初始化项目，由ModelHub XC社区提供模型
Model: jiayicheng/mix329_tillend_bc329 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: other
|
||||||
|
base_model: Qwen/Qwen3-8B
|
||||||
|
tags:
|
||||||
|
- llama-factory
|
||||||
|
- full
|
||||||
|
- generated_from_trainer
|
||||||
|
model-index:
|
||||||
|
- name: train_output
|
||||||
|
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. -->
|
||||||
|
|
||||||
|
# train_output
|
||||||
|
|
||||||
|
This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on the sft_fullteacher329_hf_same dataset.
|
||||||
|
|
||||||
|
## Model description
|
||||||
|
|
||||||
|
More information needed
|
||||||
|
|
||||||
|
## Intended uses & limitations
|
||||||
|
|
||||||
|
More information needed
|
||||||
|
|
||||||
|
## Training and evaluation data
|
||||||
|
|
||||||
|
More information needed
|
||||||
|
|
||||||
|
## Training procedure
|
||||||
|
|
||||||
|
### Training hyperparameters
|
||||||
|
|
||||||
|
The following hyperparameters were used during training:
|
||||||
|
- learning_rate: 4e-05
|
||||||
|
- train_batch_size: 1
|
||||||
|
- eval_batch_size: 8
|
||||||
|
- seed: 42
|
||||||
|
- distributed_type: multi-GPU
|
||||||
|
- num_devices: 4
|
||||||
|
- gradient_accumulation_steps: 4
|
||||||
|
- total_train_batch_size: 16
|
||||||
|
- total_eval_batch_size: 32
|
||||||
|
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.98) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
||||||
|
- lr_scheduler_type: cosine
|
||||||
|
- lr_scheduler_warmup_ratio: 0.1
|
||||||
|
- num_epochs: 7.0
|
||||||
|
|
||||||
|
### Training results
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
### Framework versions
|
||||||
|
|
||||||
|
- Transformers 4.57.1
|
||||||
|
- Pytorch 2.8.0+cu128
|
||||||
|
- Datasets 4.8.4
|
||||||
|
- Tokenizers 0.22.1
|
||||||
28
added_tokens.json
Normal file
28
added_tokens.json
Normal file
@@ -0,0 +1,28 @@
|
|||||||
|
{
|
||||||
|
"</think>": 151668,
|
||||||
|
"</tool_call>": 151658,
|
||||||
|
"</tool_response>": 151666,
|
||||||
|
"<think>": 151667,
|
||||||
|
"<tool_call>": 151657,
|
||||||
|
"<tool_response>": 151665,
|
||||||
|
"<|box_end|>": 151649,
|
||||||
|
"<|box_start|>": 151648,
|
||||||
|
"<|endoftext|>": 151643,
|
||||||
|
"<|file_sep|>": 151664,
|
||||||
|
"<|fim_middle|>": 151660,
|
||||||
|
"<|fim_pad|>": 151662,
|
||||||
|
"<|fim_prefix|>": 151659,
|
||||||
|
"<|fim_suffix|>": 151661,
|
||||||
|
"<|im_end|>": 151645,
|
||||||
|
"<|im_start|>": 151644,
|
||||||
|
"<|image_pad|>": 151655,
|
||||||
|
"<|object_ref_end|>": 151647,
|
||||||
|
"<|object_ref_start|>": 151646,
|
||||||
|
"<|quad_end|>": 151651,
|
||||||
|
"<|quad_start|>": 151650,
|
||||||
|
"<|repo_name|>": 151663,
|
||||||
|
"<|video_pad|>": 151656,
|
||||||
|
"<|vision_end|>": 151653,
|
||||||
|
"<|vision_pad|>": 151654,
|
||||||
|
"<|vision_start|>": 151652
|
||||||
|
}
|
||||||
16
all_results.json
Normal file
16
all_results.json
Normal file
@@ -0,0 +1,16 @@
|
|||||||
|
{
|
||||||
|
"achieved_tflops_per_gpu": 1.478960413497356,
|
||||||
|
"achieved_tflops_per_gpu_theoretical": 64.37018669364019,
|
||||||
|
"epoch": 7.0,
|
||||||
|
"loss_nan_ranks": 0,
|
||||||
|
"loss_rank_avg": 0.016517292708158493,
|
||||||
|
"mfu_percent": 0.47402577355684483,
|
||||||
|
"mfu_percent_theoretical": 20.631470094115446,
|
||||||
|
"total_flos": 9.154523001624986e+16,
|
||||||
|
"train_loss": 0.17878121568558522,
|
||||||
|
"train_runtime": 15474.591,
|
||||||
|
"train_samples_per_second": 0.297,
|
||||||
|
"train_steps_per_second": 0.019,
|
||||||
|
"valid_targets_mean": 880.2,
|
||||||
|
"valid_targets_min": 562
|
||||||
|
}
|
||||||
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 %}
|
||||||
68
config.json
Normal file
68
config.json
Normal file
@@ -0,0 +1,68 @@
|
|||||||
|
{
|
||||||
|
"architectures": [
|
||||||
|
"Qwen3ForCausalLM"
|
||||||
|
],
|
||||||
|
"attention_bias": false,
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"dtype": "bfloat16",
|
||||||
|
"eos_token_id": 151645,
|
||||||
|
"head_dim": 128,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 4096,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 12288,
|
||||||
|
"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"
|
||||||
|
],
|
||||||
|
"max_position_embeddings": 40960,
|
||||||
|
"max_window_layers": 36,
|
||||||
|
"model_type": "qwen3",
|
||||||
|
"num_attention_heads": 32,
|
||||||
|
"num_hidden_layers": 36,
|
||||||
|
"num_key_value_heads": 8,
|
||||||
|
"pad_token_id": 151643,
|
||||||
|
"rms_norm_eps": 1e-06,
|
||||||
|
"rope_scaling": null,
|
||||||
|
"rope_theta": 1000000,
|
||||||
|
"sliding_window": null,
|
||||||
|
"tie_word_embeddings": false,
|
||||||
|
"transformers_version": "4.57.1",
|
||||||
|
"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": "4.57.1"
|
||||||
|
}
|
||||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model-00001-of-00004.safetensors
Normal file
3
model-00001-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:49a9114e2f5e937a36f1b1c910acbf7f9fd2437566fbac29d0fb7a12b978c013
|
||||||
|
size 4902257696
|
||||||
3
model-00002-of-00004.safetensors
Normal file
3
model-00002-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:c0e216ec7239e2bbe83c40db5f911e64c04400aebf7ec75f2f64040e47cd4dd7
|
||||||
|
size 4915960368
|
||||||
3
model-00003-of-00004.safetensors
Normal file
3
model-00003-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:41058fe1591fc307c31f868f29f33c302eb6c7ab94a8ca4ee13ebab521299de7
|
||||||
|
size 4983068496
|
||||||
3
model-00004-of-00004.safetensors
Normal file
3
model-00004-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:7e0494e64a12c59d56fdcda9076bb20ab6e253e3c169a01706313bb066a4e052
|
||||||
|
size 1580230264
|
||||||
407
model.safetensors.index.json
Normal file
407
model.safetensors.index.json
Normal file
@@ -0,0 +1,407 @@
|
|||||||
|
{
|
||||||
|
"metadata": {
|
||||||
|
"total_parameters": 308224,
|
||||||
|
"total_size": 16381470720
|
||||||
|
},
|
||||||
|
"weight_map": {
|
||||||
|
"lm_head.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.22.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.norm.weight": "model-00004-of-00004.safetensors"
|
||||||
|
}
|
||||||
|
}
|
||||||
31
special_tokens_map.json
Normal file
31
special_tokens_map.json
Normal file
@@ -0,0 +1,31 @@
|
|||||||
|
{
|
||||||
|
"additional_special_tokens": [
|
||||||
|
"<|im_start|>",
|
||||||
|
"<|im_end|>",
|
||||||
|
"<|object_ref_start|>",
|
||||||
|
"<|object_ref_end|>",
|
||||||
|
"<|box_start|>",
|
||||||
|
"<|box_end|>",
|
||||||
|
"<|quad_start|>",
|
||||||
|
"<|quad_end|>",
|
||||||
|
"<|vision_start|>",
|
||||||
|
"<|vision_end|>",
|
||||||
|
"<|vision_pad|>",
|
||||||
|
"<|image_pad|>",
|
||||||
|
"<|video_pad|>"
|
||||||
|
],
|
||||||
|
"eos_token": {
|
||||||
|
"content": "<|im_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"pad_token": {
|
||||||
|
"content": "<|endoftext|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
}
|
||||||
|
}
|
||||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
||||||
|
size 11422654
|
||||||
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": 32768,
|
||||||
|
"pad_token": "<|endoftext|>",
|
||||||
|
"padding_side": "right",
|
||||||
|
"split_special_tokens": false,
|
||||||
|
"tokenizer_class": "Qwen2Tokenizer",
|
||||||
|
"unk_token": null
|
||||||
|
}
|
||||||
16
train_results.json
Normal file
16
train_results.json
Normal file
@@ -0,0 +1,16 @@
|
|||||||
|
{
|
||||||
|
"achieved_tflops_per_gpu": 1.478960413497356,
|
||||||
|
"achieved_tflops_per_gpu_theoretical": 64.37018669364019,
|
||||||
|
"epoch": 7.0,
|
||||||
|
"loss_nan_ranks": 0,
|
||||||
|
"loss_rank_avg": 0.016517292708158493,
|
||||||
|
"mfu_percent": 0.47402577355684483,
|
||||||
|
"mfu_percent_theoretical": 20.631470094115446,
|
||||||
|
"total_flos": 9.154523001624986e+16,
|
||||||
|
"train_loss": 0.17878121568558522,
|
||||||
|
"train_runtime": 15474.591,
|
||||||
|
"train_samples_per_second": 0.297,
|
||||||
|
"train_steps_per_second": 0.019,
|
||||||
|
"valid_targets_mean": 880.2,
|
||||||
|
"valid_targets_min": 562
|
||||||
|
}
|
||||||
58
trainer_log.jsonl
Normal file
58
trainer_log.jsonl
Normal file
@@ -0,0 +1,58 @@
|
|||||||
|
{"current_steps": 5, "total_steps": 287, "loss": 0.7129, "lr": 5.517241379310345e-06, "epoch": 0.12195121951219512, "percentage": 1.74, "elapsed_time": "0:04:28", "remaining_time": "4:12:26"}
|
||||||
|
{"current_steps": 10, "total_steps": 287, "loss": 0.5949, "lr": 1.2413793103448277e-05, "epoch": 0.24390243902439024, "percentage": 3.48, "elapsed_time": "0:08:41", "remaining_time": "4:00:48"}
|
||||||
|
{"current_steps": 15, "total_steps": 287, "loss": 0.3616, "lr": 1.931034482758621e-05, "epoch": 0.36585365853658536, "percentage": 5.23, "elapsed_time": "0:13:02", "remaining_time": "3:56:37"}
|
||||||
|
{"current_steps": 20, "total_steps": 287, "loss": 0.3145, "lr": 2.620689655172414e-05, "epoch": 0.4878048780487805, "percentage": 6.97, "elapsed_time": "0:17:58", "remaining_time": "4:00:04"}
|
||||||
|
{"current_steps": 25, "total_steps": 287, "loss": 0.3165, "lr": 3.310344827586207e-05, "epoch": 0.6097560975609756, "percentage": 8.71, "elapsed_time": "0:22:05", "remaining_time": "3:51:29"}
|
||||||
|
{"current_steps": 30, "total_steps": 287, "loss": 0.2592, "lr": 4e-05, "epoch": 0.7317073170731707, "percentage": 10.45, "elapsed_time": "0:27:11", "remaining_time": "3:52:59"}
|
||||||
|
{"current_steps": 35, "total_steps": 287, "loss": 0.2519, "lr": 3.99629433475729e-05, "epoch": 0.8536585365853658, "percentage": 12.2, "elapsed_time": "0:30:34", "remaining_time": "3:40:09"}
|
||||||
|
{"current_steps": 40, "total_steps": 287, "loss": 0.2633, "lr": 3.985191070984053e-05, "epoch": 0.975609756097561, "percentage": 13.94, "elapsed_time": "0:36:29", "remaining_time": "3:45:19"}
|
||||||
|
{"current_steps": 45, "total_steps": 287, "loss": 0.2297, "lr": 3.966731353658932e-05, "epoch": 1.0975609756097562, "percentage": 15.68, "elapsed_time": "0:40:00", "remaining_time": "3:35:10"}
|
||||||
|
{"current_steps": 50, "total_steps": 287, "loss": 0.2282, "lr": 3.940983588314811e-05, "epoch": 1.2195121951219512, "percentage": 17.42, "elapsed_time": "0:44:15", "remaining_time": "3:29:46"}
|
||||||
|
{"current_steps": 55, "total_steps": 287, "loss": 0.2176, "lr": 3.908043187550802e-05, "epoch": 1.3414634146341464, "percentage": 19.16, "elapsed_time": "0:48:48", "remaining_time": "3:25:50"}
|
||||||
|
{"current_steps": 60, "total_steps": 287, "loss": 0.2294, "lr": 3.868032217465097e-05, "epoch": 1.4634146341463414, "percentage": 20.91, "elapsed_time": "0:53:21", "remaining_time": "3:21:51"}
|
||||||
|
{"current_steps": 65, "total_steps": 287, "loss": 0.2184, "lr": 3.821098945318869e-05, "epoch": 1.5853658536585367, "percentage": 22.65, "elapsed_time": "0:58:38", "remaining_time": "3:20:18"}
|
||||||
|
{"current_steps": 70, "total_steps": 287, "loss": 0.2229, "lr": 3.767417290107439e-05, "epoch": 1.7073170731707317, "percentage": 24.39, "elapsed_time": "1:02:27", "remaining_time": "3:13:38"}
|
||||||
|
{"current_steps": 75, "total_steps": 287, "loss": 0.1918, "lr": 3.7071861780746934e-05, "epoch": 1.8292682926829267, "percentage": 26.13, "elapsed_time": "1:08:13", "remaining_time": "3:12:50"}
|
||||||
|
{"current_steps": 80, "total_steps": 287, "loss": 0.1834, "lr": 3.640628805559022e-05, "epoch": 1.951219512195122, "percentage": 27.87, "elapsed_time": "1:12:23", "remaining_time": "3:07:18"}
|
||||||
|
{"current_steps": 85, "total_steps": 287, "loss": 0.1949, "lr": 3.567991811902403e-05, "epoch": 2.073170731707317, "percentage": 29.62, "elapsed_time": "1:16:10", "remaining_time": "3:01:00"}
|
||||||
|
{"current_steps": 90, "total_steps": 287, "loss": 0.1904, "lr": 3.489544365487564e-05, "epoch": 2.1951219512195124, "percentage": 31.36, "elapsed_time": "1:20:31", "remaining_time": "2:56:15"}
|
||||||
|
{"current_steps": 95, "total_steps": 287, "loss": 0.1738, "lr": 3.4055771662900637e-05, "epoch": 2.317073170731707, "percentage": 33.1, "elapsed_time": "1:25:12", "remaining_time": "2:52:12"}
|
||||||
|
{"current_steps": 100, "total_steps": 287, "loss": 0.1743, "lr": 3.316401368641496e-05, "epoch": 2.4390243902439024, "percentage": 34.84, "elapsed_time": "1:29:37", "remaining_time": "2:47:36"}
|
||||||
|
{"current_steps": 105, "total_steps": 287, "loss": 0.182, "lr": 3.222347428195699e-05, "epoch": 2.5609756097560976, "percentage": 36.59, "elapsed_time": "1:33:46", "remaining_time": "2:42:33"}
|
||||||
|
{"current_steps": 110, "total_steps": 287, "loss": 0.1587, "lr": 3.1237638773707214e-05, "epoch": 2.682926829268293, "percentage": 38.33, "elapsed_time": "1:38:52", "remaining_time": "2:39:05"}
|
||||||
|
{"current_steps": 115, "total_steps": 287, "loss": 0.1708, "lr": 3.0210160338043583e-05, "epoch": 2.8048780487804876, "percentage": 40.07, "elapsed_time": "1:43:46", "remaining_time": "2:35:13"}
|
||||||
|
{"current_steps": 120, "total_steps": 287, "loss": 0.1624, "lr": 2.9144846466092773e-05, "epoch": 2.926829268292683, "percentage": 41.81, "elapsed_time": "1:48:35", "remaining_time": "2:31:07"}
|
||||||
|
{"current_steps": 125, "total_steps": 287, "loss": 0.1503, "lr": 2.804564485444265e-05, "epoch": 3.048780487804878, "percentage": 43.55, "elapsed_time": "1:52:41", "remaining_time": "2:26:02"}
|
||||||
|
{"current_steps": 130, "total_steps": 287, "loss": 0.1451, "lr": 2.691662877630023e-05, "epoch": 3.1707317073170733, "percentage": 45.3, "elapsed_time": "1:57:02", "remaining_time": "2:21:20"}
|
||||||
|
{"current_steps": 135, "total_steps": 287, "loss": 0.1455, "lr": 2.5761981987304757e-05, "epoch": 3.292682926829268, "percentage": 47.04, "elapsed_time": "2:01:31", "remaining_time": "2:16:49"}
|
||||||
|
{"current_steps": 140, "total_steps": 287, "loss": 0.1411, "lr": 2.4585983221929803e-05, "epoch": 3.4146341463414633, "percentage": 48.78, "elapsed_time": "2:07:16", "remaining_time": "2:13:38"}
|
||||||
|
{"current_steps": 145, "total_steps": 287, "loss": 0.1504, "lr": 2.3392990337925696e-05, "epoch": 3.5365853658536586, "percentage": 50.52, "elapsed_time": "2:11:07", "remaining_time": "2:08:24"}
|
||||||
|
{"current_steps": 150, "total_steps": 287, "loss": 0.1577, "lr": 2.2187424167557496e-05, "epoch": 3.658536585365854, "percentage": 52.26, "elapsed_time": "2:15:23", "remaining_time": "2:03:39"}
|
||||||
|
{"current_steps": 155, "total_steps": 287, "loss": 0.1459, "lr": 2.0973752135480505e-05, "epoch": 3.7804878048780486, "percentage": 54.01, "elapsed_time": "2:18:46", "remaining_time": "1:58:11"}
|
||||||
|
{"current_steps": 160, "total_steps": 287, "loss": 0.1474, "lr": 1.9756471703960053e-05, "epoch": 3.902439024390244, "percentage": 55.75, "elapsed_time": "2:22:50", "remaining_time": "1:53:22"}
|
||||||
|
{"current_steps": 165, "total_steps": 287, "loss": 0.1105, "lr": 1.8540093706781848e-05, "epoch": 4.024390243902439, "percentage": 57.49, "elapsed_time": "2:28:49", "remaining_time": "1:50:02"}
|
||||||
|
{"current_steps": 170, "total_steps": 287, "loss": 0.1177, "lr": 1.7329125633612044e-05, "epoch": 4.146341463414634, "percentage": 59.23, "elapsed_time": "2:33:44", "remaining_time": "1:45:48"}
|
||||||
|
{"current_steps": 175, "total_steps": 287, "loss": 0.1245, "lr": 1.6128054926749403e-05, "epoch": 4.2682926829268295, "percentage": 60.98, "elapsed_time": "2:37:25", "remaining_time": "1:40:45"}
|
||||||
|
{"current_steps": 180, "total_steps": 287, "loss": 0.1253, "lr": 1.4941332352166385e-05, "epoch": 4.390243902439025, "percentage": 62.72, "elapsed_time": "2:41:16", "remaining_time": "1:35:52"}
|
||||||
|
{"current_steps": 185, "total_steps": 287, "loss": 0.1212, "lr": 1.3773355506460369e-05, "epoch": 4.512195121951219, "percentage": 64.46, "elapsed_time": "2:46:53", "remaining_time": "1:32:00"}
|
||||||
|
{"current_steps": 190, "total_steps": 287, "loss": 0.1289, "lr": 1.2628452520832766e-05, "epoch": 4.634146341463414, "percentage": 66.2, "elapsed_time": "2:51:25", "remaining_time": "1:27:30"}
|
||||||
|
{"current_steps": 195, "total_steps": 287, "loss": 0.112, "lr": 1.1510866022483702e-05, "epoch": 4.7560975609756095, "percentage": 67.94, "elapsed_time": "2:55:28", "remaining_time": "1:22:47"}
|
||||||
|
{"current_steps": 200, "total_steps": 287, "loss": 0.1243, "lr": 1.0424737412855825e-05, "epoch": 4.878048780487805, "percentage": 69.69, "elapsed_time": "3:00:17", "remaining_time": "1:18:25"}
|
||||||
|
{"current_steps": 205, "total_steps": 287, "loss": 0.144, "lr": 9.374091520986936e-06, "epoch": 5.0, "percentage": 71.43, "elapsed_time": "3:03:34", "remaining_time": "1:13:25"}
|
||||||
|
{"current_steps": 210, "total_steps": 287, "loss": 0.1142, "lr": 8.362821688840947e-06, "epoch": 5.121951219512195, "percentage": 73.17, "elapsed_time": "3:07:08", "remaining_time": "1:08:37"}
|
||||||
|
{"current_steps": 215, "total_steps": 287, "loss": 0.1041, "lr": 7.394675343885827e-06, "epoch": 5.2439024390243905, "percentage": 74.91, "elapsed_time": "3:11:35", "remaining_time": "1:04:09"}
|
||||||
|
{"current_steps": 220, "total_steps": 287, "loss": 0.1122, "lr": 6.473240112381944e-06, "epoch": 5.365853658536586, "percentage": 76.66, "elapsed_time": "3:17:30", "remaining_time": "1:00:08"}
|
||||||
|
{"current_steps": 225, "total_steps": 287, "loss": 0.1248, "lr": 5.601930524840087e-06, "epoch": 5.487804878048781, "percentage": 78.4, "elapsed_time": "3:20:55", "remaining_time": "0:55:21"}
|
||||||
|
{"current_steps": 230, "total_steps": 287, "loss": 0.1106, "lr": 4.7839753629144395e-06, "epoch": 5.609756097560975, "percentage": 80.14, "elapsed_time": "3:25:39", "remaining_time": "0:50:58"}
|
||||||
|
{"current_steps": 235, "total_steps": 287, "loss": 0.108, "lr": 4.022405694618659e-06, "epoch": 5.7317073170731705, "percentage": 81.88, "elapsed_time": "3:30:09", "remaining_time": "0:46:30"}
|
||||||
|
{"current_steps": 240, "total_steps": 287, "loss": 0.1033, "lr": 3.320043642202444e-06, "epoch": 5.853658536585366, "percentage": 83.62, "elapsed_time": "3:34:58", "remaining_time": "0:42:05"}
|
||||||
|
{"current_steps": 245, "total_steps": 287, "loss": 0.1044, "lr": 2.679491924311226e-06, "epoch": 5.975609756097561, "percentage": 85.37, "elapsed_time": "3:39:53", "remaining_time": "0:37:41"}
|
||||||
|
{"current_steps": 250, "total_steps": 287, "loss": 0.1087, "lr": 2.103124211182164e-06, "epoch": 6.097560975609756, "percentage": 87.11, "elapsed_time": "3:43:05", "remaining_time": "0:33:01"}
|
||||||
|
{"current_steps": 255, "total_steps": 287, "loss": 0.1049, "lr": 1.5930763286168138e-06, "epoch": 6.219512195121951, "percentage": 88.85, "elapsed_time": "3:49:07", "remaining_time": "0:28:45"}
|
||||||
|
{"current_steps": 260, "total_steps": 287, "loss": 0.0969, "lr": 1.1512383433257112e-06, "epoch": 6.341463414634147, "percentage": 90.59, "elapsed_time": "3:55:10", "remaining_time": "0:24:25"}
|
||||||
|
{"current_steps": 265, "total_steps": 287, "loss": 0.1071, "lr": 7.792475589738679e-07, "epoch": 6.463414634146342, "percentage": 92.33, "elapsed_time": "3:59:46", "remaining_time": "0:19:54"}
|
||||||
|
{"current_steps": 270, "total_steps": 287, "loss": 0.1053, "lr": 4.784824488814588e-07, "epoch": 6.585365853658536, "percentage": 94.08, "elapsed_time": "4:02:45", "remaining_time": "0:15:17"}
|
||||||
|
{"current_steps": 275, "total_steps": 287, "loss": 0.1065, "lr": 2.5005754786317173e-07, "epoch": 6.7073170731707314, "percentage": 95.82, "elapsed_time": "4:07:23", "remaining_time": "0:10:47"}
|
||||||
|
{"current_steps": 280, "total_steps": 287, "loss": 0.0987, "lr": 9.481932213528444e-08, "epoch": 6.829268292682927, "percentage": 97.56, "elapsed_time": "4:12:09", "remaining_time": "0:06:18"}
|
||||||
|
{"current_steps": 285, "total_steps": 287, "loss": 0.1098, "lr": 1.334303259521219e-08, "epoch": 6.951219512195122, "percentage": 99.3, "elapsed_time": "4:16:11", "remaining_time": "0:01:47"}
|
||||||
|
{"current_steps": 287, "total_steps": 287, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "4:17:53", "remaining_time": "0:00:00"}
|
||||||
674
trainer_state.json
Normal file
674
trainer_state.json
Normal file
@@ -0,0 +1,674 @@
|
|||||||
|
{
|
||||||
|
"best_global_step": null,
|
||||||
|
"best_metric": null,
|
||||||
|
"best_model_checkpoint": null,
|
||||||
|
"epoch": 7.0,
|
||||||
|
"eval_steps": 500,
|
||||||
|
"global_step": 287,
|
||||||
|
"is_hyper_param_search": false,
|
||||||
|
"is_local_process_zero": true,
|
||||||
|
"is_world_process_zero": true,
|
||||||
|
"log_history": [
|
||||||
|
{
|
||||||
|
"epoch": 0.12195121951219512,
|
||||||
|
"grad_norm": 11.268886282590001,
|
||||||
|
"learning_rate": 5.517241379310345e-06,
|
||||||
|
"loss": 0.7129,
|
||||||
|
"loss_nan_ranks": 0,
|
||||||
|
"loss_rank_avg": 0.08619208633899689,
|
||||||
|
"step": 5,
|
||||||
|
"valid_targets_mean": 1809.8,
|
||||||
|
"valid_targets_min": 413
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.24390243902439024,
|
||||||
|
"grad_norm": 6.618387158921114,
|
||||||
|
"learning_rate": 1.2413793103448277e-05,
|
||||||
|
"loss": 0.5949,
|
||||||
|
"loss_nan_ranks": 0,
|
||||||
|
"loss_rank_avg": 0.15227359533309937,
|
||||||
|
"step": 10,
|
||||||
|
"valid_targets_mean": 1454.2,
|
||||||
|
"valid_targets_min": 1048
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.36585365853658536,
|
||||||
|
"grad_norm": 1.1697598603814097,
|
||||||
|
"learning_rate": 1.931034482758621e-05,
|
||||||
|
"loss": 0.3616,
|
||||||
|
"loss_nan_ranks": 0,
|
||||||
|
"loss_rank_avg": 0.03705377131700516,
|
||||||
|
"step": 15,
|
||||||
|
"valid_targets_mean": 1068.8,
|
||||||
|
"valid_targets_min": 603
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.4878048780487805,
|
||||||
|
"grad_norm": 1.0542992580910668,
|
||||||
|
"learning_rate": 2.620689655172414e-05,
|
||||||
|
"loss": 0.3145,
|
||||||
|
"loss_nan_ranks": 0,
|
||||||
|
"loss_rank_avg": 0.05863872170448303,
|
||||||
|
"step": 20,
|
||||||
|
"valid_targets_mean": 1012.8,
|
||||||
|
"valid_targets_min": 786
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.6097560975609756,
|
||||||
|
"grad_norm": 0.8906250398426856,
|
||||||
|
"learning_rate": 3.310344827586207e-05,
|
||||||
|
"loss": 0.3165,
|
||||||
|
"loss_nan_ranks": 0,
|
||||||
|
"loss_rank_avg": 0.1044623851776123,
|
||||||
|
"step": 25,
|
||||||
|
"valid_targets_mean": 3050.0,
|
||||||
|
"valid_targets_min": 1178
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.7317073170731707,
|
||||||
|
"grad_norm": 0.7873917512747328,
|
||||||
|
"learning_rate": 4e-05,
|
||||||
|
"loss": 0.2592,
|
||||||
|
"loss_nan_ranks": 0,
|
||||||
|
"loss_rank_avg": 0.07892066985368729,
|
||||||
|
"step": 30,
|
||||||
|
"valid_targets_mean": 2248.5,
|
||||||
|
"valid_targets_min": 1487
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.8536585365853658,
|
||||||
|
"grad_norm": 0.7365758820610112,
|
||||||
|
"learning_rate": 3.99629433475729e-05,
|
||||||
|
"loss": 0.2519,
|
||||||
|
"loss_nan_ranks": 0,
|
||||||
|
"loss_rank_avg": 0.05776943266391754,
|
||||||
|
"step": 35,
|
||||||
|
"valid_targets_mean": 2209.0,
|
||||||
|
"valid_targets_min": 853
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 0.975609756097561,
|
||||||
|
"grad_norm": 0.9982728088095962,
|
||||||
|
"learning_rate": 3.985191070984053e-05,
|
||||||
|
"loss": 0.2633,
|
||||||
|
"loss_nan_ranks": 0,
|
||||||
|
"loss_rank_avg": 0.08143679797649384,
|
||||||
|
"step": 40,
|
||||||
|
"valid_targets_mean": 1733.5,
|
||||||
|
"valid_targets_min": 542
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.0975609756097562,
|
||||||
|
"grad_norm": 0.6049830734772758,
|
||||||
|
"learning_rate": 3.966731353658932e-05,
|
||||||
|
"loss": 0.2297,
|
||||||
|
"loss_nan_ranks": 0,
|
||||||
|
"loss_rank_avg": 0.05846400931477547,
|
||||||
|
"step": 45,
|
||||||
|
"valid_targets_mean": 2682.8,
|
||||||
|
"valid_targets_min": 1287
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.2195121951219512,
|
||||||
|
"grad_norm": 0.6718448910202545,
|
||||||
|
"learning_rate": 3.940983588314811e-05,
|
||||||
|
"loss": 0.2282,
|
||||||
|
"loss_nan_ranks": 0,
|
||||||
|
"loss_rank_avg": 0.05738037824630737,
|
||||||
|
"step": 50,
|
||||||
|
"valid_targets_mean": 2266.2,
|
||||||
|
"valid_targets_min": 917
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.3414634146341464,
|
||||||
|
"grad_norm": 0.7687467547629783,
|
||||||
|
"learning_rate": 3.908043187550802e-05,
|
||||||
|
"loss": 0.2176,
|
||||||
|
"loss_nan_ranks": 0,
|
||||||
|
"loss_rank_avg": 0.034274592995643616,
|
||||||
|
"step": 55,
|
||||||
|
"valid_targets_mean": 1044.0,
|
||||||
|
"valid_targets_min": 912
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.4634146341463414,
|
||||||
|
"grad_norm": 0.4409997756684539,
|
||||||
|
"learning_rate": 3.868032217465097e-05,
|
||||||
|
"loss": 0.2294,
|
||||||
|
"loss_nan_ranks": 0,
|
||||||
|
"loss_rank_avg": 0.06288576126098633,
|
||||||
|
"step": 60,
|
||||||
|
"valid_targets_mean": 7464.2,
|
||||||
|
"valid_targets_min": 4233
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.5853658536585367,
|
||||||
|
"grad_norm": 0.6669183491635846,
|
||||||
|
"learning_rate": 3.821098945318869e-05,
|
||||||
|
"loss": 0.2184,
|
||||||
|
"loss_nan_ranks": 0,
|
||||||
|
"loss_rank_avg": 0.041596993803977966,
|
||||||
|
"step": 65,
|
||||||
|
"valid_targets_mean": 2462.2,
|
||||||
|
"valid_targets_min": 603
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.7073170731707317,
|
||||||
|
"grad_norm": 0.833951005600001,
|
||||||
|
"learning_rate": 3.767417290107439e-05,
|
||||||
|
"loss": 0.2229,
|
||||||
|
"loss_nan_ranks": 0,
|
||||||
|
"loss_rank_avg": 0.0828239768743515,
|
||||||
|
"step": 70,
|
||||||
|
"valid_targets_mean": 1676.0,
|
||||||
|
"valid_targets_min": 960
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.8292682926829267,
|
||||||
|
"grad_norm": 0.3827765345675253,
|
||||||
|
"learning_rate": 3.7071861780746934e-05,
|
||||||
|
"loss": 0.1918,
|
||||||
|
"loss_nan_ranks": 0,
|
||||||
|
"loss_rank_avg": 0.03231481462717056,
|
||||||
|
"step": 75,
|
||||||
|
"valid_targets_mean": 6333.8,
|
||||||
|
"valid_targets_min": 1529
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 1.951219512195122,
|
||||||
|
"grad_norm": 0.405420209692415,
|
||||||
|
"learning_rate": 3.640628805559022e-05,
|
||||||
|
"loss": 0.1834,
|
||||||
|
"loss_nan_ranks": 0,
|
||||||
|
"loss_rank_avg": 0.021378157660365105,
|
||||||
|
"step": 80,
|
||||||
|
"valid_targets_mean": 2585.5,
|
||||||
|
"valid_targets_min": 894
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.073170731707317,
|
||||||
|
"grad_norm": 0.6706457928261834,
|
||||||
|
"learning_rate": 3.567991811902403e-05,
|
||||||
|
"loss": 0.1949,
|
||||||
|
"loss_nan_ranks": 0,
|
||||||
|
"loss_rank_avg": 0.029131846502423286,
|
||||||
|
"step": 85,
|
||||||
|
"valid_targets_mean": 1901.5,
|
||||||
|
"valid_targets_min": 758
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.1951219512195124,
|
||||||
|
"grad_norm": 0.6506505238615833,
|
||||||
|
"learning_rate": 3.489544365487564e-05,
|
||||||
|
"loss": 0.1904,
|
||||||
|
"loss_nan_ranks": 0,
|
||||||
|
"loss_rank_avg": 0.06596972048282623,
|
||||||
|
"step": 90,
|
||||||
|
"valid_targets_mean": 2361.2,
|
||||||
|
"valid_targets_min": 421
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.317073170731707,
|
||||||
|
"grad_norm": 0.5666611455881608,
|
||||||
|
"learning_rate": 3.4055771662900637e-05,
|
||||||
|
"loss": 0.1738,
|
||||||
|
"loss_nan_ranks": 0,
|
||||||
|
"loss_rank_avg": 0.032204728573560715,
|
||||||
|
"step": 95,
|
||||||
|
"valid_targets_mean": 1985.5,
|
||||||
|
"valid_targets_min": 813
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.4390243902439024,
|
||||||
|
"grad_norm": 0.5528709212555227,
|
||||||
|
"learning_rate": 3.316401368641496e-05,
|
||||||
|
"loss": 0.1743,
|
||||||
|
"loss_nan_ranks": 0,
|
||||||
|
"loss_rank_avg": 0.03457804396748543,
|
||||||
|
"step": 100,
|
||||||
|
"valid_targets_mean": 3545.0,
|
||||||
|
"valid_targets_min": 423
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.5609756097560976,
|
||||||
|
"grad_norm": 0.8867699611106878,
|
||||||
|
"learning_rate": 3.222347428195699e-05,
|
||||||
|
"loss": 0.182,
|
||||||
|
"loss_nan_ranks": 0,
|
||||||
|
"loss_rank_avg": 0.06031285971403122,
|
||||||
|
"step": 105,
|
||||||
|
"valid_targets_mean": 1640.8,
|
||||||
|
"valid_targets_min": 938
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.682926829268293,
|
||||||
|
"grad_norm": 0.5690766882507081,
|
||||||
|
"learning_rate": 3.1237638773707214e-05,
|
||||||
|
"loss": 0.1587,
|
||||||
|
"loss_nan_ranks": 0,
|
||||||
|
"loss_rank_avg": 0.04014682024717331,
|
||||||
|
"step": 110,
|
||||||
|
"valid_targets_mean": 2029.8,
|
||||||
|
"valid_targets_min": 960
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.8048780487804876,
|
||||||
|
"grad_norm": 0.7008728096682685,
|
||||||
|
"learning_rate": 3.0210160338043583e-05,
|
||||||
|
"loss": 0.1708,
|
||||||
|
"loss_nan_ranks": 0,
|
||||||
|
"loss_rank_avg": 0.07026761770248413,
|
||||||
|
"step": 115,
|
||||||
|
"valid_targets_mean": 2580.8,
|
||||||
|
"valid_targets_min": 786
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 2.926829268292683,
|
||||||
|
"grad_norm": 0.7716450116227951,
|
||||||
|
"learning_rate": 2.9144846466092773e-05,
|
||||||
|
"loss": 0.1624,
|
||||||
|
"loss_nan_ranks": 0,
|
||||||
|
"loss_rank_avg": 0.06721051037311554,
|
||||||
|
"step": 120,
|
||||||
|
"valid_targets_mean": 2570.2,
|
||||||
|
"valid_targets_min": 1543
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 3.048780487804878,
|
||||||
|
"grad_norm": 1.5503052769053867,
|
||||||
|
"learning_rate": 2.804564485444265e-05,
|
||||||
|
"loss": 0.1503,
|
||||||
|
"loss_nan_ranks": 0,
|
||||||
|
"loss_rank_avg": 0.0261751189827919,
|
||||||
|
"step": 125,
|
||||||
|
"valid_targets_mean": 1452.5,
|
||||||
|
"valid_targets_min": 917
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 3.1707317073170733,
|
||||||
|
"grad_norm": 0.6734417093831508,
|
||||||
|
"learning_rate": 2.691662877630023e-05,
|
||||||
|
"loss": 0.1451,
|
||||||
|
"loss_nan_ranks": 0,
|
||||||
|
"loss_rank_avg": 0.028553606942296028,
|
||||||
|
"step": 130,
|
||||||
|
"valid_targets_mean": 2922.2,
|
||||||
|
"valid_targets_min": 1260
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 3.292682926829268,
|
||||||
|
"grad_norm": 1.456490794322615,
|
||||||
|
"learning_rate": 2.5761981987304757e-05,
|
||||||
|
"loss": 0.1455,
|
||||||
|
"loss_nan_ranks": 0,
|
||||||
|
"loss_rank_avg": 0.03396756574511528,
|
||||||
|
"step": 135,
|
||||||
|
"valid_targets_mean": 1340.2,
|
||||||
|
"valid_targets_min": 796
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 3.4146341463414633,
|
||||||
|
"grad_norm": 0.9411604050978699,
|
||||||
|
"learning_rate": 2.4585983221929803e-05,
|
||||||
|
"loss": 0.1411,
|
||||||
|
"loss_nan_ranks": 0,
|
||||||
|
"loss_rank_avg": 0.037783801555633545,
|
||||||
|
"step": 140,
|
||||||
|
"valid_targets_mean": 2368.0,
|
||||||
|
"valid_targets_min": 797
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 3.5365853658536586,
|
||||||
|
"grad_norm": 0.9034332983731574,
|
||||||
|
"learning_rate": 2.3392990337925696e-05,
|
||||||
|
"loss": 0.1504,
|
||||||
|
"loss_nan_ranks": 0,
|
||||||
|
"loss_rank_avg": 0.04916565865278244,
|
||||||
|
"step": 145,
|
||||||
|
"valid_targets_mean": 1793.0,
|
||||||
|
"valid_targets_min": 648
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 3.658536585365854,
|
||||||
|
"grad_norm": 0.9084489941265945,
|
||||||
|
"learning_rate": 2.2187424167557496e-05,
|
||||||
|
"loss": 0.1577,
|
||||||
|
"loss_nan_ranks": 0,
|
||||||
|
"loss_rank_avg": 0.04747513309121132,
|
||||||
|
"step": 150,
|
||||||
|
"valid_targets_mean": 2595.5,
|
||||||
|
"valid_targets_min": 870
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 3.7804878048780486,
|
||||||
|
"grad_norm": 0.8065019341177397,
|
||||||
|
"learning_rate": 2.0973752135480505e-05,
|
||||||
|
"loss": 0.1459,
|
||||||
|
"loss_nan_ranks": 0,
|
||||||
|
"loss_rank_avg": 0.030843544751405716,
|
||||||
|
"step": 155,
|
||||||
|
"valid_targets_mean": 1864.2,
|
||||||
|
"valid_targets_min": 1047
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 3.902439024390244,
|
||||||
|
"grad_norm": 0.5952164537741085,
|
||||||
|
"learning_rate": 1.9756471703960053e-05,
|
||||||
|
"loss": 0.1474,
|
||||||
|
"loss_nan_ranks": 0,
|
||||||
|
"loss_rank_avg": 0.020152652636170387,
|
||||||
|
"step": 160,
|
||||||
|
"valid_targets_mean": 1157.0,
|
||||||
|
"valid_targets_min": 537
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 4.024390243902439,
|
||||||
|
"grad_norm": 0.5913764265658609,
|
||||||
|
"learning_rate": 1.8540093706781848e-05,
|
||||||
|
"loss": 0.1105,
|
||||||
|
"loss_nan_ranks": 0,
|
||||||
|
"loss_rank_avg": 0.023658908903598785,
|
||||||
|
"step": 165,
|
||||||
|
"valid_targets_mean": 1657.0,
|
||||||
|
"valid_targets_min": 1129
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 4.146341463414634,
|
||||||
|
"grad_norm": 0.8822354625847237,
|
||||||
|
"learning_rate": 1.7329125633612044e-05,
|
||||||
|
"loss": 0.1177,
|
||||||
|
"loss_nan_ranks": 0,
|
||||||
|
"loss_rank_avg": 0.03471684455871582,
|
||||||
|
"step": 170,
|
||||||
|
"valid_targets_mean": 1434.2,
|
||||||
|
"valid_targets_min": 1080
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 4.2682926829268295,
|
||||||
|
"grad_norm": 1.1958146779982144,
|
||||||
|
"learning_rate": 1.6128054926749403e-05,
|
||||||
|
"loss": 0.1245,
|
||||||
|
"loss_nan_ranks": 0,
|
||||||
|
"loss_rank_avg": 0.03604736179113388,
|
||||||
|
"step": 175,
|
||||||
|
"valid_targets_mean": 2452.0,
|
||||||
|
"valid_targets_min": 883
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 4.390243902439025,
|
||||||
|
"grad_norm": 0.660365938604491,
|
||||||
|
"learning_rate": 1.4941332352166385e-05,
|
||||||
|
"loss": 0.1253,
|
||||||
|
"loss_nan_ranks": 0,
|
||||||
|
"loss_rank_avg": 0.022628050297498703,
|
||||||
|
"step": 180,
|
||||||
|
"valid_targets_mean": 2193.5,
|
||||||
|
"valid_targets_min": 832
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 4.512195121951219,
|
||||||
|
"grad_norm": 0.6469748368984156,
|
||||||
|
"learning_rate": 1.3773355506460369e-05,
|
||||||
|
"loss": 0.1212,
|
||||||
|
"loss_nan_ranks": 0,
|
||||||
|
"loss_rank_avg": 0.04104577377438545,
|
||||||
|
"step": 185,
|
||||||
|
"valid_targets_mean": 2404.2,
|
||||||
|
"valid_targets_min": 491
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 4.634146341463414,
|
||||||
|
"grad_norm": 0.5688289937825557,
|
||||||
|
"learning_rate": 1.2628452520832766e-05,
|
||||||
|
"loss": 0.1289,
|
||||||
|
"loss_nan_ranks": 0,
|
||||||
|
"loss_rank_avg": 0.026066523045301437,
|
||||||
|
"step": 190,
|
||||||
|
"valid_targets_mean": 1617.0,
|
||||||
|
"valid_targets_min": 648
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 4.7560975609756095,
|
||||||
|
"grad_norm": 0.8846513600102238,
|
||||||
|
"learning_rate": 1.1510866022483702e-05,
|
||||||
|
"loss": 0.112,
|
||||||
|
"loss_nan_ranks": 0,
|
||||||
|
"loss_rank_avg": 0.03839657083153725,
|
||||||
|
"step": 195,
|
||||||
|
"valid_targets_mean": 2619.5,
|
||||||
|
"valid_targets_min": 832
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 4.878048780487805,
|
||||||
|
"grad_norm": 0.8205515547497473,
|
||||||
|
"learning_rate": 1.0424737412855825e-05,
|
||||||
|
"loss": 0.1243,
|
||||||
|
"loss_nan_ranks": 0,
|
||||||
|
"loss_rank_avg": 0.05243876576423645,
|
||||||
|
"step": 200,
|
||||||
|
"valid_targets_mean": 1985.8,
|
||||||
|
"valid_targets_min": 1428
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 5.0,
|
||||||
|
"grad_norm": 0.8961051415857917,
|
||||||
|
"learning_rate": 9.374091520986936e-06,
|
||||||
|
"loss": 0.144,
|
||||||
|
"loss_nan_ranks": 0,
|
||||||
|
"loss_rank_avg": 0.026954276487231255,
|
||||||
|
"step": 205,
|
||||||
|
"valid_targets_mean": 2568.2,
|
||||||
|
"valid_targets_min": 795
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 5.121951219512195,
|
||||||
|
"grad_norm": 0.6162209862161441,
|
||||||
|
"learning_rate": 8.362821688840947e-06,
|
||||||
|
"loss": 0.1142,
|
||||||
|
"loss_nan_ranks": 0,
|
||||||
|
"loss_rank_avg": 0.024338502436876297,
|
||||||
|
"step": 210,
|
||||||
|
"valid_targets_mean": 1392.8,
|
||||||
|
"valid_targets_min": 1031
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 5.2439024390243905,
|
||||||
|
"grad_norm": 0.8925372695642547,
|
||||||
|
"learning_rate": 7.394675343885827e-06,
|
||||||
|
"loss": 0.1041,
|
||||||
|
"loss_nan_ranks": 0,
|
||||||
|
"loss_rank_avg": 0.03295106813311577,
|
||||||
|
"step": 215,
|
||||||
|
"valid_targets_mean": 3177.8,
|
||||||
|
"valid_targets_min": 1031
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 5.365853658536586,
|
||||||
|
"grad_norm": 0.6073755624637226,
|
||||||
|
"learning_rate": 6.473240112381944e-06,
|
||||||
|
"loss": 0.1122,
|
||||||
|
"loss_nan_ranks": 0,
|
||||||
|
"loss_rank_avg": 0.02173219993710518,
|
||||||
|
"step": 220,
|
||||||
|
"valid_targets_mean": 3121.0,
|
||||||
|
"valid_targets_min": 1748
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 5.487804878048781,
|
||||||
|
"grad_norm": 1.040705900656647,
|
||||||
|
"learning_rate": 5.601930524840087e-06,
|
||||||
|
"loss": 0.1248,
|
||||||
|
"loss_nan_ranks": 0,
|
||||||
|
"loss_rank_avg": 0.025791862979531288,
|
||||||
|
"step": 225,
|
||||||
|
"valid_targets_mean": 2800.5,
|
||||||
|
"valid_targets_min": 929
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 5.609756097560975,
|
||||||
|
"grad_norm": 0.8950373265293078,
|
||||||
|
"learning_rate": 4.7839753629144395e-06,
|
||||||
|
"loss": 0.1106,
|
||||||
|
"loss_nan_ranks": 0,
|
||||||
|
"loss_rank_avg": 0.014685861766338348,
|
||||||
|
"step": 230,
|
||||||
|
"valid_targets_mean": 945.0,
|
||||||
|
"valid_targets_min": 421
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 5.7317073170731705,
|
||||||
|
"grad_norm": 0.7649064738807579,
|
||||||
|
"learning_rate": 4.022405694618659e-06,
|
||||||
|
"loss": 0.108,
|
||||||
|
"loss_nan_ranks": 0,
|
||||||
|
"loss_rank_avg": 0.02761884592473507,
|
||||||
|
"step": 235,
|
||||||
|
"valid_targets_mean": 1485.0,
|
||||||
|
"valid_targets_min": 331
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 5.853658536585366,
|
||||||
|
"grad_norm": 0.8719679552921337,
|
||||||
|
"learning_rate": 3.320043642202444e-06,
|
||||||
|
"loss": 0.1033,
|
||||||
|
"loss_nan_ranks": 0,
|
||||||
|
"loss_rank_avg": 0.03598159924149513,
|
||||||
|
"step": 240,
|
||||||
|
"valid_targets_mean": 3070.0,
|
||||||
|
"valid_targets_min": 1260
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 5.975609756097561,
|
||||||
|
"grad_norm": 0.6242438144503197,
|
||||||
|
"learning_rate": 2.679491924311226e-06,
|
||||||
|
"loss": 0.1044,
|
||||||
|
"loss_nan_ranks": 0,
|
||||||
|
"loss_rank_avg": 0.025556661188602448,
|
||||||
|
"step": 245,
|
||||||
|
"valid_targets_mean": 2245.0,
|
||||||
|
"valid_targets_min": 1069
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 6.097560975609756,
|
||||||
|
"grad_norm": 0.8732700455256523,
|
||||||
|
"learning_rate": 2.103124211182164e-06,
|
||||||
|
"loss": 0.1087,
|
||||||
|
"loss_nan_ranks": 0,
|
||||||
|
"loss_rank_avg": 0.03347954526543617,
|
||||||
|
"step": 250,
|
||||||
|
"valid_targets_mean": 1517.0,
|
||||||
|
"valid_targets_min": 606
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 6.219512195121951,
|
||||||
|
"grad_norm": 1.0111215639307505,
|
||||||
|
"learning_rate": 1.5930763286168138e-06,
|
||||||
|
"loss": 0.1049,
|
||||||
|
"loss_nan_ranks": 0,
|
||||||
|
"loss_rank_avg": 0.026082392781972885,
|
||||||
|
"step": 255,
|
||||||
|
"valid_targets_mean": 1642.8,
|
||||||
|
"valid_targets_min": 960
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 6.341463414634147,
|
||||||
|
"grad_norm": 0.7577281317860388,
|
||||||
|
"learning_rate": 1.1512383433257112e-06,
|
||||||
|
"loss": 0.0969,
|
||||||
|
"loss_nan_ranks": 0,
|
||||||
|
"loss_rank_avg": 0.01752658188343048,
|
||||||
|
"step": 260,
|
||||||
|
"valid_targets_mean": 2109.5,
|
||||||
|
"valid_targets_min": 999
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 6.463414634146342,
|
||||||
|
"grad_norm": 0.6730869279262718,
|
||||||
|
"learning_rate": 7.792475589738679e-07,
|
||||||
|
"loss": 0.1071,
|
||||||
|
"loss_nan_ranks": 0,
|
||||||
|
"loss_rank_avg": 0.020278798416256905,
|
||||||
|
"step": 265,
|
||||||
|
"valid_targets_mean": 1482.5,
|
||||||
|
"valid_targets_min": 859
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 6.585365853658536,
|
||||||
|
"grad_norm": 0.7854617549186186,
|
||||||
|
"learning_rate": 4.784824488814588e-07,
|
||||||
|
"loss": 0.1053,
|
||||||
|
"loss_nan_ranks": 0,
|
||||||
|
"loss_rank_avg": 0.022827567532658577,
|
||||||
|
"step": 270,
|
||||||
|
"valid_targets_mean": 2941.8,
|
||||||
|
"valid_targets_min": 695
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 6.7073170731707314,
|
||||||
|
"grad_norm": 0.5254164831244615,
|
||||||
|
"learning_rate": 2.5005754786317173e-07,
|
||||||
|
"loss": 0.1065,
|
||||||
|
"loss_nan_ranks": 0,
|
||||||
|
"loss_rank_avg": 0.022403722628951073,
|
||||||
|
"step": 275,
|
||||||
|
"valid_targets_mean": 2718.0,
|
||||||
|
"valid_targets_min": 1325
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 6.829268292682927,
|
||||||
|
"grad_norm": 0.6678257554250038,
|
||||||
|
"learning_rate": 9.481932213528444e-08,
|
||||||
|
"loss": 0.0987,
|
||||||
|
"loss_nan_ranks": 0,
|
||||||
|
"loss_rank_avg": 0.027537822723388672,
|
||||||
|
"step": 280,
|
||||||
|
"valid_targets_mean": 3525.0,
|
||||||
|
"valid_targets_min": 1519
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 6.951219512195122,
|
||||||
|
"grad_norm": 0.8096613625255807,
|
||||||
|
"learning_rate": 1.334303259521219e-08,
|
||||||
|
"loss": 0.1098,
|
||||||
|
"loss_nan_ranks": 0,
|
||||||
|
"loss_rank_avg": 0.03351534903049469,
|
||||||
|
"step": 285,
|
||||||
|
"valid_targets_mean": 1808.5,
|
||||||
|
"valid_targets_min": 1244
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"epoch": 7.0,
|
||||||
|
"loss_nan_ranks": 0,
|
||||||
|
"loss_rank_avg": 0.016517292708158493,
|
||||||
|
"step": 287,
|
||||||
|
"total_flos": 9.154523001624986e+16,
|
||||||
|
"train_loss": 0.17878121568558522,
|
||||||
|
"train_runtime": 15474.591,
|
||||||
|
"train_samples_per_second": 0.297,
|
||||||
|
"train_steps_per_second": 0.019,
|
||||||
|
"valid_targets_mean": 880.2,
|
||||||
|
"valid_targets_min": 562
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"logging_steps": 5,
|
||||||
|
"max_steps": 287,
|
||||||
|
"num_input_tokens_seen": 0,
|
||||||
|
"num_train_epochs": 7,
|
||||||
|
"save_steps": 1500,
|
||||||
|
"stateful_callbacks": {
|
||||||
|
"TrainerControl": {
|
||||||
|
"args": {
|
||||||
|
"should_epoch_stop": false,
|
||||||
|
"should_evaluate": false,
|
||||||
|
"should_log": false,
|
||||||
|
"should_save": true,
|
||||||
|
"should_training_stop": true
|
||||||
|
},
|
||||||
|
"attributes": {}
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"total_flos": 9.154523001624986e+16,
|
||||||
|
"train_batch_size": 1,
|
||||||
|
"trial_name": null,
|
||||||
|
"trial_params": null
|
||||||
|
}
|
||||||
3
training_args.bin
Normal file
3
training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:081ed296fbda74d5a990648160888648b0a835190f03851105212ccfab915dd5
|
||||||
|
size 8465
|
||||||
BIN
training_loss.png
Normal file
BIN
training_loss.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 38 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