初始化项目，由ModelHub XC社区提供模型
Model: shubhamrgandhi/qwen3-8b-full-sft-prm-opus-distill-32k-lr5e6-flattened Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -0,0 +1,36 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
60
README.md
Normal file
60
README.md
Normal file
@@ -0,0 +1,60 @@
|
||||
---
|
||||
library_name: transformers
|
||||
license: other
|
||||
base_model: Qwen/Qwen3-8B
|
||||
tags:
|
||||
- llama-factory
|
||||
- full
|
||||
- generated_from_trainer
|
||||
model-index:
|
||||
- name: qwen3-8b-full-sft-prm-opus-distill-32k-lr5e6-flattened
|
||||
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. -->
|
||||
|
||||
# qwen3-8b-full-sft-prm-opus-distill-32k-lr5e6-flattened
|
||||
|
||||
This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on the prm_sft_train 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: 5e-06
|
||||
- train_batch_size: 1
|
||||
- eval_batch_size: 8
|
||||
- seed: 42
|
||||
- distributed_type: multi-GPU
|
||||
- num_devices: 8
|
||||
- total_train_batch_size: 8
|
||||
- total_eval_batch_size: 64
|
||||
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
||||
- lr_scheduler_type: cosine
|
||||
- lr_scheduler_warmup_ratio: 0.1
|
||||
- num_epochs: 3.0
|
||||
|
||||
### Training results
|
||||
|
||||
|
||||
|
||||
### Framework versions
|
||||
|
||||
- Transformers 4.57.6
|
||||
- Pytorch 2.9.1+cu128
|
||||
- Datasets 4.0.0
|
||||
- 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
|
||||
}
|
||||
8
all_results.json
Normal file
8
all_results.json
Normal file
@@ -0,0 +1,8 @@
|
||||
{
|
||||
"epoch": 3.0,
|
||||
"total_flos": 6.988388070252872e+17,
|
||||
"train_loss": 0.41709409590923424,
|
||||
"train_runtime": 37712.5646,
|
||||
"train_samples_per_second": 0.14,
|
||||
"train_steps_per_second": 0.018
|
||||
}
|
||||
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": "float32",
|
||||
"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-00007.safetensors
Normal file
3
model-00001-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b4ef3c6f15f7e3b16ac93f112cd65913fac0adb02bcce9d23cd35d9a4e0317f2
|
||||
size 4972454376
|
||||
3
model-00002-of-00007.safetensors
Normal file
3
model-00002-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b45a081fba864dcfbae5c6193eebd4960d437c48a0541e811c98321004ef4739
|
||||
size 4832048608
|
||||
3
model-00003-of-00007.safetensors
Normal file
3
model-00003-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:422ebe3ae19a555d839854c76079cafad6f5b6681ee92082fc2391759d1dd710
|
||||
size 4832048656
|
||||
3
model-00004-of-00007.safetensors
Normal file
3
model-00004-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5fea5d37cce14357e5ce5e6d231b96a99f434e005283f2b941487c4cd280df68
|
||||
size 4999855528
|
||||
3
model-00005-of-00007.safetensors
Normal file
3
model-00005-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2092d83ea347810640b944a66d2776437b67ddee41462e46f0653a72ff6d3a51
|
||||
size 4832048672
|
||||
3
model-00006-of-00007.safetensors
Normal file
3
model-00006-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:96bcdc5823932d34bd2b7d4e56b2b16578b099b1e1e5656101799b36d29ed5af
|
||||
size 4832048672
|
||||
3
model-00007-of-00007.safetensors
Normal file
3
model-00007-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:06be1afcb5ab8f49e41936d613681d1983740a33b71efd3cecc417a311729edc
|
||||
size 3462482728
|
||||
407
model.safetensors.index.json
Normal file
407
model.safetensors.index.json
Normal file
@@ -0,0 +1,407 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_parameters": 1023841920,
|
||||
"total_size": 32762941440
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00007-of-00007.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.self_attn.k_norm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.self_attn.q_norm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.self_attn.q_norm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.10.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.10.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.11.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.11.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.12.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.12.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.13.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.13.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.14.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.14.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.15.self_attn.k_norm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.15.self_attn.q_norm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.16.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.16.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.17.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.17.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.18.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.18.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.19.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.19.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.2.self_attn.k_norm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.2.self_attn.q_norm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.20.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.20.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.21.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.21.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.22.self_attn.k_norm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.22.self_attn.q_norm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.23.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.23.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.24.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.24.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.25.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.25.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.26.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.26.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.27.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.27.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.28.self_attn.k_norm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.28.self_attn.q_norm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.29.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.29.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.3.self_attn.k_norm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.3.self_attn.q_norm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.30.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.30.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.31.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.31.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.32.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.32.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.33.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.33.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.34.self_attn.k_norm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.34.self_attn.q_norm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.35.self_attn.k_norm.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.35.self_attn.q_norm.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.4.self_attn.k_norm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.4.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.5.self_attn.k_norm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.5.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.6.self_attn.k_norm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.6.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.7.self_attn.k_norm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.7.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.8.self_attn.k_norm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.8.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.9.self_attn.k_norm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.9.self_attn.q_norm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.norm.weight": "model-00007-of-00007.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
|
||||
}
|
||||
}
|
||||
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": 131072,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"padding_side": "right",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
8
train_results.json
Normal file
8
train_results.json
Normal file
@@ -0,0 +1,8 @@
|
||||
{
|
||||
"epoch": 3.0,
|
||||
"total_flos": 6.988388070252872e+17,
|
||||
"train_loss": 0.41709409590923424,
|
||||
"train_runtime": 37712.5646,
|
||||
"train_samples_per_second": 0.14,
|
||||
"train_steps_per_second": 0.018
|
||||
}
|
||||
67
trainer_log.jsonl
Normal file
67
trainer_log.jsonl
Normal file
@@ -0,0 +1,67 @@
|
||||
{"current_steps": 10, "total_steps": 660, "loss": 1.0602, "lr": 6.818181818181818e-07, "epoch": 0.045454545454545456, "percentage": 1.52, "elapsed_time": "0:09:42", "remaining_time": "10:31:09"}
|
||||
{"current_steps": 20, "total_steps": 660, "loss": 0.9686, "lr": 1.4393939393939396e-06, "epoch": 0.09090909090909091, "percentage": 3.03, "elapsed_time": "0:19:06", "remaining_time": "10:11:25"}
|
||||
{"current_steps": 30, "total_steps": 660, "loss": 0.8175, "lr": 2.196969696969697e-06, "epoch": 0.13636363636363635, "percentage": 4.55, "elapsed_time": "0:28:42", "remaining_time": "10:02:58"}
|
||||
{"current_steps": 40, "total_steps": 660, "loss": 0.7458, "lr": 2.954545454545455e-06, "epoch": 0.18181818181818182, "percentage": 6.06, "elapsed_time": "0:38:16", "remaining_time": "9:53:19"}
|
||||
{"current_steps": 50, "total_steps": 660, "loss": 0.6929, "lr": 3.7121212121212124e-06, "epoch": 0.22727272727272727, "percentage": 7.58, "elapsed_time": "0:47:48", "remaining_time": "9:43:16"}
|
||||
{"current_steps": 60, "total_steps": 660, "loss": 0.6465, "lr": 4.46969696969697e-06, "epoch": 0.2727272727272727, "percentage": 9.09, "elapsed_time": "0:57:23", "remaining_time": "9:33:51"}
|
||||
{"current_steps": 70, "total_steps": 660, "loss": 0.5931, "lr": 4.999685319184688e-06, "epoch": 0.3181818181818182, "percentage": 10.61, "elapsed_time": "1:06:51", "remaining_time": "9:23:31"}
|
||||
{"current_steps": 80, "total_steps": 660, "loss": 0.6159, "lr": 4.994093197099587e-06, "epoch": 0.36363636363636365, "percentage": 12.12, "elapsed_time": "1:16:21", "remaining_time": "9:13:33"}
|
||||
{"current_steps": 90, "total_steps": 660, "loss": 0.6072, "lr": 4.981526170026621e-06, "epoch": 0.4090909090909091, "percentage": 13.64, "elapsed_time": "1:25:53", "remaining_time": "9:03:56"}
|
||||
{"current_steps": 100, "total_steps": 660, "loss": 0.6049, "lr": 4.962019382530521e-06, "epoch": 0.45454545454545453, "percentage": 15.15, "elapsed_time": "1:35:18", "remaining_time": "8:53:45"}
|
||||
{"current_steps": 110, "total_steps": 660, "loss": 0.5677, "lr": 4.935627386698418e-06, "epoch": 0.5, "percentage": 16.67, "elapsed_time": "1:44:32", "remaining_time": "8:42:42"}
|
||||
{"current_steps": 120, "total_steps": 660, "loss": 0.5668, "lr": 4.902423989581143e-06, "epoch": 0.5454545454545454, "percentage": 18.18, "elapsed_time": "1:54:03", "remaining_time": "8:33:16"}
|
||||
{"current_steps": 130, "total_steps": 660, "loss": 0.5495, "lr": 4.862502046786671e-06, "epoch": 0.5909090909090909, "percentage": 19.7, "elapsed_time": "2:03:18", "remaining_time": "8:22:44"}
|
||||
{"current_steps": 140, "total_steps": 660, "loss": 0.5233, "lr": 4.815973202802966e-06, "epoch": 0.6363636363636364, "percentage": 21.21, "elapsed_time": "2:12:19", "remaining_time": "8:11:28"}
|
||||
{"current_steps": 150, "total_steps": 660, "loss": 0.5896, "lr": 4.762967578776406e-06, "epoch": 0.6818181818181818, "percentage": 22.73, "elapsed_time": "2:21:32", "remaining_time": "8:01:13"}
|
||||
{"current_steps": 160, "total_steps": 660, "loss": 0.5506, "lr": 4.703633408618955e-06, "epoch": 0.7272727272727273, "percentage": 24.24, "elapsed_time": "2:30:56", "remaining_time": "7:51:42"}
|
||||
{"current_steps": 170, "total_steps": 660, "loss": 0.5161, "lr": 4.638136624461723e-06, "epoch": 0.7727272727272727, "percentage": 25.76, "elapsed_time": "2:40:07", "remaining_time": "7:41:33"}
|
||||
{"current_steps": 180, "total_steps": 660, "loss": 0.569, "lr": 4.566660392614229e-06, "epoch": 0.8181818181818182, "percentage": 27.27, "elapsed_time": "2:49:38", "remaining_time": "7:32:22"}
|
||||
{"current_steps": 190, "total_steps": 660, "loss": 0.555, "lr": 4.489404601327081e-06, "epoch": 0.8636363636363636, "percentage": 28.79, "elapsed_time": "2:59:07", "remaining_time": "7:23:05"}
|
||||
{"current_steps": 200, "total_steps": 660, "loss": 0.5055, "lr": 4.406585301790595e-06, "epoch": 0.9090909090909091, "percentage": 30.3, "elapsed_time": "3:08:43", "remaining_time": "7:14:02"}
|
||||
{"current_steps": 210, "total_steps": 660, "loss": 0.5378, "lr": 4.318434103932622e-06, "epoch": 0.9545454545454546, "percentage": 31.82, "elapsed_time": "3:18:18", "remaining_time": "7:04:56"}
|
||||
{"current_steps": 220, "total_steps": 660, "loss": 0.4894, "lr": 4.2251975287052804e-06, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "3:27:54", "remaining_time": "6:55:48"}
|
||||
{"current_steps": 230, "total_steps": 660, "loss": 0.3795, "lr": 4.127136318671984e-06, "epoch": 1.0454545454545454, "percentage": 34.85, "elapsed_time": "3:38:18", "remaining_time": "6:48:08"}
|
||||
{"current_steps": 240, "total_steps": 660, "loss": 0.3842, "lr": 4.024524708822739e-06, "epoch": 1.0909090909090908, "percentage": 36.36, "elapsed_time": "3:47:56", "remaining_time": "6:38:54"}
|
||||
{"current_steps": 250, "total_steps": 660, "loss": 0.3773, "lr": 3.917649659656927e-06, "epoch": 1.1363636363636362, "percentage": 37.88, "elapsed_time": "3:57:30", "remaining_time": "6:29:31"}
|
||||
{"current_steps": 260, "total_steps": 660, "loss": 0.3814, "lr": 3.8068100546783315e-06, "epoch": 1.1818181818181819, "percentage": 39.39, "elapsed_time": "4:07:13", "remaining_time": "6:20:20"}
|
||||
{"current_steps": 270, "total_steps": 660, "loss": 0.3861, "lr": 3.692315864546635e-06, "epoch": 1.2272727272727273, "percentage": 40.91, "elapsed_time": "4:16:42", "remaining_time": "6:10:47"}
|
||||
{"current_steps": 280, "total_steps": 660, "loss": 0.401, "lr": 3.5744872802229296e-06, "epoch": 1.2727272727272727, "percentage": 42.42, "elapsed_time": "4:26:15", "remaining_time": "6:01:20"}
|
||||
{"current_steps": 290, "total_steps": 660, "loss": 0.3942, "lr": 3.453653817533435e-06, "epoch": 1.3181818181818181, "percentage": 43.94, "elapsed_time": "4:35:40", "remaining_time": "5:51:43"}
|
||||
{"current_steps": 300, "total_steps": 660, "loss": 0.3784, "lr": 3.3301533956555886e-06, "epoch": 1.3636363636363638, "percentage": 45.45, "elapsed_time": "4:45:12", "remaining_time": "5:42:15"}
|
||||
{"current_steps": 310, "total_steps": 660, "loss": 0.4004, "lr": 3.2043313921035747e-06, "epoch": 1.4090909090909092, "percentage": 46.97, "elapsed_time": "4:54:42", "remaining_time": "5:32:43"}
|
||||
{"current_steps": 320, "total_steps": 660, "loss": 0.3663, "lr": 3.0765396768561005e-06, "epoch": 1.4545454545454546, "percentage": 48.48, "elapsed_time": "5:04:06", "remaining_time": "5:23:07"}
|
||||
{"current_steps": 330, "total_steps": 660, "loss": 0.4158, "lr": 2.9471356283275444e-06, "epoch": 1.5, "percentage": 50.0, "elapsed_time": "5:13:50", "remaining_time": "5:13:50"}
|
||||
{"current_steps": 340, "total_steps": 660, "loss": 0.3799, "lr": 2.8164811339343736e-06, "epoch": 1.5454545454545454, "percentage": 51.52, "elapsed_time": "5:23:14", "remaining_time": "5:04:14"}
|
||||
{"current_steps": 350, "total_steps": 660, "loss": 0.3974, "lr": 2.684941578051836e-06, "epoch": 1.5909090909090908, "percentage": 53.03, "elapsed_time": "5:32:48", "remaining_time": "4:54:46"}
|
||||
{"current_steps": 360, "total_steps": 660, "loss": 0.3846, "lr": 2.5528848201911543e-06, "epoch": 1.6363636363636362, "percentage": 54.55, "elapsed_time": "5:42:28", "remaining_time": "4:45:23"}
|
||||
{"current_steps": 370, "total_steps": 660, "loss": 0.3881, "lr": 2.4206801662548314e-06, "epoch": 1.6818181818181817, "percentage": 56.06, "elapsed_time": "5:51:40", "remaining_time": "4:35:37"}
|
||||
{"current_steps": 380, "total_steps": 660, "loss": 0.3729, "lr": 2.288697335747027e-06, "epoch": 1.7272727272727273, "percentage": 57.58, "elapsed_time": "6:01:11", "remaining_time": "4:26:08"}
|
||||
{"current_steps": 390, "total_steps": 660, "loss": 0.3735, "lr": 2.157305427827264e-06, "epoch": 1.7727272727272727, "percentage": 59.09, "elapsed_time": "6:10:44", "remaining_time": "4:16:40"}
|
||||
{"current_steps": 400, "total_steps": 660, "loss": 0.3767, "lr": 2.0268718890989754e-06, "epoch": 1.8181818181818183, "percentage": 60.61, "elapsed_time": "6:20:05", "remaining_time": "4:07:03"}
|
||||
{"current_steps": 410, "total_steps": 660, "loss": 0.3745, "lr": 1.8977614860195297e-06, "epoch": 1.8636363636363638, "percentage": 62.12, "elapsed_time": "6:29:24", "remaining_time": "3:57:26"}
|
||||
{"current_steps": 420, "total_steps": 660, "loss": 0.3658, "lr": 1.7703352848054888e-06, "epoch": 1.9090909090909092, "percentage": 63.64, "elapsed_time": "6:38:54", "remaining_time": "3:47:56"}
|
||||
{"current_steps": 430, "total_steps": 660, "loss": 0.3731, "lr": 1.6449496416858285e-06, "epoch": 1.9545454545454546, "percentage": 65.15, "elapsed_time": "6:48:22", "remaining_time": "3:38:25"}
|
||||
{"current_steps": 440, "total_steps": 660, "loss": 0.3567, "lr": 1.521955206326976e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "6:57:57", "remaining_time": "3:28:58"}
|
||||
{"current_steps": 450, "total_steps": 660, "loss": 0.2403, "lr": 1.401695941216644e-06, "epoch": 2.0454545454545454, "percentage": 68.18, "elapsed_time": "7:08:14", "remaining_time": "3:19:50"}
|
||||
{"current_steps": 460, "total_steps": 660, "loss": 0.2391, "lr": 1.2845081597488288e-06, "epoch": 2.090909090909091, "percentage": 69.7, "elapsed_time": "7:17:51", "remaining_time": "3:10:22"}
|
||||
{"current_steps": 470, "total_steps": 660, "loss": 0.2451, "lr": 1.1707195857000218e-06, "epoch": 2.1363636363636362, "percentage": 71.21, "elapsed_time": "7:27:22", "remaining_time": "3:00:51"}
|
||||
{"current_steps": 480, "total_steps": 660, "loss": 0.2646, "lr": 1.0606484367268906e-06, "epoch": 2.1818181818181817, "percentage": 72.73, "elapsed_time": "7:36:56", "remaining_time": "2:51:21"}
|
||||
{"current_steps": 490, "total_steps": 660, "loss": 0.2316, "lr": 9.546025344484868e-07, "epoch": 2.227272727272727, "percentage": 74.24, "elapsed_time": "7:46:27", "remaining_time": "2:41:49"}
|
||||
{"current_steps": 500, "total_steps": 660, "loss": 0.2326, "lr": 8.528784436016879e-07, "epoch": 2.2727272727272725, "percentage": 75.76, "elapsed_time": "7:55:55", "remaining_time": "2:32:17"}
|
||||
{"current_steps": 510, "total_steps": 660, "loss": 0.2425, "lr": 7.557606426772962e-07, "epoch": 2.3181818181818183, "percentage": 77.27, "elapsed_time": "8:05:39", "remaining_time": "2:22:50"}
|
||||
{"current_steps": 520, "total_steps": 660, "loss": 0.2402, "lr": 6.635207283561671e-07, "epoch": 2.3636363636363638, "percentage": 78.79, "elapsed_time": "8:15:10", "remaining_time": "2:13:18"}
|
||||
{"current_steps": 530, "total_steps": 660, "loss": 0.2552, "lr": 5.764166559702145e-07, "epoch": 2.409090909090909, "percentage": 80.3, "elapsed_time": "8:24:35", "remaining_time": "2:03:45"}
|
||||
{"current_steps": 540, "total_steps": 660, "loss": 0.2288, "lr": 4.946920181123904e-07, "epoch": 2.4545454545454546, "percentage": 81.82, "elapsed_time": "8:34:10", "remaining_time": "1:54:15"}
|
||||
{"current_steps": 550, "total_steps": 660, "loss": 0.2302, "lr": 4.185753634130718e-07, "epoch": 2.5, "percentage": 83.33, "elapsed_time": "8:43:09", "remaining_time": "1:44:37"}
|
||||
{"current_steps": 560, "total_steps": 660, "loss": 0.2486, "lr": 3.482795573879241e-07, "epoch": 2.5454545454545454, "percentage": 84.85, "elapsed_time": "8:52:49", "remaining_time": "1:35:08"}
|
||||
{"current_steps": 570, "total_steps": 660, "loss": 0.2389, "lr": 2.840011871446963e-07, "epoch": 2.590909090909091, "percentage": 86.36, "elapsed_time": "9:02:18", "remaining_time": "1:25:37"}
|
||||
{"current_steps": 580, "total_steps": 660, "loss": 0.2463, "lr": 2.2592001161370392e-07, "epoch": 2.6363636363636362, "percentage": 87.88, "elapsed_time": "9:11:47", "remaining_time": "1:16:06"}
|
||||
{"current_steps": 590, "total_steps": 660, "loss": 0.2235, "lr": 1.74198458839491e-07, "epoch": 2.6818181818181817, "percentage": 89.39, "elapsed_time": "9:20:54", "remaining_time": "1:06:32"}
|
||||
{"current_steps": 600, "total_steps": 660, "loss": 0.2358, "lr": 1.289811717395087e-07, "epoch": 2.7272727272727275, "percentage": 90.91, "elapsed_time": "9:30:10", "remaining_time": "0:57:01"}
|
||||
{"current_steps": 610, "total_steps": 660, "loss": 0.23, "lr": 9.03946036001449e-08, "epoch": 2.7727272727272725, "percentage": 92.42, "elapsed_time": "9:39:28", "remaining_time": "0:47:29"}
|
||||
{"current_steps": 620, "total_steps": 660, "loss": 0.2348, "lr": 5.8546664441319346e-08, "epoch": 2.8181818181818183, "percentage": 93.94, "elapsed_time": "9:49:16", "remaining_time": "0:38:01"}
|
||||
{"current_steps": 630, "total_steps": 660, "loss": 0.247, "lr": 3.352641923861144e-08, "epoch": 2.8636363636363638, "percentage": 95.45, "elapsed_time": "9:58:45", "remaining_time": "0:28:30"}
|
||||
{"current_steps": 640, "total_steps": 660, "loss": 0.2284, "lr": 1.5403838846864694e-08, "epoch": 2.909090909090909, "percentage": 96.97, "elapsed_time": "10:08:21", "remaining_time": "0:19:00"}
|
||||
{"current_steps": 650, "total_steps": 660, "loss": 0.2312, "lr": 4.229604321829561e-09, "epoch": 2.9545454545454546, "percentage": 98.48, "elapsed_time": "10:17:55", "remaining_time": "0:09:30"}
|
||||
{"current_steps": 660, "total_steps": 660, "loss": 0.2323, "lr": 3.496518706597174e-11, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "10:27:27", "remaining_time": "0:00:00"}
|
||||
{"current_steps": 660, "total_steps": 660, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "10:28:32", "remaining_time": "0:00:00"}
|
||||
505
trainer_state.json
Normal file
505
trainer_state.json
Normal file
@@ -0,0 +1,505 @@
|
||||
{
|
||||
"best_global_step": null,
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 3.0,
|
||||
"eval_steps": 500,
|
||||
"global_step": 660,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.045454545454545456,
|
||||
"grad_norm": 12.912503242492676,
|
||||
"learning_rate": 6.818181818181818e-07,
|
||||
"loss": 1.0602,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"epoch": 0.09090909090909091,
|
||||
"grad_norm": 4.66077995300293,
|
||||
"learning_rate": 1.4393939393939396e-06,
|
||||
"loss": 0.9686,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 0.13636363636363635,
|
||||
"grad_norm": 2.7883694171905518,
|
||||
"learning_rate": 2.196969696969697e-06,
|
||||
"loss": 0.8175,
|
||||
"step": 30
|
||||
},
|
||||
{
|
||||
"epoch": 0.18181818181818182,
|
||||
"grad_norm": 2.6756789684295654,
|
||||
"learning_rate": 2.954545454545455e-06,
|
||||
"loss": 0.7458,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 0.22727272727272727,
|
||||
"grad_norm": 2.839015245437622,
|
||||
"learning_rate": 3.7121212121212124e-06,
|
||||
"loss": 0.6929,
|
||||
"step": 50
|
||||
},
|
||||
{
|
||||
"epoch": 0.2727272727272727,
|
||||
"grad_norm": 2.581166982650757,
|
||||
"learning_rate": 4.46969696969697e-06,
|
||||
"loss": 0.6465,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 0.3181818181818182,
|
||||
"grad_norm": 2.901815414428711,
|
||||
"learning_rate": 4.999685319184688e-06,
|
||||
"loss": 0.5931,
|
||||
"step": 70
|
||||
},
|
||||
{
|
||||
"epoch": 0.36363636363636365,
|
||||
"grad_norm": 2.5252325534820557,
|
||||
"learning_rate": 4.994093197099587e-06,
|
||||
"loss": 0.6159,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 0.4090909090909091,
|
||||
"grad_norm": 2.8176751136779785,
|
||||
"learning_rate": 4.981526170026621e-06,
|
||||
"loss": 0.6072,
|
||||
"step": 90
|
||||
},
|
||||
{
|
||||
"epoch": 0.45454545454545453,
|
||||
"grad_norm": 2.517207622528076,
|
||||
"learning_rate": 4.962019382530521e-06,
|
||||
"loss": 0.6049,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 0.5,
|
||||
"grad_norm": 2.6463892459869385,
|
||||
"learning_rate": 4.935627386698418e-06,
|
||||
"loss": 0.5677,
|
||||
"step": 110
|
||||
},
|
||||
{
|
||||
"epoch": 0.5454545454545454,
|
||||
"grad_norm": 3.6619322299957275,
|
||||
"learning_rate": 4.902423989581143e-06,
|
||||
"loss": 0.5668,
|
||||
"step": 120
|
||||
},
|
||||
{
|
||||
"epoch": 0.5909090909090909,
|
||||
"grad_norm": 2.821599245071411,
|
||||
"learning_rate": 4.862502046786671e-06,
|
||||
"loss": 0.5495,
|
||||
"step": 130
|
||||
},
|
||||
{
|
||||
"epoch": 0.6363636363636364,
|
||||
"grad_norm": 2.5070018768310547,
|
||||
"learning_rate": 4.815973202802966e-06,
|
||||
"loss": 0.5233,
|
||||
"step": 140
|
||||
},
|
||||
{
|
||||
"epoch": 0.6818181818181818,
|
||||
"grad_norm": 2.5705134868621826,
|
||||
"learning_rate": 4.762967578776406e-06,
|
||||
"loss": 0.5896,
|
||||
"step": 150
|
||||
},
|
||||
{
|
||||
"epoch": 0.7272727272727273,
|
||||
"grad_norm": 2.4343154430389404,
|
||||
"learning_rate": 4.703633408618955e-06,
|
||||
"loss": 0.5506,
|
||||
"step": 160
|
||||
},
|
||||
{
|
||||
"epoch": 0.7727272727272727,
|
||||
"grad_norm": 2.4548699855804443,
|
||||
"learning_rate": 4.638136624461723e-06,
|
||||
"loss": 0.5161,
|
||||
"step": 170
|
||||
},
|
||||
{
|
||||
"epoch": 0.8181818181818182,
|
||||
"grad_norm": 2.902329683303833,
|
||||
"learning_rate": 4.566660392614229e-06,
|
||||
"loss": 0.569,
|
||||
"step": 180
|
||||
},
|
||||
{
|
||||
"epoch": 0.8636363636363636,
|
||||
"grad_norm": 2.5096774101257324,
|
||||
"learning_rate": 4.489404601327081e-06,
|
||||
"loss": 0.555,
|
||||
"step": 190
|
||||
},
|
||||
{
|
||||
"epoch": 0.9090909090909091,
|
||||
"grad_norm": 2.590094566345215,
|
||||
"learning_rate": 4.406585301790595e-06,
|
||||
"loss": 0.5055,
|
||||
"step": 200
|
||||
},
|
||||
{
|
||||
"epoch": 0.9545454545454546,
|
||||
"grad_norm": 2.6825978755950928,
|
||||
"learning_rate": 4.318434103932622e-06,
|
||||
"loss": 0.5378,
|
||||
"step": 210
|
||||
},
|
||||
{
|
||||
"epoch": 1.0,
|
||||
"grad_norm": 3.1130728721618652,
|
||||
"learning_rate": 4.2251975287052804e-06,
|
||||
"loss": 0.4894,
|
||||
"step": 220
|
||||
},
|
||||
{
|
||||
"epoch": 1.0454545454545454,
|
||||
"grad_norm": 2.508296012878418,
|
||||
"learning_rate": 4.127136318671984e-06,
|
||||
"loss": 0.3795,
|
||||
"step": 230
|
||||
},
|
||||
{
|
||||
"epoch": 1.0909090909090908,
|
||||
"grad_norm": 2.275791883468628,
|
||||
"learning_rate": 4.024524708822739e-06,
|
||||
"loss": 0.3842,
|
||||
"step": 240
|
||||
},
|
||||
{
|
||||
"epoch": 1.1363636363636362,
|
||||
"grad_norm": 2.366997718811035,
|
||||
"learning_rate": 3.917649659656927e-06,
|
||||
"loss": 0.3773,
|
||||
"step": 250
|
||||
},
|
||||
{
|
||||
"epoch": 1.1818181818181819,
|
||||
"grad_norm": 2.7410788536071777,
|
||||
"learning_rate": 3.8068100546783315e-06,
|
||||
"loss": 0.3814,
|
||||
"step": 260
|
||||
},
|
||||
{
|
||||
"epoch": 1.2272727272727273,
|
||||
"grad_norm": 2.7614405155181885,
|
||||
"learning_rate": 3.692315864546635e-06,
|
||||
"loss": 0.3861,
|
||||
"step": 270
|
||||
},
|
||||
{
|
||||
"epoch": 1.2727272727272727,
|
||||
"grad_norm": 2.2853896617889404,
|
||||
"learning_rate": 3.5744872802229296e-06,
|
||||
"loss": 0.401,
|
||||
"step": 280
|
||||
},
|
||||
{
|
||||
"epoch": 1.3181818181818181,
|
||||
"grad_norm": 2.896815299987793,
|
||||
"learning_rate": 3.453653817533435e-06,
|
||||
"loss": 0.3942,
|
||||
"step": 290
|
||||
},
|
||||
{
|
||||
"epoch": 1.3636363636363638,
|
||||
"grad_norm": 2.7985401153564453,
|
||||
"learning_rate": 3.3301533956555886e-06,
|
||||
"loss": 0.3784,
|
||||
"step": 300
|
||||
},
|
||||
{
|
||||
"epoch": 1.4090909090909092,
|
||||
"grad_norm": 3.265619993209839,
|
||||
"learning_rate": 3.2043313921035747e-06,
|
||||
"loss": 0.4004,
|
||||
"step": 310
|
||||
},
|
||||
{
|
||||
"epoch": 1.4545454545454546,
|
||||
"grad_norm": 2.6088955402374268,
|
||||
"learning_rate": 3.0765396768561005e-06,
|
||||
"loss": 0.3663,
|
||||
"step": 320
|
||||
},
|
||||
{
|
||||
"epoch": 1.5,
|
||||
"grad_norm": 2.830472707748413,
|
||||
"learning_rate": 2.9471356283275444e-06,
|
||||
"loss": 0.4158,
|
||||
"step": 330
|
||||
},
|
||||
{
|
||||
"epoch": 1.5454545454545454,
|
||||
"grad_norm": 2.780045509338379,
|
||||
"learning_rate": 2.8164811339343736e-06,
|
||||
"loss": 0.3799,
|
||||
"step": 340
|
||||
},
|
||||
{
|
||||
"epoch": 1.5909090909090908,
|
||||
"grad_norm": 2.4751908779144287,
|
||||
"learning_rate": 2.684941578051836e-06,
|
||||
"loss": 0.3974,
|
||||
"step": 350
|
||||
},
|
||||
{
|
||||
"epoch": 1.6363636363636362,
|
||||
"grad_norm": 2.8256654739379883,
|
||||
"learning_rate": 2.5528848201911543e-06,
|
||||
"loss": 0.3846,
|
||||
"step": 360
|
||||
},
|
||||
{
|
||||
"epoch": 1.6818181818181817,
|
||||
"grad_norm": 2.9007036685943604,
|
||||
"learning_rate": 2.4206801662548314e-06,
|
||||
"loss": 0.3881,
|
||||
"step": 370
|
||||
},
|
||||
{
|
||||
"epoch": 1.7272727272727273,
|
||||
"grad_norm": 2.53434157371521,
|
||||
"learning_rate": 2.288697335747027e-06,
|
||||
"loss": 0.3729,
|
||||
"step": 380
|
||||
},
|
||||
{
|
||||
"epoch": 1.7727272727272727,
|
||||
"grad_norm": 3.7612838745117188,
|
||||
"learning_rate": 2.157305427827264e-06,
|
||||
"loss": 0.3735,
|
||||
"step": 390
|
||||
},
|
||||
{
|
||||
"epoch": 1.8181818181818183,
|
||||
"grad_norm": 2.661956310272217,
|
||||
"learning_rate": 2.0268718890989754e-06,
|
||||
"loss": 0.3767,
|
||||
"step": 400
|
||||
},
|
||||
{
|
||||
"epoch": 1.8636363636363638,
|
||||
"grad_norm": 2.765303611755371,
|
||||
"learning_rate": 1.8977614860195297e-06,
|
||||
"loss": 0.3745,
|
||||
"step": 410
|
||||
},
|
||||
{
|
||||
"epoch": 1.9090909090909092,
|
||||
"grad_norm": 2.670576810836792,
|
||||
"learning_rate": 1.7703352848054888e-06,
|
||||
"loss": 0.3658,
|
||||
"step": 420
|
||||
},
|
||||
{
|
||||
"epoch": 1.9545454545454546,
|
||||
"grad_norm": 2.4339048862457275,
|
||||
"learning_rate": 1.6449496416858285e-06,
|
||||
"loss": 0.3731,
|
||||
"step": 430
|
||||
},
|
||||
{
|
||||
"epoch": 2.0,
|
||||
"grad_norm": 2.40981125831604,
|
||||
"learning_rate": 1.521955206326976e-06,
|
||||
"loss": 0.3567,
|
||||
"step": 440
|
||||
},
|
||||
{
|
||||
"epoch": 2.0454545454545454,
|
||||
"grad_norm": 2.5268046855926514,
|
||||
"learning_rate": 1.401695941216644e-06,
|
||||
"loss": 0.2403,
|
||||
"step": 450
|
||||
},
|
||||
{
|
||||
"epoch": 2.090909090909091,
|
||||
"grad_norm": 2.764014720916748,
|
||||
"learning_rate": 1.2845081597488288e-06,
|
||||
"loss": 0.2391,
|
||||
"step": 460
|
||||
},
|
||||
{
|
||||
"epoch": 2.1363636363636362,
|
||||
"grad_norm": 2.833030939102173,
|
||||
"learning_rate": 1.1707195857000218e-06,
|
||||
"loss": 0.2451,
|
||||
"step": 470
|
||||
},
|
||||
{
|
||||
"epoch": 2.1818181818181817,
|
||||
"grad_norm": 3.5294485092163086,
|
||||
"learning_rate": 1.0606484367268906e-06,
|
||||
"loss": 0.2646,
|
||||
"step": 480
|
||||
},
|
||||
{
|
||||
"epoch": 2.227272727272727,
|
||||
"grad_norm": 2.8791749477386475,
|
||||
"learning_rate": 9.546025344484868e-07,
|
||||
"loss": 0.2316,
|
||||
"step": 490
|
||||
},
|
||||
{
|
||||
"epoch": 2.2727272727272725,
|
||||
"grad_norm": 3.4600861072540283,
|
||||
"learning_rate": 8.528784436016879e-07,
|
||||
"loss": 0.2326,
|
||||
"step": 500
|
||||
},
|
||||
{
|
||||
"epoch": 2.3181818181818183,
|
||||
"grad_norm": 3.8888542652130127,
|
||||
"learning_rate": 7.557606426772962e-07,
|
||||
"loss": 0.2425,
|
||||
"step": 510
|
||||
},
|
||||
{
|
||||
"epoch": 2.3636363636363638,
|
||||
"grad_norm": 2.9734840393066406,
|
||||
"learning_rate": 6.635207283561671e-07,
|
||||
"loss": 0.2402,
|
||||
"step": 520
|
||||
},
|
||||
{
|
||||
"epoch": 2.409090909090909,
|
||||
"grad_norm": 2.7985284328460693,
|
||||
"learning_rate": 5.764166559702145e-07,
|
||||
"loss": 0.2552,
|
||||
"step": 530
|
||||
},
|
||||
{
|
||||
"epoch": 2.4545454545454546,
|
||||
"grad_norm": 2.636850595474243,
|
||||
"learning_rate": 4.946920181123904e-07,
|
||||
"loss": 0.2288,
|
||||
"step": 540
|
||||
},
|
||||
{
|
||||
"epoch": 2.5,
|
||||
"grad_norm": 3.518472194671631,
|
||||
"learning_rate": 4.185753634130718e-07,
|
||||
"loss": 0.2302,
|
||||
"step": 550
|
||||
},
|
||||
{
|
||||
"epoch": 2.5454545454545454,
|
||||
"grad_norm": 2.759793281555176,
|
||||
"learning_rate": 3.482795573879241e-07,
|
||||
"loss": 0.2486,
|
||||
"step": 560
|
||||
},
|
||||
{
|
||||
"epoch": 2.590909090909091,
|
||||
"grad_norm": 3.072930335998535,
|
||||
"learning_rate": 2.840011871446963e-07,
|
||||
"loss": 0.2389,
|
||||
"step": 570
|
||||
},
|
||||
{
|
||||
"epoch": 2.6363636363636362,
|
||||
"grad_norm": 2.546269178390503,
|
||||
"learning_rate": 2.2592001161370392e-07,
|
||||
"loss": 0.2463,
|
||||
"step": 580
|
||||
},
|
||||
{
|
||||
"epoch": 2.6818181818181817,
|
||||
"grad_norm": 2.247389793395996,
|
||||
"learning_rate": 1.74198458839491e-07,
|
||||
"loss": 0.2235,
|
||||
"step": 590
|
||||
},
|
||||
{
|
||||
"epoch": 2.7272727272727275,
|
||||
"grad_norm": 3.309213161468506,
|
||||
"learning_rate": 1.289811717395087e-07,
|
||||
"loss": 0.2358,
|
||||
"step": 600
|
||||
},
|
||||
{
|
||||
"epoch": 2.7727272727272725,
|
||||
"grad_norm": 2.962289333343506,
|
||||
"learning_rate": 9.03946036001449e-08,
|
||||
"loss": 0.23,
|
||||
"step": 610
|
||||
},
|
||||
{
|
||||
"epoch": 2.8181818181818183,
|
||||
"grad_norm": 2.887887954711914,
|
||||
"learning_rate": 5.8546664441319346e-08,
|
||||
"loss": 0.2348,
|
||||
"step": 620
|
||||
},
|
||||
{
|
||||
"epoch": 2.8636363636363638,
|
||||
"grad_norm": 3.686352252960205,
|
||||
"learning_rate": 3.352641923861144e-08,
|
||||
"loss": 0.247,
|
||||
"step": 630
|
||||
},
|
||||
{
|
||||
"epoch": 2.909090909090909,
|
||||
"grad_norm": 3.1452362537384033,
|
||||
"learning_rate": 1.5403838846864694e-08,
|
||||
"loss": 0.2284,
|
||||
"step": 640
|
||||
},
|
||||
{
|
||||
"epoch": 2.9545454545454546,
|
||||
"grad_norm": 3.098659038543701,
|
||||
"learning_rate": 4.229604321829561e-09,
|
||||
"loss": 0.2312,
|
||||
"step": 650
|
||||
},
|
||||
{
|
||||
"epoch": 3.0,
|
||||
"grad_norm": 2.993980884552002,
|
||||
"learning_rate": 3.496518706597174e-11,
|
||||
"loss": 0.2323,
|
||||
"step": 660
|
||||
},
|
||||
{
|
||||
"epoch": 3.0,
|
||||
"step": 660,
|
||||
"total_flos": 6.988388070252872e+17,
|
||||
"train_loss": 0.41709409590923424,
|
||||
"train_runtime": 37712.5646,
|
||||
"train_samples_per_second": 0.14,
|
||||
"train_steps_per_second": 0.018
|
||||
}
|
||||
],
|
||||
"logging_steps": 10,
|
||||
"max_steps": 660,
|
||||
"num_input_tokens_seen": 0,
|
||||
"num_train_epochs": 3,
|
||||
"save_steps": 1,
|
||||
"stateful_callbacks": {
|
||||
"TrainerControl": {
|
||||
"args": {
|
||||
"should_epoch_stop": false,
|
||||
"should_evaluate": false,
|
||||
"should_log": false,
|
||||
"should_save": true,
|
||||
"should_training_stop": true
|
||||
},
|
||||
"attributes": {}
|
||||
}
|
||||
},
|
||||
"total_flos": 6.988388070252872e+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 sha256:616553aae0c24b3e2a72b535277e85687f9022d9c4bccf340d3616387efb9363
|
||||
size 6289
|
||||
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