hf-reset commited on
Commit ·
4ad1f7b
0
Parent(s):
Reset repository without checkpoints directories
Browse files- .gitattributes +36 -0
- README.md +61 -0
- added_tokens.json +28 -0
- all_results.json +16 -0
- chat_template.jinja +89 -0
- config.json +68 -0
- generation_config.json +13 -0
- merges.txt +0 -0
- model-00001-of-00004.safetensors +3 -0
- model-00002-of-00004.safetensors +3 -0
- model-00003-of-00004.safetensors +3 -0
- model-00004-of-00004.safetensors +3 -0
- model.safetensors.index.json +407 -0
- run_summary.json +12 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +240 -0
- train_results.json +16 -0
- trainer_log.jsonl +80 -0
- trainer_state.json +916 -0
- training_args.bin +3 -0
- training_loss.png +0 -0
- vocab.json +0 -0
.gitattributes
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
| 13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
| 29 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 30 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 31 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 32 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
| 33 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: Qwen/Qwen3-8B
|
| 5 |
+
tags:
|
| 6 |
+
- llama-factory
|
| 7 |
+
- full
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: All_Puzzles_5k_new_context
|
| 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 |
+
# All_Puzzles_5k_new_context
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on the DCAgent/All_Puzzles_5k_new_context dataset.
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 4e-05
|
| 39 |
+
- train_batch_size: 1
|
| 40 |
+
- eval_batch_size: 8
|
| 41 |
+
- seed: 42
|
| 42 |
+
- distributed_type: multi-GPU
|
| 43 |
+
- num_devices: 16
|
| 44 |
+
- gradient_accumulation_steps: 4
|
| 45 |
+
- total_train_batch_size: 64
|
| 46 |
+
- total_eval_batch_size: 128
|
| 47 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 48 |
+
- lr_scheduler_type: cosine
|
| 49 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 50 |
+
- num_epochs: 5.0
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
|
| 55 |
+
|
| 56 |
+
### Framework versions
|
| 57 |
+
|
| 58 |
+
- Transformers 4.55.0
|
| 59 |
+
- Pytorch 2.7.0+cu128
|
| 60 |
+
- Datasets 3.6.0
|
| 61 |
+
- 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 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"achieved_tflops_per_gpu": 2.1966163442877087,
|
| 3 |
+
"achieved_tflops_per_gpu_theoretical": 257.48074677456077,
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"loss_nan_ranks": 0,
|
| 6 |
+
"loss_rank_avg": 0.3953709602355957,
|
| 7 |
+
"mfu_percent": 0.15523790418994407,
|
| 8 |
+
"mfu_percent_theoretical": 18.19651920668274,
|
| 9 |
+
"total_flos": 1.835207408620667e+17,
|
| 10 |
+
"train_loss": 0.4235323069970819,
|
| 11 |
+
"train_runtime": 5221.6885,
|
| 12 |
+
"train_samples_per_second": 4.788,
|
| 13 |
+
"train_steps_per_second": 0.076,
|
| 14 |
+
"valid_targets_mean": 898.1,
|
| 15 |
+
"valid_targets_min": 349
|
| 16 |
+
}
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,89 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0].role == 'system' %}
|
| 4 |
+
{{- messages[0].content + '\n\n' }}
|
| 5 |
+
{%- endif %}
|
| 6 |
+
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
| 7 |
+
{%- for tool in tools %}
|
| 8 |
+
{{- "\n" }}
|
| 9 |
+
{{- tool | tojson }}
|
| 10 |
+
{%- endfor %}
|
| 11 |
+
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
| 12 |
+
{%- else %}
|
| 13 |
+
{%- if messages[0].role == 'system' %}
|
| 14 |
+
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
| 15 |
+
{%- endif %}
|
| 16 |
+
{%- endif %}
|
| 17 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 18 |
+
{%- for message in messages[::-1] %}
|
| 19 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 20 |
+
{%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
| 21 |
+
{%- set ns.multi_step_tool = false %}
|
| 22 |
+
{%- set ns.last_query_index = index %}
|
| 23 |
+
{%- endif %}
|
| 24 |
+
{%- endfor %}
|
| 25 |
+
{%- for message in messages %}
|
| 26 |
+
{%- if message.content is string %}
|
| 27 |
+
{%- set content = message.content %}
|
| 28 |
+
{%- else %}
|
| 29 |
+
{%- set content = '' %}
|
| 30 |
+
{%- endif %}
|
| 31 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
| 32 |
+
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 33 |
+
{%- elif message.role == "assistant" %}
|
| 34 |
+
{%- set reasoning_content = '' %}
|
| 35 |
+
{%- if message.reasoning_content is string %}
|
| 36 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 37 |
+
{%- else %}
|
| 38 |
+
{%- if '</think>' in content %}
|
| 39 |
+
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 40 |
+
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
| 41 |
+
{%- endif %}
|
| 42 |
+
{%- endif %}
|
| 43 |
+
{%- if loop.index0 > ns.last_query_index %}
|
| 44 |
+
{%- if loop.last or (not loop.last and reasoning_content) %}
|
| 45 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
| 46 |
+
{%- else %}
|
| 47 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 48 |
+
{%- endif %}
|
| 49 |
+
{%- else %}
|
| 50 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 51 |
+
{%- endif %}
|
| 52 |
+
{%- if message.tool_calls %}
|
| 53 |
+
{%- for tool_call in message.tool_calls %}
|
| 54 |
+
{%- if (loop.first and content) or (not loop.first) %}
|
| 55 |
+
{{- '\n' }}
|
| 56 |
+
{%- endif %}
|
| 57 |
+
{%- if tool_call.function %}
|
| 58 |
+
{%- set tool_call = tool_call.function %}
|
| 59 |
+
{%- endif %}
|
| 60 |
+
{{- '<tool_call>\n{"name": "' }}
|
| 61 |
+
{{- tool_call.name }}
|
| 62 |
+
{{- '", "arguments": ' }}
|
| 63 |
+
{%- if tool_call.arguments is string %}
|
| 64 |
+
{{- tool_call.arguments }}
|
| 65 |
+
{%- else %}
|
| 66 |
+
{{- tool_call.arguments | tojson }}
|
| 67 |
+
{%- endif %}
|
| 68 |
+
{{- '}\n</tool_call>' }}
|
| 69 |
+
{%- endfor %}
|
| 70 |
+
{%- endif %}
|
| 71 |
+
{{- '<|im_end|>\n' }}
|
| 72 |
+
{%- elif message.role == "tool" %}
|
| 73 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 74 |
+
{{- '<|im_start|>user' }}
|
| 75 |
+
{%- endif %}
|
| 76 |
+
{{- '\n<tool_response>\n' }}
|
| 77 |
+
{{- content }}
|
| 78 |
+
{{- '\n</tool_response>' }}
|
| 79 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 80 |
+
{{- '<|im_end|>\n' }}
|
| 81 |
+
{%- endif %}
|
| 82 |
+
{%- endif %}
|
| 83 |
+
{%- endfor %}
|
| 84 |
+
{%- if add_generation_prompt %}
|
| 85 |
+
{{- '<|im_start|>assistant\n' }}
|
| 86 |
+
{%- if enable_thinking is defined and enable_thinking is false %}
|
| 87 |
+
{{- '<think>\n\n</think>\n\n' }}
|
| 88 |
+
{%- endif %}
|
| 89 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151643,
|
| 8 |
+
"eos_token_id": 151645,
|
| 9 |
+
"head_dim": 128,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 4096,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 12288,
|
| 14 |
+
"layer_types": [
|
| 15 |
+
"full_attention",
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"full_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"full_attention",
|
| 49 |
+
"full_attention",
|
| 50 |
+
"full_attention"
|
| 51 |
+
],
|
| 52 |
+
"max_position_embeddings": 40960,
|
| 53 |
+
"max_window_layers": 36,
|
| 54 |
+
"model_type": "qwen3",
|
| 55 |
+
"num_attention_heads": 32,
|
| 56 |
+
"num_hidden_layers": 36,
|
| 57 |
+
"num_key_value_heads": 8,
|
| 58 |
+
"rms_norm_eps": 1e-06,
|
| 59 |
+
"rope_scaling": null,
|
| 60 |
+
"rope_theta": 1000000,
|
| 61 |
+
"sliding_window": null,
|
| 62 |
+
"tie_word_embeddings": false,
|
| 63 |
+
"torch_dtype": "bfloat16",
|
| 64 |
+
"transformers_version": "4.55.0",
|
| 65 |
+
"use_cache": false,
|
| 66 |
+
"use_sliding_window": false,
|
| 67 |
+
"vocab_size": 151936
|
| 68 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 151643,
|
| 9 |
+
"temperature": 0.6,
|
| 10 |
+
"top_k": 20,
|
| 11 |
+
"top_p": 0.95,
|
| 12 |
+
"transformers_version": "4.55.0"
|
| 13 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aba8260051c73ead84442e9f6ccdeb36e42174676862425df3dba6113447e0b2
|
| 3 |
+
size 4902257696
|
model-00002-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c7244cce4dab04a128b381d10cab37ca17ebd586504309d7b87612696e004dd0
|
| 3 |
+
size 4915960368
|
model-00003-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6844bb0842b91674cceb83cf3e5861a0a8482b19b4a1e5ea5c899606cabd82c2
|
| 3 |
+
size 4983068496
|
model-00004-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7b2f573f666d7f66dc16f3fa60e878dd1aae17534879cbb6ab6a0cfb69a2e09e
|
| 3 |
+
size 1580230264
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,407 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 308224,
|
| 4 |
+
"total_size": 16381470720
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"lm_head.weight": "model-00004-of-00004.safetensors",
|
| 8 |
+
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
| 9 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 10 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 11 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 12 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 13 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 19 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 20 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 21 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 22 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 23 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 24 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 29 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 30 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 31 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 32 |
+
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 33 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 34 |
+
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 35 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 36 |
+
"model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 37 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 38 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 39 |
+
"model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 40 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 41 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 42 |
+
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 43 |
+
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 44 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 45 |
+
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 46 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 47 |
+
"model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 48 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 49 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 50 |
+
"model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 51 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 52 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 53 |
+
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 54 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 55 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 56 |
+
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 57 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 58 |
+
"model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 59 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 60 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 61 |
+
"model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 62 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 63 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 64 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 65 |
+
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 66 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 67 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 68 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 69 |
+
"model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 70 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 71 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 72 |
+
"model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 73 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 74 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 75 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 76 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 77 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 78 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 79 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 80 |
+
"model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 81 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 82 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 83 |
+
"model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 84 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 85 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 86 |
+
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 87 |
+
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 88 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 89 |
+
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 90 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 91 |
+
"model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 92 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 93 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 94 |
+
"model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 95 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 96 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 97 |
+
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 98 |
+
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 99 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 100 |
+
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 101 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 102 |
+
"model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 103 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 104 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 105 |
+
"model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 106 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 107 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 108 |
+
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 109 |
+
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 110 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 111 |
+
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 112 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 113 |
+
"model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 114 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 115 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 116 |
+
"model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 117 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 118 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 119 |
+
"model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 120 |
+
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 121 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 122 |
+
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 123 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 124 |
+
"model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 125 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 126 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 127 |
+
"model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 128 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 129 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 130 |
+
"model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 131 |
+
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 132 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 133 |
+
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 134 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 135 |
+
"model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 136 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 137 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 138 |
+
"model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 139 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 140 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 141 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 142 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 143 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 144 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 145 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 146 |
+
"model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 147 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 148 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 149 |
+
"model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 150 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 151 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 152 |
+
"model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 153 |
+
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 154 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 155 |
+
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 156 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 157 |
+
"model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 158 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 159 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 160 |
+
"model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 161 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 162 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 163 |
+
"model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 164 |
+
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 165 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 166 |
+
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 167 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 168 |
+
"model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 169 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 170 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 171 |
+
"model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 172 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 173 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 174 |
+
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 175 |
+
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 176 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 177 |
+
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 178 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 179 |
+
"model.layers.22.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 180 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 181 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 182 |
+
"model.layers.22.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 183 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 184 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 185 |
+
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 186 |
+
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 187 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 188 |
+
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 189 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 190 |
+
"model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 191 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 192 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 193 |
+
"model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 194 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 195 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 196 |
+
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 197 |
+
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 198 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 199 |
+
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 200 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 201 |
+
"model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 202 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 203 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 204 |
+
"model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 205 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 206 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 207 |
+
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 208 |
+
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 209 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 210 |
+
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 211 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 212 |
+
"model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 213 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 214 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 215 |
+
"model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 216 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 217 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 218 |
+
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 219 |
+
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 220 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 221 |
+
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 222 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 223 |
+
"model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 224 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 225 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 226 |
+
"model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 227 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 228 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 229 |
+
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 230 |
+
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 231 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 232 |
+
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 233 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 234 |
+
"model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 235 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 236 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 237 |
+
"model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 238 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 239 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 240 |
+
"model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 241 |
+
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 242 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 243 |
+
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 244 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 245 |
+
"model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 246 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 247 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 248 |
+
"model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 249 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 250 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 251 |
+
"model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 252 |
+
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 253 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 254 |
+
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 255 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 256 |
+
"model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 257 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 258 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 259 |
+
"model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 260 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 261 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 262 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 263 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 264 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 265 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 266 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 267 |
+
"model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 268 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 269 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 270 |
+
"model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 271 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 272 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 273 |
+
"model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 274 |
+
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 275 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 276 |
+
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 277 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 278 |
+
"model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 279 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 280 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 281 |
+
"model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 282 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 283 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 284 |
+
"model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 285 |
+
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 286 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 287 |
+
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 288 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 289 |
+
"model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 290 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 291 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 292 |
+
"model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 293 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 294 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 295 |
+
"model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 296 |
+
"model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 297 |
+
"model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 298 |
+
"model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 299 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 300 |
+
"model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 301 |
+
"model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 302 |
+
"model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 303 |
+
"model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 304 |
+
"model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 305 |
+
"model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 306 |
+
"model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 307 |
+
"model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 308 |
+
"model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 309 |
+
"model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 310 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 311 |
+
"model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 312 |
+
"model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 313 |
+
"model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 314 |
+
"model.layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 315 |
+
"model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 316 |
+
"model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 317 |
+
"model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 318 |
+
"model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 319 |
+
"model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 320 |
+
"model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 321 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 322 |
+
"model.layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 323 |
+
"model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 324 |
+
"model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 325 |
+
"model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 326 |
+
"model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 327 |
+
"model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 328 |
+
"model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 329 |
+
"model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 330 |
+
"model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 331 |
+
"model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 332 |
+
"model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 333 |
+
"model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
| 334 |
+
"model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 335 |
+
"model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
| 336 |
+
"model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
| 337 |
+
"model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 338 |
+
"model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 339 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 340 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 341 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 342 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 343 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 344 |
+
"model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 345 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 346 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 347 |
+
"model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 348 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 349 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 350 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 351 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 352 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 353 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 354 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 355 |
+
"model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 356 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 357 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 358 |
+
"model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 359 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 360 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 361 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 362 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 363 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 364 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 365 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 366 |
+
"model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 367 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 368 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 369 |
+
"model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 370 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 371 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 372 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 373 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 374 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 375 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 376 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 377 |
+
"model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 378 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 379 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 380 |
+
"model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 381 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 382 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 383 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 384 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 385 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 386 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 387 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 388 |
+
"model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 389 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 390 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 391 |
+
"model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 392 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 393 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 394 |
+
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 395 |
+
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 396 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 397 |
+
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 398 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 399 |
+
"model.layers.9.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 400 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 401 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 402 |
+
"model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 403 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 404 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 405 |
+
"model.norm.weight": "model-00004-of-00004.safetensors"
|
| 406 |
+
}
|
| 407 |
+
}
|
run_summary.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"agent_name": null,
|
| 3 |
+
"training_start": null,
|
| 4 |
+
"training_end": null,
|
| 5 |
+
"created_by": "DCAgent",
|
| 6 |
+
"base_model_name": "Qwen/Qwen3-8B",
|
| 7 |
+
"dataset_name": "DCAgent/All_Puzzles_5k_new_context",
|
| 8 |
+
"training_type": "SFT",
|
| 9 |
+
"training_parameters": "https://huggingface.co/DCAgent/All_Puzzles_5k_new_context/blob/main/config.json",
|
| 10 |
+
"wandb_link": "https://wandb.ai/dogml/dc-agent/runs/All_Puzzles_5k_new_context",
|
| 11 |
+
"traces_location_s3": null
|
| 12 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
| 3 |
+
size 11422654
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,240 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
},
|
| 181 |
+
"151665": {
|
| 182 |
+
"content": "<tool_response>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"151666": {
|
| 190 |
+
"content": "</tool_response>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
+
},
|
| 197 |
+
"151667": {
|
| 198 |
+
"content": "<think>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": false
|
| 204 |
+
},
|
| 205 |
+
"151668": {
|
| 206 |
+
"content": "</think>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
+
}
|
| 213 |
+
},
|
| 214 |
+
"additional_special_tokens": [
|
| 215 |
+
"<|im_start|>",
|
| 216 |
+
"<|im_end|>",
|
| 217 |
+
"<|object_ref_start|>",
|
| 218 |
+
"<|object_ref_end|>",
|
| 219 |
+
"<|box_start|>",
|
| 220 |
+
"<|box_end|>",
|
| 221 |
+
"<|quad_start|>",
|
| 222 |
+
"<|quad_end|>",
|
| 223 |
+
"<|vision_start|>",
|
| 224 |
+
"<|vision_end|>",
|
| 225 |
+
"<|vision_pad|>",
|
| 226 |
+
"<|image_pad|>",
|
| 227 |
+
"<|video_pad|>"
|
| 228 |
+
],
|
| 229 |
+
"bos_token": null,
|
| 230 |
+
"clean_up_tokenization_spaces": false,
|
| 231 |
+
"eos_token": "<|im_end|>",
|
| 232 |
+
"errors": "replace",
|
| 233 |
+
"extra_special_tokens": {},
|
| 234 |
+
"model_max_length": 32768,
|
| 235 |
+
"pad_token": "<|endoftext|>",
|
| 236 |
+
"padding_side": "right",
|
| 237 |
+
"split_special_tokens": false,
|
| 238 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 239 |
+
"unk_token": null
|
| 240 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"achieved_tflops_per_gpu": 2.1966163442877087,
|
| 3 |
+
"achieved_tflops_per_gpu_theoretical": 257.48074677456077,
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"loss_nan_ranks": 0,
|
| 6 |
+
"loss_rank_avg": 0.3953709602355957,
|
| 7 |
+
"mfu_percent": 0.15523790418994407,
|
| 8 |
+
"mfu_percent_theoretical": 18.19651920668274,
|
| 9 |
+
"total_flos": 1.835207408620667e+17,
|
| 10 |
+
"train_loss": 0.4235323069970819,
|
| 11 |
+
"train_runtime": 5221.6885,
|
| 12 |
+
"train_samples_per_second": 4.788,
|
| 13 |
+
"train_steps_per_second": 0.076,
|
| 14 |
+
"valid_targets_mean": 898.1,
|
| 15 |
+
"valid_targets_min": 349
|
| 16 |
+
}
|
trainer_log.jsonl
ADDED
|
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 5, "total_steps": 395, "loss": 0.9711, "lr": 4.000000000000001e-06, "epoch": 0.06389776357827476, "percentage": 1.27, "elapsed_time": "0:01:16", "remaining_time": "1:39:25"}
|
| 2 |
+
{"current_steps": 10, "total_steps": 395, "loss": 0.8155, "lr": 9e-06, "epoch": 0.12779552715654952, "percentage": 2.53, "elapsed_time": "0:02:27", "remaining_time": "1:34:51"}
|
| 3 |
+
{"current_steps": 15, "total_steps": 395, "loss": 0.7286, "lr": 1.4e-05, "epoch": 0.19169329073482427, "percentage": 3.8, "elapsed_time": "0:03:40", "remaining_time": "1:33:07"}
|
| 4 |
+
{"current_steps": 20, "total_steps": 395, "loss": 0.6642, "lr": 1.9e-05, "epoch": 0.25559105431309903, "percentage": 5.06, "elapsed_time": "0:04:48", "remaining_time": "1:30:10"}
|
| 5 |
+
{"current_steps": 25, "total_steps": 395, "loss": 0.6146, "lr": 2.4e-05, "epoch": 0.3194888178913738, "percentage": 6.33, "elapsed_time": "0:05:54", "remaining_time": "1:27:26"}
|
| 6 |
+
{"current_steps": 30, "total_steps": 395, "loss": 0.573, "lr": 2.9e-05, "epoch": 0.38338658146964855, "percentage": 7.59, "elapsed_time": "0:06:59", "remaining_time": "1:25:05"}
|
| 7 |
+
{"current_steps": 35, "total_steps": 395, "loss": 0.5375, "lr": 3.4e-05, "epoch": 0.4472843450479233, "percentage": 8.86, "elapsed_time": "0:08:04", "remaining_time": "1:23:03"}
|
| 8 |
+
{"current_steps": 40, "total_steps": 395, "loss": 0.5556, "lr": 3.9e-05, "epoch": 0.5111821086261981, "percentage": 10.13, "elapsed_time": "0:09:08", "remaining_time": "1:21:03"}
|
| 9 |
+
{"current_steps": 45, "total_steps": 395, "loss": 0.5102, "lr": 3.998747096355221e-05, "epoch": 0.5750798722044729, "percentage": 11.39, "elapsed_time": "0:10:19", "remaining_time": "1:20:14"}
|
| 10 |
+
{"current_steps": 50, "total_steps": 395, "loss": 0.4923, "lr": 3.993659865551998e-05, "epoch": 0.6389776357827476, "percentage": 12.66, "elapsed_time": "0:11:30", "remaining_time": "1:19:27"}
|
| 11 |
+
{"current_steps": 55, "total_steps": 395, "loss": 0.4748, "lr": 3.984669951939583e-05, "epoch": 0.7028753993610224, "percentage": 13.92, "elapsed_time": "0:12:40", "remaining_time": "1:18:18"}
|
| 12 |
+
{"current_steps": 60, "total_steps": 395, "loss": 0.457, "lr": 3.971794953696041e-05, "epoch": 0.7667731629392971, "percentage": 15.19, "elapsed_time": "0:13:56", "remaining_time": "1:17:48"}
|
| 13 |
+
{"current_steps": 65, "total_steps": 395, "loss": 0.4803, "lr": 3.955060074235045e-05, "epoch": 0.8306709265175719, "percentage": 16.46, "elapsed_time": "0:15:05", "remaining_time": "1:16:35"}
|
| 14 |
+
{"current_steps": 70, "total_steps": 395, "loss": 0.4547, "lr": 3.934498072869008e-05, "epoch": 0.8945686900958466, "percentage": 17.72, "elapsed_time": "0:16:19", "remaining_time": "1:15:45"}
|
| 15 |
+
{"current_steps": 75, "total_steps": 395, "loss": 0.4328, "lr": 3.910149200681199e-05, "epoch": 0.9584664536741214, "percentage": 18.99, "elapsed_time": "0:17:31", "remaining_time": "1:14:46"}
|
| 16 |
+
{"current_steps": 80, "total_steps": 395, "loss": 0.4418, "lr": 3.882061121732349e-05, "epoch": 1.012779552715655, "percentage": 20.25, "elapsed_time": "0:18:25", "remaining_time": "1:12:33"}
|
| 17 |
+
{"current_steps": 85, "total_steps": 395, "loss": 0.4308, "lr": 3.850288819756019e-05, "epoch": 1.0766773162939298, "percentage": 21.52, "elapsed_time": "0:19:34", "remaining_time": "1:11:24"}
|
| 18 |
+
{"current_steps": 90, "total_steps": 395, "loss": 0.4285, "lr": 3.814894490525356e-05, "epoch": 1.1405750798722045, "percentage": 22.78, "elapsed_time": "0:20:42", "remaining_time": "1:10:10"}
|
| 19 |
+
{"current_steps": 95, "total_steps": 395, "loss": 0.42, "lr": 3.775947420101948e-05, "epoch": 1.2044728434504792, "percentage": 24.05, "elapsed_time": "0:21:55", "remaining_time": "1:09:12"}
|
| 20 |
+
{"current_steps": 100, "total_steps": 395, "loss": 0.433, "lr": 3.733523849205105e-05, "epoch": 1.268370607028754, "percentage": 25.32, "elapsed_time": "0:22:58", "remaining_time": "1:07:46"}
|
| 21 |
+
{"current_steps": 105, "total_steps": 395, "loss": 0.4202, "lr": 3.687706823967073e-05, "epoch": 1.3322683706070286, "percentage": 26.58, "elapsed_time": "0:24:02", "remaining_time": "1:06:25"}
|
| 22 |
+
{"current_steps": 110, "total_steps": 395, "loss": 0.4359, "lr": 3.6385860333663236e-05, "epoch": 1.3961661341853036, "percentage": 27.85, "elapsed_time": "0:25:06", "remaining_time": "1:05:03"}
|
| 23 |
+
{"current_steps": 115, "total_steps": 395, "loss": 0.4326, "lr": 3.5862576336571725e-05, "epoch": 1.4600638977635783, "percentage": 29.11, "elapsed_time": "0:26:14", "remaining_time": "1:03:53"}
|
| 24 |
+
{"current_steps": 120, "total_steps": 395, "loss": 0.4196, "lr": 3.530824060139396e-05, "epoch": 1.5239616613418532, "percentage": 30.38, "elapsed_time": "0:27:21", "remaining_time": "1:02:42"}
|
| 25 |
+
{"current_steps": 125, "total_steps": 395, "loss": 0.3889, "lr": 3.472393826636317e-05, "epoch": 1.5878594249201279, "percentage": 31.65, "elapsed_time": "0:28:37", "remaining_time": "1:01:48"}
|
| 26 |
+
{"current_steps": 130, "total_steps": 395, "loss": 0.4436, "lr": 3.411081313073906e-05, "epoch": 1.6517571884984026, "percentage": 32.91, "elapsed_time": "0:29:37", "remaining_time": "1:00:24"}
|
| 27 |
+
{"current_steps": 135, "total_steps": 395, "loss": 0.4069, "lr": 3.3470065415767004e-05, "epoch": 1.7156549520766773, "percentage": 34.18, "elapsed_time": "0:30:44", "remaining_time": "0:59:11"}
|
| 28 |
+
{"current_steps": 140, "total_steps": 395, "loss": 0.392, "lr": 3.28029494151886e-05, "epoch": 1.779552715654952, "percentage": 35.44, "elapsed_time": "0:31:50", "remaining_time": "0:57:59"}
|
| 29 |
+
{"current_steps": 145, "total_steps": 395, "loss": 0.4031, "lr": 3.211077103990278e-05, "epoch": 1.8434504792332267, "percentage": 36.71, "elapsed_time": "0:32:58", "remaining_time": "0:56:50"}
|
| 30 |
+
{"current_steps": 150, "total_steps": 395, "loss": 0.4247, "lr": 3.13948852615839e-05, "epoch": 1.9073482428115016, "percentage": 37.97, "elapsed_time": "0:34:02", "remaining_time": "0:55:36"}
|
| 31 |
+
{"current_steps": 155, "total_steps": 395, "loss": 0.4122, "lr": 3.065669346026106e-05, "epoch": 1.9712460063897763, "percentage": 39.24, "elapsed_time": "0:35:07", "remaining_time": "0:54:23"}
|
| 32 |
+
{"current_steps": 160, "total_steps": 395, "loss": 0.3831, "lr": 2.9897640681050877e-05, "epoch": 2.02555910543131, "percentage": 40.51, "elapsed_time": "0:36:03", "remaining_time": "0:52:57"}
|
| 33 |
+
{"current_steps": 165, "total_steps": 395, "loss": 0.3747, "lr": 2.91192128054138e-05, "epoch": 2.0894568690095845, "percentage": 41.77, "elapsed_time": "0:37:15", "remaining_time": "0:51:55"}
|
| 34 |
+
{"current_steps": 170, "total_steps": 395, "loss": 0.391, "lr": 2.832293364247141e-05, "epoch": 2.1533546325878596, "percentage": 43.04, "elapsed_time": "0:38:18", "remaining_time": "0:50:42"}
|
| 35 |
+
{"current_steps": 175, "total_steps": 395, "loss": 0.3948, "lr": 2.7510361946078482e-05, "epoch": 2.2172523961661343, "percentage": 44.3, "elapsed_time": "0:39:26", "remaining_time": "0:49:34"}
|
| 36 |
+
{"current_steps": 180, "total_steps": 395, "loss": 0.382, "lr": 2.6683088363489118e-05, "epoch": 2.281150159744409, "percentage": 45.57, "elapsed_time": "0:40:37", "remaining_time": "0:48:32"}
|
| 37 |
+
{"current_steps": 185, "total_steps": 395, "loss": 0.3991, "lr": 2.5842732321590034e-05, "epoch": 2.3450479233226837, "percentage": 46.84, "elapsed_time": "0:41:39", "remaining_time": "0:47:17"}
|
| 38 |
+
{"current_steps": 190, "total_steps": 395, "loss": 0.4022, "lr": 2.499093885679642e-05, "epoch": 2.4089456869009584, "percentage": 48.1, "elapsed_time": "0:42:39", "remaining_time": "0:46:01"}
|
| 39 |
+
{"current_steps": 195, "total_steps": 395, "loss": 0.3818, "lr": 2.4129375394815878e-05, "epoch": 2.472843450479233, "percentage": 49.37, "elapsed_time": "0:43:42", "remaining_time": "0:44:50"}
|
| 40 |
+
{"current_steps": 200, "total_steps": 395, "loss": 0.3852, "lr": 2.3259728486584297e-05, "epoch": 2.536741214057508, "percentage": 50.63, "elapsed_time": "0:44:46", "remaining_time": "0:43:39"}
|
| 41 |
+
{"current_steps": 205, "total_steps": 395, "loss": 0.3881, "lr": 2.2383700506763204e-05, "epoch": 2.600638977635783, "percentage": 51.9, "elapsed_time": "0:45:55", "remaining_time": "0:42:33"}
|
| 42 |
+
{"current_steps": 210, "total_steps": 395, "loss": 0.3927, "lr": 2.150300632126142e-05, "epoch": 2.6645367412140573, "percentage": 53.16, "elapsed_time": "0:47:04", "remaining_time": "0:41:28"}
|
| 43 |
+
{"current_steps": 215, "total_steps": 395, "loss": 0.399, "lr": 2.061936993030451e-05, "epoch": 2.7284345047923324, "percentage": 54.43, "elapsed_time": "0:48:08", "remaining_time": "0:40:17"}
|
| 44 |
+
{"current_steps": 220, "total_steps": 395, "loss": 0.3841, "lr": 1.9734521093623388e-05, "epoch": 2.792332268370607, "percentage": 55.7, "elapsed_time": "0:49:13", "remaining_time": "0:39:09"}
|
| 45 |
+
{"current_steps": 225, "total_steps": 395, "loss": 0.3793, "lr": 1.88501919443684e-05, "epoch": 2.856230031948882, "percentage": 56.96, "elapsed_time": "0:50:19", "remaining_time": "0:38:01"}
|
| 46 |
+
{"current_steps": 230, "total_steps": 395, "loss": 0.3919, "lr": 1.7968113598377356e-05, "epoch": 2.9201277955271565, "percentage": 58.23, "elapsed_time": "0:51:23", "remaining_time": "0:36:52"}
|
| 47 |
+
{"current_steps": 235, "total_steps": 395, "loss": 0.3732, "lr": 1.7090012765434974e-05, "epoch": 2.984025559105431, "percentage": 59.49, "elapsed_time": "0:52:33", "remaining_time": "0:35:47"}
|
| 48 |
+
{"current_steps": 240, "total_steps": 395, "loss": 0.3711, "lr": 1.6217608369157417e-05, "epoch": 3.038338658146965, "percentage": 60.76, "elapsed_time": "0:53:28", "remaining_time": "0:34:32"}
|
| 49 |
+
{"current_steps": 245, "total_steps": 395, "loss": 0.3657, "lr": 1.5352608182118546e-05, "epoch": 3.1022364217252396, "percentage": 62.03, "elapsed_time": "0:54:34", "remaining_time": "0:33:24"}
|
| 50 |
+
{"current_steps": 250, "total_steps": 395, "loss": 0.3412, "lr": 1.4496705482804943e-05, "epoch": 3.1661341853035143, "percentage": 63.29, "elapsed_time": "0:55:50", "remaining_time": "0:32:23"}
|
| 51 |
+
{"current_steps": 255, "total_steps": 395, "loss": 0.3666, "lr": 1.3651575740943746e-05, "epoch": 3.230031948881789, "percentage": 64.56, "elapsed_time": "0:56:57", "remaining_time": "0:31:16"}
|
| 52 |
+
{"current_steps": 260, "total_steps": 395, "loss": 0.3751, "lr": 1.2818873337691993e-05, "epoch": 3.2939297124600637, "percentage": 65.82, "elapsed_time": "0:58:06", "remaining_time": "0:30:10"}
|
| 53 |
+
{"current_steps": 265, "total_steps": 395, "loss": 0.3589, "lr": 1.2000228327107787e-05, "epoch": 3.357827476038339, "percentage": 67.09, "elapsed_time": "0:59:12", "remaining_time": "0:29:02"}
|
| 54 |
+
{"current_steps": 270, "total_steps": 395, "loss": 0.3957, "lr": 1.1197243245242978e-05, "epoch": 3.4217252396166136, "percentage": 68.35, "elapsed_time": "1:00:10", "remaining_time": "0:27:51"}
|
| 55 |
+
{"current_steps": 275, "total_steps": 395, "loss": 0.3787, "lr": 1.0411489973103525e-05, "epoch": 3.4856230031948883, "percentage": 69.62, "elapsed_time": "1:01:17", "remaining_time": "0:26:44"}
|
| 56 |
+
{"current_steps": 280, "total_steps": 395, "loss": 0.3718, "lr": 9.64450665961866e-06, "epoch": 3.549520766773163, "percentage": 70.89, "elapsed_time": "1:02:22", "remaining_time": "0:25:37"}
|
| 57 |
+
{"current_steps": 285, "total_steps": 395, "loss": 0.4002, "lr": 8.897794710642098e-06, "epoch": 3.6134185303514377, "percentage": 72.15, "elapsed_time": "1:03:21", "remaining_time": "0:24:27"}
|
| 58 |
+
{"current_steps": 290, "total_steps": 395, "loss": 0.3588, "lr": 8.172815849879607e-06, "epoch": 3.6773162939297124, "percentage": 73.42, "elapsed_time": "1:04:37", "remaining_time": "0:23:23"}
|
| 59 |
+
{"current_steps": 295, "total_steps": 395, "loss": 0.36, "lr": 7.470989257496164e-06, "epoch": 3.741214057507987, "percentage": 74.68, "elapsed_time": "1:05:46", "remaining_time": "0:22:17"}
|
| 60 |
+
{"current_steps": 300, "total_steps": 395, "loss": 0.3843, "lr": 6.7936887920041825e-06, "epoch": 3.8051118210862622, "percentage": 75.95, "elapsed_time": "1:06:49", "remaining_time": "0:21:09"}
|
| 61 |
+
{"current_steps": 305, "total_steps": 395, "loss": 0.3565, "lr": 6.1422403008709255e-06, "epoch": 3.8690095846645365, "percentage": 77.22, "elapsed_time": "1:07:57", "remaining_time": "0:20:03"}
|
| 62 |
+
{"current_steps": 310, "total_steps": 395, "loss": 0.3677, "lr": 5.517919025109839e-06, "epoch": 3.9329073482428116, "percentage": 78.48, "elapsed_time": "1:08:58", "remaining_time": "0:18:54"}
|
| 63 |
+
{"current_steps": 315, "total_steps": 395, "loss": 0.375, "lr": 4.921947102936388e-06, "epoch": 3.9968051118210863, "percentage": 79.75, "elapsed_time": "1:10:03", "remaining_time": "0:17:47"}
|
| 64 |
+
{"current_steps": 320, "total_steps": 395, "loss": 0.376, "lr": 4.3554911773751e-06, "epoch": 4.05111821086262, "percentage": 81.01, "elapsed_time": "1:10:55", "remaining_time": "0:16:37"}
|
| 65 |
+
{"current_steps": 325, "total_steps": 395, "loss": 0.3523, "lr": 3.819660112501053e-06, "epoch": 4.115015974440895, "percentage": 82.28, "elapsed_time": "1:12:03", "remaining_time": "0:15:31"}
|
| 66 |
+
{"current_steps": 330, "total_steps": 395, "loss": 0.3492, "lr": 3.315502822786407e-06, "epoch": 4.178913738019169, "percentage": 83.54, "elapsed_time": "1:13:09", "remaining_time": "0:14:24"}
|
| 67 |
+
{"current_steps": 335, "total_steps": 395, "loss": 0.3539, "lr": 2.8440062198010187e-06, "epoch": 4.242811501597444, "percentage": 84.81, "elapsed_time": "1:14:13", "remaining_time": "0:13:17"}
|
| 68 |
+
{"current_steps": 340, "total_steps": 395, "loss": 0.3854, "lr": 2.4060932802867498e-06, "epoch": 4.306709265175719, "percentage": 86.08, "elapsed_time": "1:15:18", "remaining_time": "0:12:10"}
|
| 69 |
+
{"current_steps": 345, "total_steps": 395, "loss": 0.3525, "lr": 2.0026212393871057e-06, "epoch": 4.3706070287539935, "percentage": 87.34, "elapsed_time": "1:16:26", "remaining_time": "0:11:04"}
|
| 70 |
+
{"current_steps": 350, "total_steps": 395, "loss": 0.36, "lr": 1.6343799125692194e-06, "epoch": 4.434504792332269, "percentage": 88.61, "elapsed_time": "1:17:30", "remaining_time": "0:09:57"}
|
| 71 |
+
{"current_steps": 355, "total_steps": 395, "loss": 0.3535, "lr": 1.3020901495229632e-06, "epoch": 4.498402555910543, "percentage": 89.87, "elapsed_time": "1:18:35", "remaining_time": "0:08:51"}
|
| 72 |
+
{"current_steps": 360, "total_steps": 395, "loss": 0.3647, "lr": 1.0064024230638547e-06, "epoch": 4.562300319488818, "percentage": 91.14, "elapsed_time": "1:19:42", "remaining_time": "0:07:44"}
|
| 73 |
+
{"current_steps": 365, "total_steps": 395, "loss": 0.3627, "lr": 7.478955558019408e-07, "epoch": 4.626198083067092, "percentage": 92.41, "elapsed_time": "1:20:45", "remaining_time": "0:06:38"}
|
| 74 |
+
{"current_steps": 370, "total_steps": 395, "loss": 0.388, "lr": 5.270755870693877e-07, "epoch": 4.6900958466453675, "percentage": 93.67, "elapsed_time": "1:21:43", "remaining_time": "0:05:31"}
|
| 75 |
+
{"current_steps": 375, "total_steps": 395, "loss": 0.3584, "lr": 3.4437478232470123e-07, "epoch": 4.753993610223642, "percentage": 94.94, "elapsed_time": "1:22:53", "remaining_time": "0:04:25"}
|
| 76 |
+
{"current_steps": 380, "total_steps": 395, "loss": 0.3613, "lr": 2.0015078697281477e-07, "epoch": 4.817891373801917, "percentage": 96.2, "elapsed_time": "1:24:03", "remaining_time": "0:03:19"}
|
| 77 |
+
{"current_steps": 385, "total_steps": 395, "loss": 0.3721, "lr": 9.46859262573896e-08, "epoch": 4.881789137380192, "percentage": 97.47, "elapsed_time": "1:25:01", "remaining_time": "0:02:12"}
|
| 78 |
+
{"current_steps": 390, "total_steps": 395, "loss": 0.3623, "lr": 2.8186652595918464e-08, "epoch": 4.945686900958466, "percentage": 98.73, "elapsed_time": "1:26:06", "remaining_time": "0:01:06"}
|
| 79 |
+
{"current_steps": 395, "total_steps": 395, "loss": 0.3816, "lr": 7.831414393999481e-10, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "1:26:59", "remaining_time": "0:00:00"}
|
| 80 |
+
{"current_steps": 395, "total_steps": 395, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "1:26:59", "remaining_time": "0:00:00"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,916 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 5.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 395,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.06389776357827476,
|
| 14 |
+
"grad_norm": 11.846490253365507,
|
| 15 |
+
"learning_rate": 4.000000000000001e-06,
|
| 16 |
+
"loss": 0.9711,
|
| 17 |
+
"loss_nan_ranks": 0,
|
| 18 |
+
"loss_rank_avg": 0.24778413772583008,
|
| 19 |
+
"step": 5,
|
| 20 |
+
"valid_targets_mean": 786.0,
|
| 21 |
+
"valid_targets_min": 249
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.12779552715654952,
|
| 25 |
+
"grad_norm": 3.2328125357680366,
|
| 26 |
+
"learning_rate": 9e-06,
|
| 27 |
+
"loss": 0.8155,
|
| 28 |
+
"loss_nan_ranks": 0,
|
| 29 |
+
"loss_rank_avg": 0.10182914137840271,
|
| 30 |
+
"step": 10,
|
| 31 |
+
"valid_targets_mean": 511.1,
|
| 32 |
+
"valid_targets_min": 280
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.19169329073482427,
|
| 36 |
+
"grad_norm": 2.0945651648758075,
|
| 37 |
+
"learning_rate": 1.4e-05,
|
| 38 |
+
"loss": 0.7286,
|
| 39 |
+
"loss_nan_ranks": 0,
|
| 40 |
+
"loss_rank_avg": 0.1361304372549057,
|
| 41 |
+
"step": 15,
|
| 42 |
+
"valid_targets_mean": 596.8,
|
| 43 |
+
"valid_targets_min": 242
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 0.25559105431309903,
|
| 47 |
+
"grad_norm": 1.07200943732659,
|
| 48 |
+
"learning_rate": 1.9e-05,
|
| 49 |
+
"loss": 0.6642,
|
| 50 |
+
"loss_nan_ranks": 0,
|
| 51 |
+
"loss_rank_avg": 0.17922356724739075,
|
| 52 |
+
"step": 20,
|
| 53 |
+
"valid_targets_mean": 1402.0,
|
| 54 |
+
"valid_targets_min": 284
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.3194888178913738,
|
| 58 |
+
"grad_norm": 0.7770814401104653,
|
| 59 |
+
"learning_rate": 2.4e-05,
|
| 60 |
+
"loss": 0.6146,
|
| 61 |
+
"loss_nan_ranks": 0,
|
| 62 |
+
"loss_rank_avg": 0.17424175143241882,
|
| 63 |
+
"step": 25,
|
| 64 |
+
"valid_targets_mean": 1804.3,
|
| 65 |
+
"valid_targets_min": 349
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.38338658146964855,
|
| 69 |
+
"grad_norm": 0.7818842815068471,
|
| 70 |
+
"learning_rate": 2.9e-05,
|
| 71 |
+
"loss": 0.573,
|
| 72 |
+
"loss_nan_ranks": 0,
|
| 73 |
+
"loss_rank_avg": 0.13279107213020325,
|
| 74 |
+
"step": 30,
|
| 75 |
+
"valid_targets_mean": 1157.1,
|
| 76 |
+
"valid_targets_min": 303
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.4472843450479233,
|
| 80 |
+
"grad_norm": 0.6351712153510267,
|
| 81 |
+
"learning_rate": 3.4e-05,
|
| 82 |
+
"loss": 0.5375,
|
| 83 |
+
"loss_nan_ranks": 0,
|
| 84 |
+
"loss_rank_avg": 0.09381715953350067,
|
| 85 |
+
"step": 35,
|
| 86 |
+
"valid_targets_mean": 699.2,
|
| 87 |
+
"valid_targets_min": 297
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.5111821086261981,
|
| 91 |
+
"grad_norm": 0.748671288217069,
|
| 92 |
+
"learning_rate": 3.9e-05,
|
| 93 |
+
"loss": 0.5556,
|
| 94 |
+
"loss_nan_ranks": 0,
|
| 95 |
+
"loss_rank_avg": 0.15044507384300232,
|
| 96 |
+
"step": 40,
|
| 97 |
+
"valid_targets_mean": 755.9,
|
| 98 |
+
"valid_targets_min": 248
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.5750798722044729,
|
| 102 |
+
"grad_norm": 0.5822531498171973,
|
| 103 |
+
"learning_rate": 3.998747096355221e-05,
|
| 104 |
+
"loss": 0.5102,
|
| 105 |
+
"loss_nan_ranks": 0,
|
| 106 |
+
"loss_rank_avg": 0.11345083266496658,
|
| 107 |
+
"step": 45,
|
| 108 |
+
"valid_targets_mean": 1041.4,
|
| 109 |
+
"valid_targets_min": 300
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.6389776357827476,
|
| 113 |
+
"grad_norm": 0.5368335924032368,
|
| 114 |
+
"learning_rate": 3.993659865551998e-05,
|
| 115 |
+
"loss": 0.4923,
|
| 116 |
+
"loss_nan_ranks": 0,
|
| 117 |
+
"loss_rank_avg": 0.1393553763628006,
|
| 118 |
+
"step": 50,
|
| 119 |
+
"valid_targets_mean": 1197.8,
|
| 120 |
+
"valid_targets_min": 290
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.7028753993610224,
|
| 124 |
+
"grad_norm": 0.5151565895766127,
|
| 125 |
+
"learning_rate": 3.984669951939583e-05,
|
| 126 |
+
"loss": 0.4748,
|
| 127 |
+
"loss_nan_ranks": 0,
|
| 128 |
+
"loss_rank_avg": 0.1191486194729805,
|
| 129 |
+
"step": 55,
|
| 130 |
+
"valid_targets_mean": 979.2,
|
| 131 |
+
"valid_targets_min": 294
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 0.7667731629392971,
|
| 135 |
+
"grad_norm": 0.6057433789912748,
|
| 136 |
+
"learning_rate": 3.971794953696041e-05,
|
| 137 |
+
"loss": 0.457,
|
| 138 |
+
"loss_nan_ranks": 0,
|
| 139 |
+
"loss_rank_avg": 0.12172172963619232,
|
| 140 |
+
"step": 60,
|
| 141 |
+
"valid_targets_mean": 837.6,
|
| 142 |
+
"valid_targets_min": 314
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.8306709265175719,
|
| 146 |
+
"grad_norm": 0.5494718056179938,
|
| 147 |
+
"learning_rate": 3.955060074235045e-05,
|
| 148 |
+
"loss": 0.4803,
|
| 149 |
+
"loss_nan_ranks": 0,
|
| 150 |
+
"loss_rank_avg": 0.164231076836586,
|
| 151 |
+
"step": 65,
|
| 152 |
+
"valid_targets_mean": 1367.0,
|
| 153 |
+
"valid_targets_min": 246
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.8945686900958466,
|
| 157 |
+
"grad_norm": 0.4969437818302394,
|
| 158 |
+
"learning_rate": 3.934498072869008e-05,
|
| 159 |
+
"loss": 0.4547,
|
| 160 |
+
"loss_nan_ranks": 0,
|
| 161 |
+
"loss_rank_avg": 0.11091209948062897,
|
| 162 |
+
"step": 70,
|
| 163 |
+
"valid_targets_mean": 1212.0,
|
| 164 |
+
"valid_targets_min": 288
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.9584664536741214,
|
| 168 |
+
"grad_norm": 0.5630595874895628,
|
| 169 |
+
"learning_rate": 3.910149200681199e-05,
|
| 170 |
+
"loss": 0.4328,
|
| 171 |
+
"loss_nan_ranks": 0,
|
| 172 |
+
"loss_rank_avg": 0.13822351396083832,
|
| 173 |
+
"step": 75,
|
| 174 |
+
"valid_targets_mean": 1345.7,
|
| 175 |
+
"valid_targets_min": 260
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 1.012779552715655,
|
| 179 |
+
"grad_norm": 0.5184959327438211,
|
| 180 |
+
"learning_rate": 3.882061121732349e-05,
|
| 181 |
+
"loss": 0.4418,
|
| 182 |
+
"loss_nan_ranks": 0,
|
| 183 |
+
"loss_rank_avg": 0.15021207928657532,
|
| 184 |
+
"step": 80,
|
| 185 |
+
"valid_targets_mean": 1405.2,
|
| 186 |
+
"valid_targets_min": 304
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 1.0766773162939298,
|
| 190 |
+
"grad_norm": 0.5190732098428031,
|
| 191 |
+
"learning_rate": 3.850288819756019e-05,
|
| 192 |
+
"loss": 0.4308,
|
| 193 |
+
"loss_nan_ranks": 0,
|
| 194 |
+
"loss_rank_avg": 0.08507606387138367,
|
| 195 |
+
"step": 85,
|
| 196 |
+
"valid_targets_mean": 842.1,
|
| 197 |
+
"valid_targets_min": 281
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 1.1405750798722045,
|
| 201 |
+
"grad_norm": 0.4759743184289998,
|
| 202 |
+
"learning_rate": 3.814894490525356e-05,
|
| 203 |
+
"loss": 0.4285,
|
| 204 |
+
"loss_nan_ranks": 0,
|
| 205 |
+
"loss_rank_avg": 0.11964065581560135,
|
| 206 |
+
"step": 90,
|
| 207 |
+
"valid_targets_mean": 1555.1,
|
| 208 |
+
"valid_targets_min": 246
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 1.2044728434504792,
|
| 212 |
+
"grad_norm": 0.49020448895657526,
|
| 213 |
+
"learning_rate": 3.775947420101948e-05,
|
| 214 |
+
"loss": 0.42,
|
| 215 |
+
"loss_nan_ranks": 0,
|
| 216 |
+
"loss_rank_avg": 0.09147603809833527,
|
| 217 |
+
"step": 95,
|
| 218 |
+
"valid_targets_mean": 888.9,
|
| 219 |
+
"valid_targets_min": 256
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.268370607028754,
|
| 223 |
+
"grad_norm": 0.5485831012812644,
|
| 224 |
+
"learning_rate": 3.733523849205105e-05,
|
| 225 |
+
"loss": 0.433,
|
| 226 |
+
"loss_nan_ranks": 0,
|
| 227 |
+
"loss_rank_avg": 0.12556253373622894,
|
| 228 |
+
"step": 100,
|
| 229 |
+
"valid_targets_mean": 1111.1,
|
| 230 |
+
"valid_targets_min": 244
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 1.3322683706070286,
|
| 234 |
+
"grad_norm": 0.5372234093347528,
|
| 235 |
+
"learning_rate": 3.687706823967073e-05,
|
| 236 |
+
"loss": 0.4202,
|
| 237 |
+
"loss_nan_ranks": 0,
|
| 238 |
+
"loss_rank_avg": 0.11396054923534393,
|
| 239 |
+
"step": 105,
|
| 240 |
+
"valid_targets_mean": 1179.0,
|
| 241 |
+
"valid_targets_min": 290
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 1.3961661341853036,
|
| 245 |
+
"grad_norm": 0.5243140258416459,
|
| 246 |
+
"learning_rate": 3.6385860333663236e-05,
|
| 247 |
+
"loss": 0.4359,
|
| 248 |
+
"loss_nan_ranks": 0,
|
| 249 |
+
"loss_rank_avg": 0.10478255152702332,
|
| 250 |
+
"step": 110,
|
| 251 |
+
"valid_targets_mean": 853.5,
|
| 252 |
+
"valid_targets_min": 327
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 1.4600638977635783,
|
| 256 |
+
"grad_norm": 0.3931198230357848,
|
| 257 |
+
"learning_rate": 3.5862576336571725e-05,
|
| 258 |
+
"loss": 0.4326,
|
| 259 |
+
"loss_nan_ranks": 0,
|
| 260 |
+
"loss_rank_avg": 0.07872852683067322,
|
| 261 |
+
"step": 115,
|
| 262 |
+
"valid_targets_mean": 1274.7,
|
| 263 |
+
"valid_targets_min": 336
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 1.5239616613418532,
|
| 267 |
+
"grad_norm": 0.5550204033113877,
|
| 268 |
+
"learning_rate": 3.530824060139396e-05,
|
| 269 |
+
"loss": 0.4196,
|
| 270 |
+
"loss_nan_ranks": 0,
|
| 271 |
+
"loss_rank_avg": 0.08616568148136139,
|
| 272 |
+
"step": 120,
|
| 273 |
+
"valid_targets_mean": 727.8,
|
| 274 |
+
"valid_targets_min": 223
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 1.5878594249201279,
|
| 278 |
+
"grad_norm": 0.48124183672867193,
|
| 279 |
+
"learning_rate": 3.472393826636317e-05,
|
| 280 |
+
"loss": 0.3889,
|
| 281 |
+
"loss_nan_ranks": 0,
|
| 282 |
+
"loss_rank_avg": 0.06731364876031876,
|
| 283 |
+
"step": 125,
|
| 284 |
+
"valid_targets_mean": 796.5,
|
| 285 |
+
"valid_targets_min": 236
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 1.6517571884984026,
|
| 289 |
+
"grad_norm": 0.5453207894153915,
|
| 290 |
+
"learning_rate": 3.411081313073906e-05,
|
| 291 |
+
"loss": 0.4436,
|
| 292 |
+
"loss_nan_ranks": 0,
|
| 293 |
+
"loss_rank_avg": 0.09588675200939178,
|
| 294 |
+
"step": 130,
|
| 295 |
+
"valid_targets_mean": 804.0,
|
| 296 |
+
"valid_targets_min": 256
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.7156549520766773,
|
| 300 |
+
"grad_norm": 0.5089927833169616,
|
| 301 |
+
"learning_rate": 3.3470065415767004e-05,
|
| 302 |
+
"loss": 0.4069,
|
| 303 |
+
"loss_nan_ranks": 0,
|
| 304 |
+
"loss_rank_avg": 0.08837437629699707,
|
| 305 |
+
"step": 135,
|
| 306 |
+
"valid_targets_mean": 802.1,
|
| 307 |
+
"valid_targets_min": 286
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 1.779552715654952,
|
| 311 |
+
"grad_norm": 0.5517921131975569,
|
| 312 |
+
"learning_rate": 3.28029494151886e-05,
|
| 313 |
+
"loss": 0.392,
|
| 314 |
+
"loss_nan_ranks": 0,
|
| 315 |
+
"loss_rank_avg": 0.10053038597106934,
|
| 316 |
+
"step": 140,
|
| 317 |
+
"valid_targets_mean": 812.3,
|
| 318 |
+
"valid_targets_min": 342
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.8434504792332267,
|
| 322 |
+
"grad_norm": 0.4860959242304931,
|
| 323 |
+
"learning_rate": 3.211077103990278e-05,
|
| 324 |
+
"loss": 0.4031,
|
| 325 |
+
"loss_nan_ranks": 0,
|
| 326 |
+
"loss_rank_avg": 0.09498679637908936,
|
| 327 |
+
"step": 145,
|
| 328 |
+
"valid_targets_mean": 1162.9,
|
| 329 |
+
"valid_targets_min": 408
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 1.9073482428115016,
|
| 333 |
+
"grad_norm": 0.656360992535297,
|
| 334 |
+
"learning_rate": 3.13948852615839e-05,
|
| 335 |
+
"loss": 0.4247,
|
| 336 |
+
"loss_nan_ranks": 0,
|
| 337 |
+
"loss_rank_avg": 0.08237992972135544,
|
| 338 |
+
"step": 150,
|
| 339 |
+
"valid_targets_mean": 611.3,
|
| 340 |
+
"valid_targets_min": 280
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 1.9712460063897763,
|
| 344 |
+
"grad_norm": 0.5564754420514622,
|
| 345 |
+
"learning_rate": 3.065669346026106e-05,
|
| 346 |
+
"loss": 0.4122,
|
| 347 |
+
"loss_nan_ranks": 0,
|
| 348 |
+
"loss_rank_avg": 0.12957195937633514,
|
| 349 |
+
"step": 155,
|
| 350 |
+
"valid_targets_mean": 1156.9,
|
| 351 |
+
"valid_targets_min": 328
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 2.02555910543131,
|
| 355 |
+
"grad_norm": 0.5283956293371946,
|
| 356 |
+
"learning_rate": 2.9897640681050877e-05,
|
| 357 |
+
"loss": 0.3831,
|
| 358 |
+
"loss_nan_ranks": 0,
|
| 359 |
+
"loss_rank_avg": 0.08559633791446686,
|
| 360 |
+
"step": 160,
|
| 361 |
+
"valid_targets_mean": 826.2,
|
| 362 |
+
"valid_targets_min": 276
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 2.0894568690095845,
|
| 366 |
+
"grad_norm": 0.5808828530964132,
|
| 367 |
+
"learning_rate": 2.91192128054138e-05,
|
| 368 |
+
"loss": 0.3747,
|
| 369 |
+
"loss_nan_ranks": 0,
|
| 370 |
+
"loss_rank_avg": 0.10059662163257599,
|
| 371 |
+
"step": 165,
|
| 372 |
+
"valid_targets_mean": 963.9,
|
| 373 |
+
"valid_targets_min": 227
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 2.1533546325878596,
|
| 377 |
+
"grad_norm": 0.5473070037696547,
|
| 378 |
+
"learning_rate": 2.832293364247141e-05,
|
| 379 |
+
"loss": 0.391,
|
| 380 |
+
"loss_nan_ranks": 0,
|
| 381 |
+
"loss_rank_avg": 0.11035449802875519,
|
| 382 |
+
"step": 170,
|
| 383 |
+
"valid_targets_mean": 914.4,
|
| 384 |
+
"valid_targets_min": 307
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 2.2172523961661343,
|
| 388 |
+
"grad_norm": 0.5112472057581164,
|
| 389 |
+
"learning_rate": 2.7510361946078482e-05,
|
| 390 |
+
"loss": 0.3948,
|
| 391 |
+
"loss_nan_ranks": 0,
|
| 392 |
+
"loss_rank_avg": 0.11642749607563019,
|
| 393 |
+
"step": 175,
|
| 394 |
+
"valid_targets_mean": 1093.4,
|
| 395 |
+
"valid_targets_min": 279
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 2.281150159744409,
|
| 399 |
+
"grad_norm": 0.5671250337110724,
|
| 400 |
+
"learning_rate": 2.6683088363489118e-05,
|
| 401 |
+
"loss": 0.382,
|
| 402 |
+
"loss_nan_ranks": 0,
|
| 403 |
+
"loss_rank_avg": 0.15333333611488342,
|
| 404 |
+
"step": 180,
|
| 405 |
+
"valid_targets_mean": 1280.8,
|
| 406 |
+
"valid_targets_min": 272
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 2.3450479233226837,
|
| 410 |
+
"grad_norm": 0.5323581621974115,
|
| 411 |
+
"learning_rate": 2.5842732321590034e-05,
|
| 412 |
+
"loss": 0.3991,
|
| 413 |
+
"loss_nan_ranks": 0,
|
| 414 |
+
"loss_rank_avg": 0.055257927626371384,
|
| 415 |
+
"step": 185,
|
| 416 |
+
"valid_targets_mean": 530.2,
|
| 417 |
+
"valid_targets_min": 305
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 2.4089456869009584,
|
| 421 |
+
"grad_norm": 0.5774267041450761,
|
| 422 |
+
"learning_rate": 2.499093885679642e-05,
|
| 423 |
+
"loss": 0.4022,
|
| 424 |
+
"loss_nan_ranks": 0,
|
| 425 |
+
"loss_rank_avg": 0.10308852046728134,
|
| 426 |
+
"step": 190,
|
| 427 |
+
"valid_targets_mean": 929.1,
|
| 428 |
+
"valid_targets_min": 316
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 2.472843450479233,
|
| 432 |
+
"grad_norm": 0.479806307231531,
|
| 433 |
+
"learning_rate": 2.4129375394815878e-05,
|
| 434 |
+
"loss": 0.3818,
|
| 435 |
+
"loss_nan_ranks": 0,
|
| 436 |
+
"loss_rank_avg": 0.091952383518219,
|
| 437 |
+
"step": 195,
|
| 438 |
+
"valid_targets_mean": 804.2,
|
| 439 |
+
"valid_targets_min": 280
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 2.536741214057508,
|
| 443 |
+
"grad_norm": 0.5154347190551083,
|
| 444 |
+
"learning_rate": 2.3259728486584297e-05,
|
| 445 |
+
"loss": 0.3852,
|
| 446 |
+
"loss_nan_ranks": 0,
|
| 447 |
+
"loss_rank_avg": 0.0646277368068695,
|
| 448 |
+
"step": 200,
|
| 449 |
+
"valid_targets_mean": 886.0,
|
| 450 |
+
"valid_targets_min": 252
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 2.600638977635783,
|
| 454 |
+
"grad_norm": 0.5564248322608677,
|
| 455 |
+
"learning_rate": 2.2383700506763204e-05,
|
| 456 |
+
"loss": 0.3881,
|
| 457 |
+
"loss_nan_ranks": 0,
|
| 458 |
+
"loss_rank_avg": 0.11787280440330505,
|
| 459 |
+
"step": 205,
|
| 460 |
+
"valid_targets_mean": 1338.1,
|
| 461 |
+
"valid_targets_min": 297
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 2.6645367412140573,
|
| 465 |
+
"grad_norm": 0.5649358970314645,
|
| 466 |
+
"learning_rate": 2.150300632126142e-05,
|
| 467 |
+
"loss": 0.3927,
|
| 468 |
+
"loss_nan_ranks": 0,
|
| 469 |
+
"loss_rank_avg": 0.12201130390167236,
|
| 470 |
+
"step": 210,
|
| 471 |
+
"valid_targets_mean": 950.6,
|
| 472 |
+
"valid_targets_min": 252
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 2.7284345047923324,
|
| 476 |
+
"grad_norm": 0.5505603589241066,
|
| 477 |
+
"learning_rate": 2.061936993030451e-05,
|
| 478 |
+
"loss": 0.399,
|
| 479 |
+
"loss_nan_ranks": 0,
|
| 480 |
+
"loss_rank_avg": 0.08587691932916641,
|
| 481 |
+
"step": 215,
|
| 482 |
+
"valid_targets_mean": 673.4,
|
| 483 |
+
"valid_targets_min": 252
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 2.792332268370607,
|
| 487 |
+
"grad_norm": 0.469281232216392,
|
| 488 |
+
"learning_rate": 1.9734521093623388e-05,
|
| 489 |
+
"loss": 0.3841,
|
| 490 |
+
"loss_nan_ranks": 0,
|
| 491 |
+
"loss_rank_avg": 0.06283603608608246,
|
| 492 |
+
"step": 220,
|
| 493 |
+
"valid_targets_mean": 534.2,
|
| 494 |
+
"valid_targets_min": 276
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 2.856230031948882,
|
| 498 |
+
"grad_norm": 0.45045003545833173,
|
| 499 |
+
"learning_rate": 1.88501919443684e-05,
|
| 500 |
+
"loss": 0.3793,
|
| 501 |
+
"loss_nan_ranks": 0,
|
| 502 |
+
"loss_rank_avg": 0.06877297163009644,
|
| 503 |
+
"step": 225,
|
| 504 |
+
"valid_targets_mean": 800.3,
|
| 505 |
+
"valid_targets_min": 321
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 2.9201277955271565,
|
| 509 |
+
"grad_norm": 0.5542115698623601,
|
| 510 |
+
"learning_rate": 1.7968113598377356e-05,
|
| 511 |
+
"loss": 0.3919,
|
| 512 |
+
"loss_nan_ranks": 0,
|
| 513 |
+
"loss_rank_avg": 0.09367597103118896,
|
| 514 |
+
"step": 230,
|
| 515 |
+
"valid_targets_mean": 828.5,
|
| 516 |
+
"valid_targets_min": 296
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 2.984025559105431,
|
| 520 |
+
"grad_norm": 0.49115940004120073,
|
| 521 |
+
"learning_rate": 1.7090012765434974e-05,
|
| 522 |
+
"loss": 0.3732,
|
| 523 |
+
"loss_nan_ranks": 0,
|
| 524 |
+
"loss_rank_avg": 0.11718938499689102,
|
| 525 |
+
"step": 235,
|
| 526 |
+
"valid_targets_mean": 1134.6,
|
| 527 |
+
"valid_targets_min": 308
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 3.038338658146965,
|
| 531 |
+
"grad_norm": 0.4961661446091427,
|
| 532 |
+
"learning_rate": 1.6217608369157417e-05,
|
| 533 |
+
"loss": 0.3711,
|
| 534 |
+
"loss_nan_ranks": 0,
|
| 535 |
+
"loss_rank_avg": 0.08628679066896439,
|
| 536 |
+
"step": 240,
|
| 537 |
+
"valid_targets_mean": 897.1,
|
| 538 |
+
"valid_targets_min": 237
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 3.1022364217252396,
|
| 542 |
+
"grad_norm": 0.5625252307584591,
|
| 543 |
+
"learning_rate": 1.5352608182118546e-05,
|
| 544 |
+
"loss": 0.3657,
|
| 545 |
+
"loss_nan_ranks": 0,
|
| 546 |
+
"loss_rank_avg": 0.06718944013118744,
|
| 547 |
+
"step": 245,
|
| 548 |
+
"valid_targets_mean": 688.9,
|
| 549 |
+
"valid_targets_min": 284
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 3.1661341853035143,
|
| 553 |
+
"grad_norm": 0.4117092500450208,
|
| 554 |
+
"learning_rate": 1.4496705482804943e-05,
|
| 555 |
+
"loss": 0.3412,
|
| 556 |
+
"loss_nan_ranks": 0,
|
| 557 |
+
"loss_rank_avg": 0.1296251118183136,
|
| 558 |
+
"step": 250,
|
| 559 |
+
"valid_targets_mean": 2417.2,
|
| 560 |
+
"valid_targets_min": 294
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 3.230031948881789,
|
| 564 |
+
"grad_norm": 0.5603253153383934,
|
| 565 |
+
"learning_rate": 1.3651575740943746e-05,
|
| 566 |
+
"loss": 0.3666,
|
| 567 |
+
"loss_nan_ranks": 0,
|
| 568 |
+
"loss_rank_avg": 0.09331008791923523,
|
| 569 |
+
"step": 255,
|
| 570 |
+
"valid_targets_mean": 751.1,
|
| 571 |
+
"valid_targets_min": 316
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 3.2939297124600637,
|
| 575 |
+
"grad_norm": 0.7801650462926311,
|
| 576 |
+
"learning_rate": 1.2818873337691993e-05,
|
| 577 |
+
"loss": 0.3751,
|
| 578 |
+
"loss_nan_ranks": 0,
|
| 579 |
+
"loss_rank_avg": 0.11444778740406036,
|
| 580 |
+
"step": 260,
|
| 581 |
+
"valid_targets_mean": 1448.1,
|
| 582 |
+
"valid_targets_min": 299
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 3.357827476038339,
|
| 586 |
+
"grad_norm": 0.5521691390101056,
|
| 587 |
+
"learning_rate": 1.2000228327107787e-05,
|
| 588 |
+
"loss": 0.3589,
|
| 589 |
+
"loss_nan_ranks": 0,
|
| 590 |
+
"loss_rank_avg": 0.10444329679012299,
|
| 591 |
+
"step": 265,
|
| 592 |
+
"valid_targets_mean": 1164.5,
|
| 593 |
+
"valid_targets_min": 313
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 3.4217252396166136,
|
| 597 |
+
"grad_norm": 0.5174902722351483,
|
| 598 |
+
"learning_rate": 1.1197243245242978e-05,
|
| 599 |
+
"loss": 0.3957,
|
| 600 |
+
"loss_nan_ranks": 0,
|
| 601 |
+
"loss_rank_avg": 0.11329581588506699,
|
| 602 |
+
"step": 270,
|
| 603 |
+
"valid_targets_mean": 934.5,
|
| 604 |
+
"valid_targets_min": 252
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 3.4856230031948883,
|
| 608 |
+
"grad_norm": 0.381664416110785,
|
| 609 |
+
"learning_rate": 1.0411489973103525e-05,
|
| 610 |
+
"loss": 0.3787,
|
| 611 |
+
"loss_nan_ranks": 0,
|
| 612 |
+
"loss_rank_avg": 0.08905354142189026,
|
| 613 |
+
"step": 275,
|
| 614 |
+
"valid_targets_mean": 1839.3,
|
| 615 |
+
"valid_targets_min": 309
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 3.549520766773163,
|
| 619 |
+
"grad_norm": 0.4441706360203761,
|
| 620 |
+
"learning_rate": 9.64450665961866e-06,
|
| 621 |
+
"loss": 0.3718,
|
| 622 |
+
"loss_nan_ranks": 0,
|
| 623 |
+
"loss_rank_avg": 0.09643789380788803,
|
| 624 |
+
"step": 280,
|
| 625 |
+
"valid_targets_mean": 1026.9,
|
| 626 |
+
"valid_targets_min": 254
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 3.6134185303514377,
|
| 630 |
+
"grad_norm": 0.6803653208497206,
|
| 631 |
+
"learning_rate": 8.897794710642098e-06,
|
| 632 |
+
"loss": 0.4002,
|
| 633 |
+
"loss_nan_ranks": 0,
|
| 634 |
+
"loss_rank_avg": 0.10784462839365005,
|
| 635 |
+
"step": 285,
|
| 636 |
+
"valid_targets_mean": 679.8,
|
| 637 |
+
"valid_targets_min": 246
|
| 638 |
+
},
|
| 639 |
+
{
|
| 640 |
+
"epoch": 3.6773162939297124,
|
| 641 |
+
"grad_norm": 0.48185624970132773,
|
| 642 |
+
"learning_rate": 8.172815849879607e-06,
|
| 643 |
+
"loss": 0.3588,
|
| 644 |
+
"loss_nan_ranks": 0,
|
| 645 |
+
"loss_rank_avg": 0.09011870622634888,
|
| 646 |
+
"step": 290,
|
| 647 |
+
"valid_targets_mean": 1201.2,
|
| 648 |
+
"valid_targets_min": 315
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 3.741214057507987,
|
| 652 |
+
"grad_norm": 0.46147197176222315,
|
| 653 |
+
"learning_rate": 7.470989257496164e-06,
|
| 654 |
+
"loss": 0.36,
|
| 655 |
+
"loss_nan_ranks": 0,
|
| 656 |
+
"loss_rank_avg": 0.11226803064346313,
|
| 657 |
+
"step": 295,
|
| 658 |
+
"valid_targets_mean": 1546.2,
|
| 659 |
+
"valid_targets_min": 278
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 3.8051118210862622,
|
| 663 |
+
"grad_norm": 0.4881382276211086,
|
| 664 |
+
"learning_rate": 6.7936887920041825e-06,
|
| 665 |
+
"loss": 0.3843,
|
| 666 |
+
"loss_nan_ranks": 0,
|
| 667 |
+
"loss_rank_avg": 0.05719579756259918,
|
| 668 |
+
"step": 300,
|
| 669 |
+
"valid_targets_mean": 578.7,
|
| 670 |
+
"valid_targets_min": 289
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 3.8690095846645365,
|
| 674 |
+
"grad_norm": 0.5220486930264989,
|
| 675 |
+
"learning_rate": 6.1422403008709255e-06,
|
| 676 |
+
"loss": 0.3565,
|
| 677 |
+
"loss_nan_ranks": 0,
|
| 678 |
+
"loss_rank_avg": 0.10710662603378296,
|
| 679 |
+
"step": 305,
|
| 680 |
+
"valid_targets_mean": 1408.2,
|
| 681 |
+
"valid_targets_min": 253
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 3.9329073482428116,
|
| 685 |
+
"grad_norm": 0.6996611027064502,
|
| 686 |
+
"learning_rate": 5.517919025109839e-06,
|
| 687 |
+
"loss": 0.3677,
|
| 688 |
+
"loss_nan_ranks": 0,
|
| 689 |
+
"loss_rank_avg": 0.06878411769866943,
|
| 690 |
+
"step": 310,
|
| 691 |
+
"valid_targets_mean": 634.9,
|
| 692 |
+
"valid_targets_min": 216
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 3.9968051118210863,
|
| 696 |
+
"grad_norm": 0.6104117917798728,
|
| 697 |
+
"learning_rate": 4.921947102936388e-06,
|
| 698 |
+
"loss": 0.375,
|
| 699 |
+
"loss_nan_ranks": 0,
|
| 700 |
+
"loss_rank_avg": 0.06509823352098465,
|
| 701 |
+
"step": 315,
|
| 702 |
+
"valid_targets_mean": 438.2,
|
| 703 |
+
"valid_targets_min": 296
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 4.05111821086262,
|
| 707 |
+
"grad_norm": 0.4993863760440147,
|
| 708 |
+
"learning_rate": 4.3554911773751e-06,
|
| 709 |
+
"loss": 0.376,
|
| 710 |
+
"loss_nan_ranks": 0,
|
| 711 |
+
"loss_rank_avg": 0.09259297698736191,
|
| 712 |
+
"step": 320,
|
| 713 |
+
"valid_targets_mean": 1178.0,
|
| 714 |
+
"valid_targets_min": 271
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 4.115015974440895,
|
| 718 |
+
"grad_norm": 0.627230044261856,
|
| 719 |
+
"learning_rate": 3.819660112501053e-06,
|
| 720 |
+
"loss": 0.3523,
|
| 721 |
+
"loss_nan_ranks": 0,
|
| 722 |
+
"loss_rank_avg": 0.10122501105070114,
|
| 723 |
+
"step": 325,
|
| 724 |
+
"valid_targets_mean": 764.9,
|
| 725 |
+
"valid_targets_min": 277
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 4.178913738019169,
|
| 729 |
+
"grad_norm": 0.5009958845944742,
|
| 730 |
+
"learning_rate": 3.315502822786407e-06,
|
| 731 |
+
"loss": 0.3492,
|
| 732 |
+
"loss_nan_ranks": 0,
|
| 733 |
+
"loss_rank_avg": 0.11668196320533752,
|
| 734 |
+
"step": 330,
|
| 735 |
+
"valid_targets_mean": 1165.8,
|
| 736 |
+
"valid_targets_min": 246
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 4.242811501597444,
|
| 740 |
+
"grad_norm": 0.5779680870195052,
|
| 741 |
+
"learning_rate": 2.8440062198010187e-06,
|
| 742 |
+
"loss": 0.3539,
|
| 743 |
+
"loss_nan_ranks": 0,
|
| 744 |
+
"loss_rank_avg": 0.11113809794187546,
|
| 745 |
+
"step": 335,
|
| 746 |
+
"valid_targets_mean": 1176.1,
|
| 747 |
+
"valid_targets_min": 269
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 4.306709265175719,
|
| 751 |
+
"grad_norm": 0.49187096474479775,
|
| 752 |
+
"learning_rate": 2.4060932802867498e-06,
|
| 753 |
+
"loss": 0.3854,
|
| 754 |
+
"loss_nan_ranks": 0,
|
| 755 |
+
"loss_rank_avg": 0.10995353758335114,
|
| 756 |
+
"step": 340,
|
| 757 |
+
"valid_targets_mean": 1489.2,
|
| 758 |
+
"valid_targets_min": 294
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 4.3706070287539935,
|
| 762 |
+
"grad_norm": 0.42913487565196407,
|
| 763 |
+
"learning_rate": 2.0026212393871057e-06,
|
| 764 |
+
"loss": 0.3525,
|
| 765 |
+
"loss_nan_ranks": 0,
|
| 766 |
+
"loss_rank_avg": 0.06569594889879227,
|
| 767 |
+
"step": 345,
|
| 768 |
+
"valid_targets_mean": 976.4,
|
| 769 |
+
"valid_targets_min": 332
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 4.434504792332269,
|
| 773 |
+
"grad_norm": 0.45716132082829014,
|
| 774 |
+
"learning_rate": 1.6343799125692194e-06,
|
| 775 |
+
"loss": 0.36,
|
| 776 |
+
"loss_nan_ranks": 0,
|
| 777 |
+
"loss_rank_avg": 0.10210828483104706,
|
| 778 |
+
"step": 350,
|
| 779 |
+
"valid_targets_mean": 1301.8,
|
| 780 |
+
"valid_targets_min": 252
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 4.498402555910543,
|
| 784 |
+
"grad_norm": 0.5603523568813122,
|
| 785 |
+
"learning_rate": 1.3020901495229632e-06,
|
| 786 |
+
"loss": 0.3535,
|
| 787 |
+
"loss_nan_ranks": 0,
|
| 788 |
+
"loss_rank_avg": 0.10452935099601746,
|
| 789 |
+
"step": 355,
|
| 790 |
+
"valid_targets_mean": 781.4,
|
| 791 |
+
"valid_targets_min": 341
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 4.562300319488818,
|
| 795 |
+
"grad_norm": 0.45113711082486735,
|
| 796 |
+
"learning_rate": 1.0064024230638547e-06,
|
| 797 |
+
"loss": 0.3647,
|
| 798 |
+
"loss_nan_ranks": 0,
|
| 799 |
+
"loss_rank_avg": 0.09068584442138672,
|
| 800 |
+
"step": 360,
|
| 801 |
+
"valid_targets_mean": 1382.1,
|
| 802 |
+
"valid_targets_min": 256
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 4.626198083067092,
|
| 806 |
+
"grad_norm": 0.48953575156113116,
|
| 807 |
+
"learning_rate": 7.478955558019408e-07,
|
| 808 |
+
"loss": 0.3627,
|
| 809 |
+
"loss_nan_ranks": 0,
|
| 810 |
+
"loss_rank_avg": 0.05830701068043709,
|
| 811 |
+
"step": 365,
|
| 812 |
+
"valid_targets_mean": 534.4,
|
| 813 |
+
"valid_targets_min": 267
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 4.6900958466453675,
|
| 817 |
+
"grad_norm": 0.5577785282531451,
|
| 818 |
+
"learning_rate": 5.270755870693877e-07,
|
| 819 |
+
"loss": 0.388,
|
| 820 |
+
"loss_nan_ranks": 0,
|
| 821 |
+
"loss_rank_avg": 0.082918182015419,
|
| 822 |
+
"step": 370,
|
| 823 |
+
"valid_targets_mean": 801.8,
|
| 824 |
+
"valid_targets_min": 248
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 4.753993610223642,
|
| 828 |
+
"grad_norm": 0.4818208004744513,
|
| 829 |
+
"learning_rate": 3.4437478232470123e-07,
|
| 830 |
+
"loss": 0.3584,
|
| 831 |
+
"loss_nan_ranks": 0,
|
| 832 |
+
"loss_rank_avg": 0.11186303198337555,
|
| 833 |
+
"step": 375,
|
| 834 |
+
"valid_targets_mean": 1315.8,
|
| 835 |
+
"valid_targets_min": 298
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 4.817891373801917,
|
| 839 |
+
"grad_norm": 0.5100939365357313,
|
| 840 |
+
"learning_rate": 2.0015078697281477e-07,
|
| 841 |
+
"loss": 0.3613,
|
| 842 |
+
"loss_nan_ranks": 0,
|
| 843 |
+
"loss_rank_avg": 0.11327642947435379,
|
| 844 |
+
"step": 380,
|
| 845 |
+
"valid_targets_mean": 1227.6,
|
| 846 |
+
"valid_targets_min": 319
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 4.881789137380192,
|
| 850 |
+
"grad_norm": 0.48308223541051,
|
| 851 |
+
"learning_rate": 9.46859262573896e-08,
|
| 852 |
+
"loss": 0.3721,
|
| 853 |
+
"loss_nan_ranks": 0,
|
| 854 |
+
"loss_rank_avg": 0.10510426759719849,
|
| 855 |
+
"step": 385,
|
| 856 |
+
"valid_targets_mean": 1129.6,
|
| 857 |
+
"valid_targets_min": 291
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 4.945686900958466,
|
| 861 |
+
"grad_norm": 0.4428115820847821,
|
| 862 |
+
"learning_rate": 2.8186652595918464e-08,
|
| 863 |
+
"loss": 0.3623,
|
| 864 |
+
"loss_nan_ranks": 0,
|
| 865 |
+
"loss_rank_avg": 0.06555093824863434,
|
| 866 |
+
"step": 390,
|
| 867 |
+
"valid_targets_mean": 938.8,
|
| 868 |
+
"valid_targets_min": 316
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 5.0,
|
| 872 |
+
"grad_norm": 1.0632772814975506,
|
| 873 |
+
"learning_rate": 7.831414393999481e-10,
|
| 874 |
+
"loss": 0.3816,
|
| 875 |
+
"loss_nan_ranks": 0,
|
| 876 |
+
"loss_rank_avg": 0.3953709602355957,
|
| 877 |
+
"step": 395,
|
| 878 |
+
"valid_targets_mean": 898.1,
|
| 879 |
+
"valid_targets_min": 349
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 5.0,
|
| 883 |
+
"loss_nan_ranks": 0,
|
| 884 |
+
"loss_rank_avg": 0.3953709602355957,
|
| 885 |
+
"step": 395,
|
| 886 |
+
"total_flos": 1.835207408620667e+17,
|
| 887 |
+
"train_loss": 0.4235323069970819,
|
| 888 |
+
"train_runtime": 5221.6885,
|
| 889 |
+
"train_samples_per_second": 4.788,
|
| 890 |
+
"train_steps_per_second": 0.076,
|
| 891 |
+
"valid_targets_mean": 898.1,
|
| 892 |
+
"valid_targets_min": 349
|
| 893 |
+
}
|
| 894 |
+
],
|
| 895 |
+
"logging_steps": 5,
|
| 896 |
+
"max_steps": 395,
|
| 897 |
+
"num_input_tokens_seen": 0,
|
| 898 |
+
"num_train_epochs": 5,
|
| 899 |
+
"save_steps": 500,
|
| 900 |
+
"stateful_callbacks": {
|
| 901 |
+
"TrainerControl": {
|
| 902 |
+
"args": {
|
| 903 |
+
"should_epoch_stop": false,
|
| 904 |
+
"should_evaluate": false,
|
| 905 |
+
"should_log": false,
|
| 906 |
+
"should_save": false,
|
| 907 |
+
"should_training_stop": false
|
| 908 |
+
},
|
| 909 |
+
"attributes": {}
|
| 910 |
+
}
|
| 911 |
+
},
|
| 912 |
+
"total_flos": 1.835207408620667e+17,
|
| 913 |
+
"train_batch_size": 1,
|
| 914 |
+
"trial_name": null,
|
| 915 |
+
"trial_params": null
|
| 916 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f006f6902b2d692f208aa05bb7b56caf60add0873e8d8270275fe82d25abfde3
|
| 3 |
+
size 8529
|
training_loss.png
ADDED
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|