初始化项目，由ModelHub XC社区提供模型
Model: laion/swesmith-3160__Qwen3-8B Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -0,0 +1,36 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
61
README.md
Normal file
61
README.md
Normal file
@@ -0,0 +1,61 @@
|
||||
---
|
||||
library_name: transformers
|
||||
license: other
|
||||
base_model: Qwen/Qwen3-8B
|
||||
tags:
|
||||
- llama-factory
|
||||
- full
|
||||
- generated_from_trainer
|
||||
model-index:
|
||||
- name: swesmith-3160__Qwen3-8B
|
||||
results: []
|
||||
---
|
||||
|
||||
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
||||
should probably proofread and complete it, then remove this comment. -->
|
||||
|
||||
# swesmith-3160__Qwen3-8B
|
||||
|
||||
This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on the /e/data1/datasets/playground/ot/hf_hub/datasets--laion--swesmith-unified-3160/snapshots/ebee68a1798546a79293aadc7ac631850f238447_thinking_preprocessed dataset.
|
||||
|
||||
## Model description
|
||||
|
||||
More information needed
|
||||
|
||||
## Intended uses & limitations
|
||||
|
||||
More information needed
|
||||
|
||||
## Training and evaluation data
|
||||
|
||||
More information needed
|
||||
|
||||
## Training procedure
|
||||
|
||||
### Training hyperparameters
|
||||
|
||||
The following hyperparameters were used during training:
|
||||
- learning_rate: 4e-05
|
||||
- train_batch_size: 1
|
||||
- eval_batch_size: 8
|
||||
- seed: 42
|
||||
- distributed_type: multi-GPU
|
||||
- num_devices: 32
|
||||
- gradient_accumulation_steps: 3
|
||||
- total_train_batch_size: 96
|
||||
- total_eval_batch_size: 256
|
||||
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.98) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
||||
- lr_scheduler_type: cosine
|
||||
- lr_scheduler_warmup_ratio: 0.1
|
||||
- num_epochs: 7.0
|
||||
|
||||
### Training results
|
||||
|
||||
|
||||
|
||||
### Framework versions
|
||||
|
||||
- Transformers 4.57.6
|
||||
- Pytorch 2.9.1+cu130
|
||||
- Datasets 4.7.0
|
||||
- Tokenizers 0.22.2
|
||||
28
added_tokens.json
Normal file
28
added_tokens.json
Normal file
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"</think>": 151668,
|
||||
"</tool_call>": 151658,
|
||||
"</tool_response>": 151666,
|
||||
"<think>": 151667,
|
||||
"<tool_call>": 151657,
|
||||
"<tool_response>": 151665,
|
||||
"<|box_end|>": 151649,
|
||||
"<|box_start|>": 151648,
|
||||
"<|endoftext|>": 151643,
|
||||
"<|file_sep|>": 151664,
|
||||
"<|fim_middle|>": 151660,
|
||||
"<|fim_pad|>": 151662,
|
||||
"<|fim_prefix|>": 151659,
|
||||
"<|fim_suffix|>": 151661,
|
||||
"<|im_end|>": 151645,
|
||||
"<|im_start|>": 151644,
|
||||
"<|image_pad|>": 151655,
|
||||
"<|object_ref_end|>": 151647,
|
||||
"<|object_ref_start|>": 151646,
|
||||
"<|quad_end|>": 151651,
|
||||
"<|quad_start|>": 151650,
|
||||
"<|repo_name|>": 151663,
|
||||
"<|video_pad|>": 151656,
|
||||
"<|vision_end|>": 151653,
|
||||
"<|vision_pad|>": 151654,
|
||||
"<|vision_start|>": 151652
|
||||
}
|
||||
16
all_results.json
Normal file
16
all_results.json
Normal file
@@ -0,0 +1,16 @@
|
||||
{
|
||||
"achieved_tflops_per_gpu": 25246.89276564641,
|
||||
"achieved_tflops_per_gpu_theoretical": 950998.3624027147,
|
||||
"epoch": 7.0,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.045412518084049225,
|
||||
"mfu_percent": 1784.2327042859654,
|
||||
"mfu_percent_theoretical": 67208.36483411411,
|
||||
"total_flos": 6.648213778192138e+17,
|
||||
"train_loss": 0.0,
|
||||
"train_runtime": 0.8229,
|
||||
"train_samples_per_second": 26879.554,
|
||||
"train_steps_per_second": 280.704,
|
||||
"valid_targets_mean": 5649.8,
|
||||
"valid_targets_min": 1409
|
||||
}
|
||||
89
chat_template.jinja
Normal file
89
chat_template.jinja
Normal file
@@ -0,0 +1,89 @@
|
||||
{%- if tools %}
|
||||
{{- '<|im_start|>system\n' }}
|
||||
{%- if messages[0].role == 'system' %}
|
||||
{{- messages[0].content + '\n\n' }}
|
||||
{%- endif %}
|
||||
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
||||
{%- for tool in tools %}
|
||||
{{- "\n" }}
|
||||
{{- tool | tojson }}
|
||||
{%- endfor %}
|
||||
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
||||
{%- else %}
|
||||
{%- if messages[0].role == 'system' %}
|
||||
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
||||
{%- for message in messages[::-1] %}
|
||||
{%- set index = (messages|length - 1) - loop.index0 %}
|
||||
{%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
||||
{%- set ns.multi_step_tool = false %}
|
||||
{%- set ns.last_query_index = index %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- for message in messages %}
|
||||
{%- if message.content is string %}
|
||||
{%- set content = message.content %}
|
||||
{%- else %}
|
||||
{%- set content = '' %}
|
||||
{%- endif %}
|
||||
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
||||
{%- elif message.role == "assistant" %}
|
||||
{%- set reasoning_content = '' %}
|
||||
{%- if message.reasoning_content is string %}
|
||||
{%- set reasoning_content = message.reasoning_content %}
|
||||
{%- else %}
|
||||
{%- if '</think>' in content %}
|
||||
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
||||
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- if loop.index0 > ns.last_query_index %}
|
||||
{%- if loop.last or (not loop.last and reasoning_content) %}
|
||||
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||
{%- endif %}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||
{%- endif %}
|
||||
{%- if message.tool_calls %}
|
||||
{%- for tool_call in message.tool_calls %}
|
||||
{%- if (loop.first and content) or (not loop.first) %}
|
||||
{{- '\n' }}
|
||||
{%- endif %}
|
||||
{%- if tool_call.function %}
|
||||
{%- set tool_call = tool_call.function %}
|
||||
{%- endif %}
|
||||
{{- '<tool_call>\n{"name": "' }}
|
||||
{{- tool_call.name }}
|
||||
{{- '", "arguments": ' }}
|
||||
{%- if tool_call.arguments is string %}
|
||||
{{- tool_call.arguments }}
|
||||
{%- else %}
|
||||
{{- tool_call.arguments | tojson }}
|
||||
{%- endif %}
|
||||
{{- '}\n</tool_call>' }}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- elif message.role == "tool" %}
|
||||
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
||||
{{- '<|im_start|>user' }}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_response>\n' }}
|
||||
{{- content }}
|
||||
{{- '\n</tool_response>' }}
|
||||
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- if add_generation_prompt %}
|
||||
{{- '<|im_start|>assistant\n' }}
|
||||
{%- if enable_thinking is defined and enable_thinking is false %}
|
||||
{{- '<think>\n\n</think>\n\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
68
config.json
Normal file
68
config.json
Normal file
@@ -0,0 +1,68 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen3ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 151645,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 12288,
|
||||
"layer_types": [
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention"
|
||||
],
|
||||
"max_position_embeddings": 40960,
|
||||
"max_window_layers": 36,
|
||||
"model_type": "qwen3",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 36,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 151643,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 1000000,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "4.57.6",
|
||||
"use_cache": false,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
12
generation_config.json
Normal file
12
generation_config.json
Normal file
@@ -0,0 +1,12 @@
|
||||
{
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"pad_token_id": 151643,
|
||||
"temperature": 0.6,
|
||||
"top_k": 20,
|
||||
"top_p": 0.95,
|
||||
"transformers_version": "4.57.6"
|
||||
}
|
||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model-00001-of-00004.safetensors
Normal file
3
model-00001-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:397d956bbd594bb92215c4241a4a426e569d14ff57209b5b8e02b8ac698e762f
|
||||
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 sha256:33e86342234a23c15c23e1f30a5f106165b28c83d2f2aedc689ffa2993d96258
|
||||
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 sha256:18dcd5da6aec46ec740bfeb93c4bf762b799321284b99f4ccd51c20a01c68264
|
||||
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 sha256:4e4907aba701fbd4b828f92809e227dd2efa5582dab29992ea4bd5a50ad08168
|
||||
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": "ebee68a1798546a79293aadc7ac631850f238447_thinking_preprocessed",
|
||||
"training_start": null,
|
||||
"training_end": null,
|
||||
"created_by": "DCAgent",
|
||||
"base_model_name": "Qwen/Qwen3-8B",
|
||||
"dataset_name": "/e/data1/datasets/playground/ot/hf_hub/datasets--laion--swesmith-unified-3160/snapshots/ebee68a1798546a79293aadc7ac631850f238447_thinking_preprocessed",
|
||||
"training_type": "SFT",
|
||||
"training_parameters": "https://huggingface.co/laion/swesmith-unified-3160__Qwen3-8B/blob/main/config.json",
|
||||
"wandb_link": null,
|
||||
"traces_location_s3": null
|
||||
}
|
||||
31
special_tokens_map.json
Normal file
31
special_tokens_map.json
Normal file
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"eos_token": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
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
|
||||
}
|
||||
12
train_results.json
Normal file
12
train_results.json
Normal file
@@ -0,0 +1,12 @@
|
||||
{
|
||||
"achieved_tflops_per_gpu": 25246.89276564641,
|
||||
"achieved_tflops_per_gpu_theoretical": 950998.3624027147,
|
||||
"epoch": 7.0,
|
||||
"mfu_percent": 1784.2327042859654,
|
||||
"mfu_percent_theoretical": 67208.36483411411,
|
||||
"total_flos": 6.648213778192138e+17,
|
||||
"train_loss": 0.0,
|
||||
"train_runtime": 0.8229,
|
||||
"train_samples_per_second": 26879.554,
|
||||
"train_steps_per_second": 280.704
|
||||
}
|
||||
52
trainer_log.jsonl
Normal file
52
trainer_log.jsonl
Normal file
@@ -0,0 +1,52 @@
|
||||
{"current_steps": 5, "total_steps": 231, "loss": 0.367, "lr": 6.666666666666667e-06, "epoch": 0.15151515151515152, "percentage": 2.16, "elapsed_time": "0:02:33", "remaining_time": "1:55:38"}
|
||||
{"current_steps": 10, "total_steps": 231, "loss": 0.3295, "lr": 1.5000000000000002e-05, "epoch": 0.30303030303030304, "percentage": 4.33, "elapsed_time": "0:05:01", "remaining_time": "1:50:57"}
|
||||
{"current_steps": 15, "total_steps": 231, "loss": 0.2893, "lr": 2.3333333333333336e-05, "epoch": 0.45454545454545453, "percentage": 6.49, "elapsed_time": "0:07:33", "remaining_time": "1:48:45"}
|
||||
{"current_steps": 20, "total_steps": 231, "loss": 0.2586, "lr": 3.1666666666666666e-05, "epoch": 0.6060606060606061, "percentage": 8.66, "elapsed_time": "0:10:03", "remaining_time": "1:46:01"}
|
||||
{"current_steps": 25, "total_steps": 231, "loss": 0.2338, "lr": 4e-05, "epoch": 0.7575757575757576, "percentage": 10.82, "elapsed_time": "0:12:31", "remaining_time": "1:43:11"}
|
||||
{"current_steps": 30, "total_steps": 231, "loss": 0.2068, "lr": 3.994244399375679e-05, "epoch": 0.9090909090909091, "percentage": 12.99, "elapsed_time": "0:15:02", "remaining_time": "1:40:48"}
|
||||
{"current_steps": 35, "total_steps": 231, "loss": 0.1976, "lr": 3.977010724441261e-05, "epoch": 1.0606060606060606, "percentage": 15.15, "elapsed_time": "0:17:33", "remaining_time": "1:38:21"}
|
||||
{"current_steps": 40, "total_steps": 231, "loss": 0.1883, "lr": 3.9483981653469586e-05, "epoch": 1.2121212121212122, "percentage": 17.32, "elapsed_time": "0:20:05", "remaining_time": "1:35:54"}
|
||||
{"current_steps": 45, "total_steps": 231, "loss": 0.1793, "lr": 3.908571404555758e-05, "epoch": 1.3636363636363638, "percentage": 19.48, "elapsed_time": "0:22:36", "remaining_time": "1:33:25"}
|
||||
{"current_steps": 50, "total_steps": 231, "loss": 0.18, "lr": 3.8577596689969346e-05, "epoch": 1.5151515151515151, "percentage": 21.65, "elapsed_time": "0:25:06", "remaining_time": "1:30:54"}
|
||||
{"current_steps": 55, "total_steps": 231, "loss": 0.1726, "lr": 3.7962554107273926e-05, "epoch": 1.6666666666666665, "percentage": 23.81, "elapsed_time": "0:27:36", "remaining_time": "1:28:20"}
|
||||
{"current_steps": 60, "total_steps": 231, "loss": 0.173, "lr": 3.724412623694427e-05, "epoch": 1.8181818181818183, "percentage": 25.97, "elapsed_time": "0:30:06", "remaining_time": "1:25:49"}
|
||||
{"current_steps": 65, "total_steps": 231, "loss": 0.178, "lr": 3.642644806287938e-05, "epoch": 1.9696969696969697, "percentage": 28.14, "elapsed_time": "0:32:37", "remaining_time": "1:23:20"}
|
||||
{"current_steps": 70, "total_steps": 231, "loss": 0.1706, "lr": 3.55142258140884e-05, "epoch": 2.121212121212121, "percentage": 30.3, "elapsed_time": "0:35:08", "remaining_time": "1:20:50"}
|
||||
{"current_steps": 75, "total_steps": 231, "loss": 0.1622, "lr": 3.451270987751598e-05, "epoch": 2.2727272727272725, "percentage": 32.47, "elapsed_time": "0:37:42", "remaining_time": "1:18:25"}
|
||||
{"current_steps": 80, "total_steps": 231, "loss": 0.1596, "lr": 3.342766457891194e-05, "epoch": 2.4242424242424243, "percentage": 34.63, "elapsed_time": "0:40:15", "remaining_time": "1:15:58"}
|
||||
{"current_steps": 85, "total_steps": 231, "loss": 0.1565, "lr": 3.226533500567433e-05, "epoch": 2.5757575757575757, "percentage": 36.8, "elapsed_time": "0:42:48", "remaining_time": "1:13:31"}
|
||||
{"current_steps": 90, "total_steps": 231, "loss": 0.1604, "lr": 3.1032411062620544e-05, "epoch": 2.7272727272727275, "percentage": 38.96, "elapsed_time": "0:45:17", "remaining_time": "1:10:56"}
|
||||
{"current_steps": 95, "total_steps": 231, "loss": 0.162, "lr": 2.973598896756697e-05, "epoch": 2.878787878787879, "percentage": 41.13, "elapsed_time": "0:47:46", "remaining_time": "1:08:23"}
|
||||
{"current_steps": 100, "total_steps": 231, "loss": 0.1527, "lr": 2.8383530408333285e-05, "epoch": 3.0303030303030303, "percentage": 43.29, "elapsed_time": "0:50:15", "remaining_time": "1:05:50"}
|
||||
{"current_steps": 105, "total_steps": 231, "loss": 0.1494, "lr": 2.6982819596247373e-05, "epoch": 3.1818181818181817, "percentage": 45.45, "elapsed_time": "0:52:43", "remaining_time": "1:03:16"}
|
||||
{"current_steps": 110, "total_steps": 231, "loss": 0.1517, "lr": 2.554191846333378e-05, "epoch": 3.3333333333333335, "percentage": 47.62, "elapsed_time": "0:55:11", "remaining_time": "1:00:42"}
|
||||
{"current_steps": 115, "total_steps": 231, "loss": 0.1503, "lr": 2.4069120261052682e-05, "epoch": 3.484848484848485, "percentage": 49.78, "elapsed_time": "0:57:41", "remaining_time": "0:58:11"}
|
||||
{"current_steps": 120, "total_steps": 231, "loss": 0.1504, "lr": 2.2572901827656626e-05, "epoch": 3.6363636363636362, "percentage": 51.95, "elapsed_time": "1:00:10", "remaining_time": "0:55:39"}
|
||||
{"current_steps": 125, "total_steps": 231, "loss": 0.1471, "lr": 2.1061874798894992e-05, "epoch": 3.787878787878788, "percentage": 54.11, "elapsed_time": "1:02:40", "remaining_time": "0:53:09"}
|
||||
{"current_steps": 130, "total_steps": 231, "loss": 0.1483, "lr": 1.9544736042877886e-05, "epoch": 3.9393939393939394, "percentage": 56.28, "elapsed_time": "1:05:09", "remaining_time": "0:50:37"}
|
||||
{"current_steps": 135, "total_steps": 231, "loss": 0.1394, "lr": 1.8030217604376628e-05, "epoch": 4.090909090909091, "percentage": 58.44, "elapsed_time": "1:07:39", "remaining_time": "0:48:06"}
|
||||
{"current_steps": 140, "total_steps": 231, "loss": 0.1412, "lr": 1.6527036446661396e-05, "epoch": 4.242424242424242, "percentage": 60.61, "elapsed_time": "1:10:09", "remaining_time": "0:45:36"}
|
||||
{"current_steps": 145, "total_steps": 231, "loss": 0.1369, "lr": 1.5043844280142005e-05, "epoch": 4.393939393939394, "percentage": 62.77, "elapsed_time": "1:12:41", "remaining_time": "0:43:06"}
|
||||
{"current_steps": 150, "total_steps": 231, "loss": 0.1429, "lr": 1.358917776657806e-05, "epoch": 4.545454545454545, "percentage": 64.94, "elapsed_time": "1:15:09", "remaining_time": "0:40:34"}
|
||||
{"current_steps": 155, "total_steps": 231, "loss": 0.1379, "lr": 1.2171409385463218e-05, "epoch": 4.696969696969697, "percentage": 67.1, "elapsed_time": "1:17:34", "remaining_time": "0:38:02"}
|
||||
{"current_steps": 160, "total_steps": 231, "loss": 0.147, "lr": 1.0798699245376959e-05, "epoch": 4.848484848484849, "percentage": 69.26, "elapsed_time": "1:20:02", "remaining_time": "0:35:31"}
|
||||
{"current_steps": 165, "total_steps": 231, "loss": 0.1418, "lr": 9.478948117658577e-06, "epoch": 5.0, "percentage": 71.43, "elapsed_time": "1:22:32", "remaining_time": "0:33:00"}
|
||||
{"current_steps": 170, "total_steps": 231, "loss": 0.1385, "lr": 8.219751962722726e-06, "epoch": 5.151515151515151, "percentage": 73.59, "elapsed_time": "1:24:58", "remaining_time": "0:30:29"}
|
||||
{"current_steps": 175, "total_steps": 231, "loss": 0.1335, "lr": 7.028358210744881e-06, "epoch": 5.303030303030303, "percentage": 75.76, "elapsed_time": "1:27:28", "remaining_time": "0:27:59"}
|
||||
{"current_steps": 180, "total_steps": 231, "loss": 0.1368, "lr": 5.911624048347757e-06, "epoch": 5.454545454545454, "percentage": 77.92, "elapsed_time": "1:29:57", "remaining_time": "0:25:29"}
|
||||
{"current_steps": 185, "total_steps": 231, "loss": 0.1307, "lr": 4.875976951373633e-06, "epoch": 5.606060606060606, "percentage": 80.09, "elapsed_time": "1:32:24", "remaining_time": "0:22:58"}
|
||||
{"current_steps": 190, "total_steps": 231, "loss": 0.1369, "lr": 3.927377690900436e-06, "epoch": 5.757575757575758, "percentage": 82.25, "elapsed_time": "1:34:52", "remaining_time": "0:20:28"}
|
||||
{"current_steps": 195, "total_steps": 231, "loss": 0.1389, "lr": 3.071286025423983e-06, "epoch": 5.909090909090909, "percentage": 84.42, "elapsed_time": "1:37:19", "remaining_time": "0:17:58"}
|
||||
{"current_steps": 200, "total_steps": 231, "loss": 0.1477, "lr": 2.312629276668554e-06, "epoch": 6.0606060606060606, "percentage": 86.58, "elapsed_time": "1:39:49", "remaining_time": "0:15:28"}
|
||||
{"current_steps": 205, "total_steps": 231, "loss": 0.1363, "lr": 1.6557739698909436e-06, "epoch": 6.212121212121212, "percentage": 88.74, "elapsed_time": "1:42:16", "remaining_time": "0:12:58"}
|
||||
{"current_steps": 210, "total_steps": 231, "loss": 0.1381, "lr": 1.1045007019049182e-06, "epoch": 6.363636363636363, "percentage": 90.91, "elapsed_time": "1:44:44", "remaining_time": "0:10:28"}
|
||||
{"current_steps": 215, "total_steps": 231, "loss": 0.1336, "lr": 6.619823814758786e-07, "epoch": 6.515151515151516, "percentage": 93.07, "elapsed_time": "1:47:14", "remaining_time": "0:07:58"}
|
||||
{"current_steps": 220, "total_steps": 231, "loss": 0.1378, "lr": 3.307659673251595e-07, "epoch": 6.666666666666667, "percentage": 95.24, "elapsed_time": "1:49:38", "remaining_time": "0:05:28"}
|
||||
{"current_steps": 225, "total_steps": 231, "loss": 0.1311, "lr": 1.1275780885282806e-07, "epoch": 6.818181818181818, "percentage": 97.4, "elapsed_time": "1:52:02", "remaining_time": "0:02:59"}
|
||||
{"current_steps": 230, "total_steps": 231, "loss": 0.1337, "lr": 9.212673951897177e-09, "epoch": 6.96969696969697, "percentage": 99.57, "elapsed_time": "1:54:29", "remaining_time": "0:00:29"}
|
||||
{"current_steps": 231, "total_steps": 231, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "1:55:06", "remaining_time": "0:00:00"}
|
||||
{"current_steps": 231, "total_steps": 231, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "0:00:00", "remaining_time": "0:00:00"}
|
||||
{"current_steps": 231, "total_steps": 231, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "0:00:00", "remaining_time": "0:00:00"}
|
||||
{"current_steps": 231, "total_steps": 231, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "0:00:00", "remaining_time": "0:00:00"}
|
||||
{"current_steps": 231, "total_steps": 231, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "0:00:00", "remaining_time": "0:00:00"}
|
||||
{"current_steps": 231, "total_steps": 231, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "0:00:00", "remaining_time": "0:00:00"}
|
||||
549
trainer_state.json
Normal file
549
trainer_state.json
Normal file
@@ -0,0 +1,549 @@
|
||||
{
|
||||
"best_global_step": null,
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 7.0,
|
||||
"eval_steps": 500,
|
||||
"global_step": 231,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.15151515151515152,
|
||||
"grad_norm": 3.5902750493970834,
|
||||
"learning_rate": 6.666666666666667e-06,
|
||||
"loss": 0.367,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.11483248323202133,
|
||||
"step": 5,
|
||||
"valid_targets_mean": 6069.3,
|
||||
"valid_targets_min": 1102
|
||||
},
|
||||
{
|
||||
"epoch": 0.30303030303030304,
|
||||
"grad_norm": 1.523293973634436,
|
||||
"learning_rate": 1.5000000000000002e-05,
|
||||
"loss": 0.3295,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.09902024269104004,
|
||||
"step": 10,
|
||||
"valid_targets_mean": 5740.2,
|
||||
"valid_targets_min": 975
|
||||
},
|
||||
{
|
||||
"epoch": 0.45454545454545453,
|
||||
"grad_norm": 0.5204685681128319,
|
||||
"learning_rate": 2.3333333333333336e-05,
|
||||
"loss": 0.2893,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.09341852366924286,
|
||||
"step": 15,
|
||||
"valid_targets_mean": 6076.2,
|
||||
"valid_targets_min": 826
|
||||
},
|
||||
{
|
||||
"epoch": 0.6060606060606061,
|
||||
"grad_norm": 0.42120403433587034,
|
||||
"learning_rate": 3.1666666666666666e-05,
|
||||
"loss": 0.2586,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.09784922748804092,
|
||||
"step": 20,
|
||||
"valid_targets_mean": 6676.1,
|
||||
"valid_targets_min": 1629
|
||||
},
|
||||
{
|
||||
"epoch": 0.7575757575757576,
|
||||
"grad_norm": 0.29716404096054466,
|
||||
"learning_rate": 4e-05,
|
||||
"loss": 0.2338,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.07702332735061646,
|
||||
"step": 25,
|
||||
"valid_targets_mean": 5522.2,
|
||||
"valid_targets_min": 1847
|
||||
},
|
||||
{
|
||||
"epoch": 0.9090909090909091,
|
||||
"grad_norm": 0.2074554716015637,
|
||||
"learning_rate": 3.994244399375679e-05,
|
||||
"loss": 0.2068,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.08520618081092834,
|
||||
"step": 30,
|
||||
"valid_targets_mean": 7733.2,
|
||||
"valid_targets_min": 1249
|
||||
},
|
||||
{
|
||||
"epoch": 1.0606060606060606,
|
||||
"grad_norm": 0.19383308521357237,
|
||||
"learning_rate": 3.977010724441261e-05,
|
||||
"loss": 0.1976,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.05378055199980736,
|
||||
"step": 35,
|
||||
"valid_targets_mean": 4624.0,
|
||||
"valid_targets_min": 355
|
||||
},
|
||||
{
|
||||
"epoch": 1.2121212121212122,
|
||||
"grad_norm": 0.16410603240518978,
|
||||
"learning_rate": 3.9483981653469586e-05,
|
||||
"loss": 0.1883,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.06615366041660309,
|
||||
"step": 40,
|
||||
"valid_targets_mean": 6550.9,
|
||||
"valid_targets_min": 1255
|
||||
},
|
||||
{
|
||||
"epoch": 1.3636363636363638,
|
||||
"grad_norm": 0.15449427864484538,
|
||||
"learning_rate": 3.908571404555758e-05,
|
||||
"loss": 0.1793,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.05769656226038933,
|
||||
"step": 45,
|
||||
"valid_targets_mean": 6499.9,
|
||||
"valid_targets_min": 1751
|
||||
},
|
||||
{
|
||||
"epoch": 1.5151515151515151,
|
||||
"grad_norm": 0.14398778497253703,
|
||||
"learning_rate": 3.8577596689969346e-05,
|
||||
"loss": 0.18,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.056848011910915375,
|
||||
"step": 50,
|
||||
"valid_targets_mean": 7237.5,
|
||||
"valid_targets_min": 372
|
||||
},
|
||||
{
|
||||
"epoch": 1.6666666666666665,
|
||||
"grad_norm": 0.13956070879698368,
|
||||
"learning_rate": 3.7962554107273926e-05,
|
||||
"loss": 0.1726,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.06066435948014259,
|
||||
"step": 55,
|
||||
"valid_targets_mean": 6926.7,
|
||||
"valid_targets_min": 1357
|
||||
},
|
||||
{
|
||||
"epoch": 1.8181818181818183,
|
||||
"grad_norm": 0.1443322809922013,
|
||||
"learning_rate": 3.724412623694427e-05,
|
||||
"loss": 0.173,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.05192989856004715,
|
||||
"step": 60,
|
||||
"valid_targets_mean": 5459.8,
|
||||
"valid_targets_min": 433
|
||||
},
|
||||
{
|
||||
"epoch": 1.9696969696969697,
|
||||
"grad_norm": 0.15138224844404377,
|
||||
"learning_rate": 3.642644806287938e-05,
|
||||
"loss": 0.178,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.0544576533138752,
|
||||
"step": 65,
|
||||
"valid_targets_mean": 6176.4,
|
||||
"valid_targets_min": 1173
|
||||
},
|
||||
{
|
||||
"epoch": 2.121212121212121,
|
||||
"grad_norm": 0.14788211295786652,
|
||||
"learning_rate": 3.55142258140884e-05,
|
||||
"loss": 0.1706,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.050428979098796844,
|
||||
"step": 70,
|
||||
"valid_targets_mean": 6172.1,
|
||||
"valid_targets_min": 1078
|
||||
},
|
||||
{
|
||||
"epoch": 2.2727272727272725,
|
||||
"grad_norm": 0.1489025346241851,
|
||||
"learning_rate": 3.451270987751598e-05,
|
||||
"loss": 0.1622,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.0515875369310379,
|
||||
"step": 75,
|
||||
"valid_targets_mean": 5412.4,
|
||||
"valid_targets_min": 1256
|
||||
},
|
||||
{
|
||||
"epoch": 2.4242424242424243,
|
||||
"grad_norm": 0.15974193131852008,
|
||||
"learning_rate": 3.342766457891194e-05,
|
||||
"loss": 0.1596,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.052027106285095215,
|
||||
"step": 80,
|
||||
"valid_targets_mean": 5327.2,
|
||||
"valid_targets_min": 1029
|
||||
},
|
||||
{
|
||||
"epoch": 2.5757575757575757,
|
||||
"grad_norm": 0.14890130460372,
|
||||
"learning_rate": 3.226533500567433e-05,
|
||||
"loss": 0.1565,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.05260023474693298,
|
||||
"step": 85,
|
||||
"valid_targets_mean": 6336.1,
|
||||
"valid_targets_min": 826
|
||||
},
|
||||
{
|
||||
"epoch": 2.7272727272727275,
|
||||
"grad_norm": 0.15497597762513154,
|
||||
"learning_rate": 3.1032411062620544e-05,
|
||||
"loss": 0.1604,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.0602923147380352,
|
||||
"step": 90,
|
||||
"valid_targets_mean": 5714.4,
|
||||
"valid_targets_min": 1409
|
||||
},
|
||||
{
|
||||
"epoch": 2.878787878787879,
|
||||
"grad_norm": 0.14743414796367607,
|
||||
"learning_rate": 2.973598896756697e-05,
|
||||
"loss": 0.162,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.04700557142496109,
|
||||
"step": 95,
|
||||
"valid_targets_mean": 5250.4,
|
||||
"valid_targets_min": 978
|
||||
},
|
||||
{
|
||||
"epoch": 3.0303030303030303,
|
||||
"grad_norm": 0.14875208431462822,
|
||||
"learning_rate": 2.8383530408333285e-05,
|
||||
"loss": 0.1527,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.050968416035175323,
|
||||
"step": 100,
|
||||
"valid_targets_mean": 6015.5,
|
||||
"valid_targets_min": 1215
|
||||
},
|
||||
{
|
||||
"epoch": 3.1818181818181817,
|
||||
"grad_norm": 0.14720059201307634,
|
||||
"learning_rate": 2.6982819596247373e-05,
|
||||
"loss": 0.1494,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.048501770943403244,
|
||||
"step": 105,
|
||||
"valid_targets_mean": 6575.0,
|
||||
"valid_targets_min": 1490
|
||||
},
|
||||
{
|
||||
"epoch": 3.3333333333333335,
|
||||
"grad_norm": 0.14554091849093376,
|
||||
"learning_rate": 2.554191846333378e-05,
|
||||
"loss": 0.1517,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.04890170693397522,
|
||||
"step": 110,
|
||||
"valid_targets_mean": 6384.5,
|
||||
"valid_targets_min": 1102
|
||||
},
|
||||
{
|
||||
"epoch": 3.484848484848485,
|
||||
"grad_norm": 0.14816303968679037,
|
||||
"learning_rate": 2.4069120261052682e-05,
|
||||
"loss": 0.1503,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.05088581144809723,
|
||||
"step": 115,
|
||||
"valid_targets_mean": 6863.3,
|
||||
"valid_targets_min": 2033
|
||||
},
|
||||
{
|
||||
"epoch": 3.6363636363636362,
|
||||
"grad_norm": 0.18861192867251467,
|
||||
"learning_rate": 2.2572901827656626e-05,
|
||||
"loss": 0.1504,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.051915183663368225,
|
||||
"step": 120,
|
||||
"valid_targets_mean": 5318.8,
|
||||
"valid_targets_min": 909
|
||||
},
|
||||
{
|
||||
"epoch": 3.787878787878788,
|
||||
"grad_norm": 0.17975884303700998,
|
||||
"learning_rate": 2.1061874798894992e-05,
|
||||
"loss": 0.1471,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.04352159798145294,
|
||||
"step": 125,
|
||||
"valid_targets_mean": 5009.9,
|
||||
"valid_targets_min": 372
|
||||
},
|
||||
{
|
||||
"epoch": 3.9393939393939394,
|
||||
"grad_norm": 0.14992809475322363,
|
||||
"learning_rate": 1.9544736042877886e-05,
|
||||
"loss": 0.1483,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.06831197440624237,
|
||||
"step": 130,
|
||||
"valid_targets_mean": 6830.1,
|
||||
"valid_targets_min": 947
|
||||
},
|
||||
{
|
||||
"epoch": 4.090909090909091,
|
||||
"grad_norm": 0.14832791011346455,
|
||||
"learning_rate": 1.8030217604376628e-05,
|
||||
"loss": 0.1394,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.04658203199505806,
|
||||
"step": 135,
|
||||
"valid_targets_mean": 5643.2,
|
||||
"valid_targets_min": 355
|
||||
},
|
||||
{
|
||||
"epoch": 4.242424242424242,
|
||||
"grad_norm": 0.17266841542411188,
|
||||
"learning_rate": 1.6527036446661396e-05,
|
||||
"loss": 0.1412,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.046023882925510406,
|
||||
"step": 140,
|
||||
"valid_targets_mean": 6153.0,
|
||||
"valid_targets_min": 510
|
||||
},
|
||||
{
|
||||
"epoch": 4.393939393939394,
|
||||
"grad_norm": 0.15432680905719748,
|
||||
"learning_rate": 1.5043844280142005e-05,
|
||||
"loss": 0.1369,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.04154321551322937,
|
||||
"step": 145,
|
||||
"valid_targets_mean": 6060.3,
|
||||
"valid_targets_min": 563
|
||||
},
|
||||
{
|
||||
"epoch": 4.545454545454545,
|
||||
"grad_norm": 0.15852075197915375,
|
||||
"learning_rate": 1.358917776657806e-05,
|
||||
"loss": 0.1429,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.045568957924842834,
|
||||
"step": 150,
|
||||
"valid_targets_mean": 6214.1,
|
||||
"valid_targets_min": 932
|
||||
},
|
||||
{
|
||||
"epoch": 4.696969696969697,
|
||||
"grad_norm": 0.15361105601774092,
|
||||
"learning_rate": 1.2171409385463218e-05,
|
||||
"loss": 0.1379,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.046185821294784546,
|
||||
"step": 155,
|
||||
"valid_targets_mean": 6136.9,
|
||||
"valid_targets_min": 1255
|
||||
},
|
||||
{
|
||||
"epoch": 4.848484848484849,
|
||||
"grad_norm": 0.14910920681280979,
|
||||
"learning_rate": 1.0798699245376959e-05,
|
||||
"loss": 0.147,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.053926583379507065,
|
||||
"step": 160,
|
||||
"valid_targets_mean": 7605.3,
|
||||
"valid_targets_min": 1808
|
||||
},
|
||||
{
|
||||
"epoch": 5.0,
|
||||
"grad_norm": 0.15956391595199854,
|
||||
"learning_rate": 9.478948117658577e-06,
|
||||
"loss": 0.1418,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.04224388301372528,
|
||||
"step": 165,
|
||||
"valid_targets_mean": 4956.4,
|
||||
"valid_targets_min": 1186
|
||||
},
|
||||
{
|
||||
"epoch": 5.151515151515151,
|
||||
"grad_norm": 0.16166354923486542,
|
||||
"learning_rate": 8.219751962722726e-06,
|
||||
"loss": 0.1385,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.04815865680575371,
|
||||
"step": 170,
|
||||
"valid_targets_mean": 6351.8,
|
||||
"valid_targets_min": 1414
|
||||
},
|
||||
{
|
||||
"epoch": 5.303030303030303,
|
||||
"grad_norm": 0.15713749630090504,
|
||||
"learning_rate": 7.028358210744881e-06,
|
||||
"loss": 0.1335,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.04832237958908081,
|
||||
"step": 175,
|
||||
"valid_targets_mean": 6324.0,
|
||||
"valid_targets_min": 537
|
||||
},
|
||||
{
|
||||
"epoch": 5.454545454545454,
|
||||
"grad_norm": 0.16623362872731065,
|
||||
"learning_rate": 5.911624048347757e-06,
|
||||
"loss": 0.1368,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.04412321001291275,
|
||||
"step": 180,
|
||||
"valid_targets_mean": 5107.0,
|
||||
"valid_targets_min": 975
|
||||
},
|
||||
{
|
||||
"epoch": 5.606060606060606,
|
||||
"grad_norm": 0.14675183366084796,
|
||||
"learning_rate": 4.875976951373633e-06,
|
||||
"loss": 0.1307,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.03708821162581444,
|
||||
"step": 185,
|
||||
"valid_targets_mean": 6408.9,
|
||||
"valid_targets_min": 1162
|
||||
},
|
||||
{
|
||||
"epoch": 5.757575757575758,
|
||||
"grad_norm": 0.16118513545891452,
|
||||
"learning_rate": 3.927377690900436e-06,
|
||||
"loss": 0.1369,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.04341595247387886,
|
||||
"step": 190,
|
||||
"valid_targets_mean": 6496.9,
|
||||
"valid_targets_min": 1027
|
||||
},
|
||||
{
|
||||
"epoch": 5.909090909090909,
|
||||
"grad_norm": 0.18904653293771853,
|
||||
"learning_rate": 3.071286025423983e-06,
|
||||
"loss": 0.1389,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.059906527400016785,
|
||||
"step": 195,
|
||||
"valid_targets_mean": 6184.4,
|
||||
"valid_targets_min": 978
|
||||
},
|
||||
{
|
||||
"epoch": 6.0606060606060606,
|
||||
"grad_norm": 0.16058499044576713,
|
||||
"learning_rate": 2.312629276668554e-06,
|
||||
"loss": 0.1477,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.0467909500002861,
|
||||
"step": 200,
|
||||
"valid_targets_mean": 5470.1,
|
||||
"valid_targets_min": 1107
|
||||
},
|
||||
{
|
||||
"epoch": 6.212121212121212,
|
||||
"grad_norm": 0.16458313236617705,
|
||||
"learning_rate": 1.6557739698909436e-06,
|
||||
"loss": 0.1363,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.039594992995262146,
|
||||
"step": 205,
|
||||
"valid_targets_mean": 6872.1,
|
||||
"valid_targets_min": 1222
|
||||
},
|
||||
{
|
||||
"epoch": 6.363636363636363,
|
||||
"grad_norm": 0.1520783842215095,
|
||||
"learning_rate": 1.1045007019049182e-06,
|
||||
"loss": 0.1381,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.042891182005405426,
|
||||
"step": 210,
|
||||
"valid_targets_mean": 5591.5,
|
||||
"valid_targets_min": 1134
|
||||
},
|
||||
{
|
||||
"epoch": 6.515151515151516,
|
||||
"grad_norm": 0.17583323971560555,
|
||||
"learning_rate": 6.619823814758786e-07,
|
||||
"loss": 0.1336,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.04007503390312195,
|
||||
"step": 215,
|
||||
"valid_targets_mean": 5927.2,
|
||||
"valid_targets_min": 1202
|
||||
},
|
||||
{
|
||||
"epoch": 6.666666666666667,
|
||||
"grad_norm": 0.15107528231407247,
|
||||
"learning_rate": 3.307659673251595e-07,
|
||||
"loss": 0.1378,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.05574905872344971,
|
||||
"step": 220,
|
||||
"valid_targets_mean": 7710.5,
|
||||
"valid_targets_min": 975
|
||||
},
|
||||
{
|
||||
"epoch": 6.818181818181818,
|
||||
"grad_norm": 0.1525570611116513,
|
||||
"learning_rate": 1.1275780885282806e-07,
|
||||
"loss": 0.1311,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.036159858107566833,
|
||||
"step": 225,
|
||||
"valid_targets_mean": 6852.6,
|
||||
"valid_targets_min": 474
|
||||
},
|
||||
{
|
||||
"epoch": 6.96969696969697,
|
||||
"grad_norm": 0.1772473530958802,
|
||||
"learning_rate": 9.212673951897177e-09,
|
||||
"loss": 0.1337,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.048351939767599106,
|
||||
"step": 230,
|
||||
"valid_targets_mean": 7166.3,
|
||||
"valid_targets_min": 1121
|
||||
},
|
||||
{
|
||||
"epoch": 7.0,
|
||||
"step": 231,
|
||||
"total_flos": 6.648213778192138e+17,
|
||||
"train_loss": 0.0,
|
||||
"train_runtime": 0.8229,
|
||||
"train_samples_per_second": 26879.554,
|
||||
"train_steps_per_second": 280.704
|
||||
}
|
||||
],
|
||||
"logging_steps": 5,
|
||||
"max_steps": 231,
|
||||
"num_input_tokens_seen": 0,
|
||||
"num_train_epochs": 7,
|
||||
"save_steps": 300,
|
||||
"stateful_callbacks": {
|
||||
"TrainerControl": {
|
||||
"args": {
|
||||
"should_epoch_stop": false,
|
||||
"should_evaluate": false,
|
||||
"should_log": false,
|
||||
"should_save": true,
|
||||
"should_training_stop": true
|
||||
},
|
||||
"attributes": {}
|
||||
}
|
||||
},
|
||||
"total_flos": 6.648213778192138e+17,
|
||||
"train_batch_size": 1,
|
||||
"trial_name": null,
|
||||
"trial_params": null
|
||||
}
|
||||
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 sha256:75b0709038736c41bed8fd986360f8250dd202549dda10b15287ebcbc870550b
|
||||
size 8657
|
||||
BIN
training_loss.png
Normal file
BIN
training_loss.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 39 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