percentage": 68.62, "elapsed_time": "5:47:51", "remaining_time": "2:39:04"}
|
||||
{"current_steps": 860, "total_steps": 1246, "loss": 0.3862, "lr": 1.0654037505067474e-05, "epoch": 4.834586466165414, "percentage": 69.02, "elapsed_time": "5:49:50", "remaining_time": "2:37:01"}
|
||||
{"current_steps": 865, "total_steps": 1246, "loss": 0.3912, "lr": 1.0407194939608388e-05, "epoch": 4.862781954887218, "percentage": 69.42, "elapsed_time": "5:51:43", "remaining_time": "2:34:55"}
|
||||
{"current_steps": 870, "total_steps": 1246, "loss": 0.3902, "lr": 1.016223588029598e-05, "epoch": 4.890977443609023, "percentage": 69.82, "elapsed_time": "5:53:41", "remaining_time": "2:32:51"}
|
||||
{"current_steps": 875, "total_steps": 1246, "loss": 0.3869, "lr": 9.919208423791327e-06, "epoch": 4.919172932330827, "percentage": 70.22, "elapsed_time": "5:55:42", "remaining_time": "2:30:49"}
|
||||
{"current_steps": 880, "total_steps": 1246, "loss": 0.3923, "lr": 9.678160287493586e-06, "epoch": 4.947368421052632, "percentage": 70.63, "elapsed_time": "5:57:45", "remaining_time": "2:28:47"}
|
||||
{"current_steps": 885, "total_steps": 1246, "loss": 0.3849, "lr": 9.439138800170873e-06, "epoch": 4.975563909774436, "percentage": 71.03, "elapsed_time": "5:59:53", "remaining_time": "2:26:48"}
|
||||
{"current_steps": 890, "total_steps": 1246, "loss": 0.3942, "lr": 9.202190892667482e-06, "epoch": 5.0, "percentage": 71.43, "elapsed_time": "6:01:40", "remaining_time": "2:24:40"}
|
||||
{"current_steps": 895, "total_steps": 1246, "loss": 0.3772, "lr": 8.9673630886892e-06, "epoch": 5.0281954887218046, "percentage": 71.83, "elapsed_time": "6:03:43", "remaining_time": "2:22:38"}
|
||||
{"current_steps": 900, "total_steps": 1246, "loss": 0.3911, "lr": 8.734701495668564e-06, "epoch": 5.056390977443609, "percentage": 72.23, "elapsed_time": "6:05:42", "remaining_time": "2:20:35"}
|
||||
{"current_steps": 905, "total_steps": 1246, "loss": 0.3771, "lr": 8.504251795711865e-06, "epoch": 5.084586466165414, "percentage": 72.63, "elapsed_time": "6:07:54", "remaining_time": "2:18:37"}
|
||||
{"current_steps": 910, "total_steps": 1246, "loss": 0.3792, "lr": 8.276059236629704e-06, "epoch": 5.112781954887218, "percentage": 73.03, "elapsed_time": "6:09:51", "remaining_time": "2:16:33"}
|
||||
{"current_steps": 915, "total_steps": 1246, "loss": 0.3792, "lr": 8.050168623052737e-06, "epoch": 5.140977443609023, "percentage": 73.43, "elapsed_time": "6:11:41", "remaining_time": "2:14:27"}
|
||||
{"current_steps": 920, "total_steps": 1246, "loss": 0.3846, "lr": 7.826624307634478e-06, "epoch": 5.169172932330827, "percentage": 73.84, "elapsed_time": "6:13:38", "remaining_time": "2:12:23"}
|
||||
{"current_steps": 925, "total_steps": 1246, "loss": 0.3804, "lr": 7.605470182342862e-06, "epoch": 5.197368421052632, "percentage": 74.24, "elapsed_time": "6:15:31", "remaining_time": "2:10:18"}
|
||||
{"current_steps": 930, "total_steps": 1246, "loss": 0.3847, "lr": 7.386749669842246e-06, "epoch": 5.225563909774436, "percentage": 74.64, "elapsed_time": "6:17:37", "remaining_time": "2:08:18"}
|
||||
{"current_steps": 935, "total_steps": 1246, "loss": 0.3802, "lr": 7.170505714967551e-06, "epoch": 5.253759398496241, "percentage": 75.04, "elapsed_time": "6:19:34", "remaining_time": "2:06:15"}
|
||||
{"current_steps": 940, "total_steps": 1246, "loss": 0.3883, "lr": 6.956780776292211e-06, "epoch": 5.2819548872180455, "percentage": 75.44, "elapsed_time": "6:21:35", "remaining_time": "2:04:13"}
|
||||
{"current_steps": 945, "total_steps": 1246, "loss": 0.3815, "lr": 6.7456168177916494e-06, "epoch": 5.31015037593985, "percentage": 75.84, "elapsed_time": "6:23:31", "remaining_time": "2:02:09"}
|
||||
{"current_steps": 950, "total_steps": 1246, "loss": 0.3851, "lr": 6.537055300603796e-06, "epoch": 5.338345864661654, "percentage": 76.24, "elapsed_time": "6:25:24", "remaining_time": "2:00:04"}
|
||||
{"current_steps": 955, "total_steps": 1246, "loss": 0.3842, "lr": 6.331137174888382e-06, "epoch": 5.366541353383458, "percentage": 76.65, "elapsed_time": "6:27:27", "remaining_time": "1:58:03"}
|
||||
{"current_steps": 960, "total_steps": 1246, "loss": 0.3832, "lr": 6.127902871786573e-06, "epoch": 5.394736842105263, "percentage": 77.05, "elapsed_time": "6:29:24", "remaining_time": "1:56:00"}
|
||||
{"current_steps": 965, "total_steps": 1246, "loss": 0.3805, "lr": 5.927392295482468e-06, "epoch": 5.422932330827067, "percentage": 77.45, "elapsed_time": "6:31:29", "remaining_time": "1:53:59"}
|
||||
{"current_steps": 970, "total_steps": 1246, "loss": 0.3892, "lr": 5.729644815368076e-06, "epoch": 5.451127819548872, "percentage": 77.85, "elapsed_time": "6:33:24", "remaining_time": "1:51:56"}
|
||||
{"current_steps": 975, "total_steps": 1246, "loss": 0.3765, "lr": 5.534699258313314e-06, "epoch": 5.4793233082706765, "percentage": 78.25, "elapsed_time": "6:35:30", "remaining_time": "1:49:55"}
|
||||
{"current_steps": 980, "total_steps": 1246, "loss": 0.3842, "lr": 5.342593901042532e-06, "epoch": 5.507518796992481, "percentage": 78.65, "elapsed_time": "6:37:33", "remaining_time": "1:47:54"}
|
||||
{"current_steps": 985, "total_steps": 1246, "loss": 0.388, "lr": 5.15336646261903e-06, "epoch": 5.535714285714286, "percentage": 79.05, "elapsed_time": "6:39:33", "remaining_time": "1:45:52"}
|
||||
{"current_steps": 990, "total_steps": 1246, "loss": 0.3811, "lr": 4.9670540970390636e-06, "epoch": 5.56390977443609, "percentage": 79.45, "elapsed_time": "6:41:39", "remaining_time": "1:43:51"}
|
||||
{"current_steps": 995, "total_steps": 1246, "loss": 0.3848, "lr": 4.783693385936841e-06, "epoch": 5.592105263157895, "percentage": 79.86, "elapsed_time": "6:43:33", "remaining_time": "1:41:48"}
|
||||
{"current_steps": 1000, "total_steps": 1246, "loss": 0.3774, "lr": 4.603320331401873e-06, "epoch": 5.620300751879699, "percentage": 80.26, "elapsed_time": "6:45:34", "remaining_time": "1:39:46"}
|
||||
{"current_steps": 1005, "total_steps": 1246, "loss": 0.3829, "lr": 4.425970348910118e-06, "epoch": 5.648496240601504, "percentage": 80.66, "elapsed_time": "6:47:29", "remaining_time": "1:37:43"}
|
||||
{"current_steps": 1010, "total_steps": 1246, "loss": 0.3871, "lr": 4.251678260370282e-06, "epoch": 5.676691729323308, "percentage": 81.06, "elapsed_time": "6:49:37", "remaining_time": "1:35:42"}
|
||||
{"current_steps": 1015, "total_steps": 1246, "loss": 0.3776, "lr": 4.080478287286711e-06, "epoch": 5.704887218045113, "percentage": 81.46, "elapsed_time": "6:51:35", "remaining_time": "1:33:40"}
|
||||
{"current_steps": 1020, "total_steps": 1246, "loss": 0.3825, "lr": 3.912404044040146e-06, "epoch": 5.7330827067669174, "percentage": 81.86, "elapsed_time": "6:53:32", "remaining_time": "1:31:37"}
|
||||
{"current_steps": 1025, "total_steps": 1246, "loss": 0.3803, "lr": 3.747488531287662e-06, "epoch": 5.761278195488722, "percentage": 82.26, "elapsed_time": "6:55:34", "remaining_time": "1:29:36"}
|
||||
{"current_steps": 1030, "total_steps": 1246, "loss": 0.3835, "lr": 3.58576412948316e-06, "epoch": 5.7894736842105265, "percentage": 82.66, "elapsed_time": "6:57:30", "remaining_time": "1:27:33"}
|
||||
{"current_steps": 1035, "total_steps": 1246, "loss": 0.3844, "lr": 3.4272625925195667e-06, "epoch": 5.817669172932331, "percentage": 83.07, "elapsed_time": "6:59:26", "remaining_time": "1:25:30"}
|
||||
{"current_steps": 1040, "total_steps": 1246, "loss": 0.3809, "lr": 3.2720150414941366e-06, "epoch": 5.845864661654136, "percentage": 83.47, "elapsed_time": "7:01:19", "remaining_time": "1:23:27"}
|
||||
{"current_steps": 1045, "total_steps": 1246, "loss": 0.3835, "lr": 3.120051958597916e-06, "epoch": 5.87406015037594, "percentage": 83.87, "elapsed_time": "7:03:16", "remaining_time": "1:21:24"}
|
||||
{"current_steps": 1050, "total_steps": 1246, "loss": 0.3777, "lr": 2.971403181130734e-06, "epoch": 5.902255639097744, "percentage": 84.27, "elapsed_time": "7:05:10", "remaining_time": "1:19:21"}
|
||||
{"current_steps": 1055, "total_steps": 1246, "loss": 0.386, "lr": 2.8260978956427388e-06, "epoch": 5.930451127819548, "percentage": 84.67, "elapsed_time": "7:07:07", "remaining_time": "1:17:19"}
|
||||
{"current_steps": 1060, "total_steps": 1246, "loss": 0.3805, "lr": 2.6841646322037827e-06, "epoch": 5.958646616541353, "percentage": 85.07, "elapsed_time": "7:09:12", "remaining_time": "1:15:18"}
|
||||
{"current_steps": 1065, "total_steps": 1246, "loss": 0.3826, "lr": 2.5456312588016285e-06, "epoch": 5.9868421052631575, "percentage": 85.47, "elapsed_time": "7:11:09", "remaining_time": "1:13:16"}
|
||||
{"current_steps": 1070, "total_steps": 1246, "loss": 0.374, "lr": 2.410524975870221e-06, "epoch": 6.011278195488722, "percentage": 85.87, "elapsed_time": "7:12:57", "remaining_time": "1:11:12"}
|
||||
{"current_steps": 1075, "total_steps": 1246, "loss": 0.38, "lr": 2.2788723109489675e-06, "epoch": 6.0394736842105265, "percentage": 86.28, "elapsed_time": "7:14:55", "remaining_time": "1:09:10"}
|
||||
{"current_steps": 1080, "total_steps": 1246, "loss": 0.3803, "lr": 2.1506991134742017e-06, "epoch": 6.067669172932331, "percentage": 86.68, "elapsed_time": "7:16:56", "remaining_time": "1:07:09"}
|
||||
{"current_steps": 1085, "total_steps": 1246, "loss": 0.3777, "lr": 2.026030549703735e-06, "epoch": 6.095864661654136, "percentage": 87.08, "elapsed_time": "7:18:48", "remaining_time": "1:05:06"}
|
||||
{"current_steps": 1090, "total_steps": 1246, "loss": 0.3819, "lr": 1.9048910977755675e-06, "epoch": 6.12406015037594, "percentage": 87.48, "elapsed_time": "7:20:50", "remaining_time": "1:03:05"}
|
||||
{"current_steps": 1095, "total_steps": 1246, "loss": 0.3803, "lr": 1.7873045429017356e-06, "epoch": 6.152255639097745, "percentage": 87.88, "elapsed_time": "7:22:51", "remaining_time": "1:01:04"}
|
||||
{"current_steps": 1100, "total_steps": 1246, "loss": 0.3842, "lr": 1.6732939726981645e-06, "epoch": 6.180451127819548, "percentage": 88.28, "elapsed_time": "7:24:53", "remaining_time": "0:59:02"}
|
||||
{"current_steps": 1105, "total_steps": 1246, "loss": 0.3792, "lr": 1.5628817726515166e-06, "epoch": 6.208646616541353, "percentage": 88.68, "elapsed_time": "7:26:41", "remaining_time": "0:56:59"}
|
||||
{"current_steps": 1110, "total_steps": 1246, "loss": 0.388, "lr": 1.4560896217239017e-06, "epoch": 6.2368421052631575, "percentage": 89.09, "elapsed_time": "7:28:47", "remaining_time": "0:54:59"}
|
||||
{"current_steps": 1115, "total_steps": 1246, "loss": 0.3864, "lr": 1.3529384880963092e-06, "epoch": 6.265037593984962, "percentage": 89.49, "elapsed_time": "7:30:44", "remaining_time": "0:52:57"}
|
||||
{"current_steps": 1120, "total_steps": 1246, "loss": 0.3805, "lr": 1.2534486250515943e-06, "epoch": 6.293233082706767, "percentage": 89.89, "elapsed_time": "7:32:42", "remaining_time": "0:50:55"}
|
||||
{"current_steps": 1125, "total_steps": 1246, "loss": 0.3777, "lr": 1.1576395669978212e-06, "epoch": 6.321428571428571, "percentage": 90.29, "elapsed_time": "7:34:40", "remaining_time": "0:48:54"}
|
||||
{"current_steps": 1130, "total_steps": 1246, "loss": 0.3809, "lr": 1.0655301256327788e-06, "epoch": 6.349624060150376, "percentage": 90.69, "elapsed_time": "7:36:40", "remaining_time": "0:46:52"}
|
||||
{"current_steps": 1135, "total_steps": 1246, "loss": 0.3794, "lr": 9.771383862503847e-07, "epoch": 6.37781954887218, "percentage": 91.09, "elapsed_time": "7:38:44", "remaining_time": "0:44:51"}
|
||||
{"current_steps": 1140, "total_steps": 1246, "loss": 0.3782, "lr": 8.924817041897072e-07, "epoch": 6.406015037593985, "percentage": 91.49, "elapsed_time": "7:40:42", "remaining_time": "0:42:50"}
|
||||
{"current_steps": 1145, "total_steps": 1246, "loss": 0.3722, "lr": 8.115767014273213e-07, "epoch": 6.434210526315789, "percentage": 91.89, "elapsed_time": "7:42:41", "remaining_time": "0:40:48"}
|
||||
{"current_steps": 1150, "total_steps": 1246, "loss": 0.3797, "lr": 7.344392633136555e-07, "epoch": 6.462406015037594, "percentage": 92.3, "elapsed_time": "7:44:36", "remaining_time": "0:38:47"}
|
||||
{"current_steps": 1155, "total_steps": 1246, "loss": 0.3818, "lr": 6.610845354539796e-07, "epoch": 6.4906015037593985, "percentage": 92.7, "elapsed_time": "7:46:31", "remaining_time": "0:36:45"}
|
||||
{"current_steps": 1160, "total_steps": 1246, "loss": 0.3764, "lr": 5.91526920734613e-07, "epoch": 6.518796992481203, "percentage": 93.1, "elapsed_time": "7:48:24", "remaining_time": "0:34:43"}
|
||||
{"current_steps": 1165, "total_steps": 1246, "loss": 0.3819, "lr": 5.257800764949972e-07, "epoch": 6.546992481203008, "percentage": 93.5, "elapsed_time": "7:50:25", "remaining_time": "0:32:42"}
|
||||
{"current_steps": 1170, "total_steps": 1246, "loss": 0.3784, "lr": 4.6385691184611894e-07, "epoch": 6.575187969924812, "percentage": 93.9, "elapsed_time": "7:52:29", "remaining_time": "0:30:41"}
|
||||
{"current_steps": 1175, "total_steps": 1246, "loss": 0.3756, "lr": 4.057695851358823e-07, "epoch": 6.603383458646617, "percentage": 94.3, "elapsed_time": "7:54:30", "remaining_time": "0:28:40"}
|
||||
{"current_steps": 1180, "total_steps": 1246, "loss": 0.3767, "lr": 3.5152950156184475e-07, "epoch": 6.631578947368421, "percentage": 94.7, "elapsed_time": "7:56:37", "remaining_time": "0:26:39"}
|
||||
{"current_steps": 1185, "total_steps": 1246, "loss": 0.38, "lr": 3.0114731093187743e-07, "epoch": 6.659774436090226, "percentage": 95.1, "elapsed_time": "7:58:43", "remaining_time": "0:24:38"}
|
||||
{"current_steps": 1190, "total_steps": 1246, "loss": 0.3867, "lr": 2.5463290557310895e-07, "epoch": 6.68796992481203, "percentage": 95.51, "elapsed_time": "8:00:41", "remaining_time": "0:22:37"}
|
||||
{"current_steps": 1195, "total_steps": 1246, "loss": 0.3802, "lr": 2.1199541838961003e-07, "epoch": 6.716165413533835, "percentage": 95.91, "elapsed_time": "8:02:37", "remaining_time": "0:20:35"}
|
||||
{"current_steps": 1200, "total_steps": 1246, "loss": 0.3772, "lr": 1.7324322106919033e-07, "epoch": 6.7443609022556394, "percentage": 96.31, "elapsed_time": "8:04:38", "remaining_time": "0:18:34"}
|
||||
{"current_steps": 1205, "total_steps": 1246, "loss": 0.381, "lr": 1.3838392243965548e-07, "epoch": 6.772556390977444, "percentage": 96.71, "elapsed_time": "8:06:37", "remaining_time": "0:16:33"}
|
||||
{"current_steps": 1210, "total_steps": 1246, "loss": 0.3807, "lr": 1.0742436697483761e-07, "epoch": 6.8007518796992485, "percentage": 97.11, "elapsed_time": "8:08:28", "remaining_time": "0:14:31"}
|
||||
{"current_steps": 1215, "total_steps": 1246, "loss": 0.385, "lr": 8.03706334507215e-08, "epoch": 6.828947368421053, "percentage": 97.51, "elapsed_time": "8:10:26", "remaining_time": "0:12:30"}
|
||||
{"current_steps": 1220, "total_steps": 1246, "loss": 0.3771, "lr": 5.72280337518949e-08, "epoch": 6.857142857142857, "percentage": 97.91, "elapsed_time": "8:12:25", "remaining_time": "0:10:29"}
|
||||
{"current_steps": 1225, "total_steps": 1246, "loss": 0.3788, "lr": 3.8001111828593897e-08, "epoch": 6.885338345864661, "percentage": 98.31, "elapsed_time": "8:14:27", "remaining_time": "0:08:28"}
|
||||
{"current_steps": 1230, "total_steps": 1246, "loss": 0.3862, "lr": 2.2693642804505477e-08, "epoch": 6.913533834586466, "percentage": 98.72, "elapsed_time": "8:16:27", "remaining_time": "0:06:27"}
|
||||
{"current_steps": 1235, "total_steps": 1246, "loss": 0.3796, "lr": 1.1308632235547123e-08, "epoch": 6.94172932330827, "percentage": 99.12, "elapsed_time": "8:18:27", "remaining_time": "0:04:26"}
|
||||
{"current_steps": 1240, "total_steps": 1246, "loss": 0.3829, "lr": 3.848315519729973e-09, "epoch": 6.969924812030075, "percentage": 99.52, "elapsed_time": "8:20:17", "remaining_time": "0:02:25"}
|
||||
{"current_steps": 1245, "total_steps": 1246, "loss": 0.3839, "lr": 3.1415745826102185e-10, "epoch": 6.9981203007518795, "percentage": 99.92, "elapsed_time": "8:22:17", "remaining_time": "0:00:24"}
|
||||
{"current_steps": 1246, "total_steps": 1246, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "8:22:32", "remaining_time": "0:00:00"}
|
||||
{"current_steps": 1246, "total_steps": 1246, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "0:00:00", "remaining_time": "0:00:00"}
|
||||
{"current_steps": 1246, "total_steps": 1246, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "0:00:00", "remaining_time": "0:00:00"}
|
||||
{"current_steps": 1246, "total_steps": 1246, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "0:00:00", "remaining_time": "0:00:00"}
|
||||
{"current_steps": 1246, "total_steps": 1246, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "0:00:00", "remaining_time": "0:00:00"}
|
||||
{"current_steps": 1246, "total_steps": 1246, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "0:00:00", "remaining_time": "0:00:00"}
|
||||
2782
trainer_state.json
Normal file
2782
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 sha256:8f07295e2d267ef5fd63334abfb65cac81ee6d56411ad769998e8479ed742aec
|
||||
size 8657
|
||||
BIN
training_loss.png
Normal file
BIN
training_loss.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 38 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