初始化项目，由ModelHub XC社区提供模型
Model: penfever/nl2bash-3k-traces-restore-hp 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
|
||||
60
README.md
Normal file
60
README.md
Normal file
@@ -0,0 +1,60 @@
|
||||
---
|
||||
library_name: transformers
|
||||
license: apache-2.0
|
||||
base_model: Qwen/Qwen3-8B
|
||||
tags:
|
||||
- llama-factory
|
||||
- full
|
||||
- generated_from_trainer
|
||||
model-index:
|
||||
- name: nl2bash-3k-traces-restore-hp
|
||||
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. -->
|
||||
|
||||
# nl2bash-3k-traces-restore-hp
|
||||
|
||||
This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on the DCAgent/nl2bash-3k-traces dataset.
|
||||
|
||||
## Model description
|
||||
|
||||
More information needed
|
||||
|
||||
## Intended uses & limitations
|
||||
|
||||
More information needed
|
||||
|
||||
## Training and evaluation data
|
||||
|
||||
More information needed
|
||||
|
||||
## Training procedure
|
||||
|
||||
### Training hyperparameters
|
||||
|
||||
The following hyperparameters were used during training:
|
||||
- learning_rate: 4e-05
|
||||
- train_batch_size: 1
|
||||
- eval_batch_size: 8
|
||||
- seed: 42
|
||||
- distributed_type: multi-GPU
|
||||
- num_devices: 16
|
||||
- total_train_batch_size: 16
|
||||
- total_eval_batch_size: 128
|
||||
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
||||
- lr_scheduler_type: cosine
|
||||
- lr_scheduler_warmup_ratio: 0.1
|
||||
- num_epochs: 6.0
|
||||
|
||||
### Training results
|
||||
|
||||
|
||||
|
||||
### Framework versions
|
||||
|
||||
- Transformers 4.56.0
|
||||
- Pytorch 2.7.0+cu128
|
||||
- Datasets 3.6.0
|
||||
- Tokenizers 0.22.1
|
||||
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": 0.001951399015158965,
|
||||
"achieved_tflops_per_gpu_theoretical": 1016.3713688469504,
|
||||
"epoch": 6.0,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.133074551820755,
|
||||
"mfu_percent": 0.00013790805760840742,
|
||||
"mfu_percent_theoretical": 71.82836528953713,
|
||||
"total_flos": 123574112944128.0,
|
||||
"train_loss": 0.2030692549064906,
|
||||
"train_runtime": 3957.8692,
|
||||
"train_samples_per_second": 4.79,
|
||||
"train_steps_per_second": 0.3,
|
||||
"valid_targets_mean": 1319.8,
|
||||
"valid_targets_min": 875
|
||||
}
|
||||
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": "4.56.0",
|
||||
"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": "4.56.0"
|
||||
}
|
||||
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:b2ff25930b01ffcdd98c5bb83d6b103fe5f9184cbb01bc173e4d9c111636e9b1
|
||||
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 sha256:719862a4f1ad6cfca37428d712a8657ea7a38721cd06b00911d367935eec5ce9
|
||||
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:b57d1078ace2df52e246fa9b24e18e68cde285ef0edead701901b187a500cdf1
|
||||
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 sha256:7c28b5eef7400bfb294d2d3965ed853b73dfb2de1a4a5e44e1de3a01091da3e1
|
||||
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": null,
|
||||
"training_start": null,
|
||||
"training_end": null,
|
||||
"created_by": "DCAgent",
|
||||
"base_model_name": "Qwen/Qwen3-8B",
|
||||
"dataset_name": "DCAgent/nl2bash-3k-traces",
|
||||
"training_type": "SFT",
|
||||
"training_parameters": "https://huggingface.co/penfever/nl2bash-3k-traces-restore-hp/blob/main/config.json",
|
||||
"wandb_link": "https://wandb.ai/dogml/dc-agent/runs/nl2bash-3k-traces_hub-model-id_nl2bash-3k-traces-restore-hp_Qwen3-8B",
|
||||
"traces_location_s3": null
|
||||
}
|
||||
31
special_tokens_map.json
Normal file
31
special_tokens_map.json
Normal file
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"eos_token": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
BIN
tokenizer.json
(Stored with Git LFS)
Normal file
BIN
tokenizer.json
(Stored with Git LFS)
Normal file
Binary file not shown.
240
tokenizer_config.json
Normal file
240
tokenizer_config.json
Normal file
@@ -0,0 +1,240 @@
|
||||
{
|
||||
"add_bos_token": false,
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"151643": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151644": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151645": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151646": {
|
||||
"content": "<|object_ref_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151647": {
|
||||
"content": "<|object_ref_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151648": {
|
||||
"content": "<|box_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151649": {
|
||||
"content": "<|box_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151650": {
|
||||
"content": "<|quad_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151651": {
|
||||
"content": "<|quad_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151652": {
|
||||
"content": "<|vision_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151653": {
|
||||
"content": "<|vision_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151654": {
|
||||
"content": "<|vision_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151655": {
|
||||
"content": "<|image_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151656": {
|
||||
"content": "<|video_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151657": {
|
||||
"content": "<tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151658": {
|
||||
"content": "</tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151659": {
|
||||
"content": "<|fim_prefix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151660": {
|
||||
"content": "<|fim_middle|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151661": {
|
||||
"content": "<|fim_suffix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151662": {
|
||||
"content": "<|fim_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151663": {
|
||||
"content": "<|repo_name|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151664": {
|
||||
"content": "<|file_sep|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151665": {
|
||||
"content": "<tool_response>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151666": {
|
||||
"content": "</tool_response>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151667": {
|
||||
"content": "<think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151668": {
|
||||
"content": "</think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"bos_token": null,
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": {},
|
||||
"model_max_length": 32768,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"padding_side": "right",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
16
train_results.json
Normal file
16
train_results.json
Normal file
@@ -0,0 +1,16 @@
|
||||
{
|
||||
"achieved_tflops_per_gpu": 0.001951399015158965,
|
||||
"achieved_tflops_per_gpu_theoretical": 1016.3713688469504,
|
||||
"epoch": 6.0,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.133074551820755,
|
||||
"mfu_percent": 0.00013790805760840742,
|
||||
"mfu_percent_theoretical": 71.82836528953713,
|
||||
"total_flos": 123574112944128.0,
|
||||
"train_loss": 0.2030692549064906,
|
||||
"train_runtime": 3957.8692,
|
||||
"train_samples_per_second": 4.79,
|
||||
"train_steps_per_second": 0.3,
|
||||
"valid_targets_mean": 1319.8,
|
||||
"valid_targets_min": 875
|
||||
}
|
||||
238
trainer_log.jsonl
Normal file
238
trainer_log.jsonl
Normal file
@@ -0,0 +1,238 @@
|
||||
{"current_steps": 5, "total_steps": 1188, "loss": 1.0237, "lr": 1.3445378151260504e-06, "epoch": 0.025252525252525252, "percentage": 0.42, "elapsed_time": "0:00:26", "remaining_time": "1:43:47"}
|
||||
{"current_steps": 10, "total_steps": 1188, "loss": 0.9775, "lr": 3.0252100840336137e-06, "epoch": 0.050505050505050504, "percentage": 0.84, "elapsed_time": "0:00:39", "remaining_time": "1:18:09"}
|
||||
{"current_steps": 15, "total_steps": 1188, "loss": 0.8599, "lr": 4.705882352941177e-06, "epoch": 0.07575757575757576, "percentage": 1.26, "elapsed_time": "0:00:53", "remaining_time": "1:10:17"}
|
||||
{"current_steps": 20, "total_steps": 1188, "loss": 0.7379, "lr": 6.386554621848739e-06, "epoch": 0.10101010101010101, "percentage": 1.68, "elapsed_time": "0:01:08", "remaining_time": "1:06:40"}
|
||||
{"current_steps": 25, "total_steps": 1188, "loss": 0.6167, "lr": 8.067226890756303e-06, "epoch": 0.12626262626262627, "percentage": 2.1, "elapsed_time": "0:01:22", "remaining_time": "1:04:19"}
|
||||
{"current_steps": 30, "total_steps": 1188, "loss": 0.5299, "lr": 9.747899159663867e-06, "epoch": 0.15151515151515152, "percentage": 2.53, "elapsed_time": "0:01:37", "remaining_time": "1:02:27"}
|
||||
{"current_steps": 35, "total_steps": 1188, "loss": 0.4981, "lr": 1.1428571428571429e-05, "epoch": 0.17676767676767677, "percentage": 2.95, "elapsed_time": "0:01:51", "remaining_time": "1:01:12"}
|
||||
{"current_steps": 40, "total_steps": 1188, "loss": 0.4407, "lr": 1.3109243697478993e-05, "epoch": 0.20202020202020202, "percentage": 3.37, "elapsed_time": "0:02:05", "remaining_time": "1:00:08"}
|
||||
{"current_steps": 45, "total_steps": 1188, "loss": 0.414, "lr": 1.4789915966386557e-05, "epoch": 0.22727272727272727, "percentage": 3.79, "elapsed_time": "0:02:20", "remaining_time": "0:59:33"}
|
||||
{"current_steps": 50, "total_steps": 1188, "loss": 0.3676, "lr": 1.647058823529412e-05, "epoch": 0.25252525252525254, "percentage": 4.21, "elapsed_time": "0:02:35", "remaining_time": "0:58:58"}
|
||||
{"current_steps": 55, "total_steps": 1188, "loss": 0.3464, "lr": 1.8151260504201682e-05, "epoch": 0.2777777777777778, "percentage": 4.63, "elapsed_time": "0:02:49", "remaining_time": "0:58:04"}
|
||||
{"current_steps": 60, "total_steps": 1188, "loss": 0.338, "lr": 1.9831932773109244e-05, "epoch": 0.30303030303030304, "percentage": 5.05, "elapsed_time": "0:03:03", "remaining_time": "0:57:37"}
|
||||
{"current_steps": 65, "total_steps": 1188, "loss": 0.3275, "lr": 2.1512605042016807e-05, "epoch": 0.3282828282828283, "percentage": 5.47, "elapsed_time": "0:03:18", "remaining_time": "0:57:06"}
|
||||
{"current_steps": 70, "total_steps": 1188, "loss": 0.2979, "lr": 2.3193277310924373e-05, "epoch": 0.35353535353535354, "percentage": 5.89, "elapsed_time": "0:03:32", "remaining_time": "0:56:28"}
|
||||
{"current_steps": 75, "total_steps": 1188, "loss": 0.2957, "lr": 2.4873949579831935e-05, "epoch": 0.3787878787878788, "percentage": 6.31, "elapsed_time": "0:03:46", "remaining_time": "0:55:55"}
|
||||
{"current_steps": 80, "total_steps": 1188, "loss": 0.3063, "lr": 2.6554621848739497e-05, "epoch": 0.40404040404040403, "percentage": 6.73, "elapsed_time": "0:04:00", "remaining_time": "0:55:27"}
|
||||
{"current_steps": 85, "total_steps": 1188, "loss": 0.2973, "lr": 2.8235294117647063e-05, "epoch": 0.4292929292929293, "percentage": 7.15, "elapsed_time": "0:04:14", "remaining_time": "0:55:01"}
|
||||
{"current_steps": 90, "total_steps": 1188, "loss": 0.2854, "lr": 2.9915966386554626e-05, "epoch": 0.45454545454545453, "percentage": 7.58, "elapsed_time": "0:04:28", "remaining_time": "0:54:41"}
|
||||
{"current_steps": 95, "total_steps": 1188, "loss": 0.2698, "lr": 3.159663865546219e-05, "epoch": 0.4797979797979798, "percentage": 8.0, "elapsed_time": "0:04:43", "remaining_time": "0:54:22"}
|
||||
{"current_steps": 100, "total_steps": 1188, "loss": 0.2831, "lr": 3.3277310924369754e-05, "epoch": 0.5050505050505051, "percentage": 8.42, "elapsed_time": "0:04:58", "remaining_time": "0:54:02"}
|
||||
{"current_steps": 105, "total_steps": 1188, "loss": 0.2821, "lr": 3.495798319327731e-05, "epoch": 0.5303030303030303, "percentage": 8.84, "elapsed_time": "0:06:15", "remaining_time": "1:04:37"}
|
||||
{"current_steps": 110, "total_steps": 1188, "loss": 0.2799, "lr": 3.663865546218488e-05, "epoch": 0.5555555555555556, "percentage": 9.26, "elapsed_time": "0:06:30", "remaining_time": "1:03:44"}
|
||||
{"current_steps": 115, "total_steps": 1188, "loss": 0.279, "lr": 3.8319327731092444e-05, "epoch": 0.5808080808080808, "percentage": 9.68, "elapsed_time": "0:06:44", "remaining_time": "1:02:54"}
|
||||
{"current_steps": 120, "total_steps": 1188, "loss": 0.2694, "lr": 4e-05, "epoch": 0.6060606060606061, "percentage": 10.1, "elapsed_time": "0:06:58", "remaining_time": "1:02:03"}
|
||||
{"current_steps": 125, "total_steps": 1188, "loss": 0.2793, "lr": 3.999784088124753e-05, "epoch": 0.6313131313131313, "percentage": 10.52, "elapsed_time": "0:07:12", "remaining_time": "1:01:20"}
|
||||
{"current_steps": 130, "total_steps": 1188, "loss": 0.2597, "lr": 3.99913639911695e-05, "epoch": 0.6565656565656566, "percentage": 10.94, "elapsed_time": "0:07:26", "remaining_time": "1:00:34"}
|
||||
{"current_steps": 135, "total_steps": 1188, "loss": 0.2705, "lr": 3.998057072820338e-05, "epoch": 0.6818181818181818, "percentage": 11.36, "elapsed_time": "0:07:40", "remaining_time": "0:59:49"}
|
||||
{"current_steps": 140, "total_steps": 1188, "loss": 0.2753, "lr": 3.996546342274282e-05, "epoch": 0.7070707070707071, "percentage": 11.78, "elapsed_time": "0:07:54", "remaining_time": "0:59:13"}
|
||||
{"current_steps": 145, "total_steps": 1188, "loss": 0.2598, "lr": 3.9946045336634485e-05, "epoch": 0.7323232323232324, "percentage": 12.21, "elapsed_time": "0:08:09", "remaining_time": "0:58:37"}
|
||||
{"current_steps": 150, "total_steps": 1188, "loss": 0.2704, "lr": 3.9922320662473755e-05, "epoch": 0.7575757575757576, "percentage": 12.63, "elapsed_time": "0:08:23", "remaining_time": "0:58:02"}
|
||||
{"current_steps": 155, "total_steps": 1188, "loss": 0.2545, "lr": 3.989429452269951e-05, "epoch": 0.7828282828282829, "percentage": 13.05, "elapsed_time": "0:08:37", "remaining_time": "0:57:30"}
|
||||
{"current_steps": 160, "total_steps": 1188, "loss": 0.2619, "lr": 3.986197296848816e-05, "epoch": 0.8080808080808081, "percentage": 13.47, "elapsed_time": "0:08:51", "remaining_time": "0:56:54"}
|
||||
{"current_steps": 165, "total_steps": 1188, "loss": 0.2628, "lr": 3.982536297844706e-05, "epoch": 0.8333333333333334, "percentage": 13.89, "elapsed_time": "0:09:04", "remaining_time": "0:56:18"}
|
||||
{"current_steps": 170, "total_steps": 1188, "loss": 0.2588, "lr": 3.978447245710784e-05, "epoch": 0.8585858585858586, "percentage": 14.31, "elapsed_time": "0:09:18", "remaining_time": "0:55:47"}
|
||||
{"current_steps": 175, "total_steps": 1188, "loss": 0.2538, "lr": 3.973931023321962e-05, "epoch": 0.8838383838383839, "percentage": 14.73, "elapsed_time": "0:09:32", "remaining_time": "0:55:16"}
|
||||
{"current_steps": 180, "total_steps": 1188, "loss": 0.2409, "lr": 3.9689886057842866e-05, "epoch": 0.9090909090909091, "percentage": 15.15, "elapsed_time": "0:09:47", "remaining_time": "0:54:52"}
|
||||
{"current_steps": 185, "total_steps": 1188, "loss": 0.2545, "lr": 3.963621060224396e-05, "epoch": 0.9343434343434344, "percentage": 15.57, "elapsed_time": "0:10:01", "remaining_time": "0:54:21"}
|
||||
{"current_steps": 190, "total_steps": 1188, "loss": 0.2553, "lr": 3.957829545559118e-05, "epoch": 0.9595959595959596, "percentage": 15.99, "elapsed_time": "0:10:14", "remaining_time": "0:53:48"}
|
||||
{"current_steps": 195, "total_steps": 1188, "loss": 0.2546, "lr": 3.951615312245243e-05, "epoch": 0.9848484848484849, "percentage": 16.41, "elapsed_time": "0:10:29", "remaining_time": "0:53:23"}
|
||||
{"current_steps": 200, "total_steps": 1188, "loss": 0.2535, "lr": 3.9449797020095404e-05, "epoch": 1.0101010101010102, "percentage": 16.84, "elapsed_time": "0:10:43", "remaining_time": "0:52:58"}
|
||||
{"current_steps": 205, "total_steps": 1188, "loss": 0.2277, "lr": 3.937924147559059e-05, "epoch": 1.0353535353535352, "percentage": 17.26, "elapsed_time": "0:12:00", "remaining_time": "0:57:36"}
|
||||
{"current_steps": 210, "total_steps": 1188, "loss": 0.2358, "lr": 3.9304501722717925e-05, "epoch": 1.0606060606060606, "percentage": 17.68, "elapsed_time": "0:12:14", "remaining_time": "0:57:00"}
|
||||
{"current_steps": 215, "total_steps": 1188, "loss": 0.2333, "lr": 3.922559389867758e-05, "epoch": 1.0858585858585859, "percentage": 18.1, "elapsed_time": "0:12:28", "remaining_time": "0:56:25"}
|
||||
{"current_steps": 220, "total_steps": 1188, "loss": 0.2289, "lr": 3.914253504060585e-05, "epoch": 1.1111111111111112, "percentage": 18.52, "elapsed_time": "0:12:42", "remaining_time": "0:55:53"}
|
||||
{"current_steps": 225, "total_steps": 1188, "loss": 0.225, "lr": 3.90553430818965e-05, "epoch": 1.1363636363636362, "percentage": 18.94, "elapsed_time": "0:12:55", "remaining_time": "0:55:19"}
|
||||
{"current_steps": 230, "total_steps": 1188, "loss": 0.23, "lr": 3.896403684832887e-05, "epoch": 1.1616161616161615, "percentage": 19.36, "elapsed_time": "0:13:08", "remaining_time": "0:54:44"}
|
||||
{"current_steps": 235, "total_steps": 1188, "loss": 0.2314, "lr": 3.886863605400306e-05, "epoch": 1.1868686868686869, "percentage": 19.78, "elapsed_time": "0:13:22", "remaining_time": "0:54:13"}
|
||||
{"current_steps": 240, "total_steps": 1188, "loss": 0.2231, "lr": 3.876916129708347e-05, "epoch": 1.2121212121212122, "percentage": 20.2, "elapsed_time": "0:13:36", "remaining_time": "0:53:45"}
|
||||
{"current_steps": 245, "total_steps": 1188, "loss": 0.2363, "lr": 3.866563405535142e-05, "epoch": 1.2373737373737375, "percentage": 20.62, "elapsed_time": "0:13:50", "remaining_time": "0:53:17"}
|
||||
{"current_steps": 250, "total_steps": 1188, "loss": 0.2187, "lr": 3.855807668156779e-05, "epoch": 1.2626262626262625, "percentage": 21.04, "elapsed_time": "0:14:04", "remaining_time": "0:52:48"}
|
||||
{"current_steps": 255, "total_steps": 1188, "loss": 0.2273, "lr": 3.844651239864687e-05, "epoch": 1.2878787878787878, "percentage": 21.46, "elapsed_time": "0:14:18", "remaining_time": "0:52:21"}
|
||||
{"current_steps": 260, "total_steps": 1188, "loss": 0.227, "lr": 3.8330965294642186e-05, "epoch": 1.3131313131313131, "percentage": 21.89, "elapsed_time": "0:14:32", "remaining_time": "0:51:52"}
|
||||
{"current_steps": 265, "total_steps": 1188, "loss": 0.2331, "lr": 3.821146031754565e-05, "epoch": 1.3383838383838385, "percentage": 22.31, "elapsed_time": "0:14:46", "remaining_time": "0:51:26"}
|
||||
{"current_steps": 270, "total_steps": 1188, "loss": 0.2198, "lr": 3.808802326990096e-05, "epoch": 1.3636363636363638, "percentage": 22.73, "elapsed_time": "0:15:00", "remaining_time": "0:51:01"}
|
||||
{"current_steps": 275, "total_steps": 1188, "loss": 0.2212, "lr": 3.7960680803232544e-05, "epoch": 1.3888888888888888, "percentage": 23.15, "elapsed_time": "0:15:14", "remaining_time": "0:50:35"}
|
||||
{"current_steps": 280, "total_steps": 1188, "loss": 0.2239, "lr": 3.782946041229119e-05, "epoch": 1.4141414141414141, "percentage": 23.57, "elapsed_time": "0:15:27", "remaining_time": "0:50:07"}
|
||||
{"current_steps": 285, "total_steps": 1188, "loss": 0.234, "lr": 3.769439042911758e-05, "epoch": 1.4393939393939394, "percentage": 23.99, "elapsed_time": "0:15:40", "remaining_time": "0:49:39"}
|
||||
{"current_steps": 290, "total_steps": 1188, "loss": 0.2173, "lr": 3.755550001692506e-05, "epoch": 1.4646464646464645, "percentage": 24.41, "elapsed_time": "0:15:54", "remaining_time": "0:49:15"}
|
||||
{"current_steps": 295, "total_steps": 1188, "loss": 0.2105, "lr": 3.7412819163802986e-05, "epoch": 1.4898989898989898, "percentage": 24.83, "elapsed_time": "0:16:07", "remaining_time": "0:48:49"}
|
||||
{"current_steps": 300, "total_steps": 1188, "loss": 0.2359, "lr": 3.726637867624191e-05, "epoch": 1.5151515151515151, "percentage": 25.25, "elapsed_time": "0:16:21", "remaining_time": "0:48:25"}
|
||||
{"current_steps": 305, "total_steps": 1188, "loss": 0.2152, "lr": 3.711621017248213e-05, "epoch": 1.5404040404040404, "percentage": 25.67, "elapsed_time": "0:17:38", "remaining_time": "0:51:05"}
|
||||
{"current_steps": 310, "total_steps": 1188, "loss": 0.2259, "lr": 3.6962346075686876e-05, "epoch": 1.5656565656565657, "percentage": 26.09, "elapsed_time": "0:17:54", "remaining_time": "0:50:41"}
|
||||
{"current_steps": 315, "total_steps": 1188, "loss": 0.2276, "lr": 3.680481960694183e-05, "epoch": 1.5909090909090908, "percentage": 26.52, "elapsed_time": "0:18:07", "remaining_time": "0:50:14"}
|
||||
{"current_steps": 320, "total_steps": 1188, "loss": 0.2275, "lr": 3.6643664778082254e-05, "epoch": 1.6161616161616161, "percentage": 26.94, "elapsed_time": "0:18:21", "remaining_time": "0:49:47"}
|
||||
{"current_steps": 325, "total_steps": 1188, "loss": 0.2193, "lr": 3.6478916384349465e-05, "epoch": 1.6414141414141414, "percentage": 27.36, "elapsed_time": "0:18:34", "remaining_time": "0:49:20"}
|
||||
{"current_steps": 330, "total_steps": 1188, "loss": 0.2243, "lr": 3.631060999687809e-05, "epoch": 1.6666666666666665, "percentage": 27.78, "elapsed_time": "0:18:48", "remaining_time": "0:48:54"}
|
||||
{"current_steps": 335, "total_steps": 1188, "loss": 0.2132, "lr": 3.613878195501586e-05, "epoch": 1.691919191919192, "percentage": 28.2, "elapsed_time": "0:19:02", "remaining_time": "0:48:28"}
|
||||
{"current_steps": 340, "total_steps": 1188, "loss": 0.2148, "lr": 3.596346935847752e-05, "epoch": 1.7171717171717171, "percentage": 28.62, "elapsed_time": "0:19:16", "remaining_time": "0:48:03"}
|
||||
{"current_steps": 345, "total_steps": 1188, "loss": 0.225, "lr": 3.578471005933454e-05, "epoch": 1.7424242424242424, "percentage": 29.04, "elapsed_time": "0:19:30", "remaining_time": "0:47:40"}
|
||||
{"current_steps": 350, "total_steps": 1188, "loss": 0.2148, "lr": 3.5602542653842416e-05, "epoch": 1.7676767676767677, "percentage": 29.46, "elapsed_time": "0:19:43", "remaining_time": "0:47:14"}
|
||||
{"current_steps": 355, "total_steps": 1188, "loss": 0.2203, "lr": 3.541700647410728e-05, "epoch": 1.7929292929292928, "percentage": 29.88, "elapsed_time": "0:19:57", "remaining_time": "0:46:49"}
|
||||
{"current_steps": 360, "total_steps": 1188, "loss": 0.2307, "lr": 3.522814157959362e-05, "epoch": 1.8181818181818183, "percentage": 30.3, "elapsed_time": "0:20:11", "remaining_time": "0:46:26"}
|
||||
{"current_steps": 365, "total_steps": 1188, "loss": 0.23, "lr": 3.5035988748474974e-05, "epoch": 1.8434343434343434, "percentage": 30.72, "elapsed_time": "0:20:25", "remaining_time": "0:46:02"}
|
||||
{"current_steps": 370, "total_steps": 1188, "loss": 0.2128, "lr": 3.484058946882946e-05, "epoch": 1.8686868686868687, "percentage": 31.14, "elapsed_time": "0:20:38", "remaining_time": "0:45:38"}
|
||||
{"current_steps": 375, "total_steps": 1188, "loss": 0.221, "lr": 3.4641985929681954e-05, "epoch": 1.893939393939394, "percentage": 31.57, "elapsed_time": "0:20:52", "remaining_time": "0:45:15"}
|
||||
{"current_steps": 380, "total_steps": 1188, "loss": 0.2149, "lr": 3.4440221011895026e-05, "epoch": 1.9191919191919191, "percentage": 31.99, "elapsed_time": "0:21:06", "remaining_time": "0:44:52"}
|
||||
{"current_steps": 385, "total_steps": 1188, "loss": 0.2226, "lr": 3.423533827891044e-05, "epoch": 1.9444444444444444, "percentage": 32.41, "elapsed_time": "0:21:18", "remaining_time": "0:44:27"}
|
||||
{"current_steps": 390, "total_steps": 1188, "loss": 0.2269, "lr": 3.402738196734327e-05, "epoch": 1.9696969696969697, "percentage": 32.83, "elapsed_time": "0:21:32", "remaining_time": "0:44:04"}
|
||||
{"current_steps": 395, "total_steps": 1188, "loss": 0.2196, "lr": 3.381639697743073e-05, "epoch": 1.9949494949494948, "percentage": 33.25, "elapsed_time": "0:21:46", "remaining_time": "0:43:43"}
|
||||
{"current_steps": 400, "total_steps": 1188, "loss": 0.1951, "lr": 3.3602428863337625e-05, "epoch": 2.0202020202020203, "percentage": 33.67, "elapsed_time": "0:22:00", "remaining_time": "0:43:21"}
|
||||
{"current_steps": 405, "total_steps": 1188, "loss": 0.1904, "lr": 3.338552382332073e-05, "epoch": 2.0454545454545454, "percentage": 34.09, "elapsed_time": "0:23:22", "remaining_time": "0:45:12"}
|
||||
{"current_steps": 410, "total_steps": 1188, "loss": 0.1952, "lr": 3.3165728689753976e-05, "epoch": 2.0707070707070705, "percentage": 34.51, "elapsed_time": "0:23:36", "remaining_time": "0:44:48"}
|
||||
{"current_steps": 415, "total_steps": 1188, "loss": 0.1938, "lr": 3.2943090919016815e-05, "epoch": 2.095959595959596, "percentage": 34.93, "elapsed_time": "0:23:50", "remaining_time": "0:44:24"}
|
||||
{"current_steps": 420, "total_steps": 1188, "loss": 0.1834, "lr": 3.2717658581247844e-05, "epoch": 2.121212121212121, "percentage": 35.35, "elapsed_time": "0:24:05", "remaining_time": "0:44:03"}
|
||||
{"current_steps": 425, "total_steps": 1188, "loss": 0.1995, "lr": 3.248948034996583e-05, "epoch": 2.1464646464646466, "percentage": 35.77, "elapsed_time": "0:24:18", "remaining_time": "0:43:39"}
|
||||
{"current_steps": 430, "total_steps": 1188, "loss": 0.184, "lr": 3.2258605491560606e-05, "epoch": 2.1717171717171717, "percentage": 36.2, "elapsed_time": "0:24:32", "remaining_time": "0:43:15"}
|
||||
{"current_steps": 435, "total_steps": 1188, "loss": 0.1889, "lr": 3.2025083854655776e-05, "epoch": 2.196969696969697, "percentage": 36.62, "elapsed_time": "0:24:45", "remaining_time": "0:42:51"}
|
||||
{"current_steps": 440, "total_steps": 1188, "loss": 0.1922, "lr": 3.178896585934588e-05, "epoch": 2.2222222222222223, "percentage": 37.04, "elapsed_time": "0:24:58", "remaining_time": "0:42:28"}
|
||||
{"current_steps": 445, "total_steps": 1188, "loss": 0.181, "lr": 3.1550302486310076e-05, "epoch": 2.2474747474747474, "percentage": 37.46, "elapsed_time": "0:25:11", "remaining_time": "0:42:04"}
|
||||
{"current_steps": 450, "total_steps": 1188, "loss": 0.1932, "lr": 3.130914526580478e-05, "epoch": 2.2727272727272725, "percentage": 37.88, "elapsed_time": "0:25:24", "remaining_time": "0:41:40"}
|
||||
{"current_steps": 455, "total_steps": 1188, "loss": 0.1943, "lr": 3.10655462665377e-05, "epoch": 2.297979797979798, "percentage": 38.3, "elapsed_time": "0:25:38", "remaining_time": "0:41:18"}
|
||||
{"current_steps": 460, "total_steps": 1188, "loss": 0.1858, "lr": 3.0819558084425574e-05, "epoch": 2.323232323232323, "percentage": 38.72, "elapsed_time": "0:25:52", "remaining_time": "0:40:56"}
|
||||
{"current_steps": 465, "total_steps": 1188, "loss": 0.1912, "lr": 3.0571233831238093e-05, "epoch": 2.3484848484848486, "percentage": 39.14, "elapsed_time": "0:26:06", "remaining_time": "0:40:35"}
|
||||
{"current_steps": 470, "total_steps": 1188, "loss": 0.1907, "lr": 3.032062712313044e-05, "epoch": 2.3737373737373737, "percentage": 39.56, "elapsed_time": "0:26:20", "remaining_time": "0:40:13"}
|
||||
{"current_steps": 475, "total_steps": 1188, "loss": 0.1963, "lr": 3.0067792069066902e-05, "epoch": 2.398989898989899, "percentage": 39.98, "elapsed_time": "0:26:34", "remaining_time": "0:39:53"}
|
||||
{"current_steps": 480, "total_steps": 1188, "loss": 0.2008, "lr": 2.9812783259138133e-05, "epoch": 2.4242424242424243, "percentage": 40.4, "elapsed_time": "0:26:48", "remaining_time": "0:39:32"}
|
||||
{"current_steps": 485, "total_steps": 1188, "loss": 0.1868, "lr": 2.955565575277449e-05, "epoch": 2.4494949494949494, "percentage": 40.82, "elapsed_time": "0:27:01", "remaining_time": "0:39:11"}
|
||||
{"current_steps": 490, "total_steps": 1188, "loss": 0.1896, "lr": 2.929646506685805e-05, "epoch": 2.474747474747475, "percentage": 41.25, "elapsed_time": "0:27:14", "remaining_time": "0:38:48"}
|
||||
{"current_steps": 495, "total_steps": 1188, "loss": 0.1853, "lr": 2.9035267163735856e-05, "epoch": 2.5, "percentage": 41.67, "elapsed_time": "0:27:27", "remaining_time": "0:38:26"}
|
||||
{"current_steps": 500, "total_steps": 1188, "loss": 0.1917, "lr": 2.8772118439136972e-05, "epoch": 2.525252525252525, "percentage": 42.09, "elapsed_time": "0:27:41", "remaining_time": "0:38:06"}
|
||||
{"current_steps": 505, "total_steps": 1188, "loss": 0.2, "lr": 2.8507075709996015e-05, "epoch": 2.5505050505050506, "percentage": 42.51, "elapsed_time": "0:29:05", "remaining_time": "0:39:20"}
|
||||
{"current_steps": 510, "total_steps": 1188, "loss": 0.1841, "lr": 2.8240196202185636e-05, "epoch": 2.5757575757575757, "percentage": 42.93, "elapsed_time": "0:29:18", "remaining_time": "0:38:57"}
|
||||
{"current_steps": 515, "total_steps": 1188, "loss": 0.2015, "lr": 2.797153753816084e-05, "epoch": 2.601010101010101, "percentage": 43.35, "elapsed_time": "0:29:31", "remaining_time": "0:38:35"}
|
||||
{"current_steps": 520, "total_steps": 1188, "loss": 0.1847, "lr": 2.770115772451758e-05, "epoch": 2.6262626262626263, "percentage": 43.77, "elapsed_time": "0:29:45", "remaining_time": "0:38:13"}
|
||||
{"current_steps": 525, "total_steps": 1188, "loss": 0.1868, "lr": 2.7429115139468443e-05, "epoch": 2.6515151515151514, "percentage": 44.19, "elapsed_time": "0:29:58", "remaining_time": "0:37:51"}
|
||||
{"current_steps": 530, "total_steps": 1188, "loss": 0.1955, "lr": 2.7155468520238116e-05, "epoch": 2.676767676767677, "percentage": 44.61, "elapsed_time": "0:30:13", "remaining_time": "0:37:30"}
|
||||
{"current_steps": 535, "total_steps": 1188, "loss": 0.1881, "lr": 2.6880276950381316e-05, "epoch": 2.702020202020202, "percentage": 45.03, "elapsed_time": "0:30:27", "remaining_time": "0:37:10"}
|
||||
{"current_steps": 540, "total_steps": 1188, "loss": 0.1805, "lr": 2.6603599847025935e-05, "epoch": 2.7272727272727275, "percentage": 45.45, "elapsed_time": "0:30:39", "remaining_time": "0:36:47"}
|
||||
{"current_steps": 545, "total_steps": 1188, "loss": 0.191, "lr": 2.63254969480442e-05, "epoch": 2.7525252525252526, "percentage": 45.88, "elapsed_time": "0:30:53", "remaining_time": "0:36:26"}
|
||||
{"current_steps": 550, "total_steps": 1188, "loss": 0.1875, "lr": 2.6046028299154545e-05, "epoch": 2.7777777777777777, "percentage": 46.3, "elapsed_time": "0:31:08", "remaining_time": "0:36:07"}
|
||||
{"current_steps": 555, "total_steps": 1188, "loss": 0.1886, "lr": 2.5765254240957024e-05, "epoch": 2.8030303030303028, "percentage": 46.72, "elapsed_time": "0:31:21", "remaining_time": "0:35:46"}
|
||||
{"current_steps": 560, "total_steps": 1188, "loss": 0.1867, "lr": 2.5483235395905056e-05, "epoch": 2.8282828282828283, "percentage": 47.14, "elapsed_time": "0:31:34", "remaining_time": "0:35:24"}
|
||||
{"current_steps": 565, "total_steps": 1188, "loss": 0.1894, "lr": 2.5200032655216343e-05, "epoch": 2.8535353535353534, "percentage": 47.56, "elapsed_time": "0:31:47", "remaining_time": "0:35:03"}
|
||||
{"current_steps": 570, "total_steps": 1188, "loss": 0.1858, "lr": 2.4915707165725694e-05, "epoch": 2.878787878787879, "percentage": 47.98, "elapsed_time": "0:32:00", "remaining_time": "0:34:42"}
|
||||
{"current_steps": 575, "total_steps": 1188, "loss": 0.1847, "lr": 2.4630320316682724e-05, "epoch": 2.904040404040404, "percentage": 48.4, "elapsed_time": "0:32:13", "remaining_time": "0:34:21"}
|
||||
{"current_steps": 580, "total_steps": 1188, "loss": 0.1856, "lr": 2.4343933726497183e-05, "epoch": 2.929292929292929, "percentage": 48.82, "elapsed_time": "0:32:26", "remaining_time": "0:34:00"}
|
||||
{"current_steps": 585, "total_steps": 1188, "loss": 0.1887, "lr": 2.4056609229434812e-05, "epoch": 2.9545454545454546, "percentage": 49.24, "elapsed_time": "0:32:39", "remaining_time": "0:33:39"}
|
||||
{"current_steps": 590, "total_steps": 1188, "loss": 0.1867, "lr": 2.376840886226656e-05, "epoch": 2.9797979797979797, "percentage": 49.66, "elapsed_time": "0:32:51", "remaining_time": "0:33:18"}
|
||||
{"current_steps": 595, "total_steps": 1188, "loss": 0.1831, "lr": 2.347939485087416e-05, "epoch": 3.005050505050505, "percentage": 50.08, "elapsed_time": "0:33:04", "remaining_time": "0:32:58"}
|
||||
{"current_steps": 600, "total_steps": 1188, "loss": 0.157, "lr": 2.3189629596814788e-05, "epoch": 3.0303030303030303, "percentage": 50.51, "elapsed_time": "0:33:18", "remaining_time": "0:32:39"}
|
||||
{"current_steps": 605, "total_steps": 1188, "loss": 0.1605, "lr": 2.2899175663847823e-05, "epoch": 3.0555555555555554, "percentage": 50.93, "elapsed_time": "0:34:39", "remaining_time": "0:33:23"}
|
||||
{"current_steps": 610, "total_steps": 1188, "loss": 0.1609, "lr": 2.2608095764426602e-05, "epoch": 3.080808080808081, "percentage": 51.35, "elapsed_time": "0:34:52", "remaining_time": "0:33:02"}
|
||||
{"current_steps": 615, "total_steps": 1188, "loss": 0.1649, "lr": 2.2316452746158063e-05, "epoch": 3.106060606060606, "percentage": 51.77, "elapsed_time": "0:35:06", "remaining_time": "0:32:42"}
|
||||
{"current_steps": 620, "total_steps": 1188, "loss": 0.161, "lr": 2.2024309578233174e-05, "epoch": 3.1313131313131315, "percentage": 52.19, "elapsed_time": "0:35:20", "remaining_time": "0:32:22"}
|
||||
{"current_steps": 625, "total_steps": 1188, "loss": 0.1574, "lr": 2.1731729337831173e-05, "epoch": 3.1565656565656566, "percentage": 52.61, "elapsed_time": "0:35:33", "remaining_time": "0:32:02"}
|
||||
{"current_steps": 630, "total_steps": 1188, "loss": 0.165, "lr": 2.143877519650042e-05, "epoch": 3.1818181818181817, "percentage": 53.03, "elapsed_time": "0:35:45", "remaining_time": "0:31:40"}
|
||||
{"current_steps": 635, "total_steps": 1188, "loss": 0.1654, "lr": 2.1145510406518928e-05, "epoch": 3.207070707070707, "percentage": 53.45, "elapsed_time": "0:36:00", "remaining_time": "0:31:21"}
|
||||
{"current_steps": 640, "total_steps": 1188, "loss": 0.1603, "lr": 2.0851998287237452e-05, "epoch": 3.2323232323232323, "percentage": 53.87, "elapsed_time": "0:36:12", "remaining_time": "0:31:00"}
|
||||
{"current_steps": 645, "total_steps": 1188, "loss": 0.1568, "lr": 2.0558302211408075e-05, "epoch": 3.257575757575758, "percentage": 54.29, "elapsed_time": "0:36:27", "remaining_time": "0:30:41"}
|
||||
{"current_steps": 650, "total_steps": 1188, "loss": 0.1657, "lr": 2.0264485591501272e-05, "epoch": 3.282828282828283, "percentage": 54.71, "elapsed_time": "0:36:41", "remaining_time": "0:30:21"}
|
||||
{"current_steps": 655, "total_steps": 1188, "loss": 0.1626, "lr": 1.9970611866014432e-05, "epoch": 3.308080808080808, "percentage": 55.13, "elapsed_time": "0:36:53", "remaining_time": "0:30:01"}
|
||||
{"current_steps": 660, "total_steps": 1188, "loss": 0.1581, "lr": 1.967674448577471e-05, "epoch": 3.3333333333333335, "percentage": 55.56, "elapsed_time": "0:37:06", "remaining_time": "0:29:41"}
|
||||
{"current_steps": 665, "total_steps": 1188, "loss": 0.1586, "lr": 1.9382946900239247e-05, "epoch": 3.3585858585858586, "percentage": 55.98, "elapsed_time": "0:37:18", "remaining_time": "0:29:20"}
|
||||
{"current_steps": 670, "total_steps": 1188, "loss": 0.171, "lr": 1.9089282543795692e-05, "epoch": 3.3838383838383836, "percentage": 56.4, "elapsed_time": "0:37:32", "remaining_time": "0:29:01"}
|
||||
{"current_steps": 675, "total_steps": 1188, "loss": 0.1549, "lr": 1.879581482206592e-05, "epoch": 3.409090909090909, "percentage": 56.82, "elapsed_time": "0:37:45", "remaining_time": "0:28:41"}
|
||||
{"current_steps": 680, "total_steps": 1188, "loss": 0.1645, "lr": 1.8502607098216056e-05, "epoch": 3.4343434343434343, "percentage": 57.24, "elapsed_time": "0:37:59", "remaining_time": "0:28:22"}
|
||||
{"current_steps": 685, "total_steps": 1188, "loss": 0.1636, "lr": 1.8209722679275602e-05, "epoch": 3.45959595959596, "percentage": 57.66, "elapsed_time": "0:38:13", "remaining_time": "0:28:03"}
|
||||
{"current_steps": 690, "total_steps": 1188, "loss": 0.1615, "lr": 1.791722480246868e-05, "epoch": 3.484848484848485, "percentage": 58.08, "elapsed_time": "0:38:25", "remaining_time": "0:27:44"}
|
||||
{"current_steps": 695, "total_steps": 1188, "loss": 0.1592, "lr": 1.762517662156037e-05, "epoch": 3.51010101010101, "percentage": 58.5, "elapsed_time": "0:38:38", "remaining_time": "0:27:24"}
|
||||
{"current_steps": 700, "total_steps": 1188, "loss": 0.1648, "lr": 1.733364119322109e-05, "epoch": 3.5353535353535355, "percentage": 58.92, "elapsed_time": "0:38:51", "remaining_time": "0:27:05"}
|
||||
{"current_steps": 705, "total_steps": 1188, "loss": 0.1683, "lr": 1.704268146341185e-05, "epoch": 3.5606060606060606, "percentage": 59.34, "elapsed_time": "0:40:07", "remaining_time": "0:27:29"}
|
||||
{"current_steps": 710, "total_steps": 1188, "loss": 0.1626, "lr": 1.675236025379355e-05, "epoch": 3.5858585858585856, "percentage": 59.76, "elapsed_time": "0:40:21", "remaining_time": "0:27:10"}
|
||||
{"current_steps": 715, "total_steps": 1188, "loss": 0.1628, "lr": 1.6462740248162988e-05, "epoch": 3.611111111111111, "percentage": 60.19, "elapsed_time": "0:40:34", "remaining_time": "0:26:50"}
|
||||
{"current_steps": 720, "total_steps": 1188, "loss": 0.1579, "lr": 1.6173883978918682e-05, "epoch": 3.6363636363636362, "percentage": 60.61, "elapsed_time": "0:40:46", "remaining_time": "0:26:30"}
|
||||
{"current_steps": 725, "total_steps": 1188, "loss": 0.1606, "lr": 1.5885853813559392e-05, "epoch": 3.6616161616161618, "percentage": 61.03, "elapsed_time": "0:41:00", "remaining_time": "0:26:11"}
|
||||
{"current_steps": 730, "total_steps": 1188, "loss": 0.1639, "lr": 1.5598711941218265e-05, "epoch": 3.686868686868687, "percentage": 61.45, "elapsed_time": "0:41:14", "remaining_time": "0:25:52"}
|
||||
{"current_steps": 735, "total_steps": 1188, "loss": 0.1686, "lr": 1.531252035923541e-05, "epoch": 3.712121212121212, "percentage": 61.87, "elapsed_time": "0:41:28", "remaining_time": "0:25:34"}
|
||||
{"current_steps": 740, "total_steps": 1188, "loss": 0.1652, "lr": 1.5027340859771972e-05, "epoch": 3.7373737373737375, "percentage": 62.29, "elapsed_time": "0:41:42", "remaining_time": "0:25:15"}
|
||||
{"current_steps": 745, "total_steps": 1188, "loss": 0.1628, "lr": 1.4743235016468474e-05, "epoch": 3.7626262626262625, "percentage": 62.71, "elapsed_time": "0:41:56", "remaining_time": "0:24:56"}
|
||||
{"current_steps": 750, "total_steps": 1188, "loss": 0.1614, "lr": 1.4460264171150296e-05, "epoch": 3.787878787878788, "percentage": 63.13, "elapsed_time": "0:42:09", "remaining_time": "0:24:37"}
|
||||
{"current_steps": 755, "total_steps": 1188, "loss": 0.1659, "lr": 1.4178489420583297e-05, "epoch": 3.813131313131313, "percentage": 63.55, "elapsed_time": "0:42:23", "remaining_time": "0:24:18"}
|
||||
{"current_steps": 760, "total_steps": 1188, "loss": 0.1595, "lr": 1.3897971603282278e-05, "epoch": 3.8383838383838382, "percentage": 63.97, "elapsed_time": "0:42:35", "remaining_time": "0:23:59"}
|
||||
{"current_steps": 765, "total_steps": 1188, "loss": 0.166, "lr": 1.36187712863752e-05, "epoch": 3.8636363636363638, "percentage": 64.39, "elapsed_time": "0:42:49", "remaining_time": "0:23:40"}
|
||||
{"current_steps": 770, "total_steps": 1188, "loss": 0.1599, "lr": 1.3340948752526069e-05, "epoch": 3.888888888888889, "percentage": 64.81, "elapsed_time": "0:43:02", "remaining_time": "0:23:22"}
|
||||
{"current_steps": 775, "total_steps": 1188, "loss": 0.1596, "lr": 1.3064563986919142e-05, "epoch": 3.9141414141414144, "percentage": 65.24, "elapsed_time": "0:43:15", "remaining_time": "0:23:03"}
|
||||
{"current_steps": 780, "total_steps": 1188, "loss": 0.1628, "lr": 1.278967666430745e-05, "epoch": 3.9393939393939394, "percentage": 65.66, "elapsed_time": "0:43:29", "remaining_time": "0:22:45"}
|
||||
{"current_steps": 785, "total_steps": 1188, "loss": 0.1641, "lr": 1.2516346136128318e-05, "epoch": 3.9646464646464645, "percentage": 66.08, "elapsed_time": "0:43:43", "remaining_time": "0:22:27"}
|
||||
{"current_steps": 790, "total_steps": 1188, "loss": 0.1634, "lr": 1.2244631417688632e-05, "epoch": 3.98989898989899, "percentage": 66.5, "elapsed_time": "0:43:58", "remaining_time": "0:22:09"}
|
||||
{"current_steps": 795, "total_steps": 1188, "loss": 0.1509, "lr": 1.197459117542278e-05, "epoch": 4.015151515151516, "percentage": 66.92, "elapsed_time": "0:44:12", "remaining_time": "0:21:51"}
|
||||
{"current_steps": 800, "total_steps": 1188, "loss": 0.1365, "lr": 1.170628371422587e-05, "epoch": 4.040404040404041, "percentage": 67.34, "elapsed_time": "0:44:25", "remaining_time": "0:21:32"}
|
||||
{"current_steps": 805, "total_steps": 1188, "loss": 0.1454, "lr": 1.1439766964864995e-05, "epoch": 4.065656565656566, "percentage": 67.76, "elapsed_time": "0:45:55", "remaining_time": "0:21:51"}
|
||||
{"current_steps": 810, "total_steps": 1188, "loss": 0.1405, "lr": 1.117509847147128e-05, "epoch": 4.090909090909091, "percentage": 68.18, "elapsed_time": "0:46:08", "remaining_time": "0:21:32"}
|
||||
{"current_steps": 815, "total_steps": 1188, "loss": 0.138, "lr": 1.0912335379115469e-05, "epoch": 4.116161616161616, "percentage": 68.6, "elapsed_time": "0:46:22", "remaining_time": "0:21:13"}
|
||||
{"current_steps": 820, "total_steps": 1188, "loss": 0.1441, "lr": 1.0651534421469569e-05, "epoch": 4.141414141414141, "percentage": 69.02, "elapsed_time": "0:46:33", "remaining_time": "0:20:53"}
|
||||
{"current_steps": 825, "total_steps": 1188, "loss": 0.1423, "lr": 1.0392751908557406e-05, "epoch": 4.166666666666667, "percentage": 69.44, "elapsed_time": "0:46:47", "remaining_time": "0:20:35"}
|
||||
{"current_steps": 830, "total_steps": 1188, "loss": 0.1385, "lr": 1.013604371459663e-05, "epoch": 4.191919191919192, "percentage": 69.87, "elapsed_time": "0:47:01", "remaining_time": "0:20:16"}
|
||||
{"current_steps": 835, "total_steps": 1188, "loss": 0.1434, "lr": 9.881465265934802e-06, "epoch": 4.217171717171717, "percentage": 70.29, "elapsed_time": "0:47:14", "remaining_time": "0:19:58"}
|
||||
{"current_steps": 840, "total_steps": 1188, "loss": 0.1395, "lr": 9.62907152908215e-06, "epoch": 4.242424242424242, "percentage": 70.71, "elapsed_time": "0:47:27", "remaining_time": "0:19:39"}
|
||||
{"current_steps": 845, "total_steps": 1188, "loss": 0.145, "lr": 9.378916998843716e-06, "epoch": 4.267676767676767, "percentage": 71.13, "elapsed_time": "0:47:39", "remaining_time": "0:19:20"}
|
||||
{"current_steps": 850, "total_steps": 1188, "loss": 0.1407, "lr": 9.13105568655322e-06, "epoch": 4.292929292929293, "percentage": 71.55, "elapsed_time": "0:47:53", "remaining_time": "0:19:02"}
|
||||
{"current_steps": 855, "total_steps": 1188, "loss": 0.1433, "lr": 8.885541108411386e-06, "epoch": 4.318181818181818, "percentage": 71.97, "elapsed_time": "0:48:05", "remaining_time": "0:18:43"}
|
||||
{"current_steps": 860, "total_steps": 1188, "loss": 0.146, "lr": 8.642426273931202e-06, "epoch": 4.343434343434343, "percentage": 72.39, "elapsed_time": "0:48:19", "remaining_time": "0:18:25"}
|
||||
{"current_steps": 865, "total_steps": 1188, "loss": 0.1386, "lr": 8.40176367449247e-06, "epoch": 4.3686868686868685, "percentage": 72.81, "elapsed_time": "0:48:32", "remaining_time": "0:18:07"}
|
||||
{"current_steps": 870, "total_steps": 1188, "loss": 0.1461, "lr": 8.16360527200833e-06, "epoch": 4.393939393939394, "percentage": 73.23, "elapsed_time": "0:48:45", "remaining_time": "0:17:49"}
|
||||
{"current_steps": 875, "total_steps": 1188, "loss": 0.1456, "lr": 7.928002487706077e-06, "epoch": 4.41919191919192, "percentage": 73.65, "elapsed_time": "0:48:57", "remaining_time": "0:17:30"}
|
||||
{"current_steps": 880, "total_steps": 1188, "loss": 0.1423, "lr": 7.69500619102469e-06, "epoch": 4.444444444444445, "percentage": 74.07, "elapsed_time": "0:49:10", "remaining_time": "0:17:12"}
|
||||
{"current_steps": 885, "total_steps": 1188, "loss": 0.1453, "lr": 7.464666688631497e-06, "epoch": 4.46969696969697, "percentage": 74.49, "elapsed_time": "0:49:23", "remaining_time": "0:16:54"}
|
||||
{"current_steps": 890, "total_steps": 1188, "loss": 0.1366, "lr": 7.237033713560415e-06, "epoch": 4.494949494949495, "percentage": 74.92, "elapsed_time": "0:49:36", "remaining_time": "0:16:36"}
|
||||
{"current_steps": 895, "total_steps": 1188, "loss": 0.1416, "lr": 7.01215641447395e-06, "epoch": 4.52020202020202, "percentage": 75.34, "elapsed_time": "0:49:48", "remaining_time": "0:16:18"}
|
||||
{"current_steps": 900, "total_steps": 1188, "loss": 0.144, "lr": 6.790083345051457e-06, "epoch": 4.545454545454545, "percentage": 75.76, "elapsed_time": "0:50:00", "remaining_time": "0:16:00"}
|
||||
{"current_steps": 905, "total_steps": 1188, "loss": 0.142, "lr": 6.570862453505793e-06, "epoch": 4.570707070707071, "percentage": 76.18, "elapsed_time": "0:50:53", "remaining_time": "0:15:54"}
|
||||
{"current_steps": 910, "total_steps": 1188, "loss": 0.1398, "lr": 6.35454107223074e-06, "epoch": 4.595959595959596, "percentage": 76.6, "elapsed_time": "0:51:07", "remaining_time": "0:15:37"}
|
||||
{"current_steps": 915, "total_steps": 1188, "loss": 0.1419, "lr": 6.141165907581395e-06, "epoch": 4.621212121212121, "percentage": 77.02, "elapsed_time": "0:51:21", "remaining_time": "0:15:19"}
|
||||
{"current_steps": 920, "total_steps": 1188, "loss": 0.138, "lr": 5.9307830297896755e-06, "epoch": 4.646464646464646, "percentage": 77.44, "elapsed_time": "0:51:34", "remaining_time": "0:15:01"}
|
||||
{"current_steps": 925, "total_steps": 1188, "loss": 0.1378, "lr": 5.723437863017256e-06, "epoch": 4.671717171717171, "percentage": 77.86, "elapsed_time": "0:51:48", "remaining_time": "0:14:43"}
|
||||
{"current_steps": 930, "total_steps": 1188, "loss": 0.138, "lr": 5.519175175547919e-06, "epoch": 4.696969696969697, "percentage": 78.28, "elapsed_time": "0:52:00", "remaining_time": "0:14:25"}
|
||||
{"current_steps": 935, "total_steps": 1188, "loss": 0.1466, "lr": 5.318039070121557e-06, "epoch": 4.722222222222222, "percentage": 78.7, "elapsed_time": "0:52:14", "remaining_time": "0:14:08"}
|
||||
{"current_steps": 940, "total_steps": 1188, "loss": 0.1371, "lr": 5.120072974411863e-06, "epoch": 4.747474747474747, "percentage": 79.12, "elapsed_time": "0:52:27", "remaining_time": "0:13:50"}
|
||||
{"current_steps": 945, "total_steps": 1188, "loss": 0.1408, "lr": 4.92531963164981e-06, "epoch": 4.7727272727272725, "percentage": 79.55, "elapsed_time": "0:52:41", "remaining_time": "0:13:33"}
|
||||
{"current_steps": 950, "total_steps": 1188, "loss": 0.1377, "lr": 4.733821091394841e-06, "epoch": 4.797979797979798, "percentage": 79.97, "elapsed_time": "0:52:54", "remaining_time": "0:13:15"}
|
||||
{"current_steps": 955, "total_steps": 1188, "loss": 0.1341, "lr": 4.5456187004558806e-06, "epoch": 4.8232323232323235, "percentage": 80.39, "elapsed_time": "0:53:08", "remaining_time": "0:12:57"}
|
||||
{"current_steps": 960, "total_steps": 1188, "loss": 0.1415, "lr": 4.360753093964094e-06, "epoch": 4.848484848484849, "percentage": 80.81, "elapsed_time": "0:53:22", "remaining_time": "0:12:40"}
|
||||
{"current_steps": 965, "total_steps": 1188, "loss": 0.1474, "lr": 4.179264186599239e-06, "epoch": 4.873737373737374, "percentage": 81.23, "elapsed_time": "0:53:36", "remaining_time": "0:12:23"}
|
||||
{"current_steps": 970, "total_steps": 1188, "loss": 0.1362, "lr": 4.001191163971645e-06, "epoch": 4.898989898989899, "percentage": 81.65, "elapsed_time": "0:53:49", "remaining_time": "0:12:05"}
|
||||
{"current_steps": 975, "total_steps": 1188, "loss": 0.1436, "lr": 3.826572474161565e-06, "epoch": 4.924242424242424, "percentage": 82.07, "elapsed_time": "0:54:02", "remaining_time": "0:11:48"}
|
||||
{"current_steps": 980, "total_steps": 1188, "loss": 0.1378, "lr": 3.65544581941776e-06, "epoch": 4.94949494949495, "percentage": 82.49, "elapsed_time": "0:54:14", "remaining_time": "0:11:30"}
|
||||
{"current_steps": 985, "total_steps": 1188, "loss": 0.1428, "lr": 3.487848148017161e-06, "epoch": 4.974747474747475, "percentage": 82.91, "elapsed_time": "0:54:28", "remaining_time": "0:11:13"}
|
||||
{"current_steps": 990, "total_steps": 1188, "loss": 0.1371, "lr": 3.3238156462872937e-06, "epoch": 5.0, "percentage": 83.33, "elapsed_time": "0:54:41", "remaining_time": "0:10:56"}
|
||||
{"current_steps": 995, "total_steps": 1188, "loss": 0.1309, "lr": 3.1633837307932037e-06, "epoch": 5.025252525252525, "percentage": 83.75, "elapsed_time": "0:54:54", "remaining_time": "0:10:39"}
|
||||
{"current_steps": 1000, "total_steps": 1188, "loss": 0.1292, "lr": 3.0065870406906094e-06, "epoch": 5.05050505050505, "percentage": 84.18, "elapsed_time": "0:55:08", "remaining_time": "0:10:22"}
|
||||
{"current_steps": 1005, "total_steps": 1188, "loss": 0.1253, "lr": 2.8534594302469142e-06, "epoch": 5.075757575757576, "percentage": 84.6, "elapsed_time": "0:56:20", "remaining_time": "0:10:15"}
|
||||
{"current_steps": 1010, "total_steps": 1188, "loss": 0.1276, "lr": 2.7040339615316315e-06, "epoch": 5.101010101010101, "percentage": 85.02, "elapsed_time": "0:56:33", "remaining_time": "0:09:58"}
|
||||
{"current_steps": 1015, "total_steps": 1188, "loss": 0.1323, "lr": 2.5583428972779236e-06, "epoch": 5.126262626262626, "percentage": 85.44, "elapsed_time": "0:56:47", "remaining_time": "0:09:40"}
|
||||
{"current_steps": 1020, "total_steps": 1188, "loss": 0.1323, "lr": 2.4164176939166883e-06, "epoch": 5.151515151515151, "percentage": 85.86, "elapsed_time": "0:57:00", "remaining_time": "0:09:23"}
|
||||
{"current_steps": 1025, "total_steps": 1188, "loss": 0.1353, "lr": 2.278288994784723e-06, "epoch": 5.1767676767676765, "percentage": 86.28, "elapsed_time": "0:57:14", "remaining_time": "0:09:06"}
|
||||
{"current_steps": 1030, "total_steps": 1188, "loss": 0.1335, "lr": 2.143986623508478e-06, "epoch": 5.202020202020202, "percentage": 86.7, "elapsed_time": "0:57:26", "remaining_time": "0:08:48"}
|
||||
{"current_steps": 1035, "total_steps": 1188, "loss": 0.1302, "lr": 2.0135395775647916e-06, "epoch": 5.2272727272727275, "percentage": 87.12, "elapsed_time": "0:57:41", "remaining_time": "0:08:31"}
|
||||
{"current_steps": 1040, "total_steps": 1188, "loss": 0.1292, "lr": 1.8869760220199707e-06, "epoch": 5.252525252525253, "percentage": 87.54, "elapsed_time": "0:57:53", "remaining_time": "0:08:14"}
|
||||
{"current_steps": 1045, "total_steps": 1188, "loss": 0.1331, "lr": 1.7643232834486347e-06, "epoch": 5.277777777777778, "percentage": 87.96, "elapsed_time": "0:58:06", "remaining_time": "0:07:57"}
|
||||
{"current_steps": 1050, "total_steps": 1188, "loss": 0.1284, "lr": 1.6456078440335699e-06, "epoch": 5.303030303030303, "percentage": 88.38, "elapsed_time": "0:58:19", "remaining_time": "0:07:39"}
|
||||
{"current_steps": 1055, "total_steps": 1188, "loss": 0.1252, "lr": 1.530855335847916e-06, "epoch": 5.328282828282829, "percentage": 88.8, "elapsed_time": "0:58:31", "remaining_time": "0:07:22"}
|
||||
{"current_steps": 1060, "total_steps": 1188, "loss": 0.1281, "lr": 1.4200905353209127e-06, "epoch": 5.353535353535354, "percentage": 89.23, "elapsed_time": "0:58:44", "remaining_time": "0:07:05"}
|
||||
{"current_steps": 1065, "total_steps": 1188, "loss": 0.1294, "lr": 1.3133373578883557e-06, "epoch": 5.378787878787879, "percentage": 89.65, "elapsed_time": "0:58:56", "remaining_time": "0:06:48"}
|
||||
{"current_steps": 1070, "total_steps": 1188, "loss": 0.1299, "lr": 1.210618852828962e-06, "epoch": 5.404040404040404, "percentage": 90.07, "elapsed_time": "0:59:10", "remaining_time": "0:06:31"}
|
||||
{"current_steps": 1075, "total_steps": 1188, "loss": 0.1277, "lr": 1.111957198287792e-06, "epoch": 5.429292929292929, "percentage": 90.49, "elapsed_time": "0:59:23", "remaining_time": "0:06:14"}
|
||||
{"current_steps": 1080, "total_steps": 1188, "loss": 0.1263, "lr": 1.0173736964876867e-06, "epoch": 5.454545454545454, "percentage": 90.91, "elapsed_time": "0:59:36", "remaining_time": "0:05:57"}
|
||||
{"current_steps": 1085, "total_steps": 1188, "loss": 0.1284, "lr": 9.268887691298878e-07, "epoch": 5.47979797979798, "percentage": 91.33, "elapsed_time": "0:59:50", "remaining_time": "0:05:40"}
|
||||
{"current_steps": 1090, "total_steps": 1188, "loss": 0.1277, "lr": 8.405219529847453e-07, "epoch": 5.505050505050505, "percentage": 91.75, "elapsed_time": "1:00:03", "remaining_time": "0:05:23"}
|
||||
{"current_steps": 1095, "total_steps": 1188, "loss": 0.1345, "lr": 7.582918956734909e-07, "epoch": 5.53030303030303, "percentage": 92.17, "elapsed_time": "1:00:16", "remaining_time": "0:05:07"}
|
||||
{"current_steps": 1100, "total_steps": 1188, "loss": 0.1265, "lr": 6.802163516419979e-07, "epoch": 5.555555555555555, "percentage": 92.59, "elapsed_time": "1:00:30", "remaining_time": "0:04:50"}
|
||||
{"current_steps": 1105, "total_steps": 1188, "loss": 0.1307, "lr": 6.063121783273907e-07, "epoch": 5.58080808080808, "percentage": 93.01, "elapsed_time": "1:01:44", "remaining_time": "0:04:38"}
|
||||
{"current_steps": 1110, "total_steps": 1188, "loss": 0.1277, "lr": 5.365953325183216e-07, "epoch": 5.606060606060606, "percentage": 93.43, "elapsed_time": "1:01:57", "remaining_time": "0:04:21"}
|
||||
{"current_steps": 1115, "total_steps": 1188, "loss": 0.1323, "lr": 4.7108086690970113e-07, "epoch": 5.6313131313131315, "percentage": 93.86, "elapsed_time": "1:02:11", "remaining_time": "0:04:04"}
|
||||
{"current_steps": 1120, "total_steps": 1188, "loss": 0.1235, "lr": 4.0978292685265765e-07, "epoch": 5.656565656565657, "percentage": 94.28, "elapsed_time": "1:02:24", "remaining_time": "0:03:47"}
|
||||
{"current_steps": 1125, "total_steps": 1188, "loss": 0.1302, "lr": 3.5271474730037557e-07, "epoch": 5.681818181818182, "percentage": 94.7, "elapsed_time": "1:02:37", "remaining_time": "0:03:30"}
|
||||
{"current_steps": 1130, "total_steps": 1188, "loss": 0.127, "lr": 2.998886499505171e-07, "epoch": 5.707070707070707, "percentage": 95.12, "elapsed_time": "1:02:51", "remaining_time": "0:03:13"}
|
||||
{"current_steps": 1135, "total_steps": 1188, "loss": 0.1345, "lr": 2.513160405848303e-07, "epoch": 5.732323232323233, "percentage": 95.54, "elapsed_time": "1:03:04", "remaining_time": "0:02:56"}
|
||||
{"current_steps": 1140, "total_steps": 1188, "loss": 0.1328, "lr": 2.0700740660648312e-07, "epoch": 5.757575757575758, "percentage": 95.96, "elapsed_time": "1:03:16", "remaining_time": "0:02:39"}
|
||||
{"current_steps": 1145, "total_steps": 1188, "loss": 0.1284, "lr": 1.669723147757263e-07, "epoch": 5.782828282828283, "percentage": 96.38, "elapsed_time": "1:03:29", "remaining_time": "0:02:23"}
|
||||
{"current_steps": 1150, "total_steps": 1188, "loss": 0.1331, "lr": 1.312194091443142e-07, "epoch": 5.808080808080808, "percentage": 96.8, "elapsed_time": "1:03:42", "remaining_time": "0:02:06"}
|
||||
{"current_steps": 1155, "total_steps": 1188, "loss": 0.1306, "lr": 9.975640918915119e-08, "epoch": 5.833333333333333, "percentage": 97.22, "elapsed_time": "1:03:55", "remaining_time": "0:01:49"}
|
||||
{"current_steps": 1160, "total_steps": 1188, "loss": 0.1304, "lr": 7.259010814555378e-08, "epoch": 5.858585858585858, "percentage": 97.64, "elapsed_time": "1:04:08", "remaining_time": "0:01:32"}
|
||||
{"current_steps": 1165, "total_steps": 1188, "loss": 0.1292, "lr": 4.972637154052606e-08, "epoch": 5.883838383838384, "percentage": 98.06, "elapsed_time": "1:04:21", "remaining_time": "0:01:16"}
|
||||
{"current_steps": 1170, "total_steps": 1188, "loss": 0.1341, "lr": 3.117013592631501e-08, "epoch": 5.909090909090909, "percentage": 98.48, "elapsed_time": "1:04:34", "remaining_time": "0:00:59"}
|
||||
{"current_steps": 1175, "total_steps": 1188, "loss": 0.1267, "lr": 1.6925407814545325e-08, "epoch": 5.934343434343434, "percentage": 98.91, "elapsed_time": "1:04:47", "remaining_time": "0:00:43"}
|
||||
{"current_steps": 1180, "total_steps": 1188, "loss": 0.1297, "lr": 6.995262811178016e-09, "epoch": 5.959595959595959, "percentage": 99.33, "elapsed_time": "1:05:01", "remaining_time": "0:00:26"}
|
||||
{"current_steps": 1185, "total_steps": 1188, "loss": 0.1304, "lr": 1.3818449524416467e-09, "epoch": 5.984848484848484, "percentage": 99.75, "elapsed_time": "1:05:14", "remaining_time": "0:00:09"}
|
||||
{"current_steps": 1188, "total_steps": 1188, "epoch": 6.0, "percentage": 100.0, "elapsed_time": "1:05:54", "remaining_time": "0:00:00"}
|
||||
2654
trainer_state.json
Normal file
2654
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 sha256:67bd93f609301173c1d380511c7edcd9a67297c6f5e72816ca28043ba61fc617
|
||||
size 8657
|
||||
BIN
training_loss.png
Normal file
BIN
training_loss.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 36 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