初始化项目，由ModelHub XC社区提供模型
Model: raca-workspace-v1/grpo-tool-sat-sft-qwen3-1p7b-sft-20260419-075623-96e9 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
|
||||
58
README.md
Normal file
58
README.md
Normal file
@@ -0,0 +1,58 @@
|
||||
---
|
||||
library_name: transformers
|
||||
license: other
|
||||
base_model: Qwen/Qwen3-1.7B-Base
|
||||
tags:
|
||||
- llama-factory
|
||||
- full
|
||||
- generated_from_trainer
|
||||
model-index:
|
||||
- name: sft-20260419-075623-96e9
|
||||
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. -->
|
||||
|
||||
# sft-20260419-075623-96e9
|
||||
|
||||
This model is a fine-tuned version of [Qwen/Qwen3-1.7B-Base](https://huggingface.co/Qwen/Qwen3-1.7B-Base) on the grpo_tool_sat_sft 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: 2e-05
|
||||
- train_batch_size: 8
|
||||
- eval_batch_size: 8
|
||||
- seed: 1
|
||||
- gradient_accumulation_steps: 2
|
||||
- total_train_batch_size: 16
|
||||
- optimizer: Use OptimizerNames.ADAMW_TORCH 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: 0.03
|
||||
- num_epochs: 2
|
||||
|
||||
### Training results
|
||||
|
||||
|
||||
|
||||
### Framework versions
|
||||
|
||||
- Transformers 4.52.4
|
||||
- Pytorch 2.10.0+cu128
|
||||
- Datasets 3.6.0
|
||||
- Tokenizers 0.21.1
|
||||
28
added_tokens.json
Normal file
28
added_tokens.json
Normal file
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"</think>": 151668,
|
||||
"</tool_call>": 151658,
|
||||
"</tool_response>": 151666,
|
||||
"<think>": 151667,
|
||||
"<tool_call>": 151657,
|
||||
"<tool_response>": 151665,
|
||||
"<|box_end|>": 151649,
|
||||
"<|box_start|>": 151648,
|
||||
"<|endoftext|>": 151643,
|
||||
"<|file_sep|>": 151664,
|
||||
"<|fim_middle|>": 151660,
|
||||
"<|fim_pad|>": 151662,
|
||||
"<|fim_prefix|>": 151659,
|
||||
"<|fim_suffix|>": 151661,
|
||||
"<|im_end|>": 151645,
|
||||
"<|im_start|>": 151644,
|
||||
"<|image_pad|>": 151655,
|
||||
"<|object_ref_end|>": 151647,
|
||||
"<|object_ref_start|>": 151646,
|
||||
"<|quad_end|>": 151651,
|
||||
"<|quad_start|>": 151650,
|
||||
"<|repo_name|>": 151663,
|
||||
"<|video_pad|>": 151656,
|
||||
"<|vision_end|>": 151653,
|
||||
"<|vision_pad|>": 151654,
|
||||
"<|vision_start|>": 151652
|
||||
}
|
||||
8
all_results.json
Normal file
8
all_results.json
Normal file
@@ -0,0 +1,8 @@
|
||||
{
|
||||
"epoch": 2.0,
|
||||
"total_flos": 7576988418048000.0,
|
||||
"train_loss": 0.4733153915405273,
|
||||
"train_runtime": 560.9841,
|
||||
"train_samples_per_second": 28.521,
|
||||
"train_steps_per_second": 1.783
|
||||
}
|
||||
85
chat_template.jinja
Normal file
85
chat_template.jinja
Normal file
@@ -0,0 +1,85 @@
|
||||
{%- 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 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.role == "user") or (message.role == "system" and not loop.first) %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
||||
{%- elif message.role == "assistant" %}
|
||||
{%- set content = message.content %}
|
||||
{%- set reasoning_content = '' %}
|
||||
{%- if message.reasoning_content is defined and message.reasoning_content is not none %}
|
||||
{%- set reasoning_content = message.reasoning_content %}
|
||||
{%- else %}
|
||||
{%- if '</think>' in message.content %}
|
||||
{%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
|
||||
{%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').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' }}
|
||||
{{- message.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 %}
|
||||
30
config.json
Normal file
30
config.json
Normal file
@@ -0,0 +1,30 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen3ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"eos_token_id": 151643,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 2048,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 6144,
|
||||
"max_position_embeddings": 32768,
|
||||
"max_window_layers": 28,
|
||||
"model_type": "qwen3",
|
||||
"num_attention_heads": 16,
|
||||
"num_hidden_layers": 28,
|
||||
"num_key_value_heads": 8,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 1000000,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": true,
|
||||
"torch_dtype": "float32",
|
||||
"transformers_version": "4.52.4",
|
||||
"use_cache": false,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
6
generation_config.json
Normal file
6
generation_config.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"bos_token_id": 151643,
|
||||
"eos_token_id": 151643,
|
||||
"max_new_tokens": 2048,
|
||||
"transformers_version": "4.52.4"
|
||||
}
|
||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model-00001-of-00002.safetensors
Normal file
3
model-00001-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d8ba7f238ee0598d6c89ab5eb5b4dd2d20ea9a56b933a07fab33d71573513d73
|
||||
size 4969539560
|
||||
3
model-00002-of-00002.safetensors
Normal file
3
model-00002-of-00002.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:69f5457aac64807025eee48f6f678ddc6a846a9d14efdcc29f85448533285e6a
|
||||
size 1912795688
|
||||
317
model.safetensors.index.json
Normal file
317
model.safetensors.index.json
Normal file
@@ -0,0 +1,317 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 6882299904
|
||||
},
|
||||
"weight_map": {
|
||||
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
||||
"model.norm.weight": "model-00002-of-00002.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": "<|endoftext|>",
|
||||
"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": "<|endoftext|>",
|
||||
"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": 2.0,
|
||||
"total_flos": 7576988418048000.0,
|
||||
"train_loss": 0.4733153915405273,
|
||||
"train_runtime": 560.9841,
|
||||
"train_samples_per_second": 28.521,
|
||||
"train_steps_per_second": 1.783
|
||||
}
|
||||
41
trainer_log.jsonl
Normal file
41
trainer_log.jsonl
Normal file
@@ -0,0 +1,41 @@
|
||||
{"current_steps": 25, "total_steps": 1000, "loss": 2.3428, "lr": 1.6000000000000003e-05, "epoch": 0.05, "percentage": 2.5, "elapsed_time": "0:00:14", "remaining_time": "0:09:09"}
|
||||
{"current_steps": 50, "total_steps": 1000, "loss": 0.7368, "lr": 1.998107236150145e-05, "epoch": 0.1, "percentage": 5.0, "elapsed_time": "0:00:25", "remaining_time": "0:08:11"}
|
||||
{"current_steps": 75, "total_steps": 1000, "loss": 0.5067, "lr": 1.989863301061654e-05, "epoch": 0.15, "percentage": 7.5, "elapsed_time": "0:00:37", "remaining_time": "0:07:44"}
|
||||
{"current_steps": 100, "total_steps": 1000, "loss": 0.4279, "lr": 1.9751334064160708e-05, "epoch": 0.2, "percentage": 10.0, "elapsed_time": "0:00:49", "remaining_time": "0:07:24"}
|
||||
{"current_steps": 125, "total_steps": 1000, "loss": 0.419, "lr": 1.9540140680664915e-05, "epoch": 0.25, "percentage": 12.5, "elapsed_time": "0:01:01", "remaining_time": "0:07:08"}
|
||||
{"current_steps": 150, "total_steps": 1000, "loss": 0.4207, "lr": 1.9266436679230866e-05, "epoch": 0.3, "percentage": 15.0, "elapsed_time": "0:01:13", "remaining_time": "0:06:53"}
|
||||
{"current_steps": 175, "total_steps": 1000, "loss": 0.4169, "lr": 1.8932015472223692e-05, "epoch": 0.35, "percentage": 17.5, "elapsed_time": "0:01:24", "remaining_time": "0:06:39"}
|
||||
{"current_steps": 200, "total_steps": 1000, "loss": 0.4185, "lr": 1.8539068314154355e-05, "epoch": 0.4, "percentage": 20.0, "elapsed_time": "0:01:36", "remaining_time": "0:06:26"}
|
||||
{"current_steps": 225, "total_steps": 1000, "loss": 0.4197, "lr": 1.8090169943749477e-05, "epoch": 0.45, "percentage": 22.5, "elapsed_time": "0:01:48", "remaining_time": "0:06:13"}
|
||||
{"current_steps": 250, "total_steps": 1000, "loss": 0.42, "lr": 1.758826171328727e-05, "epoch": 0.5, "percentage": 25.0, "elapsed_time": "0:02:00", "remaining_time": "0:06:00"}
|
||||
{"current_steps": 275, "total_steps": 1000, "loss": 0.4209, "lr": 1.7036632315742464e-05, "epoch": 0.55, "percentage": 27.5, "elapsed_time": "0:02:12", "remaining_time": "0:05:48"}
|
||||
{"current_steps": 300, "total_steps": 1000, "loss": 0.4168, "lr": 1.6438896236023374e-05, "epoch": 0.6, "percentage": 30.0, "elapsed_time": "0:02:23", "remaining_time": "0:05:35"}
|
||||
{"current_steps": 325, "total_steps": 1000, "loss": 0.4155, "lr": 1.57989700674967e-05, "epoch": 0.65, "percentage": 32.5, "elapsed_time": "0:02:35", "remaining_time": "0:05:23"}
|
||||
{"current_steps": 350, "total_steps": 1000, "loss": 0.4171, "lr": 1.512104684898319e-05, "epoch": 0.7, "percentage": 35.0, "elapsed_time": "0:02:47", "remaining_time": "0:05:11"}
|
||||
{"current_steps": 375, "total_steps": 1000, "loss": 0.4143, "lr": 1.4409568590377918e-05, "epoch": 0.75, "percentage": 37.5, "elapsed_time": "0:02:59", "remaining_time": "0:04:58"}
|
||||
{"current_steps": 400, "total_steps": 1000, "loss": 0.4144, "lr": 1.3669197166917723e-05, "epoch": 0.8, "percentage": 40.0, "elapsed_time": "0:03:11", "remaining_time": "0:04:46"}
|
||||
{"current_steps": 425, "total_steps": 1000, "loss": 0.4152, "lr": 1.2904783772807534e-05, "epoch": 0.85, "percentage": 42.5, "elapsed_time": "0:03:23", "remaining_time": "0:04:34"}
|
||||
{"current_steps": 450, "total_steps": 1000, "loss": 0.4161, "lr": 1.2121337134357121e-05, "epoch": 0.9, "percentage": 45.0, "elapsed_time": "0:03:34", "remaining_time": "0:04:22"}
|
||||
{"current_steps": 475, "total_steps": 1000, "loss": 0.4154, "lr": 1.1323990690907734e-05, "epoch": 0.95, "percentage": 47.5, "elapsed_time": "0:03:46", "remaining_time": "0:04:10"}
|
||||
{"current_steps": 500, "total_steps": 1000, "loss": 0.4142, "lr": 1.0517968958591705e-05, "epoch": 1.0, "percentage": 50.0, "elapsed_time": "0:03:58", "remaining_time": "0:03:58"}
|
||||
{"current_steps": 525, "total_steps": 1000, "loss": 0.4138, "lr": 9.708553297322407e-06, "epoch": 1.05, "percentage": 52.5, "elapsed_time": "0:04:43", "remaining_time": "0:04:16"}
|
||||
{"current_steps": 550, "total_steps": 1000, "loss": 0.4142, "lr": 8.901047305322172e-06, "epoch": 1.1, "percentage": 55.0, "elapsed_time": "0:04:55", "remaining_time": "0:04:01"}
|
||||
{"current_steps": 575, "total_steps": 1000, "loss": 0.4138, "lr": 8.100742067936432e-06, "epoch": 1.15, "percentage": 57.5, "elapsed_time": "0:05:06", "remaining_time": "0:03:46"}
|
||||
{"current_steps": 600, "total_steps": 1000, "loss": 0.4125, "lr": 7.312881488436928e-06, "epoch": 1.2, "percentage": 60.0, "elapsed_time": "0:05:18", "remaining_time": "0:03:32"}
|
||||
{"current_steps": 625, "total_steps": 1000, "loss": 0.4108, "lr": 6.542627927979772e-06, "epoch": 1.25, "percentage": 62.5, "elapsed_time": "0:05:30", "remaining_time": "0:03:18"}
|
||||
{"current_steps": 650, "total_steps": 1000, "loss": 0.4112, "lr": 5.795028379858355e-06, "epoch": 1.3, "percentage": 65.0, "elapsed_time": "0:05:42", "remaining_time": "0:03:04"}
|
||||
{"current_steps": 675, "total_steps": 1000, "loss": 0.413, "lr": 5.074981399690219e-06, "epoch": 1.35, "percentage": 67.5, "elapsed_time": "0:05:54", "remaining_time": "0:02:50"}
|
||||
{"current_steps": 700, "total_steps": 1000, "loss": 0.4136, "lr": 4.3872050082238535e-06, "epoch": 1.4, "percentage": 70.0, "elapsed_time": "0:06:05", "remaining_time": "0:02:36"}
|
||||
{"current_steps": 725, "total_steps": 1000, "loss": 0.4115, "lr": 3.736205777078381e-06, "epoch": 1.45, "percentage": 72.5, "elapsed_time": "0:06:17", "remaining_time": "0:02:23"}
|
||||
{"current_steps": 750, "total_steps": 1000, "loss": 0.4125, "lr": 3.126249299978086e-06, "epoch": 1.5, "percentage": 75.0, "elapsed_time": "0:06:29", "remaining_time": "0:02:09"}
|
||||
{"current_steps": 775, "total_steps": 1000, "loss": 0.4122, "lr": 2.5613322429654573e-06, "epoch": 1.55, "percentage": 77.5, "elapsed_time": "0:06:41", "remaining_time": "0:01:56"}
|
||||
{"current_steps": 800, "total_steps": 1000, "loss": 0.412, "lr": 2.0451561567303378e-06, "epoch": 1.6, "percentage": 80.0, "elapsed_time": "0:06:53", "remaining_time": "0:01:43"}
|
||||
{"current_steps": 825, "total_steps": 1000, "loss": 0.4123, "lr": 1.5811032226467304e-06, "epoch": 1.65, "percentage": 82.5, "elapsed_time": "0:07:05", "remaining_time": "0:01:30"}
|
||||
{"current_steps": 850, "total_steps": 1000, "loss": 0.4106, "lr": 1.1722140914384162e-06, "epoch": 1.7, "percentage": 85.0, "elapsed_time": "0:07:17", "remaining_time": "0:01:17"}
|
||||
{"current_steps": 875, "total_steps": 1000, "loss": 0.4118, "lr": 8.211679596828481e-07, "epoch": 1.75, "percentage": 87.5, "elapsed_time": "0:07:28", "remaining_time": "0:01:04"}
|
||||
{"current_steps": 900, "total_steps": 1000, "loss": 0.4125, "lr": 5.30265014699628e-07, "epoch": 1.8, "percentage": 90.0, "elapsed_time": "0:07:40", "remaining_time": "0:00:51"}
|
||||
{"current_steps": 925, "total_steps": 1000, "loss": 0.4115, "lr": 3.0141136285129825e-07, "epoch": 1.85, "percentage": 92.5, "elapsed_time": "0:07:52", "remaining_time": "0:00:38"}
|
||||
{"current_steps": 950, "total_steps": 1000, "loss": 0.4122, "lr": 1.361065400119399e-07, "epoch": 1.9, "percentage": 95.0, "elapsed_time": "0:08:04", "remaining_time": "0:00:25"}
|
||||
{"current_steps": 975, "total_steps": 1000, "loss": 0.4112, "lr": 3.543368603973529e-08, "epoch": 1.95, "percentage": 97.5, "elapsed_time": "0:08:16", "remaining_time": "0:00:12"}
|
||||
{"current_steps": 1000, "total_steps": 1000, "loss": 0.4103, "lr": 5.244763404133046e-11, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "0:08:28", "remaining_time": "0:00:00"}
|
||||
{"current_steps": 1000, "total_steps": 1000, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "0:09:13", "remaining_time": "0:00:00"}
|
||||
323
trainer_state.json
Normal file
323
trainer_state.json
Normal file
@@ -0,0 +1,323 @@
|
||||
{
|
||||
"best_global_step": null,
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 2.0,
|
||||
"eval_steps": 500,
|
||||
"global_step": 1000,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.05,
|
||||
"grad_norm": 11.879703521728516,
|
||||
"learning_rate": 1.6000000000000003e-05,
|
||||
"loss": 2.3428,
|
||||
"step": 25
|
||||
},
|
||||
{
|
||||
"epoch": 0.1,
|
||||
"grad_norm": 5.421560287475586,
|
||||
"learning_rate": 1.998107236150145e-05,
|
||||
"loss": 0.7368,
|
||||
"step": 50
|
||||
},
|
||||
{
|
||||
"epoch": 0.15,
|
||||
"grad_norm": 2.313567876815796,
|
||||
"learning_rate": 1.989863301061654e-05,
|
||||
"loss": 0.5067,
|
||||
"step": 75
|
||||
},
|
||||
{
|
||||
"epoch": 0.2,
|
||||
"grad_norm": 2.5316965579986572,
|
||||
"learning_rate": 1.9751334064160708e-05,
|
||||
"loss": 0.4279,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 0.25,
|
||||
"grad_norm": 2.5976717472076416,
|
||||
"learning_rate": 1.9540140680664915e-05,
|
||||
"loss": 0.419,
|
||||
"step": 125
|
||||
},
|
||||
{
|
||||
"epoch": 0.3,
|
||||
"grad_norm": 1.39866304397583,
|
||||
"learning_rate": 1.9266436679230866e-05,
|
||||
"loss": 0.4207,
|
||||
"step": 150
|
||||
},
|
||||
{
|
||||
"epoch": 0.35,
|
||||
"grad_norm": 1.8767157793045044,
|
||||
"learning_rate": 1.8932015472223692e-05,
|
||||
"loss": 0.4169,
|
||||
"step": 175
|
||||
},
|
||||
{
|
||||
"epoch": 0.4,
|
||||
"grad_norm": 2.209038734436035,
|
||||
"learning_rate": 1.8539068314154355e-05,
|
||||
"loss": 0.4185,
|
||||
"step": 200
|
||||
},
|
||||
{
|
||||
"epoch": 0.45,
|
||||
"grad_norm": 2.1389389038085938,
|
||||
"learning_rate": 1.8090169943749477e-05,
|
||||
"loss": 0.4197,
|
||||
"step": 225
|
||||
},
|
||||
{
|
||||
"epoch": 0.5,
|
||||
"grad_norm": 1.957894206047058,
|
||||
"learning_rate": 1.758826171328727e-05,
|
||||
"loss": 0.42,
|
||||
"step": 250
|
||||
},
|
||||
{
|
||||
"epoch": 0.55,
|
||||
"grad_norm": 1.7354559898376465,
|
||||
"learning_rate": 1.7036632315742464e-05,
|
||||
"loss": 0.4209,
|
||||
"step": 275
|
||||
},
|
||||
{
|
||||
"epoch": 0.6,
|
||||
"grad_norm": 1.4375723600387573,
|
||||
"learning_rate": 1.6438896236023374e-05,
|
||||
"loss": 0.4168,
|
||||
"step": 300
|
||||
},
|
||||
{
|
||||
"epoch": 0.65,
|
||||
"grad_norm": 1.7558571100234985,
|
||||
"learning_rate": 1.57989700674967e-05,
|
||||
"loss": 0.4155,
|
||||
"step": 325
|
||||
},
|
||||
{
|
||||
"epoch": 0.7,
|
||||
"grad_norm": 1.6743788719177246,
|
||||
"learning_rate": 1.512104684898319e-05,
|
||||
"loss": 0.4171,
|
||||
"step": 350
|
||||
},
|
||||
{
|
||||
"epoch": 0.75,
|
||||
"grad_norm": 1.1145944595336914,
|
||||
"learning_rate": 1.4409568590377918e-05,
|
||||
"loss": 0.4143,
|
||||
"step": 375
|
||||
},
|
||||
{
|
||||
"epoch": 0.8,
|
||||
"grad_norm": 2.5990407466888428,
|
||||
"learning_rate": 1.3669197166917723e-05,
|
||||
"loss": 0.4144,
|
||||
"step": 400
|
||||
},
|
||||
{
|
||||
"epoch": 0.85,
|
||||
"grad_norm": 2.7390551567077637,
|
||||
"learning_rate": 1.2904783772807534e-05,
|
||||
"loss": 0.4152,
|
||||
"step": 425
|
||||
},
|
||||
{
|
||||
"epoch": 0.9,
|
||||
"grad_norm": 1.1414133310317993,
|
||||
"learning_rate": 1.2121337134357121e-05,
|
||||
"loss": 0.4161,
|
||||
"step": 450
|
||||
},
|
||||
{
|
||||
"epoch": 0.95,
|
||||
"grad_norm": 1.2553099393844604,
|
||||
"learning_rate": 1.1323990690907734e-05,
|
||||
"loss": 0.4154,
|
||||
"step": 475
|
||||
},
|
||||
{
|
||||
"epoch": 1.0,
|
||||
"grad_norm": 1.7206685543060303,
|
||||
"learning_rate": 1.0517968958591705e-05,
|
||||
"loss": 0.4142,
|
||||
"step": 500
|
||||
},
|
||||
{
|
||||
"epoch": 1.05,
|
||||
"grad_norm": 1.1427602767944336,
|
||||
"learning_rate": 9.708553297322407e-06,
|
||||
"loss": 0.4138,
|
||||
"step": 525
|
||||
},
|
||||
{
|
||||
"epoch": 1.1,
|
||||
"grad_norm": 1.4284802675247192,
|
||||
"learning_rate": 8.901047305322172e-06,
|
||||
"loss": 0.4142,
|
||||
"step": 550
|
||||
},
|
||||
{
|
||||
"epoch": 1.15,
|
||||
"grad_norm": 1.6178677082061768,
|
||||
"learning_rate": 8.100742067936432e-06,
|
||||
"loss": 0.4138,
|
||||
"step": 575
|
||||
},
|
||||
{
|
||||
"epoch": 1.2,
|
||||
"grad_norm": 1.2968213558197021,
|
||||
"learning_rate": 7.312881488436928e-06,
|
||||
"loss": 0.4125,
|
||||
"step": 600
|
||||
},
|
||||
{
|
||||
"epoch": 1.25,
|
||||
"grad_norm": 1.2272377014160156,
|
||||
"learning_rate": 6.542627927979772e-06,
|
||||
"loss": 0.4108,
|
||||
"step": 625
|
||||
},
|
||||
{
|
||||
"epoch": 1.3,
|
||||
"grad_norm": 1.5362012386322021,
|
||||
"learning_rate": 5.795028379858355e-06,
|
||||
"loss": 0.4112,
|
||||
"step": 650
|
||||
},
|
||||
{
|
||||
"epoch": 1.35,
|
||||
"grad_norm": 1.4780094623565674,
|
||||
"learning_rate": 5.074981399690219e-06,
|
||||
"loss": 0.413,
|
||||
"step": 675
|
||||
},
|
||||
{
|
||||
"epoch": 1.4,
|
||||
"grad_norm": 2.2684173583984375,
|
||||
"learning_rate": 4.3872050082238535e-06,
|
||||
"loss": 0.4136,
|
||||
"step": 700
|
||||
},
|
||||
{
|
||||
"epoch": 1.45,
|
||||
"grad_norm": 1.7533961534500122,
|
||||
"learning_rate": 3.736205777078381e-06,
|
||||
"loss": 0.4115,
|
||||
"step": 725
|
||||
},
|
||||
{
|
||||
"epoch": 1.5,
|
||||
"grad_norm": 2.0084352493286133,
|
||||
"learning_rate": 3.126249299978086e-06,
|
||||
"loss": 0.4125,
|
||||
"step": 750
|
||||
},
|
||||
{
|
||||
"epoch": 1.55,
|
||||
"grad_norm": 1.6931928396224976,
|
||||
"learning_rate": 2.5613322429654573e-06,
|
||||
"loss": 0.4122,
|
||||
"step": 775
|
||||
},
|
||||
{
|
||||
"epoch": 1.6,
|
||||
"grad_norm": 1.7414414882659912,
|
||||
"learning_rate": 2.0451561567303378e-06,
|
||||
"loss": 0.412,
|
||||
"step": 800
|
||||
},
|
||||
{
|
||||
"epoch": 1.65,
|
||||
"grad_norm": 1.7203795909881592,
|
||||
"learning_rate": 1.5811032226467304e-06,
|
||||
"loss": 0.4123,
|
||||
"step": 825
|
||||
},
|
||||
{
|
||||
"epoch": 1.7,
|
||||
"grad_norm": 2.252686023712158,
|
||||
"learning_rate": 1.1722140914384162e-06,
|
||||
"loss": 0.4106,
|
||||
"step": 850
|
||||
},
|
||||
{
|
||||
"epoch": 1.75,
|
||||
"grad_norm": 1.8625959157943726,
|
||||
"learning_rate": 8.211679596828481e-07,
|
||||
"loss": 0.4118,
|
||||
"step": 875
|
||||
},
|
||||
{
|
||||
"epoch": 1.8,
|
||||
"grad_norm": 1.6265811920166016,
|
||||
"learning_rate": 5.30265014699628e-07,
|
||||
"loss": 0.4125,
|
||||
"step": 900
|
||||
},
|
||||
{
|
||||
"epoch": 1.85,
|
||||
"grad_norm": 1.9654788970947266,
|
||||
"learning_rate": 3.0141136285129825e-07,
|
||||
"loss": 0.4115,
|
||||
"step": 925
|
||||
},
|
||||
{
|
||||
"epoch": 1.9,
|
||||
"grad_norm": 1.8853169679641724,
|
||||
"learning_rate": 1.361065400119399e-07,
|
||||
"loss": 0.4122,
|
||||
"step": 950
|
||||
},
|
||||
{
|
||||
"epoch": 1.95,
|
||||
"grad_norm": 1.8307050466537476,
|
||||
"learning_rate": 3.543368603973529e-08,
|
||||
"loss": 0.4112,
|
||||
"step": 975
|
||||
},
|
||||
{
|
||||
"epoch": 2.0,
|
||||
"grad_norm": 1.647140622138977,
|
||||
"learning_rate": 5.244763404133046e-11,
|
||||
"loss": 0.4103,
|
||||
"step": 1000
|
||||
},
|
||||
{
|
||||
"epoch": 2.0,
|
||||
"step": 1000,
|
||||
"total_flos": 7576988418048000.0,
|
||||
"train_loss": 0.4733153915405273,
|
||||
"train_runtime": 560.9841,
|
||||
"train_samples_per_second": 28.521,
|
||||
"train_steps_per_second": 1.783
|
||||
}
|
||||
],
|
||||
"logging_steps": 25,
|
||||
"max_steps": 1000,
|
||||
"num_input_tokens_seen": 0,
|
||||
"num_train_epochs": 2,
|
||||
"save_steps": 500,
|
||||
"stateful_callbacks": {
|
||||
"TrainerControl": {
|
||||
"args": {
|
||||
"should_epoch_stop": false,
|
||||
"should_evaluate": false,
|
||||
"should_log": false,
|
||||
"should_save": true,
|
||||
"should_training_stop": true
|
||||
},
|
||||
"attributes": {}
|
||||
}
|
||||
},
|
||||
"total_flos": 7576988418048000.0,
|
||||
"train_batch_size": 8,
|
||||
"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 sha256:94c1b33e223efd142408df3677a5307912e94bcfec5de6e12166050d8c55e309
|
||||
size 6225
|
||||
BIN
training_loss.png
Normal file
BIN
training_loss.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 34 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