初始化项目，由ModelHub XC社区提供模型
Model: rashadaziz/Qwen2.5-7B-MLC 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
|
||||
64
README.md
Normal file
64
README.md
Normal file
@@ -0,0 +1,64 @@
|
||||
---
|
||||
library_name: transformers
|
||||
license: apache-2.0
|
||||
base_model: Qwen/Qwen2.5-7B-Instruct
|
||||
tags:
|
||||
- llama-factory
|
||||
- full
|
||||
- trl
|
||||
- dpo
|
||||
- llama-factory
|
||||
- generated_from_trainer
|
||||
model-index:
|
||||
- name: qwen2.5-7b-mlc
|
||||
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-mlc
|
||||
|
||||
This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the dpo-pku-saferlhf-alpaca3-8b-multilin 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: 6e-07
|
||||
- train_batch_size: 1
|
||||
- eval_batch_size: 8
|
||||
- seed: 42
|
||||
- distributed_type: multi-GPU
|
||||
- num_devices: 8
|
||||
- gradient_accumulation_steps: 4
|
||||
- total_train_batch_size: 32
|
||||
- total_eval_batch_size: 64
|
||||
- optimizer: Use 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 2.6.0+cu124
|
||||
- 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": 8.768589976326636e+17,
|
||||
"train_loss": 0.23950207320631442,
|
||||
"train_runtime": 868.6403,
|
||||
"train_samples_per_second": 9.836,
|
||||
"train_steps_per_second": 0.307
|
||||
}
|
||||
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
|
||||
}
|
||||
4
extractor/config.json
Normal file
4
extractor/config.json
Normal file
@@ -0,0 +1,4 @@
|
||||
{
|
||||
"hs_layer_index": 28,
|
||||
"extractor_dim": 512
|
||||
}
|
||||
3
extractor/extractor.pt
Normal file
3
extractor/extractor.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0502ab7e533ebb6efc43a424e3dca8bec9c2895004c9415a871266ac1772aaf2
|
||||
size 3672484
|
||||
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"
|
||||
}
|
||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model-00001-of-00004.safetensors
Normal file
3
model-00001-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:abd0bc45332e8cd0b2a06b5519c069f48850c412a72aeda64030fe8c96fcfdad
|
||||
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:ca053f739611bbcd5163ecafc68d6305e0899d8ab504d688fa2f8d1b84f82c96
|
||||
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 sha256:13631d5150ae2042a16252c85fa061559986082590ee109c0d08e47204544daa
|
||||
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:c2c2c38b3f53953c7e4ada1fdde8949daa539cc1e75c2540febcbbe2cfa7b48c
|
||||
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"
|
||||
}
|
||||
}
|
||||
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": 8.768589976326636e+17,
|
||||
"train_loss": 0.23950207320631442,
|
||||
"train_runtime": 868.6403,
|
||||
"train_samples_per_second": 9.836,
|
||||
"train_steps_per_second": 0.307
|
||||
}
|
||||
268
trainer_log.jsonl
Normal file
268
trainer_log.jsonl
Normal file
@@ -0,0 +1,268 @@
|
||||
{"current_steps": 1, "total_steps": 267, "loss": 1.0274, "accuracy": 0.0, "lr": 0.0, "epoch": 0.011235955056179775, "percentage": 0.37, "elapsed_time": "0:00:03", "remaining_time": "0:17:43"}
|
||||
{"current_steps": 2, "total_steps": 267, "loss": 0.6931, "accuracy": 0.0, "lr": 2.222222222222222e-08, "epoch": 0.02247191011235955, "percentage": 0.75, "elapsed_time": "0:00:06", "remaining_time": "0:15:26"}
|
||||
{"current_steps": 3, "total_steps": 267, "loss": 1.0053, "accuracy": 0.4375, "lr": 4.444444444444444e-08, "epoch": 0.033707865168539325, "percentage": 1.12, "elapsed_time": "0:00:09", "remaining_time": "0:14:17"}
|
||||
{"current_steps": 4, "total_steps": 267, "loss": 0.6751, "accuracy": 0.6875, "lr": 6.666666666666665e-08, "epoch": 0.0449438202247191, "percentage": 1.5, "elapsed_time": "0:00:12", "remaining_time": "0:13:42"}
|
||||
{"current_steps": 5, "total_steps": 267, "loss": 1.0233, "accuracy": 0.65625, "lr": 8.888888888888888e-08, "epoch": 0.056179775280898875, "percentage": 1.87, "elapsed_time": "0:00:14", "remaining_time": "0:12:58"}
|
||||
{"current_steps": 6, "total_steps": 267, "loss": 0.693, "accuracy": 0.5625, "lr": 1.111111111111111e-07, "epoch": 0.06741573033707865, "percentage": 2.25, "elapsed_time": "0:00:17", "remaining_time": "0:12:42"}
|
||||
{"current_steps": 7, "total_steps": 267, "loss": 1.0279, "accuracy": 0.375, "lr": 1.333333333333333e-07, "epoch": 0.07865168539325842, "percentage": 2.62, "elapsed_time": "0:00:20", "remaining_time": "0:12:29"}
|
||||
{"current_steps": 8, "total_steps": 267, "loss": 0.6962, "accuracy": 0.53125, "lr": 1.5555555555555554e-07, "epoch": 0.0898876404494382, "percentage": 3.0, "elapsed_time": "0:00:22", "remaining_time": "0:12:24"}
|
||||
{"current_steps": 9, "total_steps": 267, "loss": 1.0276, "accuracy": 0.5, "lr": 1.7777777777777776e-07, "epoch": 0.10112359550561797, "percentage": 3.37, "elapsed_time": "0:00:26", "remaining_time": "0:12:26"}
|
||||
{"current_steps": 10, "total_steps": 267, "loss": 0.6828, "accuracy": 0.5625, "lr": 2e-07, "epoch": 0.11235955056179775, "percentage": 3.75, "elapsed_time": "0:00:28", "remaining_time": "0:12:23"}
|
||||
{"current_steps": 11, "total_steps": 267, "loss": 1.006, "accuracy": 0.59375, "lr": 2.222222222222222e-07, "epoch": 0.12359550561797752, "percentage": 4.12, "elapsed_time": "0:00:31", "remaining_time": "0:12:23"}
|
||||
{"current_steps": 12, "total_steps": 267, "loss": 0.6744, "accuracy": 0.65625, "lr": 2.4444444444444445e-07, "epoch": 0.1348314606741573, "percentage": 4.49, "elapsed_time": "0:00:34", "remaining_time": "0:12:19"}
|
||||
{"current_steps": 13, "total_steps": 267, "loss": 1.0026, "accuracy": 0.65625, "lr": 2.666666666666666e-07, "epoch": 0.14606741573033707, "percentage": 4.87, "elapsed_time": "0:00:37", "remaining_time": "0:12:13"}
|
||||
{"current_steps": 14, "total_steps": 267, "loss": 0.6583, "accuracy": 0.75, "lr": 2.8888888888888885e-07, "epoch": 0.15730337078651685, "percentage": 5.24, "elapsed_time": "0:00:40", "remaining_time": "0:12:03"}
|
||||
{"current_steps": 15, "total_steps": 267, "loss": 0.9936, "accuracy": 0.6875, "lr": 3.1111111111111107e-07, "epoch": 0.16853932584269662, "percentage": 5.62, "elapsed_time": "0:00:42", "remaining_time": "0:11:56"}
|
||||
{"current_steps": 16, "total_steps": 267, "loss": 0.6448, "accuracy": 0.71875, "lr": 3.3333333333333335e-07, "epoch": 0.1797752808988764, "percentage": 5.99, "elapsed_time": "0:00:45", "remaining_time": "0:11:56"}
|
||||
{"current_steps": 17, "total_steps": 267, "loss": 0.927, "accuracy": 0.78125, "lr": 3.5555555555555553e-07, "epoch": 0.19101123595505617, "percentage": 6.37, "elapsed_time": "0:00:48", "remaining_time": "0:11:50"}
|
||||
{"current_steps": 18, "total_steps": 267, "loss": 0.5746, "accuracy": 0.78125, "lr": 3.7777777777777775e-07, "epoch": 0.20224719101123595, "percentage": 6.74, "elapsed_time": "0:00:51", "remaining_time": "0:11:46"}
|
||||
{"current_steps": 19, "total_steps": 267, "loss": 0.9401, "accuracy": 0.75, "lr": 4e-07, "epoch": 0.21348314606741572, "percentage": 7.12, "elapsed_time": "0:00:53", "remaining_time": "0:11:41"}
|
||||
{"current_steps": 20, "total_steps": 267, "loss": 0.6031, "accuracy": 0.78125, "lr": 4.222222222222222e-07, "epoch": 0.2247191011235955, "percentage": 7.49, "elapsed_time": "0:00:56", "remaining_time": "0:11:37"}
|
||||
{"current_steps": 21, "total_steps": 267, "loss": 0.8475, "accuracy": 0.78125, "lr": 4.444444444444444e-07, "epoch": 0.23595505617977527, "percentage": 7.87, "elapsed_time": "0:00:59", "remaining_time": "0:11:32"}
|
||||
{"current_steps": 22, "total_steps": 267, "loss": 0.5813, "accuracy": 0.71875, "lr": 4.6666666666666666e-07, "epoch": 0.24719101123595505, "percentage": 8.24, "elapsed_time": "0:01:02", "remaining_time": "0:11:31"}
|
||||
{"current_steps": 23, "total_steps": 267, "loss": 0.7386, "accuracy": 0.84375, "lr": 4.888888888888889e-07, "epoch": 0.25842696629213485, "percentage": 8.61, "elapsed_time": "0:01:05", "remaining_time": "0:11:35"}
|
||||
{"current_steps": 24, "total_steps": 267, "loss": 0.5544, "accuracy": 0.75, "lr": 5.111111111111111e-07, "epoch": 0.2696629213483146, "percentage": 8.99, "elapsed_time": "0:01:08", "remaining_time": "0:11:33"}
|
||||
{"current_steps": 25, "total_steps": 267, "loss": 0.8138, "accuracy": 0.6875, "lr": 5.333333333333332e-07, "epoch": 0.2808988764044944, "percentage": 9.36, "elapsed_time": "0:01:11", "remaining_time": "0:11:34"}
|
||||
{"current_steps": 26, "total_steps": 267, "loss": 0.3758, "accuracy": 0.875, "lr": 5.555555555555555e-07, "epoch": 0.29213483146067415, "percentage": 9.74, "elapsed_time": "0:01:14", "remaining_time": "0:11:28"}
|
||||
{"current_steps": 27, "total_steps": 267, "loss": 0.7267, "accuracy": 0.875, "lr": 5.777777777777777e-07, "epoch": 0.30337078651685395, "percentage": 10.11, "elapsed_time": "0:01:17", "remaining_time": "0:11:24"}
|
||||
{"current_steps": 28, "total_steps": 267, "loss": 0.3772, "accuracy": 0.75, "lr": 6e-07, "epoch": 0.3146067415730337, "percentage": 10.49, "elapsed_time": "0:01:19", "remaining_time": "0:11:19"}
|
||||
{"current_steps": 29, "total_steps": 267, "loss": 0.8013, "accuracy": 0.78125, "lr": 5.999742982722021e-07, "epoch": 0.3258426966292135, "percentage": 10.86, "elapsed_time": "0:01:22", "remaining_time": "0:11:16"}
|
||||
{"current_steps": 30, "total_steps": 267, "loss": 0.7047, "accuracy": 0.59375, "lr": 5.998971974926671e-07, "epoch": 0.33707865168539325, "percentage": 11.24, "elapsed_time": "0:01:26", "remaining_time": "0:11:20"}
|
||||
{"current_steps": 31, "total_steps": 267, "loss": 0.9562, "accuracy": 0.59375, "lr": 5.997687108722169e-07, "epoch": 0.34831460674157305, "percentage": 11.61, "elapsed_time": "0:01:28", "remaining_time": "0:11:15"}
|
||||
{"current_steps": 32, "total_steps": 267, "loss": 0.3156, "accuracy": 0.90625, "lr": 5.995888604263721e-07, "epoch": 0.3595505617977528, "percentage": 11.99, "elapsed_time": "0:01:31", "remaining_time": "0:11:12"}
|
||||
{"current_steps": 33, "total_steps": 267, "loss": 0.8618, "accuracy": 0.78125, "lr": 5.99357676971581e-07, "epoch": 0.3707865168539326, "percentage": 12.36, "elapsed_time": "0:01:34", "remaining_time": "0:11:10"}
|
||||
{"current_steps": 34, "total_steps": 267, "loss": 0.3738, "accuracy": 0.90625, "lr": 5.990752001199384e-07, "epoch": 0.38202247191011235, "percentage": 12.73, "elapsed_time": "0:01:37", "remaining_time": "0:11:07"}
|
||||
{"current_steps": 35, "total_steps": 267, "loss": 0.5639, "accuracy": 0.96875, "lr": 5.987414782723985e-07, "epoch": 0.39325842696629215, "percentage": 13.11, "elapsed_time": "0:01:40", "remaining_time": "0:11:04"}
|
||||
{"current_steps": 36, "total_steps": 267, "loss": 0.3975, "accuracy": 0.78125, "lr": 5.983565686104819e-07, "epoch": 0.4044943820224719, "percentage": 13.48, "elapsed_time": "0:01:42", "remaining_time": "0:10:59"}
|
||||
{"current_steps": 37, "total_steps": 267, "loss": 0.6816, "accuracy": 0.8125, "lr": 5.979205370864779e-07, "epoch": 0.4157303370786517, "percentage": 13.86, "elapsed_time": "0:01:45", "remaining_time": "0:10:54"}
|
||||
{"current_steps": 38, "total_steps": 267, "loss": 0.3216, "accuracy": 0.84375, "lr": 5.974334584121432e-07, "epoch": 0.42696629213483145, "percentage": 14.23, "elapsed_time": "0:01:48", "remaining_time": "0:10:51"}
|
||||
{"current_steps": 39, "total_steps": 267, "loss": 0.6304, "accuracy": 0.875, "lr": 5.968954160459011e-07, "epoch": 0.43820224719101125, "percentage": 14.61, "elapsed_time": "0:01:51", "remaining_time": "0:10:49"}
|
||||
{"current_steps": 40, "total_steps": 267, "loss": 0.3583, "accuracy": 0.84375, "lr": 5.963065021785413e-07, "epoch": 0.449438202247191, "percentage": 14.98, "elapsed_time": "0:01:54", "remaining_time": "0:10:47"}
|
||||
{"current_steps": 41, "total_steps": 267, "loss": 0.6716, "accuracy": 0.78125, "lr": 5.956668177174233e-07, "epoch": 0.4606741573033708, "percentage": 15.36, "elapsed_time": "0:01:57", "remaining_time": "0:10:50"}
|
||||
{"current_steps": 42, "total_steps": 267, "loss": 0.389, "accuracy": 0.84375, "lr": 5.949764722691863e-07, "epoch": 0.47191011235955055, "percentage": 15.73, "elapsed_time": "0:02:00", "remaining_time": "0:10:45"}
|
||||
{"current_steps": 43, "total_steps": 267, "loss": 0.4871, "accuracy": 0.90625, "lr": 5.942355841209691e-07, "epoch": 0.48314606741573035, "percentage": 16.1, "elapsed_time": "0:02:03", "remaining_time": "0:10:41"}
|
||||
{"current_steps": 44, "total_steps": 267, "loss": 0.3946, "accuracy": 0.71875, "lr": 5.934442802201417e-07, "epoch": 0.4943820224719101, "percentage": 16.48, "elapsed_time": "0:02:06", "remaining_time": "0:10:39"}
|
||||
{"current_steps": 45, "total_steps": 267, "loss": 0.464, "accuracy": 0.875, "lr": 5.926026961525537e-07, "epoch": 0.5056179775280899, "percentage": 16.85, "elapsed_time": "0:02:09", "remaining_time": "0:10:39"}
|
||||
{"current_steps": 46, "total_steps": 267, "loss": 0.4054, "accuracy": 0.875, "lr": 5.91710976119303e-07, "epoch": 0.5168539325842697, "percentage": 17.23, "elapsed_time": "0:02:12", "remaining_time": "0:10:35"}
|
||||
{"current_steps": 47, "total_steps": 267, "loss": 0.5265, "accuracy": 0.84375, "lr": 5.907692729120263e-07, "epoch": 0.5280898876404494, "percentage": 17.6, "elapsed_time": "0:02:15", "remaining_time": "0:10:33"}
|
||||
{"current_steps": 48, "total_steps": 267, "loss": 0.3377, "accuracy": 0.875, "lr": 5.897777478867205e-07, "epoch": 0.5393258426966292, "percentage": 17.98, "elapsed_time": "0:02:18", "remaining_time": "0:10:30"}
|
||||
{"current_steps": 49, "total_steps": 267, "loss": 0.4602, "accuracy": 0.84375, "lr": 5.887365709360941e-07, "epoch": 0.550561797752809, "percentage": 18.35, "elapsed_time": "0:02:21", "remaining_time": "0:10:30"}
|
||||
{"current_steps": 50, "total_steps": 267, "loss": 0.287, "accuracy": 0.90625, "lr": 5.876459204604579e-07, "epoch": 0.5617977528089888, "percentage": 18.73, "elapsed_time": "0:02:24", "remaining_time": "0:10:26"}
|
||||
{"current_steps": 51, "total_steps": 267, "loss": 0.4242, "accuracy": 0.875, "lr": 5.86505983337156e-07, "epoch": 0.5730337078651685, "percentage": 19.1, "elapsed_time": "0:02:27", "remaining_time": "0:10:23"}
|
||||
{"current_steps": 52, "total_steps": 267, "loss": 0.6326, "accuracy": 0.8125, "lr": 5.85316954888546e-07, "epoch": 0.5842696629213483, "percentage": 19.48, "elapsed_time": "0:02:30", "remaining_time": "0:10:22"}
|
||||
{"current_steps": 53, "total_steps": 267, "loss": 0.3262, "accuracy": 0.9375, "lr": 5.840790388485317e-07, "epoch": 0.5955056179775281, "percentage": 19.85, "elapsed_time": "0:02:33", "remaining_time": "0:10:18"}
|
||||
{"current_steps": 54, "total_steps": 267, "loss": 0.3079, "accuracy": 0.84375, "lr": 5.827924473276535e-07, "epoch": 0.6067415730337079, "percentage": 20.22, "elapsed_time": "0:02:35", "remaining_time": "0:10:14"}
|
||||
{"current_steps": 55, "total_steps": 267, "loss": 0.423, "accuracy": 0.9375, "lr": 5.814574007767452e-07, "epoch": 0.6179775280898876, "percentage": 20.6, "elapsed_time": "0:02:39", "remaining_time": "0:10:13"}
|
||||
{"current_steps": 56, "total_steps": 267, "loss": 0.2409, "accuracy": 0.90625, "lr": 5.800741279491605e-07, "epoch": 0.6292134831460674, "percentage": 20.97, "elapsed_time": "0:02:41", "remaining_time": "0:10:09"}
|
||||
{"current_steps": 57, "total_steps": 267, "loss": 0.3143, "accuracy": 0.90625, "lr": 5.786428658615773e-07, "epoch": 0.6404494382022472, "percentage": 21.35, "elapsed_time": "0:02:44", "remaining_time": "0:10:06"}
|
||||
{"current_steps": 58, "total_steps": 267, "loss": 0.3021, "accuracy": 0.78125, "lr": 5.77163859753386e-07, "epoch": 0.651685393258427, "percentage": 21.72, "elapsed_time": "0:02:46", "remaining_time": "0:10:01"}
|
||||
{"current_steps": 59, "total_steps": 267, "loss": 0.3899, "accuracy": 0.875, "lr": 5.756373630446695e-07, "epoch": 0.6629213483146067, "percentage": 22.1, "elapsed_time": "0:02:49", "remaining_time": "0:09:57"}
|
||||
{"current_steps": 60, "total_steps": 267, "loss": 0.303, "accuracy": 0.875, "lr": 5.740636372927802e-07, "epoch": 0.6741573033707865, "percentage": 22.47, "elapsed_time": "0:02:52", "remaining_time": "0:09:55"}
|
||||
{"current_steps": 61, "total_steps": 267, "loss": 0.4159, "accuracy": 0.8125, "lr": 5.724429521475244e-07, "epoch": 0.6853932584269663, "percentage": 22.85, "elapsed_time": "0:02:55", "remaining_time": "0:09:51"}
|
||||
{"current_steps": 62, "total_steps": 267, "loss": 0.2468, "accuracy": 0.875, "lr": 5.707755853049582e-07, "epoch": 0.6966292134831461, "percentage": 23.22, "elapsed_time": "0:02:57", "remaining_time": "0:09:47"}
|
||||
{"current_steps": 63, "total_steps": 267, "loss": 0.2869, "accuracy": 0.9375, "lr": 5.690618224598064e-07, "epoch": 0.7078651685393258, "percentage": 23.6, "elapsed_time": "0:03:00", "remaining_time": "0:09:44"}
|
||||
{"current_steps": 64, "total_steps": 267, "loss": 0.2658, "accuracy": 0.875, "lr": 5.673019572565103e-07, "epoch": 0.7191011235955056, "percentage": 23.97, "elapsed_time": "0:03:03", "remaining_time": "0:09:41"}
|
||||
{"current_steps": 65, "total_steps": 267, "loss": 0.2926, "accuracy": 0.90625, "lr": 5.654962912389125e-07, "epoch": 0.7303370786516854, "percentage": 24.34, "elapsed_time": "0:03:06", "remaining_time": "0:09:38"}
|
||||
{"current_steps": 66, "total_steps": 267, "loss": 0.3194, "accuracy": 0.90625, "lr": 5.636451337985896e-07, "epoch": 0.7415730337078652, "percentage": 24.72, "elapsed_time": "0:03:08", "remaining_time": "0:09:35"}
|
||||
{"current_steps": 67, "total_steps": 267, "loss": 0.3793, "accuracy": 0.875, "lr": 5.617488021218391e-07, "epoch": 0.7528089887640449, "percentage": 25.09, "elapsed_time": "0:03:11", "remaining_time": "0:09:32"}
|
||||
{"current_steps": 68, "total_steps": 267, "loss": 0.129, "accuracy": 0.96875, "lr": 5.598076211353317e-07, "epoch": 0.7640449438202247, "percentage": 25.47, "elapsed_time": "0:03:15", "remaining_time": "0:09:30"}
|
||||
{"current_steps": 69, "total_steps": 267, "loss": 0.3873, "accuracy": 0.90625, "lr": 5.578219234504358e-07, "epoch": 0.7752808988764045, "percentage": 25.84, "elapsed_time": "0:03:18", "remaining_time": "0:09:28"}
|
||||
{"current_steps": 70, "total_steps": 267, "loss": 0.3256, "accuracy": 0.84375, "lr": 5.557920493062276e-07, "epoch": 0.7865168539325843, "percentage": 26.22, "elapsed_time": "0:03:21", "remaining_time": "0:09:27"}
|
||||
{"current_steps": 71, "total_steps": 267, "loss": 0.3599, "accuracy": 0.875, "lr": 5.537183465111921e-07, "epoch": 0.797752808988764, "percentage": 26.59, "elapsed_time": "0:03:24", "remaining_time": "0:09:24"}
|
||||
{"current_steps": 72, "total_steps": 267, "loss": 0.327, "accuracy": 0.84375, "lr": 5.516011703836272e-07, "epoch": 0.8089887640449438, "percentage": 26.97, "elapsed_time": "0:03:26", "remaining_time": "0:09:20"}
|
||||
{"current_steps": 73, "total_steps": 267, "loss": 0.2826, "accuracy": 0.96875, "lr": 5.494408836907636e-07, "epoch": 0.8202247191011236, "percentage": 27.34, "elapsed_time": "0:03:29", "remaining_time": "0:09:17"}
|
||||
{"current_steps": 74, "total_steps": 267, "loss": 0.1745, "accuracy": 0.875, "lr": 5.472378565866046e-07, "epoch": 0.8314606741573034, "percentage": 27.72, "elapsed_time": "0:03:32", "remaining_time": "0:09:14"}
|
||||
{"current_steps": 75, "total_steps": 267, "loss": 0.2656, "accuracy": 0.96875, "lr": 5.449924665485037e-07, "epoch": 0.8426966292134831, "percentage": 28.09, "elapsed_time": "0:03:35", "remaining_time": "0:09:11"}
|
||||
{"current_steps": 76, "total_steps": 267, "loss": 0.2152, "accuracy": 0.9375, "lr": 5.427050983124842e-07, "epoch": 0.8539325842696629, "percentage": 28.46, "elapsed_time": "0:03:38", "remaining_time": "0:09:08"}
|
||||
{"current_steps": 77, "total_steps": 267, "loss": 0.5194, "accuracy": 0.8125, "lr": 5.403761438073181e-07, "epoch": 0.8651685393258427, "percentage": 28.84, "elapsed_time": "0:03:40", "remaining_time": "0:09:04"}
|
||||
{"current_steps": 78, "total_steps": 267, "loss": 0.3831, "accuracy": 0.78125, "lr": 5.380060020873705e-07, "epoch": 0.8764044943820225, "percentage": 29.21, "elapsed_time": "0:03:43", "remaining_time": "0:09:01"}
|
||||
{"current_steps": 79, "total_steps": 267, "loss": 0.3575, "accuracy": 0.875, "lr": 5.355950792642234e-07, "epoch": 0.8876404494382022, "percentage": 29.59, "elapsed_time": "0:03:47", "remaining_time": "0:09:01"}
|
||||
{"current_steps": 80, "total_steps": 267, "loss": 0.262, "accuracy": 0.90625, "lr": 5.331437884370913e-07, "epoch": 0.898876404494382, "percentage": 29.96, "elapsed_time": "0:03:50", "remaining_time": "0:08:58"}
|
||||
{"current_steps": 81, "total_steps": 267, "loss": 0.3208, "accuracy": 0.875, "lr": 5.306525496220379e-07, "epoch": 0.9101123595505618, "percentage": 30.34, "elapsed_time": "0:03:53", "remaining_time": "0:08:55"}
|
||||
{"current_steps": 82, "total_steps": 267, "loss": 0.2275, "accuracy": 0.875, "lr": 5.281217896800093e-07, "epoch": 0.9213483146067416, "percentage": 30.71, "elapsed_time": "0:03:55", "remaining_time": "0:08:51"}
|
||||
{"current_steps": 83, "total_steps": 267, "loss": 0.3738, "accuracy": 0.84375, "lr": 5.255519422436932e-07, "epoch": 0.9325842696629213, "percentage": 31.09, "elapsed_time": "0:03:58", "remaining_time": "0:08:47"}
|
||||
{"current_steps": 84, "total_steps": 267, "loss": 0.2277, "accuracy": 0.90625, "lr": 5.229434476432182e-07, "epoch": 0.9438202247191011, "percentage": 31.46, "elapsed_time": "0:04:00", "remaining_time": "0:08:44"}
|
||||
{"current_steps": 85, "total_steps": 267, "loss": 0.2272, "accuracy": 0.90625, "lr": 5.202967528307056e-07, "epoch": 0.9550561797752809, "percentage": 31.84, "elapsed_time": "0:04:03", "remaining_time": "0:08:41"}
|
||||
{"current_steps": 86, "total_steps": 267, "loss": 0.1575, "accuracy": 0.9375, "lr": 5.176123113036862e-07, "epoch": 0.9662921348314607, "percentage": 32.21, "elapsed_time": "0:04:06", "remaining_time": "0:08:38"}
|
||||
{"current_steps": 87, "total_steps": 267, "loss": 0.4572, "accuracy": 0.875, "lr": 5.148905830273963e-07, "epoch": 0.9775280898876404, "percentage": 32.58, "elapsed_time": "0:04:08", "remaining_time": "0:08:34"}
|
||||
{"current_steps": 88, "total_steps": 267, "loss": 0.1776, "accuracy": 0.9375, "lr": 5.121320343559642e-07, "epoch": 0.9887640449438202, "percentage": 32.96, "elapsed_time": "0:04:11", "remaining_time": "0:08:31"}
|
||||
{"current_steps": 89, "total_steps": 267, "loss": 0.2496, "accuracy": 0.90625, "lr": 5.093371379525041e-07, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:04:14", "remaining_time": "0:08:29"}
|
||||
{"current_steps": 90, "total_steps": 267, "loss": 0.099, "accuracy": 1.0, "lr": 5.065063727081262e-07, "epoch": 1.0112359550561798, "percentage": 33.71, "elapsed_time": "0:04:18", "remaining_time": "0:08:29"}
|
||||
{"current_steps": 91, "total_steps": 267, "loss": 0.2264, "accuracy": 0.96875, "lr": 5.036402236598825e-07, "epoch": 1.0224719101123596, "percentage": 34.08, "elapsed_time": "0:04:21", "remaining_time": "0:08:25"}
|
||||
{"current_steps": 92, "total_steps": 267, "loss": 0.2003, "accuracy": 0.9375, "lr": 5.007391819076575e-07, "epoch": 1.0337078651685394, "percentage": 34.46, "elapsed_time": "0:04:24", "remaining_time": "0:08:23"}
|
||||
{"current_steps": 93, "total_steps": 267, "loss": 0.1786, "accuracy": 0.96875, "lr": 4.978037445300206e-07, "epoch": 1.0449438202247192, "percentage": 34.83, "elapsed_time": "0:04:28", "remaining_time": "0:08:21"}
|
||||
{"current_steps": 94, "total_steps": 267, "loss": 0.2174, "accuracy": 0.96875, "lr": 4.94834414499055e-07, "epoch": 1.0561797752808988, "percentage": 35.21, "elapsed_time": "0:04:30", "remaining_time": "0:08:18"}
|
||||
{"current_steps": 95, "total_steps": 267, "loss": 0.1504, "accuracy": 1.0, "lr": 4.918317005941754e-07, "epoch": 1.0674157303370786, "percentage": 35.58, "elapsed_time": "0:04:33", "remaining_time": "0:08:15"}
|
||||
{"current_steps": 96, "total_steps": 267, "loss": 0.1015, "accuracy": 0.96875, "lr": 4.887961173149512e-07, "epoch": 1.0786516853932584, "percentage": 35.96, "elapsed_time": "0:04:36", "remaining_time": "0:08:12"}
|
||||
{"current_steps": 97, "total_steps": 267, "loss": 0.1686, "accuracy": 0.96875, "lr": 4.857281847929502e-07, "epoch": 1.0898876404494382, "percentage": 36.33, "elapsed_time": "0:04:39", "remaining_time": "0:08:09"}
|
||||
{"current_steps": 98, "total_steps": 267, "loss": 0.1916, "accuracy": 0.90625, "lr": 4.826284287026162e-07, "epoch": 1.101123595505618, "percentage": 36.7, "elapsed_time": "0:04:42", "remaining_time": "0:08:07"}
|
||||
{"current_steps": 99, "total_steps": 267, "loss": 0.249, "accuracy": 0.96875, "lr": 4.794973801711977e-07, "epoch": 1.1123595505617978, "percentage": 37.08, "elapsed_time": "0:04:46", "remaining_time": "0:08:06"}
|
||||
{"current_steps": 100, "total_steps": 267, "loss": 0.1337, "accuracy": 0.96875, "lr": 4.763355756877419e-07, "epoch": 1.1235955056179776, "percentage": 37.45, "elapsed_time": "0:04:49", "remaining_time": "0:08:02"}
|
||||
{"current_steps": 101, "total_steps": 267, "loss": 0.2113, "accuracy": 0.96875, "lr": 4.731435570111701e-07, "epoch": 1.1348314606741572, "percentage": 37.83, "elapsed_time": "0:04:51", "remaining_time": "0:07:59"}
|
||||
{"current_steps": 102, "total_steps": 267, "loss": 0.1575, "accuracy": 0.96875, "lr": 4.699218710774498e-07, "epoch": 1.146067415730337, "percentage": 38.2, "elapsed_time": "0:04:54", "remaining_time": "0:07:56"}
|
||||
{"current_steps": 103, "total_steps": 267, "loss": 0.1139, "accuracy": 1.0, "lr": 4.666710699058806e-07, "epoch": 1.1573033707865168, "percentage": 38.58, "elapsed_time": "0:04:57", "remaining_time": "0:07:53"}
|
||||
{"current_steps": 104, "total_steps": 267, "loss": 0.0999, "accuracy": 0.9375, "lr": 4.6339171050450815e-07, "epoch": 1.1685393258426966, "percentage": 38.95, "elapsed_time": "0:05:00", "remaining_time": "0:07:50"}
|
||||
{"current_steps": 105, "total_steps": 267, "loss": 0.2152, "accuracy": 1.0, "lr": 4.6008435477468346e-07, "epoch": 1.1797752808988764, "percentage": 39.33, "elapsed_time": "0:05:03", "remaining_time": "0:07:48"}
|
||||
{"current_steps": 106, "total_steps": 267, "loss": 0.0716, "accuracy": 1.0, "lr": 4.567495694147846e-07, "epoch": 1.1910112359550562, "percentage": 39.7, "elapsed_time": "0:05:06", "remaining_time": "0:07:46"}
|
||||
{"current_steps": 107, "total_steps": 267, "loss": 0.2069, "accuracy": 0.9375, "lr": 4.5338792582311554e-07, "epoch": 1.202247191011236, "percentage": 40.07, "elapsed_time": "0:05:09", "remaining_time": "0:07:43"}
|
||||
{"current_steps": 108, "total_steps": 267, "loss": 0.083, "accuracy": 0.96875, "lr": 4.5e-07, "epoch": 1.2134831460674158, "percentage": 40.45, "elapsed_time": "0:05:12", "remaining_time": "0:07:40"}
|
||||
{"current_steps": 109, "total_steps": 267, "loss": 0.2762, "accuracy": 0.9375, "lr": 4.465863724490865e-07, "epoch": 1.2247191011235956, "percentage": 40.82, "elapsed_time": "0:05:14", "remaining_time": "0:07:36"}
|
||||
{"current_steps": 110, "total_steps": 267, "loss": 0.1996, "accuracy": 0.9375, "lr": 4.431476280778825e-07, "epoch": 1.2359550561797752, "percentage": 41.2, "elapsed_time": "0:05:17", "remaining_time": "0:07:33"}
|
||||
{"current_steps": 111, "total_steps": 267, "loss": 0.1587, "accuracy": 1.0, "lr": 4.396843560975334e-07, "epoch": 1.247191011235955, "percentage": 41.57, "elapsed_time": "0:05:20", "remaining_time": "0:07:30"}
|
||||
{"current_steps": 112, "total_steps": 267, "loss": 0.0545, "accuracy": 0.96875, "lr": 4.36197149921864e-07, "epoch": 1.2584269662921348, "percentage": 41.95, "elapsed_time": "0:05:23", "remaining_time": "0:07:27"}
|
||||
{"current_steps": 113, "total_steps": 267, "loss": 0.1557, "accuracy": 0.96875, "lr": 4.326866070657004e-07, "epoch": 1.2696629213483146, "percentage": 42.32, "elapsed_time": "0:05:26", "remaining_time": "0:07:24"}
|
||||
{"current_steps": 114, "total_steps": 267, "loss": 0.1042, "accuracy": 0.96875, "lr": 4.2915332904248856e-07, "epoch": 1.2808988764044944, "percentage": 42.7, "elapsed_time": "0:05:28", "remaining_time": "0:07:21"}
|
||||
{"current_steps": 115, "total_steps": 267, "loss": 0.2075, "accuracy": 0.96875, "lr": 4.2559792126122843e-07, "epoch": 1.2921348314606742, "percentage": 43.07, "elapsed_time": "0:05:31", "remaining_time": "0:07:18"}
|
||||
{"current_steps": 116, "total_steps": 267, "loss": 0.0697, "accuracy": 0.96875, "lr": 4.220209929227401e-07, "epoch": 1.303370786516854, "percentage": 43.45, "elapsed_time": "0:05:34", "remaining_time": "0:07:15"}
|
||||
{"current_steps": 117, "total_steps": 267, "loss": 0.1262, "accuracy": 1.0, "lr": 4.184231569152801e-07, "epoch": 1.3146067415730336, "percentage": 43.82, "elapsed_time": "0:05:37", "remaining_time": "0:07:12"}
|
||||
{"current_steps": 118, "total_steps": 267, "loss": 0.2046, "accuracy": 0.90625, "lr": 4.1480502970952696e-07, "epoch": 1.3258426966292136, "percentage": 44.19, "elapsed_time": "0:05:40", "remaining_time": "0:07:09"}
|
||||
{"current_steps": 119, "total_steps": 267, "loss": 0.2055, "accuracy": 0.96875, "lr": 4.111672312529509e-07, "epoch": 1.3370786516853932, "percentage": 44.57, "elapsed_time": "0:05:42", "remaining_time": "0:07:06"}
|
||||
{"current_steps": 120, "total_steps": 267, "loss": 0.0681, "accuracy": 1.0, "lr": 4.0751038486359e-07, "epoch": 1.348314606741573, "percentage": 44.94, "elapsed_time": "0:05:46", "remaining_time": "0:07:04"}
|
||||
{"current_steps": 121, "total_steps": 267, "loss": 0.1519, "accuracy": 1.0, "lr": 4.0383511712324786e-07, "epoch": 1.3595505617977528, "percentage": 45.32, "elapsed_time": "0:05:49", "remaining_time": "0:07:01"}
|
||||
{"current_steps": 122, "total_steps": 267, "loss": 0.3835, "accuracy": 0.84375, "lr": 4.0014205777013123e-07, "epoch": 1.3707865168539326, "percentage": 45.69, "elapsed_time": "0:05:52", "remaining_time": "0:06:58"}
|
||||
{"current_steps": 123, "total_steps": 267, "loss": 0.1535, "accuracy": 0.9375, "lr": 3.964318395909485e-07, "epoch": 1.3820224719101124, "percentage": 46.07, "elapsed_time": "0:05:54", "remaining_time": "0:06:55"}
|
||||
{"current_steps": 124, "total_steps": 267, "loss": 0.139, "accuracy": 0.90625, "lr": 3.927050983124842e-07, "epoch": 1.3932584269662922, "percentage": 46.44, "elapsed_time": "0:05:57", "remaining_time": "0:06:52"}
|
||||
{"current_steps": 125, "total_steps": 267, "loss": 0.1352, "accuracy": 1.0, "lr": 3.8896247249267124e-07, "epoch": 1.404494382022472, "percentage": 46.82, "elapsed_time": "0:06:00", "remaining_time": "0:06:49"}
|
||||
{"current_steps": 126, "total_steps": 267, "loss": 0.0778, "accuracy": 1.0, "lr": 3.8520460341117685e-07, "epoch": 1.4157303370786516, "percentage": 47.19, "elapsed_time": "0:06:02", "remaining_time": "0:06:46"}
|
||||
{"current_steps": 127, "total_steps": 267, "loss": 0.1312, "accuracy": 0.96875, "lr": 3.8143213495952226e-07, "epoch": 1.4269662921348314, "percentage": 47.57, "elapsed_time": "0:06:05", "remaining_time": "0:06:43"}
|
||||
{"current_steps": 128, "total_steps": 267, "loss": 0.2656, "accuracy": 0.84375, "lr": 3.776457135307562e-07, "epoch": 1.4382022471910112, "percentage": 47.94, "elapsed_time": "0:06:08", "remaining_time": "0:06:40"}
|
||||
{"current_steps": 129, "total_steps": 267, "loss": 0.1645, "accuracy": 0.96875, "lr": 3.7384598790869793e-07, "epoch": 1.449438202247191, "percentage": 48.31, "elapsed_time": "0:06:11", "remaining_time": "0:06:37"}
|
||||
{"current_steps": 130, "total_steps": 267, "loss": 0.1513, "accuracy": 0.9375, "lr": 3.7003360915677166e-07, "epoch": 1.4606741573033708, "percentage": 48.69, "elapsed_time": "0:06:14", "remaining_time": "0:06:34"}
|
||||
{"current_steps": 131, "total_steps": 267, "loss": 0.1166, "accuracy": 1.0, "lr": 3.6620923050645043e-07, "epoch": 1.4719101123595506, "percentage": 49.06, "elapsed_time": "0:06:17", "remaining_time": "0:06:31"}
|
||||
{"current_steps": 132, "total_steps": 267, "loss": 0.0758, "accuracy": 0.96875, "lr": 3.6237350724532774e-07, "epoch": 1.4831460674157304, "percentage": 49.44, "elapsed_time": "0:06:19", "remaining_time": "0:06:28"}
|
||||
{"current_steps": 133, "total_steps": 267, "loss": 0.1505, "accuracy": 0.96875, "lr": 3.585270966048385e-07, "epoch": 1.49438202247191, "percentage": 49.81, "elapsed_time": "0:06:22", "remaining_time": "0:06:25"}
|
||||
{"current_steps": 134, "total_steps": 267, "loss": 0.1338, "accuracy": 0.9375, "lr": 3.546706576476443e-07, "epoch": 1.50561797752809, "percentage": 50.19, "elapsed_time": "0:06:25", "remaining_time": "0:06:22"}
|
||||
{"current_steps": 135, "total_steps": 267, "loss": 0.2142, "accuracy": 0.90625, "lr": 3.5080485115470735e-07, "epoch": 1.5168539325842696, "percentage": 50.56, "elapsed_time": "0:06:28", "remaining_time": "0:06:19"}
|
||||
{"current_steps": 136, "total_steps": 267, "loss": 0.0719, "accuracy": 0.96875, "lr": 3.469303395120693e-07, "epoch": 1.5280898876404494, "percentage": 50.94, "elapsed_time": "0:06:31", "remaining_time": "0:06:17"}
|
||||
{"current_steps": 137, "total_steps": 267, "loss": 0.209, "accuracy": 0.96875, "lr": 3.4304778659735374e-07, "epoch": 1.5393258426966292, "percentage": 51.31, "elapsed_time": "0:06:34", "remaining_time": "0:06:14"}
|
||||
{"current_steps": 138, "total_steps": 267, "loss": 0.0997, "accuracy": 0.9375, "lr": 3.3915785766601553e-07, "epoch": 1.550561797752809, "percentage": 51.69, "elapsed_time": "0:06:37", "remaining_time": "0:06:11"}
|
||||
{"current_steps": 139, "total_steps": 267, "loss": 0.1895, "accuracy": 0.96875, "lr": 3.352612192373513e-07, "epoch": 1.5617977528089888, "percentage": 52.06, "elapsed_time": "0:06:40", "remaining_time": "0:06:08"}
|
||||
{"current_steps": 140, "total_steps": 267, "loss": 0.0899, "accuracy": 0.96875, "lr": 3.31358538980296e-07, "epoch": 1.5730337078651684, "percentage": 52.43, "elapsed_time": "0:06:43", "remaining_time": "0:06:05"}
|
||||
{"current_steps": 141, "total_steps": 267, "loss": 0.1419, "accuracy": 1.0, "lr": 3.2745048559902074e-07, "epoch": 1.5842696629213484, "percentage": 52.81, "elapsed_time": "0:06:46", "remaining_time": "0:06:03"}
|
||||
{"current_steps": 142, "total_steps": 267, "loss": 0.0978, "accuracy": 0.96875, "lr": 3.235377287183535e-07, "epoch": 1.595505617977528, "percentage": 53.18, "elapsed_time": "0:06:49", "remaining_time": "0:06:00"}
|
||||
{"current_steps": 143, "total_steps": 267, "loss": 0.1075, "accuracy": 1.0, "lr": 3.1962093876904293e-07, "epoch": 1.606741573033708, "percentage": 53.56, "elapsed_time": "0:06:51", "remaining_time": "0:05:57"}
|
||||
{"current_steps": 144, "total_steps": 267, "loss": 0.1602, "accuracy": 0.96875, "lr": 3.1570078687288317e-07, "epoch": 1.6179775280898876, "percentage": 53.93, "elapsed_time": "0:06:54", "remaining_time": "0:05:53"}
|
||||
{"current_steps": 145, "total_steps": 267, "loss": 0.1349, "accuracy": 1.0, "lr": 3.117779447277206e-07, "epoch": 1.6292134831460674, "percentage": 54.31, "elapsed_time": "0:06:56", "remaining_time": "0:05:50"}
|
||||
{"current_steps": 146, "total_steps": 267, "loss": 0.0887, "accuracy": 0.96875, "lr": 3.07853084492362e-07, "epoch": 1.6404494382022472, "percentage": 54.68, "elapsed_time": "0:06:59", "remaining_time": "0:05:47"}
|
||||
{"current_steps": 147, "total_steps": 267, "loss": 0.127, "accuracy": 0.96875, "lr": 3.039268786714033e-07, "epoch": 1.651685393258427, "percentage": 55.06, "elapsed_time": "0:07:02", "remaining_time": "0:05:44"}
|
||||
{"current_steps": 148, "total_steps": 267, "loss": 0.0798, "accuracy": 1.0, "lr": 3e-07, "epoch": 1.6629213483146068, "percentage": 55.43, "elapsed_time": "0:07:05", "remaining_time": "0:05:42"}
|
||||
{"current_steps": 149, "total_steps": 267, "loss": 0.2058, "accuracy": 0.9375, "lr": 2.960731213285967e-07, "epoch": 1.6741573033707864, "percentage": 55.81, "elapsed_time": "0:07:08", "remaining_time": "0:05:39"}
|
||||
{"current_steps": 150, "total_steps": 267, "loss": 0.1549, "accuracy": 0.90625, "lr": 2.921469155076381e-07, "epoch": 1.6853932584269664, "percentage": 56.18, "elapsed_time": "0:07:11", "remaining_time": "0:05:36"}
|
||||
{"current_steps": 151, "total_steps": 267, "loss": 0.1435, "accuracy": 0.9375, "lr": 2.882220552722795e-07, "epoch": 1.696629213483146, "percentage": 56.55, "elapsed_time": "0:07:13", "remaining_time": "0:05:32"}
|
||||
{"current_steps": 152, "total_steps": 267, "loss": 0.1067, "accuracy": 0.90625, "lr": 2.8429921312711686e-07, "epoch": 1.7078651685393258, "percentage": 56.93, "elapsed_time": "0:07:16", "remaining_time": "0:05:29"}
|
||||
{"current_steps": 153, "total_steps": 267, "loss": 0.1457, "accuracy": 0.96875, "lr": 2.8037906123095704e-07, "epoch": 1.7191011235955056, "percentage": 57.3, "elapsed_time": "0:07:18", "remaining_time": "0:05:26"}
|
||||
{"current_steps": 154, "total_steps": 267, "loss": 0.0782, "accuracy": 0.96875, "lr": 2.7646227128164656e-07, "epoch": 1.7303370786516854, "percentage": 57.68, "elapsed_time": "0:07:21", "remaining_time": "0:05:23"}
|
||||
{"current_steps": 155, "total_steps": 267, "loss": 0.1812, "accuracy": 0.96875, "lr": 2.725495144009793e-07, "epoch": 1.7415730337078652, "percentage": 58.05, "elapsed_time": "0:07:24", "remaining_time": "0:05:21"}
|
||||
{"current_steps": 156, "total_steps": 267, "loss": 0.0712, "accuracy": 1.0, "lr": 2.68641461019704e-07, "epoch": 1.7528089887640448, "percentage": 58.43, "elapsed_time": "0:07:26", "remaining_time": "0:05:17"}
|
||||
{"current_steps": 157, "total_steps": 267, "loss": 0.1051, "accuracy": 1.0, "lr": 2.647387807626487e-07, "epoch": 1.7640449438202248, "percentage": 58.8, "elapsed_time": "0:07:29", "remaining_time": "0:05:14"}
|
||||
{"current_steps": 158, "total_steps": 267, "loss": 0.0683, "accuracy": 1.0, "lr": 2.608421423339846e-07, "epoch": 1.7752808988764044, "percentage": 59.18, "elapsed_time": "0:07:31", "remaining_time": "0:05:11"}
|
||||
{"current_steps": 159, "total_steps": 267, "loss": 0.0788, "accuracy": 1.0, "lr": 2.5695221340264623e-07, "epoch": 1.7865168539325844, "percentage": 59.55, "elapsed_time": "0:07:35", "remaining_time": "0:05:09"}
|
||||
{"current_steps": 160, "total_steps": 267, "loss": 0.0829, "accuracy": 0.96875, "lr": 2.530696604879307e-07, "epoch": 1.797752808988764, "percentage": 59.93, "elapsed_time": "0:07:38", "remaining_time": "0:05:06"}
|
||||
{"current_steps": 161, "total_steps": 267, "loss": 0.189, "accuracy": 0.9375, "lr": 2.491951488452926e-07, "epoch": 1.8089887640449438, "percentage": 60.3, "elapsed_time": "0:07:41", "remaining_time": "0:05:03"}
|
||||
{"current_steps": 162, "total_steps": 267, "loss": 0.1039, "accuracy": 0.96875, "lr": 2.4532934235235574e-07, "epoch": 1.8202247191011236, "percentage": 60.67, "elapsed_time": "0:07:44", "remaining_time": "0:05:00"}
|
||||
{"current_steps": 163, "total_steps": 267, "loss": 0.1056, "accuracy": 1.0, "lr": 2.414729033951615e-07, "epoch": 1.8314606741573034, "percentage": 61.05, "elapsed_time": "0:07:47", "remaining_time": "0:04:58"}
|
||||
{"current_steps": 164, "total_steps": 267, "loss": 0.1456, "accuracy": 0.96875, "lr": 2.3762649275467223e-07, "epoch": 1.8426966292134832, "percentage": 61.42, "elapsed_time": "0:07:50", "remaining_time": "0:04:55"}
|
||||
{"current_steps": 165, "total_steps": 267, "loss": 0.1951, "accuracy": 0.9375, "lr": 2.337907694935497e-07, "epoch": 1.8539325842696628, "percentage": 61.8, "elapsed_time": "0:07:53", "remaining_time": "0:04:52"}
|
||||
{"current_steps": 166, "total_steps": 267, "loss": 0.0779, "accuracy": 0.96875, "lr": 2.2996639084322847e-07, "epoch": 1.8651685393258428, "percentage": 62.17, "elapsed_time": "0:07:55", "remaining_time": "0:04:49"}
|
||||
{"current_steps": 167, "total_steps": 267, "loss": 0.1155, "accuracy": 1.0, "lr": 2.2615401209130207e-07, "epoch": 1.8764044943820224, "percentage": 62.55, "elapsed_time": "0:07:58", "remaining_time": "0:04:46"}
|
||||
{"current_steps": 168, "total_steps": 267, "loss": 0.0378, "accuracy": 1.0, "lr": 2.2235428646924374e-07, "epoch": 1.8876404494382022, "percentage": 62.92, "elapsed_time": "0:08:01", "remaining_time": "0:04:43"}
|
||||
{"current_steps": 169, "total_steps": 267, "loss": 0.1174, "accuracy": 1.0, "lr": 2.1856786504047773e-07, "epoch": 1.898876404494382, "percentage": 63.3, "elapsed_time": "0:08:04", "remaining_time": "0:04:40"}
|
||||
{"current_steps": 170, "total_steps": 267, "loss": 0.1658, "accuracy": 0.9375, "lr": 2.147953965888232e-07, "epoch": 1.9101123595505618, "percentage": 63.67, "elapsed_time": "0:08:06", "remaining_time": "0:04:37"}
|
||||
{"current_steps": 171, "total_steps": 267, "loss": 0.1371, "accuracy": 1.0, "lr": 2.1103752750732873e-07, "epoch": 1.9213483146067416, "percentage": 64.04, "elapsed_time": "0:08:09", "remaining_time": "0:04:34"}
|
||||
{"current_steps": 172, "total_steps": 267, "loss": 0.1283, "accuracy": 0.96875, "lr": 2.072949016875158e-07, "epoch": 1.9325842696629212, "percentage": 64.42, "elapsed_time": "0:08:12", "remaining_time": "0:04:31"}
|
||||
{"current_steps": 173, "total_steps": 267, "loss": 0.1472, "accuracy": 1.0, "lr": 2.0356816040905157e-07, "epoch": 1.9438202247191012, "percentage": 64.79, "elapsed_time": "0:08:15", "remaining_time": "0:04:29"}
|
||||
{"current_steps": 174, "total_steps": 267, "loss": 0.0865, "accuracy": 0.96875, "lr": 1.9985794222986874e-07, "epoch": 1.9550561797752808, "percentage": 65.17, "elapsed_time": "0:08:19", "remaining_time": "0:04:26"}
|
||||
{"current_steps": 175, "total_steps": 267, "loss": 0.1419, "accuracy": 1.0, "lr": 1.9616488287675203e-07, "epoch": 1.9662921348314608, "percentage": 65.54, "elapsed_time": "0:08:21", "remaining_time": "0:04:23"}
|
||||
{"current_steps": 176, "total_steps": 267, "loss": 0.0648, "accuracy": 1.0, "lr": 1.9248961513640992e-07, "epoch": 1.9775280898876404, "percentage": 65.92, "elapsed_time": "0:08:24", "remaining_time": "0:04:20"}
|
||||
{"current_steps": 177, "total_steps": 267, "loss": 0.1892, "accuracy": 0.90625, "lr": 1.888327687470491e-07, "epoch": 1.9887640449438202, "percentage": 66.29, "elapsed_time": "0:08:27", "remaining_time": "0:04:17"}
|
||||
{"current_steps": 178, "total_steps": 267, "loss": 0.1074, "accuracy": 0.96875, "lr": 1.8519497029047307e-07, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:08:30", "remaining_time": "0:04:15"}
|
||||
{"current_steps": 179, "total_steps": 267, "loss": 0.1312, "accuracy": 0.96875, "lr": 1.8157684308471986e-07, "epoch": 2.0112359550561796, "percentage": 67.04, "elapsed_time": "0:08:33", "remaining_time": "0:04:12"}
|
||||
{"current_steps": 180, "total_steps": 267, "loss": 0.0342, "accuracy": 1.0, "lr": 1.7797900707725997e-07, "epoch": 2.0224719101123596, "percentage": 67.42, "elapsed_time": "0:08:36", "remaining_time": "0:04:09"}
|
||||
{"current_steps": 181, "total_steps": 267, "loss": 0.1039, "accuracy": 1.0, "lr": 1.7440207873877165e-07, "epoch": 2.033707865168539, "percentage": 67.79, "elapsed_time": "0:08:39", "remaining_time": "0:04:06"}
|
||||
{"current_steps": 182, "total_steps": 267, "loss": 0.0563, "accuracy": 1.0, "lr": 1.708466709575114e-07, "epoch": 2.044943820224719, "percentage": 68.16, "elapsed_time": "0:08:42", "remaining_time": "0:04:03"}
|
||||
{"current_steps": 183, "total_steps": 267, "loss": 0.1916, "accuracy": 0.9375, "lr": 1.6731339293429966e-07, "epoch": 2.056179775280899, "percentage": 68.54, "elapsed_time": "0:08:44", "remaining_time": "0:04:00"}
|
||||
{"current_steps": 184, "total_steps": 267, "loss": 0.0437, "accuracy": 1.0, "lr": 1.6380285007813597e-07, "epoch": 2.067415730337079, "percentage": 68.91, "elapsed_time": "0:08:47", "remaining_time": "0:03:58"}
|
||||
{"current_steps": 185, "total_steps": 267, "loss": 0.0796, "accuracy": 1.0, "lr": 1.6031564390246656e-07, "epoch": 2.0786516853932584, "percentage": 69.29, "elapsed_time": "0:08:51", "remaining_time": "0:03:55"}
|
||||
{"current_steps": 186, "total_steps": 267, "loss": 0.0258, "accuracy": 1.0, "lr": 1.5685237192211744e-07, "epoch": 2.0898876404494384, "percentage": 69.66, "elapsed_time": "0:08:54", "remaining_time": "0:03:52"}
|
||||
{"current_steps": 187, "total_steps": 267, "loss": 0.1075, "accuracy": 1.0, "lr": 1.5341362755091361e-07, "epoch": 2.101123595505618, "percentage": 70.04, "elapsed_time": "0:08:56", "remaining_time": "0:03:49"}
|
||||
{"current_steps": 188, "total_steps": 267, "loss": 0.0312, "accuracy": 1.0, "lr": 1.5000000000000007e-07, "epoch": 2.1123595505617976, "percentage": 70.41, "elapsed_time": "0:08:59", "remaining_time": "0:03:46"}
|
||||
{"current_steps": 189, "total_steps": 267, "loss": 0.1254, "accuracy": 0.96875, "lr": 1.4661207417688443e-07, "epoch": 2.1235955056179776, "percentage": 70.79, "elapsed_time": "0:09:02", "remaining_time": "0:03:43"}
|
||||
{"current_steps": 190, "total_steps": 267, "loss": 0.0377, "accuracy": 1.0, "lr": 1.4325043058521534e-07, "epoch": 2.134831460674157, "percentage": 71.16, "elapsed_time": "0:09:05", "remaining_time": "0:03:40"}
|
||||
{"current_steps": 191, "total_steps": 267, "loss": 0.0793, "accuracy": 1.0, "lr": 1.3991564522531654e-07, "epoch": 2.146067415730337, "percentage": 71.54, "elapsed_time": "0:09:08", "remaining_time": "0:03:38"}
|
||||
{"current_steps": 192, "total_steps": 267, "loss": 0.0383, "accuracy": 1.0, "lr": 1.3660828949549187e-07, "epoch": 2.157303370786517, "percentage": 71.91, "elapsed_time": "0:09:11", "remaining_time": "0:03:35"}
|
||||
{"current_steps": 193, "total_steps": 267, "loss": 0.1458, "accuracy": 1.0, "lr": 1.3332893009411942e-07, "epoch": 2.168539325842697, "percentage": 72.28, "elapsed_time": "0:09:14", "remaining_time": "0:03:32"}
|
||||
{"current_steps": 194, "total_steps": 267, "loss": 0.0638, "accuracy": 0.96875, "lr": 1.3007812892255022e-07, "epoch": 2.1797752808988764, "percentage": 72.66, "elapsed_time": "0:09:17", "remaining_time": "0:03:29"}
|
||||
{"current_steps": 195, "total_steps": 267, "loss": 0.1004, "accuracy": 1.0, "lr": 1.2685644298882994e-07, "epoch": 2.191011235955056, "percentage": 73.03, "elapsed_time": "0:09:19", "remaining_time": "0:03:26"}
|
||||
{"current_steps": 196, "total_steps": 267, "loss": 0.0465, "accuracy": 1.0, "lr": 1.2366442431225808e-07, "epoch": 2.202247191011236, "percentage": 73.41, "elapsed_time": "0:09:22", "remaining_time": "0:03:23"}
|
||||
{"current_steps": 197, "total_steps": 267, "loss": 0.1297, "accuracy": 0.96875, "lr": 1.2050261982880228e-07, "epoch": 2.2134831460674156, "percentage": 73.78, "elapsed_time": "0:09:25", "remaining_time": "0:03:20"}
|
||||
{"current_steps": 198, "total_steps": 267, "loss": 0.0623, "accuracy": 1.0, "lr": 1.173715712973838e-07, "epoch": 2.2247191011235956, "percentage": 74.16, "elapsed_time": "0:09:27", "remaining_time": "0:03:17"}
|
||||
{"current_steps": 199, "total_steps": 267, "loss": 0.0998, "accuracy": 1.0, "lr": 1.1427181520704978e-07, "epoch": 2.235955056179775, "percentage": 74.53, "elapsed_time": "0:09:31", "remaining_time": "0:03:15"}
|
||||
{"current_steps": 200, "total_steps": 267, "loss": 0.023, "accuracy": 1.0, "lr": 1.112038826850488e-07, "epoch": 2.247191011235955, "percentage": 74.91, "elapsed_time": "0:09:34", "remaining_time": "0:03:12"}
|
||||
{"current_steps": 201, "total_steps": 267, "loss": 0.1257, "accuracy": 0.96875, "lr": 1.081682994058246e-07, "epoch": 2.258426966292135, "percentage": 75.28, "elapsed_time": "0:09:36", "remaining_time": "0:03:09"}
|
||||
{"current_steps": 202, "total_steps": 267, "loss": 0.0354, "accuracy": 1.0, "lr": 1.0516558550094493e-07, "epoch": 2.2696629213483144, "percentage": 75.66, "elapsed_time": "0:09:39", "remaining_time": "0:03:06"}
|
||||
{"current_steps": 203, "total_steps": 267, "loss": 0.1027, "accuracy": 1.0, "lr": 1.0219625546997934e-07, "epoch": 2.2808988764044944, "percentage": 76.03, "elapsed_time": "0:09:42", "remaining_time": "0:03:03"}
|
||||
{"current_steps": 204, "total_steps": 267, "loss": 0.0157, "accuracy": 1.0, "lr": 9.926081809234262e-08, "epoch": 2.292134831460674, "percentage": 76.4, "elapsed_time": "0:09:45", "remaining_time": "0:03:00"}
|
||||
{"current_steps": 205, "total_steps": 267, "loss": 0.0935, "accuracy": 1.0, "lr": 9.635977634011746e-08, "epoch": 2.303370786516854, "percentage": 76.78, "elapsed_time": "0:09:47", "remaining_time": "0:02:57"}
|
||||
{"current_steps": 206, "total_steps": 267, "loss": 0.0231, "accuracy": 1.0, "lr": 9.349362729187375e-08, "epoch": 2.3146067415730336, "percentage": 77.15, "elapsed_time": "0:09:50", "remaining_time": "0:02:54"}
|
||||
{"current_steps": 207, "total_steps": 267, "loss": 0.1331, "accuracy": 0.96875, "lr": 9.066286204749601e-08, "epoch": 2.3258426966292136, "percentage": 77.53, "elapsed_time": "0:09:53", "remaining_time": "0:02:52"}
|
||||
{"current_steps": 208, "total_steps": 267, "loss": 0.025, "accuracy": 1.0, "lr": 8.786796564403575e-08, "epoch": 2.337078651685393, "percentage": 77.9, "elapsed_time": "0:09:56", "remaining_time": "0:02:49"}
|
||||
{"current_steps": 209, "total_steps": 267, "loss": 0.0843, "accuracy": 1.0, "lr": 8.510941697260371e-08, "epoch": 2.348314606741573, "percentage": 78.28, "elapsed_time": "0:09:59", "remaining_time": "0:02:46"}
|
||||
{"current_steps": 210, "total_steps": 267, "loss": 0.0292, "accuracy": 1.0, "lr": 8.238768869631377e-08, "epoch": 2.359550561797753, "percentage": 78.65, "elapsed_time": "0:10:02", "remaining_time": "0:02:43"}
|
||||
{"current_steps": 211, "total_steps": 267, "loss": 0.0855, "accuracy": 1.0, "lr": 7.97032471692944e-08, "epoch": 2.370786516853933, "percentage": 79.03, "elapsed_time": "0:10:04", "remaining_time": "0:02:40"}
|
||||
{"current_steps": 212, "total_steps": 267, "loss": 0.0179, "accuracy": 1.0, "lr": 7.705655235678169e-08, "epoch": 2.3820224719101124, "percentage": 79.4, "elapsed_time": "0:10:07", "remaining_time": "0:02:37"}
|
||||
{"current_steps": 213, "total_steps": 267, "loss": 0.1083, "accuracy": 1.0, "lr": 7.444805775630681e-08, "epoch": 2.393258426966292, "percentage": 79.78, "elapsed_time": "0:10:10", "remaining_time": "0:02:34"}
|
||||
{"current_steps": 214, "total_steps": 267, "loss": 0.0258, "accuracy": 1.0, "lr": 7.187821031999071e-08, "epoch": 2.404494382022472, "percentage": 80.15, "elapsed_time": "0:10:13", "remaining_time": "0:02:32"}
|
||||
{"current_steps": 215, "total_steps": 267, "loss": 0.1113, "accuracy": 1.0, "lr": 6.934745037796215e-08, "epoch": 2.4157303370786516, "percentage": 80.52, "elapsed_time": "0:10:16", "remaining_time": "0:02:29"}
|
||||
{"current_steps": 216, "total_steps": 267, "loss": 0.0249, "accuracy": 1.0, "lr": 6.685621156290873e-08, "epoch": 2.4269662921348316, "percentage": 80.9, "elapsed_time": "0:10:19", "remaining_time": "0:02:26"}
|
||||
{"current_steps": 217, "total_steps": 267, "loss": 0.0918, "accuracy": 1.0, "lr": 6.440492073577657e-08, "epoch": 2.438202247191011, "percentage": 81.27, "elapsed_time": "0:10:22", "remaining_time": "0:02:23"}
|
||||
{"current_steps": 218, "total_steps": 267, "loss": 0.0585, "accuracy": 1.0, "lr": 6.199399791262948e-08, "epoch": 2.449438202247191, "percentage": 81.65, "elapsed_time": "0:10:25", "remaining_time": "0:02:20"}
|
||||
{"current_steps": 219, "total_steps": 267, "loss": 0.0821, "accuracy": 1.0, "lr": 5.962385619268184e-08, "epoch": 2.460674157303371, "percentage": 82.02, "elapsed_time": "0:10:29", "remaining_time": "0:02:17"}
|
||||
{"current_steps": 220, "total_steps": 267, "loss": 0.0268, "accuracy": 1.0, "lr": 5.7294901687515794e-08, "epoch": 2.4719101123595504, "percentage": 82.4, "elapsed_time": "0:10:32", "remaining_time": "0:02:15"}
|
||||
{"current_steps": 221, "total_steps": 267, "loss": 0.0826, "accuracy": 1.0, "lr": 5.5007533451496326e-08, "epoch": 2.4831460674157304, "percentage": 82.77, "elapsed_time": "0:10:34", "remaining_time": "0:02:12"}
|
||||
{"current_steps": 222, "total_steps": 267, "loss": 0.08, "accuracy": 1.0, "lr": 5.2762143413395286e-08, "epoch": 2.49438202247191, "percentage": 83.15, "elapsed_time": "0:10:37", "remaining_time": "0:02:09"}
|
||||
{"current_steps": 223, "total_steps": 267, "loss": 0.0794, "accuracy": 1.0, "lr": 5.0559116309236397e-08, "epoch": 2.50561797752809, "percentage": 83.52, "elapsed_time": "0:10:40", "remaining_time": "0:02:06"}
|
||||
{"current_steps": 224, "total_steps": 267, "loss": 0.0284, "accuracy": 1.0, "lr": 4.839882961637282e-08, "epoch": 2.5168539325842696, "percentage": 83.9, "elapsed_time": "0:10:43", "remaining_time": "0:02:03"}
|
||||
{"current_steps": 225, "total_steps": 267, "loss": 0.1163, "accuracy": 1.0, "lr": 4.628165348880804e-08, "epoch": 2.5280898876404496, "percentage": 84.27, "elapsed_time": "0:10:45", "remaining_time": "0:02:00"}
|
||||
{"current_steps": 226, "total_steps": 267, "loss": 0.0612, "accuracy": 1.0, "lr": 4.4207950693772346e-08, "epoch": 2.539325842696629, "percentage": 84.64, "elapsed_time": "0:10:48", "remaining_time": "0:01:57"}
|
||||
{"current_steps": 227, "total_steps": 267, "loss": 0.0844, "accuracy": 1.0, "lr": 4.217807654956419e-08, "epoch": 2.550561797752809, "percentage": 85.02, "elapsed_time": "0:10:51", "remaining_time": "0:01:54"}
|
||||
{"current_steps": 228, "total_steps": 267, "loss": 0.0241, "accuracy": 1.0, "lr": 4.0192378864668387e-08, "epoch": 2.561797752808989, "percentage": 85.39, "elapsed_time": "0:10:54", "remaining_time": "0:01:51"}
|
||||
{"current_steps": 229, "total_steps": 267, "loss": 0.0809, "accuracy": 1.0, "lr": 3.825119787816085e-08, "epoch": 2.5730337078651684, "percentage": 85.77, "elapsed_time": "0:10:57", "remaining_time": "0:01:49"}
|
||||
{"current_steps": 230, "total_steps": 267, "loss": 0.0183, "accuracy": 1.0, "lr": 3.635486620141042e-08, "epoch": 2.5842696629213484, "percentage": 86.14, "elapsed_time": "0:11:00", "remaining_time": "0:01:46"}
|
||||
{"current_steps": 231, "total_steps": 267, "loss": 0.09, "accuracy": 1.0, "lr": 3.450370876108747e-08, "epoch": 2.595505617977528, "percentage": 86.52, "elapsed_time": "0:11:03", "remaining_time": "0:01:43"}
|
||||
{"current_steps": 232, "total_steps": 267, "loss": 0.0417, "accuracy": 1.0, "lr": 3.269804274348966e-08, "epoch": 2.606741573033708, "percentage": 86.89, "elapsed_time": "0:11:06", "remaining_time": "0:01:40"}
|
||||
{"current_steps": 233, "total_steps": 267, "loss": 0.0962, "accuracy": 1.0, "lr": 3.0938177540193524e-08, "epoch": 2.6179775280898876, "percentage": 87.27, "elapsed_time": "0:11:08", "remaining_time": "0:01:37"}
|
||||
{"current_steps": 234, "total_steps": 267, "loss": 0.0259, "accuracy": 1.0, "lr": 2.922441469504188e-08, "epoch": 2.629213483146067, "percentage": 87.64, "elapsed_time": "0:11:11", "remaining_time": "0:01:34"}
|
||||
{"current_steps": 235, "total_steps": 267, "loss": 0.1124, "accuracy": 0.96875, "lr": 2.755704785247559e-08, "epoch": 2.640449438202247, "percentage": 88.01, "elapsed_time": "0:11:14", "remaining_time": "0:01:31"}
|
||||
{"current_steps": 236, "total_steps": 267, "loss": 0.0453, "accuracy": 1.0, "lr": 2.5936362707219705e-08, "epoch": 2.6516853932584272, "percentage": 88.39, "elapsed_time": "0:11:16", "remaining_time": "0:01:28"}
|
||||
{"current_steps": 237, "total_steps": 267, "loss": 0.1132, "accuracy": 0.96875, "lr": 2.436263695533054e-08, "epoch": 2.662921348314607, "percentage": 88.76, "elapsed_time": "0:11:19", "remaining_time": "0:01:26"}
|
||||
{"current_steps": 238, "total_steps": 267, "loss": 0.0269, "accuracy": 1.0, "lr": 2.283614024661398e-08, "epoch": 2.6741573033707864, "percentage": 89.14, "elapsed_time": "0:11:22", "remaining_time": "0:01:23"}
|
||||
{"current_steps": 239, "total_steps": 267, "loss": 0.0907, "accuracy": 1.0, "lr": 2.1357134138422727e-08, "epoch": 2.6853932584269664, "percentage": 89.51, "elapsed_time": "0:11:24", "remaining_time": "0:01:20"}
|
||||
{"current_steps": 240, "total_steps": 267, "loss": 0.0174, "accuracy": 1.0, "lr": 1.9925872050839508e-08, "epoch": 2.696629213483146, "percentage": 89.89, "elapsed_time": "0:11:27", "remaining_time": "0:01:17"}
|
||||
{"current_steps": 241, "total_steps": 267, "loss": 0.0922, "accuracy": 0.96875, "lr": 1.8542599223254784e-08, "epoch": 2.7078651685393256, "percentage": 90.26, "elapsed_time": "0:11:30", "remaining_time": "0:01:14"}
|
||||
{"current_steps": 242, "total_steps": 267, "loss": 0.0331, "accuracy": 1.0, "lr": 1.720755267234647e-08, "epoch": 2.7191011235955056, "percentage": 90.64, "elapsed_time": "0:11:33", "remaining_time": "0:01:11"}
|
||||
{"current_steps": 243, "total_steps": 267, "loss": 0.0907, "accuracy": 1.0, "lr": 1.5920961151468326e-08, "epoch": 2.7303370786516856, "percentage": 91.01, "elapsed_time": "0:11:36", "remaining_time": "0:01:08"}
|
||||
{"current_steps": 244, "total_steps": 267, "loss": 0.0197, "accuracy": 1.0, "lr": 1.468304511145394e-08, "epoch": 2.741573033707865, "percentage": 91.39, "elapsed_time": "0:11:39", "remaining_time": "0:01:05"}
|
||||
{"current_steps": 245, "total_steps": 267, "loss": 0.0983, "accuracy": 1.0, "lr": 1.349401666284401e-08, "epoch": 2.752808988764045, "percentage": 91.76, "elapsed_time": "0:11:42", "remaining_time": "0:01:03"}
|
||||
{"current_steps": 246, "total_steps": 267, "loss": 0.0266, "accuracy": 1.0, "lr": 1.2354079539542084e-08, "epoch": 2.764044943820225, "percentage": 92.13, "elapsed_time": "0:11:45", "remaining_time": "0:01:00"}
|
||||
{"current_steps": 247, "total_steps": 267, "loss": 0.0912, "accuracy": 1.0, "lr": 1.1263429063905849e-08, "epoch": 2.7752808988764044, "percentage": 92.51, "elapsed_time": "0:11:48", "remaining_time": "0:00:57"}
|
||||
{"current_steps": 248, "total_steps": 267, "loss": 0.0238, "accuracy": 1.0, "lr": 1.0222252113279539e-08, "epoch": 2.7865168539325844, "percentage": 92.88, "elapsed_time": "0:11:51", "remaining_time": "0:00:54"}
|
||||
{"current_steps": 249, "total_steps": 267, "loss": 0.0903, "accuracy": 1.0, "lr": 9.230727087973711e-09, "epoch": 2.797752808988764, "percentage": 93.26, "elapsed_time": "0:11:54", "remaining_time": "0:00:51"}
|
||||
{"current_steps": 250, "total_steps": 267, "loss": 0.029, "accuracy": 1.0, "lr": 8.289023880697032e-09, "epoch": 2.808988764044944, "percentage": 93.63, "elapsed_time": "0:11:56", "remaining_time": "0:00:48"}
|
||||
{"current_steps": 251, "total_steps": 267, "loss": 0.0787, "accuracy": 1.0, "lr": 7.3973038474462015e-09, "epoch": 2.8202247191011236, "percentage": 94.01, "elapsed_time": "0:11:59", "remaining_time": "0:00:45"}
|
||||
{"current_steps": 252, "total_steps": 267, "loss": 0.0279, "accuracy": 1.0, "lr": 6.555719779858293e-09, "epoch": 2.831460674157303, "percentage": 94.38, "elapsed_time": "0:12:02", "remaining_time": "0:00:42"}
|
||||
{"current_steps": 253, "total_steps": 267, "loss": 0.0838, "accuracy": 1.0, "lr": 5.76441587903087e-09, "epoch": 2.842696629213483, "percentage": 94.76, "elapsed_time": "0:12:04", "remaining_time": "0:00:40"}
|
||||
{"current_steps": 254, "total_steps": 267, "loss": 0.0423, "accuracy": 1.0, "lr": 5.023527730813648e-09, "epoch": 2.853932584269663, "percentage": 95.13, "elapsed_time": "0:12:07", "remaining_time": "0:00:37"}
|
||||
{"current_steps": 255, "total_steps": 267, "loss": 0.1052, "accuracy": 1.0, "lr": 4.333182282576675e-09, "epoch": 2.865168539325843, "percentage": 95.51, "elapsed_time": "0:12:09", "remaining_time": "0:00:34"}
|
||||
{"current_steps": 256, "total_steps": 267, "loss": 0.0598, "accuracy": 0.9375, "lr": 3.693497821458702e-09, "epoch": 2.8764044943820224, "percentage": 95.88, "elapsed_time": "0:12:13", "remaining_time": "0:00:31"}
|
||||
{"current_steps": 257, "total_steps": 267, "loss": 0.1037, "accuracy": 0.96875, "lr": 3.1045839540989273e-09, "epoch": 2.8876404494382024, "percentage": 96.25, "elapsed_time": "0:12:15", "remaining_time": "0:00:28"}
|
||||
{"current_steps": 258, "total_steps": 267, "loss": 0.0159, "accuracy": 1.0, "lr": 2.5665415878568854e-09, "epoch": 2.898876404494382, "percentage": 96.63, "elapsed_time": "0:12:18", "remaining_time": "0:00:25"}
|
||||
{"current_steps": 259, "total_steps": 267, "loss": 0.0747, "accuracy": 1.0, "lr": 2.079462913522112e-09, "epoch": 2.9101123595505616, "percentage": 97.0, "elapsed_time": "0:12:22", "remaining_time": "0:00:22"}
|
||||
{"current_steps": 260, "total_steps": 267, "loss": 0.0581, "accuracy": 1.0, "lr": 1.643431389518013e-09, "epoch": 2.9213483146067416, "percentage": 97.38, "elapsed_time": "0:12:24", "remaining_time": "0:00:20"}
|
||||
{"current_steps": 261, "total_steps": 267, "loss": 0.0906, "accuracy": 1.0, "lr": 1.2585217276015025e-09, "epoch": 2.932584269662921, "percentage": 97.75, "elapsed_time": "0:12:26", "remaining_time": "0:00:17"}
|
||||
{"current_steps": 262, "total_steps": 267, "loss": 0.0164, "accuracy": 1.0, "lr": 9.247998800616108e-10, "epoch": 2.943820224719101, "percentage": 98.13, "elapsed_time": "0:12:30", "remaining_time": "0:00:14"}
|
||||
{"current_steps": 263, "total_steps": 267, "loss": 0.0849, "accuracy": 1.0, "lr": 6.423230284189562e-10, "epoch": 2.955056179775281, "percentage": 98.5, "elapsed_time": "0:12:33", "remaining_time": "0:00:11"}
|
||||
{"current_steps": 264, "total_steps": 267, "loss": 0.0623, "accuracy": 0.96875, "lr": 4.1113957362785e-10, "epoch": 2.966292134831461, "percentage": 98.88, "elapsed_time": "0:12:35", "remaining_time": "0:00:08"}
|
||||
{"current_steps": 265, "total_steps": 267, "loss": 0.0743, "accuracy": 1.0, "lr": 2.312891277831297e-10, "epoch": 2.9775280898876404, "percentage": 99.25, "elapsed_time": "0:12:38", "remaining_time": "0:00:05"}
|
||||
{"current_steps": 266, "total_steps": 267, "loss": 0.0336, "accuracy": 1.0, "lr": 1.0280250733282203e-10, "epoch": 2.98876404494382, "percentage": 99.63, "elapsed_time": "0:12:40", "remaining_time": "0:00:02"}
|
||||
{"current_steps": 267, "total_steps": 267, "loss": 0.0814, "accuracy": 1.0, "lr": 2.570172779789992e-11, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:12:43", "remaining_time": "0:00:00"}
|
||||
{"current_steps": 267, "total_steps": 267, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:14:28", "remaining_time": "0:00:00"}
|
||||
4449
trainer_state.json
Normal file
4449
trainer_state.json
Normal file
File diff suppressed because it is too large
Load Diff
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 sha256:59cd0418a47b169a821745759f4790439e6942342e9dc9933a709074803faa38
|
||||
size 7352
|
||||
BIN
training_dpo_losses.png
Normal file
BIN
training_dpo_losses.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 53 KiB |
BIN
training_loss.png
Normal file
BIN
training_loss.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 51 KiB |
BIN
training_mlc_losses.png
Normal file
BIN
training_mlc_losses.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 34 KiB |
BIN
training_rewards_accuracies.png
Normal file
BIN
training_rewards_accuracies.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 44 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