Final model from fleet-sft-overfit-github-Qwen3-32B (exit code: 0)
Browse files- .gitattributes +1 -0
- .uploaded_checkpoints +0 -0
- README.md +135 -0
- added_tokens.json +28 -0
- all_results.json +12 -0
- chat_template.jinja +89 -0
- config.json +30 -0
- eval_github/all_results.json +7 -0
- eval_github/eval_results.json +7 -0
- eval_github/trainer_log.jsonl +15 -0
- eval_results.json +7 -0
- final_metrics.json +1 -0
- generation_config.json +13 -0
- merges.txt +0 -0
- model-00001-of-00014.safetensors +3 -0
- model-00002-of-00014.safetensors +3 -0
- model-00003-of-00014.safetensors +3 -0
- model-00004-of-00014.safetensors +3 -0
- model-00005-of-00014.safetensors +3 -0
- model-00006-of-00014.safetensors +3 -0
- model-00007-of-00014.safetensors +3 -0
- model-00008-of-00014.safetensors +3 -0
- model-00009-of-00014.safetensors +3 -0
- model-00010-of-00014.safetensors +3 -0
- model-00011-of-00014.safetensors +3 -0
- model-00012-of-00014.safetensors +3 -0
- model-00013-of-00014.safetensors +3 -0
- model-00014-of-00014.safetensors +3 -0
- model.safetensors.index.json +714 -0
- per_env_metrics.json +3 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +240 -0
- train_results.json +8 -0
- trainer_log.jsonl +142 -0
- trainer_state.json +1101 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -34,3 +34,4 @@ saved_model/**/* 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 |
checkpoint-350/tokenizer.json 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 |
checkpoint-350/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
.uploaded_checkpoints
ADDED
|
File without changes
|
README.md
ADDED
|
@@ -0,0 +1,135 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: other
|
| 4 |
+
base_model: Qwen/Qwen3-32B
|
| 5 |
+
tags:
|
| 6 |
+
- llama-factory
|
| 7 |
+
- full
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: fleet-sft-full
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# fleet-sft-full
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [Qwen/Qwen3-32B](https://huggingface.co/Qwen/Qwen3-32B) on the fleet_trajectories_train dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 1.8278
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 2e-05
|
| 41 |
+
- train_batch_size: 1
|
| 42 |
+
- eval_batch_size: 1
|
| 43 |
+
- seed: 42
|
| 44 |
+
- distributed_type: multi-GPU
|
| 45 |
+
- num_devices: 8
|
| 46 |
+
- total_train_batch_size: 8
|
| 47 |
+
- total_eval_batch_size: 8
|
| 48 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 49 |
+
- lr_scheduler_type: cosine
|
| 50 |
+
- lr_scheduler_warmup_ratio: 0.05
|
| 51 |
+
- num_epochs: 50.0
|
| 52 |
+
|
| 53 |
+
### Training results
|
| 54 |
+
|
| 55 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 56 |
+
|:-------------:|:-------:|:----:|:---------------:|
|
| 57 |
+
| No log | 0 | 0 | 1.4682 |
|
| 58 |
+
| 1.3518 | 0.7143 | 5 | 1.3431 |
|
| 59 |
+
| 0.9051 | 1.4286 | 10 | 1.2059 |
|
| 60 |
+
| 0.8625 | 2.1429 | 15 | 1.1277 |
|
| 61 |
+
| 0.6971 | 2.8571 | 20 | 1.1145 |
|
| 62 |
+
| 0.4243 | 3.5714 | 25 | 1.1612 |
|
| 63 |
+
| 0.1901 | 4.2857 | 30 | 1.3399 |
|
| 64 |
+
| 0.1171 | 5.0 | 35 | 1.3959 |
|
| 65 |
+
| 0.0593 | 5.7143 | 40 | 1.4992 |
|
| 66 |
+
| 0.0265 | 6.4286 | 45 | 1.5967 |
|
| 67 |
+
| 0.0229 | 7.1429 | 50 | 1.6269 |
|
| 68 |
+
| 0.0167 | 7.8571 | 55 | 1.6505 |
|
| 69 |
+
| 0.0119 | 8.5714 | 60 | 1.6626 |
|
| 70 |
+
| 0.0094 | 9.2857 | 65 | 1.6874 |
|
| 71 |
+
| 0.0089 | 10.0 | 70 | 1.7035 |
|
| 72 |
+
| 0.0062 | 10.7143 | 75 | 1.7053 |
|
| 73 |
+
| 0.0072 | 11.4286 | 80 | 1.7082 |
|
| 74 |
+
| 0.008 | 12.1429 | 85 | 1.6972 |
|
| 75 |
+
| 0.006 | 12.8571 | 90 | 1.6969 |
|
| 76 |
+
| 0.0044 | 13.5714 | 95 | 1.7049 |
|
| 77 |
+
| 0.0036 | 14.2857 | 100 | 1.7229 |
|
| 78 |
+
| 0.0035 | 15.0 | 105 | 1.7421 |
|
| 79 |
+
| 0.0026 | 15.7143 | 110 | 1.7550 |
|
| 80 |
+
| 0.0023 | 16.4286 | 115 | 1.7617 |
|
| 81 |
+
| 0.0021 | 17.1429 | 120 | 1.7656 |
|
| 82 |
+
| 0.0025 | 17.8571 | 125 | 1.7683 |
|
| 83 |
+
| 0.0018 | 18.5714 | 130 | 1.7750 |
|
| 84 |
+
| 0.002 | 19.2857 | 135 | 1.7667 |
|
| 85 |
+
| 0.0036 | 20.0 | 140 | 1.7492 |
|
| 86 |
+
| 0.0025 | 20.7143 | 145 | 1.7378 |
|
| 87 |
+
| 0.0017 | 21.4286 | 150 | 1.7389 |
|
| 88 |
+
| 0.0016 | 22.1429 | 155 | 1.7510 |
|
| 89 |
+
| 0.0016 | 22.8571 | 160 | 1.7623 |
|
| 90 |
+
| 0.0014 | 23.5714 | 165 | 1.7705 |
|
| 91 |
+
| 0.0013 | 24.2857 | 170 | 1.7751 |
|
| 92 |
+
| 0.0015 | 25.0 | 175 | 1.7802 |
|
| 93 |
+
| 0.0011 | 25.7143 | 180 | 1.7830 |
|
| 94 |
+
| 0.0012 | 26.4286 | 185 | 1.7873 |
|
| 95 |
+
| 0.0011 | 27.1429 | 190 | 1.7919 |
|
| 96 |
+
| 0.0012 | 27.8571 | 195 | 1.7959 |
|
| 97 |
+
| 0.0012 | 28.5714 | 200 | 1.7993 |
|
| 98 |
+
| 0.001 | 29.2857 | 205 | 1.8018 |
|
| 99 |
+
| 0.0012 | 30.0 | 210 | 1.8040 |
|
| 100 |
+
| 0.001 | 30.7143 | 215 | 1.8073 |
|
| 101 |
+
| 0.001 | 31.4286 | 220 | 1.8092 |
|
| 102 |
+
| 0.0014 | 32.1429 | 225 | 1.8116 |
|
| 103 |
+
| 0.0011 | 32.8571 | 230 | 1.8135 |
|
| 104 |
+
| 0.001 | 33.5714 | 235 | 1.8141 |
|
| 105 |
+
| 0.0011 | 34.2857 | 240 | 1.8167 |
|
| 106 |
+
| 0.0009 | 35.0 | 245 | 1.8182 |
|
| 107 |
+
| 0.001 | 35.7143 | 250 | 1.8190 |
|
| 108 |
+
| 0.0011 | 36.4286 | 255 | 1.8204 |
|
| 109 |
+
| 0.0012 | 37.1429 | 260 | 1.8216 |
|
| 110 |
+
| 0.0009 | 37.8571 | 265 | 1.8221 |
|
| 111 |
+
| 0.001 | 38.5714 | 270 | 1.8223 |
|
| 112 |
+
| 0.0013 | 39.2857 | 275 | 1.8238 |
|
| 113 |
+
| 0.0011 | 40.0 | 280 | 1.8247 |
|
| 114 |
+
| 0.0009 | 40.7143 | 285 | 1.8251 |
|
| 115 |
+
| 0.0011 | 41.4286 | 290 | 1.8253 |
|
| 116 |
+
| 0.001 | 42.1429 | 295 | 1.8262 |
|
| 117 |
+
| 0.001 | 42.8571 | 300 | 1.8267 |
|
| 118 |
+
| 0.0011 | 43.5714 | 305 | 1.8267 |
|
| 119 |
+
| 0.0012 | 44.2857 | 310 | 1.8272 |
|
| 120 |
+
| 0.0009 | 45.0 | 315 | 1.8278 |
|
| 121 |
+
| 0.0008 | 45.7143 | 320 | 1.8276 |
|
| 122 |
+
| 0.0009 | 46.4286 | 325 | 1.8282 |
|
| 123 |
+
| 0.001 | 47.1429 | 330 | 1.8282 |
|
| 124 |
+
| 0.001 | 47.8571 | 335 | 1.8279 |
|
| 125 |
+
| 0.0008 | 48.5714 | 340 | 1.8282 |
|
| 126 |
+
| 0.0012 | 49.2857 | 345 | 1.8281 |
|
| 127 |
+
| 0.001 | 50.0 | 350 | 1.8278 |
|
| 128 |
+
|
| 129 |
+
|
| 130 |
+
### Framework versions
|
| 131 |
+
|
| 132 |
+
- Transformers 4.52.4
|
| 133 |
+
- Pytorch 2.10.0+cu128
|
| 134 |
+
- Datasets 3.6.0
|
| 135 |
+
- 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 |
+
}
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 50.0,
|
| 3 |
+
"eval_loss": 1.8277511596679688,
|
| 4 |
+
"eval_runtime": 21.3223,
|
| 5 |
+
"eval_samples_per_second": 2.345,
|
| 6 |
+
"eval_steps_per_second": 0.328,
|
| 7 |
+
"total_flos": 86960020979712.0,
|
| 8 |
+
"train_loss": 0.06868666498057012,
|
| 9 |
+
"train_runtime": 10021.0579,
|
| 10 |
+
"train_samples_per_second": 0.249,
|
| 11 |
+
"train_steps_per_second": 0.035
|
| 12 |
+
}
|
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 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 5120,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 25600,
|
| 14 |
+
"max_position_embeddings": 40960,
|
| 15 |
+
"max_window_layers": 64,
|
| 16 |
+
"model_type": "qwen3",
|
| 17 |
+
"num_attention_heads": 64,
|
| 18 |
+
"num_hidden_layers": 64,
|
| 19 |
+
"num_key_value_heads": 8,
|
| 20 |
+
"rms_norm_eps": 1e-06,
|
| 21 |
+
"rope_scaling": null,
|
| 22 |
+
"rope_theta": 1000000,
|
| 23 |
+
"sliding_window": null,
|
| 24 |
+
"tie_word_embeddings": false,
|
| 25 |
+
"torch_dtype": "bfloat16",
|
| 26 |
+
"transformers_version": "4.52.4",
|
| 27 |
+
"use_cache": false,
|
| 28 |
+
"use_sliding_window": false,
|
| 29 |
+
"vocab_size": 151936
|
| 30 |
+
}
|
eval_github/all_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"eval_loss": 1.7327340841293335,
|
| 3 |
+
"eval_model_preparation_time": 0.6122,
|
| 4 |
+
"eval_runtime": 246.6863,
|
| 5 |
+
"eval_samples_per_second": 2.363,
|
| 6 |
+
"eval_steps_per_second": 0.296
|
| 7 |
+
}
|
eval_github/eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"eval_loss": 1.7327340841293335,
|
| 3 |
+
"eval_model_preparation_time": 0.6122,
|
| 4 |
+
"eval_runtime": 246.6863,
|
| 5 |
+
"eval_samples_per_second": 2.363,
|
| 6 |
+
"eval_steps_per_second": 0.296
|
| 7 |
+
}
|
eval_github/trainer_log.jsonl
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 5, "total_steps": 73, "percentage": 6.85, "elapsed_time": "0:00:13", "remaining_time": "0:02:59"}
|
| 2 |
+
{"current_steps": 10, "total_steps": 73, "percentage": 13.7, "elapsed_time": "0:00:19", "remaining_time": "0:02:03"}
|
| 3 |
+
{"current_steps": 15, "total_steps": 73, "percentage": 20.55, "elapsed_time": "0:00:37", "remaining_time": "0:02:24"}
|
| 4 |
+
{"current_steps": 20, "total_steps": 73, "percentage": 27.4, "elapsed_time": "0:00:57", "remaining_time": "0:02:31"}
|
| 5 |
+
{"current_steps": 25, "total_steps": 73, "percentage": 34.25, "elapsed_time": "0:01:15", "remaining_time": "0:02:25"}
|
| 6 |
+
{"current_steps": 30, "total_steps": 73, "percentage": 41.1, "elapsed_time": "0:01:30", "remaining_time": "0:02:10"}
|
| 7 |
+
{"current_steps": 35, "total_steps": 73, "percentage": 47.95, "elapsed_time": "0:01:52", "remaining_time": "0:02:02"}
|
| 8 |
+
{"current_steps": 40, "total_steps": 73, "percentage": 54.79, "elapsed_time": "0:02:06", "remaining_time": "0:01:43"}
|
| 9 |
+
{"current_steps": 45, "total_steps": 73, "percentage": 61.64, "elapsed_time": "0:02:29", "remaining_time": "0:01:32"}
|
| 10 |
+
{"current_steps": 50, "total_steps": 73, "percentage": 68.49, "elapsed_time": "0:02:39", "remaining_time": "0:01:13"}
|
| 11 |
+
{"current_steps": 55, "total_steps": 73, "percentage": 75.34, "elapsed_time": "0:02:54", "remaining_time": "0:00:57"}
|
| 12 |
+
{"current_steps": 60, "total_steps": 73, "percentage": 82.19, "elapsed_time": "0:03:17", "remaining_time": "0:00:42"}
|
| 13 |
+
{"current_steps": 65, "total_steps": 73, "percentage": 89.04, "elapsed_time": "0:03:30", "remaining_time": "0:00:25"}
|
| 14 |
+
{"current_steps": 70, "total_steps": 73, "percentage": 95.89, "elapsed_time": "0:03:37", "remaining_time": "0:00:09"}
|
| 15 |
+
{"current_steps": 0, "total_steps": 73, "eval_loss": 1.7327340841293335, "percentage": 0.0, "elapsed_time": "0:04:04", "remaining_time": "0:00:00"}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 50.0,
|
| 3 |
+
"eval_loss": 1.8277511596679688,
|
| 4 |
+
"eval_runtime": 21.3223,
|
| 5 |
+
"eval_samples_per_second": 2.345,
|
| 6 |
+
"eval_steps_per_second": 0.328
|
| 7 |
+
}
|
final_metrics.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"final_train_loss": 0.001, "final_eval_loss": 1.8277511596679688}
|
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": "4.52.4"
|
| 13 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9888555858ca4c8a666a3c2f146018189fb3af90e454ee2f386246ea598955d6
|
| 3 |
+
size 4932307584
|
model-00002-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0d5011268768b63a1809dd73d2b98bb7c8a1f6ba49018fb06eb590e339f989dc
|
| 3 |
+
size 4875989696
|
model-00003-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:af10a7d1bf08dffc83a37fcd902c8b1b42c19f00f6d6dac9ea4dc6e818a5254b
|
| 3 |
+
size 4875989720
|
model-00004-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aa6402dc5a0871a5d70ec5bfcf7440fda612fda8d10d07ab813f83b9d4fa21e6
|
| 3 |
+
size 4875989752
|
model-00005-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c1c2e10597ac9d07446327926eb8a8d7c9d2beb109e7585922377a1aa739dd79
|
| 3 |
+
size 4875989752
|
model-00006-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c5a316b818ffd0797b51ef786437ccc18e76cf3984e95d88d0dfe99cd07fdb0e
|
| 3 |
+
size 4875989752
|
model-00007-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:66079a17bb52ee309d68a4edc6808c588671cf93806b5f382063a16d39eaf823
|
| 3 |
+
size 4875989752
|
model-00008-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2b6e5c7831bc2769ef356ce1db54a6ed49effdd7737b9ef081f41a7229bc388e
|
| 3 |
+
size 4875989752
|
model-00009-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a19897889140f789f853f21bfbb6c54403d01870816a4948de0578920066c0a2
|
| 3 |
+
size 4875989752
|
model-00010-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ff5aa0bc8c5a47e2fdeac02df8a44dfff278cf3f1019fc3d2b381e66de30b807
|
| 3 |
+
size 4875989752
|
model-00011-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:03466830fb842c57237e194a789539c0e810fb72f96e0e33746a1c4814c3349d
|
| 3 |
+
size 4875989752
|
model-00012-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e150746100e126f608bbd46e96d753321633415760fa3c6a2f0bceb1a8bde27b
|
| 3 |
+
size 4875989752
|
model-00013-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f384883df124d14241e89cb2262e5d3a1026edb088c91fdb0ca31cad3b57b9c3
|
| 3 |
+
size 4875989752
|
model-00014-of-00014.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d4cd46b9e4ee0dfc4188ce2c787650095a76b2e0508c6c564f42d6360d2a3897
|
| 3 |
+
size 2080144040
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,714 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 65524246528
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "model-00014-of-00014.safetensors",
|
| 7 |
+
"model.embed_tokens.weight": "model-00001-of-00014.safetensors",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
|
| 13 |
+
"model.layers.0.self_attn.k_norm.weight": "model-00001-of-00014.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.q_norm.weight": "model-00001-of-00014.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
|
| 19 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors",
|
| 20 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
|
| 21 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
|
| 22 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
|
| 23 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
|
| 24 |
+
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00014.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.q_norm.weight": "model-00001-of-00014.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
|
| 29 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
|
| 30 |
+
"model.layers.10.input_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 31 |
+
"model.layers.10.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
|
| 32 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
|
| 33 |
+
"model.layers.10.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
|
| 34 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 35 |
+
"model.layers.10.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
|
| 36 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
|
| 37 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
|
| 38 |
+
"model.layers.10.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
|
| 39 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
|
| 40 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
|
| 41 |
+
"model.layers.11.input_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 42 |
+
"model.layers.11.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
|
| 43 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
|
| 44 |
+
"model.layers.11.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
|
| 45 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 46 |
+
"model.layers.11.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
|
| 47 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
|
| 48 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
|
| 49 |
+
"model.layers.11.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
|
| 50 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
|
| 51 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
|
| 52 |
+
"model.layers.12.input_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 53 |
+
"model.layers.12.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
|
| 54 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
|
| 55 |
+
"model.layers.12.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
|
| 56 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 57 |
+
"model.layers.12.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
|
| 58 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
|
| 59 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
|
| 60 |
+
"model.layers.12.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
|
| 61 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
|
| 62 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
|
| 63 |
+
"model.layers.13.input_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 64 |
+
"model.layers.13.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
|
| 65 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
|
| 66 |
+
"model.layers.13.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
|
| 67 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 68 |
+
"model.layers.13.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
|
| 69 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
|
| 70 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
|
| 71 |
+
"model.layers.13.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
|
| 72 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
|
| 73 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
|
| 74 |
+
"model.layers.14.input_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 75 |
+
"model.layers.14.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
|
| 76 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
|
| 77 |
+
"model.layers.14.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
|
| 78 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 79 |
+
"model.layers.14.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
|
| 80 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
|
| 81 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
|
| 82 |
+
"model.layers.14.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
|
| 83 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
|
| 84 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
|
| 85 |
+
"model.layers.15.input_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 86 |
+
"model.layers.15.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
|
| 87 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
|
| 88 |
+
"model.layers.15.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
|
| 89 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 90 |
+
"model.layers.15.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
|
| 91 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
|
| 92 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
|
| 93 |
+
"model.layers.15.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
|
| 94 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
|
| 95 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
|
| 96 |
+
"model.layers.16.input_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 97 |
+
"model.layers.16.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
|
| 98 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
|
| 99 |
+
"model.layers.16.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
|
| 100 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 101 |
+
"model.layers.16.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
|
| 102 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
|
| 103 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
|
| 104 |
+
"model.layers.16.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
|
| 105 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
|
| 106 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
|
| 107 |
+
"model.layers.17.input_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 108 |
+
"model.layers.17.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
|
| 109 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
|
| 110 |
+
"model.layers.17.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
|
| 111 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
|
| 112 |
+
"model.layers.17.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
|
| 113 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
|
| 114 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
|
| 115 |
+
"model.layers.17.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
|
| 116 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
|
| 117 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
|
| 118 |
+
"model.layers.18.input_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 119 |
+
"model.layers.18.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
|
| 120 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
|
| 121 |
+
"model.layers.18.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
|
| 122 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 123 |
+
"model.layers.18.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
|
| 124 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
|
| 125 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
|
| 126 |
+
"model.layers.18.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
|
| 127 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
|
| 128 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
|
| 129 |
+
"model.layers.19.input_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 130 |
+
"model.layers.19.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
|
| 131 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
|
| 132 |
+
"model.layers.19.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
|
| 133 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 134 |
+
"model.layers.19.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
|
| 135 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
|
| 136 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
|
| 137 |
+
"model.layers.19.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
|
| 138 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
|
| 139 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
|
| 140 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00014.safetensors",
|
| 141 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
|
| 142 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
|
| 143 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
|
| 144 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
|
| 145 |
+
"model.layers.2.self_attn.k_norm.weight": "model-00001-of-00014.safetensors",
|
| 146 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
|
| 147 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
|
| 148 |
+
"model.layers.2.self_attn.q_norm.weight": "model-00001-of-00014.safetensors",
|
| 149 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
|
| 150 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
|
| 151 |
+
"model.layers.20.input_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 152 |
+
"model.layers.20.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
|
| 153 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
|
| 154 |
+
"model.layers.20.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
|
| 155 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 156 |
+
"model.layers.20.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
|
| 157 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
|
| 158 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
|
| 159 |
+
"model.layers.20.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
|
| 160 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
|
| 161 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
|
| 162 |
+
"model.layers.21.input_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 163 |
+
"model.layers.21.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
|
| 164 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
|
| 165 |
+
"model.layers.21.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
|
| 166 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 167 |
+
"model.layers.21.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
|
| 168 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
|
| 169 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
|
| 170 |
+
"model.layers.21.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
|
| 171 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
|
| 172 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
|
| 173 |
+
"model.layers.22.input_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 174 |
+
"model.layers.22.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
|
| 175 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
|
| 176 |
+
"model.layers.22.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
|
| 177 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
|
| 178 |
+
"model.layers.22.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
|
| 179 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
|
| 180 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
|
| 181 |
+
"model.layers.22.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
|
| 182 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
|
| 183 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
|
| 184 |
+
"model.layers.23.input_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 185 |
+
"model.layers.23.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
|
| 186 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
|
| 187 |
+
"model.layers.23.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
|
| 188 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 189 |
+
"model.layers.23.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
|
| 190 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
|
| 191 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
|
| 192 |
+
"model.layers.23.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
|
| 193 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
|
| 194 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
|
| 195 |
+
"model.layers.24.input_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 196 |
+
"model.layers.24.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
|
| 197 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
|
| 198 |
+
"model.layers.24.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
|
| 199 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 200 |
+
"model.layers.24.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
|
| 201 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
|
| 202 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
|
| 203 |
+
"model.layers.24.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
|
| 204 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
|
| 205 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
|
| 206 |
+
"model.layers.25.input_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 207 |
+
"model.layers.25.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
|
| 208 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
|
| 209 |
+
"model.layers.25.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
|
| 210 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 211 |
+
"model.layers.25.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
|
| 212 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
|
| 213 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
|
| 214 |
+
"model.layers.25.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
|
| 215 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
|
| 216 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
|
| 217 |
+
"model.layers.26.input_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 218 |
+
"model.layers.26.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
|
| 219 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
|
| 220 |
+
"model.layers.26.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
|
| 221 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 222 |
+
"model.layers.26.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
|
| 223 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
|
| 224 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
|
| 225 |
+
"model.layers.26.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
|
| 226 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
|
| 227 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
|
| 228 |
+
"model.layers.27.input_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 229 |
+
"model.layers.27.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
|
| 230 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
|
| 231 |
+
"model.layers.27.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
|
| 232 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
|
| 233 |
+
"model.layers.27.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
|
| 234 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
|
| 235 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
|
| 236 |
+
"model.layers.27.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
|
| 237 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
|
| 238 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
|
| 239 |
+
"model.layers.28.input_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 240 |
+
"model.layers.28.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
|
| 241 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
|
| 242 |
+
"model.layers.28.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
|
| 243 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 244 |
+
"model.layers.28.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
|
| 245 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
|
| 246 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
|
| 247 |
+
"model.layers.28.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
|
| 248 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
|
| 249 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
|
| 250 |
+
"model.layers.29.input_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 251 |
+
"model.layers.29.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
|
| 252 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
|
| 253 |
+
"model.layers.29.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
|
| 254 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 255 |
+
"model.layers.29.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
|
| 256 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
|
| 257 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
|
| 258 |
+
"model.layers.29.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
|
| 259 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
|
| 260 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
|
| 261 |
+
"model.layers.3.input_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 262 |
+
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
|
| 263 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
|
| 264 |
+
"model.layers.3.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
|
| 265 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 266 |
+
"model.layers.3.self_attn.k_norm.weight": "model-00001-of-00014.safetensors",
|
| 267 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
|
| 268 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
|
| 269 |
+
"model.layers.3.self_attn.q_norm.weight": "model-00001-of-00014.safetensors",
|
| 270 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
|
| 271 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
|
| 272 |
+
"model.layers.30.input_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 273 |
+
"model.layers.30.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
|
| 274 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
|
| 275 |
+
"model.layers.30.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
|
| 276 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 277 |
+
"model.layers.30.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
|
| 278 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
|
| 279 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
|
| 280 |
+
"model.layers.30.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
|
| 281 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
|
| 282 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
|
| 283 |
+
"model.layers.31.input_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 284 |
+
"model.layers.31.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
|
| 285 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
|
| 286 |
+
"model.layers.31.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
|
| 287 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 288 |
+
"model.layers.31.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
|
| 289 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
|
| 290 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
|
| 291 |
+
"model.layers.31.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
|
| 292 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
|
| 293 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
|
| 294 |
+
"model.layers.32.input_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 295 |
+
"model.layers.32.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
|
| 296 |
+
"model.layers.32.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
|
| 297 |
+
"model.layers.32.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
|
| 298 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
|
| 299 |
+
"model.layers.32.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
|
| 300 |
+
"model.layers.32.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
|
| 301 |
+
"model.layers.32.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
|
| 302 |
+
"model.layers.32.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
|
| 303 |
+
"model.layers.32.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
|
| 304 |
+
"model.layers.32.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
|
| 305 |
+
"model.layers.33.input_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 306 |
+
"model.layers.33.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
|
| 307 |
+
"model.layers.33.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
|
| 308 |
+
"model.layers.33.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
|
| 309 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 310 |
+
"model.layers.33.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
|
| 311 |
+
"model.layers.33.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
|
| 312 |
+
"model.layers.33.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
|
| 313 |
+
"model.layers.33.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
|
| 314 |
+
"model.layers.33.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
|
| 315 |
+
"model.layers.33.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
|
| 316 |
+
"model.layers.34.input_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 317 |
+
"model.layers.34.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
|
| 318 |
+
"model.layers.34.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
|
| 319 |
+
"model.layers.34.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
|
| 320 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 321 |
+
"model.layers.34.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
|
| 322 |
+
"model.layers.34.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
|
| 323 |
+
"model.layers.34.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
|
| 324 |
+
"model.layers.34.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
|
| 325 |
+
"model.layers.34.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
|
| 326 |
+
"model.layers.34.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
|
| 327 |
+
"model.layers.35.input_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 328 |
+
"model.layers.35.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
|
| 329 |
+
"model.layers.35.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
|
| 330 |
+
"model.layers.35.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
|
| 331 |
+
"model.layers.35.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 332 |
+
"model.layers.35.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
|
| 333 |
+
"model.layers.35.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
|
| 334 |
+
"model.layers.35.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
|
| 335 |
+
"model.layers.35.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
|
| 336 |
+
"model.layers.35.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
|
| 337 |
+
"model.layers.35.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
|
| 338 |
+
"model.layers.36.input_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 339 |
+
"model.layers.36.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
|
| 340 |
+
"model.layers.36.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
|
| 341 |
+
"model.layers.36.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
|
| 342 |
+
"model.layers.36.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 343 |
+
"model.layers.36.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
|
| 344 |
+
"model.layers.36.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
|
| 345 |
+
"model.layers.36.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
|
| 346 |
+
"model.layers.36.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
|
| 347 |
+
"model.layers.36.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
|
| 348 |
+
"model.layers.36.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
|
| 349 |
+
"model.layers.37.input_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 350 |
+
"model.layers.37.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
|
| 351 |
+
"model.layers.37.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
|
| 352 |
+
"model.layers.37.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
|
| 353 |
+
"model.layers.37.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
|
| 354 |
+
"model.layers.37.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
|
| 355 |
+
"model.layers.37.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
|
| 356 |
+
"model.layers.37.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
|
| 357 |
+
"model.layers.37.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
|
| 358 |
+
"model.layers.37.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
|
| 359 |
+
"model.layers.37.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
|
| 360 |
+
"model.layers.38.input_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 361 |
+
"model.layers.38.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
|
| 362 |
+
"model.layers.38.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
|
| 363 |
+
"model.layers.38.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
|
| 364 |
+
"model.layers.38.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 365 |
+
"model.layers.38.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
|
| 366 |
+
"model.layers.38.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
|
| 367 |
+
"model.layers.38.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
|
| 368 |
+
"model.layers.38.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
|
| 369 |
+
"model.layers.38.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
|
| 370 |
+
"model.layers.38.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
|
| 371 |
+
"model.layers.39.input_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 372 |
+
"model.layers.39.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
|
| 373 |
+
"model.layers.39.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
|
| 374 |
+
"model.layers.39.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
|
| 375 |
+
"model.layers.39.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 376 |
+
"model.layers.39.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
|
| 377 |
+
"model.layers.39.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
|
| 378 |
+
"model.layers.39.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
|
| 379 |
+
"model.layers.39.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
|
| 380 |
+
"model.layers.39.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
|
| 381 |
+
"model.layers.39.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
|
| 382 |
+
"model.layers.4.input_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 383 |
+
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
|
| 384 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
|
| 385 |
+
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
|
| 386 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 387 |
+
"model.layers.4.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
|
| 388 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
|
| 389 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
|
| 390 |
+
"model.layers.4.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
|
| 391 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
|
| 392 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
|
| 393 |
+
"model.layers.40.input_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 394 |
+
"model.layers.40.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
|
| 395 |
+
"model.layers.40.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
|
| 396 |
+
"model.layers.40.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
|
| 397 |
+
"model.layers.40.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 398 |
+
"model.layers.40.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
|
| 399 |
+
"model.layers.40.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
|
| 400 |
+
"model.layers.40.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
|
| 401 |
+
"model.layers.40.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
|
| 402 |
+
"model.layers.40.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
|
| 403 |
+
"model.layers.40.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
|
| 404 |
+
"model.layers.41.input_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 405 |
+
"model.layers.41.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
|
| 406 |
+
"model.layers.41.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
|
| 407 |
+
"model.layers.41.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
|
| 408 |
+
"model.layers.41.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 409 |
+
"model.layers.41.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
|
| 410 |
+
"model.layers.41.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
|
| 411 |
+
"model.layers.41.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
|
| 412 |
+
"model.layers.41.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
|
| 413 |
+
"model.layers.41.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
|
| 414 |
+
"model.layers.41.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
|
| 415 |
+
"model.layers.42.input_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 416 |
+
"model.layers.42.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
|
| 417 |
+
"model.layers.42.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
|
| 418 |
+
"model.layers.42.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
|
| 419 |
+
"model.layers.42.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
|
| 420 |
+
"model.layers.42.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
|
| 421 |
+
"model.layers.42.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
|
| 422 |
+
"model.layers.42.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
|
| 423 |
+
"model.layers.42.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
|
| 424 |
+
"model.layers.42.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
|
| 425 |
+
"model.layers.42.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
|
| 426 |
+
"model.layers.43.input_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 427 |
+
"model.layers.43.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
|
| 428 |
+
"model.layers.43.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
|
| 429 |
+
"model.layers.43.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
|
| 430 |
+
"model.layers.43.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 431 |
+
"model.layers.43.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
|
| 432 |
+
"model.layers.43.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
|
| 433 |
+
"model.layers.43.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
|
| 434 |
+
"model.layers.43.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
|
| 435 |
+
"model.layers.43.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
|
| 436 |
+
"model.layers.43.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
|
| 437 |
+
"model.layers.44.input_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 438 |
+
"model.layers.44.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
|
| 439 |
+
"model.layers.44.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
|
| 440 |
+
"model.layers.44.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
|
| 441 |
+
"model.layers.44.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 442 |
+
"model.layers.44.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
|
| 443 |
+
"model.layers.44.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
|
| 444 |
+
"model.layers.44.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
|
| 445 |
+
"model.layers.44.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
|
| 446 |
+
"model.layers.44.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
|
| 447 |
+
"model.layers.44.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
|
| 448 |
+
"model.layers.45.input_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 449 |
+
"model.layers.45.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
|
| 450 |
+
"model.layers.45.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
|
| 451 |
+
"model.layers.45.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
|
| 452 |
+
"model.layers.45.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 453 |
+
"model.layers.45.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
|
| 454 |
+
"model.layers.45.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
|
| 455 |
+
"model.layers.45.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
|
| 456 |
+
"model.layers.45.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
|
| 457 |
+
"model.layers.45.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
|
| 458 |
+
"model.layers.45.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
|
| 459 |
+
"model.layers.46.input_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 460 |
+
"model.layers.46.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
|
| 461 |
+
"model.layers.46.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
|
| 462 |
+
"model.layers.46.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
|
| 463 |
+
"model.layers.46.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 464 |
+
"model.layers.46.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
|
| 465 |
+
"model.layers.46.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
|
| 466 |
+
"model.layers.46.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
|
| 467 |
+
"model.layers.46.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
|
| 468 |
+
"model.layers.46.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
|
| 469 |
+
"model.layers.46.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
|
| 470 |
+
"model.layers.47.input_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 471 |
+
"model.layers.47.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
|
| 472 |
+
"model.layers.47.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
|
| 473 |
+
"model.layers.47.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
|
| 474 |
+
"model.layers.47.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
|
| 475 |
+
"model.layers.47.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
|
| 476 |
+
"model.layers.47.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
|
| 477 |
+
"model.layers.47.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
|
| 478 |
+
"model.layers.47.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
|
| 479 |
+
"model.layers.47.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
|
| 480 |
+
"model.layers.47.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
|
| 481 |
+
"model.layers.48.input_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 482 |
+
"model.layers.48.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
|
| 483 |
+
"model.layers.48.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
|
| 484 |
+
"model.layers.48.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
|
| 485 |
+
"model.layers.48.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 486 |
+
"model.layers.48.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
|
| 487 |
+
"model.layers.48.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
|
| 488 |
+
"model.layers.48.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
|
| 489 |
+
"model.layers.48.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
|
| 490 |
+
"model.layers.48.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
|
| 491 |
+
"model.layers.48.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
|
| 492 |
+
"model.layers.49.input_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 493 |
+
"model.layers.49.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
|
| 494 |
+
"model.layers.49.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
|
| 495 |
+
"model.layers.49.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
|
| 496 |
+
"model.layers.49.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 497 |
+
"model.layers.49.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
|
| 498 |
+
"model.layers.49.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
|
| 499 |
+
"model.layers.49.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
|
| 500 |
+
"model.layers.49.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
|
| 501 |
+
"model.layers.49.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
|
| 502 |
+
"model.layers.49.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
|
| 503 |
+
"model.layers.5.input_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 504 |
+
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
|
| 505 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
|
| 506 |
+
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
|
| 507 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 508 |
+
"model.layers.5.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
|
| 509 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
|
| 510 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
|
| 511 |
+
"model.layers.5.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
|
| 512 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
|
| 513 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
|
| 514 |
+
"model.layers.50.input_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 515 |
+
"model.layers.50.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
|
| 516 |
+
"model.layers.50.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
|
| 517 |
+
"model.layers.50.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
|
| 518 |
+
"model.layers.50.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 519 |
+
"model.layers.50.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
|
| 520 |
+
"model.layers.50.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
|
| 521 |
+
"model.layers.50.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
|
| 522 |
+
"model.layers.50.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
|
| 523 |
+
"model.layers.50.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
|
| 524 |
+
"model.layers.50.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
|
| 525 |
+
"model.layers.51.input_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 526 |
+
"model.layers.51.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
|
| 527 |
+
"model.layers.51.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
|
| 528 |
+
"model.layers.51.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
|
| 529 |
+
"model.layers.51.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 530 |
+
"model.layers.51.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
|
| 531 |
+
"model.layers.51.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
|
| 532 |
+
"model.layers.51.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
|
| 533 |
+
"model.layers.51.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
|
| 534 |
+
"model.layers.51.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
|
| 535 |
+
"model.layers.51.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
|
| 536 |
+
"model.layers.52.input_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 537 |
+
"model.layers.52.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
|
| 538 |
+
"model.layers.52.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
|
| 539 |
+
"model.layers.52.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
|
| 540 |
+
"model.layers.52.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
|
| 541 |
+
"model.layers.52.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
|
| 542 |
+
"model.layers.52.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
|
| 543 |
+
"model.layers.52.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
|
| 544 |
+
"model.layers.52.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
|
| 545 |
+
"model.layers.52.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
|
| 546 |
+
"model.layers.52.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
|
| 547 |
+
"model.layers.53.input_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 548 |
+
"model.layers.53.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
|
| 549 |
+
"model.layers.53.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
|
| 550 |
+
"model.layers.53.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
|
| 551 |
+
"model.layers.53.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 552 |
+
"model.layers.53.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
|
| 553 |
+
"model.layers.53.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
|
| 554 |
+
"model.layers.53.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
|
| 555 |
+
"model.layers.53.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
|
| 556 |
+
"model.layers.53.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
|
| 557 |
+
"model.layers.53.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
|
| 558 |
+
"model.layers.54.input_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 559 |
+
"model.layers.54.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
|
| 560 |
+
"model.layers.54.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
|
| 561 |
+
"model.layers.54.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
|
| 562 |
+
"model.layers.54.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 563 |
+
"model.layers.54.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
|
| 564 |
+
"model.layers.54.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
|
| 565 |
+
"model.layers.54.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
|
| 566 |
+
"model.layers.54.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
|
| 567 |
+
"model.layers.54.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
|
| 568 |
+
"model.layers.54.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
|
| 569 |
+
"model.layers.55.input_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 570 |
+
"model.layers.55.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
|
| 571 |
+
"model.layers.55.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
|
| 572 |
+
"model.layers.55.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
|
| 573 |
+
"model.layers.55.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 574 |
+
"model.layers.55.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
|
| 575 |
+
"model.layers.55.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
|
| 576 |
+
"model.layers.55.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
|
| 577 |
+
"model.layers.55.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
|
| 578 |
+
"model.layers.55.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
|
| 579 |
+
"model.layers.55.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
|
| 580 |
+
"model.layers.56.input_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 581 |
+
"model.layers.56.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
|
| 582 |
+
"model.layers.56.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
|
| 583 |
+
"model.layers.56.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
|
| 584 |
+
"model.layers.56.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 585 |
+
"model.layers.56.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
|
| 586 |
+
"model.layers.56.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
|
| 587 |
+
"model.layers.56.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
|
| 588 |
+
"model.layers.56.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
|
| 589 |
+
"model.layers.56.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
|
| 590 |
+
"model.layers.56.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
|
| 591 |
+
"model.layers.57.input_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 592 |
+
"model.layers.57.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
|
| 593 |
+
"model.layers.57.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
|
| 594 |
+
"model.layers.57.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
|
| 595 |
+
"model.layers.57.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
|
| 596 |
+
"model.layers.57.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
|
| 597 |
+
"model.layers.57.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
|
| 598 |
+
"model.layers.57.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
|
| 599 |
+
"model.layers.57.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
|
| 600 |
+
"model.layers.57.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
|
| 601 |
+
"model.layers.57.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
|
| 602 |
+
"model.layers.58.input_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 603 |
+
"model.layers.58.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
|
| 604 |
+
"model.layers.58.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
|
| 605 |
+
"model.layers.58.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
|
| 606 |
+
"model.layers.58.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 607 |
+
"model.layers.58.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
|
| 608 |
+
"model.layers.58.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
|
| 609 |
+
"model.layers.58.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
|
| 610 |
+
"model.layers.58.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
|
| 611 |
+
"model.layers.58.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
|
| 612 |
+
"model.layers.58.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
|
| 613 |
+
"model.layers.59.input_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 614 |
+
"model.layers.59.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
|
| 615 |
+
"model.layers.59.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
|
| 616 |
+
"model.layers.59.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
|
| 617 |
+
"model.layers.59.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 618 |
+
"model.layers.59.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
|
| 619 |
+
"model.layers.59.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
|
| 620 |
+
"model.layers.59.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
|
| 621 |
+
"model.layers.59.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
|
| 622 |
+
"model.layers.59.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
|
| 623 |
+
"model.layers.59.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
|
| 624 |
+
"model.layers.6.input_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 625 |
+
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
|
| 626 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
|
| 627 |
+
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
|
| 628 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 629 |
+
"model.layers.6.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
|
| 630 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
|
| 631 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
|
| 632 |
+
"model.layers.6.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
|
| 633 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
|
| 634 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
|
| 635 |
+
"model.layers.60.input_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 636 |
+
"model.layers.60.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
|
| 637 |
+
"model.layers.60.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
|
| 638 |
+
"model.layers.60.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
|
| 639 |
+
"model.layers.60.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 640 |
+
"model.layers.60.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
|
| 641 |
+
"model.layers.60.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
|
| 642 |
+
"model.layers.60.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
|
| 643 |
+
"model.layers.60.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
|
| 644 |
+
"model.layers.60.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
|
| 645 |
+
"model.layers.60.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
|
| 646 |
+
"model.layers.61.input_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 647 |
+
"model.layers.61.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
|
| 648 |
+
"model.layers.61.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
|
| 649 |
+
"model.layers.61.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
|
| 650 |
+
"model.layers.61.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 651 |
+
"model.layers.61.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
|
| 652 |
+
"model.layers.61.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
|
| 653 |
+
"model.layers.61.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
|
| 654 |
+
"model.layers.61.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
|
| 655 |
+
"model.layers.61.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
|
| 656 |
+
"model.layers.61.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
|
| 657 |
+
"model.layers.62.input_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 658 |
+
"model.layers.62.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
|
| 659 |
+
"model.layers.62.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
|
| 660 |
+
"model.layers.62.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
|
| 661 |
+
"model.layers.62.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
|
| 662 |
+
"model.layers.62.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
|
| 663 |
+
"model.layers.62.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
|
| 664 |
+
"model.layers.62.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
|
| 665 |
+
"model.layers.62.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
|
| 666 |
+
"model.layers.62.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
|
| 667 |
+
"model.layers.62.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
|
| 668 |
+
"model.layers.63.input_layernorm.weight": "model-00014-of-00014.safetensors",
|
| 669 |
+
"model.layers.63.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
|
| 670 |
+
"model.layers.63.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
|
| 671 |
+
"model.layers.63.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
|
| 672 |
+
"model.layers.63.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
|
| 673 |
+
"model.layers.63.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
|
| 674 |
+
"model.layers.63.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
|
| 675 |
+
"model.layers.63.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
|
| 676 |
+
"model.layers.63.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
|
| 677 |
+
"model.layers.63.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
|
| 678 |
+
"model.layers.63.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
|
| 679 |
+
"model.layers.7.input_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 680 |
+
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
|
| 681 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
|
| 682 |
+
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
|
| 683 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
|
| 684 |
+
"model.layers.7.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
|
| 685 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
|
| 686 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
|
| 687 |
+
"model.layers.7.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
|
| 688 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
|
| 689 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
|
| 690 |
+
"model.layers.8.input_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 691 |
+
"model.layers.8.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
|
| 692 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
|
| 693 |
+
"model.layers.8.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
|
| 694 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 695 |
+
"model.layers.8.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
|
| 696 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
|
| 697 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
|
| 698 |
+
"model.layers.8.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
|
| 699 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
|
| 700 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
|
| 701 |
+
"model.layers.9.input_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 702 |
+
"model.layers.9.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
|
| 703 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
|
| 704 |
+
"model.layers.9.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
|
| 705 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
|
| 706 |
+
"model.layers.9.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
|
| 707 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
|
| 708 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
|
| 709 |
+
"model.layers.9.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
|
| 710 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
|
| 711 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
|
| 712 |
+
"model.norm.weight": "model-00014-of-00014.safetensors"
|
| 713 |
+
}
|
| 714 |
+
}
|
per_env_metrics.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"github": 1.7327340841293335
|
| 3 |
+
}
|
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": 131072,
|
| 235 |
+
"pad_token": "<|endoftext|>",
|
| 236 |
+
"padding_side": "right",
|
| 237 |
+
"split_special_tokens": false,
|
| 238 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 239 |
+
"unk_token": null
|
| 240 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 50.0,
|
| 3 |
+
"total_flos": 86960020979712.0,
|
| 4 |
+
"train_loss": 0.06868666498057012,
|
| 5 |
+
"train_runtime": 10021.0579,
|
| 6 |
+
"train_samples_per_second": 0.249,
|
| 7 |
+
"train_steps_per_second": 0.035
|
| 8 |
+
}
|
trainer_log.jsonl
ADDED
|
@@ -0,0 +1,142 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 0, "total_steps": 350, "eval_loss": 1.468239188194275, "epoch": 0, "percentage": 0.0, "elapsed_time": "0:00:18", "remaining_time": "0:00:00"}
|
| 2 |
+
{"current_steps": 5, "total_steps": 350, "loss": 1.3518, "lr": 4.444444444444444e-06, "epoch": 0.7142857142857143, "percentage": 1.43, "elapsed_time": "0:02:23", "remaining_time": "2:44:57"}
|
| 3 |
+
{"current_steps": 5, "total_steps": 350, "eval_loss": 1.3430589437484741, "epoch": 0.7142857142857143, "percentage": 1.43, "elapsed_time": "0:02:42", "remaining_time": "3:07:06"}
|
| 4 |
+
{"current_steps": 10, "total_steps": 350, "loss": 0.9051, "lr": 1e-05, "epoch": 1.4285714285714286, "percentage": 2.86, "elapsed_time": "0:04:55", "remaining_time": "2:47:30"}
|
| 5 |
+
{"current_steps": 10, "total_steps": 350, "eval_loss": 1.2059158086776733, "epoch": 1.4285714285714286, "percentage": 2.86, "elapsed_time": "0:05:16", "remaining_time": "2:59:19"}
|
| 6 |
+
{"current_steps": 15, "total_steps": 350, "loss": 0.8625, "lr": 1.555555555555556e-05, "epoch": 2.142857142857143, "percentage": 4.29, "elapsed_time": "0:07:07", "remaining_time": "2:39:10"}
|
| 7 |
+
{"current_steps": 15, "total_steps": 350, "eval_loss": 1.127707600593567, "epoch": 2.142857142857143, "percentage": 4.29, "elapsed_time": "0:07:28", "remaining_time": "2:46:45"}
|
| 8 |
+
{"current_steps": 20, "total_steps": 350, "loss": 0.6971, "lr": 1.9999552296652432e-05, "epoch": 2.857142857142857, "percentage": 5.71, "elapsed_time": "0:09:12", "remaining_time": "2:32:01"}
|
| 9 |
+
{"current_steps": 20, "total_steps": 350, "eval_loss": 1.114540696144104, "epoch": 2.857142857142857, "percentage": 5.71, "elapsed_time": "0:09:33", "remaining_time": "2:37:40"}
|
| 10 |
+
{"current_steps": 25, "total_steps": 350, "loss": 0.4243, "lr": 1.9983886888289515e-05, "epoch": 3.571428571428571, "percentage": 7.14, "elapsed_time": "0:11:41", "remaining_time": "2:32:04"}
|
| 11 |
+
{"current_steps": 25, "total_steps": 350, "eval_loss": 1.1612136363983154, "epoch": 3.571428571428571, "percentage": 7.14, "elapsed_time": "0:12:02", "remaining_time": "2:36:35"}
|
| 12 |
+
{"current_steps": 30, "total_steps": 350, "loss": 0.1901, "lr": 1.994587638407389e-05, "epoch": 4.285714285714286, "percentage": 8.57, "elapsed_time": "0:14:07", "remaining_time": "2:30:35"}
|
| 13 |
+
{"current_steps": 30, "total_steps": 350, "eval_loss": 1.3399298191070557, "epoch": 4.285714285714286, "percentage": 8.57, "elapsed_time": "0:14:27", "remaining_time": "2:34:12"}
|
| 14 |
+
{"current_steps": 35, "total_steps": 350, "loss": 0.1171, "lr": 1.9885605855918887e-05, "epoch": 5.0, "percentage": 10.0, "elapsed_time": "0:16:04", "remaining_time": "2:24:36"}
|
| 15 |
+
{"current_steps": 35, "total_steps": 350, "eval_loss": 1.3959039449691772, "epoch": 5.0, "percentage": 10.0, "elapsed_time": "0:16:24", "remaining_time": "2:27:41"}
|
| 16 |
+
{"current_steps": 40, "total_steps": 350, "loss": 0.0593, "lr": 1.9803210196251057e-05, "epoch": 5.714285714285714, "percentage": 11.43, "elapsed_time": "0:18:19", "remaining_time": "2:22:03"}
|
| 17 |
+
{"current_steps": 40, "total_steps": 350, "eval_loss": 1.4992326498031616, "epoch": 5.714285714285714, "percentage": 11.43, "elapsed_time": "0:18:40", "remaining_time": "2:24:47"}
|
| 18 |
+
{"current_steps": 45, "total_steps": 350, "loss": 0.0265, "lr": 1.9698873816105272e-05, "epoch": 6.428571428571429, "percentage": 12.86, "elapsed_time": "0:20:48", "remaining_time": "2:21:04"}
|
| 19 |
+
{"current_steps": 45, "total_steps": 350, "eval_loss": 1.5966981649398804, "epoch": 6.428571428571429, "percentage": 12.86, "elapsed_time": "0:21:09", "remaining_time": "2:23:24"}
|
| 20 |
+
{"current_steps": 50, "total_steps": 350, "loss": 0.0229, "lr": 1.9572830232391467e-05, "epoch": 7.142857142857143, "percentage": 14.29, "elapsed_time": "0:23:18", "remaining_time": "2:19:49"}
|
| 21 |
+
{"current_steps": 50, "total_steps": 350, "eval_loss": 1.6269463300704956, "epoch": 7.142857142857143, "percentage": 14.29, "elapsed_time": "0:23:39", "remaining_time": "2:21:56"}
|
| 22 |
+
{"current_steps": 55, "total_steps": 350, "loss": 0.0167, "lr": 1.942536154525673e-05, "epoch": 7.857142857142857, "percentage": 15.71, "elapsed_time": "0:25:09", "remaining_time": "2:14:54"}
|
| 23 |
+
{"current_steps": 55, "total_steps": 350, "eval_loss": 1.6504554748535156, "epoch": 7.857142857142857, "percentage": 15.71, "elapsed_time": "0:25:30", "remaining_time": "2:16:46"}
|
| 24 |
+
{"current_steps": 60, "total_steps": 350, "loss": 0.0119, "lr": 1.9256797806712478e-05, "epoch": 8.571428571428571, "percentage": 17.14, "elapsed_time": "0:27:31", "remaining_time": "2:13:00"}
|
| 25 |
+
{"current_steps": 60, "total_steps": 350, "eval_loss": 1.6625537872314453, "epoch": 8.571428571428571, "percentage": 17.14, "elapsed_time": "0:27:52", "remaining_time": "2:14:41"}
|
| 26 |
+
{"current_steps": 65, "total_steps": 350, "loss": 0.0094, "lr": 1.9067516281939826e-05, "epoch": 9.285714285714286, "percentage": 18.57, "elapsed_time": "0:30:04", "remaining_time": "2:11:50"}
|
| 27 |
+
{"current_steps": 65, "total_steps": 350, "eval_loss": 1.6874204874038696, "epoch": 9.285714285714286, "percentage": 18.57, "elapsed_time": "0:30:25", "remaining_time": "2:13:24"}
|
| 28 |
+
{"current_steps": 70, "total_steps": 350, "loss": 0.0089, "lr": 1.885794060492637e-05, "epoch": 10.0, "percentage": 20.0, "elapsed_time": "0:32:03", "remaining_time": "2:08:15"}
|
| 29 |
+
{"current_steps": 70, "total_steps": 350, "eval_loss": 1.7034786939620972, "epoch": 10.0, "percentage": 20.0, "elapsed_time": "0:32:25", "remaining_time": "2:09:42"}
|
| 30 |
+
{"current_steps": 75, "total_steps": 350, "loss": 0.0062, "lr": 1.862853983032423e-05, "epoch": 10.714285714285714, "percentage": 21.43, "elapsed_time": "0:34:23", "remaining_time": "2:06:05"}
|
| 31 |
+
{"current_steps": 75, "total_steps": 350, "eval_loss": 1.7052545547485352, "epoch": 10.714285714285714, "percentage": 21.43, "elapsed_time": "0:34:44", "remaining_time": "2:07:22"}
|
| 32 |
+
{"current_steps": 80, "total_steps": 350, "loss": 0.0072, "lr": 1.83798273836514e-05, "epoch": 11.428571428571429, "percentage": 22.86, "elapsed_time": "0:36:46", "remaining_time": "2:04:05"}
|
| 33 |
+
{"current_steps": 80, "total_steps": 350, "eval_loss": 1.7082165479660034, "epoch": 11.428571428571429, "percentage": 22.86, "elapsed_time": "0:37:07", "remaining_time": "2:05:19"}
|
| 34 |
+
{"current_steps": 85, "total_steps": 350, "loss": 0.008, "lr": 1.8112359912185923e-05, "epoch": 12.142857142857142, "percentage": 24.29, "elapsed_time": "0:39:17", "remaining_time": "2:02:28"}
|
| 35 |
+
{"current_steps": 85, "total_steps": 350, "eval_loss": 1.6972074508666992, "epoch": 12.142857142857142, "percentage": 24.29, "elapsed_time": "0:39:38", "remaining_time": "2:03:35"}
|
| 36 |
+
{"current_steps": 90, "total_steps": 350, "loss": 0.006, "lr": 1.7826736039124782e-05, "epoch": 12.857142857142858, "percentage": 25.71, "elapsed_time": "0:41:27", "remaining_time": "1:59:47"}
|
| 37 |
+
{"current_steps": 90, "total_steps": 350, "eval_loss": 1.6968964338302612, "epoch": 12.857142857142858, "percentage": 25.71, "elapsed_time": "0:41:49", "remaining_time": "2:00:48"}
|
| 38 |
+
{"current_steps": 95, "total_steps": 350, "loss": 0.0044, "lr": 1.7523595023795814e-05, "epoch": 13.571428571428571, "percentage": 27.14, "elapsed_time": "0:44:02", "remaining_time": "1:58:12"}
|
| 39 |
+
{"current_steps": 95, "total_steps": 350, "eval_loss": 1.7048730850219727, "epoch": 13.571428571428571, "percentage": 27.14, "elapsed_time": "0:44:24", "remaining_time": "1:59:11"}
|
| 40 |
+
{"current_steps": 100, "total_steps": 350, "loss": 0.0036, "lr": 1.720361533092124e-05, "epoch": 14.285714285714286, "percentage": 28.57, "elapsed_time": "0:46:07", "remaining_time": "1:55:19"}
|
| 41 |
+
{"current_steps": 100, "total_steps": 350, "eval_loss": 1.7229158878326416, "epoch": 14.285714285714286, "percentage": 28.57, "elapsed_time": "0:46:29", "remaining_time": "1:56:12"}
|
| 42 |
+
{"current_steps": 105, "total_steps": 350, "loss": 0.0035, "lr": 1.6867513112135012e-05, "epoch": 15.0, "percentage": 30.0, "elapsed_time": "0:48:22", "remaining_time": "1:52:53"}
|
| 43 |
+
{"current_steps": 105, "total_steps": 350, "eval_loss": 1.7421244382858276, "epoch": 15.0, "percentage": 30.0, "elapsed_time": "0:48:44", "remaining_time": "1:53:43"}
|
| 44 |
+
{"current_steps": 110, "total_steps": 350, "loss": 0.0026, "lr": 1.6516040603152448e-05, "epoch": 15.714285714285714, "percentage": 31.43, "elapsed_time": "0:50:43", "remaining_time": "1:50:41"}
|
| 45 |
+
{"current_steps": 110, "total_steps": 350, "eval_loss": 1.7549571990966797, "epoch": 15.714285714285714, "percentage": 31.43, "elapsed_time": "0:51:05", "remaining_time": "1:51:28"}
|
| 46 |
+
{"current_steps": 115, "total_steps": 350, "loss": 0.0023, "lr": 1.614998444017954e-05, "epoch": 16.428571428571427, "percentage": 32.86, "elapsed_time": "0:53:17", "remaining_time": "1:48:54"}
|
| 47 |
+
{"current_steps": 115, "total_steps": 350, "eval_loss": 1.7617460489273071, "epoch": 16.428571428571427, "percentage": 32.86, "elapsed_time": "0:53:39", "remaining_time": "1:49:38"}
|
| 48 |
+
{"current_steps": 120, "total_steps": 350, "loss": 0.0021, "lr": 1.5770163899329943e-05, "epoch": 17.142857142857142, "percentage": 34.29, "elapsed_time": "0:55:29", "remaining_time": "1:46:20"}
|
| 49 |
+
{"current_steps": 120, "total_steps": 350, "eval_loss": 1.7655525207519531, "epoch": 17.142857142857142, "percentage": 34.29, "elapsed_time": "0:55:51", "remaining_time": "1:47:02"}
|
| 50 |
+
{"current_steps": 125, "total_steps": 350, "loss": 0.0025, "lr": 1.5377429062990122e-05, "epoch": 17.857142857142858, "percentage": 35.71, "elapsed_time": "0:57:29", "remaining_time": "1:43:29"}
|
| 51 |
+
{"current_steps": 125, "total_steps": 350, "eval_loss": 1.768291711807251, "epoch": 17.857142857142858, "percentage": 35.71, "elapsed_time": "0:57:51", "remaining_time": "1:44:08"}
|
| 52 |
+
{"current_steps": 130, "total_steps": 350, "loss": 0.0018, "lr": 1.497265891723643e-05, "epoch": 18.571428571428573, "percentage": 37.14, "elapsed_time": "0:59:51", "remaining_time": "1:41:17"}
|
| 53 |
+
{"current_steps": 130, "total_steps": 350, "eval_loss": 1.7749742269515991, "epoch": 18.571428571428573, "percentage": 37.14, "elapsed_time": "1:00:13", "remaining_time": "1:41:54"}
|
| 54 |
+
{"current_steps": 135, "total_steps": 350, "loss": 0.002, "lr": 1.4556759384562418e-05, "epoch": 19.285714285714285, "percentage": 38.57, "elapsed_time": "1:02:09", "remaining_time": "1:38:59"}
|
| 55 |
+
{"current_steps": 135, "total_steps": 350, "eval_loss": 1.7667394876480103, "epoch": 19.285714285714285, "percentage": 38.57, "elapsed_time": "1:02:31", "remaining_time": "1:39:35"}
|
| 56 |
+
{"current_steps": 140, "total_steps": 350, "loss": 0.0036, "lr": 1.4130661296319313e-05, "epoch": 20.0, "percentage": 40.0, "elapsed_time": "1:04:19", "remaining_time": "1:36:29"}
|
| 57 |
+
{"current_steps": 140, "total_steps": 350, "eval_loss": 1.7492411136627197, "epoch": 20.0, "percentage": 40.0, "elapsed_time": "1:04:41", "remaining_time": "1:37:02"}
|
| 58 |
+
{"current_steps": 145, "total_steps": 350, "loss": 0.0025, "lr": 1.369531830940757e-05, "epoch": 20.714285714285715, "percentage": 41.43, "elapsed_time": "1:06:42", "remaining_time": "1:34:18"}
|
| 59 |
+
{"current_steps": 145, "total_steps": 350, "eval_loss": 1.7377521991729736, "epoch": 20.714285714285715, "percentage": 41.43, "elapsed_time": "1:07:04", "remaining_time": "1:34:49"}
|
| 60 |
+
{"current_steps": 150, "total_steps": 350, "loss": 0.0017, "lr": 1.325170477188224e-05, "epoch": 21.428571428571427, "percentage": 42.86, "elapsed_time": "1:09:03", "remaining_time": "1:32:04"}
|
| 61 |
+
{"current_steps": 150, "total_steps": 350, "eval_loss": 1.7388665676116943, "epoch": 21.428571428571427, "percentage": 42.86, "elapsed_time": "1:09:25", "remaining_time": "1:32:34"}
|
| 62 |
+
{"current_steps": 155, "total_steps": 350, "loss": 0.0016, "lr": 1.2800813542249073e-05, "epoch": 22.142857142857142, "percentage": 44.29, "elapsed_time": "1:11:31", "remaining_time": "1:29:58"}
|
| 63 |
+
{"current_steps": 155, "total_steps": 350, "eval_loss": 1.7510356903076172, "epoch": 22.142857142857142, "percentage": 44.29, "elapsed_time": "1:11:53", "remaining_time": "1:30:26"}
|
| 64 |
+
{"current_steps": 160, "total_steps": 350, "loss": 0.0016, "lr": 1.234365376733215e-05, "epoch": 22.857142857142858, "percentage": 45.71, "elapsed_time": "1:13:33", "remaining_time": "1:27:21"}
|
| 65 |
+
{"current_steps": 160, "total_steps": 350, "eval_loss": 1.7622946500778198, "epoch": 22.857142857142858, "percentage": 45.71, "elapsed_time": "1:13:55", "remaining_time": "1:27:47"}
|
| 66 |
+
{"current_steps": 165, "total_steps": 350, "loss": 0.0014, "lr": 1.188124862368634e-05, "epoch": 23.571428571428573, "percentage": 47.14, "elapsed_time": "1:15:56", "remaining_time": "1:25:08"}
|
| 67 |
+
{"current_steps": 165, "total_steps": 350, "eval_loss": 1.770511507987976, "epoch": 23.571428571428573, "percentage": 47.14, "elapsed_time": "1:16:18", "remaining_time": "1:25:33"}
|
| 68 |
+
{"current_steps": 170, "total_steps": 350, "loss": 0.0013, "lr": 1.1414633027609585e-05, "epoch": 24.285714285714285, "percentage": 48.57, "elapsed_time": "1:18:49", "remaining_time": "1:23:27"}
|
| 69 |
+
{"current_steps": 170, "total_steps": 350, "eval_loss": 1.7750704288482666, "epoch": 24.285714285714285, "percentage": 48.57, "elapsed_time": "1:19:11", "remaining_time": "1:23:50"}
|
| 70 |
+
{"current_steps": 175, "total_steps": 350, "loss": 0.0015, "lr": 1.0944851318880314e-05, "epoch": 25.0, "percentage": 50.0, "elapsed_time": "1:20:56", "remaining_time": "1:20:56"}
|
| 71 |
+
{"current_steps": 175, "total_steps": 350, "eval_loss": 1.7801543474197388, "epoch": 25.0, "percentage": 50.0, "elapsed_time": "1:21:18", "remaining_time": "1:21:18"}
|
| 72 |
+
{"current_steps": 180, "total_steps": 350, "loss": 0.0011, "lr": 1.047295492340397e-05, "epoch": 25.714285714285715, "percentage": 51.43, "elapsed_time": "1:23:20", "remaining_time": "1:18:42"}
|
| 73 |
+
{"current_steps": 180, "total_steps": 350, "eval_loss": 1.7830265760421753, "epoch": 25.714285714285715, "percentage": 51.43, "elapsed_time": "1:23:42", "remaining_time": "1:19:03"}
|
| 74 |
+
{"current_steps": 185, "total_steps": 350, "loss": 0.0012, "lr": 1e-05, "epoch": 26.428571428571427, "percentage": 52.86, "elapsed_time": "1:25:36", "remaining_time": "1:16:20"}
|
| 75 |
+
{"current_steps": 185, "total_steps": 350, "eval_loss": 1.7872556447982788, "epoch": 26.428571428571427, "percentage": 52.86, "elapsed_time": "1:25:58", "remaining_time": "1:16:40"}
|
| 76 |
+
{"current_steps": 190, "total_steps": 350, "loss": 0.0011, "lr": 9.527045076596036e-06, "epoch": 27.142857142857142, "percentage": 54.29, "elapsed_time": "1:28:07", "remaining_time": "1:14:12"}
|
| 77 |
+
{"current_steps": 190, "total_steps": 350, "eval_loss": 1.7918928861618042, "epoch": 27.142857142857142, "percentage": 54.29, "elapsed_time": "1:28:29", "remaining_time": "1:14:31"}
|
| 78 |
+
{"current_steps": 195, "total_steps": 350, "loss": 0.0012, "lr": 9.055148681119688e-06, "epoch": 27.857142857142858, "percentage": 55.71, "elapsed_time": "1:30:05", "remaining_time": "1:11:36"}
|
| 79 |
+
{"current_steps": 195, "total_steps": 350, "eval_loss": 1.7959425449371338, "epoch": 27.857142857142858, "percentage": 55.71, "elapsed_time": "1:30:27", "remaining_time": "1:11:54"}
|
| 80 |
+
{"current_steps": 200, "total_steps": 350, "loss": 0.0012, "lr": 8.585366972390416e-06, "epoch": 28.571428571428573, "percentage": 57.14, "elapsed_time": "1:32:47", "remaining_time": "1:09:35"}
|
| 81 |
+
{"current_steps": 200, "total_steps": 350, "eval_loss": 1.7992604970932007, "epoch": 28.571428571428573, "percentage": 57.14, "elapsed_time": "1:33:09", "remaining_time": "1:09:51"}
|
| 82 |
+
{"current_steps": 205, "total_steps": 350, "loss": 0.001, "lr": 8.118751376313666e-06, "epoch": 29.285714285714285, "percentage": 58.57, "elapsed_time": "1:35:27", "remaining_time": "1:07:30"}
|
| 83 |
+
{"current_steps": 205, "total_steps": 350, "eval_loss": 1.801768183708191, "epoch": 29.285714285714285, "percentage": 58.57, "elapsed_time": "1:35:48", "remaining_time": "1:07:46"}
|
| 84 |
+
{"current_steps": 210, "total_steps": 350, "loss": 0.0012, "lr": 7.65634623266785e-06, "epoch": 30.0, "percentage": 60.0, "elapsed_time": "1:37:30", "remaining_time": "1:05:00"}
|
| 85 |
+
{"current_steps": 210, "total_steps": 350, "eval_loss": 1.8040063381195068, "epoch": 30.0, "percentage": 60.0, "elapsed_time": "1:37:52", "remaining_time": "1:05:15"}
|
| 86 |
+
{"current_steps": 215, "total_steps": 350, "loss": 0.001, "lr": 7.199186457750931e-06, "epoch": 30.714285714285715, "percentage": 61.43, "elapsed_time": "1:39:45", "remaining_time": "1:02:38"}
|
| 87 |
+
{"current_steps": 215, "total_steps": 350, "eval_loss": 1.807271957397461, "epoch": 30.714285714285715, "percentage": 61.43, "elapsed_time": "1:40:07", "remaining_time": "1:02:52"}
|
| 88 |
+
{"current_steps": 220, "total_steps": 350, "loss": 0.001, "lr": 6.748295228117765e-06, "epoch": 31.428571428571427, "percentage": 62.86, "elapsed_time": "1:42:19", "remaining_time": "1:00:27"}
|
| 89 |
+
{"current_steps": 220, "total_steps": 350, "eval_loss": 1.8091932535171509, "epoch": 31.428571428571427, "percentage": 62.86, "elapsed_time": "1:42:41", "remaining_time": "1:00:40"}
|
| 90 |
+
{"current_steps": 225, "total_steps": 350, "loss": 0.0014, "lr": 6.304681690592431e-06, "epoch": 32.142857142857146, "percentage": 64.29, "elapsed_time": "1:44:37", "remaining_time": "0:58:07"}
|
| 91 |
+
{"current_steps": 225, "total_steps": 350, "eval_loss": 1.8116446733474731, "epoch": 32.142857142857146, "percentage": 64.29, "elapsed_time": "1:44:59", "remaining_time": "0:58:19"}
|
| 92 |
+
{"current_steps": 230, "total_steps": 350, "loss": 0.0011, "lr": 5.869338703680691e-06, "epoch": 32.857142857142854, "percentage": 65.71, "elapsed_time": "1:46:42", "remaining_time": "0:55:40"}
|
| 93 |
+
{"current_steps": 230, "total_steps": 350, "eval_loss": 1.8134872913360596, "epoch": 32.857142857142854, "percentage": 65.71, "elapsed_time": "1:47:04", "remaining_time": "0:55:51"}
|
| 94 |
+
{"current_steps": 235, "total_steps": 350, "loss": 0.001, "lr": 5.443240615437586e-06, "epoch": 33.57142857142857, "percentage": 67.14, "elapsed_time": "1:49:15", "remaining_time": "0:53:27"}
|
| 95 |
+
{"current_steps": 235, "total_steps": 350, "eval_loss": 1.814117670059204, "epoch": 33.57142857142857, "percentage": 67.14, "elapsed_time": "1:49:37", "remaining_time": "0:53:38"}
|
| 96 |
+
{"current_steps": 240, "total_steps": 350, "loss": 0.0011, "lr": 5.027341082763575e-06, "epoch": 34.285714285714285, "percentage": 68.57, "elapsed_time": "1:51:34", "remaining_time": "0:51:08"}
|
| 97 |
+
{"current_steps": 240, "total_steps": 350, "eval_loss": 1.8167412281036377, "epoch": 34.285714285714285, "percentage": 68.57, "elapsed_time": "1:51:56", "remaining_time": "0:51:18"}
|
| 98 |
+
{"current_steps": 245, "total_steps": 350, "loss": 0.0009, "lr": 4.622570937009879e-06, "epoch": 35.0, "percentage": 70.0, "elapsed_time": "1:53:47", "remaining_time": "0:48:46"}
|
| 99 |
+
{"current_steps": 245, "total_steps": 350, "eval_loss": 1.8182238340377808, "epoch": 35.0, "percentage": 70.0, "elapsed_time": "1:54:10", "remaining_time": "0:48:55"}
|
| 100 |
+
{"current_steps": 250, "total_steps": 350, "loss": 0.001, "lr": 4.229836100670058e-06, "epoch": 35.714285714285715, "percentage": 71.43, "elapsed_time": "1:55:50", "remaining_time": "0:46:20"}
|
| 101 |
+
{"current_steps": 250, "total_steps": 350, "eval_loss": 1.8190386295318604, "epoch": 35.714285714285715, "percentage": 71.43, "elapsed_time": "1:56:12", "remaining_time": "0:46:29"}
|
| 102 |
+
{"current_steps": 255, "total_steps": 350, "loss": 0.0011, "lr": 3.850015559820465e-06, "epoch": 36.42857142857143, "percentage": 72.86, "elapsed_time": "1:58:30", "remaining_time": "0:44:09"}
|
| 103 |
+
{"current_steps": 255, "total_steps": 350, "eval_loss": 1.8204212188720703, "epoch": 36.42857142857143, "percentage": 72.86, "elapsed_time": "1:58:52", "remaining_time": "0:44:17"}
|
| 104 |
+
{"current_steps": 260, "total_steps": 350, "loss": 0.0012, "lr": 3.483959396847554e-06, "epoch": 37.142857142857146, "percentage": 74.29, "elapsed_time": "2:00:59", "remaining_time": "0:41:52"}
|
| 105 |
+
{"current_steps": 260, "total_steps": 350, "eval_loss": 1.821565866470337, "epoch": 37.142857142857146, "percentage": 74.29, "elapsed_time": "2:01:21", "remaining_time": "0:42:00"}
|
| 106 |
+
{"current_steps": 265, "total_steps": 350, "loss": 0.0009, "lr": 3.132486887864992e-06, "epoch": 37.857142857142854, "percentage": 75.71, "elapsed_time": "2:03:02", "remaining_time": "0:39:27"}
|
| 107 |
+
{"current_steps": 265, "total_steps": 350, "eval_loss": 1.8220727443695068, "epoch": 37.857142857142854, "percentage": 75.71, "elapsed_time": "2:03:24", "remaining_time": "0:39:34"}
|
| 108 |
+
{"current_steps": 270, "total_steps": 350, "loss": 0.001, "lr": 2.7963846690787633e-06, "epoch": 38.57142857142857, "percentage": 77.14, "elapsed_time": "2:05:40", "remaining_time": "0:37:14"}
|
| 109 |
+
{"current_steps": 270, "total_steps": 350, "eval_loss": 1.822296380996704, "epoch": 38.57142857142857, "percentage": 77.14, "elapsed_time": "2:06:02", "remaining_time": "0:37:20"}
|
| 110 |
+
{"current_steps": 275, "total_steps": 350, "loss": 0.0013, "lr": 2.4764049762041874e-06, "epoch": 39.285714285714285, "percentage": 78.57, "elapsed_time": "2:08:10", "remaining_time": "0:34:57"}
|
| 111 |
+
{"current_steps": 275, "total_steps": 350, "eval_loss": 1.8238246440887451, "epoch": 39.285714285714285, "percentage": 78.57, "elapsed_time": "2:08:32", "remaining_time": "0:35:03"}
|
| 112 |
+
{"current_steps": 280, "total_steps": 350, "loss": 0.0011, "lr": 2.1732639608752173e-06, "epoch": 40.0, "percentage": 80.0, "elapsed_time": "2:10:23", "remaining_time": "0:32:35"}
|
| 113 |
+
{"current_steps": 280, "total_steps": 350, "eval_loss": 1.824698567390442, "epoch": 40.0, "percentage": 80.0, "elapsed_time": "2:10:46", "remaining_time": "0:32:41"}
|
| 114 |
+
{"current_steps": 285, "total_steps": 350, "loss": 0.0009, "lr": 1.8876400878140776e-06, "epoch": 40.714285714285715, "percentage": 81.43, "elapsed_time": "2:12:47", "remaining_time": "0:30:17"}
|
| 115 |
+
{"current_steps": 285, "total_steps": 350, "eval_loss": 1.8251045942306519, "epoch": 40.714285714285715, "percentage": 81.43, "elapsed_time": "2:13:09", "remaining_time": "0:30:22"}
|
| 116 |
+
{"current_steps": 290, "total_steps": 350, "loss": 0.0011, "lr": 1.6201726163485997e-06, "epoch": 41.42857142857143, "percentage": 82.86, "elapsed_time": "2:15:21", "remaining_time": "0:28:00"}
|
| 117 |
+
{"current_steps": 290, "total_steps": 350, "eval_loss": 1.8252718448638916, "epoch": 41.42857142857143, "percentage": 82.86, "elapsed_time": "2:15:43", "remaining_time": "0:28:04"}
|
| 118 |
+
{"current_steps": 295, "total_steps": 350, "loss": 0.001, "lr": 1.3714601696757713e-06, "epoch": 42.142857142857146, "percentage": 84.29, "elapsed_time": "2:17:49", "remaining_time": "0:25:41"}
|
| 119 |
+
{"current_steps": 295, "total_steps": 350, "eval_loss": 1.826216459274292, "epoch": 42.142857142857146, "percentage": 84.29, "elapsed_time": "2:18:11", "remaining_time": "0:25:45"}
|
| 120 |
+
{"current_steps": 300, "total_steps": 350, "loss": 0.001, "lr": 1.1420593950736326e-06, "epoch": 42.857142857142854, "percentage": 85.71, "elapsed_time": "2:19:53", "remaining_time": "0:23:18"}
|
| 121 |
+
{"current_steps": 300, "total_steps": 350, "eval_loss": 1.8267167806625366, "epoch": 42.857142857142854, "percentage": 85.71, "elapsed_time": "2:20:15", "remaining_time": "0:23:22"}
|
| 122 |
+
{"current_steps": 305, "total_steps": 350, "loss": 0.0011, "lr": 9.324837180601743e-07, "epoch": 43.57142857142857, "percentage": 87.14, "elapsed_time": "2:22:27", "remaining_time": "0:21:01"}
|
| 123 |
+
{"current_steps": 305, "total_steps": 350, "eval_loss": 1.8267269134521484, "epoch": 43.57142857142857, "percentage": 87.14, "elapsed_time": "2:22:49", "remaining_time": "0:21:04"}
|
| 124 |
+
{"current_steps": 310, "total_steps": 350, "loss": 0.0012, "lr": 7.432021932875222e-07, "epoch": 44.285714285714285, "percentage": 88.57, "elapsed_time": "2:25:13", "remaining_time": "0:18:44"}
|
| 125 |
+
{"current_steps": 310, "total_steps": 350, "eval_loss": 1.8272424936294556, "epoch": 44.285714285714285, "percentage": 88.57, "elapsed_time": "2:25:35", "remaining_time": "0:18:47"}
|
| 126 |
+
{"current_steps": 315, "total_steps": 350, "loss": 0.0009, "lr": 5.746384547432738e-07, "epoch": 45.0, "percentage": 90.0, "elapsed_time": "2:27:34", "remaining_time": "0:16:23"}
|
| 127 |
+
{"current_steps": 315, "total_steps": 350, "eval_loss": 1.8278112411499023, "epoch": 45.0, "percentage": 90.0, "elapsed_time": "2:27:56", "remaining_time": "0:16:26"}
|
| 128 |
+
{"current_steps": 320, "total_steps": 350, "loss": 0.0008, "lr": 4.2716976760853513e-07, "epoch": 45.714285714285715, "percentage": 91.43, "elapsed_time": "2:29:58", "remaining_time": "0:14:03"}
|
| 129 |
+
{"current_steps": 320, "total_steps": 350, "eval_loss": 1.8275575637817383, "epoch": 45.714285714285715, "percentage": 91.43, "elapsed_time": "2:30:20", "remaining_time": "0:14:05"}
|
| 130 |
+
{"current_steps": 325, "total_steps": 350, "loss": 0.0009, "lr": 3.011261838947277e-07, "epoch": 46.42857142857143, "percentage": 92.86, "elapsed_time": "2:32:46", "remaining_time": "0:11:45"}
|
| 131 |
+
{"current_steps": 325, "total_steps": 350, "eval_loss": 1.8281974792480469, "epoch": 46.42857142857143, "percentage": 92.86, "elapsed_time": "2:33:08", "remaining_time": "0:11:46"}
|
| 132 |
+
{"current_steps": 330, "total_steps": 350, "loss": 0.001, "lr": 1.9678980374894352e-07, "epoch": 47.142857142857146, "percentage": 94.29, "elapsed_time": "2:35:14", "remaining_time": "0:09:24"}
|
| 133 |
+
{"current_steps": 330, "total_steps": 350, "eval_loss": 1.8281824588775635, "epoch": 47.142857142857146, "percentage": 94.29, "elapsed_time": "2:35:36", "remaining_time": "0:09:25"}
|
| 134 |
+
{"current_steps": 335, "total_steps": 350, "loss": 0.001, "lr": 1.1439414408111471e-07, "epoch": 47.857142857142854, "percentage": 95.71, "elapsed_time": "2:37:13", "remaining_time": "0:07:02"}
|
| 135 |
+
{"current_steps": 335, "total_steps": 350, "eval_loss": 1.827906847000122, "epoch": 47.857142857142854, "percentage": 95.71, "elapsed_time": "2:37:35", "remaining_time": "0:07:03"}
|
| 136 |
+
{"current_steps": 340, "total_steps": 350, "loss": 0.0008, "lr": 5.412361592611382e-08, "epoch": 48.57142857142857, "percentage": 97.14, "elapsed_time": "2:39:50", "remaining_time": "0:04:42"}
|
| 137 |
+
{"current_steps": 340, "total_steps": 350, "eval_loss": 1.828213095664978, "epoch": 48.57142857142857, "percentage": 97.14, "elapsed_time": "2:40:12", "remaining_time": "0:04:42"}
|
| 138 |
+
{"current_steps": 345, "total_steps": 350, "loss": 0.0012, "lr": 1.611311171048735e-08, "epoch": 49.285714285714285, "percentage": 98.57, "elapsed_time": "2:42:25", "remaining_time": "0:02:21"}
|
| 139 |
+
{"current_steps": 345, "total_steps": 350, "eval_loss": 1.8280681371688843, "epoch": 49.285714285714285, "percentage": 98.57, "elapsed_time": "2:42:47", "remaining_time": "0:02:21"}
|
| 140 |
+
{"current_steps": 350, "total_steps": 350, "loss": 0.001, "lr": 4.477033475702719e-10, "epoch": 50.0, "percentage": 100.0, "elapsed_time": "2:44:38", "remaining_time": "0:00:00"}
|
| 141 |
+
{"current_steps": 350, "total_steps": 350, "eval_loss": 1.8277511596679688, "epoch": 50.0, "percentage": 100.0, "elapsed_time": "2:45:00", "remaining_time": "0:00:00"}
|
| 142 |
+
{"current_steps": 350, "total_steps": 350, "epoch": 50.0, "percentage": 100.0, "elapsed_time": "2:46:59", "remaining_time": "0:00:00"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1101 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 50.0,
|
| 6 |
+
"eval_steps": 5,
|
| 7 |
+
"global_step": 350,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0,
|
| 14 |
+
"eval_loss": 1.468239188194275,
|
| 15 |
+
"eval_runtime": 18.8322,
|
| 16 |
+
"eval_samples_per_second": 2.655,
|
| 17 |
+
"eval_steps_per_second": 0.372,
|
| 18 |
+
"step": 0
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 0.7142857142857143,
|
| 22 |
+
"grad_norm": 5.422401428222656,
|
| 23 |
+
"learning_rate": 4.444444444444444e-06,
|
| 24 |
+
"loss": 1.3518,
|
| 25 |
+
"step": 5
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 0.7142857142857143,
|
| 29 |
+
"eval_loss": 1.3430589437484741,
|
| 30 |
+
"eval_runtime": 19.2589,
|
| 31 |
+
"eval_samples_per_second": 2.596,
|
| 32 |
+
"eval_steps_per_second": 0.363,
|
| 33 |
+
"step": 5
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 1.4285714285714286,
|
| 37 |
+
"grad_norm": 2.686959981918335,
|
| 38 |
+
"learning_rate": 1e-05,
|
| 39 |
+
"loss": 0.9051,
|
| 40 |
+
"step": 10
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 1.4285714285714286,
|
| 44 |
+
"eval_loss": 1.2059158086776733,
|
| 45 |
+
"eval_runtime": 20.856,
|
| 46 |
+
"eval_samples_per_second": 2.397,
|
| 47 |
+
"eval_steps_per_second": 0.336,
|
| 48 |
+
"step": 10
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 2.142857142857143,
|
| 52 |
+
"grad_norm": 1.8475016355514526,
|
| 53 |
+
"learning_rate": 1.555555555555556e-05,
|
| 54 |
+
"loss": 0.8625,
|
| 55 |
+
"step": 15
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 2.142857142857143,
|
| 59 |
+
"eval_loss": 1.127707600593567,
|
| 60 |
+
"eval_runtime": 20.3953,
|
| 61 |
+
"eval_samples_per_second": 2.452,
|
| 62 |
+
"eval_steps_per_second": 0.343,
|
| 63 |
+
"step": 15
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 2.857142857142857,
|
| 67 |
+
"grad_norm": 1.3544838428497314,
|
| 68 |
+
"learning_rate": 1.9999552296652432e-05,
|
| 69 |
+
"loss": 0.6971,
|
| 70 |
+
"step": 20
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 2.857142857142857,
|
| 74 |
+
"eval_loss": 1.114540696144104,
|
| 75 |
+
"eval_runtime": 20.5519,
|
| 76 |
+
"eval_samples_per_second": 2.433,
|
| 77 |
+
"eval_steps_per_second": 0.341,
|
| 78 |
+
"step": 20
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 3.571428571428571,
|
| 82 |
+
"grad_norm": 1.6196757555007935,
|
| 83 |
+
"learning_rate": 1.9983886888289515e-05,
|
| 84 |
+
"loss": 0.4243,
|
| 85 |
+
"step": 25
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 3.571428571428571,
|
| 89 |
+
"eval_loss": 1.1612136363983154,
|
| 90 |
+
"eval_runtime": 20.8803,
|
| 91 |
+
"eval_samples_per_second": 2.395,
|
| 92 |
+
"eval_steps_per_second": 0.335,
|
| 93 |
+
"step": 25
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 4.285714285714286,
|
| 97 |
+
"grad_norm": 1.041768193244934,
|
| 98 |
+
"learning_rate": 1.994587638407389e-05,
|
| 99 |
+
"loss": 0.1901,
|
| 100 |
+
"step": 30
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 4.285714285714286,
|
| 104 |
+
"eval_loss": 1.3399298191070557,
|
| 105 |
+
"eval_runtime": 20.3992,
|
| 106 |
+
"eval_samples_per_second": 2.451,
|
| 107 |
+
"eval_steps_per_second": 0.343,
|
| 108 |
+
"step": 30
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 5.0,
|
| 112 |
+
"grad_norm": 0.8406388163566589,
|
| 113 |
+
"learning_rate": 1.9885605855918887e-05,
|
| 114 |
+
"loss": 0.1171,
|
| 115 |
+
"step": 35
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 5.0,
|
| 119 |
+
"eval_loss": 1.3959039449691772,
|
| 120 |
+
"eval_runtime": 20.6168,
|
| 121 |
+
"eval_samples_per_second": 2.425,
|
| 122 |
+
"eval_steps_per_second": 0.34,
|
| 123 |
+
"step": 35
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 5.714285714285714,
|
| 127 |
+
"grad_norm": 0.7612068057060242,
|
| 128 |
+
"learning_rate": 1.9803210196251057e-05,
|
| 129 |
+
"loss": 0.0593,
|
| 130 |
+
"step": 40
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 5.714285714285714,
|
| 134 |
+
"eval_loss": 1.4992326498031616,
|
| 135 |
+
"eval_runtime": 21.0617,
|
| 136 |
+
"eval_samples_per_second": 2.374,
|
| 137 |
+
"eval_steps_per_second": 0.332,
|
| 138 |
+
"step": 40
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 6.428571428571429,
|
| 142 |
+
"grad_norm": 0.5397480130195618,
|
| 143 |
+
"learning_rate": 1.9698873816105272e-05,
|
| 144 |
+
"loss": 0.0265,
|
| 145 |
+
"step": 45
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 6.428571428571429,
|
| 149 |
+
"eval_loss": 1.5966981649398804,
|
| 150 |
+
"eval_runtime": 20.5478,
|
| 151 |
+
"eval_samples_per_second": 2.433,
|
| 152 |
+
"eval_steps_per_second": 0.341,
|
| 153 |
+
"step": 45
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 7.142857142857143,
|
| 157 |
+
"grad_norm": 0.34659039974212646,
|
| 158 |
+
"learning_rate": 1.9572830232391467e-05,
|
| 159 |
+
"loss": 0.0229,
|
| 160 |
+
"step": 50
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 7.142857142857143,
|
| 164 |
+
"eval_loss": 1.6269463300704956,
|
| 165 |
+
"eval_runtime": 21.143,
|
| 166 |
+
"eval_samples_per_second": 2.365,
|
| 167 |
+
"eval_steps_per_second": 0.331,
|
| 168 |
+
"step": 50
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 7.857142857142857,
|
| 172 |
+
"grad_norm": 0.5654157996177673,
|
| 173 |
+
"learning_rate": 1.942536154525673e-05,
|
| 174 |
+
"loss": 0.0167,
|
| 175 |
+
"step": 55
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 7.857142857142857,
|
| 179 |
+
"eval_loss": 1.6504554748535156,
|
| 180 |
+
"eval_runtime": 20.9122,
|
| 181 |
+
"eval_samples_per_second": 2.391,
|
| 182 |
+
"eval_steps_per_second": 0.335,
|
| 183 |
+
"step": 55
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 8.571428571428571,
|
| 187 |
+
"grad_norm": 0.47888287901878357,
|
| 188 |
+
"learning_rate": 1.9256797806712478e-05,
|
| 189 |
+
"loss": 0.0119,
|
| 190 |
+
"step": 60
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 8.571428571428571,
|
| 194 |
+
"eval_loss": 1.6625537872314453,
|
| 195 |
+
"eval_runtime": 20.8644,
|
| 196 |
+
"eval_samples_per_second": 2.396,
|
| 197 |
+
"eval_steps_per_second": 0.335,
|
| 198 |
+
"step": 60
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 9.285714285714286,
|
| 202 |
+
"grad_norm": 0.17783451080322266,
|
| 203 |
+
"learning_rate": 1.9067516281939826e-05,
|
| 204 |
+
"loss": 0.0094,
|
| 205 |
+
"step": 65
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 9.285714285714286,
|
| 209 |
+
"eval_loss": 1.6874204874038696,
|
| 210 |
+
"eval_runtime": 21.4952,
|
| 211 |
+
"eval_samples_per_second": 2.326,
|
| 212 |
+
"eval_steps_per_second": 0.326,
|
| 213 |
+
"step": 65
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 10.0,
|
| 217 |
+
"grad_norm": 0.3508545160293579,
|
| 218 |
+
"learning_rate": 1.885794060492637e-05,
|
| 219 |
+
"loss": 0.0089,
|
| 220 |
+
"step": 70
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 10.0,
|
| 224 |
+
"eval_loss": 1.7034786939620972,
|
| 225 |
+
"eval_runtime": 21.6794,
|
| 226 |
+
"eval_samples_per_second": 2.306,
|
| 227 |
+
"eval_steps_per_second": 0.323,
|
| 228 |
+
"step": 70
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 10.714285714285714,
|
| 232 |
+
"grad_norm": 0.3566827178001404,
|
| 233 |
+
"learning_rate": 1.862853983032423e-05,
|
| 234 |
+
"loss": 0.0062,
|
| 235 |
+
"step": 75
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 10.714285714285714,
|
| 239 |
+
"eval_loss": 1.7052545547485352,
|
| 240 |
+
"eval_runtime": 21.1384,
|
| 241 |
+
"eval_samples_per_second": 2.365,
|
| 242 |
+
"eval_steps_per_second": 0.331,
|
| 243 |
+
"step": 75
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 11.428571428571429,
|
| 247 |
+
"grad_norm": 0.20090198516845703,
|
| 248 |
+
"learning_rate": 1.83798273836514e-05,
|
| 249 |
+
"loss": 0.0072,
|
| 250 |
+
"step": 80
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 11.428571428571429,
|
| 254 |
+
"eval_loss": 1.7082165479660034,
|
| 255 |
+
"eval_runtime": 21.7116,
|
| 256 |
+
"eval_samples_per_second": 2.303,
|
| 257 |
+
"eval_steps_per_second": 0.322,
|
| 258 |
+
"step": 80
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 12.142857142857142,
|
| 262 |
+
"grad_norm": 0.16760864853858948,
|
| 263 |
+
"learning_rate": 1.8112359912185923e-05,
|
| 264 |
+
"loss": 0.008,
|
| 265 |
+
"step": 85
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 12.142857142857142,
|
| 269 |
+
"eval_loss": 1.6972074508666992,
|
| 270 |
+
"eval_runtime": 21.5935,
|
| 271 |
+
"eval_samples_per_second": 2.316,
|
| 272 |
+
"eval_steps_per_second": 0.324,
|
| 273 |
+
"step": 85
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 12.857142857142858,
|
| 277 |
+
"grad_norm": 0.1947411298751831,
|
| 278 |
+
"learning_rate": 1.7826736039124782e-05,
|
| 279 |
+
"loss": 0.006,
|
| 280 |
+
"step": 90
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 12.857142857142858,
|
| 284 |
+
"eval_loss": 1.6968964338302612,
|
| 285 |
+
"eval_runtime": 21.3118,
|
| 286 |
+
"eval_samples_per_second": 2.346,
|
| 287 |
+
"eval_steps_per_second": 0.328,
|
| 288 |
+
"step": 90
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 13.571428571428571,
|
| 292 |
+
"grad_norm": 0.2383287250995636,
|
| 293 |
+
"learning_rate": 1.7523595023795814e-05,
|
| 294 |
+
"loss": 0.0044,
|
| 295 |
+
"step": 95
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 13.571428571428571,
|
| 299 |
+
"eval_loss": 1.7048730850219727,
|
| 300 |
+
"eval_runtime": 21.8112,
|
| 301 |
+
"eval_samples_per_second": 2.292,
|
| 302 |
+
"eval_steps_per_second": 0.321,
|
| 303 |
+
"step": 95
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 14.285714285714286,
|
| 307 |
+
"grad_norm": 0.0442085787653923,
|
| 308 |
+
"learning_rate": 1.720361533092124e-05,
|
| 309 |
+
"loss": 0.0036,
|
| 310 |
+
"step": 100
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 14.285714285714286,
|
| 314 |
+
"eval_loss": 1.7229158878326416,
|
| 315 |
+
"eval_runtime": 21.3718,
|
| 316 |
+
"eval_samples_per_second": 2.34,
|
| 317 |
+
"eval_steps_per_second": 0.328,
|
| 318 |
+
"step": 100
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 15.0,
|
| 322 |
+
"grad_norm": 0.15548433363437653,
|
| 323 |
+
"learning_rate": 1.6867513112135012e-05,
|
| 324 |
+
"loss": 0.0035,
|
| 325 |
+
"step": 105
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 15.0,
|
| 329 |
+
"eval_loss": 1.7421244382858276,
|
| 330 |
+
"eval_runtime": 21.513,
|
| 331 |
+
"eval_samples_per_second": 2.324,
|
| 332 |
+
"eval_steps_per_second": 0.325,
|
| 333 |
+
"step": 105
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 15.714285714285714,
|
| 337 |
+
"grad_norm": 0.14688356220722198,
|
| 338 |
+
"learning_rate": 1.6516040603152448e-05,
|
| 339 |
+
"loss": 0.0026,
|
| 340 |
+
"step": 110
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 15.714285714285714,
|
| 344 |
+
"eval_loss": 1.7549571990966797,
|
| 345 |
+
"eval_runtime": 21.852,
|
| 346 |
+
"eval_samples_per_second": 2.288,
|
| 347 |
+
"eval_steps_per_second": 0.32,
|
| 348 |
+
"step": 110
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 16.428571428571427,
|
| 352 |
+
"grad_norm": 0.11230692267417908,
|
| 353 |
+
"learning_rate": 1.614998444017954e-05,
|
| 354 |
+
"loss": 0.0023,
|
| 355 |
+
"step": 115
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 16.428571428571427,
|
| 359 |
+
"eval_loss": 1.7617460489273071,
|
| 360 |
+
"eval_runtime": 21.5895,
|
| 361 |
+
"eval_samples_per_second": 2.316,
|
| 362 |
+
"eval_steps_per_second": 0.324,
|
| 363 |
+
"step": 115
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 17.142857142857142,
|
| 367 |
+
"grad_norm": 0.05092110484838486,
|
| 368 |
+
"learning_rate": 1.5770163899329943e-05,
|
| 369 |
+
"loss": 0.0021,
|
| 370 |
+
"step": 120
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 17.142857142857142,
|
| 374 |
+
"eval_loss": 1.7655525207519531,
|
| 375 |
+
"eval_runtime": 21.8701,
|
| 376 |
+
"eval_samples_per_second": 2.286,
|
| 377 |
+
"eval_steps_per_second": 0.32,
|
| 378 |
+
"step": 120
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 17.857142857142858,
|
| 382 |
+
"grad_norm": 0.11048714816570282,
|
| 383 |
+
"learning_rate": 1.5377429062990122e-05,
|
| 384 |
+
"loss": 0.0025,
|
| 385 |
+
"step": 125
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 17.857142857142858,
|
| 389 |
+
"eval_loss": 1.768291711807251,
|
| 390 |
+
"eval_runtime": 21.9645,
|
| 391 |
+
"eval_samples_per_second": 2.276,
|
| 392 |
+
"eval_steps_per_second": 0.319,
|
| 393 |
+
"step": 125
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 18.571428571428573,
|
| 397 |
+
"grad_norm": 0.07220487296581268,
|
| 398 |
+
"learning_rate": 1.497265891723643e-05,
|
| 399 |
+
"loss": 0.0018,
|
| 400 |
+
"step": 130
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 18.571428571428573,
|
| 404 |
+
"eval_loss": 1.7749742269515991,
|
| 405 |
+
"eval_runtime": 21.6791,
|
| 406 |
+
"eval_samples_per_second": 2.306,
|
| 407 |
+
"eval_steps_per_second": 0.323,
|
| 408 |
+
"step": 130
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 19.285714285714285,
|
| 412 |
+
"grad_norm": 0.09813550859689713,
|
| 413 |
+
"learning_rate": 1.4556759384562418e-05,
|
| 414 |
+
"loss": 0.002,
|
| 415 |
+
"step": 135
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 19.285714285714285,
|
| 419 |
+
"eval_loss": 1.7667394876480103,
|
| 420 |
+
"eval_runtime": 22.2338,
|
| 421 |
+
"eval_samples_per_second": 2.249,
|
| 422 |
+
"eval_steps_per_second": 0.315,
|
| 423 |
+
"step": 135
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 20.0,
|
| 427 |
+
"grad_norm": 0.06082721799612045,
|
| 428 |
+
"learning_rate": 1.4130661296319313e-05,
|
| 429 |
+
"loss": 0.0036,
|
| 430 |
+
"step": 140
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 20.0,
|
| 434 |
+
"eval_loss": 1.7492411136627197,
|
| 435 |
+
"eval_runtime": 21.9099,
|
| 436 |
+
"eval_samples_per_second": 2.282,
|
| 437 |
+
"eval_steps_per_second": 0.319,
|
| 438 |
+
"step": 140
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 20.714285714285715,
|
| 442 |
+
"grad_norm": 0.19404393434524536,
|
| 443 |
+
"learning_rate": 1.369531830940757e-05,
|
| 444 |
+
"loss": 0.0025,
|
| 445 |
+
"step": 145
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 20.714285714285715,
|
| 449 |
+
"eval_loss": 1.7377521991729736,
|
| 450 |
+
"eval_runtime": 21.7672,
|
| 451 |
+
"eval_samples_per_second": 2.297,
|
| 452 |
+
"eval_steps_per_second": 0.322,
|
| 453 |
+
"step": 145
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 21.428571428571427,
|
| 457 |
+
"grad_norm": 0.05864373594522476,
|
| 458 |
+
"learning_rate": 1.325170477188224e-05,
|
| 459 |
+
"loss": 0.0017,
|
| 460 |
+
"step": 150
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 21.428571428571427,
|
| 464 |
+
"eval_loss": 1.7388665676116943,
|
| 465 |
+
"eval_runtime": 22.2013,
|
| 466 |
+
"eval_samples_per_second": 2.252,
|
| 467 |
+
"eval_steps_per_second": 0.315,
|
| 468 |
+
"step": 150
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 22.142857142857142,
|
| 472 |
+
"grad_norm": 0.04350695759057999,
|
| 473 |
+
"learning_rate": 1.2800813542249073e-05,
|
| 474 |
+
"loss": 0.0016,
|
| 475 |
+
"step": 155
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 22.142857142857142,
|
| 479 |
+
"eval_loss": 1.7510356903076172,
|
| 480 |
+
"eval_runtime": 22.0791,
|
| 481 |
+
"eval_samples_per_second": 2.265,
|
| 482 |
+
"eval_steps_per_second": 0.317,
|
| 483 |
+
"step": 155
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 22.857142857142858,
|
| 487 |
+
"grad_norm": 0.09723013639450073,
|
| 488 |
+
"learning_rate": 1.234365376733215e-05,
|
| 489 |
+
"loss": 0.0016,
|
| 490 |
+
"step": 160
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 22.857142857142858,
|
| 494 |
+
"eval_loss": 1.7622946500778198,
|
| 495 |
+
"eval_runtime": 22.0297,
|
| 496 |
+
"eval_samples_per_second": 2.27,
|
| 497 |
+
"eval_steps_per_second": 0.318,
|
| 498 |
+
"step": 160
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 23.571428571428573,
|
| 502 |
+
"grad_norm": 0.046282168477773666,
|
| 503 |
+
"learning_rate": 1.188124862368634e-05,
|
| 504 |
+
"loss": 0.0014,
|
| 505 |
+
"step": 165
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 23.571428571428573,
|
| 509 |
+
"eval_loss": 1.770511507987976,
|
| 510 |
+
"eval_runtime": 21.9343,
|
| 511 |
+
"eval_samples_per_second": 2.28,
|
| 512 |
+
"eval_steps_per_second": 0.319,
|
| 513 |
+
"step": 165
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 24.285714285714285,
|
| 517 |
+
"grad_norm": 0.03766458481550217,
|
| 518 |
+
"learning_rate": 1.1414633027609585e-05,
|
| 519 |
+
"loss": 0.0013,
|
| 520 |
+
"step": 170
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 24.285714285714285,
|
| 524 |
+
"eval_loss": 1.7750704288482666,
|
| 525 |
+
"eval_runtime": 22.0134,
|
| 526 |
+
"eval_samples_per_second": 2.271,
|
| 527 |
+
"eval_steps_per_second": 0.318,
|
| 528 |
+
"step": 170
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 25.0,
|
| 532 |
+
"grad_norm": 0.14919541776180267,
|
| 533 |
+
"learning_rate": 1.0944851318880314e-05,
|
| 534 |
+
"loss": 0.0015,
|
| 535 |
+
"step": 175
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 25.0,
|
| 539 |
+
"eval_loss": 1.7801543474197388,
|
| 540 |
+
"eval_runtime": 22.0082,
|
| 541 |
+
"eval_samples_per_second": 2.272,
|
| 542 |
+
"eval_steps_per_second": 0.318,
|
| 543 |
+
"step": 175
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 25.714285714285715,
|
| 547 |
+
"grad_norm": 0.01755683310329914,
|
| 548 |
+
"learning_rate": 1.047295492340397e-05,
|
| 549 |
+
"loss": 0.0011,
|
| 550 |
+
"step": 180
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 25.714285714285715,
|
| 554 |
+
"eval_loss": 1.7830265760421753,
|
| 555 |
+
"eval_runtime": 22.0185,
|
| 556 |
+
"eval_samples_per_second": 2.271,
|
| 557 |
+
"eval_steps_per_second": 0.318,
|
| 558 |
+
"step": 180
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 26.428571428571427,
|
| 562 |
+
"grad_norm": 0.051639165729284286,
|
| 563 |
+
"learning_rate": 1e-05,
|
| 564 |
+
"loss": 0.0012,
|
| 565 |
+
"step": 185
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 26.428571428571427,
|
| 569 |
+
"eval_loss": 1.7872556447982788,
|
| 570 |
+
"eval_runtime": 22.2185,
|
| 571 |
+
"eval_samples_per_second": 2.25,
|
| 572 |
+
"eval_steps_per_second": 0.315,
|
| 573 |
+
"step": 185
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 27.142857142857142,
|
| 577 |
+
"grad_norm": 0.05077521875500679,
|
| 578 |
+
"learning_rate": 9.527045076596036e-06,
|
| 579 |
+
"loss": 0.0011,
|
| 580 |
+
"step": 190
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 27.142857142857142,
|
| 584 |
+
"eval_loss": 1.7918928861618042,
|
| 585 |
+
"eval_runtime": 22.0395,
|
| 586 |
+
"eval_samples_per_second": 2.269,
|
| 587 |
+
"eval_steps_per_second": 0.318,
|
| 588 |
+
"step": 190
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 27.857142857142858,
|
| 592 |
+
"grad_norm": 0.0997517928481102,
|
| 593 |
+
"learning_rate": 9.055148681119688e-06,
|
| 594 |
+
"loss": 0.0012,
|
| 595 |
+
"step": 195
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 27.857142857142858,
|
| 599 |
+
"eval_loss": 1.7959425449371338,
|
| 600 |
+
"eval_runtime": 21.9538,
|
| 601 |
+
"eval_samples_per_second": 2.278,
|
| 602 |
+
"eval_steps_per_second": 0.319,
|
| 603 |
+
"step": 195
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 28.571428571428573,
|
| 607 |
+
"grad_norm": 0.07028105854988098,
|
| 608 |
+
"learning_rate": 8.585366972390416e-06,
|
| 609 |
+
"loss": 0.0012,
|
| 610 |
+
"step": 200
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 28.571428571428573,
|
| 614 |
+
"eval_loss": 1.7992604970932007,
|
| 615 |
+
"eval_runtime": 22.074,
|
| 616 |
+
"eval_samples_per_second": 2.265,
|
| 617 |
+
"eval_steps_per_second": 0.317,
|
| 618 |
+
"step": 200
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 29.285714285714285,
|
| 622 |
+
"grad_norm": 0.05388140678405762,
|
| 623 |
+
"learning_rate": 8.118751376313666e-06,
|
| 624 |
+
"loss": 0.001,
|
| 625 |
+
"step": 205
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 29.285714285714285,
|
| 629 |
+
"eval_loss": 1.801768183708191,
|
| 630 |
+
"eval_runtime": 21.8246,
|
| 631 |
+
"eval_samples_per_second": 2.291,
|
| 632 |
+
"eval_steps_per_second": 0.321,
|
| 633 |
+
"step": 205
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 30.0,
|
| 637 |
+
"grad_norm": 0.0411839634180069,
|
| 638 |
+
"learning_rate": 7.65634623266785e-06,
|
| 639 |
+
"loss": 0.0012,
|
| 640 |
+
"step": 210
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 30.0,
|
| 644 |
+
"eval_loss": 1.8040063381195068,
|
| 645 |
+
"eval_runtime": 22.2164,
|
| 646 |
+
"eval_samples_per_second": 2.251,
|
| 647 |
+
"eval_steps_per_second": 0.315,
|
| 648 |
+
"step": 210
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 30.714285714285715,
|
| 652 |
+
"grad_norm": 0.04949762672185898,
|
| 653 |
+
"learning_rate": 7.199186457750931e-06,
|
| 654 |
+
"loss": 0.001,
|
| 655 |
+
"step": 215
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 30.714285714285715,
|
| 659 |
+
"eval_loss": 1.807271957397461,
|
| 660 |
+
"eval_runtime": 22.2074,
|
| 661 |
+
"eval_samples_per_second": 2.252,
|
| 662 |
+
"eval_steps_per_second": 0.315,
|
| 663 |
+
"step": 215
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 31.428571428571427,
|
| 667 |
+
"grad_norm": 0.041917722672224045,
|
| 668 |
+
"learning_rate": 6.748295228117765e-06,
|
| 669 |
+
"loss": 0.001,
|
| 670 |
+
"step": 220
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 31.428571428571427,
|
| 674 |
+
"eval_loss": 1.8091932535171509,
|
| 675 |
+
"eval_runtime": 22.225,
|
| 676 |
+
"eval_samples_per_second": 2.25,
|
| 677 |
+
"eval_steps_per_second": 0.315,
|
| 678 |
+
"step": 220
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 32.142857142857146,
|
| 682 |
+
"grad_norm": 0.06832437217235565,
|
| 683 |
+
"learning_rate": 6.304681690592431e-06,
|
| 684 |
+
"loss": 0.0014,
|
| 685 |
+
"step": 225
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 32.142857142857146,
|
| 689 |
+
"eval_loss": 1.8116446733474731,
|
| 690 |
+
"eval_runtime": 22.2548,
|
| 691 |
+
"eval_samples_per_second": 2.247,
|
| 692 |
+
"eval_steps_per_second": 0.315,
|
| 693 |
+
"step": 225
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 32.857142857142854,
|
| 697 |
+
"grad_norm": 0.0969175174832344,
|
| 698 |
+
"learning_rate": 5.869338703680691e-06,
|
| 699 |
+
"loss": 0.0011,
|
| 700 |
+
"step": 230
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 32.857142857142854,
|
| 704 |
+
"eval_loss": 1.8134872913360596,
|
| 705 |
+
"eval_runtime": 22.0272,
|
| 706 |
+
"eval_samples_per_second": 2.27,
|
| 707 |
+
"eval_steps_per_second": 0.318,
|
| 708 |
+
"step": 230
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 33.57142857142857,
|
| 712 |
+
"grad_norm": 0.0360889658331871,
|
| 713 |
+
"learning_rate": 5.443240615437586e-06,
|
| 714 |
+
"loss": 0.001,
|
| 715 |
+
"step": 235
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 33.57142857142857,
|
| 719 |
+
"eval_loss": 1.814117670059204,
|
| 720 |
+
"eval_runtime": 21.875,
|
| 721 |
+
"eval_samples_per_second": 2.286,
|
| 722 |
+
"eval_steps_per_second": 0.32,
|
| 723 |
+
"step": 235
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 34.285714285714285,
|
| 727 |
+
"grad_norm": 0.047800276428461075,
|
| 728 |
+
"learning_rate": 5.027341082763575e-06,
|
| 729 |
+
"loss": 0.0011,
|
| 730 |
+
"step": 240
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 34.285714285714285,
|
| 734 |
+
"eval_loss": 1.8167412281036377,
|
| 735 |
+
"eval_runtime": 21.996,
|
| 736 |
+
"eval_samples_per_second": 2.273,
|
| 737 |
+
"eval_steps_per_second": 0.318,
|
| 738 |
+
"step": 240
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 35.0,
|
| 742 |
+
"grad_norm": 0.03180164098739624,
|
| 743 |
+
"learning_rate": 4.622570937009879e-06,
|
| 744 |
+
"loss": 0.0009,
|
| 745 |
+
"step": 245
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 35.0,
|
| 749 |
+
"eval_loss": 1.8182238340377808,
|
| 750 |
+
"eval_runtime": 22.4068,
|
| 751 |
+
"eval_samples_per_second": 2.231,
|
| 752 |
+
"eval_steps_per_second": 0.312,
|
| 753 |
+
"step": 245
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 35.714285714285715,
|
| 757 |
+
"grad_norm": 0.020492179319262505,
|
| 758 |
+
"learning_rate": 4.229836100670058e-06,
|
| 759 |
+
"loss": 0.001,
|
| 760 |
+
"step": 250
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 35.714285714285715,
|
| 764 |
+
"eval_loss": 1.8190386295318604,
|
| 765 |
+
"eval_runtime": 22.0033,
|
| 766 |
+
"eval_samples_per_second": 2.272,
|
| 767 |
+
"eval_steps_per_second": 0.318,
|
| 768 |
+
"step": 250
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 36.42857142857143,
|
| 772 |
+
"grad_norm": 0.09310004115104675,
|
| 773 |
+
"learning_rate": 3.850015559820465e-06,
|
| 774 |
+
"loss": 0.0011,
|
| 775 |
+
"step": 255
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 36.42857142857143,
|
| 779 |
+
"eval_loss": 1.8204212188720703,
|
| 780 |
+
"eval_runtime": 21.9927,
|
| 781 |
+
"eval_samples_per_second": 2.273,
|
| 782 |
+
"eval_steps_per_second": 0.318,
|
| 783 |
+
"step": 255
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 37.142857142857146,
|
| 787 |
+
"grad_norm": 0.056946855038404465,
|
| 788 |
+
"learning_rate": 3.483959396847554e-06,
|
| 789 |
+
"loss": 0.0012,
|
| 790 |
+
"step": 260
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 37.142857142857146,
|
| 794 |
+
"eval_loss": 1.821565866470337,
|
| 795 |
+
"eval_runtime": 21.8674,
|
| 796 |
+
"eval_samples_per_second": 2.287,
|
| 797 |
+
"eval_steps_per_second": 0.32,
|
| 798 |
+
"step": 260
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 37.857142857142854,
|
| 802 |
+
"grad_norm": 0.04144909605383873,
|
| 803 |
+
"learning_rate": 3.132486887864992e-06,
|
| 804 |
+
"loss": 0.0009,
|
| 805 |
+
"step": 265
|
| 806 |
+
},
|
| 807 |
+
{
|
| 808 |
+
"epoch": 37.857142857142854,
|
| 809 |
+
"eval_loss": 1.8220727443695068,
|
| 810 |
+
"eval_runtime": 22.0788,
|
| 811 |
+
"eval_samples_per_second": 2.265,
|
| 812 |
+
"eval_steps_per_second": 0.317,
|
| 813 |
+
"step": 265
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 38.57142857142857,
|
| 817 |
+
"grad_norm": 0.020420927554368973,
|
| 818 |
+
"learning_rate": 2.7963846690787633e-06,
|
| 819 |
+
"loss": 0.001,
|
| 820 |
+
"step": 270
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 38.57142857142857,
|
| 824 |
+
"eval_loss": 1.822296380996704,
|
| 825 |
+
"eval_runtime": 22.0319,
|
| 826 |
+
"eval_samples_per_second": 2.269,
|
| 827 |
+
"eval_steps_per_second": 0.318,
|
| 828 |
+
"step": 270
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 39.285714285714285,
|
| 832 |
+
"grad_norm": 0.03683812543749809,
|
| 833 |
+
"learning_rate": 2.4764049762041874e-06,
|
| 834 |
+
"loss": 0.0013,
|
| 835 |
+
"step": 275
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 39.285714285714285,
|
| 839 |
+
"eval_loss": 1.8238246440887451,
|
| 840 |
+
"eval_runtime": 22.3005,
|
| 841 |
+
"eval_samples_per_second": 2.242,
|
| 842 |
+
"eval_steps_per_second": 0.314,
|
| 843 |
+
"step": 275
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 40.0,
|
| 847 |
+
"grad_norm": 0.07886708527803421,
|
| 848 |
+
"learning_rate": 2.1732639608752173e-06,
|
| 849 |
+
"loss": 0.0011,
|
| 850 |
+
"step": 280
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 40.0,
|
| 854 |
+
"eval_loss": 1.824698567390442,
|
| 855 |
+
"eval_runtime": 22.3675,
|
| 856 |
+
"eval_samples_per_second": 2.235,
|
| 857 |
+
"eval_steps_per_second": 0.313,
|
| 858 |
+
"step": 280
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 40.714285714285715,
|
| 862 |
+
"grad_norm": 0.04558909684419632,
|
| 863 |
+
"learning_rate": 1.8876400878140776e-06,
|
| 864 |
+
"loss": 0.0009,
|
| 865 |
+
"step": 285
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 40.714285714285715,
|
| 869 |
+
"eval_loss": 1.8251045942306519,
|
| 870 |
+
"eval_runtime": 22.0914,
|
| 871 |
+
"eval_samples_per_second": 2.263,
|
| 872 |
+
"eval_steps_per_second": 0.317,
|
| 873 |
+
"step": 285
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 41.42857142857143,
|
| 877 |
+
"grad_norm": 0.037249855697155,
|
| 878 |
+
"learning_rate": 1.6201726163485997e-06,
|
| 879 |
+
"loss": 0.0011,
|
| 880 |
+
"step": 290
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 41.42857142857143,
|
| 884 |
+
"eval_loss": 1.8252718448638916,
|
| 885 |
+
"eval_runtime": 22.0174,
|
| 886 |
+
"eval_samples_per_second": 2.271,
|
| 887 |
+
"eval_steps_per_second": 0.318,
|
| 888 |
+
"step": 290
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 42.142857142857146,
|
| 892 |
+
"grad_norm": 0.0819711983203888,
|
| 893 |
+
"learning_rate": 1.3714601696757713e-06,
|
| 894 |
+
"loss": 0.001,
|
| 895 |
+
"step": 295
|
| 896 |
+
},
|
| 897 |
+
{
|
| 898 |
+
"epoch": 42.142857142857146,
|
| 899 |
+
"eval_loss": 1.826216459274292,
|
| 900 |
+
"eval_runtime": 21.9895,
|
| 901 |
+
"eval_samples_per_second": 2.274,
|
| 902 |
+
"eval_steps_per_second": 0.318,
|
| 903 |
+
"step": 295
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 42.857142857142854,
|
| 907 |
+
"grad_norm": 0.04518039524555206,
|
| 908 |
+
"learning_rate": 1.1420593950736326e-06,
|
| 909 |
+
"loss": 0.001,
|
| 910 |
+
"step": 300
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 42.857142857142854,
|
| 914 |
+
"eval_loss": 1.8267167806625366,
|
| 915 |
+
"eval_runtime": 21.8488,
|
| 916 |
+
"eval_samples_per_second": 2.288,
|
| 917 |
+
"eval_steps_per_second": 0.32,
|
| 918 |
+
"step": 300
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 43.57142857142857,
|
| 922 |
+
"grad_norm": 0.03789067268371582,
|
| 923 |
+
"learning_rate": 9.324837180601743e-07,
|
| 924 |
+
"loss": 0.0011,
|
| 925 |
+
"step": 305
|
| 926 |
+
},
|
| 927 |
+
{
|
| 928 |
+
"epoch": 43.57142857142857,
|
| 929 |
+
"eval_loss": 1.8267269134521484,
|
| 930 |
+
"eval_runtime": 22.0372,
|
| 931 |
+
"eval_samples_per_second": 2.269,
|
| 932 |
+
"eval_steps_per_second": 0.318,
|
| 933 |
+
"step": 305
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 44.285714285714285,
|
| 937 |
+
"grad_norm": 0.07329820841550827,
|
| 938 |
+
"learning_rate": 7.432021932875222e-07,
|
| 939 |
+
"loss": 0.0012,
|
| 940 |
+
"step": 310
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 44.285714285714285,
|
| 944 |
+
"eval_loss": 1.8272424936294556,
|
| 945 |
+
"eval_runtime": 21.9242,
|
| 946 |
+
"eval_samples_per_second": 2.281,
|
| 947 |
+
"eval_steps_per_second": 0.319,
|
| 948 |
+
"step": 310
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 45.0,
|
| 952 |
+
"grad_norm": 0.0455288402736187,
|
| 953 |
+
"learning_rate": 5.746384547432738e-07,
|
| 954 |
+
"loss": 0.0009,
|
| 955 |
+
"step": 315
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 45.0,
|
| 959 |
+
"eval_loss": 1.8278112411499023,
|
| 960 |
+
"eval_runtime": 22.3633,
|
| 961 |
+
"eval_samples_per_second": 2.236,
|
| 962 |
+
"eval_steps_per_second": 0.313,
|
| 963 |
+
"step": 315
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 45.714285714285715,
|
| 967 |
+
"grad_norm": 0.05950823426246643,
|
| 968 |
+
"learning_rate": 4.2716976760853513e-07,
|
| 969 |
+
"loss": 0.0008,
|
| 970 |
+
"step": 320
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 45.714285714285715,
|
| 974 |
+
"eval_loss": 1.8275575637817383,
|
| 975 |
+
"eval_runtime": 21.8644,
|
| 976 |
+
"eval_samples_per_second": 2.287,
|
| 977 |
+
"eval_steps_per_second": 0.32,
|
| 978 |
+
"step": 320
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 46.42857142857143,
|
| 982 |
+
"grad_norm": 0.04292258992791176,
|
| 983 |
+
"learning_rate": 3.011261838947277e-07,
|
| 984 |
+
"loss": 0.0009,
|
| 985 |
+
"step": 325
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 46.42857142857143,
|
| 989 |
+
"eval_loss": 1.8281974792480469,
|
| 990 |
+
"eval_runtime": 22.2434,
|
| 991 |
+
"eval_samples_per_second": 2.248,
|
| 992 |
+
"eval_steps_per_second": 0.315,
|
| 993 |
+
"step": 325
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 47.142857142857146,
|
| 997 |
+
"grad_norm": 0.03321965038776398,
|
| 998 |
+
"learning_rate": 1.9678980374894352e-07,
|
| 999 |
+
"loss": 0.001,
|
| 1000 |
+
"step": 330
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"epoch": 47.142857142857146,
|
| 1004 |
+
"eval_loss": 1.8281824588775635,
|
| 1005 |
+
"eval_runtime": 21.8282,
|
| 1006 |
+
"eval_samples_per_second": 2.291,
|
| 1007 |
+
"eval_steps_per_second": 0.321,
|
| 1008 |
+
"step": 330
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 47.857142857142854,
|
| 1012 |
+
"grad_norm": 0.05279669910669327,
|
| 1013 |
+
"learning_rate": 1.1439414408111471e-07,
|
| 1014 |
+
"loss": 0.001,
|
| 1015 |
+
"step": 335
|
| 1016 |
+
},
|
| 1017 |
+
{
|
| 1018 |
+
"epoch": 47.857142857142854,
|
| 1019 |
+
"eval_loss": 1.827906847000122,
|
| 1020 |
+
"eval_runtime": 21.7868,
|
| 1021 |
+
"eval_samples_per_second": 2.295,
|
| 1022 |
+
"eval_steps_per_second": 0.321,
|
| 1023 |
+
"step": 335
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 48.57142857142857,
|
| 1027 |
+
"grad_norm": 0.03341998532414436,
|
| 1028 |
+
"learning_rate": 5.412361592611382e-08,
|
| 1029 |
+
"loss": 0.0008,
|
| 1030 |
+
"step": 340
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"epoch": 48.57142857142857,
|
| 1034 |
+
"eval_loss": 1.828213095664978,
|
| 1035 |
+
"eval_runtime": 21.9519,
|
| 1036 |
+
"eval_samples_per_second": 2.278,
|
| 1037 |
+
"eval_steps_per_second": 0.319,
|
| 1038 |
+
"step": 340
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 49.285714285714285,
|
| 1042 |
+
"grad_norm": 0.04219294339418411,
|
| 1043 |
+
"learning_rate": 1.611311171048735e-08,
|
| 1044 |
+
"loss": 0.0012,
|
| 1045 |
+
"step": 345
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 49.285714285714285,
|
| 1049 |
+
"eval_loss": 1.8280681371688843,
|
| 1050 |
+
"eval_runtime": 22.1409,
|
| 1051 |
+
"eval_samples_per_second": 2.258,
|
| 1052 |
+
"eval_steps_per_second": 0.316,
|
| 1053 |
+
"step": 345
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 50.0,
|
| 1057 |
+
"grad_norm": 0.046254031360149384,
|
| 1058 |
+
"learning_rate": 4.477033475702719e-10,
|
| 1059 |
+
"loss": 0.001,
|
| 1060 |
+
"step": 350
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 50.0,
|
| 1064 |
+
"eval_loss": 1.8277511596679688,
|
| 1065 |
+
"eval_runtime": 21.972,
|
| 1066 |
+
"eval_samples_per_second": 2.276,
|
| 1067 |
+
"eval_steps_per_second": 0.319,
|
| 1068 |
+
"step": 350
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"epoch": 50.0,
|
| 1072 |
+
"step": 350,
|
| 1073 |
+
"total_flos": 86960020979712.0,
|
| 1074 |
+
"train_loss": 0.06868666498057012,
|
| 1075 |
+
"train_runtime": 10021.0579,
|
| 1076 |
+
"train_samples_per_second": 0.249,
|
| 1077 |
+
"train_steps_per_second": 0.035
|
| 1078 |
+
}
|
| 1079 |
+
],
|
| 1080 |
+
"logging_steps": 5,
|
| 1081 |
+
"max_steps": 350,
|
| 1082 |
+
"num_input_tokens_seen": 0,
|
| 1083 |
+
"num_train_epochs": 50,
|
| 1084 |
+
"save_steps": 999,
|
| 1085 |
+
"stateful_callbacks": {
|
| 1086 |
+
"TrainerControl": {
|
| 1087 |
+
"args": {
|
| 1088 |
+
"should_epoch_stop": false,
|
| 1089 |
+
"should_evaluate": false,
|
| 1090 |
+
"should_log": false,
|
| 1091 |
+
"should_save": true,
|
| 1092 |
+
"should_training_stop": true
|
| 1093 |
+
},
|
| 1094 |
+
"attributes": {}
|
| 1095 |
+
}
|
| 1096 |
+
},
|
| 1097 |
+
"total_flos": 86960020979712.0,
|
| 1098 |
+
"train_batch_size": 1,
|
| 1099 |
+
"trial_name": null,
|
| 1100 |
+
"trial_params": null
|
| 1101 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7c4773a06dc1c1cb607b6e8a89f6139cacfc21196cb28236cdf04ddfaf8fcbef
|
| 3 |
+
size 8017
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|