hf-reset commited on
Commit ·
4534ab6
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 +158 -0
- trainer_state.json +1774 -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: bash_textbook_tasks_traces
|
| 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 |
+
# bash_textbook_tasks_traces
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on the DCAgent/bash_textbook_tasks_traces 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": 4.616871406366803,
|
| 3 |
+
"achieved_tflops_per_gpu_theoretical": 162.61941901551205,
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"loss_nan_ranks": 0,
|
| 6 |
+
"loss_rank_avg": 0.38632673025131226,
|
| 7 |
+
"mfu_percent": 0.3262806647609048,
|
| 8 |
+
"mfu_percent_theoretical": 11.49253844632594,
|
| 9 |
+
"total_flos": 1.2145665807220736e+18,
|
| 10 |
+
"train_loss": 0.4196553195358082,
|
| 11 |
+
"train_runtime": 16441.9592,
|
| 12 |
+
"train_samples_per_second": 3.04,
|
| 13 |
+
"train_steps_per_second": 0.048,
|
| 14 |
+
"valid_targets_mean": 3155.6,
|
| 15 |
+
"valid_targets_min": 917
|
| 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:b4fea3ad425a210b5094698622562a4c7feafa0c4dc5489ec439ed42bbde0474
|
| 3 |
+
size 4902257696
|
model-00002-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8bafb37eab9eaddeea26a7942bf2e453482e768c35161b3c4a6c000c105436fa
|
| 3 |
+
size 4915960368
|
model-00003-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:05815b7612aa39277cdcabbe7d730cbe71b57da6ac0e18d0c7ed36f9347734bf
|
| 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:e7fc0c641e4df1327ecd8f0dee796830bdcd3c22f3b29e25c83c8800d2c5cc7e
|
| 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/bash_textbook_tasks_traces",
|
| 8 |
+
"training_type": "SFT",
|
| 9 |
+
"training_parameters": "https://huggingface.co/DCAgent/bash_textbook_tasks_traces/blob/main/config.json",
|
| 10 |
+
"wandb_link": "https://wandb.ai/dogml/dc-agent/runs/bash_textbook_tasks_traces",
|
| 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": 4.616871406366803,
|
| 3 |
+
"achieved_tflops_per_gpu_theoretical": 162.61941901551205,
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"loss_nan_ranks": 0,
|
| 6 |
+
"loss_rank_avg": 0.38632673025131226,
|
| 7 |
+
"mfu_percent": 0.3262806647609048,
|
| 8 |
+
"mfu_percent_theoretical": 11.49253844632594,
|
| 9 |
+
"total_flos": 1.2145665807220736e+18,
|
| 10 |
+
"train_loss": 0.4196553195358082,
|
| 11 |
+
"train_runtime": 16441.9592,
|
| 12 |
+
"train_samples_per_second": 3.04,
|
| 13 |
+
"train_steps_per_second": 0.048,
|
| 14 |
+
"valid_targets_mean": 3155.6,
|
| 15 |
+
"valid_targets_min": 917
|
| 16 |
+
}
|
trainer_log.jsonl
ADDED
|
@@ -0,0 +1,158 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 5, "total_steps": 785, "loss": 0.7455, "lr": 2.0253164556962026e-06, "epoch": 0.032, "percentage": 0.64, "elapsed_time": "0:02:00", "remaining_time": "5:12:59"}
|
| 2 |
+
{"current_steps": 10, "total_steps": 785, "loss": 0.7168, "lr": 4.556962025316456e-06, "epoch": 0.064, "percentage": 1.27, "elapsed_time": "0:03:53", "remaining_time": "5:01:41"}
|
| 3 |
+
{"current_steps": 15, "total_steps": 785, "loss": 0.662, "lr": 7.08860759493671e-06, "epoch": 0.096, "percentage": 1.91, "elapsed_time": "0:05:44", "remaining_time": "4:54:41"}
|
| 4 |
+
{"current_steps": 20, "total_steps": 785, "loss": 0.6259, "lr": 9.620253164556963e-06, "epoch": 0.128, "percentage": 2.55, "elapsed_time": "0:07:24", "remaining_time": "4:43:37"}
|
| 5 |
+
{"current_steps": 25, "total_steps": 785, "loss": 0.6034, "lr": 1.2151898734177216e-05, "epoch": 0.16, "percentage": 3.18, "elapsed_time": "0:09:13", "remaining_time": "4:40:29"}
|
| 6 |
+
{"current_steps": 30, "total_steps": 785, "loss": 0.5807, "lr": 1.468354430379747e-05, "epoch": 0.192, "percentage": 3.82, "elapsed_time": "0:11:00", "remaining_time": "4:36:54"}
|
| 7 |
+
{"current_steps": 35, "total_steps": 785, "loss": 0.5433, "lr": 1.7215189873417723e-05, "epoch": 0.224, "percentage": 4.46, "elapsed_time": "0:12:47", "remaining_time": "4:34:08"}
|
| 8 |
+
{"current_steps": 40, "total_steps": 785, "loss": 0.5255, "lr": 1.974683544303798e-05, "epoch": 0.256, "percentage": 5.1, "elapsed_time": "0:14:44", "remaining_time": "4:34:39"}
|
| 9 |
+
{"current_steps": 45, "total_steps": 785, "loss": 0.5254, "lr": 2.2278481012658228e-05, "epoch": 0.288, "percentage": 5.73, "elapsed_time": "0:16:34", "remaining_time": "4:32:37"}
|
| 10 |
+
{"current_steps": 50, "total_steps": 785, "loss": 0.504, "lr": 2.481012658227848e-05, "epoch": 0.32, "percentage": 6.37, "elapsed_time": "0:18:23", "remaining_time": "4:30:21"}
|
| 11 |
+
{"current_steps": 55, "total_steps": 785, "loss": 0.5226, "lr": 2.7341772151898737e-05, "epoch": 0.352, "percentage": 7.01, "elapsed_time": "0:20:14", "remaining_time": "4:28:35"}
|
| 12 |
+
{"current_steps": 60, "total_steps": 785, "loss": 0.4865, "lr": 2.987341772151899e-05, "epoch": 0.384, "percentage": 7.64, "elapsed_time": "0:22:07", "remaining_time": "4:27:16"}
|
| 13 |
+
{"current_steps": 65, "total_steps": 785, "loss": 0.484, "lr": 3.240506329113924e-05, "epoch": 0.416, "percentage": 8.28, "elapsed_time": "0:23:49", "remaining_time": "4:23:50"}
|
| 14 |
+
{"current_steps": 70, "total_steps": 785, "loss": 0.4681, "lr": 3.49367088607595e-05, "epoch": 0.448, "percentage": 8.92, "elapsed_time": "0:25:40", "remaining_time": "4:22:11"}
|
| 15 |
+
{"current_steps": 75, "total_steps": 785, "loss": 0.474, "lr": 3.746835443037975e-05, "epoch": 0.48, "percentage": 9.55, "elapsed_time": "0:27:24", "remaining_time": "4:19:31"}
|
| 16 |
+
{"current_steps": 80, "total_steps": 785, "loss": 0.4638, "lr": 4e-05, "epoch": 0.512, "percentage": 10.19, "elapsed_time": "0:29:06", "remaining_time": "4:16:30"}
|
| 17 |
+
{"current_steps": 85, "total_steps": 785, "loss": 0.4739, "lr": 3.999504991751045e-05, "epoch": 0.544, "percentage": 10.83, "elapsed_time": "0:30:44", "remaining_time": "4:13:10"}
|
| 18 |
+
{"current_steps": 90, "total_steps": 785, "loss": 0.449, "lr": 3.9980202120373464e-05, "epoch": 0.576, "percentage": 11.46, "elapsed_time": "0:32:31", "remaining_time": "4:11:08"}
|
| 19 |
+
{"current_steps": 95, "total_steps": 785, "loss": 0.4557, "lr": 3.995546395837111e-05, "epoch": 0.608, "percentage": 12.1, "elapsed_time": "0:34:14", "remaining_time": "4:08:44"}
|
| 20 |
+
{"current_steps": 100, "total_steps": 785, "loss": 0.4534, "lr": 3.992084767709763e-05, "epoch": 0.64, "percentage": 12.74, "elapsed_time": "0:35:59", "remaining_time": "4:06:30"}
|
| 21 |
+
{"current_steps": 105, "total_steps": 785, "loss": 0.4602, "lr": 3.987637041189781e-05, "epoch": 0.672, "percentage": 13.38, "elapsed_time": "0:37:42", "remaining_time": "4:04:11"}
|
| 22 |
+
{"current_steps": 110, "total_steps": 785, "loss": 0.4583, "lr": 3.982205417938482e-05, "epoch": 0.704, "percentage": 14.01, "elapsed_time": "0:39:32", "remaining_time": "4:02:39"}
|
| 23 |
+
{"current_steps": 115, "total_steps": 785, "loss": 0.4453, "lr": 3.975792586654179e-05, "epoch": 0.736, "percentage": 14.65, "elapsed_time": "0:41:15", "remaining_time": "4:00:21"}
|
| 24 |
+
{"current_steps": 120, "total_steps": 785, "loss": 0.4403, "lr": 3.968401721741259e-05, "epoch": 0.768, "percentage": 15.29, "elapsed_time": "0:43:00", "remaining_time": "3:58:22"}
|
| 25 |
+
{"current_steps": 125, "total_steps": 785, "loss": 0.4448, "lr": 3.960036481738819e-05, "epoch": 0.8, "percentage": 15.92, "elapsed_time": "0:44:41", "remaining_time": "3:56:00"}
|
| 26 |
+
{"current_steps": 130, "total_steps": 785, "loss": 0.4289, "lr": 3.950701007509667e-05, "epoch": 0.832, "percentage": 16.56, "elapsed_time": "0:46:33", "remaining_time": "3:54:34"}
|
| 27 |
+
{"current_steps": 135, "total_steps": 785, "loss": 0.4476, "lr": 3.940399920190552e-05, "epoch": 0.864, "percentage": 17.2, "elapsed_time": "0:48:17", "remaining_time": "3:52:29"}
|
| 28 |
+
{"current_steps": 140, "total_steps": 785, "loss": 0.4455, "lr": 3.92913831890467e-05, "epoch": 0.896, "percentage": 17.83, "elapsed_time": "0:50:08", "remaining_time": "3:51:01"}
|
| 29 |
+
{"current_steps": 145, "total_steps": 785, "loss": 0.445, "lr": 3.916921778237556e-05, "epoch": 0.928, "percentage": 18.47, "elapsed_time": "0:51:54", "remaining_time": "3:49:04"}
|
| 30 |
+
{"current_steps": 150, "total_steps": 785, "loss": 0.4523, "lr": 3.903756345477612e-05, "epoch": 0.96, "percentage": 19.11, "elapsed_time": "0:53:32", "remaining_time": "3:46:39"}
|
| 31 |
+
{"current_steps": 155, "total_steps": 785, "loss": 0.4414, "lr": 3.889648537622657e-05, "epoch": 0.992, "percentage": 19.75, "elapsed_time": "0:55:19", "remaining_time": "3:44:53"}
|
| 32 |
+
{"current_steps": 160, "total_steps": 785, "loss": 0.4448, "lr": 3.874605338153952e-05, "epoch": 1.0192, "percentage": 20.38, "elapsed_time": "0:57:00", "remaining_time": "3:42:42"}
|
| 33 |
+
{"current_steps": 165, "total_steps": 785, "loss": 0.439, "lr": 3.8586341935793265e-05, "epoch": 1.0512, "percentage": 21.02, "elapsed_time": "0:58:44", "remaining_time": "3:40:44"}
|
| 34 |
+
{"current_steps": 170, "total_steps": 785, "loss": 0.4328, "lr": 3.841743009747089e-05, "epoch": 1.0832, "percentage": 21.66, "elapsed_time": "1:00:28", "remaining_time": "3:38:48"}
|
| 35 |
+
{"current_steps": 175, "total_steps": 785, "loss": 0.4357, "lr": 3.8239401479325714e-05, "epoch": 1.1152, "percentage": 22.29, "elapsed_time": "1:02:08", "remaining_time": "3:36:36"}
|
| 36 |
+
{"current_steps": 180, "total_steps": 785, "loss": 0.4112, "lr": 3.8052344206992276e-05, "epoch": 1.1472, "percentage": 22.93, "elapsed_time": "1:03:59", "remaining_time": "3:35:05"}
|
| 37 |
+
{"current_steps": 185, "total_steps": 785, "loss": 0.4311, "lr": 3.7856350875363396e-05, "epoch": 1.1792, "percentage": 23.57, "elapsed_time": "1:05:40", "remaining_time": "3:33:01"}
|
| 38 |
+
{"current_steps": 190, "total_steps": 785, "loss": 0.4192, "lr": 3.765151850275497e-05, "epoch": 1.2112, "percentage": 24.2, "elapsed_time": "1:07:26", "remaining_time": "3:31:12"}
|
| 39 |
+
{"current_steps": 195, "total_steps": 785, "loss": 0.4117, "lr": 3.7437948482881104e-05, "epoch": 1.2432, "percentage": 24.84, "elapsed_time": "1:09:18", "remaining_time": "3:29:41"}
|
| 40 |
+
{"current_steps": 200, "total_steps": 785, "loss": 0.4177, "lr": 3.721574653466336e-05, "epoch": 1.2752, "percentage": 25.48, "elapsed_time": "1:11:04", "remaining_time": "3:27:53"}
|
| 41 |
+
{"current_steps": 205, "total_steps": 785, "loss": 0.4233, "lr": 3.698502264989903e-05, "epoch": 1.3072, "percentage": 26.11, "elapsed_time": "1:12:47", "remaining_time": "3:25:56"}
|
| 42 |
+
{"current_steps": 210, "total_steps": 785, "loss": 0.4194, "lr": 3.674589103881432e-05, "epoch": 1.3392, "percentage": 26.75, "elapsed_time": "1:14:41", "remaining_time": "3:24:30"}
|
| 43 |
+
{"current_steps": 215, "total_steps": 785, "loss": 0.4182, "lr": 3.64984700735293e-05, "epoch": 1.3712, "percentage": 27.39, "elapsed_time": "1:16:33", "remaining_time": "3:22:59"}
|
| 44 |
+
{"current_steps": 220, "total_steps": 785, "loss": 0.4275, "lr": 3.624288222946273e-05, "epoch": 1.4032, "percentage": 28.03, "elapsed_time": "1:18:20", "remaining_time": "3:21:11"}
|
| 45 |
+
{"current_steps": 225, "total_steps": 785, "loss": 0.4232, "lr": 3.597925402470578e-05, "epoch": 1.4352, "percentage": 28.66, "elapsed_time": "1:20:08", "remaining_time": "3:19:26"}
|
| 46 |
+
{"current_steps": 230, "total_steps": 785, "loss": 0.4253, "lr": 3.570771595739445e-05, "epoch": 1.4672, "percentage": 29.3, "elapsed_time": "1:21:58", "remaining_time": "3:17:47"}
|
| 47 |
+
{"current_steps": 235, "total_steps": 785, "loss": 0.4105, "lr": 3.5428402441111964e-05, "epoch": 1.4992, "percentage": 29.94, "elapsed_time": "1:23:49", "remaining_time": "3:16:11"}
|
| 48 |
+
{"current_steps": 240, "total_steps": 785, "loss": 0.4085, "lr": 3.5141451738352936e-05, "epoch": 1.5312000000000001, "percentage": 30.57, "elapsed_time": "1:25:38", "remaining_time": "3:14:28"}
|
| 49 |
+
{"current_steps": 245, "total_steps": 785, "loss": 0.4129, "lr": 3.4847005892082266e-05, "epoch": 1.5632000000000001, "percentage": 31.21, "elapsed_time": "1:27:24", "remaining_time": "3:12:40"}
|
| 50 |
+
{"current_steps": 250, "total_steps": 785, "loss": 0.4116, "lr": 3.454521065542273e-05, "epoch": 1.5952, "percentage": 31.85, "elapsed_time": "1:29:19", "remaining_time": "3:11:09"}
|
| 51 |
+
{"current_steps": 255, "total_steps": 785, "loss": 0.4294, "lr": 3.423621541950597e-05, "epoch": 1.6272, "percentage": 32.48, "elapsed_time": "1:30:53", "remaining_time": "3:08:55"}
|
| 52 |
+
{"current_steps": 260, "total_steps": 785, "loss": 0.4269, "lr": 3.3920173139522664e-05, "epoch": 1.6592, "percentage": 33.12, "elapsed_time": "1:32:33", "remaining_time": "3:06:53"}
|
| 53 |
+
{"current_steps": 265, "total_steps": 785, "loss": 0.4164, "lr": 3.35972402590084e-05, "epoch": 1.6912, "percentage": 33.76, "elapsed_time": "1:34:20", "remaining_time": "3:05:07"}
|
| 54 |
+
{"current_steps": 270, "total_steps": 785, "loss": 0.412, "lr": 3.326757663240291e-05, "epoch": 1.7231999999999998, "percentage": 34.39, "elapsed_time": "1:36:03", "remaining_time": "3:03:13"}
|
| 55 |
+
{"current_steps": 275, "total_steps": 785, "loss": 0.4199, "lr": 3.293134544592073e-05, "epoch": 1.7551999999999999, "percentage": 35.03, "elapsed_time": "1:37:44", "remaining_time": "3:01:15"}
|
| 56 |
+
{"current_steps": 280, "total_steps": 785, "loss": 0.4151, "lr": 3.258871313677274e-05, "epoch": 1.7872, "percentage": 35.67, "elapsed_time": "1:39:28", "remaining_time": "2:59:25"}
|
| 57 |
+
{"current_steps": 285, "total_steps": 785, "loss": 0.4165, "lr": 3.2239849310778316e-05, "epoch": 1.8192, "percentage": 36.31, "elapsed_time": "1:41:13", "remaining_time": "2:57:35"}
|
| 58 |
+
{"current_steps": 290, "total_steps": 785, "loss": 0.4019, "lr": 3.188492665840909e-05, "epoch": 1.8512, "percentage": 36.94, "elapsed_time": "1:42:59", "remaining_time": "2:55:48"}
|
| 59 |
+
{"current_steps": 295, "total_steps": 785, "loss": 0.4125, "lr": 3.1524120869305726e-05, "epoch": 1.8832, "percentage": 37.58, "elapsed_time": "1:44:52", "remaining_time": "2:54:11"}
|
| 60 |
+
{"current_steps": 300, "total_steps": 785, "loss": 0.4035, "lr": 3.11576105453101e-05, "epoch": 1.9152, "percentage": 38.22, "elapsed_time": "1:46:36", "remaining_time": "2:52:20"}
|
| 61 |
+
{"current_steps": 305, "total_steps": 785, "loss": 0.4243, "lr": 3.0785577112055916e-05, "epoch": 1.9472, "percentage": 38.85, "elapsed_time": "1:48:22", "remaining_time": "2:50:32"}
|
| 62 |
+
{"current_steps": 310, "total_steps": 785, "loss": 0.4156, "lr": 3.040820472916153e-05, "epoch": 1.9792, "percentage": 39.49, "elapsed_time": "1:50:00", "remaining_time": "2:48:32"}
|
| 63 |
+
{"current_steps": 315, "total_steps": 785, "loss": 0.4175, "lr": 3.002568019906939e-05, "epoch": 2.0064, "percentage": 40.13, "elapsed_time": "1:51:36", "remaining_time": "2:46:31"}
|
| 64 |
+
{"current_steps": 320, "total_steps": 785, "loss": 0.408, "lr": 2.963819287457733e-05, "epoch": 2.0384, "percentage": 40.76, "elapsed_time": "1:53:25", "remaining_time": "2:44:49"}
|
| 65 |
+
{"current_steps": 325, "total_steps": 785, "loss": 0.4075, "lr": 2.924593456510733e-05, "epoch": 2.0704, "percentage": 41.4, "elapsed_time": "1:55:10", "remaining_time": "2:43:00"}
|
| 66 |
+
{"current_steps": 330, "total_steps": 785, "loss": 0.4052, "lr": 2.8849099441758306e-05, "epoch": 2.1024, "percentage": 42.04, "elapsed_time": "1:56:54", "remaining_time": "2:41:11"}
|
| 67 |
+
{"current_steps": 335, "total_steps": 785, "loss": 0.3929, "lr": 2.844788394118979e-05, "epoch": 2.1344, "percentage": 42.68, "elapsed_time": "1:58:46", "remaining_time": "2:39:33"}
|
| 68 |
+
{"current_steps": 340, "total_steps": 785, "loss": 0.4008, "lr": 2.8042486668384164e-05, "epoch": 2.1664, "percentage": 43.31, "elapsed_time": "2:00:28", "remaining_time": "2:37:40"}
|
| 69 |
+
{"current_steps": 345, "total_steps": 785, "loss": 0.4025, "lr": 2.7633108298335582e-05, "epoch": 2.1984, "percentage": 43.95, "elapsed_time": "2:02:07", "remaining_time": "2:35:45"}
|
| 70 |
+
{"current_steps": 350, "total_steps": 785, "loss": 0.3976, "lr": 2.721995147671416e-05, "epoch": 2.2304, "percentage": 44.59, "elapsed_time": "2:03:51", "remaining_time": "2:33:56"}
|
| 71 |
+
{"current_steps": 355, "total_steps": 785, "loss": 0.3962, "lr": 2.68032207195547e-05, "epoch": 2.2624, "percentage": 45.22, "elapsed_time": "2:05:39", "remaining_time": "2:32:12"}
|
| 72 |
+
{"current_steps": 360, "total_steps": 785, "loss": 0.398, "lr": 2.6383122312019604e-05, "epoch": 2.2944, "percentage": 45.86, "elapsed_time": "2:07:29", "remaining_time": "2:30:30"}
|
| 73 |
+
{"current_steps": 365, "total_steps": 785, "loss": 0.4117, "lr": 2.595986420628597e-05, "epoch": 2.3264, "percentage": 46.5, "elapsed_time": "2:09:23", "remaining_time": "2:28:53"}
|
| 74 |
+
{"current_steps": 370, "total_steps": 785, "loss": 0.403, "lr": 2.5533655918607573e-05, "epoch": 2.3584, "percentage": 47.13, "elapsed_time": "2:10:58", "remaining_time": "2:26:54"}
|
| 75 |
+
{"current_steps": 375, "total_steps": 785, "loss": 0.3973, "lr": 2.510470842560259e-05, "epoch": 2.3904, "percentage": 47.77, "elapsed_time": "2:12:51", "remaining_time": "2:25:15"}
|
| 76 |
+
{"current_steps": 380, "total_steps": 785, "loss": 0.4017, "lr": 2.467323405981841e-05, "epoch": 2.4224, "percentage": 48.41, "elapsed_time": "2:14:29", "remaining_time": "2:23:20"}
|
| 77 |
+
{"current_steps": 385, "total_steps": 785, "loss": 0.4033, "lr": 2.423944640462533e-05, "epoch": 2.4544, "percentage": 49.04, "elapsed_time": "2:16:09", "remaining_time": "2:21:28"}
|
| 78 |
+
{"current_steps": 390, "total_steps": 785, "loss": 0.3995, "lr": 2.3803560188490968e-05, "epoch": 2.4864, "percentage": 49.68, "elapsed_time": "2:17:51", "remaining_time": "2:19:37"}
|
| 79 |
+
{"current_steps": 395, "total_steps": 785, "loss": 0.4008, "lr": 2.336579117868789e-05, "epoch": 2.5183999999999997, "percentage": 50.32, "elapsed_time": "2:19:44", "remaining_time": "2:17:58"}
|
| 80 |
+
{"current_steps": 400, "total_steps": 785, "loss": 0.4065, "lr": 2.292635607448711e-05, "epoch": 2.5504, "percentage": 50.96, "elapsed_time": "2:21:23", "remaining_time": "2:16:05"}
|
| 81 |
+
{"current_steps": 405, "total_steps": 785, "loss": 0.409, "lr": 2.248547239989008e-05, "epoch": 2.5824, "percentage": 51.59, "elapsed_time": "2:23:07", "remaining_time": "2:14:17"}
|
| 82 |
+
{"current_steps": 410, "total_steps": 785, "loss": 0.3978, "lr": 2.204335839595255e-05, "epoch": 2.6144, "percentage": 52.23, "elapsed_time": "2:24:45", "remaining_time": "2:12:24"}
|
| 83 |
+
{"current_steps": 415, "total_steps": 785, "loss": 0.4034, "lr": 2.1600232912753452e-05, "epoch": 2.6464, "percentage": 52.87, "elapsed_time": "2:26:23", "remaining_time": "2:10:31"}
|
| 84 |
+
{"current_steps": 420, "total_steps": 785, "loss": 0.4014, "lr": 2.1156315301062293e-05, "epoch": 2.6784, "percentage": 53.5, "elapsed_time": "2:28:11", "remaining_time": "2:08:46"}
|
| 85 |
+
{"current_steps": 425, "total_steps": 785, "loss": 0.4103, "lr": 2.0711825303758712e-05, "epoch": 2.7104, "percentage": 54.14, "elapsed_time": "2:29:49", "remaining_time": "2:06:54"}
|
| 86 |
+
{"current_steps": 430, "total_steps": 785, "loss": 0.4139, "lr": 2.0266982947057962e-05, "epoch": 2.7424, "percentage": 54.78, "elapsed_time": "2:31:29", "remaining_time": "2:05:03"}
|
| 87 |
+
{"current_steps": 435, "total_steps": 785, "loss": 0.3831, "lr": 1.9822008431596083e-05, "epoch": 2.7744, "percentage": 55.41, "elapsed_time": "2:33:12", "remaining_time": "2:03:16"}
|
| 88 |
+
{"current_steps": 440, "total_steps": 785, "loss": 0.3972, "lr": 1.937712202342881e-05, "epoch": 2.8064, "percentage": 56.05, "elapsed_time": "2:34:57", "remaining_time": "2:01:30"}
|
| 89 |
+
{"current_steps": 445, "total_steps": 785, "loss": 0.387, "lr": 1.8932543944998037e-05, "epoch": 2.8384, "percentage": 56.69, "elapsed_time": "2:36:35", "remaining_time": "1:59:38"}
|
| 90 |
+
{"current_steps": 450, "total_steps": 785, "loss": 0.3901, "lr": 1.8488494266119877e-05, "epoch": 2.8704, "percentage": 57.32, "elapsed_time": "2:38:28", "remaining_time": "1:57:58"}
|
| 91 |
+
{"current_steps": 455, "total_steps": 785, "loss": 0.385, "lr": 1.804519279504834e-05, "epoch": 2.9024, "percentage": 57.96, "elapsed_time": "2:40:15", "remaining_time": "1:56:13"}
|
| 92 |
+
{"current_steps": 460, "total_steps": 785, "loss": 0.393, "lr": 1.7602858969668365e-05, "epoch": 2.9344, "percentage": 58.6, "elapsed_time": "2:42:01", "remaining_time": "1:54:28"}
|
| 93 |
+
{"current_steps": 465, "total_steps": 785, "loss": 0.3972, "lr": 1.716171174887231e-05, "epoch": 2.9664, "percentage": 59.24, "elapsed_time": "2:43:48", "remaining_time": "1:52:43"}
|
| 94 |
+
{"current_steps": 470, "total_steps": 785, "loss": 0.3914, "lr": 1.6721969504173484e-05, "epoch": 2.9984, "percentage": 59.87, "elapsed_time": "2:45:34", "remaining_time": "1:50:58"}
|
| 95 |
+
{"current_steps": 475, "total_steps": 785, "loss": 0.3797, "lr": 1.628384991161041e-05, "epoch": 3.0256, "percentage": 60.51, "elapsed_time": "2:47:02", "remaining_time": "1:49:00"}
|
| 96 |
+
{"current_steps": 480, "total_steps": 785, "loss": 0.3778, "lr": 1.5847569843995452e-05, "epoch": 3.0576, "percentage": 61.15, "elapsed_time": "2:48:49", "remaining_time": "1:47:16"}
|
| 97 |
+
{"current_steps": 485, "total_steps": 785, "loss": 0.3819, "lr": 1.5413345263560922e-05, "epoch": 3.0896, "percentage": 61.78, "elapsed_time": "2:50:32", "remaining_time": "1:45:29"}
|
| 98 |
+
{"current_steps": 490, "total_steps": 785, "loss": 0.3906, "lr": 1.4981391115056032e-05, "epoch": 3.1216, "percentage": 62.42, "elapsed_time": "2:52:13", "remaining_time": "1:43:41"}
|
| 99 |
+
{"current_steps": 495, "total_steps": 785, "loss": 0.3897, "lr": 1.455192121934748e-05, "epoch": 3.1536, "percentage": 63.06, "elapsed_time": "2:53:59", "remaining_time": "1:41:56"}
|
| 100 |
+
{"current_steps": 500, "total_steps": 785, "loss": 0.3974, "lr": 1.4125148167576303e-05, "epoch": 3.1856, "percentage": 63.69, "elapsed_time": "2:55:39", "remaining_time": "1:40:07"}
|
| 101 |
+
{"current_steps": 505, "total_steps": 785, "loss": 0.3858, "lr": 1.3701283215923563e-05, "epoch": 3.2176, "percentage": 64.33, "elapsed_time": "2:57:21", "remaining_time": "1:38:20"}
|
| 102 |
+
{"current_steps": 510, "total_steps": 785, "loss": 0.3903, "lr": 1.328053618103677e-05, "epoch": 3.2496, "percentage": 64.97, "elapsed_time": "2:58:58", "remaining_time": "1:36:30"}
|
| 103 |
+
{"current_steps": 515, "total_steps": 785, "loss": 0.3861, "lr": 1.2863115336168916e-05, "epoch": 3.2816, "percentage": 65.61, "elapsed_time": "3:00:41", "remaining_time": "1:34:43"}
|
| 104 |
+
{"current_steps": 520, "total_steps": 785, "loss": 0.3945, "lr": 1.2449227308081509e-05, "epoch": 3.3136, "percentage": 66.24, "elapsed_time": "3:02:36", "remaining_time": "1:33:03"}
|
| 105 |
+
{"current_steps": 525, "total_steps": 785, "loss": 0.3951, "lr": 1.2039076974762587e-05, "epoch": 3.3456, "percentage": 66.88, "elapsed_time": "3:04:18", "remaining_time": "1:31:16"}
|
| 106 |
+
{"current_steps": 530, "total_steps": 785, "loss": 0.3829, "lr": 1.163286736401044e-05, "epoch": 3.3776, "percentage": 67.52, "elapsed_time": "3:06:08", "remaining_time": "1:29:33"}
|
| 107 |
+
{"current_steps": 535, "total_steps": 785, "loss": 0.4, "lr": 1.123079955293322e-05, "epoch": 3.4096, "percentage": 68.15, "elapsed_time": "3:07:57", "remaining_time": "1:27:49"}
|
| 108 |
+
{"current_steps": 540, "total_steps": 785, "loss": 0.3952, "lr": 1.0833072568414037e-05, "epoch": 3.4416, "percentage": 68.79, "elapsed_time": "3:09:40", "remaining_time": "1:26:03"}
|
| 109 |
+
{"current_steps": 545, "total_steps": 785, "loss": 0.3903, "lr": 1.0439883288591057e-05, "epoch": 3.4736000000000002, "percentage": 69.43, "elapsed_time": "3:11:27", "remaining_time": "1:24:18"}
|
| 110 |
+
{"current_steps": 550, "total_steps": 785, "loss": 0.3785, "lr": 1.0051426345401202e-05, "epoch": 3.5056000000000003, "percentage": 70.06, "elapsed_time": "3:13:10", "remaining_time": "1:22:32"}
|
| 111 |
+
{"current_steps": 555, "total_steps": 785, "loss": 0.3901, "lr": 9.667894028235704e-06, "epoch": 3.5376, "percentage": 70.7, "elapsed_time": "3:14:52", "remaining_time": "1:20:45"}
|
| 112 |
+
{"current_steps": 560, "total_steps": 785, "loss": 0.3911, "lr": 9.289476188755315e-06, "epoch": 3.5696, "percentage": 71.34, "elapsed_time": "3:16:31", "remaining_time": "1:18:57"}
|
| 113 |
+
{"current_steps": 565, "total_steps": 785, "loss": 0.3873, "lr": 8.916360146912122e-06, "epoch": 3.6016, "percentage": 71.97, "elapsed_time": "3:18:13", "remaining_time": "1:17:11"}
|
| 114 |
+
{"current_steps": 570, "total_steps": 785, "loss": 0.3994, "lr": 8.548730598224646e-06, "epoch": 3.6336, "percentage": 72.61, "elapsed_time": "3:20:02", "remaining_time": "1:15:27"}
|
| 115 |
+
{"current_steps": 575, "total_steps": 785, "loss": 0.388, "lr": 8.186769522352053e-06, "epoch": 3.6656, "percentage": 73.25, "elapsed_time": "3:21:50", "remaining_time": "1:13:42"}
|
| 116 |
+
{"current_steps": 580, "total_steps": 785, "loss": 0.3811, "lr": 7.830656093012714e-06, "epoch": 3.6976, "percentage": 73.89, "elapsed_time": "3:23:37", "remaining_time": "1:11:58"}
|
| 117 |
+
{"current_steps": 585, "total_steps": 785, "loss": 0.3869, "lr": 7.480566589291696e-06, "epoch": 3.7296, "percentage": 74.52, "elapsed_time": "3:25:20", "remaining_time": "1:10:12"}
|
| 118 |
+
{"current_steps": 590, "total_steps": 785, "loss": 0.3931, "lr": 7.1366743083812285e-06, "epoch": 3.7616, "percentage": 75.16, "elapsed_time": "3:27:03", "remaining_time": "1:08:26"}
|
| 119 |
+
{"current_steps": 595, "total_steps": 785, "loss": 0.3869, "lr": 6.799149479797101e-06, "epoch": 3.7936, "percentage": 75.8, "elapsed_time": "3:28:51", "remaining_time": "1:06:41"}
|
| 120 |
+
{"current_steps": 600, "total_steps": 785, "loss": 0.3867, "lr": 6.4681591811137e-06, "epoch": 3.8256, "percentage": 76.43, "elapsed_time": "3:30:39", "remaining_time": "1:04:57"}
|
| 121 |
+
{"current_steps": 605, "total_steps": 785, "loss": 0.3822, "lr": 6.143867255259197e-06, "epoch": 3.8576, "percentage": 77.07, "elapsed_time": "3:32:21", "remaining_time": "1:03:10"}
|
| 122 |
+
{"current_steps": 610, "total_steps": 785, "loss": 0.3958, "lr": 5.8264342294119504e-06, "epoch": 3.8895999999999997, "percentage": 77.71, "elapsed_time": "3:33:57", "remaining_time": "1:01:22"}
|
| 123 |
+
{"current_steps": 615, "total_steps": 785, "loss": 0.4026, "lr": 5.516017235538258e-06, "epoch": 3.9215999999999998, "percentage": 78.34, "elapsed_time": "3:35:41", "remaining_time": "0:59:37"}
|
| 124 |
+
{"current_steps": 620, "total_steps": 785, "loss": 0.3881, "lr": 5.212769932610695e-06, "epoch": 3.9536, "percentage": 78.98, "elapsed_time": "3:37:27", "remaining_time": "0:57:52"}
|
| 125 |
+
{"current_steps": 625, "total_steps": 785, "loss": 0.3854, "lr": 4.916842430545681e-06, "epoch": 3.9856, "percentage": 79.62, "elapsed_time": "3:39:19", "remaining_time": "0:56:08"}
|
| 126 |
+
{"current_steps": 630, "total_steps": 785, "loss": 0.3935, "lr": 4.628381215897837e-06, "epoch": 4.0128, "percentage": 80.25, "elapsed_time": "3:40:34", "remaining_time": "0:54:16"}
|
| 127 |
+
{"current_steps": 635, "total_steps": 785, "loss": 0.3818, "lr": 4.347529079347914e-06, "epoch": 4.0448, "percentage": 80.89, "elapsed_time": "3:42:22", "remaining_time": "0:52:31"}
|
| 128 |
+
{"current_steps": 640, "total_steps": 785, "loss": 0.3879, "lr": 4.074425045020247e-06, "epoch": 4.0768, "percentage": 81.53, "elapsed_time": "3:44:09", "remaining_time": "0:50:47"}
|
| 129 |
+
{"current_steps": 645, "total_steps": 785, "loss": 0.3898, "lr": 3.8092043016646487e-06, "epoch": 4.1088, "percentage": 82.17, "elapsed_time": "3:45:54", "remaining_time": "0:49:02"}
|
| 130 |
+
{"current_steps": 650, "total_steps": 785, "loss": 0.3895, "lr": 3.551998135736867e-06, "epoch": 4.1408, "percentage": 82.8, "elapsed_time": "3:47:44", "remaining_time": "0:47:18"}
|
| 131 |
+
{"current_steps": 655, "total_steps": 785, "loss": 0.3711, "lr": 3.3029338664107267e-06, "epoch": 4.1728, "percentage": 83.44, "elapsed_time": "3:49:29", "remaining_time": "0:45:32"}
|
| 132 |
+
{"current_steps": 660, "total_steps": 785, "loss": 0.391, "lr": 3.0621347825540625e-06, "epoch": 4.2048, "percentage": 84.08, "elapsed_time": "3:51:14", "remaining_time": "0:43:47"}
|
| 133 |
+
{"current_steps": 665, "total_steps": 785, "loss": 0.3869, "lr": 2.8297200816997183e-06, "epoch": 4.2368, "percentage": 84.71, "elapsed_time": "3:52:53", "remaining_time": "0:42:01"}
|
| 134 |
+
{"current_steps": 670, "total_steps": 785, "loss": 0.3807, "lr": 2.605804811041803e-06, "epoch": 4.2688, "percentage": 85.35, "elapsed_time": "3:54:31", "remaining_time": "0:40:15"}
|
| 135 |
+
{"current_steps": 675, "total_steps": 785, "loss": 0.3783, "lr": 2.390499810486351e-06, "epoch": 4.3008, "percentage": 85.99, "elapsed_time": "3:56:15", "remaining_time": "0:38:30"}
|
| 136 |
+
{"current_steps": 680, "total_steps": 785, "loss": 0.3837, "lr": 2.183911657784685e-06, "epoch": 4.3328, "percentage": 86.62, "elapsed_time": "3:58:04", "remaining_time": "0:36:45"}
|
| 137 |
+
{"current_steps": 685, "total_steps": 785, "loss": 0.3837, "lr": 1.986142615776532e-06, "epoch": 4.3648, "percentage": 87.26, "elapsed_time": "3:59:54", "remaining_time": "0:35:01"}
|
| 138 |
+
{"current_steps": 690, "total_steps": 785, "loss": 0.3943, "lr": 1.7972905817690644e-06, "epoch": 4.3968, "percentage": 87.9, "elapsed_time": "4:01:32", "remaining_time": "0:33:15"}
|
| 139 |
+
{"current_steps": 695, "total_steps": 785, "loss": 0.391, "lr": 1.617449039076955e-06, "epoch": 4.4288, "percentage": 88.54, "elapsed_time": "4:03:18", "remaining_time": "0:31:30"}
|
| 140 |
+
{"current_steps": 700, "total_steps": 785, "loss": 0.3834, "lr": 1.4467070107473413e-06, "epoch": 4.4608, "percentage": 89.17, "elapsed_time": "4:04:54", "remaining_time": "0:29:44"}
|
| 141 |
+
{"current_steps": 705, "total_steps": 785, "loss": 0.3818, "lr": 1.2851490154926816e-06, "epoch": 4.4928, "percentage": 89.81, "elapsed_time": "4:06:36", "remaining_time": "0:27:59"}
|
| 142 |
+
{"current_steps": 710, "total_steps": 785, "loss": 0.3832, "lr": 1.1328550258533211e-06, "epoch": 4.5248, "percentage": 90.45, "elapsed_time": "4:08:18", "remaining_time": "0:26:13"}
|
| 143 |
+
{"current_steps": 715, "total_steps": 785, "loss": 0.3928, "lr": 9.899004286103953e-07, "epoch": 4.5568, "percentage": 91.08, "elapsed_time": "4:09:55", "remaining_time": "0:24:28"}
|
| 144 |
+
{"current_steps": 720, "total_steps": 785, "loss": 0.3839, "lr": 8.5635598746876e-07, "epoch": 4.5888, "percentage": 91.72, "elapsed_time": "4:11:46", "remaining_time": "0:22:43"}
|
| 145 |
+
{"current_steps": 725, "total_steps": 785, "loss": 0.3751, "lr": 7.32287808028389e-07, "epoch": 4.6208, "percentage": 92.36, "elapsed_time": "4:13:29", "remaining_time": "0:20:58"}
|
| 146 |
+
{"current_steps": 730, "total_steps": 785, "loss": 0.3818, "lr": 6.177573050615327e-07, "epoch": 4.6528, "percentage": 92.99, "elapsed_time": "4:15:17", "remaining_time": "0:19:14"}
|
| 147 |
+
{"current_steps": 735, "total_steps": 785, "loss": 0.3846, "lr": 5.128211721119213e-07, "epoch": 4.6848, "percentage": 93.63, "elapsed_time": "4:17:09", "remaining_time": "0:17:29"}
|
| 148 |
+
{"current_steps": 740, "total_steps": 785, "loss": 0.3957, "lr": 4.175313534309755e-07, "epoch": 4.7168, "percentage": 94.27, "elapsed_time": "4:18:51", "remaining_time": "0:15:44"}
|
| 149 |
+
{"current_steps": 745, "total_steps": 785, "loss": 0.3858, "lr": 3.319350182649861e-07, "epoch": 4.7488, "percentage": 94.9, "elapsed_time": "4:20:41", "remaining_time": "0:13:59"}
|
| 150 |
+
{"current_steps": 750, "total_steps": 785, "loss": 0.3758, "lr": 2.560745375059392e-07, "epoch": 4.7808, "percentage": 95.54, "elapsed_time": "4:22:24", "remaining_time": "0:12:14"}
|
| 151 |
+
{"current_steps": 755, "total_steps": 785, "loss": 0.38, "lr": 1.8998746271758016e-07, "epoch": 4.8128, "percentage": 96.18, "elapsed_time": "4:24:08", "remaining_time": "0:10:29"}
|
| 152 |
+
{"current_steps": 760, "total_steps": 785, "loss": 0.3926, "lr": 1.337065075470778e-07, "epoch": 4.8448, "percentage": 96.82, "elapsed_time": "4:25:43", "remaining_time": "0:08:44"}
|
| 153 |
+
{"current_steps": 765, "total_steps": 785, "loss": 0.3866, "lr": 8.725953153150279e-08, "epoch": 4.8768, "percentage": 97.45, "elapsed_time": "4:27:22", "remaining_time": "0:06:59"}
|
| 154 |
+
{"current_steps": 770, "total_steps": 785, "loss": 0.3764, "lr": 5.066952630711886e-08, "epoch": 4.9088, "percentage": 98.09, "elapsed_time": "4:29:15", "remaining_time": "0:05:14"}
|
| 155 |
+
{"current_steps": 775, "total_steps": 785, "loss": 0.3897, "lr": 2.3954604228342283e-08, "epoch": 4.9408, "percentage": 98.73, "elapsed_time": "4:30:59", "remaining_time": "0:03:29"}
|
| 156 |
+
{"current_steps": 780, "total_steps": 785, "loss": 0.3905, "lr": 7.12798940197601e-09, "epoch": 4.9728, "percentage": 99.36, "elapsed_time": "4:32:38", "remaining_time": "0:01:44"}
|
| 157 |
+
{"current_steps": 785, "total_steps": 785, "loss": 0.3821, "lr": 1.9801114115480802e-10, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "4:33:59", "remaining_time": "0:00:00"}
|
| 158 |
+
{"current_steps": 785, "total_steps": 785, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "4:33:59", "remaining_time": "0:00:00"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1774 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 785,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.032,
|
| 14 |
+
"grad_norm": 6.107608851383935,
|
| 15 |
+
"learning_rate": 2.0253164556962026e-06,
|
| 16 |
+
"loss": 0.7455,
|
| 17 |
+
"loss_nan_ranks": 0,
|
| 18 |
+
"loss_rank_avg": 0.17644742131233215,
|
| 19 |
+
"step": 5,
|
| 20 |
+
"valid_targets_mean": 4706.8,
|
| 21 |
+
"valid_targets_min": 1106
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.064,
|
| 25 |
+
"grad_norm": 4.127049955682705,
|
| 26 |
+
"learning_rate": 4.556962025316456e-06,
|
| 27 |
+
"loss": 0.7168,
|
| 28 |
+
"loss_nan_ranks": 0,
|
| 29 |
+
"loss_rank_avg": 0.15632694959640503,
|
| 30 |
+
"step": 10,
|
| 31 |
+
"valid_targets_mean": 4084.8,
|
| 32 |
+
"valid_targets_min": 810
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.096,
|
| 36 |
+
"grad_norm": 2.3029768018854244,
|
| 37 |
+
"learning_rate": 7.08860759493671e-06,
|
| 38 |
+
"loss": 0.662,
|
| 39 |
+
"loss_nan_ranks": 0,
|
| 40 |
+
"loss_rank_avg": 0.1367417573928833,
|
| 41 |
+
"step": 15,
|
| 42 |
+
"valid_targets_mean": 4292.0,
|
| 43 |
+
"valid_targets_min": 1183
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 0.128,
|
| 47 |
+
"grad_norm": 0.9446288361337228,
|
| 48 |
+
"learning_rate": 9.620253164556963e-06,
|
| 49 |
+
"loss": 0.6259,
|
| 50 |
+
"loss_nan_ranks": 0,
|
| 51 |
+
"loss_rank_avg": 0.17443199455738068,
|
| 52 |
+
"step": 20,
|
| 53 |
+
"valid_targets_mean": 4366.4,
|
| 54 |
+
"valid_targets_min": 794
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.16,
|
| 58 |
+
"grad_norm": 0.7185214756105344,
|
| 59 |
+
"learning_rate": 1.2151898734177216e-05,
|
| 60 |
+
"loss": 0.6034,
|
| 61 |
+
"loss_nan_ranks": 0,
|
| 62 |
+
"loss_rank_avg": 0.15555769205093384,
|
| 63 |
+
"step": 25,
|
| 64 |
+
"valid_targets_mean": 4660.7,
|
| 65 |
+
"valid_targets_min": 791
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.192,
|
| 69 |
+
"grad_norm": 0.5760489151085344,
|
| 70 |
+
"learning_rate": 1.468354430379747e-05,
|
| 71 |
+
"loss": 0.5807,
|
| 72 |
+
"loss_nan_ranks": 0,
|
| 73 |
+
"loss_rank_avg": 0.10560796409845352,
|
| 74 |
+
"step": 30,
|
| 75 |
+
"valid_targets_mean": 2108.0,
|
| 76 |
+
"valid_targets_min": 626
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.224,
|
| 80 |
+
"grad_norm": 0.4877135466876705,
|
| 81 |
+
"learning_rate": 1.7215189873417723e-05,
|
| 82 |
+
"loss": 0.5433,
|
| 83 |
+
"loss_nan_ranks": 0,
|
| 84 |
+
"loss_rank_avg": 0.11195793747901917,
|
| 85 |
+
"step": 35,
|
| 86 |
+
"valid_targets_mean": 2955.8,
|
| 87 |
+
"valid_targets_min": 986
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.256,
|
| 91 |
+
"grad_norm": 0.3624410004020328,
|
| 92 |
+
"learning_rate": 1.974683544303798e-05,
|
| 93 |
+
"loss": 0.5255,
|
| 94 |
+
"loss_nan_ranks": 0,
|
| 95 |
+
"loss_rank_avg": 0.13301032781600952,
|
| 96 |
+
"step": 40,
|
| 97 |
+
"valid_targets_mean": 4398.3,
|
| 98 |
+
"valid_targets_min": 974
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.288,
|
| 102 |
+
"grad_norm": 0.3161733355122809,
|
| 103 |
+
"learning_rate": 2.2278481012658228e-05,
|
| 104 |
+
"loss": 0.5254,
|
| 105 |
+
"loss_nan_ranks": 0,
|
| 106 |
+
"loss_rank_avg": 0.09797270596027374,
|
| 107 |
+
"step": 45,
|
| 108 |
+
"valid_targets_mean": 3789.7,
|
| 109 |
+
"valid_targets_min": 971
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.32,
|
| 113 |
+
"grad_norm": 0.3282787112321606,
|
| 114 |
+
"learning_rate": 2.481012658227848e-05,
|
| 115 |
+
"loss": 0.504,
|
| 116 |
+
"loss_nan_ranks": 0,
|
| 117 |
+
"loss_rank_avg": 0.11803701519966125,
|
| 118 |
+
"step": 50,
|
| 119 |
+
"valid_targets_mean": 3716.9,
|
| 120 |
+
"valid_targets_min": 745
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.352,
|
| 124 |
+
"grad_norm": 0.3304161820612071,
|
| 125 |
+
"learning_rate": 2.7341772151898737e-05,
|
| 126 |
+
"loss": 0.5226,
|
| 127 |
+
"loss_nan_ranks": 0,
|
| 128 |
+
"loss_rank_avg": 0.1383068859577179,
|
| 129 |
+
"step": 55,
|
| 130 |
+
"valid_targets_mean": 3657.2,
|
| 131 |
+
"valid_targets_min": 742
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 0.384,
|
| 135 |
+
"grad_norm": 0.26548459531887825,
|
| 136 |
+
"learning_rate": 2.987341772151899e-05,
|
| 137 |
+
"loss": 0.4865,
|
| 138 |
+
"loss_nan_ranks": 0,
|
| 139 |
+
"loss_rank_avg": 0.1221662163734436,
|
| 140 |
+
"step": 60,
|
| 141 |
+
"valid_targets_mean": 4677.1,
|
| 142 |
+
"valid_targets_min": 790
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.416,
|
| 146 |
+
"grad_norm": 0.28910632104468453,
|
| 147 |
+
"learning_rate": 3.240506329113924e-05,
|
| 148 |
+
"loss": 0.484,
|
| 149 |
+
"loss_nan_ranks": 0,
|
| 150 |
+
"loss_rank_avg": 0.11457986384630203,
|
| 151 |
+
"step": 65,
|
| 152 |
+
"valid_targets_mean": 3794.5,
|
| 153 |
+
"valid_targets_min": 1093
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.448,
|
| 157 |
+
"grad_norm": 0.28039748750342514,
|
| 158 |
+
"learning_rate": 3.49367088607595e-05,
|
| 159 |
+
"loss": 0.4681,
|
| 160 |
+
"loss_nan_ranks": 0,
|
| 161 |
+
"loss_rank_avg": 0.13367806375026703,
|
| 162 |
+
"step": 70,
|
| 163 |
+
"valid_targets_mean": 4306.7,
|
| 164 |
+
"valid_targets_min": 811
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.48,
|
| 168 |
+
"grad_norm": 0.3515687541623445,
|
| 169 |
+
"learning_rate": 3.746835443037975e-05,
|
| 170 |
+
"loss": 0.474,
|
| 171 |
+
"loss_nan_ranks": 0,
|
| 172 |
+
"loss_rank_avg": 0.09756779670715332,
|
| 173 |
+
"step": 75,
|
| 174 |
+
"valid_targets_mean": 3202.6,
|
| 175 |
+
"valid_targets_min": 995
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 0.512,
|
| 179 |
+
"grad_norm": 0.29574743171943335,
|
| 180 |
+
"learning_rate": 4e-05,
|
| 181 |
+
"loss": 0.4638,
|
| 182 |
+
"loss_nan_ranks": 0,
|
| 183 |
+
"loss_rank_avg": 0.10536515712738037,
|
| 184 |
+
"step": 80,
|
| 185 |
+
"valid_targets_mean": 3387.2,
|
| 186 |
+
"valid_targets_min": 778
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.544,
|
| 190 |
+
"grad_norm": 0.304879438569274,
|
| 191 |
+
"learning_rate": 3.999504991751045e-05,
|
| 192 |
+
"loss": 0.4739,
|
| 193 |
+
"loss_nan_ranks": 0,
|
| 194 |
+
"loss_rank_avg": 0.09783598780632019,
|
| 195 |
+
"step": 85,
|
| 196 |
+
"valid_targets_mean": 2869.9,
|
| 197 |
+
"valid_targets_min": 769
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 0.576,
|
| 201 |
+
"grad_norm": 0.27264054448960384,
|
| 202 |
+
"learning_rate": 3.9980202120373464e-05,
|
| 203 |
+
"loss": 0.449,
|
| 204 |
+
"loss_nan_ranks": 0,
|
| 205 |
+
"loss_rank_avg": 0.1292189657688141,
|
| 206 |
+
"step": 90,
|
| 207 |
+
"valid_targets_mean": 5253.2,
|
| 208 |
+
"valid_targets_min": 1530
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 0.608,
|
| 212 |
+
"grad_norm": 0.28510371417891295,
|
| 213 |
+
"learning_rate": 3.995546395837111e-05,
|
| 214 |
+
"loss": 0.4557,
|
| 215 |
+
"loss_nan_ranks": 0,
|
| 216 |
+
"loss_rank_avg": 0.09879469871520996,
|
| 217 |
+
"step": 95,
|
| 218 |
+
"valid_targets_mean": 3112.0,
|
| 219 |
+
"valid_targets_min": 909
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.64,
|
| 223 |
+
"grad_norm": 0.3042715840047225,
|
| 224 |
+
"learning_rate": 3.992084767709763e-05,
|
| 225 |
+
"loss": 0.4534,
|
| 226 |
+
"loss_nan_ranks": 0,
|
| 227 |
+
"loss_rank_avg": 0.11518902331590652,
|
| 228 |
+
"step": 100,
|
| 229 |
+
"valid_targets_mean": 3185.5,
|
| 230 |
+
"valid_targets_min": 896
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.672,
|
| 234 |
+
"grad_norm": 0.3122541792144832,
|
| 235 |
+
"learning_rate": 3.987637041189781e-05,
|
| 236 |
+
"loss": 0.4602,
|
| 237 |
+
"loss_nan_ranks": 0,
|
| 238 |
+
"loss_rank_avg": 0.10355521738529205,
|
| 239 |
+
"step": 105,
|
| 240 |
+
"valid_targets_mean": 3099.8,
|
| 241 |
+
"valid_targets_min": 877
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.704,
|
| 245 |
+
"grad_norm": 0.3010397462755949,
|
| 246 |
+
"learning_rate": 3.982205417938482e-05,
|
| 247 |
+
"loss": 0.4583,
|
| 248 |
+
"loss_nan_ranks": 0,
|
| 249 |
+
"loss_rank_avg": 0.09757611155509949,
|
| 250 |
+
"step": 110,
|
| 251 |
+
"valid_targets_mean": 2974.1,
|
| 252 |
+
"valid_targets_min": 735
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.736,
|
| 256 |
+
"grad_norm": 0.2723793782396818,
|
| 257 |
+
"learning_rate": 3.975792586654179e-05,
|
| 258 |
+
"loss": 0.4453,
|
| 259 |
+
"loss_nan_ranks": 0,
|
| 260 |
+
"loss_rank_avg": 0.0976935625076294,
|
| 261 |
+
"step": 115,
|
| 262 |
+
"valid_targets_mean": 4154.2,
|
| 263 |
+
"valid_targets_min": 932
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 0.768,
|
| 267 |
+
"grad_norm": 0.2777107583881316,
|
| 268 |
+
"learning_rate": 3.968401721741259e-05,
|
| 269 |
+
"loss": 0.4403,
|
| 270 |
+
"loss_nan_ranks": 0,
|
| 271 |
+
"loss_rank_avg": 0.11072695255279541,
|
| 272 |
+
"step": 120,
|
| 273 |
+
"valid_targets_mean": 4520.2,
|
| 274 |
+
"valid_targets_min": 989
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.8,
|
| 278 |
+
"grad_norm": 0.29626977921824504,
|
| 279 |
+
"learning_rate": 3.960036481738819e-05,
|
| 280 |
+
"loss": 0.4448,
|
| 281 |
+
"loss_nan_ranks": 0,
|
| 282 |
+
"loss_rank_avg": 0.09114716947078705,
|
| 283 |
+
"step": 125,
|
| 284 |
+
"valid_targets_mean": 3407.4,
|
| 285 |
+
"valid_targets_min": 1066
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.832,
|
| 289 |
+
"grad_norm": 0.27035588866639104,
|
| 290 |
+
"learning_rate": 3.950701007509667e-05,
|
| 291 |
+
"loss": 0.4289,
|
| 292 |
+
"loss_nan_ranks": 0,
|
| 293 |
+
"loss_rank_avg": 0.10672830790281296,
|
| 294 |
+
"step": 130,
|
| 295 |
+
"valid_targets_mean": 4044.8,
|
| 296 |
+
"valid_targets_min": 909
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.864,
|
| 300 |
+
"grad_norm": 0.34837201643421056,
|
| 301 |
+
"learning_rate": 3.940399920190552e-05,
|
| 302 |
+
"loss": 0.4476,
|
| 303 |
+
"loss_nan_ranks": 0,
|
| 304 |
+
"loss_rank_avg": 0.1184217780828476,
|
| 305 |
+
"step": 135,
|
| 306 |
+
"valid_targets_mean": 3964.4,
|
| 307 |
+
"valid_targets_min": 633
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 0.896,
|
| 311 |
+
"grad_norm": 0.27938671284433453,
|
| 312 |
+
"learning_rate": 3.92913831890467e-05,
|
| 313 |
+
"loss": 0.4455,
|
| 314 |
+
"loss_nan_ranks": 0,
|
| 315 |
+
"loss_rank_avg": 0.12027984112501144,
|
| 316 |
+
"step": 140,
|
| 317 |
+
"valid_targets_mean": 4521.9,
|
| 318 |
+
"valid_targets_min": 1131
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.928,
|
| 322 |
+
"grad_norm": 0.31804065299221124,
|
| 323 |
+
"learning_rate": 3.916921778237556e-05,
|
| 324 |
+
"loss": 0.445,
|
| 325 |
+
"loss_nan_ranks": 0,
|
| 326 |
+
"loss_rank_avg": 0.0931854322552681,
|
| 327 |
+
"step": 145,
|
| 328 |
+
"valid_targets_mean": 3013.6,
|
| 329 |
+
"valid_targets_min": 766
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 0.96,
|
| 333 |
+
"grad_norm": 0.2744925417793362,
|
| 334 |
+
"learning_rate": 3.903756345477612e-05,
|
| 335 |
+
"loss": 0.4523,
|
| 336 |
+
"loss_nan_ranks": 0,
|
| 337 |
+
"loss_rank_avg": 0.10946588218212128,
|
| 338 |
+
"step": 150,
|
| 339 |
+
"valid_targets_mean": 4371.4,
|
| 340 |
+
"valid_targets_min": 541
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 0.992,
|
| 344 |
+
"grad_norm": 0.2856537317229886,
|
| 345 |
+
"learning_rate": 3.889648537622657e-05,
|
| 346 |
+
"loss": 0.4414,
|
| 347 |
+
"loss_nan_ranks": 0,
|
| 348 |
+
"loss_rank_avg": 0.11907991021871567,
|
| 349 |
+
"step": 155,
|
| 350 |
+
"valid_targets_mean": 4329.2,
|
| 351 |
+
"valid_targets_min": 624
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 1.0192,
|
| 355 |
+
"grad_norm": 0.2879141707463672,
|
| 356 |
+
"learning_rate": 3.874605338153952e-05,
|
| 357 |
+
"loss": 0.4448,
|
| 358 |
+
"loss_nan_ranks": 0,
|
| 359 |
+
"loss_rank_avg": 0.11861169338226318,
|
| 360 |
+
"step": 160,
|
| 361 |
+
"valid_targets_mean": 4391.5,
|
| 362 |
+
"valid_targets_min": 778
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 1.0512,
|
| 366 |
+
"grad_norm": 0.29661655419869887,
|
| 367 |
+
"learning_rate": 3.8586341935793265e-05,
|
| 368 |
+
"loss": 0.439,
|
| 369 |
+
"loss_nan_ranks": 0,
|
| 370 |
+
"loss_rank_avg": 0.10656130313873291,
|
| 371 |
+
"step": 165,
|
| 372 |
+
"valid_targets_mean": 3601.3,
|
| 373 |
+
"valid_targets_min": 1213
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 1.0832,
|
| 377 |
+
"grad_norm": 0.28570287652110415,
|
| 378 |
+
"learning_rate": 3.841743009747089e-05,
|
| 379 |
+
"loss": 0.4328,
|
| 380 |
+
"loss_nan_ranks": 0,
|
| 381 |
+
"loss_rank_avg": 0.1121365949511528,
|
| 382 |
+
"step": 170,
|
| 383 |
+
"valid_targets_mean": 4714.2,
|
| 384 |
+
"valid_targets_min": 965
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 1.1152,
|
| 388 |
+
"grad_norm": 0.27398298369656376,
|
| 389 |
+
"learning_rate": 3.8239401479325714e-05,
|
| 390 |
+
"loss": 0.4357,
|
| 391 |
+
"loss_nan_ranks": 0,
|
| 392 |
+
"loss_rank_avg": 0.12218301743268967,
|
| 393 |
+
"step": 175,
|
| 394 |
+
"valid_targets_mean": 4598.1,
|
| 395 |
+
"valid_targets_min": 1201
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.1472,
|
| 399 |
+
"grad_norm": 0.2711176693333212,
|
| 400 |
+
"learning_rate": 3.8052344206992276e-05,
|
| 401 |
+
"loss": 0.4112,
|
| 402 |
+
"loss_nan_ranks": 0,
|
| 403 |
+
"loss_rank_avg": 0.09930449724197388,
|
| 404 |
+
"step": 180,
|
| 405 |
+
"valid_targets_mean": 3603.8,
|
| 406 |
+
"valid_targets_min": 699
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 1.1792,
|
| 410 |
+
"grad_norm": 0.2929354661757715,
|
| 411 |
+
"learning_rate": 3.7856350875363396e-05,
|
| 412 |
+
"loss": 0.4311,
|
| 413 |
+
"loss_nan_ranks": 0,
|
| 414 |
+
"loss_rank_avg": 0.10408104211091995,
|
| 415 |
+
"step": 185,
|
| 416 |
+
"valid_targets_mean": 3858.0,
|
| 417 |
+
"valid_targets_min": 899
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 1.2112,
|
| 421 |
+
"grad_norm": 0.3048058460665974,
|
| 422 |
+
"learning_rate": 3.765151850275497e-05,
|
| 423 |
+
"loss": 0.4192,
|
| 424 |
+
"loss_nan_ranks": 0,
|
| 425 |
+
"loss_rank_avg": 0.09669551253318787,
|
| 426 |
+
"step": 190,
|
| 427 |
+
"valid_targets_mean": 3769.9,
|
| 428 |
+
"valid_targets_min": 614
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 1.2432,
|
| 432 |
+
"grad_norm": 0.30457339863231014,
|
| 433 |
+
"learning_rate": 3.7437948482881104e-05,
|
| 434 |
+
"loss": 0.4117,
|
| 435 |
+
"loss_nan_ranks": 0,
|
| 436 |
+
"loss_rank_avg": 0.0848011001944542,
|
| 437 |
+
"step": 195,
|
| 438 |
+
"valid_targets_mean": 3365.2,
|
| 439 |
+
"valid_targets_min": 750
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 1.2752,
|
| 443 |
+
"grad_norm": 0.26188787177664613,
|
| 444 |
+
"learning_rate": 3.721574653466336e-05,
|
| 445 |
+
"loss": 0.4177,
|
| 446 |
+
"loss_nan_ranks": 0,
|
| 447 |
+
"loss_rank_avg": 0.08277255296707153,
|
| 448 |
+
"step": 200,
|
| 449 |
+
"valid_targets_mean": 3634.0,
|
| 450 |
+
"valid_targets_min": 1159
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 1.3072,
|
| 454 |
+
"grad_norm": 0.28252106293682183,
|
| 455 |
+
"learning_rate": 3.698502264989903e-05,
|
| 456 |
+
"loss": 0.4233,
|
| 457 |
+
"loss_nan_ranks": 0,
|
| 458 |
+
"loss_rank_avg": 0.09822885692119598,
|
| 459 |
+
"step": 205,
|
| 460 |
+
"valid_targets_mean": 3658.9,
|
| 461 |
+
"valid_targets_min": 1293
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 1.3392,
|
| 465 |
+
"grad_norm": 0.290327599906892,
|
| 466 |
+
"learning_rate": 3.674589103881432e-05,
|
| 467 |
+
"loss": 0.4194,
|
| 468 |
+
"loss_nan_ranks": 0,
|
| 469 |
+
"loss_rank_avg": 0.09229561686515808,
|
| 470 |
+
"step": 210,
|
| 471 |
+
"valid_targets_mean": 3470.6,
|
| 472 |
+
"valid_targets_min": 936
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 1.3712,
|
| 476 |
+
"grad_norm": 0.2922145234243129,
|
| 477 |
+
"learning_rate": 3.64984700735293e-05,
|
| 478 |
+
"loss": 0.4182,
|
| 479 |
+
"loss_nan_ranks": 0,
|
| 480 |
+
"loss_rank_avg": 0.09459995478391647,
|
| 481 |
+
"step": 215,
|
| 482 |
+
"valid_targets_mean": 3381.3,
|
| 483 |
+
"valid_targets_min": 854
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 1.4032,
|
| 487 |
+
"grad_norm": 0.30800560949213257,
|
| 488 |
+
"learning_rate": 3.624288222946273e-05,
|
| 489 |
+
"loss": 0.4275,
|
| 490 |
+
"loss_nan_ranks": 0,
|
| 491 |
+
"loss_rank_avg": 0.15284359455108643,
|
| 492 |
+
"step": 220,
|
| 493 |
+
"valid_targets_mean": 4698.0,
|
| 494 |
+
"valid_targets_min": 1621
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 1.4352,
|
| 498 |
+
"grad_norm": 0.2946060468124792,
|
| 499 |
+
"learning_rate": 3.597925402470578e-05,
|
| 500 |
+
"loss": 0.4232,
|
| 501 |
+
"loss_nan_ranks": 0,
|
| 502 |
+
"loss_rank_avg": 0.1023549735546112,
|
| 503 |
+
"step": 225,
|
| 504 |
+
"valid_targets_mean": 3266.2,
|
| 505 |
+
"valid_targets_min": 696
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 1.4672,
|
| 509 |
+
"grad_norm": 0.2909375667048486,
|
| 510 |
+
"learning_rate": 3.570771595739445e-05,
|
| 511 |
+
"loss": 0.4253,
|
| 512 |
+
"loss_nan_ranks": 0,
|
| 513 |
+
"loss_rank_avg": 0.10413042455911636,
|
| 514 |
+
"step": 230,
|
| 515 |
+
"valid_targets_mean": 3986.3,
|
| 516 |
+
"valid_targets_min": 931
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 1.4992,
|
| 520 |
+
"grad_norm": 0.258968652511318,
|
| 521 |
+
"learning_rate": 3.5428402441111964e-05,
|
| 522 |
+
"loss": 0.4105,
|
| 523 |
+
"loss_nan_ranks": 0,
|
| 524 |
+
"loss_rank_avg": 0.08242276310920715,
|
| 525 |
+
"step": 235,
|
| 526 |
+
"valid_targets_mean": 3288.0,
|
| 527 |
+
"valid_targets_min": 825
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 1.5312000000000001,
|
| 531 |
+
"grad_norm": 0.260120898792648,
|
| 532 |
+
"learning_rate": 3.5141451738352936e-05,
|
| 533 |
+
"loss": 0.4085,
|
| 534 |
+
"loss_nan_ranks": 0,
|
| 535 |
+
"loss_rank_avg": 0.1041165292263031,
|
| 536 |
+
"step": 240,
|
| 537 |
+
"valid_targets_mean": 4548.1,
|
| 538 |
+
"valid_targets_min": 1250
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 1.5632000000000001,
|
| 542 |
+
"grad_norm": 0.3815842876872111,
|
| 543 |
+
"learning_rate": 3.4847005892082266e-05,
|
| 544 |
+
"loss": 0.4129,
|
| 545 |
+
"loss_nan_ranks": 0,
|
| 546 |
+
"loss_rank_avg": 0.10319903492927551,
|
| 547 |
+
"step": 245,
|
| 548 |
+
"valid_targets_mean": 4928.2,
|
| 549 |
+
"valid_targets_min": 1525
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.5952,
|
| 553 |
+
"grad_norm": 0.29887518088782095,
|
| 554 |
+
"learning_rate": 3.454521065542273e-05,
|
| 555 |
+
"loss": 0.4116,
|
| 556 |
+
"loss_nan_ranks": 0,
|
| 557 |
+
"loss_rank_avg": 0.09942469000816345,
|
| 558 |
+
"step": 250,
|
| 559 |
+
"valid_targets_mean": 4006.8,
|
| 560 |
+
"valid_targets_min": 923
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 1.6272,
|
| 564 |
+
"grad_norm": 0.3077625843249331,
|
| 565 |
+
"learning_rate": 3.423621541950597e-05,
|
| 566 |
+
"loss": 0.4294,
|
| 567 |
+
"loss_nan_ranks": 0,
|
| 568 |
+
"loss_rank_avg": 0.11495564132928848,
|
| 569 |
+
"step": 255,
|
| 570 |
+
"valid_targets_mean": 3654.4,
|
| 571 |
+
"valid_targets_min": 633
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 1.6592,
|
| 575 |
+
"grad_norm": 0.30742900313420013,
|
| 576 |
+
"learning_rate": 3.3920173139522664e-05,
|
| 577 |
+
"loss": 0.4269,
|
| 578 |
+
"loss_nan_ranks": 0,
|
| 579 |
+
"loss_rank_avg": 0.07939112186431885,
|
| 580 |
+
"step": 260,
|
| 581 |
+
"valid_targets_mean": 2838.2,
|
| 582 |
+
"valid_targets_min": 651
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 1.6912,
|
| 586 |
+
"grad_norm": 0.28353397923235046,
|
| 587 |
+
"learning_rate": 3.35972402590084e-05,
|
| 588 |
+
"loss": 0.4164,
|
| 589 |
+
"loss_nan_ranks": 0,
|
| 590 |
+
"loss_rank_avg": 0.11654111742973328,
|
| 591 |
+
"step": 265,
|
| 592 |
+
"valid_targets_mean": 5176.1,
|
| 593 |
+
"valid_targets_min": 1145
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 1.7231999999999998,
|
| 597 |
+
"grad_norm": 0.3159988844954844,
|
| 598 |
+
"learning_rate": 3.326757663240291e-05,
|
| 599 |
+
"loss": 0.412,
|
| 600 |
+
"loss_nan_ranks": 0,
|
| 601 |
+
"loss_rank_avg": 0.10565860569477081,
|
| 602 |
+
"step": 270,
|
| 603 |
+
"valid_targets_mean": 3831.5,
|
| 604 |
+
"valid_targets_min": 885
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 1.7551999999999999,
|
| 608 |
+
"grad_norm": 0.28303832854596667,
|
| 609 |
+
"learning_rate": 3.293134544592073e-05,
|
| 610 |
+
"loss": 0.4199,
|
| 611 |
+
"loss_nan_ranks": 0,
|
| 612 |
+
"loss_rank_avg": 0.09378932416439056,
|
| 613 |
+
"step": 275,
|
| 614 |
+
"valid_targets_mean": 4078.2,
|
| 615 |
+
"valid_targets_min": 1085
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 1.7872,
|
| 619 |
+
"grad_norm": 0.29629452883670093,
|
| 620 |
+
"learning_rate": 3.258871313677274e-05,
|
| 621 |
+
"loss": 0.4151,
|
| 622 |
+
"loss_nan_ranks": 0,
|
| 623 |
+
"loss_rank_avg": 0.11147819459438324,
|
| 624 |
+
"step": 280,
|
| 625 |
+
"valid_targets_mean": 4165.8,
|
| 626 |
+
"valid_targets_min": 1130
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.8192,
|
| 630 |
+
"grad_norm": 0.30579345790370027,
|
| 631 |
+
"learning_rate": 3.2239849310778316e-05,
|
| 632 |
+
"loss": 0.4165,
|
| 633 |
+
"loss_nan_ranks": 0,
|
| 634 |
+
"loss_rank_avg": 0.09240031242370605,
|
| 635 |
+
"step": 285,
|
| 636 |
+
"valid_targets_mean": 3160.4,
|
| 637 |
+
"valid_targets_min": 964
|
| 638 |
+
},
|
| 639 |
+
{
|
| 640 |
+
"epoch": 1.8512,
|
| 641 |
+
"grad_norm": 0.2639801571915376,
|
| 642 |
+
"learning_rate": 3.188492665840909e-05,
|
| 643 |
+
"loss": 0.4019,
|
| 644 |
+
"loss_nan_ranks": 0,
|
| 645 |
+
"loss_rank_avg": 0.10795797407627106,
|
| 646 |
+
"step": 290,
|
| 647 |
+
"valid_targets_mean": 5055.9,
|
| 648 |
+
"valid_targets_min": 1849
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 1.8832,
|
| 652 |
+
"grad_norm": 0.27607877025115213,
|
| 653 |
+
"learning_rate": 3.1524120869305726e-05,
|
| 654 |
+
"loss": 0.4125,
|
| 655 |
+
"loss_nan_ranks": 0,
|
| 656 |
+
"loss_rank_avg": 0.12126939743757248,
|
| 657 |
+
"step": 295,
|
| 658 |
+
"valid_targets_mean": 5233.9,
|
| 659 |
+
"valid_targets_min": 1737
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 1.9152,
|
| 663 |
+
"grad_norm": 0.2669974360426593,
|
| 664 |
+
"learning_rate": 3.11576105453101e-05,
|
| 665 |
+
"loss": 0.4035,
|
| 666 |
+
"loss_nan_ranks": 0,
|
| 667 |
+
"loss_rank_avg": 0.09347060322761536,
|
| 668 |
+
"step": 300,
|
| 669 |
+
"valid_targets_mean": 4767.1,
|
| 670 |
+
"valid_targets_min": 1224
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 1.9472,
|
| 674 |
+
"grad_norm": 0.3345770824254686,
|
| 675 |
+
"learning_rate": 3.0785577112055916e-05,
|
| 676 |
+
"loss": 0.4243,
|
| 677 |
+
"loss_nan_ranks": 0,
|
| 678 |
+
"loss_rank_avg": 0.0994449108839035,
|
| 679 |
+
"step": 305,
|
| 680 |
+
"valid_targets_mean": 3115.7,
|
| 681 |
+
"valid_targets_min": 787
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 1.9792,
|
| 685 |
+
"grad_norm": 0.2848512696158886,
|
| 686 |
+
"learning_rate": 3.040820472916153e-05,
|
| 687 |
+
"loss": 0.4156,
|
| 688 |
+
"loss_nan_ranks": 0,
|
| 689 |
+
"loss_rank_avg": 0.09286624193191528,
|
| 690 |
+
"step": 310,
|
| 691 |
+
"valid_targets_mean": 3558.1,
|
| 692 |
+
"valid_targets_min": 793
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 2.0064,
|
| 696 |
+
"grad_norm": 0.3082601924350668,
|
| 697 |
+
"learning_rate": 3.002568019906939e-05,
|
| 698 |
+
"loss": 0.4175,
|
| 699 |
+
"loss_nan_ranks": 0,
|
| 700 |
+
"loss_rank_avg": 0.13024066388607025,
|
| 701 |
+
"step": 315,
|
| 702 |
+
"valid_targets_mean": 4633.3,
|
| 703 |
+
"valid_targets_min": 710
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 2.0384,
|
| 707 |
+
"grad_norm": 0.2972613402450226,
|
| 708 |
+
"learning_rate": 2.963819287457733e-05,
|
| 709 |
+
"loss": 0.408,
|
| 710 |
+
"loss_nan_ranks": 0,
|
| 711 |
+
"loss_rank_avg": 0.14002487063407898,
|
| 712 |
+
"step": 320,
|
| 713 |
+
"valid_targets_mean": 5598.2,
|
| 714 |
+
"valid_targets_min": 1014
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 2.0704,
|
| 718 |
+
"grad_norm": 0.29338748624504957,
|
| 719 |
+
"learning_rate": 2.924593456510733e-05,
|
| 720 |
+
"loss": 0.4075,
|
| 721 |
+
"loss_nan_ranks": 0,
|
| 722 |
+
"loss_rank_avg": 0.11791073530912399,
|
| 723 |
+
"step": 325,
|
| 724 |
+
"valid_targets_mean": 4469.2,
|
| 725 |
+
"valid_targets_min": 909
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 2.1024,
|
| 729 |
+
"grad_norm": 0.2788624095471663,
|
| 730 |
+
"learning_rate": 2.8849099441758306e-05,
|
| 731 |
+
"loss": 0.4052,
|
| 732 |
+
"loss_nan_ranks": 0,
|
| 733 |
+
"loss_rank_avg": 0.09456164389848709,
|
| 734 |
+
"step": 330,
|
| 735 |
+
"valid_targets_mean": 2896.9,
|
| 736 |
+
"valid_targets_min": 1122
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 2.1344,
|
| 740 |
+
"grad_norm": 0.2581699312084376,
|
| 741 |
+
"learning_rate": 2.844788394118979e-05,
|
| 742 |
+
"loss": 0.3929,
|
| 743 |
+
"loss_nan_ranks": 0,
|
| 744 |
+
"loss_rank_avg": 0.09569685161113739,
|
| 745 |
+
"step": 335,
|
| 746 |
+
"valid_targets_mean": 3911.0,
|
| 747 |
+
"valid_targets_min": 940
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 2.1664,
|
| 751 |
+
"grad_norm": 0.31608505858012337,
|
| 752 |
+
"learning_rate": 2.8042486668384164e-05,
|
| 753 |
+
"loss": 0.4008,
|
| 754 |
+
"loss_nan_ranks": 0,
|
| 755 |
+
"loss_rank_avg": 0.1096731573343277,
|
| 756 |
+
"step": 340,
|
| 757 |
+
"valid_targets_mean": 4302.9,
|
| 758 |
+
"valid_targets_min": 1251
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 2.1984,
|
| 762 |
+
"grad_norm": 0.2880911863813072,
|
| 763 |
+
"learning_rate": 2.7633108298335582e-05,
|
| 764 |
+
"loss": 0.4025,
|
| 765 |
+
"loss_nan_ranks": 0,
|
| 766 |
+
"loss_rank_avg": 0.09002970159053802,
|
| 767 |
+
"step": 345,
|
| 768 |
+
"valid_targets_mean": 3883.4,
|
| 769 |
+
"valid_targets_min": 841
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 2.2304,
|
| 773 |
+
"grad_norm": 0.33383503829503497,
|
| 774 |
+
"learning_rate": 2.721995147671416e-05,
|
| 775 |
+
"loss": 0.3976,
|
| 776 |
+
"loss_nan_ranks": 0,
|
| 777 |
+
"loss_rank_avg": 0.11322958767414093,
|
| 778 |
+
"step": 350,
|
| 779 |
+
"valid_targets_mean": 4466.8,
|
| 780 |
+
"valid_targets_min": 890
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 2.2624,
|
| 784 |
+
"grad_norm": 0.3060080665890357,
|
| 785 |
+
"learning_rate": 2.68032207195547e-05,
|
| 786 |
+
"loss": 0.3962,
|
| 787 |
+
"loss_nan_ranks": 0,
|
| 788 |
+
"loss_rank_avg": 0.1092362031340599,
|
| 789 |
+
"step": 355,
|
| 790 |
+
"valid_targets_mean": 3826.1,
|
| 791 |
+
"valid_targets_min": 1137
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 2.2944,
|
| 795 |
+
"grad_norm": 0.26221504446327776,
|
| 796 |
+
"learning_rate": 2.6383122312019604e-05,
|
| 797 |
+
"loss": 0.398,
|
| 798 |
+
"loss_nan_ranks": 0,
|
| 799 |
+
"loss_rank_avg": 0.08882156014442444,
|
| 800 |
+
"step": 360,
|
| 801 |
+
"valid_targets_mean": 4397.3,
|
| 802 |
+
"valid_targets_min": 1033
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 2.3264,
|
| 806 |
+
"grad_norm": 0.3340098068516625,
|
| 807 |
+
"learning_rate": 2.595986420628597e-05,
|
| 808 |
+
"loss": 0.4117,
|
| 809 |
+
"loss_nan_ranks": 0,
|
| 810 |
+
"loss_rank_avg": 0.12631461024284363,
|
| 811 |
+
"step": 365,
|
| 812 |
+
"valid_targets_mean": 4953.4,
|
| 813 |
+
"valid_targets_min": 2095
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 2.3584,
|
| 817 |
+
"grad_norm": 0.27145668481073304,
|
| 818 |
+
"learning_rate": 2.5533655918607573e-05,
|
| 819 |
+
"loss": 0.403,
|
| 820 |
+
"loss_nan_ranks": 0,
|
| 821 |
+
"loss_rank_avg": 0.10268014669418335,
|
| 822 |
+
"step": 370,
|
| 823 |
+
"valid_targets_mean": 4452.4,
|
| 824 |
+
"valid_targets_min": 899
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 2.3904,
|
| 828 |
+
"grad_norm": 0.2810788522245723,
|
| 829 |
+
"learning_rate": 2.510470842560259e-05,
|
| 830 |
+
"loss": 0.3973,
|
| 831 |
+
"loss_nan_ranks": 0,
|
| 832 |
+
"loss_rank_avg": 0.1246403232216835,
|
| 833 |
+
"step": 375,
|
| 834 |
+
"valid_targets_mean": 5544.6,
|
| 835 |
+
"valid_targets_min": 1007
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 2.4224,
|
| 839 |
+
"grad_norm": 0.3126736568714705,
|
| 840 |
+
"learning_rate": 2.467323405981841e-05,
|
| 841 |
+
"loss": 0.4017,
|
| 842 |
+
"loss_nan_ranks": 0,
|
| 843 |
+
"loss_rank_avg": 0.08612629771232605,
|
| 844 |
+
"step": 380,
|
| 845 |
+
"valid_targets_mean": 2997.2,
|
| 846 |
+
"valid_targets_min": 810
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 2.4544,
|
| 850 |
+
"grad_norm": 0.2953368163016378,
|
| 851 |
+
"learning_rate": 2.423944640462533e-05,
|
| 852 |
+
"loss": 0.4033,
|
| 853 |
+
"loss_nan_ranks": 0,
|
| 854 |
+
"loss_rank_avg": 0.08532306551933289,
|
| 855 |
+
"step": 385,
|
| 856 |
+
"valid_targets_mean": 3594.6,
|
| 857 |
+
"valid_targets_min": 752
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 2.4864,
|
| 861 |
+
"grad_norm": 0.29200179241732954,
|
| 862 |
+
"learning_rate": 2.3803560188490968e-05,
|
| 863 |
+
"loss": 0.3995,
|
| 864 |
+
"loss_nan_ranks": 0,
|
| 865 |
+
"loss_rank_avg": 0.09730486571788788,
|
| 866 |
+
"step": 390,
|
| 867 |
+
"valid_targets_mean": 4327.1,
|
| 868 |
+
"valid_targets_min": 783
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 2.5183999999999997,
|
| 872 |
+
"grad_norm": 0.2946762576979655,
|
| 873 |
+
"learning_rate": 2.336579117868789e-05,
|
| 874 |
+
"loss": 0.4008,
|
| 875 |
+
"loss_nan_ranks": 0,
|
| 876 |
+
"loss_rank_avg": 0.11689925938844681,
|
| 877 |
+
"step": 395,
|
| 878 |
+
"valid_targets_mean": 4077.4,
|
| 879 |
+
"valid_targets_min": 965
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 2.5504,
|
| 883 |
+
"grad_norm": 0.28832935456119246,
|
| 884 |
+
"learning_rate": 2.292635607448711e-05,
|
| 885 |
+
"loss": 0.4065,
|
| 886 |
+
"loss_nan_ranks": 0,
|
| 887 |
+
"loss_rank_avg": 0.09628384560346603,
|
| 888 |
+
"step": 400,
|
| 889 |
+
"valid_targets_mean": 3998.8,
|
| 890 |
+
"valid_targets_min": 948
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 2.5824,
|
| 894 |
+
"grad_norm": 0.28622185841806863,
|
| 895 |
+
"learning_rate": 2.248547239989008e-05,
|
| 896 |
+
"loss": 0.409,
|
| 897 |
+
"loss_nan_ranks": 0,
|
| 898 |
+
"loss_rank_avg": 0.0933937281370163,
|
| 899 |
+
"step": 405,
|
| 900 |
+
"valid_targets_mean": 4487.5,
|
| 901 |
+
"valid_targets_min": 801
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 2.6144,
|
| 905 |
+
"grad_norm": 0.2746389328095657,
|
| 906 |
+
"learning_rate": 2.204335839595255e-05,
|
| 907 |
+
"loss": 0.3978,
|
| 908 |
+
"loss_nan_ranks": 0,
|
| 909 |
+
"loss_rank_avg": 0.11653994023799896,
|
| 910 |
+
"step": 410,
|
| 911 |
+
"valid_targets_mean": 4645.2,
|
| 912 |
+
"valid_targets_min": 656
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 2.6464,
|
| 916 |
+
"grad_norm": 0.3133949368221043,
|
| 917 |
+
"learning_rate": 2.1600232912753452e-05,
|
| 918 |
+
"loss": 0.4034,
|
| 919 |
+
"loss_nan_ranks": 0,
|
| 920 |
+
"loss_rank_avg": 0.11006447672843933,
|
| 921 |
+
"step": 415,
|
| 922 |
+
"valid_targets_mean": 3497.1,
|
| 923 |
+
"valid_targets_min": 1033
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 2.6784,
|
| 927 |
+
"grad_norm": 0.26840721362327946,
|
| 928 |
+
"learning_rate": 2.1156315301062293e-05,
|
| 929 |
+
"loss": 0.4014,
|
| 930 |
+
"loss_nan_ranks": 0,
|
| 931 |
+
"loss_rank_avg": 0.10718810558319092,
|
| 932 |
+
"step": 420,
|
| 933 |
+
"valid_targets_mean": 4133.1,
|
| 934 |
+
"valid_targets_min": 1486
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 2.7104,
|
| 938 |
+
"grad_norm": 0.28328827868904544,
|
| 939 |
+
"learning_rate": 2.0711825303758712e-05,
|
| 940 |
+
"loss": 0.4103,
|
| 941 |
+
"loss_nan_ranks": 0,
|
| 942 |
+
"loss_rank_avg": 0.12090544402599335,
|
| 943 |
+
"step": 425,
|
| 944 |
+
"valid_targets_mean": 5332.2,
|
| 945 |
+
"valid_targets_min": 923
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 2.7424,
|
| 949 |
+
"grad_norm": 0.3169828962163063,
|
| 950 |
+
"learning_rate": 2.0266982947057962e-05,
|
| 951 |
+
"loss": 0.4139,
|
| 952 |
+
"loss_nan_ranks": 0,
|
| 953 |
+
"loss_rank_avg": 0.09149235486984253,
|
| 954 |
+
"step": 430,
|
| 955 |
+
"valid_targets_mean": 3602.7,
|
| 956 |
+
"valid_targets_min": 827
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 2.7744,
|
| 960 |
+
"grad_norm": 0.24585141329828905,
|
| 961 |
+
"learning_rate": 1.9822008431596083e-05,
|
| 962 |
+
"loss": 0.3831,
|
| 963 |
+
"loss_nan_ranks": 0,
|
| 964 |
+
"loss_rank_avg": 0.0855756402015686,
|
| 965 |
+
"step": 435,
|
| 966 |
+
"valid_targets_mean": 3692.9,
|
| 967 |
+
"valid_targets_min": 1508
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 2.8064,
|
| 971 |
+
"grad_norm": 0.28624685923515464,
|
| 972 |
+
"learning_rate": 1.937712202342881e-05,
|
| 973 |
+
"loss": 0.3972,
|
| 974 |
+
"loss_nan_ranks": 0,
|
| 975 |
+
"loss_rank_avg": 0.10186800360679626,
|
| 976 |
+
"step": 440,
|
| 977 |
+
"valid_targets_mean": 4585.4,
|
| 978 |
+
"valid_targets_min": 877
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 2.8384,
|
| 982 |
+
"grad_norm": 0.2588341586751398,
|
| 983 |
+
"learning_rate": 1.8932543944998037e-05,
|
| 984 |
+
"loss": 0.387,
|
| 985 |
+
"loss_nan_ranks": 0,
|
| 986 |
+
"loss_rank_avg": 0.07834403216838837,
|
| 987 |
+
"step": 445,
|
| 988 |
+
"valid_targets_mean": 3711.6,
|
| 989 |
+
"valid_targets_min": 746
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 2.8704,
|
| 993 |
+
"grad_norm": 0.30323288737998944,
|
| 994 |
+
"learning_rate": 1.8488494266119877e-05,
|
| 995 |
+
"loss": 0.3901,
|
| 996 |
+
"loss_nan_ranks": 0,
|
| 997 |
+
"loss_rank_avg": 0.09488328546285629,
|
| 998 |
+
"step": 450,
|
| 999 |
+
"valid_targets_mean": 2979.2,
|
| 1000 |
+
"valid_targets_min": 722
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"epoch": 2.9024,
|
| 1004 |
+
"grad_norm": 0.24266113449716165,
|
| 1005 |
+
"learning_rate": 1.804519279504834e-05,
|
| 1006 |
+
"loss": 0.385,
|
| 1007 |
+
"loss_nan_ranks": 0,
|
| 1008 |
+
"loss_rank_avg": 0.07156480848789215,
|
| 1009 |
+
"step": 455,
|
| 1010 |
+
"valid_targets_mean": 4107.6,
|
| 1011 |
+
"valid_targets_min": 742
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 2.9344,
|
| 1015 |
+
"grad_norm": 0.28261298997066275,
|
| 1016 |
+
"learning_rate": 1.7602858969668365e-05,
|
| 1017 |
+
"loss": 0.393,
|
| 1018 |
+
"loss_nan_ranks": 0,
|
| 1019 |
+
"loss_rank_avg": 0.09054580330848694,
|
| 1020 |
+
"step": 460,
|
| 1021 |
+
"valid_targets_mean": 3750.1,
|
| 1022 |
+
"valid_targets_min": 1213
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 2.9664,
|
| 1026 |
+
"grad_norm": 0.259989135927338,
|
| 1027 |
+
"learning_rate": 1.716171174887231e-05,
|
| 1028 |
+
"loss": 0.3972,
|
| 1029 |
+
"loss_nan_ranks": 0,
|
| 1030 |
+
"loss_rank_avg": 0.09447605907917023,
|
| 1031 |
+
"step": 465,
|
| 1032 |
+
"valid_targets_mean": 4066.9,
|
| 1033 |
+
"valid_targets_min": 797
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 2.9984,
|
| 1037 |
+
"grad_norm": 0.2842931846792312,
|
| 1038 |
+
"learning_rate": 1.6721969504173484e-05,
|
| 1039 |
+
"loss": 0.3914,
|
| 1040 |
+
"loss_nan_ranks": 0,
|
| 1041 |
+
"loss_rank_avg": 0.10005789995193481,
|
| 1042 |
+
"step": 470,
|
| 1043 |
+
"valid_targets_mean": 4615.3,
|
| 1044 |
+
"valid_targets_min": 1184
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 3.0256,
|
| 1048 |
+
"grad_norm": 0.2942258678514413,
|
| 1049 |
+
"learning_rate": 1.628384991161041e-05,
|
| 1050 |
+
"loss": 0.3797,
|
| 1051 |
+
"loss_nan_ranks": 0,
|
| 1052 |
+
"loss_rank_avg": 0.106219083070755,
|
| 1053 |
+
"step": 475,
|
| 1054 |
+
"valid_targets_mean": 4277.8,
|
| 1055 |
+
"valid_targets_min": 1094
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 3.0576,
|
| 1059 |
+
"grad_norm": 0.2690806364664981,
|
| 1060 |
+
"learning_rate": 1.5847569843995452e-05,
|
| 1061 |
+
"loss": 0.3778,
|
| 1062 |
+
"loss_nan_ranks": 0,
|
| 1063 |
+
"loss_rank_avg": 0.09493634104728699,
|
| 1064 |
+
"step": 480,
|
| 1065 |
+
"valid_targets_mean": 3908.0,
|
| 1066 |
+
"valid_targets_min": 784
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 3.0896,
|
| 1070 |
+
"grad_norm": 0.26353669494610443,
|
| 1071 |
+
"learning_rate": 1.5413345263560922e-05,
|
| 1072 |
+
"loss": 0.3819,
|
| 1073 |
+
"loss_nan_ranks": 0,
|
| 1074 |
+
"loss_rank_avg": 0.11369521915912628,
|
| 1075 |
+
"step": 485,
|
| 1076 |
+
"valid_targets_mean": 4864.3,
|
| 1077 |
+
"valid_targets_min": 972
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 3.1216,
|
| 1081 |
+
"grad_norm": 0.4041290592713129,
|
| 1082 |
+
"learning_rate": 1.4981391115056032e-05,
|
| 1083 |
+
"loss": 0.3906,
|
| 1084 |
+
"loss_nan_ranks": 0,
|
| 1085 |
+
"loss_rank_avg": 0.09258768707513809,
|
| 1086 |
+
"step": 490,
|
| 1087 |
+
"valid_targets_mean": 2708.4,
|
| 1088 |
+
"valid_targets_min": 989
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 3.1536,
|
| 1092 |
+
"grad_norm": 0.25878391245076104,
|
| 1093 |
+
"learning_rate": 1.455192121934748e-05,
|
| 1094 |
+
"loss": 0.3897,
|
| 1095 |
+
"loss_nan_ranks": 0,
|
| 1096 |
+
"loss_rank_avg": 0.07488387823104858,
|
| 1097 |
+
"step": 495,
|
| 1098 |
+
"valid_targets_mean": 3082.7,
|
| 1099 |
+
"valid_targets_min": 656
|
| 1100 |
+
},
|
| 1101 |
+
{
|
| 1102 |
+
"epoch": 3.1856,
|
| 1103 |
+
"grad_norm": 0.253759150529026,
|
| 1104 |
+
"learning_rate": 1.4125148167576303e-05,
|
| 1105 |
+
"loss": 0.3974,
|
| 1106 |
+
"loss_nan_ranks": 0,
|
| 1107 |
+
"loss_rank_avg": 0.1091025173664093,
|
| 1108 |
+
"step": 500,
|
| 1109 |
+
"valid_targets_mean": 4998.2,
|
| 1110 |
+
"valid_targets_min": 1150
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"epoch": 3.2176,
|
| 1114 |
+
"grad_norm": 0.2683080146842537,
|
| 1115 |
+
"learning_rate": 1.3701283215923563e-05,
|
| 1116 |
+
"loss": 0.3858,
|
| 1117 |
+
"loss_nan_ranks": 0,
|
| 1118 |
+
"loss_rank_avg": 0.07230888307094574,
|
| 1119 |
+
"step": 505,
|
| 1120 |
+
"valid_targets_mean": 3185.6,
|
| 1121 |
+
"valid_targets_min": 827
|
| 1122 |
+
},
|
| 1123 |
+
{
|
| 1124 |
+
"epoch": 3.2496,
|
| 1125 |
+
"grad_norm": 0.2947819206644499,
|
| 1126 |
+
"learning_rate": 1.328053618103677e-05,
|
| 1127 |
+
"loss": 0.3903,
|
| 1128 |
+
"loss_nan_ranks": 0,
|
| 1129 |
+
"loss_rank_avg": 0.11434278637170792,
|
| 1130 |
+
"step": 510,
|
| 1131 |
+
"valid_targets_mean": 4241.5,
|
| 1132 |
+
"valid_targets_min": 734
|
| 1133 |
+
},
|
| 1134 |
+
{
|
| 1135 |
+
"epoch": 3.2816,
|
| 1136 |
+
"grad_norm": 0.2705047308271746,
|
| 1137 |
+
"learning_rate": 1.2863115336168916e-05,
|
| 1138 |
+
"loss": 0.3861,
|
| 1139 |
+
"loss_nan_ranks": 0,
|
| 1140 |
+
"loss_rank_avg": 0.11061400175094604,
|
| 1141 |
+
"step": 515,
|
| 1142 |
+
"valid_targets_mean": 4625.5,
|
| 1143 |
+
"valid_targets_min": 965
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 3.3136,
|
| 1147 |
+
"grad_norm": 0.2610230513683317,
|
| 1148 |
+
"learning_rate": 1.2449227308081509e-05,
|
| 1149 |
+
"loss": 0.3945,
|
| 1150 |
+
"loss_nan_ranks": 0,
|
| 1151 |
+
"loss_rank_avg": 0.10025350749492645,
|
| 1152 |
+
"step": 520,
|
| 1153 |
+
"valid_targets_mean": 4237.3,
|
| 1154 |
+
"valid_targets_min": 1048
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 3.3456,
|
| 1158 |
+
"grad_norm": 0.2825954817857534,
|
| 1159 |
+
"learning_rate": 1.2039076974762587e-05,
|
| 1160 |
+
"loss": 0.3951,
|
| 1161 |
+
"loss_nan_ranks": 0,
|
| 1162 |
+
"loss_rank_avg": 0.10196895897388458,
|
| 1163 |
+
"step": 525,
|
| 1164 |
+
"valid_targets_mean": 4061.5,
|
| 1165 |
+
"valid_targets_min": 810
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 3.3776,
|
| 1169 |
+
"grad_norm": 0.24013472756026968,
|
| 1170 |
+
"learning_rate": 1.163286736401044e-05,
|
| 1171 |
+
"loss": 0.3829,
|
| 1172 |
+
"loss_nan_ranks": 0,
|
| 1173 |
+
"loss_rank_avg": 0.08009563386440277,
|
| 1174 |
+
"step": 530,
|
| 1175 |
+
"valid_targets_mean": 3982.6,
|
| 1176 |
+
"valid_targets_min": 843
|
| 1177 |
+
},
|
| 1178 |
+
{
|
| 1179 |
+
"epoch": 3.4096,
|
| 1180 |
+
"grad_norm": 0.26036428326503036,
|
| 1181 |
+
"learning_rate": 1.123079955293322e-05,
|
| 1182 |
+
"loss": 0.4,
|
| 1183 |
+
"loss_nan_ranks": 0,
|
| 1184 |
+
"loss_rank_avg": 0.11866132915019989,
|
| 1185 |
+
"step": 535,
|
| 1186 |
+
"valid_targets_mean": 4450.6,
|
| 1187 |
+
"valid_targets_min": 1048
|
| 1188 |
+
},
|
| 1189 |
+
{
|
| 1190 |
+
"epoch": 3.4416,
|
| 1191 |
+
"grad_norm": 0.24881198574724328,
|
| 1192 |
+
"learning_rate": 1.0833072568414037e-05,
|
| 1193 |
+
"loss": 0.3952,
|
| 1194 |
+
"loss_nan_ranks": 0,
|
| 1195 |
+
"loss_rank_avg": 0.09163567423820496,
|
| 1196 |
+
"step": 540,
|
| 1197 |
+
"valid_targets_mean": 4590.5,
|
| 1198 |
+
"valid_targets_min": 702
|
| 1199 |
+
},
|
| 1200 |
+
{
|
| 1201 |
+
"epoch": 3.4736000000000002,
|
| 1202 |
+
"grad_norm": 0.2843932556205226,
|
| 1203 |
+
"learning_rate": 1.0439883288591057e-05,
|
| 1204 |
+
"loss": 0.3903,
|
| 1205 |
+
"loss_nan_ranks": 0,
|
| 1206 |
+
"loss_rank_avg": 0.09883452206850052,
|
| 1207 |
+
"step": 545,
|
| 1208 |
+
"valid_targets_mean": 3780.2,
|
| 1209 |
+
"valid_targets_min": 975
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 3.5056000000000003,
|
| 1213 |
+
"grad_norm": 0.27338503039297785,
|
| 1214 |
+
"learning_rate": 1.0051426345401202e-05,
|
| 1215 |
+
"loss": 0.3785,
|
| 1216 |
+
"loss_nan_ranks": 0,
|
| 1217 |
+
"loss_rank_avg": 0.08160857856273651,
|
| 1218 |
+
"step": 550,
|
| 1219 |
+
"valid_targets_mean": 3942.5,
|
| 1220 |
+
"valid_targets_min": 938
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 3.5376,
|
| 1224 |
+
"grad_norm": 0.2674094532197557,
|
| 1225 |
+
"learning_rate": 9.667894028235704e-06,
|
| 1226 |
+
"loss": 0.3901,
|
| 1227 |
+
"loss_nan_ranks": 0,
|
| 1228 |
+
"loss_rank_avg": 0.10117650032043457,
|
| 1229 |
+
"step": 555,
|
| 1230 |
+
"valid_targets_mean": 3955.4,
|
| 1231 |
+
"valid_targets_min": 793
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 3.5696,
|
| 1235 |
+
"grad_norm": 0.27380161269817377,
|
| 1236 |
+
"learning_rate": 9.289476188755315e-06,
|
| 1237 |
+
"loss": 0.3911,
|
| 1238 |
+
"loss_nan_ranks": 0,
|
| 1239 |
+
"loss_rank_avg": 0.087982177734375,
|
| 1240 |
+
"step": 560,
|
| 1241 |
+
"valid_targets_mean": 3488.1,
|
| 1242 |
+
"valid_targets_min": 874
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 3.6016,
|
| 1246 |
+
"grad_norm": 0.31002515430693867,
|
| 1247 |
+
"learning_rate": 8.916360146912122e-06,
|
| 1248 |
+
"loss": 0.3873,
|
| 1249 |
+
"loss_nan_ranks": 0,
|
| 1250 |
+
"loss_rank_avg": 0.11359541863203049,
|
| 1251 |
+
"step": 565,
|
| 1252 |
+
"valid_targets_mean": 3674.3,
|
| 1253 |
+
"valid_targets_min": 941
|
| 1254 |
+
},
|
| 1255 |
+
{
|
| 1256 |
+
"epoch": 3.6336,
|
| 1257 |
+
"grad_norm": 0.32806171635804243,
|
| 1258 |
+
"learning_rate": 8.548730598224646e-06,
|
| 1259 |
+
"loss": 0.3994,
|
| 1260 |
+
"loss_nan_ranks": 0,
|
| 1261 |
+
"loss_rank_avg": 0.08924146741628647,
|
| 1262 |
+
"step": 570,
|
| 1263 |
+
"valid_targets_mean": 2419.3,
|
| 1264 |
+
"valid_targets_min": 639
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"epoch": 3.6656,
|
| 1268 |
+
"grad_norm": 0.2907755504334934,
|
| 1269 |
+
"learning_rate": 8.186769522352053e-06,
|
| 1270 |
+
"loss": 0.388,
|
| 1271 |
+
"loss_nan_ranks": 0,
|
| 1272 |
+
"loss_rank_avg": 0.10015973448753357,
|
| 1273 |
+
"step": 575,
|
| 1274 |
+
"valid_targets_mean": 3822.8,
|
| 1275 |
+
"valid_targets_min": 975
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 3.6976,
|
| 1279 |
+
"grad_norm": 0.28606169446008295,
|
| 1280 |
+
"learning_rate": 7.830656093012714e-06,
|
| 1281 |
+
"loss": 0.3811,
|
| 1282 |
+
"loss_nan_ranks": 0,
|
| 1283 |
+
"loss_rank_avg": 0.1018945500254631,
|
| 1284 |
+
"step": 580,
|
| 1285 |
+
"valid_targets_mean": 3379.8,
|
| 1286 |
+
"valid_targets_min": 612
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 3.7296,
|
| 1290 |
+
"grad_norm": 0.2590625610172514,
|
| 1291 |
+
"learning_rate": 7.480566589291696e-06,
|
| 1292 |
+
"loss": 0.3869,
|
| 1293 |
+
"loss_nan_ranks": 0,
|
| 1294 |
+
"loss_rank_avg": 0.11175013333559036,
|
| 1295 |
+
"step": 585,
|
| 1296 |
+
"valid_targets_mean": 4867.4,
|
| 1297 |
+
"valid_targets_min": 704
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 3.7616,
|
| 1301 |
+
"grad_norm": 0.2763907408247419,
|
| 1302 |
+
"learning_rate": 7.1366743083812285e-06,
|
| 1303 |
+
"loss": 0.3931,
|
| 1304 |
+
"loss_nan_ranks": 0,
|
| 1305 |
+
"loss_rank_avg": 0.10954703390598297,
|
| 1306 |
+
"step": 590,
|
| 1307 |
+
"valid_targets_mean": 4537.1,
|
| 1308 |
+
"valid_targets_min": 710
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 3.7936,
|
| 1312 |
+
"grad_norm": 0.24962648496447917,
|
| 1313 |
+
"learning_rate": 6.799149479797101e-06,
|
| 1314 |
+
"loss": 0.3869,
|
| 1315 |
+
"loss_nan_ranks": 0,
|
| 1316 |
+
"loss_rank_avg": 0.09462133795022964,
|
| 1317 |
+
"step": 595,
|
| 1318 |
+
"valid_targets_mean": 4469.4,
|
| 1319 |
+
"valid_targets_min": 690
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 3.8256,
|
| 1323 |
+
"grad_norm": 0.2754736478883349,
|
| 1324 |
+
"learning_rate": 6.4681591811137e-06,
|
| 1325 |
+
"loss": 0.3867,
|
| 1326 |
+
"loss_nan_ranks": 0,
|
| 1327 |
+
"loss_rank_avg": 0.11113976687192917,
|
| 1328 |
+
"step": 600,
|
| 1329 |
+
"valid_targets_mean": 4153.2,
|
| 1330 |
+
"valid_targets_min": 896
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"epoch": 3.8576,
|
| 1334 |
+
"grad_norm": 0.28158413256335013,
|
| 1335 |
+
"learning_rate": 6.143867255259197e-06,
|
| 1336 |
+
"loss": 0.3822,
|
| 1337 |
+
"loss_nan_ranks": 0,
|
| 1338 |
+
"loss_rank_avg": 0.11500473320484161,
|
| 1339 |
+
"step": 605,
|
| 1340 |
+
"valid_targets_mean": 4267.9,
|
| 1341 |
+
"valid_targets_min": 863
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 3.8895999999999997,
|
| 1345 |
+
"grad_norm": 0.2995558635935276,
|
| 1346 |
+
"learning_rate": 5.8264342294119504e-06,
|
| 1347 |
+
"loss": 0.3958,
|
| 1348 |
+
"loss_nan_ranks": 0,
|
| 1349 |
+
"loss_rank_avg": 0.10843653976917267,
|
| 1350 |
+
"step": 610,
|
| 1351 |
+
"valid_targets_mean": 3483.2,
|
| 1352 |
+
"valid_targets_min": 1058
|
| 1353 |
+
},
|
| 1354 |
+
{
|
| 1355 |
+
"epoch": 3.9215999999999998,
|
| 1356 |
+
"grad_norm": 0.26971516213282304,
|
| 1357 |
+
"learning_rate": 5.516017235538258e-06,
|
| 1358 |
+
"loss": 0.4026,
|
| 1359 |
+
"loss_nan_ranks": 0,
|
| 1360 |
+
"loss_rank_avg": 0.09091812372207642,
|
| 1361 |
+
"step": 615,
|
| 1362 |
+
"valid_targets_mean": 3210.1,
|
| 1363 |
+
"valid_targets_min": 693
|
| 1364 |
+
},
|
| 1365 |
+
{
|
| 1366 |
+
"epoch": 3.9536,
|
| 1367 |
+
"grad_norm": 0.27718460735351713,
|
| 1368 |
+
"learning_rate": 5.212769932610695e-06,
|
| 1369 |
+
"loss": 0.3881,
|
| 1370 |
+
"loss_nan_ranks": 0,
|
| 1371 |
+
"loss_rank_avg": 0.10660787671804428,
|
| 1372 |
+
"step": 620,
|
| 1373 |
+
"valid_targets_mean": 3532.4,
|
| 1374 |
+
"valid_targets_min": 701
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 3.9856,
|
| 1378 |
+
"grad_norm": 0.24222704520402027,
|
| 1379 |
+
"learning_rate": 4.916842430545681e-06,
|
| 1380 |
+
"loss": 0.3854,
|
| 1381 |
+
"loss_nan_ranks": 0,
|
| 1382 |
+
"loss_rank_avg": 0.06686671078205109,
|
| 1383 |
+
"step": 625,
|
| 1384 |
+
"valid_targets_mean": 3113.8,
|
| 1385 |
+
"valid_targets_min": 1014
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 4.0128,
|
| 1389 |
+
"grad_norm": 0.2577795312253048,
|
| 1390 |
+
"learning_rate": 4.628381215897837e-06,
|
| 1391 |
+
"loss": 0.3935,
|
| 1392 |
+
"loss_nan_ranks": 0,
|
| 1393 |
+
"loss_rank_avg": 0.10310535132884979,
|
| 1394 |
+
"step": 630,
|
| 1395 |
+
"valid_targets_mean": 4274.4,
|
| 1396 |
+
"valid_targets_min": 821
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 4.0448,
|
| 1400 |
+
"grad_norm": 0.26450694499499056,
|
| 1401 |
+
"learning_rate": 4.347529079347914e-06,
|
| 1402 |
+
"loss": 0.3818,
|
| 1403 |
+
"loss_nan_ranks": 0,
|
| 1404 |
+
"loss_rank_avg": 0.08196067810058594,
|
| 1405 |
+
"step": 635,
|
| 1406 |
+
"valid_targets_mean": 3661.9,
|
| 1407 |
+
"valid_targets_min": 798
|
| 1408 |
+
},
|
| 1409 |
+
{
|
| 1410 |
+
"epoch": 4.0768,
|
| 1411 |
+
"grad_norm": 0.25757656679535085,
|
| 1412 |
+
"learning_rate": 4.074425045020247e-06,
|
| 1413 |
+
"loss": 0.3879,
|
| 1414 |
+
"loss_nan_ranks": 0,
|
| 1415 |
+
"loss_rank_avg": 0.11379433423280716,
|
| 1416 |
+
"step": 640,
|
| 1417 |
+
"valid_targets_mean": 5251.4,
|
| 1418 |
+
"valid_targets_min": 873
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 4.1088,
|
| 1422 |
+
"grad_norm": 0.2857282667440211,
|
| 1423 |
+
"learning_rate": 3.8092043016646487e-06,
|
| 1424 |
+
"loss": 0.3898,
|
| 1425 |
+
"loss_nan_ranks": 0,
|
| 1426 |
+
"loss_rank_avg": 0.09233619272708893,
|
| 1427 |
+
"step": 645,
|
| 1428 |
+
"valid_targets_mean": 3476.4,
|
| 1429 |
+
"valid_targets_min": 942
|
| 1430 |
+
},
|
| 1431 |
+
{
|
| 1432 |
+
"epoch": 4.1408,
|
| 1433 |
+
"grad_norm": 0.26803241687834123,
|
| 1434 |
+
"learning_rate": 3.551998135736867e-06,
|
| 1435 |
+
"loss": 0.3895,
|
| 1436 |
+
"loss_nan_ranks": 0,
|
| 1437 |
+
"loss_rank_avg": 0.11338621377944946,
|
| 1438 |
+
"step": 650,
|
| 1439 |
+
"valid_targets_mean": 4720.1,
|
| 1440 |
+
"valid_targets_min": 1226
|
| 1441 |
+
},
|
| 1442 |
+
{
|
| 1443 |
+
"epoch": 4.1728,
|
| 1444 |
+
"grad_norm": 0.25400284057837186,
|
| 1445 |
+
"learning_rate": 3.3029338664107267e-06,
|
| 1446 |
+
"loss": 0.3711,
|
| 1447 |
+
"loss_nan_ranks": 0,
|
| 1448 |
+
"loss_rank_avg": 0.08650071918964386,
|
| 1449 |
+
"step": 655,
|
| 1450 |
+
"valid_targets_mean": 4031.5,
|
| 1451 |
+
"valid_targets_min": 809
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 4.2048,
|
| 1455 |
+
"grad_norm": 0.2568237062355446,
|
| 1456 |
+
"learning_rate": 3.0621347825540625e-06,
|
| 1457 |
+
"loss": 0.391,
|
| 1458 |
+
"loss_nan_ranks": 0,
|
| 1459 |
+
"loss_rank_avg": 0.09939530491828918,
|
| 1460 |
+
"step": 660,
|
| 1461 |
+
"valid_targets_mean": 4138.6,
|
| 1462 |
+
"valid_targets_min": 762
|
| 1463 |
+
},
|
| 1464 |
+
{
|
| 1465 |
+
"epoch": 4.2368,
|
| 1466 |
+
"grad_norm": 0.2676124398757461,
|
| 1467 |
+
"learning_rate": 2.8297200816997183e-06,
|
| 1468 |
+
"loss": 0.3869,
|
| 1469 |
+
"loss_nan_ranks": 0,
|
| 1470 |
+
"loss_rank_avg": 0.09458170086145401,
|
| 1471 |
+
"step": 665,
|
| 1472 |
+
"valid_targets_mean": 4247.1,
|
| 1473 |
+
"valid_targets_min": 868
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 4.2688,
|
| 1477 |
+
"grad_norm": 0.28046598824382457,
|
| 1478 |
+
"learning_rate": 2.605804811041803e-06,
|
| 1479 |
+
"loss": 0.3807,
|
| 1480 |
+
"loss_nan_ranks": 0,
|
| 1481 |
+
"loss_rank_avg": 0.10842232406139374,
|
| 1482 |
+
"step": 670,
|
| 1483 |
+
"valid_targets_mean": 3938.6,
|
| 1484 |
+
"valid_targets_min": 833
|
| 1485 |
+
},
|
| 1486 |
+
{
|
| 1487 |
+
"epoch": 4.3008,
|
| 1488 |
+
"grad_norm": 0.2570693432350438,
|
| 1489 |
+
"learning_rate": 2.390499810486351e-06,
|
| 1490 |
+
"loss": 0.3783,
|
| 1491 |
+
"loss_nan_ranks": 0,
|
| 1492 |
+
"loss_rank_avg": 0.08588958531618118,
|
| 1493 |
+
"step": 675,
|
| 1494 |
+
"valid_targets_mean": 3437.5,
|
| 1495 |
+
"valid_targets_min": 850
|
| 1496 |
+
},
|
| 1497 |
+
{
|
| 1498 |
+
"epoch": 4.3328,
|
| 1499 |
+
"grad_norm": 0.25507056895604874,
|
| 1500 |
+
"learning_rate": 2.183911657784685e-06,
|
| 1501 |
+
"loss": 0.3837,
|
| 1502 |
+
"loss_nan_ranks": 0,
|
| 1503 |
+
"loss_rank_avg": 0.09940114617347717,
|
| 1504 |
+
"step": 680,
|
| 1505 |
+
"valid_targets_mean": 4383.1,
|
| 1506 |
+
"valid_targets_min": 900
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 4.3648,
|
| 1510 |
+
"grad_norm": 0.2489526579222752,
|
| 1511 |
+
"learning_rate": 1.986142615776532e-06,
|
| 1512 |
+
"loss": 0.3837,
|
| 1513 |
+
"loss_nan_ranks": 0,
|
| 1514 |
+
"loss_rank_avg": 0.11270736902952194,
|
| 1515 |
+
"step": 685,
|
| 1516 |
+
"valid_targets_mean": 5063.6,
|
| 1517 |
+
"valid_targets_min": 960
|
| 1518 |
+
},
|
| 1519 |
+
{
|
| 1520 |
+
"epoch": 4.3968,
|
| 1521 |
+
"grad_norm": 0.30376368802757764,
|
| 1522 |
+
"learning_rate": 1.7972905817690644e-06,
|
| 1523 |
+
"loss": 0.3943,
|
| 1524 |
+
"loss_nan_ranks": 0,
|
| 1525 |
+
"loss_rank_avg": 0.08725392818450928,
|
| 1526 |
+
"step": 690,
|
| 1527 |
+
"valid_targets_mean": 3286.1,
|
| 1528 |
+
"valid_targets_min": 892
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 4.4288,
|
| 1532 |
+
"grad_norm": 0.4292351264693741,
|
| 1533 |
+
"learning_rate": 1.617449039076955e-06,
|
| 1534 |
+
"loss": 0.391,
|
| 1535 |
+
"loss_nan_ranks": 0,
|
| 1536 |
+
"loss_rank_avg": 0.11258338391780853,
|
| 1537 |
+
"step": 695,
|
| 1538 |
+
"valid_targets_mean": 4237.6,
|
| 1539 |
+
"valid_targets_min": 1186
|
| 1540 |
+
},
|
| 1541 |
+
{
|
| 1542 |
+
"epoch": 4.4608,
|
| 1543 |
+
"grad_norm": 0.25325658381922306,
|
| 1544 |
+
"learning_rate": 1.4467070107473413e-06,
|
| 1545 |
+
"loss": 0.3834,
|
| 1546 |
+
"loss_nan_ranks": 0,
|
| 1547 |
+
"loss_rank_avg": 0.0918629914522171,
|
| 1548 |
+
"step": 700,
|
| 1549 |
+
"valid_targets_mean": 4016.9,
|
| 1550 |
+
"valid_targets_min": 970
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 4.4928,
|
| 1554 |
+
"grad_norm": 0.30072408255586425,
|
| 1555 |
+
"learning_rate": 1.2851490154926816e-06,
|
| 1556 |
+
"loss": 0.3818,
|
| 1557 |
+
"loss_nan_ranks": 0,
|
| 1558 |
+
"loss_rank_avg": 0.09678243845701218,
|
| 1559 |
+
"step": 705,
|
| 1560 |
+
"valid_targets_mean": 3707.1,
|
| 1561 |
+
"valid_targets_min": 1103
|
| 1562 |
+
},
|
| 1563 |
+
{
|
| 1564 |
+
"epoch": 4.5248,
|
| 1565 |
+
"grad_norm": 0.25410126385994386,
|
| 1566 |
+
"learning_rate": 1.1328550258533211e-06,
|
| 1567 |
+
"loss": 0.3832,
|
| 1568 |
+
"loss_nan_ranks": 0,
|
| 1569 |
+
"loss_rank_avg": 0.10050881654024124,
|
| 1570 |
+
"step": 710,
|
| 1571 |
+
"valid_targets_mean": 4388.2,
|
| 1572 |
+
"valid_targets_min": 880
|
| 1573 |
+
},
|
| 1574 |
+
{
|
| 1575 |
+
"epoch": 4.5568,
|
| 1576 |
+
"grad_norm": 0.34950980807629306,
|
| 1577 |
+
"learning_rate": 9.899004286103953e-07,
|
| 1578 |
+
"loss": 0.3928,
|
| 1579 |
+
"loss_nan_ranks": 0,
|
| 1580 |
+
"loss_rank_avg": 0.0971115306019783,
|
| 1581 |
+
"step": 715,
|
| 1582 |
+
"valid_targets_mean": 2979.0,
|
| 1583 |
+
"valid_targets_min": 994
|
| 1584 |
+
},
|
| 1585 |
+
{
|
| 1586 |
+
"epoch": 4.5888,
|
| 1587 |
+
"grad_norm": 0.24312281541870698,
|
| 1588 |
+
"learning_rate": 8.5635598746876e-07,
|
| 1589 |
+
"loss": 0.3839,
|
| 1590 |
+
"loss_nan_ranks": 0,
|
| 1591 |
+
"loss_rank_avg": 0.09972332417964935,
|
| 1592 |
+
"step": 720,
|
| 1593 |
+
"valid_targets_mean": 4491.6,
|
| 1594 |
+
"valid_targets_min": 969
|
| 1595 |
+
},
|
| 1596 |
+
{
|
| 1597 |
+
"epoch": 4.6208,
|
| 1598 |
+
"grad_norm": 0.2714481941303094,
|
| 1599 |
+
"learning_rate": 7.32287808028389e-07,
|
| 1600 |
+
"loss": 0.3751,
|
| 1601 |
+
"loss_nan_ranks": 0,
|
| 1602 |
+
"loss_rank_avg": 0.08378778398036957,
|
| 1603 |
+
"step": 725,
|
| 1604 |
+
"valid_targets_mean": 4230.4,
|
| 1605 |
+
"valid_targets_min": 795
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 4.6528,
|
| 1609 |
+
"grad_norm": 0.2854227918980573,
|
| 1610 |
+
"learning_rate": 6.177573050615327e-07,
|
| 1611 |
+
"loss": 0.3818,
|
| 1612 |
+
"loss_nan_ranks": 0,
|
| 1613 |
+
"loss_rank_avg": 0.10359008610248566,
|
| 1614 |
+
"step": 730,
|
| 1615 |
+
"valid_targets_mean": 3959.3,
|
| 1616 |
+
"valid_targets_min": 1324
|
| 1617 |
+
},
|
| 1618 |
+
{
|
| 1619 |
+
"epoch": 4.6848,
|
| 1620 |
+
"grad_norm": 0.24942374686892158,
|
| 1621 |
+
"learning_rate": 5.128211721119213e-07,
|
| 1622 |
+
"loss": 0.3846,
|
| 1623 |
+
"loss_nan_ranks": 0,
|
| 1624 |
+
"loss_rank_avg": 0.11520683765411377,
|
| 1625 |
+
"step": 735,
|
| 1626 |
+
"valid_targets_mean": 5002.9,
|
| 1627 |
+
"valid_targets_min": 913
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 4.7168,
|
| 1631 |
+
"grad_norm": 0.31797210014974603,
|
| 1632 |
+
"learning_rate": 4.175313534309755e-07,
|
| 1633 |
+
"loss": 0.3957,
|
| 1634 |
+
"loss_nan_ranks": 0,
|
| 1635 |
+
"loss_rank_avg": 0.10495293140411377,
|
| 1636 |
+
"step": 740,
|
| 1637 |
+
"valid_targets_mean": 3320.9,
|
| 1638 |
+
"valid_targets_min": 706
|
| 1639 |
+
},
|
| 1640 |
+
{
|
| 1641 |
+
"epoch": 4.7488,
|
| 1642 |
+
"grad_norm": 0.2768908745456099,
|
| 1643 |
+
"learning_rate": 3.319350182649861e-07,
|
| 1644 |
+
"loss": 0.3858,
|
| 1645 |
+
"loss_nan_ranks": 0,
|
| 1646 |
+
"loss_rank_avg": 0.07093711942434311,
|
| 1647 |
+
"step": 745,
|
| 1648 |
+
"valid_targets_mean": 2778.2,
|
| 1649 |
+
"valid_targets_min": 633
|
| 1650 |
+
},
|
| 1651 |
+
{
|
| 1652 |
+
"epoch": 4.7808,
|
| 1653 |
+
"grad_norm": 0.2960407866353702,
|
| 1654 |
+
"learning_rate": 2.560745375059392e-07,
|
| 1655 |
+
"loss": 0.3758,
|
| 1656 |
+
"loss_nan_ranks": 0,
|
| 1657 |
+
"loss_rank_avg": 0.10425875335931778,
|
| 1658 |
+
"step": 750,
|
| 1659 |
+
"valid_targets_mean": 3789.5,
|
| 1660 |
+
"valid_targets_min": 896
|
| 1661 |
+
},
|
| 1662 |
+
{
|
| 1663 |
+
"epoch": 4.8128,
|
| 1664 |
+
"grad_norm": 0.2399975960595749,
|
| 1665 |
+
"learning_rate": 1.8998746271758016e-07,
|
| 1666 |
+
"loss": 0.38,
|
| 1667 |
+
"loss_nan_ranks": 0,
|
| 1668 |
+
"loss_rank_avg": 0.09158598631620407,
|
| 1669 |
+
"step": 755,
|
| 1670 |
+
"valid_targets_mean": 4844.2,
|
| 1671 |
+
"valid_targets_min": 1125
|
| 1672 |
+
},
|
| 1673 |
+
{
|
| 1674 |
+
"epoch": 4.8448,
|
| 1675 |
+
"grad_norm": 0.26684033395373213,
|
| 1676 |
+
"learning_rate": 1.337065075470778e-07,
|
| 1677 |
+
"loss": 0.3926,
|
| 1678 |
+
"loss_nan_ranks": 0,
|
| 1679 |
+
"loss_rank_avg": 0.09115723520517349,
|
| 1680 |
+
"step": 760,
|
| 1681 |
+
"valid_targets_mean": 3444.8,
|
| 1682 |
+
"valid_targets_min": 820
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 4.8768,
|
| 1686 |
+
"grad_norm": 0.258854589815443,
|
| 1687 |
+
"learning_rate": 8.725953153150279e-08,
|
| 1688 |
+
"loss": 0.3866,
|
| 1689 |
+
"loss_nan_ranks": 0,
|
| 1690 |
+
"loss_rank_avg": 0.10301363468170166,
|
| 1691 |
+
"step": 765,
|
| 1692 |
+
"valid_targets_mean": 4948.0,
|
| 1693 |
+
"valid_targets_min": 807
|
| 1694 |
+
},
|
| 1695 |
+
{
|
| 1696 |
+
"epoch": 4.9088,
|
| 1697 |
+
"grad_norm": 0.2624455783886108,
|
| 1698 |
+
"learning_rate": 5.066952630711886e-08,
|
| 1699 |
+
"loss": 0.3764,
|
| 1700 |
+
"loss_nan_ranks": 0,
|
| 1701 |
+
"loss_rank_avg": 0.08958660066127777,
|
| 1702 |
+
"step": 770,
|
| 1703 |
+
"valid_targets_mean": 3562.5,
|
| 1704 |
+
"valid_targets_min": 707
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 4.9408,
|
| 1708 |
+
"grad_norm": 0.276084245733527,
|
| 1709 |
+
"learning_rate": 2.3954604228342283e-08,
|
| 1710 |
+
"loss": 0.3897,
|
| 1711 |
+
"loss_nan_ranks": 0,
|
| 1712 |
+
"loss_rank_avg": 0.09636662155389786,
|
| 1713 |
+
"step": 775,
|
| 1714 |
+
"valid_targets_mean": 4382.5,
|
| 1715 |
+
"valid_targets_min": 754
|
| 1716 |
+
},
|
| 1717 |
+
{
|
| 1718 |
+
"epoch": 4.9728,
|
| 1719 |
+
"grad_norm": 0.24631738908048942,
|
| 1720 |
+
"learning_rate": 7.12798940197601e-09,
|
| 1721 |
+
"loss": 0.3905,
|
| 1722 |
+
"loss_nan_ranks": 0,
|
| 1723 |
+
"loss_rank_avg": 0.08279719948768616,
|
| 1724 |
+
"step": 780,
|
| 1725 |
+
"valid_targets_mean": 3800.4,
|
| 1726 |
+
"valid_targets_min": 950
|
| 1727 |
+
},
|
| 1728 |
+
{
|
| 1729 |
+
"epoch": 5.0,
|
| 1730 |
+
"grad_norm": 0.5798931353670957,
|
| 1731 |
+
"learning_rate": 1.9801114115480802e-10,
|
| 1732 |
+
"loss": 0.3821,
|
| 1733 |
+
"loss_nan_ranks": 0,
|
| 1734 |
+
"loss_rank_avg": 0.38632673025131226,
|
| 1735 |
+
"step": 785,
|
| 1736 |
+
"valid_targets_mean": 3155.6,
|
| 1737 |
+
"valid_targets_min": 917
|
| 1738 |
+
},
|
| 1739 |
+
{
|
| 1740 |
+
"epoch": 5.0,
|
| 1741 |
+
"loss_nan_ranks": 0,
|
| 1742 |
+
"loss_rank_avg": 0.38632673025131226,
|
| 1743 |
+
"step": 785,
|
| 1744 |
+
"total_flos": 1.2145665807220736e+18,
|
| 1745 |
+
"train_loss": 0.4196553195358082,
|
| 1746 |
+
"train_runtime": 16441.9592,
|
| 1747 |
+
"train_samples_per_second": 3.04,
|
| 1748 |
+
"train_steps_per_second": 0.048,
|
| 1749 |
+
"valid_targets_mean": 3155.6,
|
| 1750 |
+
"valid_targets_min": 917
|
| 1751 |
+
}
|
| 1752 |
+
],
|
| 1753 |
+
"logging_steps": 5,
|
| 1754 |
+
"max_steps": 785,
|
| 1755 |
+
"num_input_tokens_seen": 0,
|
| 1756 |
+
"num_train_epochs": 5,
|
| 1757 |
+
"save_steps": 500,
|
| 1758 |
+
"stateful_callbacks": {
|
| 1759 |
+
"TrainerControl": {
|
| 1760 |
+
"args": {
|
| 1761 |
+
"should_epoch_stop": false,
|
| 1762 |
+
"should_evaluate": false,
|
| 1763 |
+
"should_log": false,
|
| 1764 |
+
"should_save": false,
|
| 1765 |
+
"should_training_stop": false
|
| 1766 |
+
},
|
| 1767 |
+
"attributes": {}
|
| 1768 |
+
}
|
| 1769 |
+
},
|
| 1770 |
+
"total_flos": 1.2145665807220736e+18,
|
| 1771 |
+
"train_batch_size": 1,
|
| 1772 |
+
"trial_name": null,
|
| 1773 |
+
"trial_params": null
|
| 1774 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b9a678adf1c985bc07081161ccca23bbcf5ef6938301d58c50ecedf17c67c6ae
|
| 3 |
+
size 8529
|
training_loss.png
ADDED
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|