初始化项目，由ModelHub XC社区提供模型
Model: jiayicheng/mix760_3step_bc760 Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -0,0 +1,36 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
61
README.md
Normal file
61
README.md
Normal file
@@ -0,0 +1,61 @@
|
||||
---
|
||||
library_name: transformers
|
||||
license: other
|
||||
base_model: Qwen/Qwen3-8B
|
||||
tags:
|
||||
- llama-factory
|
||||
- full
|
||||
- generated_from_trainer
|
||||
model-index:
|
||||
- name: train_output
|
||||
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. -->
|
||||
|
||||
# train_output
|
||||
|
||||
This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on the sft_mixed760_official760 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: 4
|
||||
- gradient_accumulation_steps: 4
|
||||
- total_train_batch_size: 16
|
||||
- total_eval_batch_size: 32
|
||||
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.98) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
||||
- lr_scheduler_type: cosine
|
||||
- lr_scheduler_warmup_ratio: 0.1
|
||||
- num_epochs: 7.0
|
||||
|
||||
### Training results
|
||||
|
||||
|
||||
|
||||
### Framework versions
|
||||
|
||||
- Transformers 4.57.1
|
||||
- Pytorch 2.8.0+cu128
|
||||
- Datasets 4.8.4
|
||||
- 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": 1.609436800601497,
|
||||
"achieved_tflops_per_gpu_theoretical": 77.92180494493286,
|
||||
"epoch": 7.0,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.028918465599417686,
|
||||
"mfu_percent": 0.5158451283979156,
|
||||
"mfu_percent_theoretical": 24.974937482350274,
|
||||
"total_flos": 1.8900557354971955e+17,
|
||||
"train_loss": 0.14472091395155828,
|
||||
"train_runtime": 29358.9617,
|
||||
"train_samples_per_second": 0.362,
|
||||
"train_steps_per_second": 0.023,
|
||||
"valid_targets_mean": 1713.0,
|
||||
"valid_targets_min": 479
|
||||
}
|
||||
89
chat_template.jinja
Normal file
89
chat_template.jinja
Normal file
@@ -0,0 +1,89 @@
|
||||
{%- if tools %}
|
||||
{{- '<|im_start|>system\n' }}
|
||||
{%- if messages[0].role == 'system' %}
|
||||
{{- messages[0].content + '\n\n' }}
|
||||
{%- endif %}
|
||||
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
||||
{%- for tool in tools %}
|
||||
{{- "\n" }}
|
||||
{{- tool | tojson }}
|
||||
{%- endfor %}
|
||||
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
||||
{%- else %}
|
||||
{%- if messages[0].role == 'system' %}
|
||||
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
||||
{%- for message in messages[::-1] %}
|
||||
{%- set index = (messages|length - 1) - loop.index0 %}
|
||||
{%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
||||
{%- set ns.multi_step_tool = false %}
|
||||
{%- set ns.last_query_index = index %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- for message in messages %}
|
||||
{%- if message.content is string %}
|
||||
{%- set content = message.content %}
|
||||
{%- else %}
|
||||
{%- set content = '' %}
|
||||
{%- endif %}
|
||||
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
||||
{%- elif message.role == "assistant" %}
|
||||
{%- set reasoning_content = '' %}
|
||||
{%- if message.reasoning_content is string %}
|
||||
{%- set reasoning_content = message.reasoning_content %}
|
||||
{%- else %}
|
||||
{%- if '</think>' in content %}
|
||||
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
||||
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- if loop.index0 > ns.last_query_index %}
|
||||
{%- if loop.last or (not loop.last and reasoning_content) %}
|
||||
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||
{%- endif %}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||
{%- endif %}
|
||||
{%- if message.tool_calls %}
|
||||
{%- for tool_call in message.tool_calls %}
|
||||
{%- if (loop.first and content) or (not loop.first) %}
|
||||
{{- '\n' }}
|
||||
{%- endif %}
|
||||
{%- if tool_call.function %}
|
||||
{%- set tool_call = tool_call.function %}
|
||||
{%- endif %}
|
||||
{{- '<tool_call>\n{"name": "' }}
|
||||
{{- tool_call.name }}
|
||||
{{- '", "arguments": ' }}
|
||||
{%- if tool_call.arguments is string %}
|
||||
{{- tool_call.arguments }}
|
||||
{%- else %}
|
||||
{{- tool_call.arguments | tojson }}
|
||||
{%- endif %}
|
||||
{{- '}\n</tool_call>' }}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- elif message.role == "tool" %}
|
||||
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
||||
{{- '<|im_start|>user' }}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_response>\n' }}
|
||||
{{- content }}
|
||||
{{- '\n</tool_response>' }}
|
||||
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- if add_generation_prompt %}
|
||||
{{- '<|im_start|>assistant\n' }}
|
||||
{%- if enable_thinking is defined and enable_thinking is false %}
|
||||
{{- '<think>\n\n</think>\n\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
68
config.json
Normal file
68
config.json
Normal file
@@ -0,0 +1,68 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen3ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 151645,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 12288,
|
||||
"layer_types": [
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention"
|
||||
],
|
||||
"max_position_embeddings": 40960,
|
||||
"max_window_layers": 36,
|
||||
"model_type": "qwen3",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 36,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 151643,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 1000000,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "4.57.1",
|
||||
"use_cache": false,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
12
generation_config.json
Normal file
12
generation_config.json
Normal file
@@ -0,0 +1,12 @@
|
||||
{
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"pad_token_id": 151643,
|
||||
"temperature": 0.6,
|
||||
"top_k": 20,
|
||||
"top_p": 0.95,
|
||||
"transformers_version": "4.57.1"
|
||||
}
|
||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model-00001-of-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 sha256:9f7b6b47a7a2d90cadf23d85e88df041b943de2f72a4507d22bdb599217b52c8
|
||||
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 sha256:60f511032233fcb05f5b441679b8273ebc9adbd758881bcaa5c8caa114598962
|
||||
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 sha256:6b918d36b0979e5805f2b8b6e567361321bded4daf59af2ec59a4a14ec9f1ffb
|
||||
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 sha256:1f6525a643cea3ccab5eef9b73b0168b91ce12311f1f44f5fead5e15f45396b8
|
||||
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"
|
||||
}
|
||||
}
|
||||
31
special_tokens_map.json
Normal file
31
special_tokens_map.json
Normal file
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"eos_token": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
||||
size 11422654
|
||||
240
tokenizer_config.json
Normal file
240
tokenizer_config.json
Normal file
@@ -0,0 +1,240 @@
|
||||
{
|
||||
"add_bos_token": false,
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"151643": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151644": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151645": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151646": {
|
||||
"content": "<|object_ref_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151647": {
|
||||
"content": "<|object_ref_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151648": {
|
||||
"content": "<|box_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151649": {
|
||||
"content": "<|box_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151650": {
|
||||
"content": "<|quad_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151651": {
|
||||
"content": "<|quad_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151652": {
|
||||
"content": "<|vision_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151653": {
|
||||
"content": "<|vision_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151654": {
|
||||
"content": "<|vision_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151655": {
|
||||
"content": "<|image_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151656": {
|
||||
"content": "<|video_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151657": {
|
||||
"content": "<tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151658": {
|
||||
"content": "</tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151659": {
|
||||
"content": "<|fim_prefix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151660": {
|
||||
"content": "<|fim_middle|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151661": {
|
||||
"content": "<|fim_suffix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151662": {
|
||||
"content": "<|fim_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151663": {
|
||||
"content": "<|repo_name|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151664": {
|
||||
"content": "<|file_sep|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151665": {
|
||||
"content": "<tool_response>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151666": {
|
||||
"content": "</tool_response>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151667": {
|
||||
"content": "<think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151668": {
|
||||
"content": "</think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"bos_token": null,
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": {},
|
||||
"model_max_length": 32768,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"padding_side": "right",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
16
train_results.json
Normal file
16
train_results.json
Normal file
@@ -0,0 +1,16 @@
|
||||
{
|
||||
"achieved_tflops_per_gpu": 1.609436800601497,
|
||||
"achieved_tflops_per_gpu_theoretical": 77.92180494493286,
|
||||
"epoch": 7.0,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.028918465599417686,
|
||||
"mfu_percent": 0.5158451283979156,
|
||||
"mfu_percent_theoretical": 24.974937482350274,
|
||||
"total_flos": 1.8900557354971955e+17,
|
||||
"train_loss": 0.14472091395155828,
|
||||
"train_runtime": 29358.9617,
|
||||
"train_samples_per_second": 0.362,
|
||||
"train_steps_per_second": 0.023,
|
||||
"valid_targets_mean": 1713.0,
|
||||
"valid_targets_min": 479
|
||||
}
|
||||
134
trainer_log.jsonl
Normal file
134
trainer_log.jsonl
Normal file
@@ -0,0 +1,134 @@
|
||||
{"current_steps": 5, "total_steps": 665, "loss": 0.6006, "lr": 2.3880597014925373e-06, "epoch": 0.05263157894736842, "percentage": 0.75, "elapsed_time": "0:03:38", "remaining_time": "7:59:42"}
|
||||
{"current_steps": 10, "total_steps": 665, "loss": 0.6424, "lr": 5.37313432835821e-06, "epoch": 0.10526315789473684, "percentage": 1.5, "elapsed_time": "0:07:42", "remaining_time": "8:24:57"}
|
||||
{"current_steps": 15, "total_steps": 665, "loss": 0.4501, "lr": 8.35820895522388e-06, "epoch": 0.15789473684210525, "percentage": 2.26, "elapsed_time": "0:11:15", "remaining_time": "8:08:01"}
|
||||
{"current_steps": 20, "total_steps": 665, "loss": 0.3755, "lr": 1.1343283582089553e-05, "epoch": 0.21052631578947367, "percentage": 3.01, "elapsed_time": "0:16:27", "remaining_time": "8:50:36"}
|
||||
{"current_steps": 25, "total_steps": 665, "loss": 0.3576, "lr": 1.4328358208955224e-05, "epoch": 0.2631578947368421, "percentage": 3.76, "elapsed_time": "0:22:00", "remaining_time": "9:23:19"}
|
||||
{"current_steps": 30, "total_steps": 665, "loss": 0.2887, "lr": 1.7313432835820894e-05, "epoch": 0.3157894736842105, "percentage": 4.51, "elapsed_time": "0:26:21", "remaining_time": "9:17:59"}
|
||||
{"current_steps": 35, "total_steps": 665, "loss": 0.3099, "lr": 2.029850746268657e-05, "epoch": 0.3684210526315789, "percentage": 5.26, "elapsed_time": "0:28:58", "remaining_time": "8:41:29"}
|
||||
{"current_steps": 40, "total_steps": 665, "loss": 0.2594, "lr": 2.3283582089552242e-05, "epoch": 0.42105263157894735, "percentage": 6.02, "elapsed_time": "0:31:59", "remaining_time": "8:19:52"}
|
||||
{"current_steps": 45, "total_steps": 665, "loss": 0.2576, "lr": 2.6268656716417913e-05, "epoch": 0.47368421052631576, "percentage": 6.77, "elapsed_time": "0:35:41", "remaining_time": "8:11:38"}
|
||||
{"current_steps": 50, "total_steps": 665, "loss": 0.291, "lr": 2.9253731343283584e-05, "epoch": 0.5263157894736842, "percentage": 7.52, "elapsed_time": "0:38:31", "remaining_time": "7:53:48"}
|
||||
{"current_steps": 55, "total_steps": 665, "loss": 0.2378, "lr": 3.2238805970149255e-05, "epoch": 0.5789473684210527, "percentage": 8.27, "elapsed_time": "0:41:44", "remaining_time": "7:42:53"}
|
||||
{"current_steps": 60, "total_steps": 665, "loss": 0.2227, "lr": 3.522388059701493e-05, "epoch": 0.631578947368421, "percentage": 9.02, "elapsed_time": "0:45:30", "remaining_time": "7:38:49"}
|
||||
{"current_steps": 65, "total_steps": 665, "loss": 0.2336, "lr": 3.8208955223880596e-05, "epoch": 0.6842105263157895, "percentage": 9.77, "elapsed_time": "0:49:06", "remaining_time": "7:33:17"}
|
||||
{"current_steps": 70, "total_steps": 665, "loss": 0.1988, "lr": 3.9998896039909675e-05, "epoch": 0.7368421052631579, "percentage": 10.53, "elapsed_time": "0:53:01", "remaining_time": "7:30:45"}
|
||||
{"current_steps": 75, "total_steps": 665, "loss": 0.2185, "lr": 3.998647788848384e-05, "epoch": 0.7894736842105263, "percentage": 11.28, "elapsed_time": "0:56:11", "remaining_time": "7:22:04"}
|
||||
{"current_steps": 80, "total_steps": 665, "loss": 0.2002, "lr": 3.996027023188427e-05, "epoch": 0.8421052631578947, "percentage": 12.03, "elapsed_time": "0:59:48", "remaining_time": "7:17:24"}
|
||||
{"current_steps": 85, "total_steps": 665, "loss": 0.2278, "lr": 3.9920291151866977e-05, "epoch": 0.8947368421052632, "percentage": 12.78, "elapsed_time": "1:02:21", "remaining_time": "7:05:29"}
|
||||
{"current_steps": 90, "total_steps": 665, "loss": 0.2334, "lr": 3.986656823166766e-05, "epoch": 0.9473684210526315, "percentage": 13.53, "elapsed_time": "1:05:44", "remaining_time": "7:00:03"}
|
||||
{"current_steps": 95, "total_steps": 665, "loss": 0.1963, "lr": 3.979913853697095e-05, "epoch": 1.0, "percentage": 14.29, "elapsed_time": "1:09:57", "remaining_time": "6:59:46"}
|
||||
{"current_steps": 100, "total_steps": 665, "loss": 0.1857, "lr": 3.9718048590337186e-05, "epoch": 1.0526315789473684, "percentage": 15.04, "elapsed_time": "1:14:28", "remaining_time": "7:00:48"}
|
||||
{"current_steps": 105, "total_steps": 665, "loss": 0.1824, "lr": 3.962335433910463e-05, "epoch": 1.1052631578947367, "percentage": 15.79, "elapsed_time": "1:18:43", "remaining_time": "6:59:51"}
|
||||
{"current_steps": 110, "total_steps": 665, "loss": 0.205, "lr": 3.9515121116788985e-05, "epoch": 1.1578947368421053, "percentage": 16.54, "elapsed_time": "1:22:53", "remaining_time": "6:58:14"}
|
||||
{"current_steps": 115, "total_steps": 665, "loss": 0.1878, "lr": 3.939342359800714e-05, "epoch": 1.2105263157894737, "percentage": 17.29, "elapsed_time": "1:26:52", "remaining_time": "6:55:28"}
|
||||
{"current_steps": 120, "total_steps": 665, "loss": 0.1719, "lr": 3.925834574695599e-05, "epoch": 1.263157894736842, "percentage": 18.05, "elapsed_time": "1:30:57", "remaining_time": "6:53:07"}
|
||||
{"current_steps": 125, "total_steps": 665, "loss": 0.1911, "lr": 3.910998075948207e-05, "epoch": 1.3157894736842106, "percentage": 18.8, "elapsed_time": "1:33:45", "remaining_time": "6:45:03"}
|
||||
{"current_steps": 130, "total_steps": 665, "loss": 0.1753, "lr": 3.8948430998781824e-05, "epoch": 1.368421052631579, "percentage": 19.55, "elapsed_time": "1:37:17", "remaining_time": "6:40:22"}
|
||||
{"current_steps": 135, "total_steps": 665, "loss": 0.1912, "lr": 3.8773807924776976e-05, "epoch": 1.4210526315789473, "percentage": 20.3, "elapsed_time": "1:41:14", "remaining_time": "6:37:27"}
|
||||
{"current_steps": 140, "total_steps": 665, "loss": 0.1831, "lr": 3.8586232017213675e-05, "epoch": 1.4736842105263157, "percentage": 21.05, "elapsed_time": "1:43:37", "remaining_time": "6:28:36"}
|
||||
{"current_steps": 145, "total_steps": 665, "loss": 0.1812, "lr": 3.83858326925385e-05, "epoch": 1.526315789473684, "percentage": 21.8, "elapsed_time": "1:48:09", "remaining_time": "6:27:50"}
|
||||
{"current_steps": 150, "total_steps": 665, "loss": 0.1665, "lr": 3.8172748214608624e-05, "epoch": 1.5789473684210527, "percentage": 22.56, "elapsed_time": "1:50:56", "remaining_time": "6:20:54"}
|
||||
{"current_steps": 155, "total_steps": 665, "loss": 0.1776, "lr": 3.7947125599297856e-05, "epoch": 1.631578947368421, "percentage": 23.31, "elapsed_time": "1:54:52", "remaining_time": "6:17:58"}
|
||||
{"current_steps": 160, "total_steps": 665, "loss": 0.1856, "lr": 3.7709120513064196e-05, "epoch": 1.6842105263157894, "percentage": 24.06, "elapsed_time": "1:58:10", "remaining_time": "6:12:59"}
|
||||
{"current_steps": 165, "total_steps": 665, "loss": 0.1873, "lr": 3.745889716554912e-05, "epoch": 1.736842105263158, "percentage": 24.81, "elapsed_time": "2:00:58", "remaining_time": "6:06:34"}
|
||||
{"current_steps": 170, "total_steps": 665, "loss": 0.1787, "lr": 3.7196628196282415e-05, "epoch": 1.7894736842105263, "percentage": 25.56, "elapsed_time": "2:05:37", "remaining_time": "6:05:47"}
|
||||
{"current_steps": 175, "total_steps": 665, "loss": 0.1619, "lr": 3.692249455557103e-05, "epoch": 1.8421052631578947, "percentage": 26.32, "elapsed_time": "2:10:05", "remaining_time": "6:04:16"}
|
||||
{"current_steps": 180, "total_steps": 665, "loss": 0.1677, "lr": 3.6636685379653875e-05, "epoch": 1.8947368421052633, "percentage": 27.07, "elapsed_time": "2:14:00", "remaining_time": "6:01:05"}
|
||||
{"current_steps": 185, "total_steps": 665, "loss": 0.1675, "lr": 3.633939786020884e-05, "epoch": 1.9473684210526314, "percentage": 27.82, "elapsed_time": "2:16:57", "remaining_time": "5:55:20"}
|
||||
{"current_steps": 190, "total_steps": 665, "loss": 0.1779, "lr": 3.603083710830205e-05, "epoch": 2.0, "percentage": 28.57, "elapsed_time": "2:20:57", "remaining_time": "5:52:22"}
|
||||
{"current_steps": 195, "total_steps": 665, "loss": 0.1443, "lr": 3.5711216012873114e-05, "epoch": 2.0526315789473686, "percentage": 29.32, "elapsed_time": "2:24:43", "remaining_time": "5:48:48"}
|
||||
{"current_steps": 200, "total_steps": 665, "loss": 0.1406, "lr": 3.538075509385427e-05, "epoch": 2.1052631578947367, "percentage": 30.08, "elapsed_time": "2:28:50", "remaining_time": "5:46:03"}
|
||||
{"current_steps": 205, "total_steps": 665, "loss": 0.136, "lr": 3.503968235002437e-05, "epoch": 2.1578947368421053, "percentage": 30.83, "elapsed_time": "2:32:18", "remaining_time": "5:41:44"}
|
||||
{"current_steps": 210, "total_steps": 665, "loss": 0.1594, "lr": 3.468823310170309e-05, "epoch": 2.2105263157894735, "percentage": 31.58, "elapsed_time": "2:36:10", "remaining_time": "5:38:21"}
|
||||
{"current_steps": 215, "total_steps": 665, "loss": 0.1399, "lr": 3.4326649828393565e-05, "epoch": 2.263157894736842, "percentage": 32.33, "elapsed_time": "2:40:41", "remaining_time": "5:36:19"}
|
||||
{"current_steps": 220, "total_steps": 665, "loss": 0.1494, "lr": 3.395518200148571e-05, "epoch": 2.3157894736842106, "percentage": 33.08, "elapsed_time": "2:45:59", "remaining_time": "5:35:44"}
|
||||
{"current_steps": 225, "total_steps": 665, "loss": 0.149, "lr": 3.357408591213544e-05, "epoch": 2.3684210526315788, "percentage": 33.83, "elapsed_time": "2:48:32", "remaining_time": "5:29:35"}
|
||||
{"current_steps": 230, "total_steps": 665, "loss": 0.1446, "lr": 3.318362449443876e-05, "epoch": 2.4210526315789473, "percentage": 34.59, "elapsed_time": "2:52:44", "remaining_time": "5:26:42"}
|
||||
{"current_steps": 235, "total_steps": 665, "loss": 0.1496, "lr": 3.278406714402253e-05, "epoch": 2.473684210526316, "percentage": 35.34, "elapsed_time": "2:55:36", "remaining_time": "5:21:18"}
|
||||
{"current_steps": 240, "total_steps": 665, "loss": 0.1357, "lr": 3.237568953217717e-05, "epoch": 2.526315789473684, "percentage": 36.09, "elapsed_time": "3:00:00", "remaining_time": "5:18:45"}
|
||||
{"current_steps": 245, "total_steps": 665, "loss": 0.1605, "lr": 3.195877341565958e-05, "epoch": 2.5789473684210527, "percentage": 36.84, "elapsed_time": "3:03:02", "remaining_time": "5:13:47"}
|
||||
{"current_steps": 250, "total_steps": 665, "loss": 0.1365, "lr": 3.153360644229735e-05, "epoch": 2.6315789473684212, "percentage": 37.59, "elapsed_time": "3:06:17", "remaining_time": "5:09:14"}
|
||||
{"current_steps": 255, "total_steps": 665, "loss": 0.1763, "lr": 3.110048195252851e-05, "epoch": 2.6842105263157894, "percentage": 38.35, "elapsed_time": "3:10:03", "remaining_time": "5:05:35"}
|
||||
{"current_steps": 260, "total_steps": 665, "loss": 0.1496, "lr": 3.065969877701378e-05, "epoch": 2.736842105263158, "percentage": 39.1, "elapsed_time": "3:14:09", "remaining_time": "5:02:26"}
|
||||
{"current_steps": 265, "total_steps": 665, "loss": 0.1611, "lr": 3.0211561030460755e-05, "epoch": 2.7894736842105265, "percentage": 39.85, "elapsed_time": "3:17:12", "remaining_time": "4:57:40"}
|
||||
{"current_steps": 270, "total_steps": 665, "loss": 0.1212, "lr": 2.975637790180255e-05, "epoch": 2.8421052631578947, "percentage": 40.6, "elapsed_time": "3:20:40", "remaining_time": "4:53:34"}
|
||||
{"current_steps": 275, "total_steps": 665, "loss": 0.1461, "lr": 2.9294463440875375e-05, "epoch": 2.8947368421052633, "percentage": 41.35, "elapsed_time": "3:24:09", "remaining_time": "4:49:31"}
|
||||
{"current_steps": 280, "total_steps": 665, "loss": 0.1415, "lr": 2.8826136341742504e-05, "epoch": 2.9473684210526314, "percentage": 42.11, "elapsed_time": "3:27:25", "remaining_time": "4:45:12"}
|
||||
{"current_steps": 285, "total_steps": 665, "loss": 0.1587, "lr": 2.8351719722813933e-05, "epoch": 3.0, "percentage": 42.86, "elapsed_time": "3:30:54", "remaining_time": "4:41:12"}
|
||||
{"current_steps": 290, "total_steps": 665, "loss": 0.1186, "lr": 2.7871540903913465e-05, "epoch": 3.0526315789473686, "percentage": 43.61, "elapsed_time": "3:34:49", "remaining_time": "4:37:47"}
|
||||
{"current_steps": 295, "total_steps": 665, "loss": 0.1252, "lr": 2.7385931180447145e-05, "epoch": 3.1052631578947367, "percentage": 44.36, "elapsed_time": "3:37:37", "remaining_time": "4:32:56"}
|
||||
{"current_steps": 300, "total_steps": 665, "loss": 0.1249, "lr": 2.6895225594828743e-05, "epoch": 3.1578947368421053, "percentage": 45.11, "elapsed_time": "3:40:52", "remaining_time": "4:28:43"}
|
||||
{"current_steps": 305, "total_steps": 665, "loss": 0.1096, "lr": 2.639976270531996e-05, "epoch": 3.2105263157894735, "percentage": 45.86, "elapsed_time": "3:44:08", "remaining_time": "4:24:33"}
|
||||
{"current_steps": 310, "total_steps": 665, "loss": 0.1292, "lr": 2.5899884352444994e-05, "epoch": 3.263157894736842, "percentage": 46.62, "elapsed_time": "3:47:24", "remaining_time": "4:20:24"}
|
||||
{"current_steps": 315, "total_steps": 665, "loss": 0.1148, "lr": 2.5395935423140487e-05, "epoch": 3.3157894736842106, "percentage": 47.37, "elapsed_time": "3:51:21", "remaining_time": "4:17:03"}
|
||||
{"current_steps": 320, "total_steps": 665, "loss": 0.111, "lr": 2.4888263612803637e-05, "epoch": 3.3684210526315788, "percentage": 48.12, "elapsed_time": "3:55:33", "remaining_time": "4:13:57"}
|
||||
{"current_steps": 325, "total_steps": 665, "loss": 0.1091, "lr": 2.4377219185402613e-05, "epoch": 3.4210526315789473, "percentage": 48.87, "elapsed_time": "3:59:13", "remaining_time": "4:10:16"}
|
||||
{"current_steps": 330, "total_steps": 665, "loss": 0.1241, "lr": 2.3863154731814867e-05, "epoch": 3.473684210526316, "percentage": 49.62, "elapsed_time": "4:01:57", "remaining_time": "4:05:37"}
|
||||
{"current_steps": 335, "total_steps": 665, "loss": 0.1313, "lr": 2.3346424926559935e-05, "epoch": 3.526315789473684, "percentage": 50.38, "elapsed_time": "4:06:03", "remaining_time": "4:02:22"}
|
||||
{"current_steps": 340, "total_steps": 665, "loss": 0.1229, "lr": 2.2827386283094707e-05, "epoch": 3.5789473684210527, "percentage": 51.13, "elapsed_time": "4:10:09", "remaining_time": "3:59:07"}
|
||||
{"current_steps": 345, "total_steps": 665, "loss": 0.121, "lr": 2.2306396907839883e-05, "epoch": 3.6315789473684212, "percentage": 51.88, "elapsed_time": "4:13:37", "remaining_time": "3:55:14"}
|
||||
{"current_steps": 350, "total_steps": 665, "loss": 0.1168, "lr": 2.178381625310748e-05, "epoch": 3.6842105263157894, "percentage": 52.63, "elapsed_time": "4:17:27", "remaining_time": "3:51:43"}
|
||||
{"current_steps": 355, "total_steps": 665, "loss": 0.1054, "lr": 2.1260004869099583e-05, "epoch": 3.736842105263158, "percentage": 53.38, "elapsed_time": "4:21:10", "remaining_time": "3:48:03"}
|
||||
{"current_steps": 360, "total_steps": 665, "loss": 0.135, "lr": 2.0735324155149795e-05, "epoch": 3.7894736842105265, "percentage": 54.14, "elapsed_time": "4:25:38", "remaining_time": "3:45:03"}
|
||||
{"current_steps": 365, "total_steps": 665, "loss": 0.1331, "lr": 2.021013611037873e-05, "epoch": 3.8421052631578947, "percentage": 54.89, "elapsed_time": "4:29:23", "remaining_time": "3:41:24"}
|
||||
{"current_steps": 370, "total_steps": 665, "loss": 0.1389, "lr": 1.9684803083935676e-05, "epoch": 3.8947368421052633, "percentage": 55.64, "elapsed_time": "4:32:42", "remaining_time": "3:37:25"}
|
||||
{"current_steps": 375, "total_steps": 665, "loss": 0.115, "lr": 1.915968752499886e-05, "epoch": 3.9473684210526314, "percentage": 56.39, "elapsed_time": "4:36:32", "remaining_time": "3:33:51"}
|
||||
{"current_steps": 380, "total_steps": 665, "loss": 0.1336, "lr": 1.8635151732706586e-05, "epoch": 4.0, "percentage": 57.14, "elapsed_time": "4:40:05", "remaining_time": "3:30:03"}
|
||||
{"current_steps": 385, "total_steps": 665, "loss": 0.1049, "lr": 1.8111557606191946e-05, "epoch": 4.052631578947368, "percentage": 57.89, "elapsed_time": "4:43:43", "remaining_time": "3:26:20"}
|
||||
{"current_steps": 390, "total_steps": 665, "loss": 0.1107, "lr": 1.758926639489354e-05, "epoch": 4.105263157894737, "percentage": 58.65, "elapsed_time": "4:47:43", "remaining_time": "3:22:52"}
|
||||
{"current_steps": 395, "total_steps": 665, "loss": 0.1135, "lr": 1.7068638449314365e-05, "epoch": 4.157894736842105, "percentage": 59.4, "elapsed_time": "4:50:37", "remaining_time": "3:18:39"}
|
||||
{"current_steps": 400, "total_steps": 665, "loss": 0.1007, "lr": 1.6550032972400996e-05, "epoch": 4.2105263157894735, "percentage": 60.15, "elapsed_time": "4:53:38", "remaining_time": "3:14:32"}
|
||||
{"current_steps": 405, "total_steps": 665, "loss": 0.0856, "lr": 1.6033807771714464e-05, "epoch": 4.2631578947368425, "percentage": 60.9, "elapsed_time": "4:57:02", "remaining_time": "3:10:41"}
|
||||
{"current_steps": 410, "total_steps": 665, "loss": 0.1061, "lr": 1.552031901256391e-05, "epoch": 4.315789473684211, "percentage": 61.65, "elapsed_time": "5:00:02", "remaining_time": "3:06:36"}
|
||||
{"current_steps": 415, "total_steps": 665, "loss": 0.1026, "lr": 1.5009920972273255e-05, "epoch": 4.368421052631579, "percentage": 62.41, "elapsed_time": "5:03:16", "remaining_time": "3:02:41"}
|
||||
{"current_steps": 420, "total_steps": 665, "loss": 0.1084, "lr": 1.4502965795750487e-05, "epoch": 4.421052631578947, "percentage": 63.16, "elapsed_time": "5:08:06", "remaining_time": "2:59:43"}
|
||||
{"current_steps": 425, "total_steps": 665, "loss": 0.1041, "lr": 1.399980325252823e-05, "epoch": 4.473684210526316, "percentage": 63.91, "elapsed_time": "5:12:23", "remaining_time": "2:56:24"}
|
||||
{"current_steps": 430, "total_steps": 665, "loss": 0.0967, "lr": 1.3500780495443098e-05, "epoch": 4.526315789473684, "percentage": 64.66, "elapsed_time": "5:16:21", "remaining_time": "2:52:53"}
|
||||
{"current_steps": 435, "total_steps": 665, "loss": 0.0967, "lr": 1.3006241821120483e-05, "epoch": 4.578947368421053, "percentage": 65.41, "elapsed_time": "5:20:25", "remaining_time": "2:49:25"}
|
||||
{"current_steps": 440, "total_steps": 665, "loss": 0.0912, "lr": 1.2516528432429955e-05, "epoch": 4.631578947368421, "percentage": 66.17, "elapsed_time": "5:23:28", "remaining_time": "2:45:24"}
|
||||
{"current_steps": 445, "total_steps": 665, "loss": 0.0969, "lr": 1.2031978203075172e-05, "epoch": 4.684210526315789, "percentage": 66.92, "elapsed_time": "5:26:24", "remaining_time": "2:41:22"}
|
||||
{"current_steps": 450, "total_steps": 665, "loss": 0.0975, "lr": 1.1552925444480674e-05, "epoch": 4.7368421052631575, "percentage": 67.67, "elapsed_time": "5:29:41", "remaining_time": "2:37:31"}
|
||||
{"current_steps": 455, "total_steps": 665, "loss": 0.096, "lr": 1.1079700675136506e-05, "epoch": 4.7894736842105265, "percentage": 68.42, "elapsed_time": "5:33:35", "remaining_time": "2:33:57"}
|
||||
{"current_steps": 460, "total_steps": 665, "loss": 0.098, "lr": 1.0612630392559728e-05, "epoch": 4.842105263157895, "percentage": 69.17, "elapsed_time": "5:36:50", "remaining_time": "2:30:06"}
|
||||
{"current_steps": 465, "total_steps": 665, "loss": 0.0822, "lr": 1.015203684803013e-05, "epoch": 4.894736842105263, "percentage": 69.92, "elapsed_time": "5:41:52", "remaining_time": "2:27:02"}
|
||||
{"current_steps": 470, "total_steps": 665, "loss": 0.1013, "lr": 9.698237824255634e-06, "epoch": 4.947368421052632, "percentage": 70.68, "elapsed_time": "5:45:08", "remaining_time": "2:23:11"}
|
||||
{"current_steps": 475, "total_steps": 665, "loss": 0.0948, "lr": 9.251546416120756e-06, "epoch": 5.0, "percentage": 71.43, "elapsed_time": "5:49:27", "remaining_time": "2:19:47"}
|
||||
{"current_steps": 480, "total_steps": 665, "loss": 0.0991, "lr": 8.812270814669338e-06, "epoch": 5.052631578947368, "percentage": 72.18, "elapsed_time": "5:53:28", "remaining_time": "2:16:14"}
|
||||
{"current_steps": 485, "total_steps": 665, "loss": 0.0798, "lr": 8.38071409447074e-06, "epoch": 5.105263157894737, "percentage": 72.93, "elapsed_time": "5:55:56", "remaining_time": "2:12:06"}
|
||||
{"current_steps": 490, "total_steps": 665, "loss": 0.0807, "lr": 7.957174004516015e-06, "epoch": 5.157894736842105, "percentage": 73.68, "elapsed_time": "5:59:28", "remaining_time": "2:08:22"}
|
||||
{"current_steps": 495, "total_steps": 665, "loss": 0.0903, "lr": 7.5419427627884586e-06, "epoch": 5.2105263157894735, "percentage": 74.44, "elapsed_time": "6:02:42", "remaining_time": "2:04:33"}
|
||||
{"current_steps": 500, "total_steps": 665, "loss": 0.0876, "lr": 7.1353068546502144e-06, "epoch": 5.2631578947368425, "percentage": 75.19, "elapsed_time": "6:05:44", "remaining_time": "2:00:41"}
|
||||
{"current_steps": 505, "total_steps": 665, "loss": 0.0681, "lr": 6.737546835184101e-06, "epoch": 5.315789473684211, "percentage": 75.94, "elapsed_time": "6:10:51", "remaining_time": "1:57:29"}
|
||||
{"current_steps": 510, "total_steps": 665, "loss": 0.0795, "lr": 6.348937135626922e-06, "epoch": 5.368421052631579, "percentage": 76.69, "elapsed_time": "6:14:00", "remaining_time": "1:53:40"}
|
||||
{"current_steps": 515, "total_steps": 665, "loss": 0.095, "lr": 5.9697458740279165e-06, "epoch": 5.421052631578947, "percentage": 77.44, "elapsed_time": "6:18:26", "remaining_time": "1:50:13"}
|
||||
{"current_steps": 520, "total_steps": 665, "loss": 0.0657, "lr": 5.600234670262925e-06, "epoch": 5.473684210526316, "percentage": 78.2, "elapsed_time": "6:23:04", "remaining_time": "1:46:49"}
|
||||
{"current_steps": 525, "total_steps": 665, "loss": 0.0907, "lr": 5.240658465531914e-06, "epoch": 5.526315789473684, "percentage": 78.95, "elapsed_time": "6:26:30", "remaining_time": "1:43:04"}
|
||||
{"current_steps": 530, "total_steps": 665, "loss": 0.0811, "lr": 4.891265346464416e-06, "epoch": 5.578947368421053, "percentage": 79.7, "elapsed_time": "6:30:06", "remaining_time": "1:39:22"}
|
||||
{"current_steps": 535, "total_steps": 665, "loss": 0.0916, "lr": 4.552296373954194e-06, "epoch": 5.631578947368421, "percentage": 80.45, "elapsed_time": "6:33:00", "remaining_time": "1:35:29"}
|
||||
{"current_steps": 540, "total_steps": 665, "loss": 0.0858, "lr": 4.223985416841292e-06, "epoch": 5.684210526315789, "percentage": 81.2, "elapsed_time": "6:36:18", "remaining_time": "1:31:44"}
|
||||
{"current_steps": 545, "total_steps": 665, "loss": 0.0867, "lr": 3.906558990556126e-06, "epoch": 5.7368421052631575, "percentage": 81.95, "elapsed_time": "6:39:33", "remaining_time": "1:27:58"}
|
||||
{"current_steps": 550, "total_steps": 665, "loss": 0.0782, "lr": 3.6002361008370802e-06, "epoch": 5.7894736842105265, "percentage": 82.71, "elapsed_time": "6:43:46", "remaining_time": "1:24:25"}
|
||||
{"current_steps": 555, "total_steps": 665, "loss": 0.0857, "lr": 3.3052280926292802e-06, "epoch": 5.842105263157895, "percentage": 83.46, "elapsed_time": "6:47:47", "remaining_time": "1:20:49"}
|
||||
{"current_steps": 560, "total_steps": 665, "loss": 0.0803, "lr": 3.021738504268905e-06, "epoch": 5.894736842105263, "percentage": 84.21, "elapsed_time": "6:51:41", "remaining_time": "1:17:11"}
|
||||
{"current_steps": 565, "total_steps": 665, "loss": 0.0795, "lr": 2.7499629270535954e-06, "epoch": 5.947368421052632, "percentage": 84.96, "elapsed_time": "6:55:30", "remaining_time": "1:13:32"}
|
||||
{"current_steps": 570, "total_steps": 665, "loss": 0.0748, "lr": 2.490088870295839e-06, "epoch": 6.0, "percentage": 85.71, "elapsed_time": "6:59:18", "remaining_time": "1:09:53"}
|
||||
{"current_steps": 575, "total_steps": 665, "loss": 0.0854, "lr": 2.242295631952496e-06, "epoch": 6.052631578947368, "percentage": 86.47, "elapsed_time": "7:03:45", "remaining_time": "1:06:19"}
|
||||
{"current_steps": 580, "total_steps": 665, "loss": 0.0711, "lr": 2.0067541749196453e-06, "epoch": 6.105263157894737, "percentage": 87.22, "elapsed_time": "7:07:45", "remaining_time": "1:02:41"}
|
||||
{"current_steps": 585, "total_steps": 665, "loss": 0.0829, "lr": 1.783627009078137e-06, "epoch": 6.157894736842105, "percentage": 87.97, "elapsed_time": "7:11:24", "remaining_time": "0:58:59"}
|
||||
{"current_steps": 590, "total_steps": 665, "loss": 0.0813, "lr": 1.573068079171265e-06, "epoch": 6.2105263157894735, "percentage": 88.72, "elapsed_time": "7:15:13", "remaining_time": "0:55:19"}
|
||||
{"current_steps": 595, "total_steps": 665, "loss": 0.0719, "lr": 1.3752226585918416e-06, "epoch": 6.2631578947368425, "percentage": 89.47, "elapsed_time": "7:17:43", "remaining_time": "0:51:29"}
|
||||
{"current_steps": 600, "total_steps": 665, "loss": 0.0653, "lr": 1.1902272491520362e-06, "epoch": 6.315789473684211, "percentage": 90.23, "elapsed_time": "7:21:07", "remaining_time": "0:47:47"}
|
||||
{"current_steps": 605, "total_steps": 665, "loss": 0.0788, "lr": 1.0182094869050796e-06, "epoch": 6.368421052631579, "percentage": 90.98, "elapsed_time": "7:23:41", "remaining_time": "0:44:00"}
|
||||
{"current_steps": 610, "total_steps": 665, "loss": 0.066, "lr": 8.592880540838111e-07, "epoch": 6.421052631578947, "percentage": 91.73, "elapsed_time": "7:26:44", "remaining_time": "0:40:16"}
|
||||
{"current_steps": 615, "total_steps": 665, "loss": 0.085, "lr": 7.135725972168694e-07, "epoch": 6.473684210526316, "percentage": 92.48, "elapsed_time": "7:30:49", "remaining_time": "0:36:39"}
|
||||
{"current_steps": 620, "total_steps": 665, "loss": 0.0628, "lr": 5.811636514789598e-07, "epoch": 6.526315789473684, "percentage": 93.23, "elapsed_time": "7:34:53", "remaining_time": "0:33:00"}
|
||||
{"current_steps": 625, "total_steps": 665, "loss": 0.0716, "lr": 4.621525713274588e-07, "epoch": 6.578947368421053, "percentage": 93.98, "elapsed_time": "7:37:16", "remaining_time": "0:29:15"}
|
||||
{"current_steps": 630, "total_steps": 665, "loss": 0.0882, "lr": 3.5662146747315054e-07, "epoch": 6.631578947368421, "percentage": 94.74, "elapsed_time": "7:41:37", "remaining_time": "0:25:38"}
|
||||
{"current_steps": 635, "total_steps": 665, "loss": 0.0855, "lr": 2.6464315022861844e-07, "epoch": 6.684210526315789, "percentage": 95.49, "elapsed_time": "7:45:16", "remaining_time": "0:21:58"}
|
||||
{"current_steps": 640, "total_steps": 665, "loss": 0.0731, "lr": 1.862810792733849e-07, "epoch": 6.7368421052631575, "percentage": 96.24, "elapsed_time": "7:49:55", "remaining_time": "0:18:21"}
|
||||
{"current_steps": 645, "total_steps": 665, "loss": 0.0746, "lr": 1.2158931987041877e-07, "epoch": 6.7894736842105265, "percentage": 96.99, "elapsed_time": "7:54:21", "remaining_time": "0:14:42"}
|
||||
{"current_steps": 650, "total_steps": 665, "loss": 0.0677, "lr": 7.06125055642537e-08, "epoch": 6.842105263157895, "percentage": 97.74, "elapsed_time": "7:57:58", "remaining_time": "0:11:01"}
|
||||
{"current_steps": 655, "total_steps": 665, "loss": 0.0664, "lr": 3.3385807386456804e-08, "epoch": 6.894736842105263, "percentage": 98.5, "elapsed_time": "8:02:40", "remaining_time": "0:07:22"}
|
||||
{"current_steps": 660, "total_steps": 665, "loss": 0.0767, "lr": 9.934909589646157e-09, "epoch": 6.947368421052632, "percentage": 99.25, "elapsed_time": "8:05:14", "remaining_time": "0:03:40"}
|
||||
{"current_steps": 665, "total_steps": 665, "loss": 0.0788, "lr": 2.759919268702227e-10, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "8:08:39", "remaining_time": "0:00:00"}
|
||||
{"current_steps": 665, "total_steps": 665, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "8:09:17", "remaining_time": "0:00:00"}
|
||||
1510
trainer_state.json
Normal file
1510
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:bb46c6f147b39a2d3ffab12fddb45f96aefe4e6f49eed4e54f8f1d718c621f2e
|
||||
size 8465
|
||||
BIN
training_loss.png
Normal file
BIN
training_loss.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 42 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