初始化项目，由ModelHub XC社区提供模型
Model: Chaos1024/qwen25_plan_sft_10k Source: Original Platform
This commit is contained in:
ModelHub XC
56
.gitattributes
vendored
Normal file
56
.gitattributes
vendored
Normal file
@@ -0,0 +1,56 @@
|
|||||||
|
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||||
|
|
||||||
|
|
||||||
|
*.bz2 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
|
||||||
|
*.model filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.msgpack 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
|
||||||
|
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
saved_model/**/* 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
|
||||||
|
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.db* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ark* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
|
||||||
|
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
|
||||||
|
|
||||||
|
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.gguf* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ggml filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.llamafile* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pt2 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
|
||||||
|
merges.txt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||||
|
training_args.bin filter=lfs diff=lfs merge=lfs -text
|
||||||
|
vocab.json filter=lfs diff=lfs merge=lfs -text
|
||||||
|
model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
0
.hfd/aria2c_urls.txt
Normal file
0
.hfd/aria2c_urls.txt
Normal file
1
.hfd/last_download_command
Normal file
1
.hfd/last_download_command
Normal file
@@ -0,0 +1 @@
|
|||||||
|
REPO_ID=Chaos0818/qwen2.5_7b_instruct_10k_3epoch_plan_sft_openthought114k TOOL=aria2c INCLUDE_PATTERNS= EXCLUDE_PATTERNS= DATASET=0 HF_USERNAME= HF_TOKEN= HF_TOKEN=https://hf-mirror.com REVISION=main
|
||||||
1
.hfd/repo_metadata.json
Normal file
1
.hfd/repo_metadata.json
Normal file
File diff suppressed because one or more lines are too long
61
README.md
Normal file
61
README.md
Normal file
@@ -0,0 +1,61 @@
|
|||||||
|
---
|
||||||
|
library_name: transformers
|
||||||
|
license: other
|
||||||
|
base_model: Qwen/Qwen2.5-7B-Instruct
|
||||||
|
tags:
|
||||||
|
- llama-factory
|
||||||
|
- full
|
||||||
|
- generated_from_trainer
|
||||||
|
model-index:
|
||||||
|
- name: qwen2.5_7b_math_sft_full_3_10k_plan_fom_train
|
||||||
|
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_7b_math_sft_full_3_10k_plan_fom_train
|
||||||
|
|
||||||
|
This model is a fine-tuned version of [/scratch/pioneer/jobs/job.2746985.pioneer/qwen-7b](https://huggingface.co//scratch/pioneer/jobs/job.2746985.pioneer/qwen-7b) on the OpenThoughts-114k-plan-train-random-10k 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: 2
|
||||||
|
- eval_batch_size: 8
|
||||||
|
- seed: 42
|
||||||
|
- distributed_type: multi-GPU
|
||||||
|
- num_devices: 8
|
||||||
|
- gradient_accumulation_steps: 2
|
||||||
|
- total_train_batch_size: 32
|
||||||
|
- total_eval_batch_size: 64
|
||||||
|
- 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: 3.0
|
||||||
|
|
||||||
|
### Training results
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
### Framework versions
|
||||||
|
|
||||||
|
- Transformers 4.52.4
|
||||||
|
- Pytorch 2.7.1+cu128
|
||||||
|
- Datasets 3.6.0
|
||||||
|
- Tokenizers 0.21.1
|
||||||
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": 3.0,
|
||||||
|
"total_flos": 1.2370288879507341e+19,
|
||||||
|
"train_loss": 0.13962188102543227,
|
||||||
|
"train_runtime": 7247.2658,
|
||||||
|
"train_samples_per_second": 4.139,
|
||||||
|
"train_steps_per_second": 0.13
|
||||||
|
}
|
||||||
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 %}
|
||||||
28
config.json
Normal file
28
config.json
Normal file
@@ -0,0 +1,28 @@
|
|||||||
|
{
|
||||||
|
"architectures": [
|
||||||
|
"Qwen2ForCausalLM"
|
||||||
|
],
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"bos_token_id": 151643,
|
||||||
|
"eos_token_id": 151645,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 3584,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 18944,
|
||||||
|
"max_position_embeddings": 32768,
|
||||||
|
"max_window_layers": 28,
|
||||||
|
"model_type": "qwen2",
|
||||||
|
"num_attention_heads": 28,
|
||||||
|
"num_hidden_layers": 28,
|
||||||
|
"num_key_value_heads": 4,
|
||||||
|
"rms_norm_eps": 1e-06,
|
||||||
|
"rope_scaling": null,
|
||||||
|
"rope_theta": 1000000.0,
|
||||||
|
"sliding_window": 131072,
|
||||||
|
"tie_word_embeddings": false,
|
||||||
|
"torch_dtype": "bfloat16",
|
||||||
|
"transformers_version": "4.52.4",
|
||||||
|
"use_cache": false,
|
||||||
|
"use_sliding_window": false,
|
||||||
|
"vocab_size": 152064
|
||||||
|
}
|
||||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
|||||||
|
{"framework":"Pytorch","task":"text-generation"}
|
||||||
14
generation_config.json
Normal file
14
generation_config.json
Normal file
@@ -0,0 +1,14 @@
|
|||||||
|
{
|
||||||
|
"bos_token_id": 151643,
|
||||||
|
"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": "4.52.4"
|
||||||
|
}
|
||||||
BIN
merges.txt
(Stored with Git LFS)
Normal file
BIN
merges.txt
(Stored with Git LFS)
Normal file
Binary file not shown.
3
model-00001-of-00004.safetensors
Normal file
3
model-00001-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:be9022d1e1219ca97ba5b5efd9d4b87d2d5be27f9cd0160b55a848e627859859
|
||||||
|
size 4877660776
|
||||||
3
model-00002-of-00004.safetensors
Normal file
3
model-00002-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:69a61fab6d864c33edd9ed160d7e232da5f3afb1d6fc8704d77df11e68f003b3
|
||||||
|
size 4932751008
|
||||||
3
model-00003-of-00004.safetensors
Normal file
3
model-00003-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:60b9dfbefdb1f60a8486e0b12c6dc17ad55ce34ac91cdc3054aa46b8dc805380
|
||||||
|
size 4330865200
|
||||||
3
model-00004-of-00004.safetensors
Normal file
3
model-00004-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:5f4c18a22d0e6540d514ddbbb99c2efcac44ebd7c6d57960af35fb65a744c1a8
|
||||||
|
size 1089994880
|
||||||
346
model.safetensors.index.json
Normal file
346
model.safetensors.index.json
Normal file
@@ -0,0 +1,346 @@
|
|||||||
|
{
|
||||||
|
"metadata": {
|
||||||
|
"total_size": 15231233024
|
||||||
|
},
|
||||||
|
"weight_map": {
|
||||||
|
"lm_head.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.norm.weight": "model-00003-of-00004.safetensors"
|
||||||
|
}
|
||||||
|
}
|
||||||
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:de1ca979b023be63203769ee24390542b1d6cc9e2c936d8db2d87690a7378859
|
||||||
|
size 20692
|
||||||
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:318f13c91293f1f4afb18507fedb93f96d0fe429309d43d57319362c9dda376a
|
||||||
|
size 13234
|
||||||
31
special_tokens_map.json
Normal file
31
special_tokens_map.json
Normal file
@@ -0,0 +1,31 @@
|
|||||||
|
{
|
||||||
|
"additional_special_tokens": [
|
||||||
|
"<|im_start|>",
|
||||||
|
"<|im_end|>",
|
||||||
|
"<|object_ref_start|>",
|
||||||
|
"<|object_ref_end|>",
|
||||||
|
"<|box_start|>",
|
||||||
|
"<|box_end|>",
|
||||||
|
"<|quad_start|>",
|
||||||
|
"<|quad_end|>",
|
||||||
|
"<|vision_start|>",
|
||||||
|
"<|vision_end|>",
|
||||||
|
"<|vision_pad|>",
|
||||||
|
"<|image_pad|>",
|
||||||
|
"<|video_pad|>"
|
||||||
|
],
|
||||||
|
"eos_token": {
|
||||||
|
"content": "<|im_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"pad_token": {
|
||||||
|
"content": "<|endoftext|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
}
|
||||||
|
}
|
||||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
||||||
|
size 11421896
|
||||||
208
tokenizer_config.json
Normal file
208
tokenizer_config.json
Normal file
@@ -0,0 +1,208 @@
|
|||||||
|
{
|
||||||
|
"add_bos_token": false,
|
||||||
|
"add_prefix_space": false,
|
||||||
|
"added_tokens_decoder": {
|
||||||
|
"151643": {
|
||||||
|
"content": "<|endoftext|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151644": {
|
||||||
|
"content": "<|im_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151645": {
|
||||||
|
"content": "<|im_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151646": {
|
||||||
|
"content": "<|object_ref_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151647": {
|
||||||
|
"content": "<|object_ref_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151648": {
|
||||||
|
"content": "<|box_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151649": {
|
||||||
|
"content": "<|box_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151650": {
|
||||||
|
"content": "<|quad_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151651": {
|
||||||
|
"content": "<|quad_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151652": {
|
||||||
|
"content": "<|vision_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151653": {
|
||||||
|
"content": "<|vision_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151654": {
|
||||||
|
"content": "<|vision_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151655": {
|
||||||
|
"content": "<|image_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151656": {
|
||||||
|
"content": "<|video_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151657": {
|
||||||
|
"content": "<tool_call>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151658": {
|
||||||
|
"content": "</tool_call>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151659": {
|
||||||
|
"content": "<|fim_prefix|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151660": {
|
||||||
|
"content": "<|fim_middle|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151661": {
|
||||||
|
"content": "<|fim_suffix|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151662": {
|
||||||
|
"content": "<|fim_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151663": {
|
||||||
|
"content": "<|repo_name|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151664": {
|
||||||
|
"content": "<|file_sep|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"additional_special_tokens": [
|
||||||
|
"<|im_start|>",
|
||||||
|
"<|im_end|>",
|
||||||
|
"<|object_ref_start|>",
|
||||||
|
"<|object_ref_end|>",
|
||||||
|
"<|box_start|>",
|
||||||
|
"<|box_end|>",
|
||||||
|
"<|quad_start|>",
|
||||||
|
"<|quad_end|>",
|
||||||
|
"<|vision_start|>",
|
||||||
|
"<|vision_end|>",
|
||||||
|
"<|vision_pad|>",
|
||||||
|
"<|image_pad|>",
|
||||||
|
"<|video_pad|>"
|
||||||
|
],
|
||||||
|
"bos_token": null,
|
||||||
|
"clean_up_tokenization_spaces": false,
|
||||||
|
"eos_token": "<|im_end|>",
|
||||||
|
"errors": "replace",
|
||||||
|
"extra_special_tokens": {},
|
||||||
|
"model_max_length": 131072,
|
||||||
|
"pad_token": "<|endoftext|>",
|
||||||
|
"padding_side": "right",
|
||||||
|
"split_special_tokens": false,
|
||||||
|
"tokenizer_class": "Qwen2Tokenizer",
|
||||||
|
"unk_token": null
|
||||||
|
}
|
||||||
8
train_results.json
Normal file
8
train_results.json
Normal file
@@ -0,0 +1,8 @@
|
|||||||
|
{
|
||||||
|
"epoch": 3.0,
|
||||||
|
"total_flos": 1.2370288879507341e+19,
|
||||||
|
"train_loss": 0.13962188102543227,
|
||||||
|
"train_runtime": 7247.2658,
|
||||||
|
"train_samples_per_second": 4.139,
|
||||||
|
"train_steps_per_second": 0.13
|
||||||
|
}
|
||||||
34
trainer_log.jsonl
Normal file
34
trainer_log.jsonl
Normal file
@@ -0,0 +1,34 @@
|
|||||||
|
{"current_steps": 610, "total_steps": 939, "loss": 0.3824, "lr": 3.314183409550293e-06, "epoch": 1.9504000000000001, "percentage": 64.96, "elapsed_time": "0:03:38", "remaining_time": "0:01:58"}
|
||||||
|
{"current_steps": 620, "total_steps": 939, "loss": 0.3858, "lr": 3.140380392754901e-06, "epoch": 1.9824000000000002, "percentage": 66.03, "elapsed_time": "0:07:00", "remaining_time": "0:03:36"}
|
||||||
|
{"current_steps": 630, "total_steps": 939, "loss": 0.4165, "lr": 2.969147537486175e-06, "epoch": 2.016, "percentage": 67.09, "elapsed_time": "0:10:42", "remaining_time": "0:05:15"}
|
||||||
|
{"current_steps": 640, "total_steps": 939, "loss": 0.3785, "lr": 2.800721502948506e-06, "epoch": 2.048, "percentage": 68.16, "elapsed_time": "0:14:10", "remaining_time": "0:06:37"}
|
||||||
|
{"current_steps": 650, "total_steps": 939, "loss": 0.3911, "lr": 2.635335069067617e-06, "epoch": 2.08, "percentage": 69.22, "elapsed_time": "0:17:42", "remaining_time": "0:07:52"}
|
||||||
|
{"current_steps": 660, "total_steps": 939, "loss": 0.3997, "lr": 2.4732168147677927e-06, "epoch": 2.112, "percentage": 70.29, "elapsed_time": "0:21:13", "remaining_time": "0:08:58"}
|
||||||
|
{"current_steps": 670, "total_steps": 939, "loss": 0.3896, "lr": 2.314590802055232e-06, "epoch": 2.144, "percentage": 71.35, "elapsed_time": "0:24:38", "remaining_time": "0:09:53"}
|
||||||
|
{"current_steps": 680, "total_steps": 939, "loss": 0.3966, "lr": 2.159676266344222e-06, "epoch": 2.176, "percentage": 72.42, "elapsed_time": "0:28:10", "remaining_time": "0:10:44"}
|
||||||
|
{"current_steps": 690, "total_steps": 939, "loss": 0.3791, "lr": 2.0086873134540626e-06, "epoch": 2.208, "percentage": 73.48, "elapsed_time": "0:31:42", "remaining_time": "0:11:26"}
|
||||||
|
{"current_steps": 700, "total_steps": 939, "loss": 0.3924, "lr": 1.8618326236955908e-06, "epoch": 2.24, "percentage": 74.55, "elapsed_time": "0:35:08", "remaining_time": "0:12:00"}
|
||||||
|
{"current_steps": 710, "total_steps": 939, "loss": 0.3884, "lr": 1.7193151634562071e-06, "epoch": 2.2720000000000002, "percentage": 75.61, "elapsed_time": "0:38:39", "remaining_time": "0:12:28"}
|
||||||
|
{"current_steps": 720, "total_steps": 939, "loss": 0.3825, "lr": 1.581331904682089e-06, "epoch": 2.304, "percentage": 76.68, "elapsed_time": "0:42:09", "remaining_time": "0:12:49"}
|
||||||
|
{"current_steps": 730, "total_steps": 939, "loss": 0.391, "lr": 1.4480735526452427e-06, "epoch": 2.336, "percentage": 77.74, "elapsed_time": "0:45:46", "remaining_time": "0:13:06"}
|
||||||
|
{"current_steps": 740, "total_steps": 939, "loss": 0.3858, "lr": 1.319724282371664e-06, "epoch": 2.368, "percentage": 78.81, "elapsed_time": "0:49:16", "remaining_time": "0:13:14"}
|
||||||
|
{"current_steps": 750, "total_steps": 939, "loss": 0.3903, "lr": 1.1964614840949002e-06, "epoch": 2.4, "percentage": 79.87, "elapsed_time": "0:52:41", "remaining_time": "0:13:16"}
|
||||||
|
{"current_steps": 760, "total_steps": 939, "loss": 0.3849, "lr": 1.078455518086784e-06, "epoch": 2.432, "percentage": 80.94, "elapsed_time": "0:56:18", "remaining_time": "0:13:15"}
|
||||||
|
{"current_steps": 770, "total_steps": 939, "loss": 0.3902, "lr": 9.658694792042284e-07, "epoch": 2.464, "percentage": 82.0, "elapsed_time": "0:59:48", "remaining_time": "0:13:07"}
|
||||||
|
{"current_steps": 780, "total_steps": 939, "loss": 0.3774, "lr": 8.58858971477457e-07, "epoch": 2.496, "percentage": 83.07, "elapsed_time": "1:03:07", "remaining_time": "0:12:52"}
|
||||||
|
{"current_steps": 790, "total_steps": 939, "loss": 0.3899, "lr": 7.575718930512516e-07, "epoch": 2.528, "percentage": 84.13, "elapsed_time": "1:06:32", "remaining_time": "0:12:33"}
|
||||||
|
{"current_steps": 800, "total_steps": 939, "loss": 0.3954, "lr": 6.621482317764105e-07, "epoch": 2.56, "percentage": 85.2, "elapsed_time": "1:09:56", "remaining_time": "0:12:09"}
|
||||||
|
{"current_steps": 810, "total_steps": 939, "loss": 0.3809, "lr": 5.727198717339511e-07, "epoch": 2.592, "percentage": 86.26, "elapsed_time": "1:16:15", "remaining_time": "0:12:08"}
|
||||||
|
{"current_steps": 820, "total_steps": 939, "loss": 0.3881, "lr": 4.894104109594466e-07, "epoch": 2.624, "percentage": 87.33, "elapsed_time": "1:19:44", "remaining_time": "0:11:34"}
|
||||||
|
{"current_steps": 830, "total_steps": 939, "loss": 0.3869, "lr": 4.123349906194357e-07, "epoch": 2.656, "percentage": 88.39, "elapsed_time": "1:23:04", "remaining_time": "0:10:54"}
|
||||||
|
{"current_steps": 840, "total_steps": 939, "loss": 0.3859, "lr": 3.416001358759635e-07, "epoch": 2.6879999999999997, "percentage": 89.46, "elapsed_time": "1:26:36", "remaining_time": "0:10:12"}
|
||||||
|
{"current_steps": 850, "total_steps": 939, "loss": 0.3855, "lr": 2.7730360865923954e-07, "epoch": 2.7199999999999998, "percentage": 90.52, "elapsed_time": "1:29:59", "remaining_time": "0:09:25"}
|
||||||
|
{"current_steps": 860, "total_steps": 939, "loss": 0.384, "lr": 2.1953427255185122e-07, "epoch": 2.752, "percentage": 91.59, "elapsed_time": "1:33:29", "remaining_time": "0:08:35"}
|
||||||
|
{"current_steps": 870, "total_steps": 939, "loss": 0.3866, "lr": 1.6837196997130434e-07, "epoch": 2.784, "percentage": 92.65, "elapsed_time": "1:36:59", "remaining_time": "0:07:41"}
|
||||||
|
{"current_steps": 880, "total_steps": 939, "loss": 0.3924, "lr": 1.2388741182062348e-07, "epoch": 2.816, "percentage": 93.72, "elapsed_time": "1:40:23", "remaining_time": "0:06:43"}
|
||||||
|
{"current_steps": 890, "total_steps": 939, "loss": 0.391, "lr": 8.614207975952083e-08, "epoch": 2.848, "percentage": 94.78, "elapsed_time": "1:43:55", "remaining_time": "0:05:43"}
|
||||||
|
{"current_steps": 900, "total_steps": 939, "loss": 0.3651, "lr": 5.518814123121885e-08, "epoch": 2.88, "percentage": 95.85, "elapsed_time": "1:47:24", "remaining_time": "0:04:39"}
|
||||||
|
{"current_steps": 910, "total_steps": 939, "loss": 0.3891, "lr": 3.10683773623488e-08, "epoch": 2.912, "percentage": 96.91, "elapsed_time": "1:51:03", "remaining_time": "0:03:32"}
|
||||||
|
{"current_steps": 920, "total_steps": 939, "loss": 0.3982, "lr": 1.3816123835588835e-08, "epoch": 2.944, "percentage": 97.98, "elapsed_time": "1:54:39", "remaining_time": "0:02:22"}
|
||||||
|
{"current_steps": 930, "total_steps": 939, "loss": 0.3864, "lr": 3.4552248167507576e-09, "epoch": 2.976, "percentage": 99.04, "elapsed_time": "1:58:12", "remaining_time": "0:01:08"}
|
||||||
|
{"current_steps": 938, "total_steps": 939, "epoch": 3.0, "percentage": 99.89, "elapsed_time": "2:00:47", "remaining_time": "0:00:07"}
|
||||||
694
trainer_state.json
Normal file
694
trainer_state.json
Normal file
@@ -0,0 +1,694 @@
|
|||||||
|
{
|
||||||
|
"best_global_step": null,
|
||||||
|
"best_metric": null,
|
||||||
|
"best_model_checkpoint": null,
|
||||||
|
"epoch": 3.0,
|
||||||
|
"eval_steps": 500,
|
||||||
|
"global_step": 938,
|
||||||
|
"is_hyper_param_search": false,
|
||||||
|
"is_local_process_zero": true,
|
||||||
|
"is_world_process_zero": true,
|
||||||
|
"log_history": [
|
||||||
|
{
|
||||||
|
"epoch": 0.032,
|
||||||
|
"grad_norm": 5.314220428466797,
|
||||||
|
"learning_rate": 9.574468085106384e-07,
|
||||||
|
"loss": 0.8663,
|
||||||
|
"step": 10
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.064,
|
||||||
|
"grad_norm": 2.9840216636657715,
|
||||||
|
"learning_rate": 2.021276595744681e-06,
|
||||||
|
"loss": 0.7951,
|
||||||
|
"step": 20
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.096,
|
||||||
|
"grad_norm": 1.4162436723709106,
|
||||||
|
"learning_rate": 3.0851063829787237e-06,
|
||||||
|
"loss": 0.7093,
|
||||||
|
"step": 30
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.128,
|
||||||
|
"grad_norm": 1.0216368436813354,
|
||||||
|
"learning_rate": 4.148936170212766e-06,
|
||||||
|
"loss": 0.6386,
|
||||||
|
"step": 40
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.16,
|
||||||
|
"grad_norm": 0.7919172644615173,
|
||||||
|
"learning_rate": 5.212765957446809e-06,
|
||||||
|
"loss": 0.6059,
|
||||||
|
"step": 50
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.192,
|
||||||
|
"grad_norm": 0.7189238667488098,
|
||||||
|
"learning_rate": 6.276595744680851e-06,
|
||||||
|
"loss": 0.5966,
|
||||||
|
"step": 60
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.224,
|
||||||
|
"grad_norm": 0.8121111392974854,
|
||||||
|
"learning_rate": 7.340425531914894e-06,
|
||||||
|
"loss": 0.572,
|
||||||
|
"step": 70
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.256,
|
||||||
|
"grad_norm": 0.7291969656944275,
|
||||||
|
"learning_rate": 8.404255319148937e-06,
|
||||||
|
"loss": 0.5621,
|
||||||
|
"step": 80
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.288,
|
||||||
|
"grad_norm": 0.8778895139694214,
|
||||||
|
"learning_rate": 9.46808510638298e-06,
|
||||||
|
"loss": 0.5576,
|
||||||
|
"step": 90
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.32,
|
||||||
|
"grad_norm": 0.725179135799408,
|
||||||
|
"learning_rate": 9.999136119166803e-06,
|
||||||
|
"loss": 0.5505,
|
||||||
|
"step": 100
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.352,
|
||||||
|
"grad_norm": 0.7167001962661743,
|
||||||
|
"learning_rate": 9.9922268634943e-06,
|
||||||
|
"loss": 0.5527,
|
||||||
|
"step": 110
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.384,
|
||||||
|
"grad_norm": 0.6954172849655151,
|
||||||
|
"learning_rate": 9.978417901361958e-06,
|
||||||
|
"loss": 0.5533,
|
||||||
|
"step": 120
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.416,
|
||||||
|
"grad_norm": 0.6993622183799744,
|
||||||
|
"learning_rate": 9.95772831799724e-06,
|
||||||
|
"loss": 0.5537,
|
||||||
|
"step": 130
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.448,
|
||||||
|
"grad_norm": 0.739738404750824,
|
||||||
|
"learning_rate": 9.930186708264902e-06,
|
||||||
|
"loss": 0.5432,
|
||||||
|
"step": 140
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.48,
|
||||||
|
"grad_norm": 0.7163270115852356,
|
||||||
|
"learning_rate": 9.895831137146319e-06,
|
||||||
|
"loss": 0.5293,
|
||||||
|
"step": 150
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.512,
|
||||||
|
"grad_norm": 0.7983338236808777,
|
||||||
|
"learning_rate": 9.854709087130261e-06,
|
||||||
|
"loss": 0.5444,
|
||||||
|
"step": 160
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.544,
|
||||||
|
"grad_norm": 0.8286071419715881,
|
||||||
|
"learning_rate": 9.80687739258782e-06,
|
||||||
|
"loss": 0.5227,
|
||||||
|
"step": 170
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.576,
|
||||||
|
"grad_norm": 0.6619768142700195,
|
||||||
|
"learning_rate": 9.7524021612222e-06,
|
||||||
|
"loss": 0.5313,
|
||||||
|
"step": 180
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.608,
|
||||||
|
"grad_norm": 0.6172661185264587,
|
||||||
|
"learning_rate": 9.691358682701927e-06,
|
||||||
|
"loss": 0.5313,
|
||||||
|
"step": 190
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.64,
|
||||||
|
"grad_norm": 0.6922529339790344,
|
||||||
|
"learning_rate": 9.623831324603755e-06,
|
||||||
|
"loss": 0.5263,
|
||||||
|
"step": 200
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.672,
|
||||||
|
"grad_norm": 0.7383220195770264,
|
||||||
|
"learning_rate": 9.549913415809084e-06,
|
||||||
|
"loss": 0.536,
|
||||||
|
"step": 210
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.704,
|
||||||
|
"grad_norm": 0.9165273308753967,
|
||||||
|
"learning_rate": 9.469707117515068e-06,
|
||||||
|
"loss": 0.532,
|
||||||
|
"step": 220
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.736,
|
||||||
|
"grad_norm": 0.637290894985199,
|
||||||
|
"learning_rate": 9.383323282038632e-06,
|
||||||
|
"loss": 0.5247,
|
||||||
|
"step": 230
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.768,
|
||||||
|
"grad_norm": 0.7203924655914307,
|
||||||
|
"learning_rate": 9.29088129960862e-06,
|
||||||
|
"loss": 0.5367,
|
||||||
|
"step": 240
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8,
|
||||||
|
"grad_norm": 0.7599261403083801,
|
||||||
|
"learning_rate": 9.192508933357753e-06,
|
||||||
|
"loss": 0.535,
|
||||||
|
"step": 250
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.832,
|
||||||
|
"grad_norm": 0.7834025025367737,
|
||||||
|
"learning_rate": 9.088342142742493e-06,
|
||||||
|
"loss": 0.528,
|
||||||
|
"step": 260
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.864,
|
||||||
|
"grad_norm": 0.6317589282989502,
|
||||||
|
"learning_rate": 8.978524895634842e-06,
|
||||||
|
"loss": 0.5359,
|
||||||
|
"step": 270
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.896,
|
||||||
|
"grad_norm": 0.6225187182426453,
|
||||||
|
"learning_rate": 8.86320896934581e-06,
|
||||||
|
"loss": 0.5039,
|
||||||
|
"step": 280
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.928,
|
||||||
|
"grad_norm": 0.6623832583427429,
|
||||||
|
"learning_rate": 8.742553740855507e-06,
|
||||||
|
"loss": 0.5277,
|
||||||
|
"step": 290
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.96,
|
||||||
|
"grad_norm": 0.7472139596939087,
|
||||||
|
"learning_rate": 8.616725966539831e-06,
|
||||||
|
"loss": 0.5213,
|
||||||
|
"step": 300
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.992,
|
||||||
|
"grad_norm": 0.6038188934326172,
|
||||||
|
"learning_rate": 8.485899551698166e-06,
|
||||||
|
"loss": 0.5248,
|
||||||
|
"step": 310
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.0224,
|
||||||
|
"grad_norm": 0.6474160552024841,
|
||||||
|
"learning_rate": 8.350255310200611e-06,
|
||||||
|
"loss": 0.4818,
|
||||||
|
"step": 320
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.0544,
|
||||||
|
"grad_norm": 0.6729207634925842,
|
||||||
|
"learning_rate": 8.209980714586955e-06,
|
||||||
|
"loss": 0.4563,
|
||||||
|
"step": 330
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.0864,
|
||||||
|
"grad_norm": 0.6256211400032043,
|
||||||
|
"learning_rate": 8.065269636962765e-06,
|
||||||
|
"loss": 0.4494,
|
||||||
|
"step": 340
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.1184,
|
||||||
|
"grad_norm": 0.6500005722045898,
|
||||||
|
"learning_rate": 7.916322081050708e-06,
|
||||||
|
"loss": 0.4492,
|
||||||
|
"step": 350
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.1504,
|
||||||
|
"grad_norm": 0.5361557006835938,
|
||||||
|
"learning_rate": 7.76334390576742e-06,
|
||||||
|
"loss": 0.4539,
|
||||||
|
"step": 360
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.1824,
|
||||||
|
"grad_norm": 0.6814967393875122,
|
||||||
|
"learning_rate": 7.60654654070796e-06,
|
||||||
|
"loss": 0.4433,
|
||||||
|
"step": 370
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.2144,
|
||||||
|
"grad_norm": 0.6009787917137146,
|
||||||
|
"learning_rate": 7.446146693931111e-06,
|
||||||
|
"loss": 0.4536,
|
||||||
|
"step": 380
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.2464,
|
||||||
|
"grad_norm": 0.6081900000572205,
|
||||||
|
"learning_rate": 7.282366052449351e-06,
|
||||||
|
"loss": 0.4623,
|
||||||
|
"step": 390
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.2784,
|
||||||
|
"grad_norm": 0.6118571758270264,
|
||||||
|
"learning_rate": 7.115430975837457e-06,
|
||||||
|
"loss": 0.4437,
|
||||||
|
"step": 400
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.3104,
|
||||||
|
"grad_norm": 0.5691370368003845,
|
||||||
|
"learning_rate": 6.945572183383229e-06,
|
||||||
|
"loss": 0.4448,
|
||||||
|
"step": 410
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.3424,
|
||||||
|
"grad_norm": 0.5975236296653748,
|
||||||
|
"learning_rate": 6.773024435212678e-06,
|
||||||
|
"loss": 0.4491,
|
||||||
|
"step": 420
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.3744,
|
||||||
|
"grad_norm": 0.5852976441383362,
|
||||||
|
"learning_rate": 6.598026207830428e-06,
|
||||||
|
"loss": 0.4482,
|
||||||
|
"step": 430
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.4064,
|
||||||
|
"grad_norm": 0.4990760087966919,
|
||||||
|
"learning_rate": 6.4208193645237314e-06,
|
||||||
|
"loss": 0.4564,
|
||||||
|
"step": 440
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.4384000000000001,
|
||||||
|
"grad_norm": 0.6382614374160767,
|
||||||
|
"learning_rate": 6.241648821085666e-06,
|
||||||
|
"loss": 0.454,
|
||||||
|
"step": 450
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.4704,
|
||||||
|
"grad_norm": 0.5935061573982239,
|
||||||
|
"learning_rate": 6.060762207319479e-06,
|
||||||
|
"loss": 0.4504,
|
||||||
|
"step": 460
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.5024,
|
||||||
|
"grad_norm": 0.48114678263664246,
|
||||||
|
"learning_rate": 5.878409524791931e-06,
|
||||||
|
"loss": 0.4444,
|
||||||
|
"step": 470
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.5344,
|
||||||
|
"grad_norm": 0.5724011063575745,
|
||||||
|
"learning_rate": 5.694842801308651e-06,
|
||||||
|
"loss": 0.444,
|
||||||
|
"step": 480
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.5664,
|
||||||
|
"grad_norm": 0.5499016642570496,
|
||||||
|
"learning_rate": 5.510315742589042e-06,
|
||||||
|
"loss": 0.4311,
|
||||||
|
"step": 490
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.5984,
|
||||||
|
"grad_norm": 0.7091147303581238,
|
||||||
|
"learning_rate": 5.325083381622165e-06,
|
||||||
|
"loss": 0.4596,
|
||||||
|
"step": 500
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.6303999999999998,
|
||||||
|
"grad_norm": 0.5529297590255737,
|
||||||
|
"learning_rate": 5.139401726188208e-06,
|
||||||
|
"loss": 0.4459,
|
||||||
|
"step": 510
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.6623999999999999,
|
||||||
|
"grad_norm": 0.6218659281730652,
|
||||||
|
"learning_rate": 4.953527405032723e-06,
|
||||||
|
"loss": 0.4525,
|
||||||
|
"step": 520
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.6944,
|
||||||
|
"grad_norm": 0.599751353263855,
|
||||||
|
"learning_rate": 4.767717313182611e-06,
|
||||||
|
"loss": 0.4604,
|
||||||
|
"step": 530
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.7264,
|
||||||
|
"grad_norm": 0.5663022994995117,
|
||||||
|
"learning_rate": 4.582228256894093e-06,
|
||||||
|
"loss": 0.4418,
|
||||||
|
"step": 540
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.7584,
|
||||||
|
"grad_norm": 0.48218056559562683,
|
||||||
|
"learning_rate": 4.397316598723385e-06,
|
||||||
|
"loss": 0.4548,
|
||||||
|
"step": 550
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.7904,
|
||||||
|
"grad_norm": 0.6282760500907898,
|
||||||
|
"learning_rate": 4.2132379032105695e-06,
|
||||||
|
"loss": 0.4385,
|
||||||
|
"step": 560
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.8224,
|
||||||
|
"grad_norm": 0.5830026268959045,
|
||||||
|
"learning_rate": 4.030246583666437e-06,
|
||||||
|
"loss": 0.4507,
|
||||||
|
"step": 570
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.8544,
|
||||||
|
"grad_norm": 0.5871529579162598,
|
||||||
|
"learning_rate": 3.848595550550401e-06,
|
||||||
|
"loss": 0.4547,
|
||||||
|
"step": 580
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.8864,
|
||||||
|
"grad_norm": 0.483813613653183,
|
||||||
|
"learning_rate": 3.668535861925509e-06,
|
||||||
|
"loss": 0.4402,
|
||||||
|
"step": 590
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.9184,
|
||||||
|
"grad_norm": 0.5708866715431213,
|
||||||
|
"learning_rate": 3.4903163764736104e-06,
|
||||||
|
"loss": 0.4446,
|
||||||
|
"step": 600
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.9504000000000001,
|
||||||
|
"grad_norm": 0.6678810119628906,
|
||||||
|
"learning_rate": 3.314183409550293e-06,
|
||||||
|
"loss": 0.3824,
|
||||||
|
"step": 610
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.9824000000000002,
|
||||||
|
"grad_norm": 0.5966857075691223,
|
||||||
|
"learning_rate": 3.140380392754901e-06,
|
||||||
|
"loss": 0.3858,
|
||||||
|
"step": 620
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.016,
|
||||||
|
"grad_norm": 0.6602267622947693,
|
||||||
|
"learning_rate": 2.969147537486175e-06,
|
||||||
|
"loss": 0.4165,
|
||||||
|
"step": 630
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.048,
|
||||||
|
"grad_norm": 0.5915480256080627,
|
||||||
|
"learning_rate": 2.800721502948506e-06,
|
||||||
|
"loss": 0.3785,
|
||||||
|
"step": 640
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.08,
|
||||||
|
"grad_norm": 0.5668565034866333,
|
||||||
|
"learning_rate": 2.635335069067617e-06,
|
||||||
|
"loss": 0.3911,
|
||||||
|
"step": 650
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.112,
|
||||||
|
"grad_norm": 0.5256936550140381,
|
||||||
|
"learning_rate": 2.4732168147677927e-06,
|
||||||
|
"loss": 0.3997,
|
||||||
|
"step": 660
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.144,
|
||||||
|
"grad_norm": 0.5043026804924011,
|
||||||
|
"learning_rate": 2.314590802055232e-06,
|
||||||
|
"loss": 0.3896,
|
||||||
|
"step": 670
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.176,
|
||||||
|
"grad_norm": 0.5051006078720093,
|
||||||
|
"learning_rate": 2.159676266344222e-06,
|
||||||
|
"loss": 0.3966,
|
||||||
|
"step": 680
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.208,
|
||||||
|
"grad_norm": 0.5608514547348022,
|
||||||
|
"learning_rate": 2.0086873134540626e-06,
|
||||||
|
"loss": 0.3791,
|
||||||
|
"step": 690
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.24,
|
||||||
|
"grad_norm": 0.620739758014679,
|
||||||
|
"learning_rate": 1.8618326236955908e-06,
|
||||||
|
"loss": 0.3924,
|
||||||
|
"step": 700
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.2720000000000002,
|
||||||
|
"grad_norm": 0.5500799417495728,
|
||||||
|
"learning_rate": 1.7193151634562071e-06,
|
||||||
|
"loss": 0.3884,
|
||||||
|
"step": 710
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.304,
|
||||||
|
"grad_norm": 0.5139204859733582,
|
||||||
|
"learning_rate": 1.581331904682089e-06,
|
||||||
|
"loss": 0.3825,
|
||||||
|
"step": 720
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.336,
|
||||||
|
"grad_norm": 0.5042279958724976,
|
||||||
|
"learning_rate": 1.4480735526452427e-06,
|
||||||
|
"loss": 0.391,
|
||||||
|
"step": 730
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.368,
|
||||||
|
"grad_norm": 0.5282170176506042,
|
||||||
|
"learning_rate": 1.319724282371664e-06,
|
||||||
|
"loss": 0.3858,
|
||||||
|
"step": 740
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.4,
|
||||||
|
"grad_norm": 0.5384218692779541,
|
||||||
|
"learning_rate": 1.1964614840949002e-06,
|
||||||
|
"loss": 0.3903,
|
||||||
|
"step": 750
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.432,
|
||||||
|
"grad_norm": 0.4508267045021057,
|
||||||
|
"learning_rate": 1.078455518086784e-06,
|
||||||
|
"loss": 0.3849,
|
||||||
|
"step": 760
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.464,
|
||||||
|
"grad_norm": 0.49801719188690186,
|
||||||
|
"learning_rate": 9.658694792042284e-07,
|
||||||
|
"loss": 0.3902,
|
||||||
|
"step": 770
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.496,
|
||||||
|
"grad_norm": 0.47622281312942505,
|
||||||
|
"learning_rate": 8.58858971477457e-07,
|
||||||
|
"loss": 0.3774,
|
||||||
|
"step": 780
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.528,
|
||||||
|
"grad_norm": 0.4954831302165985,
|
||||||
|
"learning_rate": 7.575718930512516e-07,
|
||||||
|
"loss": 0.3899,
|
||||||
|
"step": 790
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.56,
|
||||||
|
"grad_norm": 0.5186880230903625,
|
||||||
|
"learning_rate": 6.621482317764105e-07,
|
||||||
|
"loss": 0.3954,
|
||||||
|
"step": 800
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.592,
|
||||||
|
"grad_norm": 0.4855698049068451,
|
||||||
|
"learning_rate": 5.727198717339511e-07,
|
||||||
|
"loss": 0.3809,
|
||||||
|
"step": 810
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.624,
|
||||||
|
"grad_norm": 0.5997398495674133,
|
||||||
|
"learning_rate": 4.894104109594466e-07,
|
||||||
|
"loss": 0.3881,
|
||||||
|
"step": 820
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.656,
|
||||||
|
"grad_norm": 0.5895832180976868,
|
||||||
|
"learning_rate": 4.123349906194357e-07,
|
||||||
|
"loss": 0.3869,
|
||||||
|
"step": 830
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.6879999999999997,
|
||||||
|
"grad_norm": 0.5051674842834473,
|
||||||
|
"learning_rate": 3.416001358759635e-07,
|
||||||
|
"loss": 0.3859,
|
||||||
|
"step": 840
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.7199999999999998,
|
||||||
|
"grad_norm": 0.5103119611740112,
|
||||||
|
"learning_rate": 2.7730360865923954e-07,
|
||||||
|
"loss": 0.3855,
|
||||||
|
"step": 850
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.752,
|
||||||
|
"grad_norm": 0.5123039484024048,
|
||||||
|
"learning_rate": 2.1953427255185122e-07,
|
||||||
|
"loss": 0.384,
|
||||||
|
"step": 860
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.784,
|
||||||
|
"grad_norm": 0.5374960899353027,
|
||||||
|
"learning_rate": 1.6837196997130434e-07,
|
||||||
|
"loss": 0.3866,
|
||||||
|
"step": 870
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.816,
|
||||||
|
"grad_norm": 0.5188184976577759,
|
||||||
|
"learning_rate": 1.2388741182062348e-07,
|
||||||
|
"loss": 0.3924,
|
||||||
|
"step": 880
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.848,
|
||||||
|
"grad_norm": 0.5518755316734314,
|
||||||
|
"learning_rate": 8.614207975952083e-08,
|
||||||
|
"loss": 0.391,
|
||||||
|
"step": 890
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.88,
|
||||||
|
"grad_norm": 0.5774142742156982,
|
||||||
|
"learning_rate": 5.518814123121885e-08,
|
||||||
|
"loss": 0.3651,
|
||||||
|
"step": 900
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.912,
|
||||||
|
"grad_norm": 0.4625570476055145,
|
||||||
|
"learning_rate": 3.10683773623488e-08,
|
||||||
|
"loss": 0.3891,
|
||||||
|
"step": 910
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.944,
|
||||||
|
"grad_norm": 0.5453880429267883,
|
||||||
|
"learning_rate": 1.3816123835588835e-08,
|
||||||
|
"loss": 0.3982,
|
||||||
|
"step": 920
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.976,
|
||||||
|
"grad_norm": 0.48320916295051575,
|
||||||
|
"learning_rate": 3.4552248167507576e-09,
|
||||||
|
"loss": 0.3864,
|
||||||
|
"step": 930
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 3.0,
|
||||||
|
"step": 938,
|
||||||
|
"total_flos": 1.2370288879507341e+19,
|
||||||
|
"train_loss": 0.13962188102543227,
|
||||||
|
"train_runtime": 7247.2658,
|
||||||
|
"train_samples_per_second": 4.139,
|
||||||
|
"train_steps_per_second": 0.13
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"logging_steps": 10,
|
||||||
|
"max_steps": 939,
|
||||||
|
"num_input_tokens_seen": 0,
|
||||||
|
"num_train_epochs": 3,
|
||||||
|
"save_steps": 200,
|
||||||
|
"stateful_callbacks": {
|
||||||
|
"TrainerControl": {
|
||||||
|
"args": {
|
||||||
|
"should_epoch_stop": false,
|
||||||
|
"should_evaluate": false,
|
||||||
|
"should_log": false,
|
||||||
|
"should_save": true,
|
||||||
|
"should_training_stop": false
|
||||||
|
},
|
||||||
|
"attributes": {}
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"total_flos": 1.2370288879507341e+19,
|
||||||
|
"train_batch_size": 2,
|
||||||
|
"trial_name": null,
|
||||||
|
"trial_params": null
|
||||||
|
}
|
||||||
988
training.log
Normal file
988
training.log
Normal file
File diff suppressed because one or more lines are too long
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:af1850436a3a6a604626c60721ed47ec9ea948cbd29a3d10cbded38e50fd8afe
|
||||||
|
size 8145
|
||||||
BIN
training_loss.png
Normal file
BIN
training_loss.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 40 KiB |
BIN
vocab.json
(Stored with Git LFS)
Normal file
BIN
vocab.json
(Stored with Git LFS)
Normal file
Binary file not shown.
Reference in New Issue
Block a user