Model save
Browse files- .gitattributes +1 -0
- README.md +60 -0
- added_tokens.json +28 -0
- chat_template.jinja +89 -0
- config.json +68 -0
- generation_config.json +13 -0
- merges.txt +0 -0
- model-00001-of-00004.safetensors +3 -0
- model-00002-of-00004.safetensors +3 -0
- model-00003-of-00004.safetensors +3 -0
- model-00004-of-00004.safetensors +3 -0
- model.safetensors.index.json +407 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +240 -0
- trainer_log.jsonl +157 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: Qwen/Qwen3-8B
|
| 5 |
+
tags:
|
| 6 |
+
- llama-factory
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
model-index:
|
| 9 |
+
- name: codeforces-sandboxes-traces-terminus-2
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# codeforces-sandboxes-traces-terminus-2
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on an unknown dataset.
|
| 19 |
+
|
| 20 |
+
## Model description
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Intended uses & limitations
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training and evaluation data
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training procedure
|
| 33 |
+
|
| 34 |
+
### Training hyperparameters
|
| 35 |
+
|
| 36 |
+
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 4e-05
|
| 38 |
+
- train_batch_size: 1
|
| 39 |
+
- eval_batch_size: 8
|
| 40 |
+
- seed: 42
|
| 41 |
+
- distributed_type: multi-GPU
|
| 42 |
+
- num_devices: 16
|
| 43 |
+
- gradient_accumulation_steps: 4
|
| 44 |
+
- total_train_batch_size: 64
|
| 45 |
+
- total_eval_batch_size: 128
|
| 46 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 47 |
+
- lr_scheduler_type: cosine
|
| 48 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 49 |
+
- num_epochs: 5.0
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
|
| 54 |
+
|
| 55 |
+
### Framework versions
|
| 56 |
+
|
| 57 |
+
- Transformers 4.55.0
|
| 58 |
+
- Pytorch 2.7.0+cu128
|
| 59 |
+
- Datasets 3.6.0
|
| 60 |
+
- Tokenizers 0.21.1
|
added_tokens.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</think>": 151668,
|
| 3 |
+
"</tool_call>": 151658,
|
| 4 |
+
"</tool_response>": 151666,
|
| 5 |
+
"<think>": 151667,
|
| 6 |
+
"<tool_call>": 151657,
|
| 7 |
+
"<tool_response>": 151665,
|
| 8 |
+
"<|box_end|>": 151649,
|
| 9 |
+
"<|box_start|>": 151648,
|
| 10 |
+
"<|endoftext|>": 151643,
|
| 11 |
+
"<|file_sep|>": 151664,
|
| 12 |
+
"<|fim_middle|>": 151660,
|
| 13 |
+
"<|fim_pad|>": 151662,
|
| 14 |
+
"<|fim_prefix|>": 151659,
|
| 15 |
+
"<|fim_suffix|>": 151661,
|
| 16 |
+
"<|im_end|>": 151645,
|
| 17 |
+
"<|im_start|>": 151644,
|
| 18 |
+
"<|image_pad|>": 151655,
|
| 19 |
+
"<|object_ref_end|>": 151647,
|
| 20 |
+
"<|object_ref_start|>": 151646,
|
| 21 |
+
"<|quad_end|>": 151651,
|
| 22 |
+
"<|quad_start|>": 151650,
|
| 23 |
+
"<|repo_name|>": 151663,
|
| 24 |
+
"<|video_pad|>": 151656,
|
| 25 |
+
"<|vision_end|>": 151653,
|
| 26 |
+
"<|vision_pad|>": 151654,
|
| 27 |
+
"<|vision_start|>": 151652
|
| 28 |
+
}
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,89 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0].role == 'system' %}
|
| 4 |
+
{{- messages[0].content + '\n\n' }}
|
| 5 |
+
{%- endif %}
|
| 6 |
+
{{- "# 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>" }}
|
| 7 |
+
{%- for tool in tools %}
|
| 8 |
+
{{- "\n" }}
|
| 9 |
+
{{- tool | tojson }}
|
| 10 |
+
{%- endfor %}
|
| 11 |
+
{{- "\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" }}
|
| 12 |
+
{%- else %}
|
| 13 |
+
{%- if messages[0].role == 'system' %}
|
| 14 |
+
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
| 15 |
+
{%- endif %}
|
| 16 |
+
{%- endif %}
|
| 17 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 18 |
+
{%- for message in messages[::-1] %}
|
| 19 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 20 |
+
{%- 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>')) %}
|
| 21 |
+
{%- set ns.multi_step_tool = false %}
|
| 22 |
+
{%- set ns.last_query_index = index %}
|
| 23 |
+
{%- endif %}
|
| 24 |
+
{%- endfor %}
|
| 25 |
+
{%- for message in messages %}
|
| 26 |
+
{%- if message.content is string %}
|
| 27 |
+
{%- set content = message.content %}
|
| 28 |
+
{%- else %}
|
| 29 |
+
{%- set content = '' %}
|
| 30 |
+
{%- endif %}
|
| 31 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
| 32 |
+
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 33 |
+
{%- elif message.role == "assistant" %}
|
| 34 |
+
{%- set reasoning_content = '' %}
|
| 35 |
+
{%- if message.reasoning_content is string %}
|
| 36 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 37 |
+
{%- else %}
|
| 38 |
+
{%- if '</think>' in content %}
|
| 39 |
+
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 40 |
+
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
| 41 |
+
{%- endif %}
|
| 42 |
+
{%- endif %}
|
| 43 |
+
{%- if loop.index0 > ns.last_query_index %}
|
| 44 |
+
{%- if loop.last or (not loop.last and reasoning_content) %}
|
| 45 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
| 46 |
+
{%- else %}
|
| 47 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 48 |
+
{%- endif %}
|
| 49 |
+
{%- else %}
|
| 50 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 51 |
+
{%- endif %}
|
| 52 |
+
{%- if message.tool_calls %}
|
| 53 |
+
{%- for tool_call in message.tool_calls %}
|
| 54 |
+
{%- if (loop.first and content) or (not loop.first) %}
|
| 55 |
+
{{- '\n' }}
|
| 56 |
+
{%- endif %}
|
| 57 |
+
{%- if tool_call.function %}
|
| 58 |
+
{%- set tool_call = tool_call.function %}
|
| 59 |
+
{%- endif %}
|
| 60 |
+
{{- '<tool_call>\n{"name": "' }}
|
| 61 |
+
{{- tool_call.name }}
|
| 62 |
+
{{- '", "arguments": ' }}
|
| 63 |
+
{%- if tool_call.arguments is string %}
|
| 64 |
+
{{- tool_call.arguments }}
|
| 65 |
+
{%- else %}
|
| 66 |
+
{{- tool_call.arguments | tojson }}
|
| 67 |
+
{%- endif %}
|
| 68 |
+
{{- '}\n</tool_call>' }}
|
| 69 |
+
{%- endfor %}
|
| 70 |
+
{%- endif %}
|
| 71 |
+
{{- '<|im_end|>\n' }}
|
| 72 |
+
{%- elif message.role == "tool" %}
|
| 73 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 74 |
+
{{- '<|im_start|>user' }}
|
| 75 |
+
{%- endif %}
|
| 76 |
+
{{- '\n<tool_response>\n' }}
|
| 77 |
+
{{- content }}
|
| 78 |
+
{{- '\n</tool_response>' }}
|
| 79 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 80 |
+
{{- '<|im_end|>\n' }}
|
| 81 |
+
{%- endif %}
|
| 82 |
+
{%- endif %}
|
| 83 |
+
{%- endfor %}
|
| 84 |
+
{%- if add_generation_prompt %}
|
| 85 |
+
{{- '<|im_start|>assistant\n' }}
|
| 86 |
+
{%- if enable_thinking is defined and enable_thinking is false %}
|
| 87 |
+
{{- '<think>\n\n</think>\n\n' }}
|
| 88 |
+
{%- endif %}
|
| 89 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151643,
|
| 8 |
+
"eos_token_id": 151645,
|
| 9 |
+
"head_dim": 128,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 4096,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 12288,
|
| 14 |
+
"layer_types": [
|
| 15 |
+
"full_attention",
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"full_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"full_attention",
|
| 49 |
+
"full_attention",
|
| 50 |
+
"full_attention"
|
| 51 |
+
],
|
| 52 |
+
"max_position_embeddings": 40960,
|
| 53 |
+
"max_window_layers": 36,
|
| 54 |
+
"model_type": "qwen3",
|
| 55 |
+
"num_attention_heads": 32,
|
| 56 |
+
"num_hidden_layers": 36,
|
| 57 |
+
"num_key_value_heads": 8,
|
| 58 |
+
"rms_norm_eps": 1e-06,
|
| 59 |
+
"rope_scaling": null,
|
| 60 |
+
"rope_theta": 1000000,
|
| 61 |
+
"sliding_window": null,
|
| 62 |
+
"tie_word_embeddings": false,
|
| 63 |
+
"torch_dtype": "bfloat16",
|
| 64 |
+
"transformers_version": "4.55.0",
|
| 65 |
+
"use_cache": false,
|
| 66 |
+
"use_sliding_window": false,
|
| 67 |
+
"vocab_size": 151936
|
| 68 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 151643,
|
| 9 |
+
"temperature": 0.6,
|
| 10 |
+
"top_k": 20,
|
| 11 |
+
"top_p": 0.95,
|
| 12 |
+
"transformers_version": "4.55.0"
|
| 13 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5ee002fb6fc1ea91d162d262d3bfb101220c5c0cf03c143d14f2a65717cda96a
|
| 3 |
+
size 4902257696
|
model-00002-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:653d1a3736fcc73605d83b58a7f2c0b3902b2f1a497045393bafeb8406f02061
|
| 3 |
+
size 4915960368
|
model-00003-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bc10ee15a222dbe805600c973f0956445ca479347a1e669326f984b45df0fb09
|
| 3 |
+
size 4983068496
|
model-00004-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:245e0ede3fdf90b73f200b9d6f031a0599f8b95c1cd8494843ffc15ec6120d2e
|
| 3 |
+
size 1580230264
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,407 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 308224,
|
| 4 |
+
"total_size": 16381470720
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"lm_head.weight": "model-00004-of-00004.safetensors",
|
| 8 |
+
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
| 9 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 10 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 11 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 12 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 13 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 19 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 20 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 21 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 22 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 23 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 24 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 29 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 30 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 31 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 32 |
+
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 33 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 34 |
+
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 35 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 36 |
+
"model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 37 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 38 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 39 |
+
"model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 40 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 41 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 42 |
+
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 43 |
+
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 44 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 45 |
+
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 46 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 47 |
+
"model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 48 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 49 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 50 |
+
"model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 51 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 52 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 53 |
+
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 54 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 55 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 56 |
+
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 57 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 58 |
+
"model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 59 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 60 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 61 |
+
"model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 62 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 63 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 64 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 65 |
+
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 66 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 67 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 68 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 69 |
+
"model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 70 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 71 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 72 |
+
"model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 73 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 74 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 75 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 76 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 77 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 78 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 79 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 80 |
+
"model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 81 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 82 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 83 |
+
"model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 84 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 85 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 86 |
+
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 87 |
+
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 88 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 89 |
+
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 90 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 91 |
+
"model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 92 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 93 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 94 |
+
"model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 95 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 96 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 97 |
+
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 98 |
+
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 99 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 100 |
+
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 101 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 102 |
+
"model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 103 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 104 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 105 |
+
"model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 106 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 107 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 108 |
+
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 109 |
+
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 110 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 111 |
+
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 112 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 113 |
+
"model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 114 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 115 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 116 |
+
"model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 117 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 118 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 119 |
+
"model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 120 |
+
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 121 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 122 |
+
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 123 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 124 |
+
"model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 125 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 126 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 127 |
+
"model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 128 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 129 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 130 |
+
"model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 131 |
+
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 132 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 133 |
+
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 134 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 135 |
+
"model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 136 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 137 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 138 |
+
"model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 139 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 140 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 141 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 142 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 143 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 144 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 145 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 146 |
+
"model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 147 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 148 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 149 |
+
"model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 150 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 151 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 152 |
+
"model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 153 |
+
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 154 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 155 |
+
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 156 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 157 |
+
"model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 158 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 159 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 160 |
+
"model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 161 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 162 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 163 |
+
"model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 164 |
+
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 165 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 166 |
+
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 167 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 168 |
+
"model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 169 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 170 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 171 |
+
"model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 172 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 173 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 174 |
+
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 175 |
+
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 176 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 177 |
+
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 178 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 179 |
+
"model.layers.22.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 180 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 181 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 182 |
+
"model.layers.22.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 183 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 184 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 185 |
+
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 186 |
+
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 187 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 188 |
+
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 189 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 190 |
+
"model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 191 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 192 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 193 |
+
"model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 194 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 195 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 196 |
+
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 197 |
+
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 198 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 199 |
+
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 200 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 201 |
+
"model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 202 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 203 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 204 |
+
"model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 205 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 206 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 207 |
+
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 208 |
+
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 209 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 210 |
+
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 211 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 212 |
+
"model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 213 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 214 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 215 |
+
"model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 216 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 217 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 218 |
+
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 219 |
+
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 220 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 221 |
+
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 222 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 223 |
+
"model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 224 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 225 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 226 |
+
"model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 227 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 228 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 229 |
+
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 230 |
+
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 231 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 232 |
+
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 233 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 234 |
+
"model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 235 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 236 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 237 |
+
"model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 238 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 239 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 240 |
+
"model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 241 |
+
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 242 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 243 |
+
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 244 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 245 |
+
"model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 246 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 247 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 248 |
+
"model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 249 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 250 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 251 |
+
"model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 252 |
+
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 253 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 254 |
+
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 255 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 256 |
+
"model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 257 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 258 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 259 |
+
"model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 260 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 261 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 262 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 263 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 264 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 265 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 266 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 267 |
+
"model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 268 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 269 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 270 |
+
"model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 271 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 272 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 273 |
+
"model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 274 |
+
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 275 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 276 |
+
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 277 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 278 |
+
"model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 279 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 280 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 281 |
+
"model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 282 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 283 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 284 |
+
"model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 285 |
+
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 286 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 287 |
+
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 288 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 289 |
+
"model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 290 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 291 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 292 |
+
"model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 293 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 294 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 295 |
+
"model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 296 |
+
"model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 297 |
+
"model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 298 |
+
"model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 299 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 300 |
+
"model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 301 |
+
"model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 302 |
+
"model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 303 |
+
"model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 304 |
+
"model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 305 |
+
"model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 306 |
+
"model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 307 |
+
"model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 308 |
+
"model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 309 |
+
"model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 310 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 311 |
+
"model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 312 |
+
"model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 313 |
+
"model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 314 |
+
"model.layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 315 |
+
"model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 316 |
+
"model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 317 |
+
"model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 318 |
+
"model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 319 |
+
"model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 320 |
+
"model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 321 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 322 |
+
"model.layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 323 |
+
"model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 324 |
+
"model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 325 |
+
"model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 326 |
+
"model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 327 |
+
"model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 328 |
+
"model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 329 |
+
"model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 330 |
+
"model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 331 |
+
"model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 332 |
+
"model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 333 |
+
"model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
| 334 |
+
"model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 335 |
+
"model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
| 336 |
+
"model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
| 337 |
+
"model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 338 |
+
"model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 339 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 340 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 341 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 342 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 343 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 344 |
+
"model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 345 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 346 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 347 |
+
"model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 348 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 349 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 350 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 351 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 352 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 353 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 354 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 355 |
+
"model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 356 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 357 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 358 |
+
"model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 359 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 360 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 361 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 362 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 363 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 364 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 365 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 366 |
+
"model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 367 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 368 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 369 |
+
"model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 370 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 371 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 372 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 373 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 374 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 375 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 376 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 377 |
+
"model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 378 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 379 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 380 |
+
"model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 381 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 382 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 383 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 384 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 385 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 386 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 387 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 388 |
+
"model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 389 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 390 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 391 |
+
"model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 392 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 393 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 394 |
+
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 395 |
+
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 396 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 397 |
+
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 398 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 399 |
+
"model.layers.9.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 400 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 401 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 402 |
+
"model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 403 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 404 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 405 |
+
"model.norm.weight": "model-00004-of-00004.safetensors"
|
| 406 |
+
}
|
| 407 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
| 3 |
+
size 11422654
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,240 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
},
|
| 181 |
+
"151665": {
|
| 182 |
+
"content": "<tool_response>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"151666": {
|
| 190 |
+
"content": "</tool_response>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
+
},
|
| 197 |
+
"151667": {
|
| 198 |
+
"content": "<think>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": false
|
| 204 |
+
},
|
| 205 |
+
"151668": {
|
| 206 |
+
"content": "</think>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
+
}
|
| 213 |
+
},
|
| 214 |
+
"additional_special_tokens": [
|
| 215 |
+
"<|im_start|>",
|
| 216 |
+
"<|im_end|>",
|
| 217 |
+
"<|object_ref_start|>",
|
| 218 |
+
"<|object_ref_end|>",
|
| 219 |
+
"<|box_start|>",
|
| 220 |
+
"<|box_end|>",
|
| 221 |
+
"<|quad_start|>",
|
| 222 |
+
"<|quad_end|>",
|
| 223 |
+
"<|vision_start|>",
|
| 224 |
+
"<|vision_end|>",
|
| 225 |
+
"<|vision_pad|>",
|
| 226 |
+
"<|image_pad|>",
|
| 227 |
+
"<|video_pad|>"
|
| 228 |
+
],
|
| 229 |
+
"bos_token": null,
|
| 230 |
+
"clean_up_tokenization_spaces": false,
|
| 231 |
+
"eos_token": "<|im_end|>",
|
| 232 |
+
"errors": "replace",
|
| 233 |
+
"extra_special_tokens": {},
|
| 234 |
+
"model_max_length": 32768,
|
| 235 |
+
"pad_token": "<|endoftext|>",
|
| 236 |
+
"padding_side": "right",
|
| 237 |
+
"split_special_tokens": false,
|
| 238 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 239 |
+
"unk_token": null
|
| 240 |
+
}
|
trainer_log.jsonl
ADDED
|
@@ -0,0 +1,157 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 5, "total_steps": 780, "loss": 0.8032, "lr": 2.0512820512820513e-06, "epoch": 0.03210272873194221, "percentage": 0.64, "elapsed_time": "0:01:41", "remaining_time": "4:22:40"}
|
| 2 |
+
{"current_steps": 10, "total_steps": 780, "loss": 0.7807, "lr": 4.615384615384616e-06, "epoch": 0.06420545746388442, "percentage": 1.28, "elapsed_time": "0:03:15", "remaining_time": "4:11:25"}
|
| 3 |
+
{"current_steps": 15, "total_steps": 780, "loss": 0.7119, "lr": 7.17948717948718e-06, "epoch": 0.09630818619582665, "percentage": 1.92, "elapsed_time": "0:04:49", "remaining_time": "4:06:01"}
|
| 4 |
+
{"current_steps": 20, "total_steps": 780, "loss": 0.6496, "lr": 9.743589743589744e-06, "epoch": 0.12841091492776885, "percentage": 2.56, "elapsed_time": "0:06:20", "remaining_time": "4:00:55"}
|
| 5 |
+
{"current_steps": 25, "total_steps": 780, "loss": 0.6397, "lr": 1.230769230769231e-05, "epoch": 0.16051364365971107, "percentage": 3.21, "elapsed_time": "0:07:47", "remaining_time": "3:55:28"}
|
| 6 |
+
{"current_steps": 30, "total_steps": 780, "loss": 0.6154, "lr": 1.4871794871794874e-05, "epoch": 0.1926163723916533, "percentage": 3.85, "elapsed_time": "0:09:20", "remaining_time": "3:53:37"}
|
| 7 |
+
{"current_steps": 35, "total_steps": 780, "loss": 0.5911, "lr": 1.7435897435897438e-05, "epoch": 0.2247191011235955, "percentage": 4.49, "elapsed_time": "0:10:51", "remaining_time": "3:51:01"}
|
| 8 |
+
{"current_steps": 40, "total_steps": 780, "loss": 0.5892, "lr": 2e-05, "epoch": 0.2568218298555377, "percentage": 5.13, "elapsed_time": "0:12:16", "remaining_time": "3:47:04"}
|
| 9 |
+
{"current_steps": 45, "total_steps": 780, "loss": 0.5387, "lr": 2.2564102564102566e-05, "epoch": 0.28892455858747995, "percentage": 5.77, "elapsed_time": "0:13:48", "remaining_time": "3:45:33"}
|
| 10 |
+
{"current_steps": 50, "total_steps": 780, "loss": 0.5399, "lr": 2.512820512820513e-05, "epoch": 0.32102728731942215, "percentage": 6.41, "elapsed_time": "0:15:14", "remaining_time": "3:42:37"}
|
| 11 |
+
{"current_steps": 55, "total_steps": 780, "loss": 0.5154, "lr": 2.7692307692307694e-05, "epoch": 0.35313001605136435, "percentage": 7.05, "elapsed_time": "0:16:46", "remaining_time": "3:41:13"}
|
| 12 |
+
{"current_steps": 60, "total_steps": 780, "loss": 0.505, "lr": 3.0256410256410257e-05, "epoch": 0.3852327447833066, "percentage": 7.69, "elapsed_time": "0:18:24", "remaining_time": "3:40:51"}
|
| 13 |
+
{"current_steps": 65, "total_steps": 780, "loss": 0.5088, "lr": 3.282051282051282e-05, "epoch": 0.4173354735152488, "percentage": 8.33, "elapsed_time": "0:19:50", "remaining_time": "3:38:13"}
|
| 14 |
+
{"current_steps": 70, "total_steps": 780, "loss": 0.495, "lr": 3.538461538461539e-05, "epoch": 0.449438202247191, "percentage": 8.97, "elapsed_time": "0:21:18", "remaining_time": "3:36:06"}
|
| 15 |
+
{"current_steps": 75, "total_steps": 780, "loss": 0.5013, "lr": 3.794871794871795e-05, "epoch": 0.48154093097913325, "percentage": 9.62, "elapsed_time": "0:22:53", "remaining_time": "3:35:15"}
|
| 16 |
+
{"current_steps": 80, "total_steps": 780, "loss": 0.4691, "lr": 3.999979972589652e-05, "epoch": 0.5136436597110754, "percentage": 10.26, "elapsed_time": "0:24:26", "remaining_time": "3:33:50"}
|
| 17 |
+
{"current_steps": 85, "total_steps": 780, "loss": 0.4792, "lr": 3.999279055341771e-05, "epoch": 0.5457463884430177, "percentage": 10.9, "elapsed_time": "0:25:51", "remaining_time": "3:31:27"}
|
| 18 |
+
{"current_steps": 90, "total_steps": 780, "loss": 0.4805, "lr": 3.9975771686375434e-05, "epoch": 0.5778491171749599, "percentage": 11.54, "elapsed_time": "0:27:23", "remaining_time": "3:30:02"}
|
| 19 |
+
{"current_steps": 95, "total_steps": 780, "loss": 0.4749, "lr": 3.9948751645524235e-05, "epoch": 0.6099518459069021, "percentage": 12.18, "elapsed_time": "0:28:50", "remaining_time": "3:27:54"}
|
| 20 |
+
{"current_steps": 100, "total_steps": 780, "loss": 0.4818, "lr": 3.9911743958858376e-05, "epoch": 0.6420545746388443, "percentage": 12.82, "elapsed_time": "0:30:09", "remaining_time": "3:25:06"}
|
| 21 |
+
{"current_steps": 105, "total_steps": 780, "loss": 0.4759, "lr": 3.9864767154838864e-05, "epoch": 0.6741573033707865, "percentage": 13.46, "elapsed_time": "0:31:45", "remaining_time": "3:24:11"}
|
| 22 |
+
{"current_steps": 110, "total_steps": 780, "loss": 0.4494, "lr": 3.9807844753116864e-05, "epoch": 0.7062600321027287, "percentage": 14.1, "elapsed_time": "0:33:19", "remaining_time": "3:22:59"}
|
| 23 |
+
{"current_steps": 115, "total_steps": 780, "loss": 0.4684, "lr": 3.9741005252758255e-05, "epoch": 0.7383627608346709, "percentage": 14.74, "elapsed_time": "0:34:46", "remaining_time": "3:21:06"}
|
| 24 |
+
{"current_steps": 120, "total_steps": 780, "loss": 0.4527, "lr": 3.966428211797514e-05, "epoch": 0.7704654895666132, "percentage": 15.38, "elapsed_time": "0:36:14", "remaining_time": "3:19:19"}
|
| 25 |
+
{"current_steps": 125, "total_steps": 780, "loss": 0.4683, "lr": 3.957771376137144e-05, "epoch": 0.8025682182985554, "percentage": 16.03, "elapsed_time": "0:37:39", "remaining_time": "3:17:17"}
|
| 26 |
+
{"current_steps": 130, "total_steps": 780, "loss": 0.4594, "lr": 3.9481343524711095e-05, "epoch": 0.8346709470304976, "percentage": 16.67, "elapsed_time": "0:39:14", "remaining_time": "3:16:13"}
|
| 27 |
+
{"current_steps": 135, "total_steps": 780, "loss": 0.4599, "lr": 3.937521965721831e-05, "epoch": 0.8667736757624398, "percentage": 17.31, "elapsed_time": "0:40:41", "remaining_time": "3:14:24"}
|
| 28 |
+
{"current_steps": 140, "total_steps": 780, "loss": 0.4346, "lr": 3.9259395291420864e-05, "epoch": 0.898876404494382, "percentage": 17.95, "elapsed_time": "0:42:19", "remaining_time": "3:13:31"}
|
| 29 |
+
{"current_steps": 145, "total_steps": 780, "loss": 0.452, "lr": 3.913392841654851e-05, "epoch": 0.9309791332263242, "percentage": 18.59, "elapsed_time": "0:43:55", "remaining_time": "3:12:23"}
|
| 30 |
+
{"current_steps": 150, "total_steps": 780, "loss": 0.4438, "lr": 3.8998881849499756e-05, "epoch": 0.9630818619582665, "percentage": 19.23, "elapsed_time": "0:45:32", "remaining_time": "3:11:14"}
|
| 31 |
+
{"current_steps": 155, "total_steps": 780, "loss": 0.4491, "lr": 3.885432320339167e-05, "epoch": 0.9951845906902087, "percentage": 19.87, "elapsed_time": "0:47:02", "remaining_time": "3:09:41"}
|
| 32 |
+
{"current_steps": 160, "total_steps": 780, "loss": 0.4309, "lr": 3.8700324853708304e-05, "epoch": 1.0256821829855538, "percentage": 20.51, "elapsed_time": "0:48:28", "remaining_time": "3:07:49"}
|
| 33 |
+
{"current_steps": 165, "total_steps": 780, "loss": 0.4441, "lr": 3.853696390206484e-05, "epoch": 1.057784911717496, "percentage": 21.15, "elapsed_time": "0:49:49", "remaining_time": "3:05:44"}
|
| 34 |
+
{"current_steps": 170, "total_steps": 780, "loss": 0.4472, "lr": 3.8364322137605484e-05, "epoch": 1.0898876404494382, "percentage": 21.79, "elapsed_time": "0:51:25", "remaining_time": "3:04:31"}
|
| 35 |
+
{"current_steps": 175, "total_steps": 780, "loss": 0.4197, "lr": 3.818248599605448e-05, "epoch": 1.1219903691813804, "percentage": 22.44, "elapsed_time": "0:52:59", "remaining_time": "3:03:12"}
|
| 36 |
+
{"current_steps": 180, "total_steps": 780, "loss": 0.4474, "lr": 3.799154651644075e-05, "epoch": 1.1540930979133226, "percentage": 23.08, "elapsed_time": "0:54:37", "remaining_time": "3:02:05"}
|
| 37 |
+
{"current_steps": 185, "total_steps": 780, "loss": 0.4382, "lr": 3.7791599295517825e-05, "epoch": 1.1861958266452648, "percentage": 23.72, "elapsed_time": "0:56:08", "remaining_time": "3:00:32"}
|
| 38 |
+
{"current_steps": 190, "total_steps": 780, "loss": 0.4368, "lr": 3.75827444399019e-05, "epoch": 1.218298555377207, "percentage": 24.36, "elapsed_time": "0:57:40", "remaining_time": "2:59:04"}
|
| 39 |
+
{"current_steps": 195, "total_steps": 780, "loss": 0.4281, "lr": 3.736508651595188e-05, "epoch": 1.2504012841091492, "percentage": 25.0, "elapsed_time": "0:59:12", "remaining_time": "2:57:38"}
|
| 40 |
+
{"current_steps": 200, "total_steps": 780, "loss": 0.4343, "lr": 3.713873449741669e-05, "epoch": 1.2825040128410916, "percentage": 25.64, "elapsed_time": "1:00:47", "remaining_time": "2:56:16"}
|
| 41 |
+
{"current_steps": 205, "total_steps": 780, "loss": 0.4231, "lr": 3.69038017108759e-05, "epoch": 1.3146067415730336, "percentage": 26.28, "elapsed_time": "1:02:26", "remaining_time": "2:55:09"}
|
| 42 |
+
{"current_steps": 210, "total_steps": 780, "loss": 0.4419, "lr": 3.6660405779001036e-05, "epoch": 1.346709470304976, "percentage": 26.92, "elapsed_time": "1:03:57", "remaining_time": "2:53:35"}
|
| 43 |
+
{"current_steps": 215, "total_steps": 780, "loss": 0.4384, "lr": 3.640866856166601e-05, "epoch": 1.3788121990369182, "percentage": 27.56, "elapsed_time": "1:05:22", "remaining_time": "2:51:46"}
|
| 44 |
+
{"current_steps": 220, "total_steps": 780, "loss": 0.4471, "lr": 3.614871609493614e-05, "epoch": 1.4109149277688604, "percentage": 28.21, "elapsed_time": "1:06:52", "remaining_time": "2:50:14"}
|
| 45 |
+
{"current_steps": 225, "total_steps": 780, "loss": 0.4404, "lr": 3.5880678527966224e-05, "epoch": 1.4430176565008026, "percentage": 28.85, "elapsed_time": "1:08:11", "remaining_time": "2:48:12"}
|
| 46 |
+
{"current_steps": 230, "total_steps": 780, "loss": 0.4293, "lr": 3.5604690057839456e-05, "epoch": 1.4751203852327448, "percentage": 29.49, "elapsed_time": "1:09:52", "remaining_time": "2:47:04"}
|
| 47 |
+
{"current_steps": 235, "total_steps": 780, "loss": 0.4374, "lr": 3.532088886237956e-05, "epoch": 1.507223113964687, "percentage": 30.13, "elapsed_time": "1:11:22", "remaining_time": "2:45:31"}
|
| 48 |
+
{"current_steps": 240, "total_steps": 780, "loss": 0.4361, "lr": 3.5029417030970005e-05, "epoch": 1.5393258426966292, "percentage": 30.77, "elapsed_time": "1:12:49", "remaining_time": "2:43:50"}
|
| 49 |
+
{"current_steps": 245, "total_steps": 780, "loss": 0.4323, "lr": 3.473042049341474e-05, "epoch": 1.5714285714285714, "percentage": 31.41, "elapsed_time": "1:14:18", "remaining_time": "2:42:16"}
|
| 50 |
+
{"current_steps": 250, "total_steps": 780, "loss": 0.438, "lr": 3.442404894687629e-05, "epoch": 1.6035313001605136, "percentage": 32.05, "elapsed_time": "1:15:43", "remaining_time": "2:40:32"}
|
| 51 |
+
{"current_steps": 255, "total_steps": 780, "loss": 0.4232, "lr": 3.411045578092754e-05, "epoch": 1.635634028892456, "percentage": 32.69, "elapsed_time": "1:17:04", "remaining_time": "2:38:40"}
|
| 52 |
+
{"current_steps": 260, "total_steps": 780, "loss": 0.4362, "lr": 3.3789798000754924e-05, "epoch": 1.667736757624398, "percentage": 33.33, "elapsed_time": "1:18:32", "remaining_time": "2:37:04"}
|
| 53 |
+
{"current_steps": 265, "total_steps": 780, "loss": 0.434, "lr": 3.34622361485514e-05, "epoch": 1.6998394863563404, "percentage": 33.97, "elapsed_time": "1:19:56", "remaining_time": "2:35:22"}
|
| 54 |
+
{"current_steps": 270, "total_steps": 780, "loss": 0.4275, "lr": 3.31279342231386e-05, "epoch": 1.7319422150882824, "percentage": 34.62, "elapsed_time": "1:21:25", "remaining_time": "2:33:47"}
|
| 55 |
+
{"current_steps": 275, "total_steps": 780, "loss": 0.4151, "lr": 3.278705959785821e-05, "epoch": 1.7640449438202248, "percentage": 35.26, "elapsed_time": "1:23:00", "remaining_time": "2:32:25"}
|
| 56 |
+
{"current_steps": 280, "total_steps": 780, "loss": 0.4082, "lr": 3.243978293677408e-05, "epoch": 1.7961476725521668, "percentage": 35.9, "elapsed_time": "1:24:48", "remaining_time": "2:31:26"}
|
| 57 |
+
{"current_steps": 285, "total_steps": 780, "loss": 0.436, "lr": 3.208627810922665e-05, "epoch": 1.8282504012841092, "percentage": 36.54, "elapsed_time": "1:26:11", "remaining_time": "2:29:41"}
|
| 58 |
+
{"current_steps": 290, "total_steps": 780, "loss": 0.4209, "lr": 3.172672210278254e-05, "epoch": 1.8603531300160514, "percentage": 37.18, "elapsed_time": "1:27:47", "remaining_time": "2:28:20"}
|
| 59 |
+
{"current_steps": 295, "total_steps": 780, "loss": 0.4319, "lr": 3.136129493462312e-05, "epoch": 1.8924558587479936, "percentage": 37.82, "elapsed_time": "1:29:14", "remaining_time": "2:26:43"}
|
| 60 |
+
{"current_steps": 300, "total_steps": 780, "loss": 0.4201, "lr": 3.0990179561416124e-05, "epoch": 1.9245585874799358, "percentage": 38.46, "elapsed_time": "1:30:37", "remaining_time": "2:25:00"}
|
| 61 |
+
{"current_steps": 305, "total_steps": 780, "loss": 0.4251, "lr": 3.061356178771564e-05, "epoch": 1.956661316211878, "percentage": 39.1, "elapsed_time": "1:32:14", "remaining_time": "2:23:39"}
|
| 62 |
+
{"current_steps": 310, "total_steps": 780, "loss": 0.4147, "lr": 3.0231630172936205e-05, "epoch": 1.9887640449438202, "percentage": 39.74, "elapsed_time": "1:33:44", "remaining_time": "2:22:06"}
|
| 63 |
+
{"current_steps": 315, "total_steps": 780, "loss": 0.4074, "lr": 2.98445759369477e-05, "epoch": 2.019261637239165, "percentage": 40.38, "elapsed_time": "1:35:14", "remaining_time": "2:20:34"}
|
| 64 |
+
{"current_steps": 320, "total_steps": 780, "loss": 0.4149, "lr": 2.945259286433819e-05, "epoch": 2.0513643659711076, "percentage": 41.03, "elapsed_time": "1:36:39", "remaining_time": "2:18:57"}
|
| 65 |
+
{"current_steps": 325, "total_steps": 780, "loss": 0.4184, "lr": 2.9055877207392752e-05, "epoch": 2.0834670947030496, "percentage": 41.67, "elapsed_time": "1:38:14", "remaining_time": "2:17:32"}
|
| 66 |
+
{"current_steps": 330, "total_steps": 780, "loss": 0.4253, "lr": 2.8654627587836724e-05, "epoch": 2.115569823434992, "percentage": 42.31, "elapsed_time": "1:39:42", "remaining_time": "2:15:58"}
|
| 67 |
+
{"current_steps": 335, "total_steps": 780, "loss": 0.4071, "lr": 2.8249044897392814e-05, "epoch": 2.1476725521669344, "percentage": 42.95, "elapsed_time": "1:41:08", "remaining_time": "2:14:21"}
|
| 68 |
+
{"current_steps": 340, "total_steps": 780, "loss": 0.4119, "lr": 2.7839332197201505e-05, "epoch": 2.1797752808988764, "percentage": 43.59, "elapsed_time": "1:42:39", "remaining_time": "2:12:51"}
|
| 69 |
+
{"current_steps": 345, "total_steps": 780, "loss": 0.4147, "lr": 2.7425694616155474e-05, "epoch": 2.211878009630819, "percentage": 44.23, "elapsed_time": "1:44:07", "remaining_time": "2:11:17"}
|
| 70 |
+
{"current_steps": 350, "total_steps": 780, "loss": 0.4137, "lr": 2.700833924819868e-05, "epoch": 2.243980738362761, "percentage": 44.87, "elapsed_time": "1:45:33", "remaining_time": "2:09:41"}
|
| 71 |
+
{"current_steps": 355, "total_steps": 780, "loss": 0.421, "lr": 2.6587475048641596e-05, "epoch": 2.276083467094703, "percentage": 45.51, "elapsed_time": "1:47:04", "remaining_time": "2:08:11"}
|
| 72 |
+
{"current_steps": 360, "total_steps": 780, "loss": 0.4124, "lr": 2.6163312729544616e-05, "epoch": 2.308186195826645, "percentage": 46.15, "elapsed_time": "1:48:34", "remaining_time": "2:06:40"}
|
| 73 |
+
{"current_steps": 365, "total_steps": 780, "loss": 0.3984, "lr": 2.5736064654221808e-05, "epoch": 2.3402889245585876, "percentage": 46.79, "elapsed_time": "1:50:07", "remaining_time": "2:05:12"}
|
| 74 |
+
{"current_steps": 370, "total_steps": 780, "loss": 0.4133, "lr": 2.5305944730918017e-05, "epoch": 2.3723916532905296, "percentage": 47.44, "elapsed_time": "1:51:36", "remaining_time": "2:03:40"}
|
| 75 |
+
{"current_steps": 375, "total_steps": 780, "loss": 0.4177, "lr": 2.487316830571244e-05, "epoch": 2.404494382022472, "percentage": 48.08, "elapsed_time": "1:53:04", "remaining_time": "2:02:07"}
|
| 76 |
+
{"current_steps": 380, "total_steps": 780, "loss": 0.4131, "lr": 2.4437952054702354e-05, "epoch": 2.436597110754414, "percentage": 48.72, "elapsed_time": "1:54:37", "remaining_time": "2:00:39"}
|
| 77 |
+
{"current_steps": 385, "total_steps": 780, "loss": 0.4183, "lr": 2.4000513875520892e-05, "epoch": 2.4686998394863564, "percentage": 49.36, "elapsed_time": "1:55:58", "remaining_time": "1:58:59"}
|
| 78 |
+
{"current_steps": 390, "total_steps": 780, "loss": 0.4037, "lr": 2.3561072778243335e-05, "epoch": 2.5008025682182984, "percentage": 50.0, "elapsed_time": "1:57:23", "remaining_time": "1:57:23"}
|
| 79 |
+
{"current_steps": 395, "total_steps": 780, "loss": 0.4075, "lr": 2.311984877573636e-05, "epoch": 2.532905296950241, "percentage": 50.64, "elapsed_time": "1:58:48", "remaining_time": "1:55:47"}
|
| 80 |
+
{"current_steps": 400, "total_steps": 780, "loss": 0.4158, "lr": 2.2677062773505235e-05, "epoch": 2.5650080256821832, "percentage": 51.28, "elapsed_time": "2:00:15", "remaining_time": "1:54:14"}
|
| 81 |
+
{"current_steps": 405, "total_steps": 780, "loss": 0.4183, "lr": 2.2232936459094158e-05, "epoch": 2.597110754414125, "percentage": 51.92, "elapsed_time": "2:01:48", "remaining_time": "1:52:47"}
|
| 82 |
+
{"current_steps": 410, "total_steps": 780, "loss": 0.3936, "lr": 2.1787692191094986e-05, "epoch": 2.629213483146067, "percentage": 52.56, "elapsed_time": "2:03:21", "remaining_time": "1:51:19"}
|
| 83 |
+
{"current_steps": 415, "total_steps": 780, "loss": 0.415, "lr": 2.1341552887820048e-05, "epoch": 2.6613162118780096, "percentage": 53.21, "elapsed_time": "2:04:47", "remaining_time": "1:49:45"}
|
| 84 |
+
{"current_steps": 420, "total_steps": 780, "loss": 0.4111, "lr": 2.0894741915694685e-05, "epoch": 2.693418940609952, "percentage": 53.85, "elapsed_time": "2:06:12", "remaining_time": "1:48:10"}
|
| 85 |
+
{"current_steps": 425, "total_steps": 780, "loss": 0.4047, "lr": 2.0447482977425465e-05, "epoch": 2.725521669341894, "percentage": 54.49, "elapsed_time": "2:07:44", "remaining_time": "1:46:42"}
|
| 86 |
+
{"current_steps": 430, "total_steps": 780, "loss": 0.4148, "lr": 2e-05, "epoch": 2.7576243980738364, "percentage": 55.13, "elapsed_time": "2:09:10", "remaining_time": "1:45:08"}
|
| 87 |
+
{"current_steps": 435, "total_steps": 780, "loss": 0.4073, "lr": 1.9552517022574542e-05, "epoch": 2.7897271268057784, "percentage": 55.77, "elapsed_time": "2:10:40", "remaining_time": "1:43:38"}
|
| 88 |
+
{"current_steps": 440, "total_steps": 780, "loss": 0.4198, "lr": 1.910525808430532e-05, "epoch": 2.821829855537721, "percentage": 56.41, "elapsed_time": "2:12:05", "remaining_time": "1:42:04"}
|
| 89 |
+
{"current_steps": 445, "total_steps": 780, "loss": 0.4064, "lr": 1.8658447112179952e-05, "epoch": 2.853932584269663, "percentage": 57.05, "elapsed_time": "2:13:26", "remaining_time": "1:40:27"}
|
| 90 |
+
{"current_steps": 450, "total_steps": 780, "loss": 0.4039, "lr": 1.821230780890502e-05, "epoch": 2.886035313001605, "percentage": 57.69, "elapsed_time": "2:14:56", "remaining_time": "1:38:57"}
|
| 91 |
+
{"current_steps": 455, "total_steps": 780, "loss": 0.3946, "lr": 1.776706354090585e-05, "epoch": 2.918138041733547, "percentage": 58.33, "elapsed_time": "2:16:33", "remaining_time": "1:37:32"}
|
| 92 |
+
{"current_steps": 460, "total_steps": 780, "loss": 0.4167, "lr": 1.7322937226494775e-05, "epoch": 2.9502407704654896, "percentage": 58.97, "elapsed_time": "2:17:58", "remaining_time": "1:35:59"}
|
| 93 |
+
{"current_steps": 465, "total_steps": 780, "loss": 0.4143, "lr": 1.6880151224263646e-05, "epoch": 2.982343499197432, "percentage": 59.62, "elapsed_time": "2:19:37", "remaining_time": "1:34:34"}
|
| 94 |
+
{"current_steps": 470, "total_steps": 780, "loss": 0.3996, "lr": 1.643892722175667e-05, "epoch": 3.012841091492777, "percentage": 60.26, "elapsed_time": "2:21:02", "remaining_time": "1:33:01"}
|
| 95 |
+
{"current_steps": 475, "total_steps": 780, "loss": 0.3963, "lr": 1.5999486124479115e-05, "epoch": 3.044943820224719, "percentage": 60.9, "elapsed_time": "2:22:31", "remaining_time": "1:31:30"}
|
| 96 |
+
{"current_steps": 480, "total_steps": 780, "loss": 0.3921, "lr": 1.5562047945297652e-05, "epoch": 3.077046548956661, "percentage": 61.54, "elapsed_time": "2:23:56", "remaining_time": "1:29:57"}
|
| 97 |
+
{"current_steps": 485, "total_steps": 780, "loss": 0.3875, "lr": 1.5126831694287564e-05, "epoch": 3.1091492776886036, "percentage": 62.18, "elapsed_time": "2:25:28", "remaining_time": "1:28:28"}
|
| 98 |
+
{"current_steps": 490, "total_steps": 780, "loss": 0.3897, "lr": 1.4694055269081987e-05, "epoch": 3.1412520064205456, "percentage": 62.82, "elapsed_time": "2:27:03", "remaining_time": "1:27:01"}
|
| 99 |
+
{"current_steps": 495, "total_steps": 780, "loss": 0.4068, "lr": 1.4263935345778202e-05, "epoch": 3.173354735152488, "percentage": 63.46, "elapsed_time": "2:28:29", "remaining_time": "1:25:29"}
|
| 100 |
+
{"current_steps": 500, "total_steps": 780, "loss": 0.4003, "lr": 1.3836687270455388e-05, "epoch": 3.20545746388443, "percentage": 64.1, "elapsed_time": "2:29:55", "remaining_time": "1:23:57"}
|
| 101 |
+
{"current_steps": 505, "total_steps": 780, "loss": 0.404, "lr": 1.341252495135841e-05, "epoch": 3.2375601926163724, "percentage": 64.74, "elapsed_time": "2:31:27", "remaining_time": "1:22:28"}
|
| 102 |
+
{"current_steps": 510, "total_steps": 780, "loss": 0.4105, "lr": 1.299166075180133e-05, "epoch": 3.2696629213483144, "percentage": 65.38, "elapsed_time": "2:33:00", "remaining_time": "1:21:00"}
|
| 103 |
+
{"current_steps": 515, "total_steps": 780, "loss": 0.4021, "lr": 1.2574305383844528e-05, "epoch": 3.301765650080257, "percentage": 66.03, "elapsed_time": "2:34:26", "remaining_time": "1:19:28"}
|
| 104 |
+
{"current_steps": 520, "total_steps": 780, "loss": 0.4041, "lr": 1.2160667802798503e-05, "epoch": 3.333868378812199, "percentage": 66.67, "elapsed_time": "2:36:02", "remaining_time": "1:18:01"}
|
| 105 |
+
{"current_steps": 525, "total_steps": 780, "loss": 0.4017, "lr": 1.1750955102607193e-05, "epoch": 3.365971107544141, "percentage": 67.31, "elapsed_time": "2:37:33", "remaining_time": "1:16:31"}
|
| 106 |
+
{"current_steps": 530, "total_steps": 780, "loss": 0.4022, "lr": 1.1345372412163276e-05, "epoch": 3.3980738362760836, "percentage": 67.95, "elapsed_time": "2:38:59", "remaining_time": "1:14:59"}
|
| 107 |
+
{"current_steps": 535, "total_steps": 780, "loss": 0.4071, "lr": 1.094412279260726e-05, "epoch": 3.4301765650080256, "percentage": 68.59, "elapsed_time": "2:40:31", "remaining_time": "1:13:30"}
|
| 108 |
+
{"current_steps": 540, "total_steps": 780, "loss": 0.4, "lr": 1.0547407135661816e-05, "epoch": 3.462279293739968, "percentage": 69.23, "elapsed_time": "2:41:52", "remaining_time": "1:11:56"}
|
| 109 |
+
{"current_steps": 545, "total_steps": 780, "loss": 0.3857, "lr": 1.0155424063052306e-05, "epoch": 3.49438202247191, "percentage": 69.87, "elapsed_time": "2:43:20", "remaining_time": "1:10:25"}
|
| 110 |
+
{"current_steps": 550, "total_steps": 780, "loss": 0.4029, "lr": 9.768369827063803e-06, "epoch": 3.5264847512038524, "percentage": 70.51, "elapsed_time": "2:44:45", "remaining_time": "1:08:53"}
|
| 111 |
+
{"current_steps": 555, "total_steps": 780, "loss": 0.4033, "lr": 9.386438212284372e-06, "epoch": 3.5585874799357944, "percentage": 71.15, "elapsed_time": "2:46:17", "remaining_time": "1:07:24"}
|
| 112 |
+
{"current_steps": 560, "total_steps": 780, "loss": 0.4145, "lr": 9.009820438583881e-06, "epoch": 3.590690208667737, "percentage": 71.79, "elapsed_time": "2:47:38", "remaining_time": "1:05:51"}
|
| 113 |
+
{"current_steps": 565, "total_steps": 780, "loss": 0.3852, "lr": 8.638705065376887e-06, "epoch": 3.6227929373996792, "percentage": 72.44, "elapsed_time": "2:49:05", "remaining_time": "1:04:20"}
|
| 114 |
+
{"current_steps": 570, "total_steps": 780, "loss": 0.376, "lr": 8.27327789721746e-06, "epoch": 3.654895666131621, "percentage": 73.08, "elapsed_time": "2:50:40", "remaining_time": "1:02:52"}
|
| 115 |
+
{"current_steps": 575, "total_steps": 780, "loss": 0.4033, "lr": 7.913721890773354e-06, "epoch": 3.686998394863563, "percentage": 73.72, "elapsed_time": "2:52:10", "remaining_time": "1:01:23"}
|
| 116 |
+
{"current_steps": 580, "total_steps": 780, "loss": 0.398, "lr": 7.560217063225923e-06, "epoch": 3.7191011235955056, "percentage": 74.36, "elapsed_time": "2:53:26", "remaining_time": "0:59:48"}
|
| 117 |
+
{"current_steps": 585, "total_steps": 780, "loss": 0.4014, "lr": 7.212940402141808e-06, "epoch": 3.751203852327448, "percentage": 75.0, "elapsed_time": "2:55:01", "remaining_time": "0:58:20"}
|
| 118 |
+
{"current_steps": 590, "total_steps": 780, "loss": 0.4097, "lr": 6.8720657768614115e-06, "epoch": 3.78330658105939, "percentage": 75.64, "elapsed_time": "2:56:29", "remaining_time": "0:56:50"}
|
| 119 |
+
{"current_steps": 595, "total_steps": 780, "loss": 0.4046, "lr": 6.537763851448593e-06, "epoch": 3.8154093097913324, "percentage": 76.28, "elapsed_time": "2:57:53", "remaining_time": "0:55:18"}
|
| 120 |
+
{"current_steps": 600, "total_steps": 780, "loss": 0.4153, "lr": 6.210201999245087e-06, "epoch": 3.8475120385232744, "percentage": 76.92, "elapsed_time": "2:59:18", "remaining_time": "0:53:47"}
|
| 121 |
+
{"current_steps": 605, "total_steps": 780, "loss": 0.4028, "lr": 5.889544219072465e-06, "epoch": 3.879614767255217, "percentage": 77.56, "elapsed_time": "3:00:49", "remaining_time": "0:52:18"}
|
| 122 |
+
{"current_steps": 610, "total_steps": 780, "loss": 0.3933, "lr": 5.5759510531237116e-06, "epoch": 3.911717495987159, "percentage": 78.21, "elapsed_time": "3:02:12", "remaining_time": "0:50:46"}
|
| 123 |
+
{"current_steps": 615, "total_steps": 780, "loss": 0.3911, "lr": 5.269579506585259e-06, "epoch": 3.943820224719101, "percentage": 78.85, "elapsed_time": "3:03:41", "remaining_time": "0:49:16"}
|
| 124 |
+
{"current_steps": 620, "total_steps": 780, "loss": 0.401, "lr": 4.97058296903e-06, "epoch": 3.975922953451043, "percentage": 79.49, "elapsed_time": "3:05:07", "remaining_time": "0:47:46"}
|
| 125 |
+
{"current_steps": 625, "total_steps": 780, "loss": 0.3997, "lr": 4.679111137620442e-06, "epoch": 4.006420545746389, "percentage": 80.13, "elapsed_time": "3:06:32", "remaining_time": "0:46:15"}
|
| 126 |
+
{"current_steps": 630, "total_steps": 780, "loss": 0.3913, "lr": 4.395309942160551e-06, "epoch": 4.03852327447833, "percentage": 80.77, "elapsed_time": "3:08:03", "remaining_time": "0:44:46"}
|
| 127 |
+
{"current_steps": 635, "total_steps": 780, "loss": 0.3949, "lr": 4.119321472033779e-06, "epoch": 4.070626003210273, "percentage": 81.41, "elapsed_time": "3:09:33", "remaining_time": "0:43:17"}
|
| 128 |
+
{"current_steps": 640, "total_steps": 780, "loss": 0.3946, "lr": 3.851283905063863e-06, "epoch": 4.102728731942215, "percentage": 82.05, "elapsed_time": "3:10:59", "remaining_time": "0:41:46"}
|
| 129 |
+
{"current_steps": 645, "total_steps": 780, "loss": 0.3872, "lr": 3.5913314383339937e-06, "epoch": 4.134831460674158, "percentage": 82.69, "elapsed_time": "3:12:26", "remaining_time": "0:40:16"}
|
| 130 |
+
{"current_steps": 650, "total_steps": 780, "loss": 0.4023, "lr": 3.3395942209989694e-06, "epoch": 4.166934189406099, "percentage": 83.33, "elapsed_time": "3:13:52", "remaining_time": "0:38:46"}
|
| 131 |
+
{"current_steps": 655, "total_steps": 780, "loss": 0.3731, "lr": 3.0961982891241083e-06, "epoch": 4.199036918138042, "percentage": 83.97, "elapsed_time": "3:15:23", "remaining_time": "0:37:17"}
|
| 132 |
+
{"current_steps": 660, "total_steps": 780, "loss": 0.395, "lr": 2.8612655025833148e-06, "epoch": 4.231139646869984, "percentage": 84.62, "elapsed_time": "3:16:47", "remaining_time": "0:35:46"}
|
| 133 |
+
{"current_steps": 665, "total_steps": 780, "loss": 0.3809, "lr": 2.6349134840481294e-06, "epoch": 4.263242375601926, "percentage": 85.26, "elapsed_time": "3:18:14", "remaining_time": "0:34:16"}
|
| 134 |
+
{"current_steps": 670, "total_steps": 780, "loss": 0.3984, "lr": 2.417255560098111e-06, "epoch": 4.295345104333869, "percentage": 85.9, "elapsed_time": "3:19:40", "remaining_time": "0:32:46"}
|
| 135 |
+
{"current_steps": 675, "total_steps": 780, "loss": 0.389, "lr": 2.2084007044821764e-06, "epoch": 4.32744783306581, "percentage": 86.54, "elapsed_time": "3:21:09", "remaining_time": "0:31:17"}
|
| 136 |
+
{"current_steps": 680, "total_steps": 780, "loss": 0.3961, "lr": 2.0084534835592584e-06, "epoch": 4.359550561797753, "percentage": 87.18, "elapsed_time": "3:22:40", "remaining_time": "0:29:48"}
|
| 137 |
+
{"current_steps": 685, "total_steps": 780, "loss": 0.4008, "lr": 1.817514003945524e-06, "epoch": 4.391653290529695, "percentage": 87.82, "elapsed_time": "3:24:06", "remaining_time": "0:28:18"}
|
| 138 |
+
{"current_steps": 690, "total_steps": 780, "loss": 0.4052, "lr": 1.6356778623945223e-06, "epoch": 4.423756019261638, "percentage": 88.46, "elapsed_time": "3:25:32", "remaining_time": "0:26:48"}
|
| 139 |
+
{"current_steps": 695, "total_steps": 780, "loss": 0.4089, "lr": 1.4630360979351644e-06, "epoch": 4.455858747993579, "percentage": 89.1, "elapsed_time": "3:26:56", "remaining_time": "0:25:18"}
|
| 140 |
+
{"current_steps": 700, "total_steps": 780, "loss": 0.4004, "lr": 1.2996751462917057e-06, "epoch": 4.487961476725522, "percentage": 89.74, "elapsed_time": "3:28:21", "remaining_time": "0:23:48"}
|
| 141 |
+
{"current_steps": 705, "total_steps": 780, "loss": 0.3842, "lr": 1.1456767966083393e-06, "epoch": 4.520064205457464, "percentage": 90.38, "elapsed_time": "3:29:50", "remaining_time": "0:22:19"}
|
| 142 |
+
{"current_steps": 710, "total_steps": 780, "loss": 0.3908, "lr": 1.0011181505002488e-06, "epoch": 4.552166934189406, "percentage": 91.03, "elapsed_time": "3:31:12", "remaining_time": "0:20:49"}
|
| 143 |
+
{"current_steps": 715, "total_steps": 780, "loss": 0.3843, "lr": 8.660715834514977e-07, "epoch": 4.584269662921348, "percentage": 91.67, "elapsed_time": "3:32:42", "remaining_time": "0:19:20"}
|
| 144 |
+
{"current_steps": 720, "total_steps": 780, "loss": 0.3861, "lr": 7.406047085791379e-07, "epoch": 4.61637239165329, "percentage": 92.31, "elapsed_time": "3:34:18", "remaining_time": "0:17:51"}
|
| 145 |
+
{"current_steps": 725, "total_steps": 780, "loss": 0.4133, "lr": 6.247803427816945e-07, "epoch": 4.648475120385233, "percentage": 92.95, "elapsed_time": "3:35:44", "remaining_time": "0:16:21"}
|
| 146 |
+
{"current_steps": 730, "total_steps": 780, "loss": 0.3965, "lr": 5.186564752889078e-07, "epoch": 4.680577849117175, "percentage": 93.59, "elapsed_time": "3:37:12", "remaining_time": "0:14:52"}
|
| 147 |
+
{"current_steps": 735, "total_steps": 780, "loss": 0.3784, "lr": 4.22286238628562e-07, "epoch": 4.712680577849117, "percentage": 94.23, "elapsed_time": "3:38:49", "remaining_time": "0:13:23"}
|
| 148 |
+
{"current_steps": 740, "total_steps": 780, "loss": 0.3961, "lr": 3.357178820248641e-07, "epoch": 4.744783306581059, "percentage": 94.87, "elapsed_time": "3:40:21", "remaining_time": "0:11:54"}
|
| 149 |
+
{"current_steps": 745, "total_steps": 780, "loss": 0.3988, "lr": 2.5899474724174313e-07, "epoch": 4.776886035313002, "percentage": 95.51, "elapsed_time": "3:41:48", "remaining_time": "0:10:25"}
|
| 150 |
+
{"current_steps": 750, "total_steps": 780, "loss": 0.3927, "lr": 1.9215524688313893e-07, "epoch": 4.808988764044944, "percentage": 96.15, "elapsed_time": "3:43:20", "remaining_time": "0:08:56"}
|
| 151 |
+
{"current_steps": 755, "total_steps": 780, "loss": 0.387, "lr": 1.3523284516113955e-07, "epoch": 4.841091492776886, "percentage": 96.79, "elapsed_time": "3:44:49", "remaining_time": "0:07:26"}
|
| 152 |
+
{"current_steps": 760, "total_steps": 780, "loss": 0.3918, "lr": 8.825604114162556e-08, "epoch": 4.873194221508828, "percentage": 97.44, "elapsed_time": "3:46:28", "remaining_time": "0:05:57"}
|
| 153 |
+
{"current_steps": 765, "total_steps": 780, "loss": 0.4068, "lr": 5.1248354475768034e-08, "epoch": 4.90529695024077, "percentage": 98.08, "elapsed_time": "3:47:56", "remaining_time": "0:04:28"}
|
| 154 |
+
{"current_steps": 770, "total_steps": 780, "loss": 0.3876, "lr": 2.4228313624568013e-08, "epoch": 4.937399678972713, "percentage": 98.72, "elapsed_time": "3:49:25", "remaining_time": "0:02:58"}
|
| 155 |
+
{"current_steps": 775, "total_steps": 780, "loss": 0.4201, "lr": 7.209446582292501e-09, "epoch": 4.969502407704655, "percentage": 99.36, "elapsed_time": "3:50:45", "remaining_time": "0:01:29"}
|
| 156 |
+
{"current_steps": 780, "total_steps": 780, "loss": 0.4005, "lr": 2.002741034812239e-10, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "3:52:03", "remaining_time": "0:00:00"}
|
| 157 |
+
{"current_steps": 780, "total_steps": 780, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "3:52:03", "remaining_time": "0:00:00"}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c66353c6010841c296af2d0521f69e43e8c7f191ee28c2904bf069ac66be1b3b
|
| 3 |
+
size 8593
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|