初始化项目，由ModelHub XC社区提供模型
Model: penfever/kimi-k2-swesmith_with_plain_docker-sandboxes-maxeps-32k Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -0,0 +1,36 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
61
README.md
Normal file
61
README.md
Normal file
@@ -0,0 +1,61 @@
|
||||
---
|
||||
library_name: transformers
|
||||
license: apache-2.0
|
||||
base_model: Qwen/Qwen3-8B
|
||||
tags:
|
||||
- llama-factory
|
||||
- full
|
||||
- generated_from_trainer
|
||||
model-index:
|
||||
- name: kimi-k2-swesmith_with_plain_docker-sandboxes-maxeps-32k
|
||||
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. -->
|
||||
|
||||
# kimi-k2-swesmith_with_plain_docker-sandboxes-maxeps-32k
|
||||
|
||||
This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on the penfever/kimi-k2-swesmith_with_plain_docker-sandboxes-maxeps-32k 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: 8
|
||||
- gradient_accumulation_steps: 2
|
||||
- total_train_batch_size: 16
|
||||
- total_eval_batch_size: 64
|
||||
- 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 4.57.3
|
||||
- Pytorch 2.9.0+cu128
|
||||
- Datasets 4.4.1
|
||||
- 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": 6.380279250156325,
|
||||
"achieved_tflops_per_gpu_theoretical": 230.37751027197544,
|
||||
"epoch": 7.0,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.22618243098258972,
|
||||
"mfu_percent": 0.6451242922301643,
|
||||
"mfu_percent_theoretical": 23.293984860664857,
|
||||
"total_flos": 6.212778952973353e+17,
|
||||
"train_loss": 0.28838339830790105,
|
||||
"train_runtime": 12171.8398,
|
||||
"train_samples_per_second": 1.088,
|
||||
"train_steps_per_second": 0.068,
|
||||
"valid_targets_mean": 9237.2,
|
||||
"valid_targets_min": 6486
|
||||
}
|
||||
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": "4.57.3",
|
||||
"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": "4.57.3"
|
||||
}
|
||||
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 sha256:663967252827af414897b22d8d5194e0dd91b0372b7b83701e350dce0fb75706
|
||||
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:dc8c1b12ea8f9c22b0d2f6d9e9fd9b1e4f56374ff261ad78b60aaf50e1de658f
|
||||
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:bd6f5c809025a18172a88461e28b069f09a54c687a2dd13198d7752d9370e718
|
||||
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 sha256:63e35f2b97b4fd80d10bffe7c6eb299d8918b68a4b476629c076d6520b1b4184
|
||||
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"
|
||||
}
|
||||
}
|
||||
12
run_summary.json
Normal file
12
run_summary.json
Normal file
@@ -0,0 +1,12 @@
|
||||
{
|
||||
"agent_name": null,
|
||||
"training_start": null,
|
||||
"training_end": null,
|
||||
"created_by": "DCAgent",
|
||||
"base_model_name": "Qwen/Qwen3-8B",
|
||||
"dataset_name": "penfever/kimi-k2-swesmith_with_plain_docker-sandboxes-maxeps-32k",
|
||||
"training_type": "SFT",
|
||||
"training_parameters": "https://huggingface.co/penfever/kimi-k2-swesmith_with_plain_docker-sandboxes-maxeps-32k/blob/main/config.json",
|
||||
"wandb_link": "https://wandb.ai/DCAgent/OpenThoughts-Agent/runs/kimi-k2-swesmith_with_plain_docker-sandboxes-maxeps-32k_Qwen3-8B",
|
||||
"traces_location_s3": null
|
||||
}
|
||||
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": 6.380279250156325,
|
||||
"achieved_tflops_per_gpu_theoretical": 230.37751027197544,
|
||||
"epoch": 7.0,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.22618243098258972,
|
||||
"mfu_percent": 0.6451242922301643,
|
||||
"mfu_percent_theoretical": 23.293984860664857,
|
||||
"total_flos": 6.212778952973353e+17,
|
||||
"train_loss": 0.28838339830790105,
|
||||
"train_runtime": 12171.8398,
|
||||
"train_samples_per_second": 1.088,
|
||||
"train_steps_per_second": 0.068,
|
||||
"valid_targets_mean": 9237.2,
|
||||
"valid_targets_min": 6486
|
||||
}
|
||||
167
trainer_log.jsonl
Normal file
167
trainer_log.jsonl
Normal file
@@ -0,0 +1,167 @@
|
||||
{"current_steps": 5, "total_steps": 833, "loss": 0.8138, "lr": 1.904761904761905e-06, "epoch": 0.04219409282700422, "percentage": 0.6, "elapsed_time": "0:01:18", "remaining_time": "3:37:55"}
|
||||
{"current_steps": 10, "total_steps": 833, "loss": 0.7793, "lr": 4.2857142857142855e-06, "epoch": 0.08438818565400844, "percentage": 1.2, "elapsed_time": "0:02:35", "remaining_time": "3:33:26"}
|
||||
{"current_steps": 15, "total_steps": 833, "loss": 0.6819, "lr": 6.666666666666667e-06, "epoch": 0.12658227848101267, "percentage": 1.8, "elapsed_time": "0:03:50", "remaining_time": "3:29:28"}
|
||||
{"current_steps": 20, "total_steps": 833, "loss": 0.6067, "lr": 9.047619047619049e-06, "epoch": 0.16877637130801687, "percentage": 2.4, "elapsed_time": "0:05:05", "remaining_time": "3:26:55"}
|
||||
{"current_steps": 25, "total_steps": 833, "loss": 0.5663, "lr": 1.1428571428571429e-05, "epoch": 0.2109704641350211, "percentage": 3.0, "elapsed_time": "0:06:21", "remaining_time": "3:25:29"}
|
||||
{"current_steps": 30, "total_steps": 833, "loss": 0.5036, "lr": 1.3809523809523811e-05, "epoch": 0.25316455696202533, "percentage": 3.6, "elapsed_time": "0:07:34", "remaining_time": "3:22:51"}
|
||||
{"current_steps": 35, "total_steps": 833, "loss": 0.4921, "lr": 1.6190476190476193e-05, "epoch": 0.29535864978902954, "percentage": 4.2, "elapsed_time": "0:08:48", "remaining_time": "3:20:45"}
|
||||
{"current_steps": 40, "total_steps": 833, "loss": 0.4657, "lr": 1.8571428571428575e-05, "epoch": 0.33755274261603374, "percentage": 4.8, "elapsed_time": "0:10:00", "remaining_time": "3:18:27"}
|
||||
{"current_steps": 45, "total_steps": 833, "loss": 0.4481, "lr": 2.0952380952380954e-05, "epoch": 0.379746835443038, "percentage": 5.4, "elapsed_time": "0:11:11", "remaining_time": "3:16:06"}
|
||||
{"current_steps": 50, "total_steps": 833, "loss": 0.4218, "lr": 2.3333333333333336e-05, "epoch": 0.4219409282700422, "percentage": 6.0, "elapsed_time": "0:12:23", "remaining_time": "3:14:01"}
|
||||
{"current_steps": 55, "total_steps": 833, "loss": 0.4183, "lr": 2.5714285714285718e-05, "epoch": 0.4641350210970464, "percentage": 6.6, "elapsed_time": "0:13:34", "remaining_time": "3:12:00"}
|
||||
{"current_steps": 60, "total_steps": 833, "loss": 0.407, "lr": 2.8095238095238096e-05, "epoch": 0.5063291139240507, "percentage": 7.2, "elapsed_time": "0:14:45", "remaining_time": "3:10:13"}
|
||||
{"current_steps": 65, "total_steps": 833, "loss": 0.3993, "lr": 3.047619047619048e-05, "epoch": 0.5485232067510548, "percentage": 7.8, "elapsed_time": "0:15:58", "remaining_time": "3:08:47"}
|
||||
{"current_steps": 70, "total_steps": 833, "loss": 0.3694, "lr": 3.285714285714286e-05, "epoch": 0.5907172995780591, "percentage": 8.4, "elapsed_time": "0:17:10", "remaining_time": "3:07:07"}
|
||||
{"current_steps": 75, "total_steps": 833, "loss": 0.3914, "lr": 3.523809523809524e-05, "epoch": 0.6329113924050633, "percentage": 9.0, "elapsed_time": "0:18:21", "remaining_time": "3:05:30"}
|
||||
{"current_steps": 80, "total_steps": 833, "loss": 0.3652, "lr": 3.761904761904762e-05, "epoch": 0.6751054852320675, "percentage": 9.6, "elapsed_time": "0:19:34", "remaining_time": "3:04:17"}
|
||||
{"current_steps": 85, "total_steps": 833, "loss": 0.3363, "lr": 4e-05, "epoch": 0.7172995780590717, "percentage": 10.2, "elapsed_time": "0:20:47", "remaining_time": "3:02:57"}
|
||||
{"current_steps": 90, "total_steps": 833, "loss": 0.3515, "lr": 3.9995601949609725e-05, "epoch": 0.759493670886076, "percentage": 10.8, "elapsed_time": "0:22:00", "remaining_time": "3:01:38"}
|
||||
{"current_steps": 95, "total_steps": 833, "loss": 0.3544, "lr": 3.998240973272361e-05, "epoch": 0.8016877637130801, "percentage": 11.4, "elapsed_time": "0:23:13", "remaining_time": "3:00:27"}
|
||||
{"current_steps": 100, "total_steps": 833, "loss": 0.355, "lr": 3.996042915134512e-05, "epoch": 0.8438818565400844, "percentage": 12.0, "elapsed_time": "0:24:26", "remaining_time": "2:59:07"}
|
||||
{"current_steps": 105, "total_steps": 833, "loss": 0.3417, "lr": 3.9929669872644716e-05, "epoch": 0.8860759493670886, "percentage": 12.61, "elapsed_time": "0:25:37", "remaining_time": "2:57:38"}
|
||||
{"current_steps": 110, "total_steps": 833, "loss": 0.3378, "lr": 3.989014542470815e-05, "epoch": 0.9282700421940928, "percentage": 13.21, "elapsed_time": "0:26:48", "remaining_time": "2:56:12"}
|
||||
{"current_steps": 115, "total_steps": 833, "loss": 0.3441, "lr": 3.98418731905868e-05, "epoch": 0.9704641350210971, "percentage": 13.81, "elapsed_time": "0:28:01", "remaining_time": "2:54:55"}
|
||||
{"current_steps": 120, "total_steps": 833, "loss": 0.3478, "lr": 3.978487440065248e-05, "epoch": 1.0084388185654007, "percentage": 14.41, "elapsed_time": "0:29:08", "remaining_time": "2:53:11"}
|
||||
{"current_steps": 125, "total_steps": 833, "loss": 0.3238, "lr": 3.9719174123260214e-05, "epoch": 1.0506329113924051, "percentage": 15.01, "elapsed_time": "0:30:19", "remaining_time": "2:51:47"}
|
||||
{"current_steps": 130, "total_steps": 833, "loss": 0.3114, "lr": 3.964480125372307e-05, "epoch": 1.0928270042194093, "percentage": 15.61, "elapsed_time": "0:31:33", "remaining_time": "2:50:41"}
|
||||
{"current_steps": 135, "total_steps": 833, "loss": 0.3161, "lr": 3.9561788501603836e-05, "epoch": 1.1350210970464134, "percentage": 16.21, "elapsed_time": "0:32:46", "remaining_time": "2:49:25"}
|
||||
{"current_steps": 140, "total_steps": 833, "loss": 0.3225, "lr": 3.94701723763292e-05, "epoch": 1.1772151898734178, "percentage": 16.81, "elapsed_time": "0:33:58", "remaining_time": "2:48:10"}
|
||||
{"current_steps": 145, "total_steps": 833, "loss": 0.3243, "lr": 3.936999317113271e-05, "epoch": 1.219409282700422, "percentage": 17.41, "elapsed_time": "0:35:12", "remaining_time": "2:47:04"}
|
||||
{"current_steps": 150, "total_steps": 833, "loss": 0.3125, "lr": 3.926129494533362e-05, "epoch": 1.261603375527426, "percentage": 18.01, "elapsed_time": "0:36:25", "remaining_time": "2:45:51"}
|
||||
{"current_steps": 155, "total_steps": 833, "loss": 0.3189, "lr": 3.914412550495937e-05, "epoch": 1.3037974683544304, "percentage": 18.61, "elapsed_time": "0:37:36", "remaining_time": "2:44:28"}
|
||||
{"current_steps": 160, "total_steps": 833, "loss": 0.3179, "lr": 3.901853638172025e-05, "epoch": 1.3459915611814346, "percentage": 19.21, "elapsed_time": "0:38:46", "remaining_time": "2:43:05"}
|
||||
{"current_steps": 165, "total_steps": 833, "loss": 0.2767, "lr": 3.888458281034551e-05, "epoch": 1.3881856540084387, "percentage": 19.81, "elapsed_time": "0:39:56", "remaining_time": "2:41:43"}
|
||||
{"current_steps": 170, "total_steps": 833, "loss": 0.3099, "lr": 3.874232370429085e-05, "epoch": 1.4303797468354431, "percentage": 20.41, "elapsed_time": "0:41:08", "remaining_time": "2:40:26"}
|
||||
{"current_steps": 175, "total_steps": 833, "loss": 0.3101, "lr": 3.8591821629827946e-05, "epoch": 1.4725738396624473, "percentage": 21.01, "elapsed_time": "0:42:18", "remaining_time": "2:39:05"}
|
||||
{"current_steps": 180, "total_steps": 833, "loss": 0.3149, "lr": 3.8433142778527536e-05, "epoch": 1.5147679324894514, "percentage": 21.61, "elapsed_time": "0:43:31", "remaining_time": "2:37:53"}
|
||||
{"current_steps": 185, "total_steps": 833, "loss": 0.3003, "lr": 3.826635693814801e-05, "epoch": 1.5569620253164556, "percentage": 22.21, "elapsed_time": "0:44:41", "remaining_time": "2:36:32"}
|
||||
{"current_steps": 190, "total_steps": 833, "loss": 0.3262, "lr": 3.8091537461942395e-05, "epoch": 1.59915611814346, "percentage": 22.81, "elapsed_time": "0:45:54", "remaining_time": "2:35:20"}
|
||||
{"current_steps": 195, "total_steps": 833, "loss": 0.2855, "lr": 3.7908761236397265e-05, "epoch": 1.6413502109704643, "percentage": 23.41, "elapsed_time": "0:47:05", "remaining_time": "2:34:04"}
|
||||
{"current_steps": 200, "total_steps": 833, "loss": 0.2953, "lr": 3.771810864741761e-05, "epoch": 1.6835443037974684, "percentage": 24.01, "elapsed_time": "0:48:17", "remaining_time": "2:32:50"}
|
||||
{"current_steps": 205, "total_steps": 833, "loss": 0.3126, "lr": 3.751966354497278e-05, "epoch": 1.7257383966244726, "percentage": 24.61, "elapsed_time": "0:50:07", "remaining_time": "2:33:33"}
|
||||
{"current_steps": 210, "total_steps": 833, "loss": 0.3115, "lr": 3.7313513206218794e-05, "epoch": 1.7679324894514767, "percentage": 25.21, "elapsed_time": "0:51:20", "remaining_time": "2:32:18"}
|
||||
{"current_steps": 215, "total_steps": 833, "loss": 0.3157, "lr": 3.709974829711344e-05, "epoch": 1.810126582278481, "percentage": 25.81, "elapsed_time": "0:52:30", "remaining_time": "2:30:57"}
|
||||
{"current_steps": 220, "total_steps": 833, "loss": 0.3129, "lr": 3.6878462832540903e-05, "epoch": 1.8523206751054853, "percentage": 26.41, "elapsed_time": "0:53:44", "remaining_time": "2:29:45"}
|
||||
{"current_steps": 225, "total_steps": 833, "loss": 0.3011, "lr": 3.6649754134963564e-05, "epoch": 1.8945147679324894, "percentage": 27.01, "elapsed_time": "0:54:56", "remaining_time": "2:28:27"}
|
||||
{"current_steps": 230, "total_steps": 833, "loss": 0.3079, "lr": 3.64137227916191e-05, "epoch": 1.9367088607594938, "percentage": 27.61, "elapsed_time": "0:56:09", "remaining_time": "2:27:15"}
|
||||
{"current_steps": 235, "total_steps": 833, "loss": 0.2883, "lr": 3.6170472610281674e-05, "epoch": 1.978902953586498, "percentage": 28.21, "elapsed_time": "0:57:21", "remaining_time": "2:25:57"}
|
||||
{"current_steps": 240, "total_steps": 833, "loss": 0.2784, "lr": 3.592011057360678e-05, "epoch": 2.0168776371308015, "percentage": 28.81, "elapsed_time": "0:58:27", "remaining_time": "2:24:27"}
|
||||
{"current_steps": 245, "total_steps": 833, "loss": 0.2875, "lr": 3.5662746792079726e-05, "epoch": 2.059071729957806, "percentage": 29.41, "elapsed_time": "0:59:38", "remaining_time": "2:23:09"}
|
||||
{"current_steps": 250, "total_steps": 833, "loss": 0.2765, "lr": 3.53984944555885e-05, "epoch": 2.1012658227848102, "percentage": 30.01, "elapsed_time": "1:00:52", "remaining_time": "2:21:58"}
|
||||
{"current_steps": 255, "total_steps": 833, "loss": 0.2902, "lr": 3.512746978364227e-05, "epoch": 2.1434599156118144, "percentage": 30.61, "elapsed_time": "1:02:07", "remaining_time": "2:20:48"}
|
||||
{"current_steps": 260, "total_steps": 833, "loss": 0.287, "lr": 3.484979197425745e-05, "epoch": 2.1856540084388185, "percentage": 31.21, "elapsed_time": "1:03:18", "remaining_time": "2:19:31"}
|
||||
{"current_steps": 265, "total_steps": 833, "loss": 0.278, "lr": 3.456558315153382e-05, "epoch": 2.2278481012658227, "percentage": 31.81, "elapsed_time": "1:04:29", "remaining_time": "2:18:14"}
|
||||
{"current_steps": 270, "total_steps": 833, "loss": 0.2854, "lr": 3.427496831194378e-05, "epoch": 2.270042194092827, "percentage": 32.41, "elapsed_time": "1:05:38", "remaining_time": "2:16:52"}
|
||||
{"current_steps": 275, "total_steps": 833, "loss": 0.2797, "lr": 3.3978075269358175e-05, "epoch": 2.3122362869198314, "percentage": 33.01, "elapsed_time": "1:06:49", "remaining_time": "2:15:35"}
|
||||
{"current_steps": 280, "total_steps": 833, "loss": 0.286, "lr": 3.3675034598833196e-05, "epoch": 2.3544303797468356, "percentage": 33.61, "elapsed_time": "1:08:01", "remaining_time": "2:14:21"}
|
||||
{"current_steps": 285, "total_steps": 833, "loss": 0.2841, "lr": 3.3365979579182774e-05, "epoch": 2.3966244725738397, "percentage": 34.21, "elapsed_time": "1:09:12", "remaining_time": "2:13:04"}
|
||||
{"current_steps": 290, "total_steps": 833, "loss": 0.2717, "lr": 3.3051046134361874e-05, "epoch": 2.438818565400844, "percentage": 34.81, "elapsed_time": "1:10:23", "remaining_time": "2:11:48"}
|
||||
{"current_steps": 295, "total_steps": 833, "loss": 0.2703, "lr": 3.27303727736865e-05, "epoch": 2.481012658227848, "percentage": 35.41, "elapsed_time": "1:11:36", "remaining_time": "2:10:36"}
|
||||
{"current_steps": 300, "total_steps": 833, "loss": 0.2754, "lr": 3.2404100530916555e-05, "epoch": 2.523206751054852, "percentage": 36.01, "elapsed_time": "1:12:48", "remaining_time": "2:09:21"}
|
||||
{"current_steps": 305, "total_steps": 833, "loss": 0.2699, "lr": 3.20723729022285e-05, "epoch": 2.5654008438818563, "percentage": 36.61, "elapsed_time": "1:14:00", "remaining_time": "2:08:07"}
|
||||
{"current_steps": 310, "total_steps": 833, "loss": 0.2846, "lr": 3.173533578310503e-05, "epoch": 2.607594936708861, "percentage": 37.21, "elapsed_time": "1:15:12", "remaining_time": "2:06:52"}
|
||||
{"current_steps": 315, "total_steps": 833, "loss": 0.2734, "lr": 3.139313740416945e-05, "epoch": 2.649789029535865, "percentage": 37.82, "elapsed_time": "1:16:22", "remaining_time": "2:05:35"}
|
||||
{"current_steps": 320, "total_steps": 833, "loss": 0.2682, "lr": 3.104592826599319e-05, "epoch": 2.691983122362869, "percentage": 38.42, "elapsed_time": "1:17:34", "remaining_time": "2:04:22"}
|
||||
{"current_steps": 325, "total_steps": 833, "loss": 0.2744, "lr": 3.06938610729048e-05, "epoch": 2.7341772151898733, "percentage": 39.02, "elapsed_time": "1:18:46", "remaining_time": "2:03:07"}
|
||||
{"current_steps": 330, "total_steps": 833, "loss": 0.2861, "lr": 3.0337090665829883e-05, "epoch": 2.7763713080168775, "percentage": 39.62, "elapsed_time": "1:19:58", "remaining_time": "2:01:54"}
|
||||
{"current_steps": 335, "total_steps": 833, "loss": 0.2847, "lr": 2.9975773954191246e-05, "epoch": 2.818565400843882, "percentage": 40.22, "elapsed_time": "1:21:12", "remaining_time": "2:00:43"}
|
||||
{"current_steps": 340, "total_steps": 833, "loss": 0.2798, "lr": 2.9610069846899355e-05, "epoch": 2.8607594936708862, "percentage": 40.82, "elapsed_time": "1:22:26", "remaining_time": "1:59:31"}
|
||||
{"current_steps": 345, "total_steps": 833, "loss": 0.2798, "lr": 2.9240139182463384e-05, "epoch": 2.9029535864978904, "percentage": 41.42, "elapsed_time": "1:23:37", "remaining_time": "1:58:17"}
|
||||
{"current_steps": 350, "total_steps": 833, "loss": 0.2826, "lr": 2.8866144658253642e-05, "epoch": 2.9451476793248945, "percentage": 42.02, "elapsed_time": "1:24:49", "remaining_time": "1:57:03"}
|
||||
{"current_steps": 355, "total_steps": 833, "loss": 0.2709, "lr": 2.8488250758946453e-05, "epoch": 2.9873417721518987, "percentage": 42.62, "elapsed_time": "1:26:01", "remaining_time": "1:55:49"}
|
||||
{"current_steps": 360, "total_steps": 833, "loss": 0.2549, "lr": 2.8106623684182944e-05, "epoch": 3.0253164556962027, "percentage": 43.22, "elapsed_time": "1:27:07", "remaining_time": "1:54:28"}
|
||||
{"current_steps": 365, "total_steps": 833, "loss": 0.2587, "lr": 2.7721431275473634e-05, "epoch": 3.067510548523207, "percentage": 43.82, "elapsed_time": "1:28:18", "remaining_time": "1:53:13"}
|
||||
{"current_steps": 370, "total_steps": 833, "loss": 0.2606, "lr": 2.733284294238086e-05, "epoch": 3.109704641350211, "percentage": 44.42, "elapsed_time": "1:29:29", "remaining_time": "1:51:59"}
|
||||
{"current_steps": 375, "total_steps": 833, "loss": 0.261, "lr": 2.694102958801163e-05, "epoch": 3.151898734177215, "percentage": 45.02, "elapsed_time": "1:30:39", "remaining_time": "1:50:43"}
|
||||
{"current_steps": 380, "total_steps": 833, "loss": 0.2545, "lr": 2.654616353385354e-05, "epoch": 3.1940928270042193, "percentage": 45.62, "elapsed_time": "1:31:53", "remaining_time": "1:49:32"}
|
||||
{"current_steps": 385, "total_steps": 833, "loss": 0.2573, "lr": 2.6148418443986967e-05, "epoch": 3.2362869198312234, "percentage": 46.22, "elapsed_time": "1:33:04", "remaining_time": "1:48:18"}
|
||||
{"current_steps": 390, "total_steps": 833, "loss": 0.2647, "lr": 2.5747969248706675e-05, "epoch": 3.278481012658228, "percentage": 46.82, "elapsed_time": "1:34:17", "remaining_time": "1:47:05"}
|
||||
{"current_steps": 395, "total_steps": 833, "loss": 0.2647, "lr": 2.5344992067586623e-05, "epoch": 3.320675105485232, "percentage": 47.42, "elapsed_time": "1:35:30", "remaining_time": "1:45:54"}
|
||||
{"current_steps": 400, "total_steps": 833, "loss": 0.2558, "lr": 2.4939664132021685e-05, "epoch": 3.3628691983122363, "percentage": 48.02, "elapsed_time": "1:36:43", "remaining_time": "1:44:41"}
|
||||
{"current_steps": 405, "total_steps": 833, "loss": 0.2628, "lr": 2.4532163707280372e-05, "epoch": 3.4050632911392404, "percentage": 48.62, "elapsed_time": "1:38:31", "remaining_time": "1:44:07"}
|
||||
{"current_steps": 410, "total_steps": 833, "loss": 0.262, "lr": 2.4122670014102905e-05, "epoch": 3.4472573839662446, "percentage": 49.22, "elapsed_time": "1:39:44", "remaining_time": "1:42:54"}
|
||||
{"current_steps": 415, "total_steps": 833, "loss": 0.2822, "lr": 2.371136314987898e-05, "epoch": 3.489451476793249, "percentage": 49.82, "elapsed_time": "1:40:57", "remaining_time": "1:41:40"}
|
||||
{"current_steps": 420, "total_steps": 833, "loss": 0.2528, "lr": 2.329842400944008e-05, "epoch": 3.5316455696202533, "percentage": 50.42, "elapsed_time": "1:42:08", "remaining_time": "1:40:26"}
|
||||
{"current_steps": 425, "total_steps": 833, "loss": 0.2575, "lr": 2.2884034205500977e-05, "epoch": 3.5738396624472575, "percentage": 51.02, "elapsed_time": "1:43:22", "remaining_time": "1:39:14"}
|
||||
{"current_steps": 430, "total_steps": 833, "loss": 0.2728, "lr": 2.246837598878557e-05, "epoch": 3.6160337552742616, "percentage": 51.62, "elapsed_time": "1:44:34", "remaining_time": "1:38:00"}
|
||||
{"current_steps": 435, "total_steps": 833, "loss": 0.2645, "lr": 2.2051632167872072e-05, "epoch": 3.6582278481012658, "percentage": 52.22, "elapsed_time": "1:45:48", "remaining_time": "1:36:48"}
|
||||
{"current_steps": 440, "total_steps": 833, "loss": 0.2468, "lr": 2.1633986028792915e-05, "epoch": 3.70042194092827, "percentage": 52.82, "elapsed_time": "1:47:01", "remaining_time": "1:35:35"}
|
||||
{"current_steps": 445, "total_steps": 833, "loss": 0.2621, "lr": 2.1215621254424592e-05, "epoch": 3.742616033755274, "percentage": 53.42, "elapsed_time": "1:48:14", "remaining_time": "1:34:22"}
|
||||
{"current_steps": 450, "total_steps": 833, "loss": 0.2667, "lr": 2.0796721843703028e-05, "epoch": 3.7848101265822782, "percentage": 54.02, "elapsed_time": "1:49:27", "remaining_time": "1:33:09"}
|
||||
{"current_steps": 455, "total_steps": 833, "loss": 0.2561, "lr": 2.0377472030699895e-05, "epoch": 3.827004219409283, "percentage": 54.62, "elapsed_time": "1:50:38", "remaining_time": "1:31:54"}
|
||||
{"current_steps": 460, "total_steps": 833, "loss": 0.2535, "lr": 1.995805620359557e-05, "epoch": 3.869198312236287, "percentage": 55.22, "elapsed_time": "1:51:49", "remaining_time": "1:30:40"}
|
||||
{"current_steps": 465, "total_steps": 833, "loss": 0.2492, "lr": 1.9538658823584258e-05, "epoch": 3.911392405063291, "percentage": 55.82, "elapsed_time": "1:53:01", "remaining_time": "1:29:26"}
|
||||
{"current_steps": 470, "total_steps": 833, "loss": 0.2576, "lr": 1.9119464343747048e-05, "epoch": 3.9535864978902953, "percentage": 56.42, "elapsed_time": "1:54:13", "remaining_time": "1:28:13"}
|
||||
{"current_steps": 475, "total_steps": 833, "loss": 0.2579, "lr": 1.8700657127928495e-05, "epoch": 3.9957805907173, "percentage": 57.02, "elapsed_time": "1:55:25", "remaining_time": "1:26:59"}
|
||||
{"current_steps": 480, "total_steps": 833, "loss": 0.2473, "lr": 1.8282421369652514e-05, "epoch": 4.033755274261603, "percentage": 57.62, "elapsed_time": "1:56:31", "remaining_time": "1:25:41"}
|
||||
{"current_steps": 485, "total_steps": 833, "loss": 0.2435, "lr": 1.786494101111308e-05, "epoch": 4.075949367088608, "percentage": 58.22, "elapsed_time": "1:57:42", "remaining_time": "1:24:27"}
|
||||
{"current_steps": 490, "total_steps": 833, "loss": 0.2358, "lr": 1.7448399662275577e-05, "epoch": 4.118143459915612, "percentage": 58.82, "elapsed_time": "1:58:53", "remaining_time": "1:23:13"}
|
||||
{"current_steps": 495, "total_steps": 833, "loss": 0.2587, "lr": 1.70329805201242e-05, "epoch": 4.160337552742616, "percentage": 59.42, "elapsed_time": "2:00:07", "remaining_time": "1:22:01"}
|
||||
{"current_steps": 500, "total_steps": 833, "loss": 0.2417, "lr": 1.661886628809096e-05, "epoch": 4.2025316455696204, "percentage": 60.02, "elapsed_time": "2:01:18", "remaining_time": "1:20:47"}
|
||||
{"current_steps": 505, "total_steps": 833, "loss": 0.2521, "lr": 1.620623909570185e-05, "epoch": 4.244725738396625, "percentage": 60.62, "elapsed_time": "2:02:29", "remaining_time": "1:19:33"}
|
||||
{"current_steps": 510, "total_steps": 833, "loss": 0.2501, "lr": 1.5795280418475313e-05, "epoch": 4.286919831223629, "percentage": 61.22, "elapsed_time": "2:03:41", "remaining_time": "1:18:20"}
|
||||
{"current_steps": 515, "total_steps": 833, "loss": 0.2508, "lr": 1.5386170998108432e-05, "epoch": 4.329113924050633, "percentage": 61.82, "elapsed_time": "2:04:54", "remaining_time": "1:17:07"}
|
||||
{"current_steps": 520, "total_steps": 833, "loss": 0.2393, "lr": 1.4979090762985793e-05, "epoch": 4.371308016877637, "percentage": 62.42, "elapsed_time": "2:06:07", "remaining_time": "1:15:54"}
|
||||
{"current_steps": 525, "total_steps": 833, "loss": 0.2479, "lr": 1.4574218749046097e-05, "epoch": 4.413502109704641, "percentage": 63.03, "elapsed_time": "2:07:17", "remaining_time": "1:14:40"}
|
||||
{"current_steps": 530, "total_steps": 833, "loss": 0.2522, "lr": 1.4171733021041236e-05, "epoch": 4.455696202531645, "percentage": 63.63, "elapsed_time": "2:08:28", "remaining_time": "1:13:26"}
|
||||
{"current_steps": 535, "total_steps": 833, "loss": 0.2438, "lr": 1.3771810594222522e-05, "epoch": 4.4978902953586495, "percentage": 64.23, "elapsed_time": "2:09:39", "remaining_time": "1:12:12"}
|
||||
{"current_steps": 540, "total_steps": 833, "loss": 0.2346, "lr": 1.3374627356488486e-05, "epoch": 4.540084388185654, "percentage": 64.83, "elapsed_time": "2:10:50", "remaining_time": "1:10:59"}
|
||||
{"current_steps": 545, "total_steps": 833, "loss": 0.2628, "lr": 1.2980357991028504e-05, "epoch": 4.582278481012658, "percentage": 65.43, "elapsed_time": "2:12:02", "remaining_time": "1:09:46"}
|
||||
{"current_steps": 550, "total_steps": 833, "loss": 0.252, "lr": 1.2589175899496241e-05, "epoch": 4.624472573839663, "percentage": 66.03, "elapsed_time": "2:13:15", "remaining_time": "1:08:33"}
|
||||
{"current_steps": 555, "total_steps": 833, "loss": 0.2471, "lr": 1.2201253125746733e-05, "epoch": 4.666666666666667, "percentage": 66.63, "elapsed_time": "2:14:27", "remaining_time": "1:07:21"}
|
||||
{"current_steps": 560, "total_steps": 833, "loss": 0.2474, "lr": 1.1816760280170615e-05, "epoch": 4.708860759493671, "percentage": 67.23, "elapsed_time": "2:15:41", "remaining_time": "1:06:08"}
|
||||
{"current_steps": 565, "total_steps": 833, "loss": 0.236, "lr": 1.1435866464658856e-05, "epoch": 4.751054852320675, "percentage": 67.83, "elapsed_time": "2:16:50", "remaining_time": "1:04:54"}
|
||||
{"current_steps": 570, "total_steps": 833, "loss": 0.2307, "lr": 1.1058739198230856e-05, "epoch": 4.793248945147679, "percentage": 68.43, "elapsed_time": "2:18:00", "remaining_time": "1:03:40"}
|
||||
{"current_steps": 575, "total_steps": 833, "loss": 0.2498, "lr": 1.0685544343358729e-05, "epoch": 4.8354430379746836, "percentage": 69.03, "elapsed_time": "2:19:14", "remaining_time": "1:02:28"}
|
||||
{"current_steps": 580, "total_steps": 833, "loss": 0.2379, "lr": 1.0316446033020198e-05, "epoch": 4.877637130801688, "percentage": 69.63, "elapsed_time": "2:20:25", "remaining_time": "1:01:15"}
|
||||
{"current_steps": 585, "total_steps": 833, "loss": 0.258, "lr": 9.951606598512042e-06, "epoch": 4.919831223628692, "percentage": 70.23, "elapsed_time": "2:21:39", "remaining_time": "1:00:03"}
|
||||
{"current_steps": 590, "total_steps": 833, "loss": 0.2328, "lr": 9.591186498056004e-06, "epoch": 4.962025316455696, "percentage": 70.83, "elapsed_time": "2:22:50", "remaining_time": "0:58:49"}
|
||||
{"current_steps": 595, "total_steps": 833, "loss": 0.2463, "lr": 9.235344246228415e-06, "epoch": 5.0, "percentage": 71.43, "elapsed_time": "2:23:53", "remaining_time": "0:57:33"}
|
||||
{"current_steps": 600, "total_steps": 833, "loss": 0.239, "lr": 8.884236344244734e-06, "epoch": 5.042194092827004, "percentage": 72.03, "elapsed_time": "2:25:03", "remaining_time": "0:56:19"}
|
||||
{"current_steps": 605, "total_steps": 833, "loss": 0.2267, "lr": 8.538017211129501e-06, "epoch": 5.084388185654008, "percentage": 72.63, "elapsed_time": "2:26:54", "remaining_time": "0:55:21"}
|
||||
{"current_steps": 610, "total_steps": 833, "loss": 0.2416, "lr": 8.196839115802071e-06, "epoch": 5.1265822784810124, "percentage": 73.23, "elapsed_time": "2:28:07", "remaining_time": "0:54:08"}
|
||||
{"current_steps": 615, "total_steps": 833, "loss": 0.236, "lr": 7.860852110107952e-06, "epoch": 5.168776371308017, "percentage": 73.83, "elapsed_time": "2:29:17", "remaining_time": "0:52:55"}
|
||||
{"current_steps": 620, "total_steps": 833, "loss": 0.2438, "lr": 7.530203962825331e-06, "epoch": 5.210970464135021, "percentage": 74.43, "elapsed_time": "2:30:30", "remaining_time": "0:51:42"}
|
||||
{"current_steps": 625, "total_steps": 833, "loss": 0.2403, "lr": 7.205040094675502e-06, "epoch": 5.253164556962025, "percentage": 75.03, "elapsed_time": "2:31:42", "remaining_time": "0:50:29"}
|
||||
{"current_steps": 630, "total_steps": 833, "loss": 0.239, "lr": 6.885503514366203e-06, "epoch": 5.29535864978903, "percentage": 75.63, "elapsed_time": "2:32:53", "remaining_time": "0:49:16"}
|
||||
{"current_steps": 635, "total_steps": 833, "loss": 0.23, "lr": 6.571734755695584e-06, "epoch": 5.337552742616034, "percentage": 76.23, "elapsed_time": "2:34:04", "remaining_time": "0:48:02"}
|
||||
{"current_steps": 640, "total_steps": 833, "loss": 0.2342, "lr": 6.2638718157448285e-06, "epoch": 5.379746835443038, "percentage": 76.83, "elapsed_time": "2:35:16", "remaining_time": "0:46:49"}
|
||||
{"current_steps": 645, "total_steps": 833, "loss": 0.2402, "lr": 5.962050094186236e-06, "epoch": 5.421940928270042, "percentage": 77.43, "elapsed_time": "2:36:27", "remaining_time": "0:45:36"}
|
||||
{"current_steps": 650, "total_steps": 833, "loss": 0.2372, "lr": 5.666402333733843e-06, "epoch": 5.4641350210970465, "percentage": 78.03, "elapsed_time": "2:37:39", "remaining_time": "0:44:23"}
|
||||
{"current_steps": 655, "total_steps": 833, "loss": 0.2344, "lr": 5.377058561762474e-06, "epoch": 5.506329113924051, "percentage": 78.63, "elapsed_time": "2:38:52", "remaining_time": "0:43:10"}
|
||||
{"current_steps": 660, "total_steps": 833, "loss": 0.231, "lr": 5.094146033121057e-06, "epoch": 5.548523206751055, "percentage": 79.23, "elapsed_time": "2:40:03", "remaining_time": "0:41:57"}
|
||||
{"current_steps": 665, "total_steps": 833, "loss": 0.2572, "lr": 4.817789174165281e-06, "epoch": 5.590717299578059, "percentage": 79.83, "elapsed_time": "2:41:16", "remaining_time": "0:40:44"}
|
||||
{"current_steps": 670, "total_steps": 833, "loss": 0.2359, "lr": 4.5481095280342925e-06, "epoch": 5.632911392405063, "percentage": 80.43, "elapsed_time": "2:42:29", "remaining_time": "0:39:31"}
|
||||
{"current_steps": 675, "total_steps": 833, "loss": 0.2402, "lr": 4.285225701195383e-06, "epoch": 5.675105485232067, "percentage": 81.03, "elapsed_time": "2:43:39", "remaining_time": "0:38:18"}
|
||||
{"current_steps": 680, "total_steps": 833, "loss": 0.2439, "lr": 4.029253311280281e-06, "epoch": 5.717299578059071, "percentage": 81.63, "elapsed_time": "2:44:52", "remaining_time": "0:37:05"}
|
||||
{"current_steps": 685, "total_steps": 833, "loss": 0.2333, "lr": 3.7803049362359103e-06, "epoch": 5.759493670886076, "percentage": 82.23, "elapsed_time": "2:46:04", "remaining_time": "0:35:52"}
|
||||
{"current_steps": 690, "total_steps": 833, "loss": 0.2424, "lr": 3.5384900648120814e-06, "epoch": 5.80168776371308, "percentage": 82.83, "elapsed_time": "2:47:17", "remaining_time": "0:34:40"}
|
||||
{"current_steps": 695, "total_steps": 833, "loss": 0.2305, "lr": 3.3039150484077555e-06, "epoch": 5.843881856540085, "percentage": 83.43, "elapsed_time": "2:48:29", "remaining_time": "0:33:27"}
|
||||
{"current_steps": 700, "total_steps": 833, "loss": 0.2316, "lr": 3.0766830542971826e-06, "epoch": 5.886075949367089, "percentage": 84.03, "elapsed_time": "2:49:40", "remaining_time": "0:32:14"}
|
||||
{"current_steps": 705, "total_steps": 833, "loss": 0.2315, "lr": 2.856894020256389e-06, "epoch": 5.928270042194093, "percentage": 84.63, "elapsed_time": "2:50:53", "remaining_time": "0:31:01"}
|
||||
{"current_steps": 710, "total_steps": 833, "loss": 0.2358, "lr": 2.6446446106100855e-06, "epoch": 5.970464135021097, "percentage": 85.23, "elapsed_time": "2:52:06", "remaining_time": "0:29:49"}
|
||||
{"current_steps": 715, "total_steps": 833, "loss": 0.2485, "lr": 2.4400281737181518e-06, "epoch": 6.008438818565401, "percentage": 85.83, "elapsed_time": "2:53:12", "remaining_time": "0:28:35"}
|
||||
{"current_steps": 720, "total_steps": 833, "loss": 0.2399, "lr": 2.2431347009206107e-06, "epoch": 6.050632911392405, "percentage": 86.43, "elapsed_time": "2:54:25", "remaining_time": "0:27:22"}
|
||||
{"current_steps": 725, "total_steps": 833, "loss": 0.231, "lr": 2.0540507869589365e-06, "epoch": 6.0928270042194095, "percentage": 87.03, "elapsed_time": "2:55:38", "remaining_time": "0:26:09"}
|
||||
{"current_steps": 730, "total_steps": 833, "loss": 0.235, "lr": 1.872859591891305e-06, "epoch": 6.135021097046414, "percentage": 87.64, "elapsed_time": "2:56:50", "remaining_time": "0:24:57"}
|
||||
{"current_steps": 735, "total_steps": 833, "loss": 0.231, "lr": 1.6996408045183255e-06, "epoch": 6.177215189873418, "percentage": 88.24, "elapsed_time": "2:58:01", "remaining_time": "0:23:44"}
|
||||
{"current_steps": 740, "total_steps": 833, "loss": 0.2225, "lr": 1.5344706073355386e-06, "epoch": 6.219409282700422, "percentage": 88.84, "elapsed_time": "2:59:12", "remaining_time": "0:22:31"}
|
||||
{"current_steps": 745, "total_steps": 833, "loss": 0.2403, "lr": 1.377421643027963e-06, "epoch": 6.261603375527426, "percentage": 89.44, "elapsed_time": "3:00:26", "remaining_time": "0:21:18"}
|
||||
{"current_steps": 750, "total_steps": 833, "loss": 0.242, "lr": 1.2285629825214817e-06, "epoch": 6.30379746835443, "percentage": 90.04, "elapsed_time": "3:01:37", "remaining_time": "0:20:05"}
|
||||
{"current_steps": 755, "total_steps": 833, "loss": 0.2198, "lr": 1.0879600946050783e-06, "epoch": 6.345991561181434, "percentage": 90.64, "elapsed_time": "3:02:49", "remaining_time": "0:18:53"}
|
||||
{"current_steps": 760, "total_steps": 833, "loss": 0.2363, "lr": 9.556748171373663e-07, "epoch": 6.3881856540084385, "percentage": 91.24, "elapsed_time": "3:04:01", "remaining_time": "0:17:40"}
|
||||
{"current_steps": 765, "total_steps": 833, "loss": 0.2378, "lr": 8.317653298499651e-07, "epoch": 6.430379746835443, "percentage": 91.84, "elapsed_time": "3:05:12", "remaining_time": "0:16:27"}
|
||||
{"current_steps": 770, "total_steps": 833, "loss": 0.2408, "lr": 7.162861287597666e-07, "epoch": 6.472573839662447, "percentage": 92.44, "elapsed_time": "3:06:21", "remaining_time": "0:15:14"}
|
||||
{"current_steps": 775, "total_steps": 833, "loss": 0.2402, "lr": 6.092880022013115e-07, "epoch": 6.514767932489452, "percentage": 93.04, "elapsed_time": "3:07:34", "remaining_time": "0:14:02"}
|
||||
{"current_steps": 780, "total_steps": 833, "loss": 0.2321, "lr": 5.108180084898284e-07, "epoch": 6.556962025316456, "percentage": 93.64, "elapsed_time": "3:08:44", "remaining_time": "0:12:49"}
|
||||
{"current_steps": 785, "total_steps": 833, "loss": 0.2387, "lr": 4.209194552247442e-07, "epoch": 6.59915611814346, "percentage": 94.24, "elapsed_time": "3:09:56", "remaining_time": "0:11:36"}
|
||||
{"current_steps": 790, "total_steps": 833, "loss": 0.2253, "lr": 3.3963188024278783e-07, "epoch": 6.641350210970464, "percentage": 94.84, "elapsed_time": "3:11:08", "remaining_time": "0:10:24"}
|
||||
{"current_steps": 795, "total_steps": 833, "loss": 0.2329, "lr": 2.6699103422904494e-07, "epoch": 6.6835443037974684, "percentage": 95.44, "elapsed_time": "3:12:21", "remaining_time": "0:09:11"}
|
||||
{"current_steps": 800, "total_steps": 833, "loss": 0.2385, "lr": 2.030288649936285e-07, "epoch": 6.725738396624473, "percentage": 96.04, "elapsed_time": "3:13:32", "remaining_time": "0:07:59"}
|
||||
{"current_steps": 805, "total_steps": 833, "loss": 0.2305, "lr": 1.477735034208805e-07, "epoch": 6.767932489451477, "percentage": 96.64, "elapsed_time": "3:15:23", "remaining_time": "0:06:47"}
|
||||
{"current_steps": 810, "total_steps": 833, "loss": 0.2394, "lr": 1.0124925109725514e-07, "epoch": 6.810126582278481, "percentage": 97.24, "elapsed_time": "3:16:33", "remaining_time": "0:05:34"}
|
||||
{"current_steps": 815, "total_steps": 833, "loss": 0.226, "lr": 6.347656962335524e-08, "epoch": 6.852320675105485, "percentage": 97.84, "elapsed_time": "3:17:46", "remaining_time": "0:04:22"}
|
||||
{"current_steps": 820, "total_steps": 833, "loss": 0.2253, "lr": 3.447207161483279e-08, "epoch": 6.894514767932489, "percentage": 98.44, "elapsed_time": "3:18:59", "remaining_time": "0:03:09"}
|
||||
{"current_steps": 825, "total_steps": 833, "loss": 0.2264, "lr": 1.424851339606903e-08, "epoch": 6.936708860759493, "percentage": 99.04, "elapsed_time": "3:20:10", "remaining_time": "0:01:56"}
|
||||
{"current_steps": 830, "total_steps": 833, "loss": 0.2299, "lr": 2.8147893898755605e-09, "epoch": 6.978902953586498, "percentage": 99.64, "elapsed_time": "3:21:22", "remaining_time": "0:00:43"}
|
||||
{"current_steps": 833, "total_steps": 833, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "3:22:48", "remaining_time": "0:00:00"}
|
||||
1873
trainer_state.json
Normal file
1873
trainer_state.json
Normal file
File diff suppressed because it is too large
Load Diff
3
training_args.bin
Normal file
3
training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:aa03aaf5d0ac2d11df5fb2cec837964b8f4e8a034f3a55dfd3d5989162546e3e
|
||||
size 8721
|
||||
BIN
training_loss.png
Normal file
BIN
training_loss.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 41 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