初始化项目，由ModelHub XC社区提供模型
Model: lllqaq/Qwen2.5-Coder-14B-Instruct-num11-v1-v2-v3-pairs-v3-triples-post-r2egym 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/Qwen2.5-Coder-14B-Instruct
|
||||
tags:
|
||||
- llama-factory
|
||||
- full
|
||||
- generated_from_trainer
|
||||
model-index:
|
||||
- name: Qwen2.5-Coder-14B-Instruct-num11_v1-v2-v3-pairs-v3-triples-post
|
||||
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. -->
|
||||
|
||||
# Qwen2.5-Coder-14B-Instruct-num11_v1-v2-v3-pairs-v3-triples-post
|
||||
|
||||
This model is a fine-tuned version of a mid-trained [Qwen/Qwen2.5-Coder-14B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-14B-Instruct) (num11_v1-v2-v3-pairs-v3-triples) on the r2egym_sft_trajectories 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: 1e-05
|
||||
- train_batch_size: 1
|
||||
- eval_batch_size: 8
|
||||
- seed: 42
|
||||
- distributed_type: multi-GPU
|
||||
- num_devices: 6
|
||||
- total_train_batch_size: 6
|
||||
- total_eval_batch_size: 48
|
||||
- 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: 0.1
|
||||
- num_epochs: 2.0
|
||||
|
||||
### Training results
|
||||
|
||||
|
||||
|
||||
### Framework versions
|
||||
|
||||
- Transformers 4.57.1
|
||||
- Pytorch 2.6.0+cu124
|
||||
- Datasets 4.0.0
|
||||
- Tokenizers 0.22.2
|
||||
24
added_tokens.json
Normal file
24
added_tokens.json
Normal file
@@ -0,0 +1,24 @@
|
||||
{
|
||||
"</tool_call>": 151658,
|
||||
"<tool_call>": 151657,
|
||||
"<|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": 456031784665088.0,
|
||||
"train_loss": 0.26182658547373117,
|
||||
"train_runtime": 16760.0523,
|
||||
"train_samples_per_second": 0.386,
|
||||
"train_steps_per_second": 0.064
|
||||
}
|
||||
54
chat_template.jinja
Normal file
54
chat_template.jinja
Normal file
@@ -0,0 +1,54 @@
|
||||
{%- if tools %}
|
||||
{{- '<|im_start|>system\n' }}
|
||||
{%- if messages[0]['role'] == 'system' %}
|
||||
{{- messages[0]['content'] }}
|
||||
{%- else %}
|
||||
{{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
|
||||
{%- endif %}
|
||||
{{- "\n\n# 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' }}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- for message in messages %}
|
||||
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
||||
{%- elif message.role == "assistant" %}
|
||||
{{- '<|im_start|>' + message.role }}
|
||||
{%- if message.content %}
|
||||
{{- '\n' + message.content }}
|
||||
{%- endif %}
|
||||
{%- for tool_call in message.tool_calls %}
|
||||
{%- if tool_call.function is defined %}
|
||||
{%- set tool_call = tool_call.function %}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_call>\n{"name": "' }}
|
||||
{{- tool_call.name }}
|
||||
{{- '", "arguments": ' }}
|
||||
{{- tool_call.arguments | tojson }}
|
||||
{{- '}\n</tool_call>' }}
|
||||
{%- endfor %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- elif message.role == "tool" %}
|
||||
{%- if (loop.index0 == 0) 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' }}
|
||||
{%- endif %}
|
||||
82
config.json
Normal file
82
config.json
Normal file
@@ -0,0 +1,82 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen2ForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 151645,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 5120,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 13824,
|
||||
"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",
|
||||
"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": 32768,
|
||||
"max_window_layers": 48,
|
||||
"model_type": "qwen2",
|
||||
"num_attention_heads": 40,
|
||||
"num_hidden_layers": 48,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 151643,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_parameters": {
|
||||
"rope_theta": 1000000.0,
|
||||
"rope_type": "default"
|
||||
},
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 10000.0,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "4.57.1",
|
||||
"use_cache": false,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 152064
|
||||
}
|
||||
13
generation_config.json
Normal file
13
generation_config.json
Normal file
@@ -0,0 +1,13 @@
|
||||
{
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"pad_token_id": 151643,
|
||||
"repetition_penalty": 1.05,
|
||||
"temperature": 0.7,
|
||||
"top_k": 20,
|
||||
"top_p": 0.8,
|
||||
"transformers_version": "4.57.1"
|
||||
}
|
||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model-00001-of-00006.safetensors
Normal file
3
model-00001-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:63121bf7dc9f658950a2bafceb8b521b10b20a7668de24077776dc984966548e
|
||||
size 4986211280
|
||||
3
model-00002-of-00006.safetensors
Normal file
3
model-00002-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:db71d3e17335bc6ddab952346ca187eccc39021ede59d478300baaadb0561b48
|
||||
size 4954847344
|
||||
3
model-00003-of-00006.safetensors
Normal file
3
model-00003-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:390643c276ccc9c8456632a5e5e44caec12602d928b8997b80fad6aede74bf4e
|
||||
size 4954847392
|
||||
3
model-00004-of-00006.safetensors
Normal file
3
model-00004-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8a9a4c2b2a69b9e1f8936b155a791599278c843d9dab81e0579213c26f1b0ca5
|
||||
size 4954847392
|
||||
3
model-00005-of-00006.safetensors
Normal file
3
model-00005-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:fc8d684c08da1964b4295356db7c6c2476ec7a35fc1065c4cad9ba5ecfb9b811
|
||||
size 4954847392
|
||||
3
model-00006-of-00006.safetensors
Normal file
3
model-00006-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d9c87d3ffa8e5d2e38d4bcf25c22b72c1d773eccddc05dcf63d3fd839339cc30
|
||||
size 4734533160
|
||||
587
model.safetensors.index.json
Normal file
587
model.safetensors.index.json
Normal file
@@ -0,0 +1,587 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_parameters": 840704,
|
||||
"total_size": 29540067328
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00006-of-00006.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.36.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.36.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.36.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.36.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.36.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.36.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.36.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.36.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.36.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.36.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.36.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.36.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.37.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.37.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.37.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.37.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.37.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.37.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.37.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.37.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.37.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.37.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.37.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.37.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.38.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.38.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.38.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.38.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.38.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.38.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.39.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.39.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.39.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.39.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.39.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.39.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.40.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.40.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.40.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.40.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.40.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.40.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.40.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.40.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.40.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.40.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.40.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.40.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.41.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.41.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.41.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.41.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.41.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.41.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.41.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.41.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.41.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.41.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.41.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.41.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.42.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.42.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.42.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.42.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.42.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.42.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.42.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.42.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.42.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.42.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.42.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
|
||||
"model.layers.42.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.43.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.43.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.43.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.43.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.43.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.43.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
|
||||
"model.layers.43.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.43.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.43.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
|
||||
"model.layers.43.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.43.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
|
||||
"model.layers.43.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.44.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.44.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.44.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.44.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.44.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.44.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
|
||||
"model.layers.44.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.44.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.44.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
|
||||
"model.layers.44.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.44.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
|
||||
"model.layers.44.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.45.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.45.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.45.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.45.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.45.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.45.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
|
||||
"model.layers.45.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.45.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.45.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
|
||||
"model.layers.45.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.45.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
|
||||
"model.layers.45.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.46.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.46.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.46.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.46.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.46.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.46.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
|
||||
"model.layers.46.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.46.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.46.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
|
||||
"model.layers.46.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.46.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
|
||||
"model.layers.46.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.47.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.47.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.47.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.47.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.47.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.47.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
|
||||
"model.layers.47.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.47.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.47.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
|
||||
"model.layers.47.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.47.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
|
||||
"model.layers.47.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.norm.weight": "model-00006-of-00006.safetensors"
|
||||
}
|
||||
}
|
||||
16
special_tokens_map.json
Normal file
16
special_tokens_map.json
Normal file
@@ -0,0 +1,16 @@
|
||||
{
|
||||
"eos_token": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
|
||||
size 11421892
|
||||
194
tokenizer_config.json
Normal file
194
tokenizer_config.json
Normal file
@@ -0,0 +1,194 @@
|
||||
{
|
||||
"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
|
||||
}
|
||||
},
|
||||
"backend": "tokenizers",
|
||||
"bos_token": null,
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": {},
|
||||
"is_local": true,
|
||||
"model_max_length": 32768,
|
||||
"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": 456031784665088.0,
|
||||
"train_loss": 0.26182658547373117,
|
||||
"train_runtime": 16760.0523,
|
||||
"train_samples_per_second": 0.386,
|
||||
"train_steps_per_second": 0.064
|
||||
}
|
||||
108
trainer_log.jsonl
Normal file
108
trainer_log.jsonl
Normal file
@@ -0,0 +1,108 @@
|
||||
{"current_steps": 10, "total_steps": 1078, "loss": 2.9472, "lr": 8.333333333333333e-07, "epoch": 0.01855287569573284, "percentage": 0.93, "elapsed_time": "0:02:58", "remaining_time": "5:17:51"}
|
||||
{"current_steps": 20, "total_steps": 1078, "loss": 2.6542, "lr": 1.7592592592592594e-06, "epoch": 0.03710575139146568, "percentage": 1.86, "elapsed_time": "0:05:39", "remaining_time": "4:59:08"}
|
||||
{"current_steps": 30, "total_steps": 1078, "loss": 1.5155, "lr": 2.6851851851851856e-06, "epoch": 0.055658627087198514, "percentage": 2.78, "elapsed_time": "0:08:03", "remaining_time": "4:41:34"}
|
||||
{"current_steps": 40, "total_steps": 1078, "loss": 0.9282, "lr": 3.6111111111111115e-06, "epoch": 0.07421150278293136, "percentage": 3.71, "elapsed_time": "0:10:27", "remaining_time": "4:31:11"}
|
||||
{"current_steps": 50, "total_steps": 1078, "loss": 0.8926, "lr": 4.537037037037038e-06, "epoch": 0.09276437847866419, "percentage": 4.64, "elapsed_time": "0:13:05", "remaining_time": "4:29:15"}
|
||||
{"current_steps": 60, "total_steps": 1078, "loss": 0.6386, "lr": 5.462962962962963e-06, "epoch": 0.11131725417439703, "percentage": 5.57, "elapsed_time": "0:15:55", "remaining_time": "4:30:14"}
|
||||
{"current_steps": 70, "total_steps": 1078, "loss": 0.4684, "lr": 6.3888888888888885e-06, "epoch": 0.12987012987012986, "percentage": 6.49, "elapsed_time": "0:18:36", "remaining_time": "4:28:00"}
|
||||
{"current_steps": 80, "total_steps": 1078, "loss": 0.3764, "lr": 7.314814814814816e-06, "epoch": 0.14842300556586271, "percentage": 7.42, "elapsed_time": "0:21:00", "remaining_time": "4:22:06"}
|
||||
{"current_steps": 90, "total_steps": 1078, "loss": 0.3314, "lr": 8.240740740740741e-06, "epoch": 0.16697588126159554, "percentage": 8.35, "elapsed_time": "0:23:17", "remaining_time": "4:15:45"}
|
||||
{"current_steps": 100, "total_steps": 1078, "loss": 0.3162, "lr": 9.166666666666666e-06, "epoch": 0.18552875695732837, "percentage": 9.28, "elapsed_time": "0:25:52", "remaining_time": "4:13:07"}
|
||||
{"current_steps": 110, "total_steps": 1078, "loss": 0.32, "lr": 9.99997377618298e-06, "epoch": 0.20408163265306123, "percentage": 10.2, "elapsed_time": "0:28:42", "remaining_time": "4:12:35"}
|
||||
{"current_steps": 120, "total_steps": 1078, "loss": 0.2867, "lr": 9.99682725096819e-06, "epoch": 0.22263450834879406, "percentage": 11.13, "elapsed_time": "0:31:22", "remaining_time": "4:10:27"}
|
||||
{"current_steps": 130, "total_steps": 1078, "loss": 0.2798, "lr": 9.988439743984155e-06, "epoch": 0.24118738404452691, "percentage": 12.06, "elapsed_time": "0:33:49", "remaining_time": "4:06:40"}
|
||||
{"current_steps": 140, "total_steps": 1078, "loss": 0.285, "lr": 9.97482005256746e-06, "epoch": 0.2597402597402597, "percentage": 12.99, "elapsed_time": "0:36:22", "remaining_time": "4:03:44"}
|
||||
{"current_steps": 150, "total_steps": 1078, "loss": 0.2687, "lr": 9.955982461893648e-06, "epoch": 0.2782931354359926, "percentage": 13.91, "elapsed_time": "0:38:39", "remaining_time": "3:59:08"}
|
||||
{"current_steps": 160, "total_steps": 1078, "loss": 0.274, "lr": 9.93194672999403e-06, "epoch": 0.29684601113172543, "percentage": 14.84, "elapsed_time": "0:41:46", "remaining_time": "3:59:43"}
|
||||
{"current_steps": 170, "total_steps": 1078, "loss": 0.2595, "lr": 9.902738067032254e-06, "epoch": 0.31539888682745826, "percentage": 15.77, "elapsed_time": "0:44:35", "remaining_time": "3:58:07"}
|
||||
{"current_steps": 180, "total_steps": 1078, "loss": 0.2503, "lr": 9.868387108862307e-06, "epoch": 0.3339517625231911, "percentage": 16.7, "elapsed_time": "0:46:58", "remaining_time": "3:54:19"}
|
||||
{"current_steps": 190, "total_steps": 1078, "loss": 0.2416, "lr": 9.828929884895753e-06, "epoch": 0.3525046382189239, "percentage": 17.63, "elapsed_time": "0:49:22", "remaining_time": "3:50:45"}
|
||||
{"current_steps": 200, "total_steps": 1078, "loss": 0.2428, "lr": 9.784407780311845e-06, "epoch": 0.37105751391465674, "percentage": 18.55, "elapsed_time": "0:51:37", "remaining_time": "3:46:38"}
|
||||
{"current_steps": 210, "total_steps": 1078, "loss": 0.2364, "lr": 9.734867492650187e-06, "epoch": 0.38961038961038963, "percentage": 19.48, "elapsed_time": "0:54:38", "remaining_time": "3:45:49"}
|
||||
{"current_steps": 220, "total_steps": 1078, "loss": 0.2384, "lr": 9.680360982831467e-06, "epoch": 0.40816326530612246, "percentage": 20.41, "elapsed_time": "0:57:12", "remaining_time": "3:43:06"}
|
||||
{"current_steps": 230, "total_steps": 1078, "loss": 0.2325, "lr": 9.620945420657625e-06, "epoch": 0.4267161410018553, "percentage": 21.34, "elapsed_time": "0:59:32", "remaining_time": "3:39:31"}
|
||||
{"current_steps": 240, "total_steps": 1078, "loss": 0.2415, "lr": 9.556683124848624e-06, "epoch": 0.4452690166975881, "percentage": 22.26, "elapsed_time": "1:01:47", "remaining_time": "3:35:44"}
|
||||
{"current_steps": 250, "total_steps": 1078, "loss": 0.2296, "lr": 9.487641497678724e-06, "epoch": 0.46382189239332094, "percentage": 23.19, "elapsed_time": "1:04:06", "remaining_time": "3:32:20"}
|
||||
{"current_steps": 260, "total_steps": 1078, "loss": 0.2318, "lr": 9.413892954280793e-06, "epoch": 0.48237476808905383, "percentage": 24.12, "elapsed_time": "1:06:59", "remaining_time": "3:30:44"}
|
||||
{"current_steps": 270, "total_steps": 1078, "loss": 0.2425, "lr": 9.335514846692846e-06, "epoch": 0.5009276437847866, "percentage": 25.05, "elapsed_time": "1:09:52", "remaining_time": "3:29:06"}
|
||||
{"current_steps": 280, "total_steps": 1078, "loss": 0.2235, "lr": 9.252589382726426e-06, "epoch": 0.5194805194805194, "percentage": 25.97, "elapsed_time": "1:12:21", "remaining_time": "3:26:12"}
|
||||
{"current_steps": 290, "total_steps": 1078, "loss": 0.2171, "lr": 9.165203539741976e-06, "epoch": 0.5380333951762524, "percentage": 26.9, "elapsed_time": "1:14:40", "remaining_time": "3:22:54"}
|
||||
{"current_steps": 300, "total_steps": 1078, "loss": 0.2393, "lr": 9.073448973421581e-06, "epoch": 0.5565862708719852, "percentage": 27.83, "elapsed_time": "1:17:13", "remaining_time": "3:20:15"}
|
||||
{"current_steps": 310, "total_steps": 1078, "loss": 0.2276, "lr": 8.977421921634833e-06, "epoch": 0.575139146567718, "percentage": 28.76, "elapsed_time": "1:19:58", "remaining_time": "3:18:07"}
|
||||
{"current_steps": 320, "total_steps": 1078, "loss": 0.2232, "lr": 8.877223103498576e-06, "epoch": 0.5936920222634509, "percentage": 29.68, "elapsed_time": "1:22:31", "remaining_time": "3:15:29"}
|
||||
{"current_steps": 330, "total_steps": 1078, "loss": 0.208, "lr": 8.772957613736483e-06, "epoch": 0.6122448979591837, "percentage": 30.61, "elapsed_time": "1:24:57", "remaining_time": "3:12:34"}
|
||||
{"current_steps": 340, "total_steps": 1078, "loss": 0.2184, "lr": 8.66473481244918e-06, "epoch": 0.6307977736549165, "percentage": 31.54, "elapsed_time": "1:27:15", "remaining_time": "3:09:24"}
|
||||
{"current_steps": 350, "total_steps": 1078, "loss": 0.2322, "lr": 8.552668210410624e-06, "epoch": 0.6493506493506493, "percentage": 32.47, "elapsed_time": "1:29:42", "remaining_time": "3:06:36"}
|
||||
{"current_steps": 360, "total_steps": 1078, "loss": 0.2252, "lr": 8.436875350010958e-06, "epoch": 0.6679035250463822, "percentage": 33.4, "elapsed_time": "1:32:42", "remaining_time": "3:04:54"}
|
||||
{"current_steps": 370, "total_steps": 1078, "loss": 0.2118, "lr": 8.317477681970786e-06, "epoch": 0.686456400742115, "percentage": 34.32, "elapsed_time": "1:35:29", "remaining_time": "3:02:43"}
|
||||
{"current_steps": 380, "total_steps": 1078, "loss": 0.2286, "lr": 8.19460043795614e-06, "epoch": 0.7050092764378478, "percentage": 35.25, "elapsed_time": "1:37:47", "remaining_time": "2:59:37"}
|
||||
{"current_steps": 390, "total_steps": 1078, "loss": 0.226, "lr": 8.068372499227738e-06, "epoch": 0.7235621521335807, "percentage": 36.18, "elapsed_time": "1:40:03", "remaining_time": "2:56:31"}
|
||||
{"current_steps": 400, "total_steps": 1078, "loss": 0.2172, "lr": 7.938926261462366e-06, "epoch": 0.7421150278293135, "percentage": 37.11, "elapsed_time": "1:42:31", "remaining_time": "2:53:47"}
|
||||
{"current_steps": 410, "total_steps": 1078, "loss": 0.2282, "lr": 7.806397495888074e-06, "epoch": 0.7606679035250464, "percentage": 38.03, "elapsed_time": "1:45:25", "remaining_time": "2:51:46"}
|
||||
{"current_steps": 420, "total_steps": 1078, "loss": 0.2174, "lr": 7.670925206878917e-06, "epoch": 0.7792207792207793, "percentage": 38.96, "elapsed_time": "1:48:13", "remaining_time": "2:49:33"}
|
||||
{"current_steps": 430, "total_steps": 1078, "loss": 0.2107, "lr": 7.532651486158554e-06, "epoch": 0.7977736549165121, "percentage": 39.89, "elapsed_time": "1:50:39", "remaining_time": "2:46:46"}
|
||||
{"current_steps": 440, "total_steps": 1078, "loss": 0.2123, "lr": 7.391721363765664e-06, "epoch": 0.8163265306122449, "percentage": 40.82, "elapsed_time": "1:53:03", "remaining_time": "2:43:56"}
|
||||
{"current_steps": 450, "total_steps": 1078, "loss": 0.2159, "lr": 7.248282655937451e-06, "epoch": 0.8348794063079777, "percentage": 41.74, "elapsed_time": "1:55:41", "remaining_time": "2:41:27"}
|
||||
{"current_steps": 460, "total_steps": 1078, "loss": 0.2213, "lr": 7.102485810070824e-06, "epoch": 0.8534322820037106, "percentage": 42.67, "elapsed_time": "1:58:34", "remaining_time": "2:39:18"}
|
||||
{"current_steps": 470, "total_steps": 1078, "loss": 0.2143, "lr": 6.954483746923865e-06, "epoch": 0.8719851576994434, "percentage": 43.6, "elapsed_time": "2:01:16", "remaining_time": "2:36:52"}
|
||||
{"current_steps": 480, "total_steps": 1078, "loss": 0.2156, "lr": 6.804431700223057e-06, "epoch": 0.8905380333951762, "percentage": 44.53, "elapsed_time": "2:03:47", "remaining_time": "2:34:13"}
|
||||
{"current_steps": 490, "total_steps": 1078, "loss": 0.2191, "lr": 6.652487053844544e-06, "epoch": 0.9090909090909091, "percentage": 45.45, "elapsed_time": "2:06:24", "remaining_time": "2:31:40"}
|
||||
{"current_steps": 500, "total_steps": 1078, "loss": 0.208, "lr": 6.49880917674019e-06, "epoch": 0.9276437847866419, "percentage": 46.38, "elapsed_time": "2:09:00", "remaining_time": "2:29:08"}
|
||||
{"current_steps": 510, "total_steps": 1078, "loss": 0.2045, "lr": 6.343559255781538e-06, "epoch": 0.9461966604823747, "percentage": 47.31, "elapsed_time": "2:11:50", "remaining_time": "2:26:50"}
|
||||
{"current_steps": 520, "total_steps": 1078, "loss": 0.1979, "lr": 6.18690012669705e-06, "epoch": 0.9647495361781077, "percentage": 48.24, "elapsed_time": "2:14:17", "remaining_time": "2:24:06"}
|
||||
{"current_steps": 530, "total_steps": 1078, "loss": 0.2027, "lr": 6.028996103279918e-06, "epoch": 0.9833024118738405, "percentage": 49.17, "elapsed_time": "2:16:36", "remaining_time": "2:21:14"}
|
||||
{"current_steps": 540, "total_steps": 1078, "loss": 0.213, "lr": 5.87001280504558e-06, "epoch": 1.0018552875695732, "percentage": 50.09, "elapsed_time": "2:19:30", "remaining_time": "2:18:59"}
|
||||
{"current_steps": 550, "total_steps": 1078, "loss": 0.14, "lr": 5.7101169835197115e-06, "epoch": 1.0204081632653061, "percentage": 51.02, "elapsed_time": "2:22:03", "remaining_time": "2:16:22"}
|
||||
{"current_steps": 560, "total_steps": 1078, "loss": 0.1305, "lr": 5.549476347338915e-06, "epoch": 1.0389610389610389, "percentage": 51.95, "elapsed_time": "2:24:42", "remaining_time": "2:13:51"}
|
||||
{"current_steps": 570, "total_steps": 1078, "loss": 0.132, "lr": 5.388259386347518e-06, "epoch": 1.0575139146567718, "percentage": 52.88, "elapsed_time": "2:27:01", "remaining_time": "2:11:01"}
|
||||
{"current_steps": 580, "total_steps": 1078, "loss": 0.1371, "lr": 5.226635194874978e-06, "epoch": 1.0760667903525047, "percentage": 53.8, "elapsed_time": "2:29:23", "remaining_time": "2:08:16"}
|
||||
{"current_steps": 590, "total_steps": 1078, "loss": 0.1292, "lr": 5.064773294379302e-06, "epoch": 1.0946196660482375, "percentage": 54.73, "elapsed_time": "2:32:02", "remaining_time": "2:05:45"}
|
||||
{"current_steps": 600, "total_steps": 1078, "loss": 0.1366, "lr": 4.9028434556424335e-06, "epoch": 1.1131725417439704, "percentage": 55.66, "elapsed_time": "2:34:43", "remaining_time": "2:03:15"}
|
||||
{"current_steps": 610, "total_steps": 1078, "loss": 0.1461, "lr": 4.741015520704148e-06, "epoch": 1.1317254174397031, "percentage": 56.59, "elapsed_time": "2:37:16", "remaining_time": "2:00:39"}
|
||||
{"current_steps": 620, "total_steps": 1078, "loss": 0.125, "lr": 4.579459224721212e-06, "epoch": 1.150278293135436, "percentage": 57.51, "elapsed_time": "2:39:39", "remaining_time": "1:57:56"}
|
||||
{"current_steps": 630, "total_steps": 1078, "loss": 0.1308, "lr": 4.418344017938634e-06, "epoch": 1.1688311688311688, "percentage": 58.44, "elapsed_time": "2:42:02", "remaining_time": "1:55:13"}
|
||||
{"current_steps": 640, "total_steps": 1078, "loss": 0.1405, "lr": 4.257838887959764e-06, "epoch": 1.1873840445269017, "percentage": 59.37, "elapsed_time": "2:45:11", "remaining_time": "1:53:02"}
|
||||
{"current_steps": 650, "total_steps": 1078, "loss": 0.1306, "lr": 4.098112182501633e-06, "epoch": 1.2059369202226344, "percentage": 60.3, "elapsed_time": "2:47:57", "remaining_time": "1:50:35"}
|
||||
{"current_steps": 660, "total_steps": 1078, "loss": 0.1319, "lr": 3.93933143282144e-06, "epoch": 1.2244897959183674, "percentage": 61.22, "elapsed_time": "2:50:37", "remaining_time": "1:48:03"}
|
||||
{"current_steps": 670, "total_steps": 1078, "loss": 0.1367, "lr": 3.7816631779994018e-06, "epoch": 1.2430426716141, "percentage": 62.15, "elapsed_time": "2:52:58", "remaining_time": "1:45:19"}
|
||||
{"current_steps": 680, "total_steps": 1078, "loss": 0.1227, "lr": 3.6252727902622575e-06, "epoch": 1.261595547309833, "percentage": 63.08, "elapsed_time": "2:55:17", "remaining_time": "1:42:35"}
|
||||
{"current_steps": 690, "total_steps": 1078, "loss": 0.1382, "lr": 3.4703243015306314e-06, "epoch": 1.2801484230055657, "percentage": 64.01, "elapsed_time": "2:58:14", "remaining_time": "1:40:13"}
|
||||
{"current_steps": 700, "total_steps": 1078, "loss": 0.1444, "lr": 3.3169802313722076e-06, "epoch": 1.2987012987012987, "percentage": 64.94, "elapsed_time": "3:00:51", "remaining_time": "1:37:39"}
|
||||
{"current_steps": 710, "total_steps": 1078, "loss": 0.1301, "lr": 3.16540141654114e-06, "epoch": 1.3172541743970316, "percentage": 65.86, "elapsed_time": "3:03:18", "remaining_time": "1:35:00"}
|
||||
{"current_steps": 720, "total_steps": 1078, "loss": 0.1283, "lr": 3.0157468422825148e-06, "epoch": 1.3358070500927643, "percentage": 66.79, "elapsed_time": "3:05:33", "remaining_time": "1:32:15"}
|
||||
{"current_steps": 730, "total_steps": 1078, "loss": 0.1223, "lr": 2.868173475578772e-06, "epoch": 1.3543599257884973, "percentage": 67.72, "elapsed_time": "3:07:58", "remaining_time": "1:29:36"}
|
||||
{"current_steps": 740, "total_steps": 1078, "loss": 0.1471, "lr": 2.722836100513027e-06, "epoch": 1.37291280148423, "percentage": 68.65, "elapsed_time": "3:10:42", "remaining_time": "1:27:06"}
|
||||
{"current_steps": 750, "total_steps": 1078, "loss": 0.1287, "lr": 2.5798871559219362e-06, "epoch": 1.391465677179963, "percentage": 69.57, "elapsed_time": "3:13:25", "remaining_time": "1:24:35"}
|
||||
{"current_steps": 760, "total_steps": 1078, "loss": 0.1341, "lr": 2.439476575508408e-06, "epoch": 1.4100185528756957, "percentage": 70.5, "elapsed_time": "3:16:01", "remaining_time": "1:22:01"}
|
||||
{"current_steps": 770, "total_steps": 1078, "loss": 0.1256, "lr": 2.301751630581855e-06, "epoch": 1.4285714285714286, "percentage": 71.43, "elapsed_time": "3:18:22", "remaining_time": "1:19:21"}
|
||||
{"current_steps": 780, "total_steps": 1078, "loss": 0.1245, "lr": 2.1668567755909257e-06, "epoch": 1.4471243042671613, "percentage": 72.36, "elapsed_time": "3:20:49", "remaining_time": "1:16:43"}
|
||||
{"current_steps": 790, "total_steps": 1078, "loss": 0.1451, "lr": 2.0349334966107363e-06, "epoch": 1.4656771799628943, "percentage": 73.28, "elapsed_time": "3:23:40", "remaining_time": "1:14:15"}
|
||||
{"current_steps": 800, "total_steps": 1078, "loss": 0.1339, "lr": 1.906120162943515e-06, "epoch": 1.4842300556586272, "percentage": 74.21, "elapsed_time": "3:26:12", "remaining_time": "1:11:39"}
|
||||
{"current_steps": 810, "total_steps": 1078, "loss": 0.1271, "lr": 1.7805518819883134e-06, "epoch": 1.50278293135436, "percentage": 75.14, "elapsed_time": "3:28:42", "remaining_time": "1:09:03"}
|
||||
{"current_steps": 820, "total_steps": 1078, "loss": 0.1262, "lr": 1.6583603575320002e-06, "epoch": 1.5213358070500926, "percentage": 76.07, "elapsed_time": "3:31:06", "remaining_time": "1:06:25"}
|
||||
{"current_steps": 830, "total_steps": 1078, "loss": 0.1244, "lr": 1.5396737516101757e-06, "epoch": 1.5398886827458256, "percentage": 76.99, "elapsed_time": "3:33:35", "remaining_time": "1:03:49"}
|
||||
{"current_steps": 840, "total_steps": 1078, "loss": 0.1266, "lr": 1.4246165500828974e-06, "epoch": 1.5584415584415585, "percentage": 77.92, "elapsed_time": "3:36:20", "remaining_time": "1:01:17"}
|
||||
{"current_steps": 850, "total_steps": 1078, "loss": 0.1298, "lr": 1.3133094320662e-06, "epoch": 1.5769944341372912, "percentage": 78.85, "elapsed_time": "3:38:55", "remaining_time": "0:58:43"}
|
||||
{"current_steps": 860, "total_steps": 1078, "loss": 0.13, "lr": 1.2058691433563675e-06, "epoch": 1.595547309833024, "percentage": 79.78, "elapsed_time": "3:41:39", "remaining_time": "0:56:11"}
|
||||
{"current_steps": 870, "total_steps": 1078, "loss": 0.1228, "lr": 1.102408373979717e-06, "epoch": 1.614100185528757, "percentage": 80.71, "elapsed_time": "3:44:04", "remaining_time": "0:53:34"}
|
||||
{"current_steps": 880, "total_steps": 1078, "loss": 0.1214, "lr": 1.0030356399963204e-06, "epoch": 1.6326530612244898, "percentage": 81.63, "elapsed_time": "3:46:30", "remaining_time": "0:50:57"}
|
||||
{"current_steps": 890, "total_steps": 1078, "loss": 0.1287, "lr": 9.078551696816434e-07, "epoch": 1.6512059369202228, "percentage": 82.56, "elapsed_time": "3:49:13", "remaining_time": "0:48:25"}
|
||||
{"current_steps": 900, "total_steps": 1078, "loss": 0.1276, "lr": 8.16966794205476e-07, "epoch": 1.6697588126159555, "percentage": 83.49, "elapsed_time": "3:52:00", "remaining_time": "0:45:53"}
|
||||
{"current_steps": 910, "total_steps": 1078, "loss": 0.1314, "lr": 7.304658429228245e-07, "epoch": 1.6883116883116882, "percentage": 84.42, "elapsed_time": "3:54:40", "remaining_time": "0:43:19"}
|
||||
{"current_steps": 920, "total_steps": 1078, "loss": 0.1267, "lr": 6.484430433865785e-07, "epoch": 1.7068645640074211, "percentage": 85.34, "elapsed_time": "3:56:58", "remaining_time": "0:40:41"}
|
||||
{"current_steps": 930, "total_steps": 1078, "loss": 0.1251, "lr": 5.709844261868381e-07, "epoch": 1.725417439703154, "percentage": 86.27, "elapsed_time": "3:59:21", "remaining_time": "0:38:05"}
|
||||
{"current_steps": 940, "total_steps": 1078, "loss": 0.1263, "lr": 4.981712347167061e-07, "epoch": 1.7439703153988868, "percentage": 87.2, "elapsed_time": "4:01:54", "remaining_time": "0:35:30"}
|
||||
{"current_steps": 950, "total_steps": 1078, "loss": 0.1267, "lr": 4.30079839959186e-07, "epoch": 1.7625231910946195, "percentage": 88.13, "elapsed_time": "4:04:27", "remaining_time": "0:32:56"}
|
||||
{"current_steps": 960, "total_steps": 1078, "loss": 0.1233, "lr": 3.667816603845681e-07, "epoch": 1.7810760667903525, "percentage": 89.05, "elapsed_time": "4:06:58", "remaining_time": "0:30:21"}
|
||||
{"current_steps": 970, "total_steps": 1078, "loss": 0.1196, "lr": 3.0834308704231485e-07, "epoch": 1.7996289424860854, "percentage": 89.98, "elapsed_time": "4:09:26", "remaining_time": "0:27:46"}
|
||||
{"current_steps": 980, "total_steps": 1078, "loss": 0.1147, "lr": 2.5482541392601924e-07, "epoch": 1.8181818181818183, "percentage": 90.91, "elapsed_time": "4:11:49", "remaining_time": "0:25:10"}
|
||||
{"current_steps": 990, "total_steps": 1078, "loss": 0.1311, "lr": 2.062847736844703e-07, "epoch": 1.836734693877551, "percentage": 91.84, "elapsed_time": "4:14:46", "remaining_time": "0:22:38"}
|
||||
{"current_steps": 1000, "total_steps": 1078, "loss": 0.1326, "lr": 1.6277207874625444e-07, "epoch": 1.8552875695732838, "percentage": 92.76, "elapsed_time": "4:17:29", "remaining_time": "0:20:05"}
|
||||
{"current_steps": 1010, "total_steps": 1078, "loss": 0.1203, "lr": 1.2433296791964754e-07, "epoch": 1.8738404452690167, "percentage": 93.69, "elapsed_time": "4:20:03", "remaining_time": "0:17:30"}
|
||||
{"current_steps": 1020, "total_steps": 1078, "loss": 0.1162, "lr": 9.100775852381227e-08, "epoch": 1.8923933209647497, "percentage": 94.62, "elapsed_time": "4:22:27", "remaining_time": "0:14:55"}
|
||||
{"current_steps": 1030, "total_steps": 1078, "loss": 0.1174, "lr": 6.283140410149213e-08, "epoch": 1.9109461966604824, "percentage": 95.55, "elapsed_time": "4:24:50", "remaining_time": "0:12:20"}
|
||||
{"current_steps": 1040, "total_steps": 1078, "loss": 0.1362, "lr": 3.9833457757572636e-08, "epoch": 1.929499072356215, "percentage": 96.47, "elapsed_time": "4:27:47", "remaining_time": "0:09:47"}
|
||||
{"current_steps": 1050, "total_steps": 1078, "loss": 0.1215, "lr": 2.2038041161960288e-08, "epoch": 1.948051948051948, "percentage": 97.4, "elapsed_time": "4:30:21", "remaining_time": "0:07:12"}
|
||||
{"current_steps": 1060, "total_steps": 1078, "loss": 0.1181, "lr": 9.463819249275751e-09, "epoch": 1.966604823747681, "percentage": 98.33, "elapsed_time": "4:32:56", "remaining_time": "0:04:38"}
|
||||
{"current_steps": 1070, "total_steps": 1078, "loss": 0.1224, "lr": 2.1239806419176556e-09, "epoch": 1.9851576994434137, "percentage": 99.26, "elapsed_time": "4:35:24", "remaining_time": "0:02:03"}
|
||||
{"current_steps": 1078, "total_steps": 1078, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "4:39:20", "remaining_time": "0:00:00"}
|
||||
792
trainer_state.json
Normal file
792
trainer_state.json
Normal file
@@ -0,0 +1,792 @@
|
||||
{
|
||||
"best_global_step": null,
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 2.0,
|
||||
"eval_steps": 500,
|
||||
"global_step": 1078,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.01855287569573284,
|
||||
"grad_norm": 60.09148197149517,
|
||||
"learning_rate": 8.333333333333333e-07,
|
||||
"loss": 2.9472,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"epoch": 0.03710575139146568,
|
||||
"grad_norm": 38.855704459472975,
|
||||
"learning_rate": 1.7592592592592594e-06,
|
||||
"loss": 2.6542,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 0.055658627087198514,
|
||||
"grad_norm": 5.063334237382181,
|
||||
"learning_rate": 2.6851851851851856e-06,
|
||||
"loss": 1.5155,
|
||||
"step": 30
|
||||
},
|
||||
{
|
||||
"epoch": 0.07421150278293136,
|
||||
"grad_norm": 2.9672953129926576,
|
||||
"learning_rate": 3.6111111111111115e-06,
|
||||
"loss": 0.9282,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 0.09276437847866419,
|
||||
"grad_norm": 1.8537537673527857,
|
||||
"learning_rate": 4.537037037037038e-06,
|
||||
"loss": 0.8926,
|
||||
"step": 50
|
||||
},
|
||||
{
|
||||
"epoch": 0.11131725417439703,
|
||||
"grad_norm": 3.428912896471263,
|
||||
"learning_rate": 5.462962962962963e-06,
|
||||
"loss": 0.6386,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 0.12987012987012986,
|
||||
"grad_norm": 5.261034391804638,
|
||||
"learning_rate": 6.3888888888888885e-06,
|
||||
"loss": 0.4684,
|
||||
"step": 70
|
||||
},
|
||||
{
|
||||
"epoch": 0.14842300556586271,
|
||||
"grad_norm": 1.3915033824673388,
|
||||
"learning_rate": 7.314814814814816e-06,
|
||||
"loss": 0.3764,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 0.16697588126159554,
|
||||
"grad_norm": 1.3167457631005255,
|
||||
"learning_rate": 8.240740740740741e-06,
|
||||
"loss": 0.3314,
|
||||
"step": 90
|
||||
},
|
||||
{
|
||||
"epoch": 0.18552875695732837,
|
||||
"grad_norm": 1.1616342114119869,
|
||||
"learning_rate": 9.166666666666666e-06,
|
||||
"loss": 0.3162,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 0.20408163265306123,
|
||||
"grad_norm": 1.6904372750211418,
|
||||
"learning_rate": 9.99997377618298e-06,
|
||||
"loss": 0.32,
|
||||
"step": 110
|
||||
},
|
||||
{
|
||||
"epoch": 0.22263450834879406,
|
||||
"grad_norm": 1.6370524652439618,
|
||||
"learning_rate": 9.99682725096819e-06,
|
||||
"loss": 0.2867,
|
||||
"step": 120
|
||||
},
|
||||
{
|
||||
"epoch": 0.24118738404452691,
|
||||
"grad_norm": 0.9996394242016245,
|
||||
"learning_rate": 9.988439743984155e-06,
|
||||
"loss": 0.2798,
|
||||
"step": 130
|
||||
},
|
||||
{
|
||||
"epoch": 0.2597402597402597,
|
||||
"grad_norm": 1.105275657101106,
|
||||
"learning_rate": 9.97482005256746e-06,
|
||||
"loss": 0.285,
|
||||
"step": 140
|
||||
},
|
||||
{
|
||||
"epoch": 0.2782931354359926,
|
||||
"grad_norm": 1.0656580706685925,
|
||||
"learning_rate": 9.955982461893648e-06,
|
||||
"loss": 0.2687,
|
||||
"step": 150
|
||||
},
|
||||
{
|
||||
"epoch": 0.29684601113172543,
|
||||
"grad_norm": 1.4055251928327075,
|
||||
"learning_rate": 9.93194672999403e-06,
|
||||
"loss": 0.274,
|
||||
"step": 160
|
||||
},
|
||||
{
|
||||
"epoch": 0.31539888682745826,
|
||||
"grad_norm": 0.955521719488787,
|
||||
"learning_rate": 9.902738067032254e-06,
|
||||
"loss": 0.2595,
|
||||
"step": 170
|
||||
},
|
||||
{
|
||||
"epoch": 0.3339517625231911,
|
||||
"grad_norm": 2.7989567654700673,
|
||||
"learning_rate": 9.868387108862307e-06,
|
||||
"loss": 0.2503,
|
||||
"step": 180
|
||||
},
|
||||
{
|
||||
"epoch": 0.3525046382189239,
|
||||
"grad_norm": 1.1080193292817926,
|
||||
"learning_rate": 9.828929884895753e-06,
|
||||
"loss": 0.2416,
|
||||
"step": 190
|
||||
},
|
||||
{
|
||||
"epoch": 0.37105751391465674,
|
||||
"grad_norm": 0.8932615001563428,
|
||||
"learning_rate": 9.784407780311845e-06,
|
||||
"loss": 0.2428,
|
||||
"step": 200
|
||||
},
|
||||
{
|
||||
"epoch": 0.38961038961038963,
|
||||
"grad_norm": 1.2146643079836965,
|
||||
"learning_rate": 9.734867492650187e-06,
|
||||
"loss": 0.2364,
|
||||
"step": 210
|
||||
},
|
||||
{
|
||||
"epoch": 0.40816326530612246,
|
||||
"grad_norm": 1.145275092602219,
|
||||
"learning_rate": 9.680360982831467e-06,
|
||||
"loss": 0.2384,
|
||||
"step": 220
|
||||
},
|
||||
{
|
||||
"epoch": 0.4267161410018553,
|
||||
"grad_norm": 0.7358756050937082,
|
||||
"learning_rate": 9.620945420657625e-06,
|
||||
"loss": 0.2325,
|
||||
"step": 230
|
||||
},
|
||||
{
|
||||
"epoch": 0.4452690166975881,
|
||||
"grad_norm": 0.9469502291509642,
|
||||
"learning_rate": 9.556683124848624e-06,
|
||||
"loss": 0.2415,
|
||||
"step": 240
|
||||
},
|
||||
{
|
||||
"epoch": 0.46382189239332094,
|
||||
"grad_norm": 0.8629958324420408,
|
||||
"learning_rate": 9.487641497678724e-06,
|
||||
"loss": 0.2296,
|
||||
"step": 250
|
||||
},
|
||||
{
|
||||
"epoch": 0.48237476808905383,
|
||||
"grad_norm": 0.9672085960501411,
|
||||
"learning_rate": 9.413892954280793e-06,
|
||||
"loss": 0.2318,
|
||||
"step": 260
|
||||
},
|
||||
{
|
||||
"epoch": 0.5009276437847866,
|
||||
"grad_norm": 0.8366109170992587,
|
||||
"learning_rate": 9.335514846692846e-06,
|
||||
"loss": 0.2425,
|
||||
"step": 270
|
||||
},
|
||||
{
|
||||
"epoch": 0.5194805194805194,
|
||||
"grad_norm": 0.8555696459778686,
|
||||
"learning_rate": 9.252589382726426e-06,
|
||||
"loss": 0.2235,
|
||||
"step": 280
|
||||
},
|
||||
{
|
||||
"epoch": 0.5380333951762524,
|
||||
"grad_norm": 0.65154561944275,
|
||||
"learning_rate": 9.165203539741976e-06,
|
||||
"loss": 0.2171,
|
||||
"step": 290
|
||||
},
|
||||
{
|
||||
"epoch": 0.5565862708719852,
|
||||
"grad_norm": 0.8174459194486984,
|
||||
"learning_rate": 9.073448973421581e-06,
|
||||
"loss": 0.2393,
|
||||
"step": 300
|
||||
},
|
||||
{
|
||||
"epoch": 0.575139146567718,
|
||||
"grad_norm": 1.179097990857863,
|
||||
"learning_rate": 8.977421921634833e-06,
|
||||
"loss": 0.2276,
|
||||
"step": 310
|
||||
},
|
||||
{
|
||||
"epoch": 0.5936920222634509,
|
||||
"grad_norm": 1.164135161117637,
|
||||
"learning_rate": 8.877223103498576e-06,
|
||||
"loss": 0.2232,
|
||||
"step": 320
|
||||
},
|
||||
{
|
||||
"epoch": 0.6122448979591837,
|
||||
"grad_norm": 0.9194559443120759,
|
||||
"learning_rate": 8.772957613736483e-06,
|
||||
"loss": 0.208,
|
||||
"step": 330
|
||||
},
|
||||
{
|
||||
"epoch": 0.6307977736549165,
|
||||
"grad_norm": 0.8725673809937737,
|
||||
"learning_rate": 8.66473481244918e-06,
|
||||
"loss": 0.2184,
|
||||
"step": 340
|
||||
},
|
||||
{
|
||||
"epoch": 0.6493506493506493,
|
||||
"grad_norm": 0.7606564604713997,
|
||||
"learning_rate": 8.552668210410624e-06,
|
||||
"loss": 0.2322,
|
||||
"step": 350
|
||||
},
|
||||
{
|
||||
"epoch": 0.6679035250463822,
|
||||
"grad_norm": 1.7475773499685987,
|
||||
"learning_rate": 8.436875350010958e-06,
|
||||
"loss": 0.2252,
|
||||
"step": 360
|
||||
},
|
||||
{
|
||||
"epoch": 0.686456400742115,
|
||||
"grad_norm": 0.8902082858576856,
|
||||
"learning_rate": 8.317477681970786e-06,
|
||||
"loss": 0.2118,
|
||||
"step": 370
|
||||
},
|
||||
{
|
||||
"epoch": 0.7050092764378478,
|
||||
"grad_norm": 0.6756559134494782,
|
||||
"learning_rate": 8.19460043795614e-06,
|
||||
"loss": 0.2286,
|
||||
"step": 380
|
||||
},
|
||||
{
|
||||
"epoch": 0.7235621521335807,
|
||||
"grad_norm": 0.7753939520244841,
|
||||
"learning_rate": 8.068372499227738e-06,
|
||||
"loss": 0.226,
|
||||
"step": 390
|
||||
},
|
||||
{
|
||||
"epoch": 0.7421150278293135,
|
||||
"grad_norm": 0.8189644955934055,
|
||||
"learning_rate": 7.938926261462366e-06,
|
||||
"loss": 0.2172,
|
||||
"step": 400
|
||||
},
|
||||
{
|
||||
"epoch": 0.7606679035250464,
|
||||
"grad_norm": 1.2227576197844174,
|
||||
"learning_rate": 7.806397495888074e-06,
|
||||
"loss": 0.2282,
|
||||
"step": 410
|
||||
},
|
||||
{
|
||||
"epoch": 0.7792207792207793,
|
||||
"grad_norm": 0.7133788769555174,
|
||||
"learning_rate": 7.670925206878917e-06,
|
||||
"loss": 0.2174,
|
||||
"step": 420
|
||||
},
|
||||
{
|
||||
"epoch": 0.7977736549165121,
|
||||
"grad_norm": 0.767835676921408,
|
||||
"learning_rate": 7.532651486158554e-06,
|
||||
"loss": 0.2107,
|
||||
"step": 430
|
||||
},
|
||||
{
|
||||
"epoch": 0.8163265306122449,
|
||||
"grad_norm": 2.48600742003163,
|
||||
"learning_rate": 7.391721363765664e-06,
|
||||
"loss": 0.2123,
|
||||
"step": 440
|
||||
},
|
||||
{
|
||||
"epoch": 0.8348794063079777,
|
||||
"grad_norm": 0.6665575100282729,
|
||||
"learning_rate": 7.248282655937451e-06,
|
||||
"loss": 0.2159,
|
||||
"step": 450
|
||||
},
|
||||
{
|
||||
"epoch": 0.8534322820037106,
|
||||
"grad_norm": 1.2649819297037939,
|
||||
"learning_rate": 7.102485810070824e-06,
|
||||
"loss": 0.2213,
|
||||
"step": 460
|
||||
},
|
||||
{
|
||||
"epoch": 0.8719851576994434,
|
||||
"grad_norm": 1.237103957840642,
|
||||
"learning_rate": 6.954483746923865e-06,
|
||||
"loss": 0.2143,
|
||||
"step": 470
|
||||
},
|
||||
{
|
||||
"epoch": 0.8905380333951762,
|
||||
"grad_norm": 1.1721776707126947,
|
||||
"learning_rate": 6.804431700223057e-06,
|
||||
"loss": 0.2156,
|
||||
"step": 480
|
||||
},
|
||||
{
|
||||
"epoch": 0.9090909090909091,
|
||||
"grad_norm": 1.0611712427213547,
|
||||
"learning_rate": 6.652487053844544e-06,
|
||||
"loss": 0.2191,
|
||||
"step": 490
|
||||
},
|
||||
{
|
||||
"epoch": 0.9276437847866419,
|
||||
"grad_norm": 0.7509649989043815,
|
||||
"learning_rate": 6.49880917674019e-06,
|
||||
"loss": 0.208,
|
||||
"step": 500
|
||||
},
|
||||
{
|
||||
"epoch": 0.9461966604823747,
|
||||
"grad_norm": 1.9679575531610882,
|
||||
"learning_rate": 6.343559255781538e-06,
|
||||
"loss": 0.2045,
|
||||
"step": 510
|
||||
},
|
||||
{
|
||||
"epoch": 0.9647495361781077,
|
||||
"grad_norm": 0.9410395170594658,
|
||||
"learning_rate": 6.18690012669705e-06,
|
||||
"loss": 0.1979,
|
||||
"step": 520
|
||||
},
|
||||
{
|
||||
"epoch": 0.9833024118738405,
|
||||
"grad_norm": 0.7001206344622368,
|
||||
"learning_rate": 6.028996103279918e-06,
|
||||
"loss": 0.2027,
|
||||
"step": 530
|
||||
},
|
||||
{
|
||||
"epoch": 1.0018552875695732,
|
||||
"grad_norm": 1.0171159957483642,
|
||||
"learning_rate": 5.87001280504558e-06,
|
||||
"loss": 0.213,
|
||||
"step": 540
|
||||
},
|
||||
{
|
||||
"epoch": 1.0204081632653061,
|
||||
"grad_norm": 1.0453391912762757,
|
||||
"learning_rate": 5.7101169835197115e-06,
|
||||
"loss": 0.14,
|
||||
"step": 550
|
||||
},
|
||||
{
|
||||
"epoch": 1.0389610389610389,
|
||||
"grad_norm": 0.8392060229822733,
|
||||
"learning_rate": 5.549476347338915e-06,
|
||||
"loss": 0.1305,
|
||||
"step": 560
|
||||
},
|
||||
{
|
||||
"epoch": 1.0575139146567718,
|
||||
"grad_norm": 0.8088617971203363,
|
||||
"learning_rate": 5.388259386347518e-06,
|
||||
"loss": 0.132,
|
||||
"step": 570
|
||||
},
|
||||
{
|
||||
"epoch": 1.0760667903525047,
|
||||
"grad_norm": 1.443734395132653,
|
||||
"learning_rate": 5.226635194874978e-06,
|
||||
"loss": 0.1371,
|
||||
"step": 580
|
||||
},
|
||||
{
|
||||
"epoch": 1.0946196660482375,
|
||||
"grad_norm": 0.8920531372659211,
|
||||
"learning_rate": 5.064773294379302e-06,
|
||||
"loss": 0.1292,
|
||||
"step": 590
|
||||
},
|
||||
{
|
||||
"epoch": 1.1131725417439704,
|
||||
"grad_norm": 1.0600375600094234,
|
||||
"learning_rate": 4.9028434556424335e-06,
|
||||
"loss": 0.1366,
|
||||
"step": 600
|
||||
},
|
||||
{
|
||||
"epoch": 1.1317254174397031,
|
||||
"grad_norm": 0.6174457523927003,
|
||||
"learning_rate": 4.741015520704148e-06,
|
||||
"loss": 0.1461,
|
||||
"step": 610
|
||||
},
|
||||
{
|
||||
"epoch": 1.150278293135436,
|
||||
"grad_norm": 0.7413719867170724,
|
||||
"learning_rate": 4.579459224721212e-06,
|
||||
"loss": 0.125,
|
||||
"step": 620
|
||||
},
|
||||
{
|
||||
"epoch": 1.1688311688311688,
|
||||
"grad_norm": 0.7428769835248965,
|
||||
"learning_rate": 4.418344017938634e-06,
|
||||
"loss": 0.1308,
|
||||
"step": 630
|
||||
},
|
||||
{
|
||||
"epoch": 1.1873840445269017,
|
||||
"grad_norm": 1.1554971703426302,
|
||||
"learning_rate": 4.257838887959764e-06,
|
||||
"loss": 0.1405,
|
||||
"step": 640
|
||||
},
|
||||
{
|
||||
"epoch": 1.2059369202226344,
|
||||
"grad_norm": 0.9187379299508138,
|
||||
"learning_rate": 4.098112182501633e-06,
|
||||
"loss": 0.1306,
|
||||
"step": 650
|
||||
},
|
||||
{
|
||||
"epoch": 1.2244897959183674,
|
||||
"grad_norm": 0.7989292570187497,
|
||||
"learning_rate": 3.93933143282144e-06,
|
||||
"loss": 0.1319,
|
||||
"step": 660
|
||||
},
|
||||
{
|
||||
"epoch": 1.2430426716141,
|
||||
"grad_norm": 0.8037568461641328,
|
||||
"learning_rate": 3.7816631779994018e-06,
|
||||
"loss": 0.1367,
|
||||
"step": 670
|
||||
},
|
||||
{
|
||||
"epoch": 1.261595547309833,
|
||||
"grad_norm": 0.7347468570406386,
|
||||
"learning_rate": 3.6252727902622575e-06,
|
||||
"loss": 0.1227,
|
||||
"step": 680
|
||||
},
|
||||
{
|
||||
"epoch": 1.2801484230055657,
|
||||
"grad_norm": 1.144050562175369,
|
||||
"learning_rate": 3.4703243015306314e-06,
|
||||
"loss": 0.1382,
|
||||
"step": 690
|
||||
},
|
||||
{
|
||||
"epoch": 1.2987012987012987,
|
||||
"grad_norm": 0.7989428953338974,
|
||||
"learning_rate": 3.3169802313722076e-06,
|
||||
"loss": 0.1444,
|
||||
"step": 700
|
||||
},
|
||||
{
|
||||
"epoch": 1.3172541743970316,
|
||||
"grad_norm": 0.616665850742756,
|
||||
"learning_rate": 3.16540141654114e-06,
|
||||
"loss": 0.1301,
|
||||
"step": 710
|
||||
},
|
||||
{
|
||||
"epoch": 1.3358070500927643,
|
||||
"grad_norm": 0.6664134211210629,
|
||||
"learning_rate": 3.0157468422825148e-06,
|
||||
"loss": 0.1283,
|
||||
"step": 720
|
||||
},
|
||||
{
|
||||
"epoch": 1.3543599257884973,
|
||||
"grad_norm": 0.5929267472787093,
|
||||
"learning_rate": 2.868173475578772e-06,
|
||||
"loss": 0.1223,
|
||||
"step": 730
|
||||
},
|
||||
{
|
||||
"epoch": 1.37291280148423,
|
||||
"grad_norm": 1.1909639489199855,
|
||||
"learning_rate": 2.722836100513027e-06,
|
||||
"loss": 0.1471,
|
||||
"step": 740
|
||||
},
|
||||
{
|
||||
"epoch": 1.391465677179963,
|
||||
"grad_norm": 0.7917032964998825,
|
||||
"learning_rate": 2.5798871559219362e-06,
|
||||
"loss": 0.1287,
|
||||
"step": 750
|
||||
},
|
||||
{
|
||||
"epoch": 1.4100185528756957,
|
||||
"grad_norm": 0.7775412493202811,
|
||||
"learning_rate": 2.439476575508408e-06,
|
||||
"loss": 0.1341,
|
||||
"step": 760
|
||||
},
|
||||
{
|
||||
"epoch": 1.4285714285714286,
|
||||
"grad_norm": 0.6871081961127913,
|
||||
"learning_rate": 2.301751630581855e-06,
|
||||
"loss": 0.1256,
|
||||
"step": 770
|
||||
},
|
||||
{
|
||||
"epoch": 1.4471243042671613,
|
||||
"grad_norm": 3.819276268656922,
|
||||
"learning_rate": 2.1668567755909257e-06,
|
||||
"loss": 0.1245,
|
||||
"step": 780
|
||||
},
|
||||
{
|
||||
"epoch": 1.4656771799628943,
|
||||
"grad_norm": 1.5879388915114736,
|
||||
"learning_rate": 2.0349334966107363e-06,
|
||||
"loss": 0.1451,
|
||||
"step": 790
|
||||
},
|
||||
{
|
||||
"epoch": 1.4842300556586272,
|
||||
"grad_norm": 1.0732264147107038,
|
||||
"learning_rate": 1.906120162943515e-06,
|
||||
"loss": 0.1339,
|
||||
"step": 800
|
||||
},
|
||||
{
|
||||
"epoch": 1.50278293135436,
|
||||
"grad_norm": 0.9759155260672688,
|
||||
"learning_rate": 1.7805518819883134e-06,
|
||||
"loss": 0.1271,
|
||||
"step": 810
|
||||
},
|
||||
{
|
||||
"epoch": 1.5213358070500926,
|
||||
"grad_norm": 0.8313050751146777,
|
||||
"learning_rate": 1.6583603575320002e-06,
|
||||
"loss": 0.1262,
|
||||
"step": 820
|
||||
},
|
||||
{
|
||||
"epoch": 1.5398886827458256,
|
||||
"grad_norm": 0.6978608117394565,
|
||||
"learning_rate": 1.5396737516101757e-06,
|
||||
"loss": 0.1244,
|
||||
"step": 830
|
||||
},
|
||||
{
|
||||
"epoch": 1.5584415584415585,
|
||||
"grad_norm": 1.5257058397579806,
|
||||
"learning_rate": 1.4246165500828974e-06,
|
||||
"loss": 0.1266,
|
||||
"step": 840
|
||||
},
|
||||
{
|
||||
"epoch": 1.5769944341372912,
|
||||
"grad_norm": 0.7687999727178765,
|
||||
"learning_rate": 1.3133094320662e-06,
|
||||
"loss": 0.1298,
|
||||
"step": 850
|
||||
},
|
||||
{
|
||||
"epoch": 1.595547309833024,
|
||||
"grad_norm": 0.9443564999213552,
|
||||
"learning_rate": 1.2058691433563675e-06,
|
||||
"loss": 0.13,
|
||||
"step": 860
|
||||
},
|
||||
{
|
||||
"epoch": 1.614100185528757,
|
||||
"grad_norm": 1.455717508617582,
|
||||
"learning_rate": 1.102408373979717e-06,
|
||||
"loss": 0.1228,
|
||||
"step": 870
|
||||
},
|
||||
{
|
||||
"epoch": 1.6326530612244898,
|
||||
"grad_norm": 0.8425010133335726,
|
||||
"learning_rate": 1.0030356399963204e-06,
|
||||
"loss": 0.1214,
|
||||
"step": 880
|
||||
},
|
||||
{
|
||||
"epoch": 1.6512059369202228,
|
||||
"grad_norm": 1.4449024332670837,
|
||||
"learning_rate": 9.078551696816434e-07,
|
||||
"loss": 0.1287,
|
||||
"step": 890
|
||||
},
|
||||
{
|
||||
"epoch": 1.6697588126159555,
|
||||
"grad_norm": 0.8028839534623334,
|
||||
"learning_rate": 8.16966794205476e-07,
|
||||
"loss": 0.1276,
|
||||
"step": 900
|
||||
},
|
||||
{
|
||||
"epoch": 1.6883116883116882,
|
||||
"grad_norm": 0.6958879285582347,
|
||||
"learning_rate": 7.304658429228245e-07,
|
||||
"loss": 0.1314,
|
||||
"step": 910
|
||||
},
|
||||
{
|
||||
"epoch": 1.7068645640074211,
|
||||
"grad_norm": 0.7638017132226432,
|
||||
"learning_rate": 6.484430433865785e-07,
|
||||
"loss": 0.1267,
|
||||
"step": 920
|
||||
},
|
||||
{
|
||||
"epoch": 1.725417439703154,
|
||||
"grad_norm": 0.5637674831928584,
|
||||
"learning_rate": 5.709844261868381e-07,
|
||||
"loss": 0.1251,
|
||||
"step": 930
|
||||
},
|
||||
{
|
||||
"epoch": 1.7439703153988868,
|
||||
"grad_norm": 0.8835722824389809,
|
||||
"learning_rate": 4.981712347167061e-07,
|
||||
"loss": 0.1263,
|
||||
"step": 940
|
||||
},
|
||||
{
|
||||
"epoch": 1.7625231910946195,
|
||||
"grad_norm": 1.0327912071957213,
|
||||
"learning_rate": 4.30079839959186e-07,
|
||||
"loss": 0.1267,
|
||||
"step": 950
|
||||
},
|
||||
{
|
||||
"epoch": 1.7810760667903525,
|
||||
"grad_norm": 0.760831900859538,
|
||||
"learning_rate": 3.667816603845681e-07,
|
||||
"loss": 0.1233,
|
||||
"step": 960
|
||||
},
|
||||
{
|
||||
"epoch": 1.7996289424860854,
|
||||
"grad_norm": 0.7886002974401526,
|
||||
"learning_rate": 3.0834308704231485e-07,
|
||||
"loss": 0.1196,
|
||||
"step": 970
|
||||
},
|
||||
{
|
||||
"epoch": 1.8181818181818183,
|
||||
"grad_norm": 0.7691394163831202,
|
||||
"learning_rate": 2.5482541392601924e-07,
|
||||
"loss": 0.1147,
|
||||
"step": 980
|
||||
},
|
||||
{
|
||||
"epoch": 1.836734693877551,
|
||||
"grad_norm": 1.3655213319729242,
|
||||
"learning_rate": 2.062847736844703e-07,
|
||||
"loss": 0.1311,
|
||||
"step": 990
|
||||
},
|
||||
{
|
||||
"epoch": 1.8552875695732838,
|
||||
"grad_norm": 0.9020502820778742,
|
||||
"learning_rate": 1.6277207874625444e-07,
|
||||
"loss": 0.1326,
|
||||
"step": 1000
|
||||
},
|
||||
{
|
||||
"epoch": 1.8738404452690167,
|
||||
"grad_norm": 1.1891039699760202,
|
||||
"learning_rate": 1.2433296791964754e-07,
|
||||
"loss": 0.1203,
|
||||
"step": 1010
|
||||
},
|
||||
{
|
||||
"epoch": 1.8923933209647497,
|
||||
"grad_norm": 0.6855058516961975,
|
||||
"learning_rate": 9.100775852381227e-08,
|
||||
"loss": 0.1162,
|
||||
"step": 1020
|
||||
},
|
||||
{
|
||||
"epoch": 1.9109461966604824,
|
||||
"grad_norm": 0.9669643922429069,
|
||||
"learning_rate": 6.283140410149213e-08,
|
||||
"loss": 0.1174,
|
||||
"step": 1030
|
||||
},
|
||||
{
|
||||
"epoch": 1.929499072356215,
|
||||
"grad_norm": 0.94328699549889,
|
||||
"learning_rate": 3.9833457757572636e-08,
|
||||
"loss": 0.1362,
|
||||
"step": 1040
|
||||
},
|
||||
{
|
||||
"epoch": 1.948051948051948,
|
||||
"grad_norm": 0.884695843246741,
|
||||
"learning_rate": 2.2038041161960288e-08,
|
||||
"loss": 0.1215,
|
||||
"step": 1050
|
||||
},
|
||||
{
|
||||
"epoch": 1.966604823747681,
|
||||
"grad_norm": 0.5985819936855686,
|
||||
"learning_rate": 9.463819249275751e-09,
|
||||
"loss": 0.1181,
|
||||
"step": 1060
|
||||
},
|
||||
{
|
||||
"epoch": 1.9851576994434137,
|
||||
"grad_norm": 0.6657018316360679,
|
||||
"learning_rate": 2.1239806419176556e-09,
|
||||
"loss": 0.1224,
|
||||
"step": 1070
|
||||
},
|
||||
{
|
||||
"epoch": 2.0,
|
||||
"step": 1078,
|
||||
"total_flos": 456031784665088.0,
|
||||
"train_loss": 0.26182658547373117,
|
||||
"train_runtime": 16760.0523,
|
||||
"train_samples_per_second": 0.386,
|
||||
"train_steps_per_second": 0.064
|
||||
}
|
||||
],
|
||||
"logging_steps": 10,
|
||||
"max_steps": 1078,
|
||||
"num_input_tokens_seen": 0,
|
||||
"num_train_epochs": 2,
|
||||
"save_steps": 10000,
|
||||
"stateful_callbacks": {
|
||||
"TrainerControl": {
|
||||
"args": {
|
||||
"should_epoch_stop": false,
|
||||
"should_evaluate": false,
|
||||
"should_log": false,
|
||||
"should_save": true,
|
||||
"should_training_stop": true
|
||||
},
|
||||
"attributes": {}
|
||||
}
|
||||
},
|
||||
"total_flos": 456031784665088.0,
|
||||
"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 sha256:455abe504c4ea38aa59c2ee5d51ebbd2b3ca7a301c1d0123d8db094c9860e642
|
||||
size 7928
|
||||
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