初始化项目，由ModelHub XC社区提供模型
Model: KKHYA/qwen3-14b-fft-if 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
|
||||
61
README.md
Normal file
61
README.md
Normal file
@@ -0,0 +1,61 @@
|
||||
---
|
||||
library_name: transformers
|
||||
license: apache-2.0
|
||||
base_model: Qwen/Qwen3-14B
|
||||
tags:
|
||||
- llama-factory
|
||||
- full
|
||||
- generated_from_trainer
|
||||
model-index:
|
||||
- name: qwen3-14b-fft-if
|
||||
results: []
|
||||
---
|
||||
|
||||
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
||||
should probably proofread and complete it, then remove this comment. -->
|
||||
|
||||
# qwen3-14b-fft-if
|
||||
|
||||
This model is a fine-tuned version of [Qwen/Qwen3-14B](https://huggingface.co/Qwen/Qwen3-14B) on the mft_tulu3_personas_if, the mft_oasst1, the mft_oasst2, the mft_coconot, the mft_aya and the mft_daring_anteater datasets.
|
||||
|
||||
## Model description
|
||||
|
||||
More information needed
|
||||
|
||||
## Intended uses & limitations
|
||||
|
||||
More information needed
|
||||
|
||||
## Training and evaluation data
|
||||
|
||||
More information needed
|
||||
|
||||
## Training procedure
|
||||
|
||||
### Training hyperparameters
|
||||
|
||||
The following hyperparameters were used during training:
|
||||
- learning_rate: 1e-05
|
||||
- train_batch_size: 4
|
||||
- eval_batch_size: 8
|
||||
- seed: 42
|
||||
- distributed_type: multi-GPU
|
||||
- num_devices: 8
|
||||
- gradient_accumulation_steps: 4
|
||||
- total_train_batch_size: 128
|
||||
- total_eval_batch_size: 64
|
||||
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.95) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
||||
- lr_scheduler_type: cosine
|
||||
- lr_scheduler_warmup_ratio: 0.1
|
||||
- num_epochs: 2.0
|
||||
|
||||
### Training results
|
||||
|
||||
|
||||
|
||||
### Framework versions
|
||||
|
||||
- Transformers 4.57.6
|
||||
- Pytorch 2.8.0+cu128
|
||||
- Datasets 3.6.0
|
||||
- Tokenizers 0.22.2
|
||||
28
added_tokens.json
Normal file
28
added_tokens.json
Normal file
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"</think>": 151668,
|
||||
"</tool_call>": 151658,
|
||||
"</tool_response>": 151666,
|
||||
"<think>": 151667,
|
||||
"<tool_call>": 151657,
|
||||
"<tool_response>": 151665,
|
||||
"<|box_end|>": 151649,
|
||||
"<|box_start|>": 151648,
|
||||
"<|endoftext|>": 151643,
|
||||
"<|file_sep|>": 151664,
|
||||
"<|fim_middle|>": 151660,
|
||||
"<|fim_pad|>": 151662,
|
||||
"<|fim_prefix|>": 151659,
|
||||
"<|fim_suffix|>": 151661,
|
||||
"<|im_end|>": 151645,
|
||||
"<|im_start|>": 151644,
|
||||
"<|image_pad|>": 151655,
|
||||
"<|object_ref_end|>": 151647,
|
||||
"<|object_ref_start|>": 151646,
|
||||
"<|quad_end|>": 151651,
|
||||
"<|quad_start|>": 151650,
|
||||
"<|repo_name|>": 151663,
|
||||
"<|video_pad|>": 151656,
|
||||
"<|vision_end|>": 151653,
|
||||
"<|vision_pad|>": 151654,
|
||||
"<|vision_start|>": 151652
|
||||
}
|
||||
8
all_results.json
Normal file
8
all_results.json
Normal file
@@ -0,0 +1,8 @@
|
||||
{
|
||||
"epoch": 2.0,
|
||||
"total_flos": 1.3931784786122113e+19,
|
||||
"train_loss": 0.5872682382094778,
|
||||
"train_runtime": 12619.0484,
|
||||
"train_samples_per_second": 8.865,
|
||||
"train_steps_per_second": 0.069
|
||||
}
|
||||
89
chat_template.jinja
Normal file
89
chat_template.jinja
Normal file
@@ -0,0 +1,89 @@
|
||||
{%- if tools %}
|
||||
{{- '<|im_start|>system\n' }}
|
||||
{%- if messages[0].role == 'system' %}
|
||||
{{- messages[0].content + '\n\n' }}
|
||||
{%- endif %}
|
||||
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
||||
{%- for tool in tools %}
|
||||
{{- "\n" }}
|
||||
{{- tool | tojson }}
|
||||
{%- endfor %}
|
||||
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
||||
{%- else %}
|
||||
{%- if messages[0].role == 'system' %}
|
||||
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
||||
{%- for message in messages[::-1] %}
|
||||
{%- set index = (messages|length - 1) - loop.index0 %}
|
||||
{%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
||||
{%- set ns.multi_step_tool = false %}
|
||||
{%- set ns.last_query_index = index %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- for message in messages %}
|
||||
{%- if message.content is string %}
|
||||
{%- set content = message.content %}
|
||||
{%- else %}
|
||||
{%- set content = '' %}
|
||||
{%- endif %}
|
||||
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
||||
{%- elif message.role == "assistant" %}
|
||||
{%- set reasoning_content = '' %}
|
||||
{%- if message.reasoning_content is string %}
|
||||
{%- set reasoning_content = message.reasoning_content %}
|
||||
{%- else %}
|
||||
{%- if '</think>' in content %}
|
||||
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
||||
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- if loop.index0 > ns.last_query_index %}
|
||||
{%- if loop.last or (not loop.last and reasoning_content) %}
|
||||
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||
{%- endif %}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||
{%- endif %}
|
||||
{%- if message.tool_calls %}
|
||||
{%- for tool_call in message.tool_calls %}
|
||||
{%- if (loop.first and content) or (not loop.first) %}
|
||||
{{- '\n' }}
|
||||
{%- endif %}
|
||||
{%- if tool_call.function %}
|
||||
{%- set tool_call = tool_call.function %}
|
||||
{%- endif %}
|
||||
{{- '<tool_call>\n{"name": "' }}
|
||||
{{- tool_call.name }}
|
||||
{{- '", "arguments": ' }}
|
||||
{%- if tool_call.arguments is string %}
|
||||
{{- tool_call.arguments }}
|
||||
{%- else %}
|
||||
{{- tool_call.arguments | tojson }}
|
||||
{%- endif %}
|
||||
{{- '}\n</tool_call>' }}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- elif message.role == "tool" %}
|
||||
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
||||
{{- '<|im_start|>user' }}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_response>\n' }}
|
||||
{{- content }}
|
||||
{{- '\n</tool_response>' }}
|
||||
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- if add_generation_prompt %}
|
||||
{{- '<|im_start|>assistant\n' }}
|
||||
{%- if enable_thinking is defined and enable_thinking is false %}
|
||||
{{- '<think>\n\n</think>\n\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
79
config.json
Normal file
79
config.json
Normal file
@@ -0,0 +1,79 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen3ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 151645,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 5120,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 17408,
|
||||
"layer_types": [
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention"
|
||||
],
|
||||
"masked_layers": null,
|
||||
"max_position_embeddings": 40960,
|
||||
"max_window_layers": 40,
|
||||
"model_type": "qwen3",
|
||||
"num_attention_heads": 40,
|
||||
"num_hidden_layers": 40,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 151643,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 1000000,
|
||||
"sliding_window": null,
|
||||
"sparsity_attn": null,
|
||||
"sparsity_mlp": null,
|
||||
"subnet_mode": null,
|
||||
"subnet_type": null,
|
||||
"threshold_attn": null,
|
||||
"threshold_mlp": null,
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "4.57.6",
|
||||
"use_cache": false,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
12
generation_config.json
Normal file
12
generation_config.json
Normal file
@@ -0,0 +1,12 @@
|
||||
{
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"pad_token_id": 151643,
|
||||
"temperature": 0.6,
|
||||
"top_k": 20,
|
||||
"top_p": 0.95,
|
||||
"transformers_version": "4.57.6"
|
||||
}
|
||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model-00001-of-00006.safetensors
Normal file
3
model-00001-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5685526345437ba992dbd3a39819da259b74523dc5a1882fd4df1beefb110b60
|
||||
size 4984780784
|
||||
3
model-00002-of-00006.safetensors
Normal file
3
model-00002-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0b03badc291eca8f88d43c65a441c5b2902204771ae6f005e7eda85b647e8a9c
|
||||
size 4980892048
|
||||
3
model-00003-of-00006.safetensors
Normal file
3
model-00003-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f89067dd96d77ebecb6a203b06769d45c8a1e44991c4f566921ffea4f2f65b4c
|
||||
size 4928485104
|
||||
3
model-00004-of-00006.safetensors
Normal file
3
model-00004-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:582772e5d983efc7b20c08bc399610347381810622602adfadd6f30c5f289ad5
|
||||
size 4980892112
|
||||
3
model-00005-of-00006.safetensors
Normal file
3
model-00005-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9de966f94fb8292bff4aa5a4276dea3a1dcefb80f1bfeaa0d7cefb21ea45d968
|
||||
size 4928485104
|
||||
3
model-00006-of-00006.safetensors
Normal file
3
model-00006-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:66c5964e494cd7c42debe0063f4984e77571a9acaddf45db15debf8b4fbcd9d8
|
||||
size 4733130504
|
||||
451
model.safetensors.index.json
Normal file
451
model.safetensors.index.json
Normal file
@@ -0,0 +1,451 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_parameters": 14768307200,
|
||||
"total_size": 29536614400
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00006-of-00006.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.12.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.12.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.19.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.19.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.20.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.20.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.22.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.22.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.23.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.23.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.24.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.24.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.25.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.25.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.26.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.26.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.27.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.27.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.28.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.28.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.29.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.29.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.30.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.30.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.31.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.31.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.32.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.32.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.33.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.33.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.34.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.34.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.35.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.35.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.36.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.36.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.36.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.36.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.36.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.36.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.36.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.36.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.36.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.36.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.36.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.37.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.37.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.37.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.37.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.37.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.37.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.37.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.37.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.37.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.37.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.37.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.38.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.38.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.38.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.38.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.38.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.38.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.38.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.38.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.39.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.39.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.39.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.39.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.39.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.39.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.39.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.39.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.5.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.norm.weight": "model-00006-of-00006.safetensors"
|
||||
}
|
||||
}
|
||||
42
qwen3_14b_if_fft_20260524_070933.log
Normal file
42
qwen3_14b_if_fft_20260524_070933.log
Normal file
@@ -0,0 +1,42 @@
|
||||
==== STARTING EXPERIMENT: qwen3_14b_if_fft ====
|
||||
Log File: saves/qwen3_14b/if/fft/qwen3_14b_if_fft_20260524_070933.log
|
||||
HF Hub: https://huggingface.co/KKHYA/qwen3-14b-fft-if
|
||||
Timestamp: 2026-05-24 07:09:33
|
||||
=====================================
|
||||
[INFO|2026-05-24 07:09:38] llamafactory.launcher:144 >> Initializing 8 distributed tasks at: 127.0.0.1:56807
|
||||
W0524 07:09:40.018000 327143 site-packages/torch/distributed/run.py:851]
|
||||
W0524 07:09:40.018000 327143 site-packages/torch/distributed/run.py:851] *****************************************
|
||||
W0524 07:09:40.018000 327143 site-packages/torch/distributed/run.py:851] Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.
|
||||
W0524 07:09:40.018000 327143 site-packages/torch/distributed/run.py:851] *****************************************
|
||||
/home/ubuntu/miniconda3/envs/lmfact/lib/python3.11/site-packages/jieba/_compat.py:18: UserWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81.
|
||||
import pkg_resources
|
||||
/home/ubuntu/miniconda3/envs/lmfact/lib/python3.11/site-packages/jieba/_compat.py:18: UserWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81.
|
||||
import pkg_resources
|
||||
/home/ubuntu/miniconda3/envs/lmfact/lib/python3.11/site-packages/jieba/_compat.py:18: UserWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81.
|
||||
import pkg_resources
|
||||
/home/ubuntu/miniconda3/envs/lmfact/lib/python3.11/site-packages/jieba/_compat.py:18: UserWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81.
|
||||
import pkg_resources
|
||||
/home/ubuntu/miniconda3/envs/lmfact/lib/python3.11/site-packages/jieba/_compat.py:18: UserWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81.
|
||||
import pkg_resources
|
||||
/home/ubuntu/miniconda3/envs/lmfact/lib/python3.11/site-packages/jieba/_compat.py:18: UserWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81.
|
||||
import pkg_resources
|
||||
/home/ubuntu/miniconda3/envs/lmfact/lib/python3.11/site-packages/jieba/_compat.py:18: UserWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81.
|
||||
import pkg_resources
|
||||
/home/ubuntu/miniconda3/envs/lmfact/lib/python3.11/site-packages/jieba/_compat.py:18: UserWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81.
|
||||
import pkg_resources
|
||||
warmup_ratio is deprecated and will be removed in v5.2. Use `warmup_steps` instead.
|
||||
warmup_ratio is deprecated and will be removed in v5.2. Use `warmup_steps` instead.
|
||||
warmup_ratio is deprecated and will be removed in v5.2. Use `warmup_steps` instead.
|
||||
warmup_ratio is deprecated and will be removed in v5.2. Use `warmup_steps` instead.
|
||||
warmup_ratio is deprecated and will be removed in v5.2. Use `warmup_steps` instead.
|
||||
warmup_ratio is deprecated and will be removed in v5.2. Use `warmup_steps` instead.
|
||||
warmup_ratio is deprecated and will be removed in v5.2. Use `warmup_steps` instead.
|
||||
warmup_ratio is deprecated and will be removed in v5.2. Use `warmup_steps` instead.
|
||||
[W524 07:09:48.158543577 ProcessGroupNCCL.cpp:932] Warning: TORCH_NCCL_AVOID_RECORD_STREAMS is the default now, this environment variable is thus deprecated. (function operator())
|
||||
[W524 07:09:48.228904983 ProcessGroupNCCL.cpp:932] Warning: TORCH_NCCL_AVOID_RECORD_STREAMS is the default now, this environment variable is thus deprecated. (function operator())
|
||||
[W524 07:09:48.250882253 ProcessGroupNCCL.cpp:932] Warning: TORCH_NCCL_AVOID_RECORD_STREAMS is the default now, this environment variable is thus deprecated. (function operator())
|
||||
[W524 07:09:48.257095700 ProcessGroupNCCL.cpp:932] Warning: TORCH_NCCL_AVOID_RECORD_STREAMS is the default now, this environment variable is thus deprecated. (function operator())
|
||||
[W524 07:09:48.274541210 ProcessGroupNCCL.cpp:932] Warning: TORCH_NCCL_AVOID_RECORD_STREAMS is the default now, this environment variable is thus deprecated. (function operator())
|
||||
[W524 07:09:49.302269372 ProcessGroupNCCL.cpp:932] Warning: TORCH_NCCL_AVOID_RECORD_STREAMS is the default now, this environment variable is thus deprecated. (function operator())
|
||||
[W524 07:09:49.357624054 ProcessGroupNCCL.cpp:932] Warning: TORCH_NCCL_AVOID_RECORD_STREAMS is the default now, this environment variable is thus deprecated. (function operator())
|
||||
[W524 07:09:49.526457819 ProcessGroupNCCL.cpp:932] Warning: TORCH_NCCL_AVOID_RECORD_STREAMS is the default now, this environment variable is thus deprecated. (function operator())
|
||||
7006
qwen3_14b_if_fft_20260524_090125.log
Normal file
7006
qwen3_14b_if_fft_20260524_090125.log
Normal file
File diff suppressed because one or more lines are too long
31
special_tokens_map.json
Normal file
31
special_tokens_map.json
Normal file
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"eos_token": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
BIN
tokenizer.json
(Stored with Git LFS)
Normal file
BIN
tokenizer.json
(Stored with Git LFS)
Normal file
Binary file not shown.
240
tokenizer_config.json
Normal file
240
tokenizer_config.json
Normal file
@@ -0,0 +1,240 @@
|
||||
{
|
||||
"add_bos_token": false,
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"151643": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151644": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151645": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151646": {
|
||||
"content": "<|object_ref_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151647": {
|
||||
"content": "<|object_ref_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151648": {
|
||||
"content": "<|box_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151649": {
|
||||
"content": "<|box_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151650": {
|
||||
"content": "<|quad_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151651": {
|
||||
"content": "<|quad_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151652": {
|
||||
"content": "<|vision_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151653": {
|
||||
"content": "<|vision_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151654": {
|
||||
"content": "<|vision_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151655": {
|
||||
"content": "<|image_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151656": {
|
||||
"content": "<|video_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151657": {
|
||||
"content": "<tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151658": {
|
||||
"content": "</tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151659": {
|
||||
"content": "<|fim_prefix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151660": {
|
||||
"content": "<|fim_middle|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151661": {
|
||||
"content": "<|fim_suffix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151662": {
|
||||
"content": "<|fim_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151663": {
|
||||
"content": "<|repo_name|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151664": {
|
||||
"content": "<|file_sep|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151665": {
|
||||
"content": "<tool_response>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151666": {
|
||||
"content": "</tool_response>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151667": {
|
||||
"content": "<think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151668": {
|
||||
"content": "</think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"bos_token": null,
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": {},
|
||||
"model_max_length": 131072,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"padding_side": "right",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
8
train_results.json
Normal file
8
train_results.json
Normal file
@@ -0,0 +1,8 @@
|
||||
{
|
||||
"epoch": 2.0,
|
||||
"total_flos": 1.3931784786122113e+19,
|
||||
"train_loss": 0.5872682382094778,
|
||||
"train_runtime": 12619.0484,
|
||||
"train_samples_per_second": 8.865,
|
||||
"train_steps_per_second": 0.069
|
||||
}
|
||||
88
trainer_log.jsonl
Normal file
88
trainer_log.jsonl
Normal file
@@ -0,0 +1,88 @@
|
||||
{"current_steps": 10, "total_steps": 874, "loss": 0.9488, "lr": 1.0227272727272729e-06, "epoch": 0.02288329519450801, "percentage": 1.14, "elapsed_time": "0:02:33", "remaining_time": "3:40:55"}
|
||||
{"current_steps": 20, "total_steps": 874, "loss": 0.8935, "lr": 2.1590909090909092e-06, "epoch": 0.04576659038901602, "percentage": 2.29, "elapsed_time": "0:04:56", "remaining_time": "3:30:57"}
|
||||
{"current_steps": 30, "total_steps": 874, "loss": 0.8345, "lr": 3.2954545454545456e-06, "epoch": 0.06864988558352403, "percentage": 3.43, "elapsed_time": "0:07:25", "remaining_time": "3:28:57"}
|
||||
{"current_steps": 40, "total_steps": 874, "loss": 0.7483, "lr": 4.4318181818181824e-06, "epoch": 0.09153318077803203, "percentage": 4.58, "elapsed_time": "0:09:54", "remaining_time": "3:26:28"}
|
||||
{"current_steps": 50, "total_steps": 874, "loss": 0.7619, "lr": 5.568181818181818e-06, "epoch": 0.11441647597254005, "percentage": 5.72, "elapsed_time": "0:12:18", "remaining_time": "3:22:54"}
|
||||
{"current_steps": 60, "total_steps": 874, "loss": 0.7492, "lr": 6.704545454545454e-06, "epoch": 0.13729977116704806, "percentage": 6.86, "elapsed_time": "0:14:40", "remaining_time": "3:19:07"}
|
||||
{"current_steps": 70, "total_steps": 874, "loss": 0.7519, "lr": 7.840909090909091e-06, "epoch": 0.16018306636155608, "percentage": 8.01, "elapsed_time": "0:17:03", "remaining_time": "3:15:54"}
|
||||
{"current_steps": 80, "total_steps": 874, "loss": 0.7103, "lr": 8.977272727272727e-06, "epoch": 0.18306636155606407, "percentage": 9.15, "elapsed_time": "0:19:25", "remaining_time": "3:12:48"}
|
||||
{"current_steps": 90, "total_steps": 874, "loss": 0.7069, "lr": 9.999960061285353e-06, "epoch": 0.20594965675057209, "percentage": 10.3, "elapsed_time": "0:21:47", "remaining_time": "3:09:51"}
|
||||
{"current_steps": 100, "total_steps": 874, "loss": 0.7032, "lr": 9.995168187508393e-06, "epoch": 0.2288329519450801, "percentage": 11.44, "elapsed_time": "0:24:07", "remaining_time": "3:06:43"}
|
||||
{"current_steps": 110, "total_steps": 874, "loss": 0.7216, "lr": 9.98239734155262e-06, "epoch": 0.2517162471395881, "percentage": 12.59, "elapsed_time": "0:26:35", "remaining_time": "3:04:38"}
|
||||
{"current_steps": 120, "total_steps": 874, "loss": 0.7085, "lr": 9.961667922776125e-06, "epoch": 0.2745995423340961, "percentage": 13.73, "elapsed_time": "0:28:56", "remaining_time": "3:01:53"}
|
||||
{"current_steps": 130, "total_steps": 874, "loss": 0.7104, "lr": 9.93301304306814e-06, "epoch": 0.2974828375286041, "percentage": 14.87, "elapsed_time": "0:31:23", "remaining_time": "2:59:39"}
|
||||
{"current_steps": 140, "total_steps": 874, "loss": 0.6963, "lr": 9.896478473958147e-06, "epoch": 0.32036613272311215, "percentage": 16.02, "elapsed_time": "0:33:40", "remaining_time": "2:56:33"}
|
||||
{"current_steps": 150, "total_steps": 874, "loss": 0.6751, "lr": 9.852122573503283e-06, "epoch": 0.34324942791762014, "percentage": 17.16, "elapsed_time": "0:36:05", "remaining_time": "2:54:11"}
|
||||
{"current_steps": 160, "total_steps": 874, "loss": 0.6757, "lr": 9.800016193070789e-06, "epoch": 0.36613272311212813, "percentage": 18.31, "elapsed_time": "0:38:22", "remaining_time": "2:51:14"}
|
||||
{"current_steps": 170, "total_steps": 874, "loss": 0.7119, "lr": 9.740242564164433e-06, "epoch": 0.3890160183066362, "percentage": 19.45, "elapsed_time": "0:40:40", "remaining_time": "2:48:27"}
|
||||
{"current_steps": 180, "total_steps": 874, "loss": 0.6598, "lr": 9.672897165475657e-06, "epoch": 0.41189931350114417, "percentage": 20.59, "elapsed_time": "0:43:06", "remaining_time": "2:46:14"}
|
||||
{"current_steps": 190, "total_steps": 874, "loss": 0.713, "lr": 9.59808757037183e-06, "epoch": 0.43478260869565216, "percentage": 21.74, "elapsed_time": "0:45:36", "remaining_time": "2:44:10"}
|
||||
{"current_steps": 200, "total_steps": 874, "loss": 0.6708, "lr": 9.515933275065218e-06, "epoch": 0.4576659038901602, "percentage": 22.88, "elapsed_time": "0:47:48", "remaining_time": "2:41:06"}
|
||||
{"current_steps": 210, "total_steps": 874, "loss": 0.6929, "lr": 9.426565507737139e-06, "epoch": 0.4805491990846682, "percentage": 24.03, "elapsed_time": "0:50:15", "remaining_time": "2:38:53"}
|
||||
{"current_steps": 220, "total_steps": 874, "loss": 0.6417, "lr": 9.330127018922195e-06, "epoch": 0.5034324942791762, "percentage": 25.17, "elapsed_time": "0:52:39", "remaining_time": "2:36:31"}
|
||||
{"current_steps": 230, "total_steps": 874, "loss": 0.6499, "lr": 9.226771853487411e-06, "epoch": 0.5263157894736842, "percentage": 26.32, "elapsed_time": "0:54:59", "remaining_time": "2:33:58"}
|
||||
{"current_steps": 240, "total_steps": 874, "loss": 0.6627, "lr": 9.116665104570513e-06, "epoch": 0.5491990846681922, "percentage": 27.46, "elapsed_time": "0:57:25", "remaining_time": "2:31:42"}
|
||||
{"current_steps": 250, "total_steps": 874, "loss": 0.6766, "lr": 8.999982649870377e-06, "epoch": 0.5720823798627003, "percentage": 28.6, "elapsed_time": "0:59:53", "remaining_time": "2:29:29"}
|
||||
{"current_steps": 260, "total_steps": 874, "loss": 0.6843, "lr": 8.876910870710885e-06, "epoch": 0.5949656750572082, "percentage": 29.75, "elapsed_time": "1:02:22", "remaining_time": "2:27:17"}
|
||||
{"current_steps": 270, "total_steps": 874, "loss": 0.6844, "lr": 8.747646354326948e-06, "epoch": 0.6178489702517163, "percentage": 30.89, "elapsed_time": "1:04:34", "remaining_time": "2:24:27"}
|
||||
{"current_steps": 280, "total_steps": 874, "loss": 0.6511, "lr": 8.612395579848244e-06, "epoch": 0.6407322654462243, "percentage": 32.04, "elapsed_time": "1:07:01", "remaining_time": "2:22:11"}
|
||||
{"current_steps": 290, "total_steps": 874, "loss": 0.6631, "lr": 8.47137458848224e-06, "epoch": 0.6636155606407322, "percentage": 33.18, "elapsed_time": "1:09:22", "remaining_time": "2:19:42"}
|
||||
{"current_steps": 300, "total_steps": 874, "loss": 0.6871, "lr": 8.324808638423353e-06, "epoch": 0.6864988558352403, "percentage": 34.32, "elapsed_time": "1:11:45", "remaining_time": "2:17:18"}
|
||||
{"current_steps": 310, "total_steps": 874, "loss": 0.6249, "lr": 8.172931845039471e-06, "epoch": 0.7093821510297483, "percentage": 35.47, "elapsed_time": "1:14:09", "remaining_time": "2:14:55"}
|
||||
{"current_steps": 320, "total_steps": 874, "loss": 0.6492, "lr": 8.01598680691057e-06, "epoch": 0.7322654462242563, "percentage": 36.61, "elapsed_time": "1:16:34", "remaining_time": "2:12:33"}
|
||||
{"current_steps": 330, "total_steps": 874, "loss": 0.6619, "lr": 7.854224218316761e-06, "epoch": 0.7551487414187643, "percentage": 37.76, "elapsed_time": "1:18:44", "remaining_time": "2:09:48"}
|
||||
{"current_steps": 340, "total_steps": 874, "loss": 0.6729, "lr": 7.687902468794803e-06, "epoch": 0.7780320366132724, "percentage": 38.9, "elapsed_time": "1:21:19", "remaining_time": "2:07:43"}
|
||||
{"current_steps": 350, "total_steps": 874, "loss": 0.631, "lr": 7.517287230402639e-06, "epoch": 0.8009153318077803, "percentage": 40.05, "elapsed_time": "1:23:32", "remaining_time": "2:05:03"}
|
||||
{"current_steps": 360, "total_steps": 874, "loss": 0.6195, "lr": 7.342651033351325e-06, "epoch": 0.8237986270022883, "percentage": 41.19, "elapsed_time": "1:25:47", "remaining_time": "2:02:29"}
|
||||
{"current_steps": 370, "total_steps": 874, "loss": 0.6352, "lr": 7.164272830682161e-06, "epoch": 0.8466819221967964, "percentage": 42.33, "elapsed_time": "1:28:08", "remaining_time": "2:00:04"}
|
||||
{"current_steps": 380, "total_steps": 874, "loss": 0.6549, "lr": 6.9824375526843705e-06, "epoch": 0.8695652173913043, "percentage": 43.48, "elapsed_time": "1:30:35", "remaining_time": "1:57:45"}
|
||||
{"current_steps": 390, "total_steps": 874, "loss": 0.6593, "lr": 6.797435651765123e-06, "epoch": 0.8924485125858124, "percentage": 44.62, "elapsed_time": "1:32:58", "remaining_time": "1:55:23"}
|
||||
{"current_steps": 400, "total_steps": 874, "loss": 0.6141, "lr": 6.609562638498845e-06, "epoch": 0.9153318077803204, "percentage": 45.77, "elapsed_time": "1:35:36", "remaining_time": "1:53:17"}
|
||||
{"current_steps": 410, "total_steps": 874, "loss": 0.6194, "lr": 6.419118609596948e-06, "epoch": 0.9382151029748284, "percentage": 46.91, "elapsed_time": "1:37:59", "remaining_time": "1:50:53"}
|
||||
{"current_steps": 420, "total_steps": 874, "loss": 0.6406, "lr": 6.2264077685519246e-06, "epoch": 0.9610983981693364, "percentage": 48.05, "elapsed_time": "1:40:16", "remaining_time": "1:48:23"}
|
||||
{"current_steps": 430, "total_steps": 874, "loss": 0.6515, "lr": 6.031737939721538e-06, "epoch": 0.9839816933638444, "percentage": 49.2, "elapsed_time": "1:42:43", "remaining_time": "1:46:03"}
|
||||
{"current_steps": 440, "total_steps": 874, "loss": 0.6155, "lr": 5.835420076629273e-06, "epoch": 1.0068649885583525, "percentage": 50.34, "elapsed_time": "1:44:57", "remaining_time": "1:43:31"}
|
||||
{"current_steps": 450, "total_steps": 874, "loss": 0.4827, "lr": 5.6377677652664345e-06, "epoch": 1.0297482837528604, "percentage": 51.49, "elapsed_time": "1:47:26", "remaining_time": "1:41:13"}
|
||||
{"current_steps": 460, "total_steps": 874, "loss": 0.5285, "lr": 5.439096723189316e-06, "epoch": 1.0526315789473684, "percentage": 52.63, "elapsed_time": "1:49:58", "remaining_time": "1:38:58"}
|
||||
{"current_steps": 470, "total_steps": 874, "loss": 0.4976, "lr": 5.239724295211541e-06, "epoch": 1.0755148741418765, "percentage": 53.78, "elapsed_time": "1:52:23", "remaining_time": "1:36:36"}
|
||||
{"current_steps": 480, "total_steps": 874, "loss": 0.4919, "lr": 5.03996894649711e-06, "epoch": 1.0983981693363845, "percentage": 54.92, "elapsed_time": "1:54:50", "remaining_time": "1:34:16"}
|
||||
{"current_steps": 490, "total_steps": 874, "loss": 0.4691, "lr": 4.840149753863887e-06, "epoch": 1.1212814645308924, "percentage": 56.06, "elapsed_time": "1:57:08", "remaining_time": "1:31:47"}
|
||||
{"current_steps": 500, "total_steps": 874, "loss": 0.4929, "lr": 4.640585896110054e-06, "epoch": 1.1441647597254005, "percentage": 57.21, "elapsed_time": "1:59:42", "remaining_time": "1:29:32"}
|
||||
{"current_steps": 510, "total_steps": 874, "loss": 0.4885, "lr": 4.441596144177681e-06, "epoch": 1.1670480549199085, "percentage": 58.35, "elapsed_time": "2:02:41", "remaining_time": "1:27:34"}
|
||||
{"current_steps": 520, "total_steps": 874, "loss": 0.4682, "lr": 4.243498351967761e-06, "epoch": 1.1899313501144164, "percentage": 59.5, "elapsed_time": "2:05:04", "remaining_time": "1:25:08"}
|
||||
{"current_steps": 530, "total_steps": 874, "loss": 0.4791, "lr": 4.046608948620098e-06, "epoch": 1.2128146453089246, "percentage": 60.64, "elapsed_time": "2:07:30", "remaining_time": "1:22:45"}
|
||||
{"current_steps": 540, "total_steps": 874, "loss": 0.4732, "lr": 3.8512424330689855e-06, "epoch": 1.2356979405034325, "percentage": 61.78, "elapsed_time": "2:09:51", "remaining_time": "1:20:19"}
|
||||
{"current_steps": 550, "total_steps": 874, "loss": 0.4849, "lr": 3.657710871682115e-06, "epoch": 1.2585812356979404, "percentage": 62.93, "elapsed_time": "2:12:12", "remaining_time": "1:17:53"}
|
||||
{"current_steps": 560, "total_steps": 874, "loss": 0.4804, "lr": 3.466323399785072e-06, "epoch": 1.2814645308924484, "percentage": 64.07, "elapsed_time": "2:14:43", "remaining_time": "1:15:32"}
|
||||
{"current_steps": 570, "total_steps": 874, "loss": 0.4926, "lr": 3.2773857278677414e-06, "epoch": 1.3043478260869565, "percentage": 65.22, "elapsed_time": "2:17:10", "remaining_time": "1:13:09"}
|
||||
{"current_steps": 580, "total_steps": 874, "loss": 0.5041, "lr": 3.0911996532612966e-06, "epoch": 1.3272311212814645, "percentage": 66.36, "elapsed_time": "2:19:27", "remaining_time": "1:10:41"}
|
||||
{"current_steps": 590, "total_steps": 874, "loss": 0.473, "lr": 2.9080625780658455e-06, "epoch": 1.3501144164759724, "percentage": 67.51, "elapsed_time": "2:21:48", "remaining_time": "1:08:15"}
|
||||
{"current_steps": 600, "total_steps": 874, "loss": 0.4664, "lr": 2.7282670340987465e-06, "epoch": 1.3729977116704806, "percentage": 68.65, "elapsed_time": "2:24:27", "remaining_time": "1:05:57"}
|
||||
{"current_steps": 610, "total_steps": 874, "loss": 0.4872, "lr": 2.552100215622401e-06, "epoch": 1.3958810068649885, "percentage": 69.79, "elapsed_time": "2:26:43", "remaining_time": "1:03:30"}
|
||||
{"current_steps": 620, "total_steps": 874, "loss": 0.5043, "lr": 2.379843520597937e-06, "epoch": 1.4187643020594964, "percentage": 70.94, "elapsed_time": "2:29:15", "remaining_time": "1:01:09"}
|
||||
{"current_steps": 630, "total_steps": 874, "loss": 0.5273, "lr": 2.2117721011975366e-06, "epoch": 1.4416475972540046, "percentage": 72.08, "elapsed_time": "2:31:34", "remaining_time": "0:58:42"}
|
||||
{"current_steps": 640, "total_steps": 874, "loss": 0.4862, "lr": 2.0481544242934105e-06, "epoch": 1.4645308924485125, "percentage": 73.23, "elapsed_time": "2:33:53", "remaining_time": "0:56:15"}
|
||||
{"current_steps": 650, "total_steps": 874, "loss": 0.4729, "lr": 1.8892518426254363e-06, "epoch": 1.4874141876430205, "percentage": 74.37, "elapsed_time": "2:36:17", "remaining_time": "0:53:51"}
|
||||
{"current_steps": 660, "total_steps": 874, "loss": 0.5103, "lr": 1.735318177332503e-06, "epoch": 1.5102974828375286, "percentage": 75.51, "elapsed_time": "2:38:40", "remaining_time": "0:51:27"}
|
||||
{"current_steps": 670, "total_steps": 874, "loss": 0.4903, "lr": 1.5865993125143297e-06, "epoch": 1.5331807780320366, "percentage": 76.66, "elapsed_time": "2:41:06", "remaining_time": "0:49:03"}
|
||||
{"current_steps": 680, "total_steps": 874, "loss": 0.4755, "lr": 1.4433328024714583e-06, "epoch": 1.5560640732265445, "percentage": 77.8, "elapsed_time": "2:43:25", "remaining_time": "0:46:37"}
|
||||
{"current_steps": 690, "total_steps": 874, "loss": 0.4482, "lr": 1.3057474922507124e-06, "epoch": 1.5789473684210527, "percentage": 78.95, "elapsed_time": "2:45:51", "remaining_time": "0:44:13"}
|
||||
{"current_steps": 700, "total_steps": 874, "loss": 0.4944, "lr": 1.1740631521023176e-06, "epoch": 1.6018306636155606, "percentage": 80.09, "elapsed_time": "2:48:08", "remaining_time": "0:41:47"}
|
||||
{"current_steps": 710, "total_steps": 874, "loss": 0.4975, "lr": 1.0484901264325026e-06, "epoch": 1.6247139588100685, "percentage": 81.24, "elapsed_time": "2:50:33", "remaining_time": "0:39:23"}
|
||||
{"current_steps": 720, "total_steps": 874, "loss": 0.4457, "lr": 9.292289978123892e-07, "epoch": 1.6475972540045767, "percentage": 82.38, "elapsed_time": "2:52:50", "remaining_time": "0:36:58"}
|
||||
{"current_steps": 730, "total_steps": 874, "loss": 0.4953, "lr": 8.16470266579813e-07, "epoch": 1.6704805491990846, "percentage": 83.52, "elapsed_time": "2:55:21", "remaining_time": "0:34:35"}
|
||||
{"current_steps": 740, "total_steps": 874, "loss": 0.4719, "lr": 7.103940465458936e-07, "epoch": 1.6933638443935926, "percentage": 84.67, "elapsed_time": "2:57:47", "remaining_time": "0:32:11"}
|
||||
{"current_steps": 750, "total_steps": 874, "loss": 0.4789, "lr": 6.111697772923836e-07, "epoch": 1.7162471395881007, "percentage": 85.81, "elapsed_time": "3:00:07", "remaining_time": "0:29:46"}
|
||||
{"current_steps": 760, "total_steps": 874, "loss": 0.4781, "lr": 5.189559535193839e-07, "epoch": 1.7391304347826086, "percentage": 86.96, "elapsed_time": "3:02:23", "remaining_time": "0:27:21"}
|
||||
{"current_steps": 770, "total_steps": 874, "loss": 0.4713, "lr": 4.338998718757315e-07, "epoch": 1.7620137299771166, "percentage": 88.1, "elapsed_time": "3:04:40", "remaining_time": "0:24:56"}
|
||||
{"current_steps": 780, "total_steps": 874, "loss": 0.5064, "lr": 3.5613739567645246e-07, "epoch": 1.7848970251716247, "percentage": 89.24, "elapsed_time": "3:07:05", "remaining_time": "0:22:32"}
|
||||
{"current_steps": 790, "total_steps": 874, "loss": 0.4907, "lr": 2.8579273788312433e-07, "epoch": 1.8077803203661327, "percentage": 90.39, "elapsed_time": "3:09:32", "remaining_time": "0:20:09"}
|
||||
{"current_steps": 800, "total_steps": 874, "loss": 0.4547, "lr": 2.2297826269378653e-07, "epoch": 1.8306636155606406, "percentage": 91.53, "elapsed_time": "3:11:52", "remaining_time": "0:17:44"}
|
||||
{"current_steps": 810, "total_steps": 874, "loss": 0.4939, "lr": 1.6779430605933233e-07, "epoch": 1.8535469107551488, "percentage": 92.68, "elapsed_time": "3:14:10", "remaining_time": "0:15:20"}
|
||||
{"current_steps": 820, "total_steps": 874, "loss": 0.5068, "lr": 1.203290154130754e-07, "epoch": 1.8764302059496567, "percentage": 93.82, "elapsed_time": "3:16:28", "remaining_time": "0:12:56"}
|
||||
{"current_steps": 830, "total_steps": 874, "loss": 0.4447, "lr": 8.065820886950404e-08, "epoch": 1.8993135011441646, "percentage": 94.97, "elapsed_time": "3:18:58", "remaining_time": "0:10:32"}
|
||||
{"current_steps": 840, "total_steps": 874, "loss": 0.4844, "lr": 4.8845254117120265e-08, "epoch": 1.9221967963386728, "percentage": 96.11, "elapsed_time": "3:21:34", "remaining_time": "0:08:09"}
|
||||
{"current_steps": 850, "total_steps": 874, "loss": 0.4735, "lr": 2.4940967198821553e-08, "epoch": 1.9450800915331807, "percentage": 97.25, "elapsed_time": "3:23:51", "remaining_time": "0:05:45"}
|
||||
{"current_steps": 860, "total_steps": 874, "loss": 0.457, "lr": 8.983531341500984e-09, "epoch": 1.9679633867276887, "percentage": 98.4, "elapsed_time": "3:26:19", "remaining_time": "0:03:21"}
|
||||
{"current_steps": 870, "total_steps": 874, "loss": 0.4556, "lr": 9.984359645276443e-10, "epoch": 1.9908466819221968, "percentage": 99.54, "elapsed_time": "3:28:41", "remaining_time": "0:00:57"}
|
||||
{"current_steps": 874, "total_steps": 874, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "3:30:17", "remaining_time": "0:00:00"}
|
||||
652
trainer_state.json
Normal file
652
trainer_state.json
Normal file
@@ -0,0 +1,652 @@
|
||||
{
|
||||
"best_global_step": null,
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 2.0,
|
||||
"eval_steps": 500,
|
||||
"global_step": 874,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"epoch": 0.02288329519450801,
|
||||
"grad_norm": 6.273149490356445,
|
||||
"learning_rate": 1.0227272727272729e-06,
|
||||
"loss": 0.9488,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"epoch": 0.04576659038901602,
|
||||
"grad_norm": 1.8167459964752197,
|
||||
"learning_rate": 2.1590909090909092e-06,
|
||||
"loss": 0.8935,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"epoch": 0.06864988558352403,
|
||||
"grad_norm": 1.2105071544647217,
|
||||
"learning_rate": 3.2954545454545456e-06,
|
||||
"loss": 0.8345,
|
||||
"step": 30
|
||||
},
|
||||
{
|
||||
"epoch": 0.09153318077803203,
|
||||
"grad_norm": 1.0105230808258057,
|
||||
"learning_rate": 4.4318181818181824e-06,
|
||||
"loss": 0.7483,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"epoch": 0.11441647597254005,
|
||||
"grad_norm": 0.6374103426933289,
|
||||
"learning_rate": 5.568181818181818e-06,
|
||||
"loss": 0.7619,
|
||||
"step": 50
|
||||
},
|
||||
{
|
||||
"epoch": 0.13729977116704806,
|
||||
"grad_norm": 0.6305025219917297,
|
||||
"learning_rate": 6.704545454545454e-06,
|
||||
"loss": 0.7492,
|
||||
"step": 60
|
||||
},
|
||||
{
|
||||
"epoch": 0.16018306636155608,
|
||||
"grad_norm": 0.7204020023345947,
|
||||
"learning_rate": 7.840909090909091e-06,
|
||||
"loss": 0.7519,
|
||||
"step": 70
|
||||
},
|
||||
{
|
||||
"epoch": 0.18306636155606407,
|
||||
"grad_norm": 0.5683720707893372,
|
||||
"learning_rate": 8.977272727272727e-06,
|
||||
"loss": 0.7103,
|
||||
"step": 80
|
||||
},
|
||||
{
|
||||
"epoch": 0.20594965675057209,
|
||||
"grad_norm": 0.5563637018203735,
|
||||
"learning_rate": 9.999960061285353e-06,
|
||||
"loss": 0.7069,
|
||||
"step": 90
|
||||
},
|
||||
{
|
||||
"epoch": 0.2288329519450801,
|
||||
"grad_norm": 0.5850629806518555,
|
||||
"learning_rate": 9.995168187508393e-06,
|
||||
"loss": 0.7032,
|
||||
"step": 100
|
||||
},
|
||||
{
|
||||
"epoch": 0.2517162471395881,
|
||||
"grad_norm": 0.5742172598838806,
|
||||
"learning_rate": 9.98239734155262e-06,
|
||||
"loss": 0.7216,
|
||||
"step": 110
|
||||
},
|
||||
{
|
||||
"epoch": 0.2745995423340961,
|
||||
"grad_norm": 0.5447644591331482,
|
||||
"learning_rate": 9.961667922776125e-06,
|
||||
"loss": 0.7085,
|
||||
"step": 120
|
||||
},
|
||||
{
|
||||
"epoch": 0.2974828375286041,
|
||||
"grad_norm": 0.6290788054466248,
|
||||
"learning_rate": 9.93301304306814e-06,
|
||||
"loss": 0.7104,
|
||||
"step": 130
|
||||
},
|
||||
{
|
||||
"epoch": 0.32036613272311215,
|
||||
"grad_norm": 0.5978163480758667,
|
||||
"learning_rate": 9.896478473958147e-06,
|
||||
"loss": 0.6963,
|
||||
"step": 140
|
||||
},
|
||||
{
|
||||
"epoch": 0.34324942791762014,
|
||||
"grad_norm": 0.5672498345375061,
|
||||
"learning_rate": 9.852122573503283e-06,
|
||||
"loss": 0.6751,
|
||||
"step": 150
|
||||
},
|
||||
{
|
||||
"epoch": 0.36613272311212813,
|
||||
"grad_norm": 0.6535360217094421,
|
||||
"learning_rate": 9.800016193070789e-06,
|
||||
"loss": 0.6757,
|
||||
"step": 160
|
||||
},
|
||||
{
|
||||
"epoch": 0.3890160183066362,
|
||||
"grad_norm": 0.5888985395431519,
|
||||
"learning_rate": 9.740242564164433e-06,
|
||||
"loss": 0.7119,
|
||||
"step": 170
|
||||
},
|
||||
{
|
||||
"epoch": 0.41189931350114417,
|
||||
"grad_norm": 0.5517858862876892,
|
||||
"learning_rate": 9.672897165475657e-06,
|
||||
"loss": 0.6598,
|
||||
"step": 180
|
||||
},
|
||||
{
|
||||
"epoch": 0.43478260869565216,
|
||||
"grad_norm": 0.5883446931838989,
|
||||
"learning_rate": 9.59808757037183e-06,
|
||||
"loss": 0.713,
|
||||
"step": 190
|
||||
},
|
||||
{
|
||||
"epoch": 0.4576659038901602,
|
||||
"grad_norm": 0.5446991920471191,
|
||||
"learning_rate": 9.515933275065218e-06,
|
||||
"loss": 0.6708,
|
||||
"step": 200
|
||||
},
|
||||
{
|
||||
"epoch": 0.4805491990846682,
|
||||
"grad_norm": 0.5323174595832825,
|
||||
"learning_rate": 9.426565507737139e-06,
|
||||
"loss": 0.6929,
|
||||
"step": 210
|
||||
},
|
||||
{
|
||||
"epoch": 0.5034324942791762,
|
||||
"grad_norm": 0.5511642098426819,
|
||||
"learning_rate": 9.330127018922195e-06,
|
||||
"loss": 0.6417,
|
||||
"step": 220
|
||||
},
|
||||
{
|
||||
"epoch": 0.5263157894736842,
|
||||
"grad_norm": 0.5513615608215332,
|
||||
"learning_rate": 9.226771853487411e-06,
|
||||
"loss": 0.6499,
|
||||
"step": 230
|
||||
},
|
||||
{
|
||||
"epoch": 0.5491990846681922,
|
||||
"grad_norm": 0.6379931569099426,
|
||||
"learning_rate": 9.116665104570513e-06,
|
||||
"loss": 0.6627,
|
||||
"step": 240
|
||||
},
|
||||
{
|
||||
"epoch": 0.5720823798627003,
|
||||
"grad_norm": 0.5682238340377808,
|
||||
"learning_rate": 8.999982649870377e-06,
|
||||
"loss": 0.6766,
|
||||
"step": 250
|
||||
},
|
||||
{
|
||||
"epoch": 0.5949656750572082,
|
||||
"grad_norm": 0.6159243583679199,
|
||||
"learning_rate": 8.876910870710885e-06,
|
||||
"loss": 0.6843,
|
||||
"step": 260
|
||||
},
|
||||
{
|
||||
"epoch": 0.6178489702517163,
|
||||
"grad_norm": 0.6061480641365051,
|
||||
"learning_rate": 8.747646354326948e-06,
|
||||
"loss": 0.6844,
|
||||
"step": 270
|
||||
},
|
||||
{
|
||||
"epoch": 0.6407322654462243,
|
||||
"grad_norm": 0.5296269059181213,
|
||||
"learning_rate": 8.612395579848244e-06,
|
||||
"loss": 0.6511,
|
||||
"step": 280
|
||||
},
|
||||
{
|
||||
"epoch": 0.6636155606407322,
|
||||
"grad_norm": 0.6145397424697876,
|
||||
"learning_rate": 8.47137458848224e-06,
|
||||
"loss": 0.6631,
|
||||
"step": 290
|
||||
},
|
||||
{
|
||||
"epoch": 0.6864988558352403,
|
||||
"grad_norm": 0.7743079662322998,
|
||||
"learning_rate": 8.324808638423353e-06,
|
||||
"loss": 0.6871,
|
||||
"step": 300
|
||||
},
|
||||
{
|
||||
"epoch": 0.7093821510297483,
|
||||
"grad_norm": 0.5358887314796448,
|
||||
"learning_rate": 8.172931845039471e-06,
|
||||
"loss": 0.6249,
|
||||
"step": 310
|
||||
},
|
||||
{
|
||||
"epoch": 0.7322654462242563,
|
||||
"grad_norm": 0.5243068933486938,
|
||||
"learning_rate": 8.01598680691057e-06,
|
||||
"loss": 0.6492,
|
||||
"step": 320
|
||||
},
|
||||
{
|
||||
"epoch": 0.7551487414187643,
|
||||
"grad_norm": 0.543357789516449,
|
||||
"learning_rate": 7.854224218316761e-06,
|
||||
"loss": 0.6619,
|
||||
"step": 330
|
||||
},
|
||||
{
|
||||
"epoch": 0.7780320366132724,
|
||||
"grad_norm": 0.6806201338768005,
|
||||
"learning_rate": 7.687902468794803e-06,
|
||||
"loss": 0.6729,
|
||||
"step": 340
|
||||
},
|
||||
{
|
||||
"epoch": 0.8009153318077803,
|
||||
"grad_norm": 0.5173719525337219,
|
||||
"learning_rate": 7.517287230402639e-06,
|
||||
"loss": 0.631,
|
||||
"step": 350
|
||||
},
|
||||
{
|
||||
"epoch": 0.8237986270022883,
|
||||
"grad_norm": 0.5824826955795288,
|
||||
"learning_rate": 7.342651033351325e-06,
|
||||
"loss": 0.6195,
|
||||
"step": 360
|
||||
},
|
||||
{
|
||||
"epoch": 0.8466819221967964,
|
||||
"grad_norm": 0.5261944532394409,
|
||||
"learning_rate": 7.164272830682161e-06,
|
||||
"loss": 0.6352,
|
||||
"step": 370
|
||||
},
|
||||
{
|
||||
"epoch": 0.8695652173913043,
|
||||
"grad_norm": 0.5619760751724243,
|
||||
"learning_rate": 6.9824375526843705e-06,
|
||||
"loss": 0.6549,
|
||||
"step": 380
|
||||
},
|
||||
{
|
||||
"epoch": 0.8924485125858124,
|
||||
"grad_norm": 0.7826661467552185,
|
||||
"learning_rate": 6.797435651765123e-06,
|
||||
"loss": 0.6593,
|
||||
"step": 390
|
||||
},
|
||||
{
|
||||
"epoch": 0.9153318077803204,
|
||||
"grad_norm": 0.5557212829589844,
|
||||
"learning_rate": 6.609562638498845e-06,
|
||||
"loss": 0.6141,
|
||||
"step": 400
|
||||
},
|
||||
{
|
||||
"epoch": 0.9382151029748284,
|
||||
"grad_norm": 0.5369032621383667,
|
||||
"learning_rate": 6.419118609596948e-06,
|
||||
"loss": 0.6194,
|
||||
"step": 410
|
||||
},
|
||||
{
|
||||
"epoch": 0.9610983981693364,
|
||||
"grad_norm": 0.636508584022522,
|
||||
"learning_rate": 6.2264077685519246e-06,
|
||||
"loss": 0.6406,
|
||||
"step": 420
|
||||
},
|
||||
{
|
||||
"epoch": 0.9839816933638444,
|
||||
"grad_norm": 0.6025350689888,
|
||||
"learning_rate": 6.031737939721538e-06,
|
||||
"loss": 0.6515,
|
||||
"step": 430
|
||||
},
|
||||
{
|
||||
"epoch": 1.0068649885583525,
|
||||
"grad_norm": 0.7006174325942993,
|
||||
"learning_rate": 5.835420076629273e-06,
|
||||
"loss": 0.6155,
|
||||
"step": 440
|
||||
},
|
||||
{
|
||||
"epoch": 1.0297482837528604,
|
||||
"grad_norm": 0.5530907511711121,
|
||||
"learning_rate": 5.6377677652664345e-06,
|
||||
"loss": 0.4827,
|
||||
"step": 450
|
||||
},
|
||||
{
|
||||
"epoch": 1.0526315789473684,
|
||||
"grad_norm": 0.5725921988487244,
|
||||
"learning_rate": 5.439096723189316e-06,
|
||||
"loss": 0.5285,
|
||||
"step": 460
|
||||
},
|
||||
{
|
||||
"epoch": 1.0755148741418765,
|
||||
"grad_norm": 0.5810708403587341,
|
||||
"learning_rate": 5.239724295211541e-06,
|
||||
"loss": 0.4976,
|
||||
"step": 470
|
||||
},
|
||||
{
|
||||
"epoch": 1.0983981693363845,
|
||||
"grad_norm": 0.49420347809791565,
|
||||
"learning_rate": 5.03996894649711e-06,
|
||||
"loss": 0.4919,
|
||||
"step": 480
|
||||
},
|
||||
{
|
||||
"epoch": 1.1212814645308924,
|
||||
"grad_norm": 0.5970099568367004,
|
||||
"learning_rate": 4.840149753863887e-06,
|
||||
"loss": 0.4691,
|
||||
"step": 490
|
||||
},
|
||||
{
|
||||
"epoch": 1.1441647597254005,
|
||||
"grad_norm": 0.5820793509483337,
|
||||
"learning_rate": 4.640585896110054e-06,
|
||||
"loss": 0.4929,
|
||||
"step": 500
|
||||
},
|
||||
{
|
||||
"epoch": 1.1670480549199085,
|
||||
"grad_norm": 0.5207763314247131,
|
||||
"learning_rate": 4.441596144177681e-06,
|
||||
"loss": 0.4885,
|
||||
"step": 510
|
||||
},
|
||||
{
|
||||
"epoch": 1.1899313501144164,
|
||||
"grad_norm": 0.5545329451560974,
|
||||
"learning_rate": 4.243498351967761e-06,
|
||||
"loss": 0.4682,
|
||||
"step": 520
|
||||
},
|
||||
{
|
||||
"epoch": 1.2128146453089246,
|
||||
"grad_norm": 0.6203777194023132,
|
||||
"learning_rate": 4.046608948620098e-06,
|
||||
"loss": 0.4791,
|
||||
"step": 530
|
||||
},
|
||||
{
|
||||
"epoch": 1.2356979405034325,
|
||||
"grad_norm": 0.592488706111908,
|
||||
"learning_rate": 3.8512424330689855e-06,
|
||||
"loss": 0.4732,
|
||||
"step": 540
|
||||
},
|
||||
{
|
||||
"epoch": 1.2585812356979404,
|
||||
"grad_norm": 0.643437922000885,
|
||||
"learning_rate": 3.657710871682115e-06,
|
||||
"loss": 0.4849,
|
||||
"step": 550
|
||||
},
|
||||
{
|
||||
"epoch": 1.2814645308924484,
|
||||
"grad_norm": 0.5146209597587585,
|
||||
"learning_rate": 3.466323399785072e-06,
|
||||
"loss": 0.4804,
|
||||
"step": 560
|
||||
},
|
||||
{
|
||||
"epoch": 1.3043478260869565,
|
||||
"grad_norm": 0.5695487856864929,
|
||||
"learning_rate": 3.2773857278677414e-06,
|
||||
"loss": 0.4926,
|
||||
"step": 570
|
||||
},
|
||||
{
|
||||
"epoch": 1.3272311212814645,
|
||||
"grad_norm": 0.6413753032684326,
|
||||
"learning_rate": 3.0911996532612966e-06,
|
||||
"loss": 0.5041,
|
||||
"step": 580
|
||||
},
|
||||
{
|
||||
"epoch": 1.3501144164759724,
|
||||
"grad_norm": 0.6373730897903442,
|
||||
"learning_rate": 2.9080625780658455e-06,
|
||||
"loss": 0.473,
|
||||
"step": 590
|
||||
},
|
||||
{
|
||||
"epoch": 1.3729977116704806,
|
||||
"grad_norm": 0.5488091111183167,
|
||||
"learning_rate": 2.7282670340987465e-06,
|
||||
"loss": 0.4664,
|
||||
"step": 600
|
||||
},
|
||||
{
|
||||
"epoch": 1.3958810068649885,
|
||||
"grad_norm": 0.6199346780776978,
|
||||
"learning_rate": 2.552100215622401e-06,
|
||||
"loss": 0.4872,
|
||||
"step": 610
|
||||
},
|
||||
{
|
||||
"epoch": 1.4187643020594964,
|
||||
"grad_norm": 0.6668885350227356,
|
||||
"learning_rate": 2.379843520597937e-06,
|
||||
"loss": 0.5043,
|
||||
"step": 620
|
||||
},
|
||||
{
|
||||
"epoch": 1.4416475972540046,
|
||||
"grad_norm": 0.5706750154495239,
|
||||
"learning_rate": 2.2117721011975366e-06,
|
||||
"loss": 0.5273,
|
||||
"step": 630
|
||||
},
|
||||
{
|
||||
"epoch": 1.4645308924485125,
|
||||
"grad_norm": 0.5967586040496826,
|
||||
"learning_rate": 2.0481544242934105e-06,
|
||||
"loss": 0.4862,
|
||||
"step": 640
|
||||
},
|
||||
{
|
||||
"epoch": 1.4874141876430205,
|
||||
"grad_norm": 0.5441915988922119,
|
||||
"learning_rate": 1.8892518426254363e-06,
|
||||
"loss": 0.4729,
|
||||
"step": 650
|
||||
},
|
||||
{
|
||||
"epoch": 1.5102974828375286,
|
||||
"grad_norm": 0.6105183362960815,
|
||||
"learning_rate": 1.735318177332503e-06,
|
||||
"loss": 0.5103,
|
||||
"step": 660
|
||||
},
|
||||
{
|
||||
"epoch": 1.5331807780320366,
|
||||
"grad_norm": 0.6279262900352478,
|
||||
"learning_rate": 1.5865993125143297e-06,
|
||||
"loss": 0.4903,
|
||||
"step": 670
|
||||
},
|
||||
{
|
||||
"epoch": 1.5560640732265445,
|
||||
"grad_norm": 0.571307897567749,
|
||||
"learning_rate": 1.4433328024714583e-06,
|
||||
"loss": 0.4755,
|
||||
"step": 680
|
||||
},
|
||||
{
|
||||
"epoch": 1.5789473684210527,
|
||||
"grad_norm": 0.546181857585907,
|
||||
"learning_rate": 1.3057474922507124e-06,
|
||||
"loss": 0.4482,
|
||||
"step": 690
|
||||
},
|
||||
{
|
||||
"epoch": 1.6018306636155606,
|
||||
"grad_norm": 0.6069242358207703,
|
||||
"learning_rate": 1.1740631521023176e-06,
|
||||
"loss": 0.4944,
|
||||
"step": 700
|
||||
},
|
||||
{
|
||||
"epoch": 1.6247139588100685,
|
||||
"grad_norm": 0.6299660205841064,
|
||||
"learning_rate": 1.0484901264325026e-06,
|
||||
"loss": 0.4975,
|
||||
"step": 710
|
||||
},
|
||||
{
|
||||
"epoch": 1.6475972540045767,
|
||||
"grad_norm": 0.5508016347885132,
|
||||
"learning_rate": 9.292289978123892e-07,
|
||||
"loss": 0.4457,
|
||||
"step": 720
|
||||
},
|
||||
{
|
||||
"epoch": 1.6704805491990846,
|
||||
"grad_norm": 0.6158504486083984,
|
||||
"learning_rate": 8.16470266579813e-07,
|
||||
"loss": 0.4953,
|
||||
"step": 730
|
||||
},
|
||||
{
|
||||
"epoch": 1.6933638443935926,
|
||||
"grad_norm": 0.5822216868400574,
|
||||
"learning_rate": 7.103940465458936e-07,
|
||||
"loss": 0.4719,
|
||||
"step": 740
|
||||
},
|
||||
{
|
||||
"epoch": 1.7162471395881007,
|
||||
"grad_norm": 0.6294801831245422,
|
||||
"learning_rate": 6.111697772923836e-07,
|
||||
"loss": 0.4789,
|
||||
"step": 750
|
||||
},
|
||||
{
|
||||
"epoch": 1.7391304347826086,
|
||||
"grad_norm": 0.5460816621780396,
|
||||
"learning_rate": 5.189559535193839e-07,
|
||||
"loss": 0.4781,
|
||||
"step": 760
|
||||
},
|
||||
{
|
||||
"epoch": 1.7620137299771166,
|
||||
"grad_norm": 0.6677026748657227,
|
||||
"learning_rate": 4.338998718757315e-07,
|
||||
"loss": 0.4713,
|
||||
"step": 770
|
||||
},
|
||||
{
|
||||
"epoch": 1.7848970251716247,
|
||||
"grad_norm": 0.6107152700424194,
|
||||
"learning_rate": 3.5613739567645246e-07,
|
||||
"loss": 0.5064,
|
||||
"step": 780
|
||||
},
|
||||
{
|
||||
"epoch": 1.8077803203661327,
|
||||
"grad_norm": 0.5857329964637756,
|
||||
"learning_rate": 2.8579273788312433e-07,
|
||||
"loss": 0.4907,
|
||||
"step": 790
|
||||
},
|
||||
{
|
||||
"epoch": 1.8306636155606406,
|
||||
"grad_norm": 0.5900473594665527,
|
||||
"learning_rate": 2.2297826269378653e-07,
|
||||
"loss": 0.4547,
|
||||
"step": 800
|
||||
},
|
||||
{
|
||||
"epoch": 1.8535469107551488,
|
||||
"grad_norm": 0.5375809669494629,
|
||||
"learning_rate": 1.6779430605933233e-07,
|
||||
"loss": 0.4939,
|
||||
"step": 810
|
||||
},
|
||||
{
|
||||
"epoch": 1.8764302059496567,
|
||||
"grad_norm": 0.5968102812767029,
|
||||
"learning_rate": 1.203290154130754e-07,
|
||||
"loss": 0.5068,
|
||||
"step": 820
|
||||
},
|
||||
{
|
||||
"epoch": 1.8993135011441646,
|
||||
"grad_norm": 0.5544958710670471,
|
||||
"learning_rate": 8.065820886950404e-08,
|
||||
"loss": 0.4447,
|
||||
"step": 830
|
||||
},
|
||||
{
|
||||
"epoch": 1.9221967963386728,
|
||||
"grad_norm": 0.5510764718055725,
|
||||
"learning_rate": 4.8845254117120265e-08,
|
||||
"loss": 0.4844,
|
||||
"step": 840
|
||||
},
|
||||
{
|
||||
"epoch": 1.9450800915331807,
|
||||
"grad_norm": 0.6316992044448853,
|
||||
"learning_rate": 2.4940967198821553e-08,
|
||||
"loss": 0.4735,
|
||||
"step": 850
|
||||
},
|
||||
{
|
||||
"epoch": 1.9679633867276887,
|
||||
"grad_norm": 0.5907024145126343,
|
||||
"learning_rate": 8.983531341500984e-09,
|
||||
"loss": 0.457,
|
||||
"step": 860
|
||||
},
|
||||
{
|
||||
"epoch": 1.9908466819221968,
|
||||
"grad_norm": 0.6300244927406311,
|
||||
"learning_rate": 9.984359645276443e-10,
|
||||
"loss": 0.4556,
|
||||
"step": 870
|
||||
},
|
||||
{
|
||||
"epoch": 2.0,
|
||||
"step": 874,
|
||||
"total_flos": 1.3931784786122113e+19,
|
||||
"train_loss": 0.5872682382094778,
|
||||
"train_runtime": 12619.0484,
|
||||
"train_samples_per_second": 8.865,
|
||||
"train_steps_per_second": 0.069
|
||||
}
|
||||
],
|
||||
"logging_steps": 10,
|
||||
"max_steps": 874,
|
||||
"num_input_tokens_seen": 0,
|
||||
"num_train_epochs": 2,
|
||||
"save_steps": 500,
|
||||
"stateful_callbacks": {
|
||||
"TrainerControl": {
|
||||
"args": {
|
||||
"should_epoch_stop": false,
|
||||
"should_evaluate": false,
|
||||
"should_log": false,
|
||||
"should_save": true,
|
||||
"should_training_stop": true
|
||||
},
|
||||
"attributes": {}
|
||||
}
|
||||
},
|
||||
"total_flos": 1.3931784786122113e+19,
|
||||
"train_batch_size": 4,
|
||||
"trial_name": null,
|
||||
"trial_params": null
|
||||
}
|
||||
3
training_args.bin
Normal file
3
training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:612a639e14ec8dd4a6e37539e79671f10cba28b59005b6c390ca83e7d24f946c
|
||||
size 7889
|
||||
BIN
training_loss.png
Normal file
BIN
training_loss.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 40 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