hf-reset commited on
Commit ·
0867df2
0
Parent(s):
Reset repository without checkpoints directories
Browse files- .gitattributes +36 -0
- README.md +60 -0
- added_tokens.json +28 -0
- all_results.json +16 -0
- chat_template.jinja +89 -0
- config.json +68 -0
- generation_config.json +12 -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 +238 -0
- trainer_state.json +2654 -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 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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: nl2bash-3k-traces-restore-hp
|
| 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 |
+
# nl2bash-3k-traces-restore-hp
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on the DCAgent/nl2bash-3k-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 |
+
- total_train_batch_size: 16
|
| 45 |
+
- total_eval_batch_size: 128
|
| 46 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 47 |
+
- lr_scheduler_type: cosine
|
| 48 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 49 |
+
- num_epochs: 6.0
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
|
| 54 |
+
|
| 55 |
+
### Framework versions
|
| 56 |
+
|
| 57 |
+
- Transformers 4.56.0
|
| 58 |
+
- Pytorch 2.7.0+cu128
|
| 59 |
+
- Datasets 3.6.0
|
| 60 |
+
- Tokenizers 0.22.1
|
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": 0.001951399015158965,
|
| 3 |
+
"achieved_tflops_per_gpu_theoretical": 1016.3713688469504,
|
| 4 |
+
"epoch": 6.0,
|
| 5 |
+
"loss_nan_ranks": 0,
|
| 6 |
+
"loss_rank_avg": 0.133074551820755,
|
| 7 |
+
"mfu_percent": 0.00013790805760840742,
|
| 8 |
+
"mfu_percent_theoretical": 71.82836528953713,
|
| 9 |
+
"total_flos": 123574112944128.0,
|
| 10 |
+
"train_loss": 0.2030692549064906,
|
| 11 |
+
"train_runtime": 3957.8692,
|
| 12 |
+
"train_samples_per_second": 4.79,
|
| 13 |
+
"train_steps_per_second": 0.3,
|
| 14 |
+
"valid_targets_mean": 1319.8,
|
| 15 |
+
"valid_targets_min": 875
|
| 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 |
+
"dtype": "bfloat16",
|
| 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 |
+
"pad_token_id": 151643,
|
| 59 |
+
"rms_norm_eps": 1e-06,
|
| 60 |
+
"rope_scaling": null,
|
| 61 |
+
"rope_theta": 1000000,
|
| 62 |
+
"sliding_window": null,
|
| 63 |
+
"tie_word_embeddings": false,
|
| 64 |
+
"transformers_version": "4.56.0",
|
| 65 |
+
"use_cache": false,
|
| 66 |
+
"use_sliding_window": false,
|
| 67 |
+
"vocab_size": 151936
|
| 68 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_sample": true,
|
| 3 |
+
"eos_token_id": [
|
| 4 |
+
151645,
|
| 5 |
+
151643
|
| 6 |
+
],
|
| 7 |
+
"pad_token_id": 151643,
|
| 8 |
+
"temperature": 0.6,
|
| 9 |
+
"top_k": 20,
|
| 10 |
+
"top_p": 0.95,
|
| 11 |
+
"transformers_version": "4.56.0"
|
| 12 |
+
}
|
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:b2ff25930b01ffcdd98c5bb83d6b103fe5f9184cbb01bc173e4d9c111636e9b1
|
| 3 |
+
size 4902257696
|
model-00002-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:719862a4f1ad6cfca37428d712a8657ea7a38721cd06b00911d367935eec5ce9
|
| 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:b57d1078ace2df52e246fa9b24e18e68cde285ef0edead701901b187a500cdf1
|
| 3 |
+
size 4983068496
|
model-00004-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7c28b5eef7400bfb294d2d3965ed853b73dfb2de1a4a5e44e1de3a01091da3e1
|
| 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/nl2bash-3k-traces",
|
| 8 |
+
"training_type": "SFT",
|
| 9 |
+
"training_parameters": "https://huggingface.co/penfever/nl2bash-3k-traces-restore-hp/blob/main/config.json",
|
| 10 |
+
"wandb_link": "https://wandb.ai/dogml/dc-agent/runs/nl2bash-3k-traces_hub-model-id_nl2bash-3k-traces-restore-hp_Qwen3-8B",
|
| 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": 0.001951399015158965,
|
| 3 |
+
"achieved_tflops_per_gpu_theoretical": 1016.3713688469504,
|
| 4 |
+
"epoch": 6.0,
|
| 5 |
+
"loss_nan_ranks": 0,
|
| 6 |
+
"loss_rank_avg": 0.133074551820755,
|
| 7 |
+
"mfu_percent": 0.00013790805760840742,
|
| 8 |
+
"mfu_percent_theoretical": 71.82836528953713,
|
| 9 |
+
"total_flos": 123574112944128.0,
|
| 10 |
+
"train_loss": 0.2030692549064906,
|
| 11 |
+
"train_runtime": 3957.8692,
|
| 12 |
+
"train_samples_per_second": 4.79,
|
| 13 |
+
"train_steps_per_second": 0.3,
|
| 14 |
+
"valid_targets_mean": 1319.8,
|
| 15 |
+
"valid_targets_min": 875
|
| 16 |
+
}
|
trainer_log.jsonl
ADDED
|
@@ -0,0 +1,238 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 5, "total_steps": 1188, "loss": 1.0237, "lr": 1.3445378151260504e-06, "epoch": 0.025252525252525252, "percentage": 0.42, "elapsed_time": "0:00:26", "remaining_time": "1:43:47"}
|
| 2 |
+
{"current_steps": 10, "total_steps": 1188, "loss": 0.9775, "lr": 3.0252100840336137e-06, "epoch": 0.050505050505050504, "percentage": 0.84, "elapsed_time": "0:00:39", "remaining_time": "1:18:09"}
|
| 3 |
+
{"current_steps": 15, "total_steps": 1188, "loss": 0.8599, "lr": 4.705882352941177e-06, "epoch": 0.07575757575757576, "percentage": 1.26, "elapsed_time": "0:00:53", "remaining_time": "1:10:17"}
|
| 4 |
+
{"current_steps": 20, "total_steps": 1188, "loss": 0.7379, "lr": 6.386554621848739e-06, "epoch": 0.10101010101010101, "percentage": 1.68, "elapsed_time": "0:01:08", "remaining_time": "1:06:40"}
|
| 5 |
+
{"current_steps": 25, "total_steps": 1188, "loss": 0.6167, "lr": 8.067226890756303e-06, "epoch": 0.12626262626262627, "percentage": 2.1, "elapsed_time": "0:01:22", "remaining_time": "1:04:19"}
|
| 6 |
+
{"current_steps": 30, "total_steps": 1188, "loss": 0.5299, "lr": 9.747899159663867e-06, "epoch": 0.15151515151515152, "percentage": 2.53, "elapsed_time": "0:01:37", "remaining_time": "1:02:27"}
|
| 7 |
+
{"current_steps": 35, "total_steps": 1188, "loss": 0.4981, "lr": 1.1428571428571429e-05, "epoch": 0.17676767676767677, "percentage": 2.95, "elapsed_time": "0:01:51", "remaining_time": "1:01:12"}
|
| 8 |
+
{"current_steps": 40, "total_steps": 1188, "loss": 0.4407, "lr": 1.3109243697478993e-05, "epoch": 0.20202020202020202, "percentage": 3.37, "elapsed_time": "0:02:05", "remaining_time": "1:00:08"}
|
| 9 |
+
{"current_steps": 45, "total_steps": 1188, "loss": 0.414, "lr": 1.4789915966386557e-05, "epoch": 0.22727272727272727, "percentage": 3.79, "elapsed_time": "0:02:20", "remaining_time": "0:59:33"}
|
| 10 |
+
{"current_steps": 50, "total_steps": 1188, "loss": 0.3676, "lr": 1.647058823529412e-05, "epoch": 0.25252525252525254, "percentage": 4.21, "elapsed_time": "0:02:35", "remaining_time": "0:58:58"}
|
| 11 |
+
{"current_steps": 55, "total_steps": 1188, "loss": 0.3464, "lr": 1.8151260504201682e-05, "epoch": 0.2777777777777778, "percentage": 4.63, "elapsed_time": "0:02:49", "remaining_time": "0:58:04"}
|
| 12 |
+
{"current_steps": 60, "total_steps": 1188, "loss": 0.338, "lr": 1.9831932773109244e-05, "epoch": 0.30303030303030304, "percentage": 5.05, "elapsed_time": "0:03:03", "remaining_time": "0:57:37"}
|
| 13 |
+
{"current_steps": 65, "total_steps": 1188, "loss": 0.3275, "lr": 2.1512605042016807e-05, "epoch": 0.3282828282828283, "percentage": 5.47, "elapsed_time": "0:03:18", "remaining_time": "0:57:06"}
|
| 14 |
+
{"current_steps": 70, "total_steps": 1188, "loss": 0.2979, "lr": 2.3193277310924373e-05, "epoch": 0.35353535353535354, "percentage": 5.89, "elapsed_time": "0:03:32", "remaining_time": "0:56:28"}
|
| 15 |
+
{"current_steps": 75, "total_steps": 1188, "loss": 0.2957, "lr": 2.4873949579831935e-05, "epoch": 0.3787878787878788, "percentage": 6.31, "elapsed_time": "0:03:46", "remaining_time": "0:55:55"}
|
| 16 |
+
{"current_steps": 80, "total_steps": 1188, "loss": 0.3063, "lr": 2.6554621848739497e-05, "epoch": 0.40404040404040403, "percentage": 6.73, "elapsed_time": "0:04:00", "remaining_time": "0:55:27"}
|
| 17 |
+
{"current_steps": 85, "total_steps": 1188, "loss": 0.2973, "lr": 2.8235294117647063e-05, "epoch": 0.4292929292929293, "percentage": 7.15, "elapsed_time": "0:04:14", "remaining_time": "0:55:01"}
|
| 18 |
+
{"current_steps": 90, "total_steps": 1188, "loss": 0.2854, "lr": 2.9915966386554626e-05, "epoch": 0.45454545454545453, "percentage": 7.58, "elapsed_time": "0:04:28", "remaining_time": "0:54:41"}
|
| 19 |
+
{"current_steps": 95, "total_steps": 1188, "loss": 0.2698, "lr": 3.159663865546219e-05, "epoch": 0.4797979797979798, "percentage": 8.0, "elapsed_time": "0:04:43", "remaining_time": "0:54:22"}
|
| 20 |
+
{"current_steps": 100, "total_steps": 1188, "loss": 0.2831, "lr": 3.3277310924369754e-05, "epoch": 0.5050505050505051, "percentage": 8.42, "elapsed_time": "0:04:58", "remaining_time": "0:54:02"}
|
| 21 |
+
{"current_steps": 105, "total_steps": 1188, "loss": 0.2821, "lr": 3.495798319327731e-05, "epoch": 0.5303030303030303, "percentage": 8.84, "elapsed_time": "0:06:15", "remaining_time": "1:04:37"}
|
| 22 |
+
{"current_steps": 110, "total_steps": 1188, "loss": 0.2799, "lr": 3.663865546218488e-05, "epoch": 0.5555555555555556, "percentage": 9.26, "elapsed_time": "0:06:30", "remaining_time": "1:03:44"}
|
| 23 |
+
{"current_steps": 115, "total_steps": 1188, "loss": 0.279, "lr": 3.8319327731092444e-05, "epoch": 0.5808080808080808, "percentage": 9.68, "elapsed_time": "0:06:44", "remaining_time": "1:02:54"}
|
| 24 |
+
{"current_steps": 120, "total_steps": 1188, "loss": 0.2694, "lr": 4e-05, "epoch": 0.6060606060606061, "percentage": 10.1, "elapsed_time": "0:06:58", "remaining_time": "1:02:03"}
|
| 25 |
+
{"current_steps": 125, "total_steps": 1188, "loss": 0.2793, "lr": 3.999784088124753e-05, "epoch": 0.6313131313131313, "percentage": 10.52, "elapsed_time": "0:07:12", "remaining_time": "1:01:20"}
|
| 26 |
+
{"current_steps": 130, "total_steps": 1188, "loss": 0.2597, "lr": 3.99913639911695e-05, "epoch": 0.6565656565656566, "percentage": 10.94, "elapsed_time": "0:07:26", "remaining_time": "1:00:34"}
|
| 27 |
+
{"current_steps": 135, "total_steps": 1188, "loss": 0.2705, "lr": 3.998057072820338e-05, "epoch": 0.6818181818181818, "percentage": 11.36, "elapsed_time": "0:07:40", "remaining_time": "0:59:49"}
|
| 28 |
+
{"current_steps": 140, "total_steps": 1188, "loss": 0.2753, "lr": 3.996546342274282e-05, "epoch": 0.7070707070707071, "percentage": 11.78, "elapsed_time": "0:07:54", "remaining_time": "0:59:13"}
|
| 29 |
+
{"current_steps": 145, "total_steps": 1188, "loss": 0.2598, "lr": 3.9946045336634485e-05, "epoch": 0.7323232323232324, "percentage": 12.21, "elapsed_time": "0:08:09", "remaining_time": "0:58:37"}
|
| 30 |
+
{"current_steps": 150, "total_steps": 1188, "loss": 0.2704, "lr": 3.9922320662473755e-05, "epoch": 0.7575757575757576, "percentage": 12.63, "elapsed_time": "0:08:23", "remaining_time": "0:58:02"}
|
| 31 |
+
{"current_steps": 155, "total_steps": 1188, "loss": 0.2545, "lr": 3.989429452269951e-05, "epoch": 0.7828282828282829, "percentage": 13.05, "elapsed_time": "0:08:37", "remaining_time": "0:57:30"}
|
| 32 |
+
{"current_steps": 160, "total_steps": 1188, "loss": 0.2619, "lr": 3.986197296848816e-05, "epoch": 0.8080808080808081, "percentage": 13.47, "elapsed_time": "0:08:51", "remaining_time": "0:56:54"}
|
| 33 |
+
{"current_steps": 165, "total_steps": 1188, "loss": 0.2628, "lr": 3.982536297844706e-05, "epoch": 0.8333333333333334, "percentage": 13.89, "elapsed_time": "0:09:04", "remaining_time": "0:56:18"}
|
| 34 |
+
{"current_steps": 170, "total_steps": 1188, "loss": 0.2588, "lr": 3.978447245710784e-05, "epoch": 0.8585858585858586, "percentage": 14.31, "elapsed_time": "0:09:18", "remaining_time": "0:55:47"}
|
| 35 |
+
{"current_steps": 175, "total_steps": 1188, "loss": 0.2538, "lr": 3.973931023321962e-05, "epoch": 0.8838383838383839, "percentage": 14.73, "elapsed_time": "0:09:32", "remaining_time": "0:55:16"}
|
| 36 |
+
{"current_steps": 180, "total_steps": 1188, "loss": 0.2409, "lr": 3.9689886057842866e-05, "epoch": 0.9090909090909091, "percentage": 15.15, "elapsed_time": "0:09:47", "remaining_time": "0:54:52"}
|
| 37 |
+
{"current_steps": 185, "total_steps": 1188, "loss": 0.2545, "lr": 3.963621060224396e-05, "epoch": 0.9343434343434344, "percentage": 15.57, "elapsed_time": "0:10:01", "remaining_time": "0:54:21"}
|
| 38 |
+
{"current_steps": 190, "total_steps": 1188, "loss": 0.2553, "lr": 3.957829545559118e-05, "epoch": 0.9595959595959596, "percentage": 15.99, "elapsed_time": "0:10:14", "remaining_time": "0:53:48"}
|
| 39 |
+
{"current_steps": 195, "total_steps": 1188, "loss": 0.2546, "lr": 3.951615312245243e-05, "epoch": 0.9848484848484849, "percentage": 16.41, "elapsed_time": "0:10:29", "remaining_time": "0:53:23"}
|
| 40 |
+
{"current_steps": 200, "total_steps": 1188, "loss": 0.2535, "lr": 3.9449797020095404e-05, "epoch": 1.0101010101010102, "percentage": 16.84, "elapsed_time": "0:10:43", "remaining_time": "0:52:58"}
|
| 41 |
+
{"current_steps": 205, "total_steps": 1188, "loss": 0.2277, "lr": 3.937924147559059e-05, "epoch": 1.0353535353535352, "percentage": 17.26, "elapsed_time": "0:12:00", "remaining_time": "0:57:36"}
|
| 42 |
+
{"current_steps": 210, "total_steps": 1188, "loss": 0.2358, "lr": 3.9304501722717925e-05, "epoch": 1.0606060606060606, "percentage": 17.68, "elapsed_time": "0:12:14", "remaining_time": "0:57:00"}
|
| 43 |
+
{"current_steps": 215, "total_steps": 1188, "loss": 0.2333, "lr": 3.922559389867758e-05, "epoch": 1.0858585858585859, "percentage": 18.1, "elapsed_time": "0:12:28", "remaining_time": "0:56:25"}
|
| 44 |
+
{"current_steps": 220, "total_steps": 1188, "loss": 0.2289, "lr": 3.914253504060585e-05, "epoch": 1.1111111111111112, "percentage": 18.52, "elapsed_time": "0:12:42", "remaining_time": "0:55:53"}
|
| 45 |
+
{"current_steps": 225, "total_steps": 1188, "loss": 0.225, "lr": 3.90553430818965e-05, "epoch": 1.1363636363636362, "percentage": 18.94, "elapsed_time": "0:12:55", "remaining_time": "0:55:19"}
|
| 46 |
+
{"current_steps": 230, "total_steps": 1188, "loss": 0.23, "lr": 3.896403684832887e-05, "epoch": 1.1616161616161615, "percentage": 19.36, "elapsed_time": "0:13:08", "remaining_time": "0:54:44"}
|
| 47 |
+
{"current_steps": 235, "total_steps": 1188, "loss": 0.2314, "lr": 3.886863605400306e-05, "epoch": 1.1868686868686869, "percentage": 19.78, "elapsed_time": "0:13:22", "remaining_time": "0:54:13"}
|
| 48 |
+
{"current_steps": 240, "total_steps": 1188, "loss": 0.2231, "lr": 3.876916129708347e-05, "epoch": 1.2121212121212122, "percentage": 20.2, "elapsed_time": "0:13:36", "remaining_time": "0:53:45"}
|
| 49 |
+
{"current_steps": 245, "total_steps": 1188, "loss": 0.2363, "lr": 3.866563405535142e-05, "epoch": 1.2373737373737375, "percentage": 20.62, "elapsed_time": "0:13:50", "remaining_time": "0:53:17"}
|
| 50 |
+
{"current_steps": 250, "total_steps": 1188, "loss": 0.2187, "lr": 3.855807668156779e-05, "epoch": 1.2626262626262625, "percentage": 21.04, "elapsed_time": "0:14:04", "remaining_time": "0:52:48"}
|
| 51 |
+
{"current_steps": 255, "total_steps": 1188, "loss": 0.2273, "lr": 3.844651239864687e-05, "epoch": 1.2878787878787878, "percentage": 21.46, "elapsed_time": "0:14:18", "remaining_time": "0:52:21"}
|
| 52 |
+
{"current_steps": 260, "total_steps": 1188, "loss": 0.227, "lr": 3.8330965294642186e-05, "epoch": 1.3131313131313131, "percentage": 21.89, "elapsed_time": "0:14:32", "remaining_time": "0:51:52"}
|
| 53 |
+
{"current_steps": 265, "total_steps": 1188, "loss": 0.2331, "lr": 3.821146031754565e-05, "epoch": 1.3383838383838385, "percentage": 22.31, "elapsed_time": "0:14:46", "remaining_time": "0:51:26"}
|
| 54 |
+
{"current_steps": 270, "total_steps": 1188, "loss": 0.2198, "lr": 3.808802326990096e-05, "epoch": 1.3636363636363638, "percentage": 22.73, "elapsed_time": "0:15:00", "remaining_time": "0:51:01"}
|
| 55 |
+
{"current_steps": 275, "total_steps": 1188, "loss": 0.2212, "lr": 3.7960680803232544e-05, "epoch": 1.3888888888888888, "percentage": 23.15, "elapsed_time": "0:15:14", "remaining_time": "0:50:35"}
|
| 56 |
+
{"current_steps": 280, "total_steps": 1188, "loss": 0.2239, "lr": 3.782946041229119e-05, "epoch": 1.4141414141414141, "percentage": 23.57, "elapsed_time": "0:15:27", "remaining_time": "0:50:07"}
|
| 57 |
+
{"current_steps": 285, "total_steps": 1188, "loss": 0.234, "lr": 3.769439042911758e-05, "epoch": 1.4393939393939394, "percentage": 23.99, "elapsed_time": "0:15:40", "remaining_time": "0:49:39"}
|
| 58 |
+
{"current_steps": 290, "total_steps": 1188, "loss": 0.2173, "lr": 3.755550001692506e-05, "epoch": 1.4646464646464645, "percentage": 24.41, "elapsed_time": "0:15:54", "remaining_time": "0:49:15"}
|
| 59 |
+
{"current_steps": 295, "total_steps": 1188, "loss": 0.2105, "lr": 3.7412819163802986e-05, "epoch": 1.4898989898989898, "percentage": 24.83, "elapsed_time": "0:16:07", "remaining_time": "0:48:49"}
|
| 60 |
+
{"current_steps": 300, "total_steps": 1188, "loss": 0.2359, "lr": 3.726637867624191e-05, "epoch": 1.5151515151515151, "percentage": 25.25, "elapsed_time": "0:16:21", "remaining_time": "0:48:25"}
|
| 61 |
+
{"current_steps": 305, "total_steps": 1188, "loss": 0.2152, "lr": 3.711621017248213e-05, "epoch": 1.5404040404040404, "percentage": 25.67, "elapsed_time": "0:17:38", "remaining_time": "0:51:05"}
|
| 62 |
+
{"current_steps": 310, "total_steps": 1188, "loss": 0.2259, "lr": 3.6962346075686876e-05, "epoch": 1.5656565656565657, "percentage": 26.09, "elapsed_time": "0:17:54", "remaining_time": "0:50:41"}
|
| 63 |
+
{"current_steps": 315, "total_steps": 1188, "loss": 0.2276, "lr": 3.680481960694183e-05, "epoch": 1.5909090909090908, "percentage": 26.52, "elapsed_time": "0:18:07", "remaining_time": "0:50:14"}
|
| 64 |
+
{"current_steps": 320, "total_steps": 1188, "loss": 0.2275, "lr": 3.6643664778082254e-05, "epoch": 1.6161616161616161, "percentage": 26.94, "elapsed_time": "0:18:21", "remaining_time": "0:49:47"}
|
| 65 |
+
{"current_steps": 325, "total_steps": 1188, "loss": 0.2193, "lr": 3.6478916384349465e-05, "epoch": 1.6414141414141414, "percentage": 27.36, "elapsed_time": "0:18:34", "remaining_time": "0:49:20"}
|
| 66 |
+
{"current_steps": 330, "total_steps": 1188, "loss": 0.2243, "lr": 3.631060999687809e-05, "epoch": 1.6666666666666665, "percentage": 27.78, "elapsed_time": "0:18:48", "remaining_time": "0:48:54"}
|
| 67 |
+
{"current_steps": 335, "total_steps": 1188, "loss": 0.2132, "lr": 3.613878195501586e-05, "epoch": 1.691919191919192, "percentage": 28.2, "elapsed_time": "0:19:02", "remaining_time": "0:48:28"}
|
| 68 |
+
{"current_steps": 340, "total_steps": 1188, "loss": 0.2148, "lr": 3.596346935847752e-05, "epoch": 1.7171717171717171, "percentage": 28.62, "elapsed_time": "0:19:16", "remaining_time": "0:48:03"}
|
| 69 |
+
{"current_steps": 345, "total_steps": 1188, "loss": 0.225, "lr": 3.578471005933454e-05, "epoch": 1.7424242424242424, "percentage": 29.04, "elapsed_time": "0:19:30", "remaining_time": "0:47:40"}
|
| 70 |
+
{"current_steps": 350, "total_steps": 1188, "loss": 0.2148, "lr": 3.5602542653842416e-05, "epoch": 1.7676767676767677, "percentage": 29.46, "elapsed_time": "0:19:43", "remaining_time": "0:47:14"}
|
| 71 |
+
{"current_steps": 355, "total_steps": 1188, "loss": 0.2203, "lr": 3.541700647410728e-05, "epoch": 1.7929292929292928, "percentage": 29.88, "elapsed_time": "0:19:57", "remaining_time": "0:46:49"}
|
| 72 |
+
{"current_steps": 360, "total_steps": 1188, "loss": 0.2307, "lr": 3.522814157959362e-05, "epoch": 1.8181818181818183, "percentage": 30.3, "elapsed_time": "0:20:11", "remaining_time": "0:46:26"}
|
| 73 |
+
{"current_steps": 365, "total_steps": 1188, "loss": 0.23, "lr": 3.5035988748474974e-05, "epoch": 1.8434343434343434, "percentage": 30.72, "elapsed_time": "0:20:25", "remaining_time": "0:46:02"}
|
| 74 |
+
{"current_steps": 370, "total_steps": 1188, "loss": 0.2128, "lr": 3.484058946882946e-05, "epoch": 1.8686868686868687, "percentage": 31.14, "elapsed_time": "0:20:38", "remaining_time": "0:45:38"}
|
| 75 |
+
{"current_steps": 375, "total_steps": 1188, "loss": 0.221, "lr": 3.4641985929681954e-05, "epoch": 1.893939393939394, "percentage": 31.57, "elapsed_time": "0:20:52", "remaining_time": "0:45:15"}
|
| 76 |
+
{"current_steps": 380, "total_steps": 1188, "loss": 0.2149, "lr": 3.4440221011895026e-05, "epoch": 1.9191919191919191, "percentage": 31.99, "elapsed_time": "0:21:06", "remaining_time": "0:44:52"}
|
| 77 |
+
{"current_steps": 385, "total_steps": 1188, "loss": 0.2226, "lr": 3.423533827891044e-05, "epoch": 1.9444444444444444, "percentage": 32.41, "elapsed_time": "0:21:18", "remaining_time": "0:44:27"}
|
| 78 |
+
{"current_steps": 390, "total_steps": 1188, "loss": 0.2269, "lr": 3.402738196734327e-05, "epoch": 1.9696969696969697, "percentage": 32.83, "elapsed_time": "0:21:32", "remaining_time": "0:44:04"}
|
| 79 |
+
{"current_steps": 395, "total_steps": 1188, "loss": 0.2196, "lr": 3.381639697743073e-05, "epoch": 1.9949494949494948, "percentage": 33.25, "elapsed_time": "0:21:46", "remaining_time": "0:43:43"}
|
| 80 |
+
{"current_steps": 400, "total_steps": 1188, "loss": 0.1951, "lr": 3.3602428863337625e-05, "epoch": 2.0202020202020203, "percentage": 33.67, "elapsed_time": "0:22:00", "remaining_time": "0:43:21"}
|
| 81 |
+
{"current_steps": 405, "total_steps": 1188, "loss": 0.1904, "lr": 3.338552382332073e-05, "epoch": 2.0454545454545454, "percentage": 34.09, "elapsed_time": "0:23:22", "remaining_time": "0:45:12"}
|
| 82 |
+
{"current_steps": 410, "total_steps": 1188, "loss": 0.1952, "lr": 3.3165728689753976e-05, "epoch": 2.0707070707070705, "percentage": 34.51, "elapsed_time": "0:23:36", "remaining_time": "0:44:48"}
|
| 83 |
+
{"current_steps": 415, "total_steps": 1188, "loss": 0.1938, "lr": 3.2943090919016815e-05, "epoch": 2.095959595959596, "percentage": 34.93, "elapsed_time": "0:23:50", "remaining_time": "0:44:24"}
|
| 84 |
+
{"current_steps": 420, "total_steps": 1188, "loss": 0.1834, "lr": 3.2717658581247844e-05, "epoch": 2.121212121212121, "percentage": 35.35, "elapsed_time": "0:24:05", "remaining_time": "0:44:03"}
|
| 85 |
+
{"current_steps": 425, "total_steps": 1188, "loss": 0.1995, "lr": 3.248948034996583e-05, "epoch": 2.1464646464646466, "percentage": 35.77, "elapsed_time": "0:24:18", "remaining_time": "0:43:39"}
|
| 86 |
+
{"current_steps": 430, "total_steps": 1188, "loss": 0.184, "lr": 3.2258605491560606e-05, "epoch": 2.1717171717171717, "percentage": 36.2, "elapsed_time": "0:24:32", "remaining_time": "0:43:15"}
|
| 87 |
+
{"current_steps": 435, "total_steps": 1188, "loss": 0.1889, "lr": 3.2025083854655776e-05, "epoch": 2.196969696969697, "percentage": 36.62, "elapsed_time": "0:24:45", "remaining_time": "0:42:51"}
|
| 88 |
+
{"current_steps": 440, "total_steps": 1188, "loss": 0.1922, "lr": 3.178896585934588e-05, "epoch": 2.2222222222222223, "percentage": 37.04, "elapsed_time": "0:24:58", "remaining_time": "0:42:28"}
|
| 89 |
+
{"current_steps": 445, "total_steps": 1188, "loss": 0.181, "lr": 3.1550302486310076e-05, "epoch": 2.2474747474747474, "percentage": 37.46, "elapsed_time": "0:25:11", "remaining_time": "0:42:04"}
|
| 90 |
+
{"current_steps": 450, "total_steps": 1188, "loss": 0.1932, "lr": 3.130914526580478e-05, "epoch": 2.2727272727272725, "percentage": 37.88, "elapsed_time": "0:25:24", "remaining_time": "0:41:40"}
|
| 91 |
+
{"current_steps": 455, "total_steps": 1188, "loss": 0.1943, "lr": 3.10655462665377e-05, "epoch": 2.297979797979798, "percentage": 38.3, "elapsed_time": "0:25:38", "remaining_time": "0:41:18"}
|
| 92 |
+
{"current_steps": 460, "total_steps": 1188, "loss": 0.1858, "lr": 3.0819558084425574e-05, "epoch": 2.323232323232323, "percentage": 38.72, "elapsed_time": "0:25:52", "remaining_time": "0:40:56"}
|
| 93 |
+
{"current_steps": 465, "total_steps": 1188, "loss": 0.1912, "lr": 3.0571233831238093e-05, "epoch": 2.3484848484848486, "percentage": 39.14, "elapsed_time": "0:26:06", "remaining_time": "0:40:35"}
|
| 94 |
+
{"current_steps": 470, "total_steps": 1188, "loss": 0.1907, "lr": 3.032062712313044e-05, "epoch": 2.3737373737373737, "percentage": 39.56, "elapsed_time": "0:26:20", "remaining_time": "0:40:13"}
|
| 95 |
+
{"current_steps": 475, "total_steps": 1188, "loss": 0.1963, "lr": 3.0067792069066902e-05, "epoch": 2.398989898989899, "percentage": 39.98, "elapsed_time": "0:26:34", "remaining_time": "0:39:53"}
|
| 96 |
+
{"current_steps": 480, "total_steps": 1188, "loss": 0.2008, "lr": 2.9812783259138133e-05, "epoch": 2.4242424242424243, "percentage": 40.4, "elapsed_time": "0:26:48", "remaining_time": "0:39:32"}
|
| 97 |
+
{"current_steps": 485, "total_steps": 1188, "loss": 0.1868, "lr": 2.955565575277449e-05, "epoch": 2.4494949494949494, "percentage": 40.82, "elapsed_time": "0:27:01", "remaining_time": "0:39:11"}
|
| 98 |
+
{"current_steps": 490, "total_steps": 1188, "loss": 0.1896, "lr": 2.929646506685805e-05, "epoch": 2.474747474747475, "percentage": 41.25, "elapsed_time": "0:27:14", "remaining_time": "0:38:48"}
|
| 99 |
+
{"current_steps": 495, "total_steps": 1188, "loss": 0.1853, "lr": 2.9035267163735856e-05, "epoch": 2.5, "percentage": 41.67, "elapsed_time": "0:27:27", "remaining_time": "0:38:26"}
|
| 100 |
+
{"current_steps": 500, "total_steps": 1188, "loss": 0.1917, "lr": 2.8772118439136972e-05, "epoch": 2.525252525252525, "percentage": 42.09, "elapsed_time": "0:27:41", "remaining_time": "0:38:06"}
|
| 101 |
+
{"current_steps": 505, "total_steps": 1188, "loss": 0.2, "lr": 2.8507075709996015e-05, "epoch": 2.5505050505050506, "percentage": 42.51, "elapsed_time": "0:29:05", "remaining_time": "0:39:20"}
|
| 102 |
+
{"current_steps": 510, "total_steps": 1188, "loss": 0.1841, "lr": 2.8240196202185636e-05, "epoch": 2.5757575757575757, "percentage": 42.93, "elapsed_time": "0:29:18", "remaining_time": "0:38:57"}
|
| 103 |
+
{"current_steps": 515, "total_steps": 1188, "loss": 0.2015, "lr": 2.797153753816084e-05, "epoch": 2.601010101010101, "percentage": 43.35, "elapsed_time": "0:29:31", "remaining_time": "0:38:35"}
|
| 104 |
+
{"current_steps": 520, "total_steps": 1188, "loss": 0.1847, "lr": 2.770115772451758e-05, "epoch": 2.6262626262626263, "percentage": 43.77, "elapsed_time": "0:29:45", "remaining_time": "0:38:13"}
|
| 105 |
+
{"current_steps": 525, "total_steps": 1188, "loss": 0.1868, "lr": 2.7429115139468443e-05, "epoch": 2.6515151515151514, "percentage": 44.19, "elapsed_time": "0:29:58", "remaining_time": "0:37:51"}
|
| 106 |
+
{"current_steps": 530, "total_steps": 1188, "loss": 0.1955, "lr": 2.7155468520238116e-05, "epoch": 2.676767676767677, "percentage": 44.61, "elapsed_time": "0:30:13", "remaining_time": "0:37:30"}
|
| 107 |
+
{"current_steps": 535, "total_steps": 1188, "loss": 0.1881, "lr": 2.6880276950381316e-05, "epoch": 2.702020202020202, "percentage": 45.03, "elapsed_time": "0:30:27", "remaining_time": "0:37:10"}
|
| 108 |
+
{"current_steps": 540, "total_steps": 1188, "loss": 0.1805, "lr": 2.6603599847025935e-05, "epoch": 2.7272727272727275, "percentage": 45.45, "elapsed_time": "0:30:39", "remaining_time": "0:36:47"}
|
| 109 |
+
{"current_steps": 545, "total_steps": 1188, "loss": 0.191, "lr": 2.63254969480442e-05, "epoch": 2.7525252525252526, "percentage": 45.88, "elapsed_time": "0:30:53", "remaining_time": "0:36:26"}
|
| 110 |
+
{"current_steps": 550, "total_steps": 1188, "loss": 0.1875, "lr": 2.6046028299154545e-05, "epoch": 2.7777777777777777, "percentage": 46.3, "elapsed_time": "0:31:08", "remaining_time": "0:36:07"}
|
| 111 |
+
{"current_steps": 555, "total_steps": 1188, "loss": 0.1886, "lr": 2.5765254240957024e-05, "epoch": 2.8030303030303028, "percentage": 46.72, "elapsed_time": "0:31:21", "remaining_time": "0:35:46"}
|
| 112 |
+
{"current_steps": 560, "total_steps": 1188, "loss": 0.1867, "lr": 2.5483235395905056e-05, "epoch": 2.8282828282828283, "percentage": 47.14, "elapsed_time": "0:31:34", "remaining_time": "0:35:24"}
|
| 113 |
+
{"current_steps": 565, "total_steps": 1188, "loss": 0.1894, "lr": 2.5200032655216343e-05, "epoch": 2.8535353535353534, "percentage": 47.56, "elapsed_time": "0:31:47", "remaining_time": "0:35:03"}
|
| 114 |
+
{"current_steps": 570, "total_steps": 1188, "loss": 0.1858, "lr": 2.4915707165725694e-05, "epoch": 2.878787878787879, "percentage": 47.98, "elapsed_time": "0:32:00", "remaining_time": "0:34:42"}
|
| 115 |
+
{"current_steps": 575, "total_steps": 1188, "loss": 0.1847, "lr": 2.4630320316682724e-05, "epoch": 2.904040404040404, "percentage": 48.4, "elapsed_time": "0:32:13", "remaining_time": "0:34:21"}
|
| 116 |
+
{"current_steps": 580, "total_steps": 1188, "loss": 0.1856, "lr": 2.4343933726497183e-05, "epoch": 2.929292929292929, "percentage": 48.82, "elapsed_time": "0:32:26", "remaining_time": "0:34:00"}
|
| 117 |
+
{"current_steps": 585, "total_steps": 1188, "loss": 0.1887, "lr": 2.4056609229434812e-05, "epoch": 2.9545454545454546, "percentage": 49.24, "elapsed_time": "0:32:39", "remaining_time": "0:33:39"}
|
| 118 |
+
{"current_steps": 590, "total_steps": 1188, "loss": 0.1867, "lr": 2.376840886226656e-05, "epoch": 2.9797979797979797, "percentage": 49.66, "elapsed_time": "0:32:51", "remaining_time": "0:33:18"}
|
| 119 |
+
{"current_steps": 595, "total_steps": 1188, "loss": 0.1831, "lr": 2.347939485087416e-05, "epoch": 3.005050505050505, "percentage": 50.08, "elapsed_time": "0:33:04", "remaining_time": "0:32:58"}
|
| 120 |
+
{"current_steps": 600, "total_steps": 1188, "loss": 0.157, "lr": 2.3189629596814788e-05, "epoch": 3.0303030303030303, "percentage": 50.51, "elapsed_time": "0:33:18", "remaining_time": "0:32:39"}
|
| 121 |
+
{"current_steps": 605, "total_steps": 1188, "loss": 0.1605, "lr": 2.2899175663847823e-05, "epoch": 3.0555555555555554, "percentage": 50.93, "elapsed_time": "0:34:39", "remaining_time": "0:33:23"}
|
| 122 |
+
{"current_steps": 610, "total_steps": 1188, "loss": 0.1609, "lr": 2.2608095764426602e-05, "epoch": 3.080808080808081, "percentage": 51.35, "elapsed_time": "0:34:52", "remaining_time": "0:33:02"}
|
| 123 |
+
{"current_steps": 615, "total_steps": 1188, "loss": 0.1649, "lr": 2.2316452746158063e-05, "epoch": 3.106060606060606, "percentage": 51.77, "elapsed_time": "0:35:06", "remaining_time": "0:32:42"}
|
| 124 |
+
{"current_steps": 620, "total_steps": 1188, "loss": 0.161, "lr": 2.2024309578233174e-05, "epoch": 3.1313131313131315, "percentage": 52.19, "elapsed_time": "0:35:20", "remaining_time": "0:32:22"}
|
| 125 |
+
{"current_steps": 625, "total_steps": 1188, "loss": 0.1574, "lr": 2.1731729337831173e-05, "epoch": 3.1565656565656566, "percentage": 52.61, "elapsed_time": "0:35:33", "remaining_time": "0:32:02"}
|
| 126 |
+
{"current_steps": 630, "total_steps": 1188, "loss": 0.165, "lr": 2.143877519650042e-05, "epoch": 3.1818181818181817, "percentage": 53.03, "elapsed_time": "0:35:45", "remaining_time": "0:31:40"}
|
| 127 |
+
{"current_steps": 635, "total_steps": 1188, "loss": 0.1654, "lr": 2.1145510406518928e-05, "epoch": 3.207070707070707, "percentage": 53.45, "elapsed_time": "0:36:00", "remaining_time": "0:31:21"}
|
| 128 |
+
{"current_steps": 640, "total_steps": 1188, "loss": 0.1603, "lr": 2.0851998287237452e-05, "epoch": 3.2323232323232323, "percentage": 53.87, "elapsed_time": "0:36:12", "remaining_time": "0:31:00"}
|
| 129 |
+
{"current_steps": 645, "total_steps": 1188, "loss": 0.1568, "lr": 2.0558302211408075e-05, "epoch": 3.257575757575758, "percentage": 54.29, "elapsed_time": "0:36:27", "remaining_time": "0:30:41"}
|
| 130 |
+
{"current_steps": 650, "total_steps": 1188, "loss": 0.1657, "lr": 2.0264485591501272e-05, "epoch": 3.282828282828283, "percentage": 54.71, "elapsed_time": "0:36:41", "remaining_time": "0:30:21"}
|
| 131 |
+
{"current_steps": 655, "total_steps": 1188, "loss": 0.1626, "lr": 1.9970611866014432e-05, "epoch": 3.308080808080808, "percentage": 55.13, "elapsed_time": "0:36:53", "remaining_time": "0:30:01"}
|
| 132 |
+
{"current_steps": 660, "total_steps": 1188, "loss": 0.1581, "lr": 1.967674448577471e-05, "epoch": 3.3333333333333335, "percentage": 55.56, "elapsed_time": "0:37:06", "remaining_time": "0:29:41"}
|
| 133 |
+
{"current_steps": 665, "total_steps": 1188, "loss": 0.1586, "lr": 1.9382946900239247e-05, "epoch": 3.3585858585858586, "percentage": 55.98, "elapsed_time": "0:37:18", "remaining_time": "0:29:20"}
|
| 134 |
+
{"current_steps": 670, "total_steps": 1188, "loss": 0.171, "lr": 1.9089282543795692e-05, "epoch": 3.3838383838383836, "percentage": 56.4, "elapsed_time": "0:37:32", "remaining_time": "0:29:01"}
|
| 135 |
+
{"current_steps": 675, "total_steps": 1188, "loss": 0.1549, "lr": 1.879581482206592e-05, "epoch": 3.409090909090909, "percentage": 56.82, "elapsed_time": "0:37:45", "remaining_time": "0:28:41"}
|
| 136 |
+
{"current_steps": 680, "total_steps": 1188, "loss": 0.1645, "lr": 1.8502607098216056e-05, "epoch": 3.4343434343434343, "percentage": 57.24, "elapsed_time": "0:37:59", "remaining_time": "0:28:22"}
|
| 137 |
+
{"current_steps": 685, "total_steps": 1188, "loss": 0.1636, "lr": 1.8209722679275602e-05, "epoch": 3.45959595959596, "percentage": 57.66, "elapsed_time": "0:38:13", "remaining_time": "0:28:03"}
|
| 138 |
+
{"current_steps": 690, "total_steps": 1188, "loss": 0.1615, "lr": 1.791722480246868e-05, "epoch": 3.484848484848485, "percentage": 58.08, "elapsed_time": "0:38:25", "remaining_time": "0:27:44"}
|
| 139 |
+
{"current_steps": 695, "total_steps": 1188, "loss": 0.1592, "lr": 1.762517662156037e-05, "epoch": 3.51010101010101, "percentage": 58.5, "elapsed_time": "0:38:38", "remaining_time": "0:27:24"}
|
| 140 |
+
{"current_steps": 700, "total_steps": 1188, "loss": 0.1648, "lr": 1.733364119322109e-05, "epoch": 3.5353535353535355, "percentage": 58.92, "elapsed_time": "0:38:51", "remaining_time": "0:27:05"}
|
| 141 |
+
{"current_steps": 705, "total_steps": 1188, "loss": 0.1683, "lr": 1.704268146341185e-05, "epoch": 3.5606060606060606, "percentage": 59.34, "elapsed_time": "0:40:07", "remaining_time": "0:27:29"}
|
| 142 |
+
{"current_steps": 710, "total_steps": 1188, "loss": 0.1626, "lr": 1.675236025379355e-05, "epoch": 3.5858585858585856, "percentage": 59.76, "elapsed_time": "0:40:21", "remaining_time": "0:27:10"}
|
| 143 |
+
{"current_steps": 715, "total_steps": 1188, "loss": 0.1628, "lr": 1.6462740248162988e-05, "epoch": 3.611111111111111, "percentage": 60.19, "elapsed_time": "0:40:34", "remaining_time": "0:26:50"}
|
| 144 |
+
{"current_steps": 720, "total_steps": 1188, "loss": 0.1579, "lr": 1.6173883978918682e-05, "epoch": 3.6363636363636362, "percentage": 60.61, "elapsed_time": "0:40:46", "remaining_time": "0:26:30"}
|
| 145 |
+
{"current_steps": 725, "total_steps": 1188, "loss": 0.1606, "lr": 1.5885853813559392e-05, "epoch": 3.6616161616161618, "percentage": 61.03, "elapsed_time": "0:41:00", "remaining_time": "0:26:11"}
|
| 146 |
+
{"current_steps": 730, "total_steps": 1188, "loss": 0.1639, "lr": 1.5598711941218265e-05, "epoch": 3.686868686868687, "percentage": 61.45, "elapsed_time": "0:41:14", "remaining_time": "0:25:52"}
|
| 147 |
+
{"current_steps": 735, "total_steps": 1188, "loss": 0.1686, "lr": 1.531252035923541e-05, "epoch": 3.712121212121212, "percentage": 61.87, "elapsed_time": "0:41:28", "remaining_time": "0:25:34"}
|
| 148 |
+
{"current_steps": 740, "total_steps": 1188, "loss": 0.1652, "lr": 1.5027340859771972e-05, "epoch": 3.7373737373737375, "percentage": 62.29, "elapsed_time": "0:41:42", "remaining_time": "0:25:15"}
|
| 149 |
+
{"current_steps": 745, "total_steps": 1188, "loss": 0.1628, "lr": 1.4743235016468474e-05, "epoch": 3.7626262626262625, "percentage": 62.71, "elapsed_time": "0:41:56", "remaining_time": "0:24:56"}
|
| 150 |
+
{"current_steps": 750, "total_steps": 1188, "loss": 0.1614, "lr": 1.4460264171150296e-05, "epoch": 3.787878787878788, "percentage": 63.13, "elapsed_time": "0:42:09", "remaining_time": "0:24:37"}
|
| 151 |
+
{"current_steps": 755, "total_steps": 1188, "loss": 0.1659, "lr": 1.4178489420583297e-05, "epoch": 3.813131313131313, "percentage": 63.55, "elapsed_time": "0:42:23", "remaining_time": "0:24:18"}
|
| 152 |
+
{"current_steps": 760, "total_steps": 1188, "loss": 0.1595, "lr": 1.3897971603282278e-05, "epoch": 3.8383838383838382, "percentage": 63.97, "elapsed_time": "0:42:35", "remaining_time": "0:23:59"}
|
| 153 |
+
{"current_steps": 765, "total_steps": 1188, "loss": 0.166, "lr": 1.36187712863752e-05, "epoch": 3.8636363636363638, "percentage": 64.39, "elapsed_time": "0:42:49", "remaining_time": "0:23:40"}
|
| 154 |
+
{"current_steps": 770, "total_steps": 1188, "loss": 0.1599, "lr": 1.3340948752526069e-05, "epoch": 3.888888888888889, "percentage": 64.81, "elapsed_time": "0:43:02", "remaining_time": "0:23:22"}
|
| 155 |
+
{"current_steps": 775, "total_steps": 1188, "loss": 0.1596, "lr": 1.3064563986919142e-05, "epoch": 3.9141414141414144, "percentage": 65.24, "elapsed_time": "0:43:15", "remaining_time": "0:23:03"}
|
| 156 |
+
{"current_steps": 780, "total_steps": 1188, "loss": 0.1628, "lr": 1.278967666430745e-05, "epoch": 3.9393939393939394, "percentage": 65.66, "elapsed_time": "0:43:29", "remaining_time": "0:22:45"}
|
| 157 |
+
{"current_steps": 785, "total_steps": 1188, "loss": 0.1641, "lr": 1.2516346136128318e-05, "epoch": 3.9646464646464645, "percentage": 66.08, "elapsed_time": "0:43:43", "remaining_time": "0:22:27"}
|
| 158 |
+
{"current_steps": 790, "total_steps": 1188, "loss": 0.1634, "lr": 1.2244631417688632e-05, "epoch": 3.98989898989899, "percentage": 66.5, "elapsed_time": "0:43:58", "remaining_time": "0:22:09"}
|
| 159 |
+
{"current_steps": 795, "total_steps": 1188, "loss": 0.1509, "lr": 1.197459117542278e-05, "epoch": 4.015151515151516, "percentage": 66.92, "elapsed_time": "0:44:12", "remaining_time": "0:21:51"}
|
| 160 |
+
{"current_steps": 800, "total_steps": 1188, "loss": 0.1365, "lr": 1.170628371422587e-05, "epoch": 4.040404040404041, "percentage": 67.34, "elapsed_time": "0:44:25", "remaining_time": "0:21:32"}
|
| 161 |
+
{"current_steps": 805, "total_steps": 1188, "loss": 0.1454, "lr": 1.1439766964864995e-05, "epoch": 4.065656565656566, "percentage": 67.76, "elapsed_time": "0:45:55", "remaining_time": "0:21:51"}
|
| 162 |
+
{"current_steps": 810, "total_steps": 1188, "loss": 0.1405, "lr": 1.117509847147128e-05, "epoch": 4.090909090909091, "percentage": 68.18, "elapsed_time": "0:46:08", "remaining_time": "0:21:32"}
|
| 163 |
+
{"current_steps": 815, "total_steps": 1188, "loss": 0.138, "lr": 1.0912335379115469e-05, "epoch": 4.116161616161616, "percentage": 68.6, "elapsed_time": "0:46:22", "remaining_time": "0:21:13"}
|
| 164 |
+
{"current_steps": 820, "total_steps": 1188, "loss": 0.1441, "lr": 1.0651534421469569e-05, "epoch": 4.141414141414141, "percentage": 69.02, "elapsed_time": "0:46:33", "remaining_time": "0:20:53"}
|
| 165 |
+
{"current_steps": 825, "total_steps": 1188, "loss": 0.1423, "lr": 1.0392751908557406e-05, "epoch": 4.166666666666667, "percentage": 69.44, "elapsed_time": "0:46:47", "remaining_time": "0:20:35"}
|
| 166 |
+
{"current_steps": 830, "total_steps": 1188, "loss": 0.1385, "lr": 1.013604371459663e-05, "epoch": 4.191919191919192, "percentage": 69.87, "elapsed_time": "0:47:01", "remaining_time": "0:20:16"}
|
| 167 |
+
{"current_steps": 835, "total_steps": 1188, "loss": 0.1434, "lr": 9.881465265934802e-06, "epoch": 4.217171717171717, "percentage": 70.29, "elapsed_time": "0:47:14", "remaining_time": "0:19:58"}
|
| 168 |
+
{"current_steps": 840, "total_steps": 1188, "loss": 0.1395, "lr": 9.62907152908215e-06, "epoch": 4.242424242424242, "percentage": 70.71, "elapsed_time": "0:47:27", "remaining_time": "0:19:39"}
|
| 169 |
+
{"current_steps": 845, "total_steps": 1188, "loss": 0.145, "lr": 9.378916998843716e-06, "epoch": 4.267676767676767, "percentage": 71.13, "elapsed_time": "0:47:39", "remaining_time": "0:19:20"}
|
| 170 |
+
{"current_steps": 850, "total_steps": 1188, "loss": 0.1407, "lr": 9.13105568655322e-06, "epoch": 4.292929292929293, "percentage": 71.55, "elapsed_time": "0:47:53", "remaining_time": "0:19:02"}
|
| 171 |
+
{"current_steps": 855, "total_steps": 1188, "loss": 0.1433, "lr": 8.885541108411386e-06, "epoch": 4.318181818181818, "percentage": 71.97, "elapsed_time": "0:48:05", "remaining_time": "0:18:43"}
|
| 172 |
+
{"current_steps": 860, "total_steps": 1188, "loss": 0.146, "lr": 8.642426273931202e-06, "epoch": 4.343434343434343, "percentage": 72.39, "elapsed_time": "0:48:19", "remaining_time": "0:18:25"}
|
| 173 |
+
{"current_steps": 865, "total_steps": 1188, "loss": 0.1386, "lr": 8.40176367449247e-06, "epoch": 4.3686868686868685, "percentage": 72.81, "elapsed_time": "0:48:32", "remaining_time": "0:18:07"}
|
| 174 |
+
{"current_steps": 870, "total_steps": 1188, "loss": 0.1461, "lr": 8.16360527200833e-06, "epoch": 4.393939393939394, "percentage": 73.23, "elapsed_time": "0:48:45", "remaining_time": "0:17:49"}
|
| 175 |
+
{"current_steps": 875, "total_steps": 1188, "loss": 0.1456, "lr": 7.928002487706077e-06, "epoch": 4.41919191919192, "percentage": 73.65, "elapsed_time": "0:48:57", "remaining_time": "0:17:30"}
|
| 176 |
+
{"current_steps": 880, "total_steps": 1188, "loss": 0.1423, "lr": 7.69500619102469e-06, "epoch": 4.444444444444445, "percentage": 74.07, "elapsed_time": "0:49:10", "remaining_time": "0:17:12"}
|
| 177 |
+
{"current_steps": 885, "total_steps": 1188, "loss": 0.1453, "lr": 7.464666688631497e-06, "epoch": 4.46969696969697, "percentage": 74.49, "elapsed_time": "0:49:23", "remaining_time": "0:16:54"}
|
| 178 |
+
{"current_steps": 890, "total_steps": 1188, "loss": 0.1366, "lr": 7.237033713560415e-06, "epoch": 4.494949494949495, "percentage": 74.92, "elapsed_time": "0:49:36", "remaining_time": "0:16:36"}
|
| 179 |
+
{"current_steps": 895, "total_steps": 1188, "loss": 0.1416, "lr": 7.01215641447395e-06, "epoch": 4.52020202020202, "percentage": 75.34, "elapsed_time": "0:49:48", "remaining_time": "0:16:18"}
|
| 180 |
+
{"current_steps": 900, "total_steps": 1188, "loss": 0.144, "lr": 6.790083345051457e-06, "epoch": 4.545454545454545, "percentage": 75.76, "elapsed_time": "0:50:00", "remaining_time": "0:16:00"}
|
| 181 |
+
{"current_steps": 905, "total_steps": 1188, "loss": 0.142, "lr": 6.570862453505793e-06, "epoch": 4.570707070707071, "percentage": 76.18, "elapsed_time": "0:50:53", "remaining_time": "0:15:54"}
|
| 182 |
+
{"current_steps": 910, "total_steps": 1188, "loss": 0.1398, "lr": 6.35454107223074e-06, "epoch": 4.595959595959596, "percentage": 76.6, "elapsed_time": "0:51:07", "remaining_time": "0:15:37"}
|
| 183 |
+
{"current_steps": 915, "total_steps": 1188, "loss": 0.1419, "lr": 6.141165907581395e-06, "epoch": 4.621212121212121, "percentage": 77.02, "elapsed_time": "0:51:21", "remaining_time": "0:15:19"}
|
| 184 |
+
{"current_steps": 920, "total_steps": 1188, "loss": 0.138, "lr": 5.9307830297896755e-06, "epoch": 4.646464646464646, "percentage": 77.44, "elapsed_time": "0:51:34", "remaining_time": "0:15:01"}
|
| 185 |
+
{"current_steps": 925, "total_steps": 1188, "loss": 0.1378, "lr": 5.723437863017256e-06, "epoch": 4.671717171717171, "percentage": 77.86, "elapsed_time": "0:51:48", "remaining_time": "0:14:43"}
|
| 186 |
+
{"current_steps": 930, "total_steps": 1188, "loss": 0.138, "lr": 5.519175175547919e-06, "epoch": 4.696969696969697, "percentage": 78.28, "elapsed_time": "0:52:00", "remaining_time": "0:14:25"}
|
| 187 |
+
{"current_steps": 935, "total_steps": 1188, "loss": 0.1466, "lr": 5.318039070121557e-06, "epoch": 4.722222222222222, "percentage": 78.7, "elapsed_time": "0:52:14", "remaining_time": "0:14:08"}
|
| 188 |
+
{"current_steps": 940, "total_steps": 1188, "loss": 0.1371, "lr": 5.120072974411863e-06, "epoch": 4.747474747474747, "percentage": 79.12, "elapsed_time": "0:52:27", "remaining_time": "0:13:50"}
|
| 189 |
+
{"current_steps": 945, "total_steps": 1188, "loss": 0.1408, "lr": 4.92531963164981e-06, "epoch": 4.7727272727272725, "percentage": 79.55, "elapsed_time": "0:52:41", "remaining_time": "0:13:33"}
|
| 190 |
+
{"current_steps": 950, "total_steps": 1188, "loss": 0.1377, "lr": 4.733821091394841e-06, "epoch": 4.797979797979798, "percentage": 79.97, "elapsed_time": "0:52:54", "remaining_time": "0:13:15"}
|
| 191 |
+
{"current_steps": 955, "total_steps": 1188, "loss": 0.1341, "lr": 4.5456187004558806e-06, "epoch": 4.8232323232323235, "percentage": 80.39, "elapsed_time": "0:53:08", "remaining_time": "0:12:57"}
|
| 192 |
+
{"current_steps": 960, "total_steps": 1188, "loss": 0.1415, "lr": 4.360753093964094e-06, "epoch": 4.848484848484849, "percentage": 80.81, "elapsed_time": "0:53:22", "remaining_time": "0:12:40"}
|
| 193 |
+
{"current_steps": 965, "total_steps": 1188, "loss": 0.1474, "lr": 4.179264186599239e-06, "epoch": 4.873737373737374, "percentage": 81.23, "elapsed_time": "0:53:36", "remaining_time": "0:12:23"}
|
| 194 |
+
{"current_steps": 970, "total_steps": 1188, "loss": 0.1362, "lr": 4.001191163971645e-06, "epoch": 4.898989898989899, "percentage": 81.65, "elapsed_time": "0:53:49", "remaining_time": "0:12:05"}
|
| 195 |
+
{"current_steps": 975, "total_steps": 1188, "loss": 0.1436, "lr": 3.826572474161565e-06, "epoch": 4.924242424242424, "percentage": 82.07, "elapsed_time": "0:54:02", "remaining_time": "0:11:48"}
|
| 196 |
+
{"current_steps": 980, "total_steps": 1188, "loss": 0.1378, "lr": 3.65544581941776e-06, "epoch": 4.94949494949495, "percentage": 82.49, "elapsed_time": "0:54:14", "remaining_time": "0:11:30"}
|
| 197 |
+
{"current_steps": 985, "total_steps": 1188, "loss": 0.1428, "lr": 3.487848148017161e-06, "epoch": 4.974747474747475, "percentage": 82.91, "elapsed_time": "0:54:28", "remaining_time": "0:11:13"}
|
| 198 |
+
{"current_steps": 990, "total_steps": 1188, "loss": 0.1371, "lr": 3.3238156462872937e-06, "epoch": 5.0, "percentage": 83.33, "elapsed_time": "0:54:41", "remaining_time": "0:10:56"}
|
| 199 |
+
{"current_steps": 995, "total_steps": 1188, "loss": 0.1309, "lr": 3.1633837307932037e-06, "epoch": 5.025252525252525, "percentage": 83.75, "elapsed_time": "0:54:54", "remaining_time": "0:10:39"}
|
| 200 |
+
{"current_steps": 1000, "total_steps": 1188, "loss": 0.1292, "lr": 3.0065870406906094e-06, "epoch": 5.05050505050505, "percentage": 84.18, "elapsed_time": "0:55:08", "remaining_time": "0:10:22"}
|
| 201 |
+
{"current_steps": 1005, "total_steps": 1188, "loss": 0.1253, "lr": 2.8534594302469142e-06, "epoch": 5.075757575757576, "percentage": 84.6, "elapsed_time": "0:56:20", "remaining_time": "0:10:15"}
|
| 202 |
+
{"current_steps": 1010, "total_steps": 1188, "loss": 0.1276, "lr": 2.7040339615316315e-06, "epoch": 5.101010101010101, "percentage": 85.02, "elapsed_time": "0:56:33", "remaining_time": "0:09:58"}
|
| 203 |
+
{"current_steps": 1015, "total_steps": 1188, "loss": 0.1323, "lr": 2.5583428972779236e-06, "epoch": 5.126262626262626, "percentage": 85.44, "elapsed_time": "0:56:47", "remaining_time": "0:09:40"}
|
| 204 |
+
{"current_steps": 1020, "total_steps": 1188, "loss": 0.1323, "lr": 2.4164176939166883e-06, "epoch": 5.151515151515151, "percentage": 85.86, "elapsed_time": "0:57:00", "remaining_time": "0:09:23"}
|
| 205 |
+
{"current_steps": 1025, "total_steps": 1188, "loss": 0.1353, "lr": 2.278288994784723e-06, "epoch": 5.1767676767676765, "percentage": 86.28, "elapsed_time": "0:57:14", "remaining_time": "0:09:06"}
|
| 206 |
+
{"current_steps": 1030, "total_steps": 1188, "loss": 0.1335, "lr": 2.143986623508478e-06, "epoch": 5.202020202020202, "percentage": 86.7, "elapsed_time": "0:57:26", "remaining_time": "0:08:48"}
|
| 207 |
+
{"current_steps": 1035, "total_steps": 1188, "loss": 0.1302, "lr": 2.0135395775647916e-06, "epoch": 5.2272727272727275, "percentage": 87.12, "elapsed_time": "0:57:41", "remaining_time": "0:08:31"}
|
| 208 |
+
{"current_steps": 1040, "total_steps": 1188, "loss": 0.1292, "lr": 1.8869760220199707e-06, "epoch": 5.252525252525253, "percentage": 87.54, "elapsed_time": "0:57:53", "remaining_time": "0:08:14"}
|
| 209 |
+
{"current_steps": 1045, "total_steps": 1188, "loss": 0.1331, "lr": 1.7643232834486347e-06, "epoch": 5.277777777777778, "percentage": 87.96, "elapsed_time": "0:58:06", "remaining_time": "0:07:57"}
|
| 210 |
+
{"current_steps": 1050, "total_steps": 1188, "loss": 0.1284, "lr": 1.6456078440335699e-06, "epoch": 5.303030303030303, "percentage": 88.38, "elapsed_time": "0:58:19", "remaining_time": "0:07:39"}
|
| 211 |
+
{"current_steps": 1055, "total_steps": 1188, "loss": 0.1252, "lr": 1.530855335847916e-06, "epoch": 5.328282828282829, "percentage": 88.8, "elapsed_time": "0:58:31", "remaining_time": "0:07:22"}
|
| 212 |
+
{"current_steps": 1060, "total_steps": 1188, "loss": 0.1281, "lr": 1.4200905353209127e-06, "epoch": 5.353535353535354, "percentage": 89.23, "elapsed_time": "0:58:44", "remaining_time": "0:07:05"}
|
| 213 |
+
{"current_steps": 1065, "total_steps": 1188, "loss": 0.1294, "lr": 1.3133373578883557e-06, "epoch": 5.378787878787879, "percentage": 89.65, "elapsed_time": "0:58:56", "remaining_time": "0:06:48"}
|
| 214 |
+
{"current_steps": 1070, "total_steps": 1188, "loss": 0.1299, "lr": 1.210618852828962e-06, "epoch": 5.404040404040404, "percentage": 90.07, "elapsed_time": "0:59:10", "remaining_time": "0:06:31"}
|
| 215 |
+
{"current_steps": 1075, "total_steps": 1188, "loss": 0.1277, "lr": 1.111957198287792e-06, "epoch": 5.429292929292929, "percentage": 90.49, "elapsed_time": "0:59:23", "remaining_time": "0:06:14"}
|
| 216 |
+
{"current_steps": 1080, "total_steps": 1188, "loss": 0.1263, "lr": 1.0173736964876867e-06, "epoch": 5.454545454545454, "percentage": 90.91, "elapsed_time": "0:59:36", "remaining_time": "0:05:57"}
|
| 217 |
+
{"current_steps": 1085, "total_steps": 1188, "loss": 0.1284, "lr": 9.268887691298878e-07, "epoch": 5.47979797979798, "percentage": 91.33, "elapsed_time": "0:59:50", "remaining_time": "0:05:40"}
|
| 218 |
+
{"current_steps": 1090, "total_steps": 1188, "loss": 0.1277, "lr": 8.405219529847453e-07, "epoch": 5.505050505050505, "percentage": 91.75, "elapsed_time": "1:00:03", "remaining_time": "0:05:23"}
|
| 219 |
+
{"current_steps": 1095, "total_steps": 1188, "loss": 0.1345, "lr": 7.582918956734909e-07, "epoch": 5.53030303030303, "percentage": 92.17, "elapsed_time": "1:00:16", "remaining_time": "0:05:07"}
|
| 220 |
+
{"current_steps": 1100, "total_steps": 1188, "loss": 0.1265, "lr": 6.802163516419979e-07, "epoch": 5.555555555555555, "percentage": 92.59, "elapsed_time": "1:00:30", "remaining_time": "0:04:50"}
|
| 221 |
+
{"current_steps": 1105, "total_steps": 1188, "loss": 0.1307, "lr": 6.063121783273907e-07, "epoch": 5.58080808080808, "percentage": 93.01, "elapsed_time": "1:01:44", "remaining_time": "0:04:38"}
|
| 222 |
+
{"current_steps": 1110, "total_steps": 1188, "loss": 0.1277, "lr": 5.365953325183216e-07, "epoch": 5.606060606060606, "percentage": 93.43, "elapsed_time": "1:01:57", "remaining_time": "0:04:21"}
|
| 223 |
+
{"current_steps": 1115, "total_steps": 1188, "loss": 0.1323, "lr": 4.7108086690970113e-07, "epoch": 5.6313131313131315, "percentage": 93.86, "elapsed_time": "1:02:11", "remaining_time": "0:04:04"}
|
| 224 |
+
{"current_steps": 1120, "total_steps": 1188, "loss": 0.1235, "lr": 4.0978292685265765e-07, "epoch": 5.656565656565657, "percentage": 94.28, "elapsed_time": "1:02:24", "remaining_time": "0:03:47"}
|
| 225 |
+
{"current_steps": 1125, "total_steps": 1188, "loss": 0.1302, "lr": 3.5271474730037557e-07, "epoch": 5.681818181818182, "percentage": 94.7, "elapsed_time": "1:02:37", "remaining_time": "0:03:30"}
|
| 226 |
+
{"current_steps": 1130, "total_steps": 1188, "loss": 0.127, "lr": 2.998886499505171e-07, "epoch": 5.707070707070707, "percentage": 95.12, "elapsed_time": "1:02:51", "remaining_time": "0:03:13"}
|
| 227 |
+
{"current_steps": 1135, "total_steps": 1188, "loss": 0.1345, "lr": 2.513160405848303e-07, "epoch": 5.732323232323233, "percentage": 95.54, "elapsed_time": "1:03:04", "remaining_time": "0:02:56"}
|
| 228 |
+
{"current_steps": 1140, "total_steps": 1188, "loss": 0.1328, "lr": 2.0700740660648312e-07, "epoch": 5.757575757575758, "percentage": 95.96, "elapsed_time": "1:03:16", "remaining_time": "0:02:39"}
|
| 229 |
+
{"current_steps": 1145, "total_steps": 1188, "loss": 0.1284, "lr": 1.669723147757263e-07, "epoch": 5.782828282828283, "percentage": 96.38, "elapsed_time": "1:03:29", "remaining_time": "0:02:23"}
|
| 230 |
+
{"current_steps": 1150, "total_steps": 1188, "loss": 0.1331, "lr": 1.312194091443142e-07, "epoch": 5.808080808080808, "percentage": 96.8, "elapsed_time": "1:03:42", "remaining_time": "0:02:06"}
|
| 231 |
+
{"current_steps": 1155, "total_steps": 1188, "loss": 0.1306, "lr": 9.975640918915119e-08, "epoch": 5.833333333333333, "percentage": 97.22, "elapsed_time": "1:03:55", "remaining_time": "0:01:49"}
|
| 232 |
+
{"current_steps": 1160, "total_steps": 1188, "loss": 0.1304, "lr": 7.259010814555378e-08, "epoch": 5.858585858585858, "percentage": 97.64, "elapsed_time": "1:04:08", "remaining_time": "0:01:32"}
|
| 233 |
+
{"current_steps": 1165, "total_steps": 1188, "loss": 0.1292, "lr": 4.972637154052606e-08, "epoch": 5.883838383838384, "percentage": 98.06, "elapsed_time": "1:04:21", "remaining_time": "0:01:16"}
|
| 234 |
+
{"current_steps": 1170, "total_steps": 1188, "loss": 0.1341, "lr": 3.117013592631501e-08, "epoch": 5.909090909090909, "percentage": 98.48, "elapsed_time": "1:04:34", "remaining_time": "0:00:59"}
|
| 235 |
+
{"current_steps": 1175, "total_steps": 1188, "loss": 0.1267, "lr": 1.6925407814545325e-08, "epoch": 5.934343434343434, "percentage": 98.91, "elapsed_time": "1:04:47", "remaining_time": "0:00:43"}
|
| 236 |
+
{"current_steps": 1180, "total_steps": 1188, "loss": 0.1297, "lr": 6.995262811178016e-09, "epoch": 5.959595959595959, "percentage": 99.33, "elapsed_time": "1:05:01", "remaining_time": "0:00:26"}
|
| 237 |
+
{"current_steps": 1185, "total_steps": 1188, "loss": 0.1304, "lr": 1.3818449524416467e-09, "epoch": 5.984848484848484, "percentage": 99.75, "elapsed_time": "1:05:14", "remaining_time": "0:00:09"}
|
| 238 |
+
{"current_steps": 1188, "total_steps": 1188, "epoch": 6.0, "percentage": 100.0, "elapsed_time": "1:05:54", "remaining_time": "0:00:00"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2654 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 6.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 1188,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.025252525252525252,
|
| 14 |
+
"grad_norm": 20.169370087659352,
|
| 15 |
+
"learning_rate": 1.3445378151260504e-06,
|
| 16 |
+
"loss": 1.0237,
|
| 17 |
+
"loss_nan_ranks": 0,
|
| 18 |
+
"loss_rank_avg": 1.0157525539398193,
|
| 19 |
+
"step": 5,
|
| 20 |
+
"valid_targets_mean": 1187.8,
|
| 21 |
+
"valid_targets_min": 751
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.050505050505050504,
|
| 25 |
+
"grad_norm": 16.675857749316165,
|
| 26 |
+
"learning_rate": 3.0252100840336137e-06,
|
| 27 |
+
"loss": 0.9775,
|
| 28 |
+
"loss_nan_ranks": 0,
|
| 29 |
+
"loss_rank_avg": 0.9797632694244385,
|
| 30 |
+
"step": 10,
|
| 31 |
+
"valid_targets_mean": 1131.0,
|
| 32 |
+
"valid_targets_min": 704
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.07575757575757576,
|
| 36 |
+
"grad_norm": 8.704541263565613,
|
| 37 |
+
"learning_rate": 4.705882352941177e-06,
|
| 38 |
+
"loss": 0.8599,
|
| 39 |
+
"loss_nan_ranks": 0,
|
| 40 |
+
"loss_rank_avg": 0.7952851057052612,
|
| 41 |
+
"step": 15,
|
| 42 |
+
"valid_targets_mean": 1290.6,
|
| 43 |
+
"valid_targets_min": 687
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 0.10101010101010101,
|
| 47 |
+
"grad_norm": 5.301964048196616,
|
| 48 |
+
"learning_rate": 6.386554621848739e-06,
|
| 49 |
+
"loss": 0.7379,
|
| 50 |
+
"loss_nan_ranks": 0,
|
| 51 |
+
"loss_rank_avg": 0.6894418001174927,
|
| 52 |
+
"step": 20,
|
| 53 |
+
"valid_targets_mean": 1500.8,
|
| 54 |
+
"valid_targets_min": 659
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.12626262626262627,
|
| 58 |
+
"grad_norm": 2.8651616903258805,
|
| 59 |
+
"learning_rate": 8.067226890756303e-06,
|
| 60 |
+
"loss": 0.6167,
|
| 61 |
+
"loss_nan_ranks": 0,
|
| 62 |
+
"loss_rank_avg": 0.5881441831588745,
|
| 63 |
+
"step": 25,
|
| 64 |
+
"valid_targets_mean": 1226.6,
|
| 65 |
+
"valid_targets_min": 693
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.15151515151515152,
|
| 69 |
+
"grad_norm": 1.9308802697891598,
|
| 70 |
+
"learning_rate": 9.747899159663867e-06,
|
| 71 |
+
"loss": 0.5299,
|
| 72 |
+
"loss_nan_ranks": 0,
|
| 73 |
+
"loss_rank_avg": 0.5140570998191833,
|
| 74 |
+
"step": 30,
|
| 75 |
+
"valid_targets_mean": 1314.4,
|
| 76 |
+
"valid_targets_min": 532
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.17676767676767677,
|
| 80 |
+
"grad_norm": 1.6911984939158233,
|
| 81 |
+
"learning_rate": 1.1428571428571429e-05,
|
| 82 |
+
"loss": 0.4981,
|
| 83 |
+
"loss_nan_ranks": 0,
|
| 84 |
+
"loss_rank_avg": 0.49357980489730835,
|
| 85 |
+
"step": 35,
|
| 86 |
+
"valid_targets_mean": 1118.2,
|
| 87 |
+
"valid_targets_min": 680
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.20202020202020202,
|
| 91 |
+
"grad_norm": 1.492452782606785,
|
| 92 |
+
"learning_rate": 1.3109243697478993e-05,
|
| 93 |
+
"loss": 0.4407,
|
| 94 |
+
"loss_nan_ranks": 0,
|
| 95 |
+
"loss_rank_avg": 0.4345753788948059,
|
| 96 |
+
"step": 40,
|
| 97 |
+
"valid_targets_mean": 1273.3,
|
| 98 |
+
"valid_targets_min": 629
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.22727272727272727,
|
| 102 |
+
"grad_norm": 1.500112384532108,
|
| 103 |
+
"learning_rate": 1.4789915966386557e-05,
|
| 104 |
+
"loss": 0.414,
|
| 105 |
+
"loss_nan_ranks": 0,
|
| 106 |
+
"loss_rank_avg": 0.3712472915649414,
|
| 107 |
+
"step": 45,
|
| 108 |
+
"valid_targets_mean": 1263.1,
|
| 109 |
+
"valid_targets_min": 620
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.25252525252525254,
|
| 113 |
+
"grad_norm": 1.0754446138300695,
|
| 114 |
+
"learning_rate": 1.647058823529412e-05,
|
| 115 |
+
"loss": 0.3676,
|
| 116 |
+
"loss_nan_ranks": 0,
|
| 117 |
+
"loss_rank_avg": 0.35347896814346313,
|
| 118 |
+
"step": 50,
|
| 119 |
+
"valid_targets_mean": 1464.4,
|
| 120 |
+
"valid_targets_min": 659
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.2777777777777778,
|
| 124 |
+
"grad_norm": 1.1618002004795733,
|
| 125 |
+
"learning_rate": 1.8151260504201682e-05,
|
| 126 |
+
"loss": 0.3464,
|
| 127 |
+
"loss_nan_ranks": 0,
|
| 128 |
+
"loss_rank_avg": 0.3541208803653717,
|
| 129 |
+
"step": 55,
|
| 130 |
+
"valid_targets_mean": 1315.9,
|
| 131 |
+
"valid_targets_min": 589
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 0.30303030303030304,
|
| 135 |
+
"grad_norm": 1.0883564166727384,
|
| 136 |
+
"learning_rate": 1.9831932773109244e-05,
|
| 137 |
+
"loss": 0.338,
|
| 138 |
+
"loss_nan_ranks": 0,
|
| 139 |
+
"loss_rank_avg": 0.3574886620044708,
|
| 140 |
+
"step": 60,
|
| 141 |
+
"valid_targets_mean": 1405.6,
|
| 142 |
+
"valid_targets_min": 758
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.3282828282828283,
|
| 146 |
+
"grad_norm": 1.0137280896162002,
|
| 147 |
+
"learning_rate": 2.1512605042016807e-05,
|
| 148 |
+
"loss": 0.3275,
|
| 149 |
+
"loss_nan_ranks": 0,
|
| 150 |
+
"loss_rank_avg": 0.3133365511894226,
|
| 151 |
+
"step": 65,
|
| 152 |
+
"valid_targets_mean": 1416.2,
|
| 153 |
+
"valid_targets_min": 753
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.35353535353535354,
|
| 157 |
+
"grad_norm": 1.0379235855718125,
|
| 158 |
+
"learning_rate": 2.3193277310924373e-05,
|
| 159 |
+
"loss": 0.2979,
|
| 160 |
+
"loss_nan_ranks": 0,
|
| 161 |
+
"loss_rank_avg": 0.3172857463359833,
|
| 162 |
+
"step": 70,
|
| 163 |
+
"valid_targets_mean": 1387.2,
|
| 164 |
+
"valid_targets_min": 615
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.3787878787878788,
|
| 168 |
+
"grad_norm": 1.0676260962261874,
|
| 169 |
+
"learning_rate": 2.4873949579831935e-05,
|
| 170 |
+
"loss": 0.2957,
|
| 171 |
+
"loss_nan_ranks": 0,
|
| 172 |
+
"loss_rank_avg": 0.2801944613456726,
|
| 173 |
+
"step": 75,
|
| 174 |
+
"valid_targets_mean": 1275.1,
|
| 175 |
+
"valid_targets_min": 831
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 0.40404040404040403,
|
| 179 |
+
"grad_norm": 1.0045547818037883,
|
| 180 |
+
"learning_rate": 2.6554621848739497e-05,
|
| 181 |
+
"loss": 0.3063,
|
| 182 |
+
"loss_nan_ranks": 0,
|
| 183 |
+
"loss_rank_avg": 0.3241528272628784,
|
| 184 |
+
"step": 80,
|
| 185 |
+
"valid_targets_mean": 1368.9,
|
| 186 |
+
"valid_targets_min": 846
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.4292929292929293,
|
| 190 |
+
"grad_norm": 0.9923280106185243,
|
| 191 |
+
"learning_rate": 2.8235294117647063e-05,
|
| 192 |
+
"loss": 0.2973,
|
| 193 |
+
"loss_nan_ranks": 0,
|
| 194 |
+
"loss_rank_avg": 0.2852829396724701,
|
| 195 |
+
"step": 85,
|
| 196 |
+
"valid_targets_mean": 1345.0,
|
| 197 |
+
"valid_targets_min": 735
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 0.45454545454545453,
|
| 201 |
+
"grad_norm": 0.9646459041819732,
|
| 202 |
+
"learning_rate": 2.9915966386554626e-05,
|
| 203 |
+
"loss": 0.2854,
|
| 204 |
+
"loss_nan_ranks": 0,
|
| 205 |
+
"loss_rank_avg": 0.2792156934738159,
|
| 206 |
+
"step": 90,
|
| 207 |
+
"valid_targets_mean": 1343.4,
|
| 208 |
+
"valid_targets_min": 738
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 0.4797979797979798,
|
| 212 |
+
"grad_norm": 1.052289746435847,
|
| 213 |
+
"learning_rate": 3.159663865546219e-05,
|
| 214 |
+
"loss": 0.2698,
|
| 215 |
+
"loss_nan_ranks": 0,
|
| 216 |
+
"loss_rank_avg": 0.26299500465393066,
|
| 217 |
+
"step": 95,
|
| 218 |
+
"valid_targets_mean": 1293.9,
|
| 219 |
+
"valid_targets_min": 773
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.5050505050505051,
|
| 223 |
+
"grad_norm": 1.1622301238597719,
|
| 224 |
+
"learning_rate": 3.3277310924369754e-05,
|
| 225 |
+
"loss": 0.2831,
|
| 226 |
+
"loss_nan_ranks": 0,
|
| 227 |
+
"loss_rank_avg": 0.311882883310318,
|
| 228 |
+
"step": 100,
|
| 229 |
+
"valid_targets_mean": 1408.7,
|
| 230 |
+
"valid_targets_min": 738
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.5303030303030303,
|
| 234 |
+
"grad_norm": 1.1114150871374988,
|
| 235 |
+
"learning_rate": 3.495798319327731e-05,
|
| 236 |
+
"loss": 0.2821,
|
| 237 |
+
"loss_nan_ranks": 0,
|
| 238 |
+
"loss_rank_avg": 0.275522381067276,
|
| 239 |
+
"step": 105,
|
| 240 |
+
"valid_targets_mean": 1212.6,
|
| 241 |
+
"valid_targets_min": 618
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.5555555555555556,
|
| 245 |
+
"grad_norm": 0.9706083743298367,
|
| 246 |
+
"learning_rate": 3.663865546218488e-05,
|
| 247 |
+
"loss": 0.2799,
|
| 248 |
+
"loss_nan_ranks": 0,
|
| 249 |
+
"loss_rank_avg": 0.2872806489467621,
|
| 250 |
+
"step": 110,
|
| 251 |
+
"valid_targets_mean": 1481.1,
|
| 252 |
+
"valid_targets_min": 918
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.5808080808080808,
|
| 256 |
+
"grad_norm": 1.1271397120654052,
|
| 257 |
+
"learning_rate": 3.8319327731092444e-05,
|
| 258 |
+
"loss": 0.279,
|
| 259 |
+
"loss_nan_ranks": 0,
|
| 260 |
+
"loss_rank_avg": 0.2863199710845947,
|
| 261 |
+
"step": 115,
|
| 262 |
+
"valid_targets_mean": 1283.5,
|
| 263 |
+
"valid_targets_min": 574
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 0.6060606060606061,
|
| 267 |
+
"grad_norm": 1.0471857507926354,
|
| 268 |
+
"learning_rate": 4e-05,
|
| 269 |
+
"loss": 0.2694,
|
| 270 |
+
"loss_nan_ranks": 0,
|
| 271 |
+
"loss_rank_avg": 0.29653966426849365,
|
| 272 |
+
"step": 120,
|
| 273 |
+
"valid_targets_mean": 1340.8,
|
| 274 |
+
"valid_targets_min": 756
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.6313131313131313,
|
| 278 |
+
"grad_norm": 1.1072262420802004,
|
| 279 |
+
"learning_rate": 3.999784088124753e-05,
|
| 280 |
+
"loss": 0.2793,
|
| 281 |
+
"loss_nan_ranks": 0,
|
| 282 |
+
"loss_rank_avg": 0.28706759214401245,
|
| 283 |
+
"step": 125,
|
| 284 |
+
"valid_targets_mean": 1297.0,
|
| 285 |
+
"valid_targets_min": 784
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.6565656565656566,
|
| 289 |
+
"grad_norm": 0.9900053971903253,
|
| 290 |
+
"learning_rate": 3.99913639911695e-05,
|
| 291 |
+
"loss": 0.2597,
|
| 292 |
+
"loss_nan_ranks": 0,
|
| 293 |
+
"loss_rank_avg": 0.2584039866924286,
|
| 294 |
+
"step": 130,
|
| 295 |
+
"valid_targets_mean": 1323.2,
|
| 296 |
+
"valid_targets_min": 618
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.6818181818181818,
|
| 300 |
+
"grad_norm": 0.9452591379939352,
|
| 301 |
+
"learning_rate": 3.998057072820338e-05,
|
| 302 |
+
"loss": 0.2705,
|
| 303 |
+
"loss_nan_ranks": 0,
|
| 304 |
+
"loss_rank_avg": 0.2791949212551117,
|
| 305 |
+
"step": 135,
|
| 306 |
+
"valid_targets_mean": 1479.4,
|
| 307 |
+
"valid_targets_min": 582
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 0.7070707070707071,
|
| 311 |
+
"grad_norm": 1.1345903226168657,
|
| 312 |
+
"learning_rate": 3.996546342274282e-05,
|
| 313 |
+
"loss": 0.2753,
|
| 314 |
+
"loss_nan_ranks": 0,
|
| 315 |
+
"loss_rank_avg": 0.270517498254776,
|
| 316 |
+
"step": 140,
|
| 317 |
+
"valid_targets_mean": 1323.2,
|
| 318 |
+
"valid_targets_min": 797
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.7323232323232324,
|
| 322 |
+
"grad_norm": 1.0964303784318785,
|
| 323 |
+
"learning_rate": 3.9946045336634485e-05,
|
| 324 |
+
"loss": 0.2598,
|
| 325 |
+
"loss_nan_ranks": 0,
|
| 326 |
+
"loss_rank_avg": 0.25797197222709656,
|
| 327 |
+
"step": 145,
|
| 328 |
+
"valid_targets_mean": 1143.2,
|
| 329 |
+
"valid_targets_min": 632
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 0.7575757575757576,
|
| 333 |
+
"grad_norm": 1.0480327343570168,
|
| 334 |
+
"learning_rate": 3.9922320662473755e-05,
|
| 335 |
+
"loss": 0.2704,
|
| 336 |
+
"loss_nan_ranks": 0,
|
| 337 |
+
"loss_rank_avg": 0.2590729296207428,
|
| 338 |
+
"step": 150,
|
| 339 |
+
"valid_targets_mean": 1109.0,
|
| 340 |
+
"valid_targets_min": 555
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 0.7828282828282829,
|
| 344 |
+
"grad_norm": 1.2063540633588965,
|
| 345 |
+
"learning_rate": 3.989429452269951e-05,
|
| 346 |
+
"loss": 0.2545,
|
| 347 |
+
"loss_nan_ranks": 0,
|
| 348 |
+
"loss_rank_avg": 0.24084429442882538,
|
| 349 |
+
"step": 155,
|
| 350 |
+
"valid_targets_mean": 1144.1,
|
| 351 |
+
"valid_targets_min": 685
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.8080808080808081,
|
| 355 |
+
"grad_norm": 1.1381600500975266,
|
| 356 |
+
"learning_rate": 3.986197296848816e-05,
|
| 357 |
+
"loss": 0.2619,
|
| 358 |
+
"loss_nan_ranks": 0,
|
| 359 |
+
"loss_rank_avg": 0.26328036189079285,
|
| 360 |
+
"step": 160,
|
| 361 |
+
"valid_targets_mean": 1215.6,
|
| 362 |
+
"valid_targets_min": 717
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.8333333333333334,
|
| 366 |
+
"grad_norm": 0.9369305409921032,
|
| 367 |
+
"learning_rate": 3.982536297844706e-05,
|
| 368 |
+
"loss": 0.2628,
|
| 369 |
+
"loss_nan_ranks": 0,
|
| 370 |
+
"loss_rank_avg": 0.25279849767684937,
|
| 371 |
+
"step": 165,
|
| 372 |
+
"valid_targets_mean": 1300.6,
|
| 373 |
+
"valid_targets_min": 679
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.8585858585858586,
|
| 377 |
+
"grad_norm": 0.8800799927020014,
|
| 378 |
+
"learning_rate": 3.978447245710784e-05,
|
| 379 |
+
"loss": 0.2588,
|
| 380 |
+
"loss_nan_ranks": 0,
|
| 381 |
+
"loss_rank_avg": 0.25856029987335205,
|
| 382 |
+
"step": 170,
|
| 383 |
+
"valid_targets_mean": 1579.3,
|
| 384 |
+
"valid_targets_min": 821
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 0.8838383838383839,
|
| 388 |
+
"grad_norm": 0.9268097877772618,
|
| 389 |
+
"learning_rate": 3.973931023321962e-05,
|
| 390 |
+
"loss": 0.2538,
|
| 391 |
+
"loss_nan_ranks": 0,
|
| 392 |
+
"loss_rank_avg": 0.24270369112491608,
|
| 393 |
+
"step": 175,
|
| 394 |
+
"valid_targets_mean": 1203.4,
|
| 395 |
+
"valid_targets_min": 684
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.9090909090909091,
|
| 399 |
+
"grad_norm": 0.9474619522436488,
|
| 400 |
+
"learning_rate": 3.9689886057842866e-05,
|
| 401 |
+
"loss": 0.2409,
|
| 402 |
+
"loss_nan_ranks": 0,
|
| 403 |
+
"loss_rank_avg": 0.25069937109947205,
|
| 404 |
+
"step": 180,
|
| 405 |
+
"valid_targets_mean": 1398.1,
|
| 406 |
+
"valid_targets_min": 711
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 0.9343434343434344,
|
| 410 |
+
"grad_norm": 1.034637445880305,
|
| 411 |
+
"learning_rate": 3.963621060224396e-05,
|
| 412 |
+
"loss": 0.2545,
|
| 413 |
+
"loss_nan_ranks": 0,
|
| 414 |
+
"loss_rank_avg": 0.24697241187095642,
|
| 415 |
+
"step": 185,
|
| 416 |
+
"valid_targets_mean": 1112.4,
|
| 417 |
+
"valid_targets_min": 582
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.9595959595959596,
|
| 421 |
+
"grad_norm": 0.9298977899777117,
|
| 422 |
+
"learning_rate": 3.957829545559118e-05,
|
| 423 |
+
"loss": 0.2553,
|
| 424 |
+
"loss_nan_ranks": 0,
|
| 425 |
+
"loss_rank_avg": 0.2632555365562439,
|
| 426 |
+
"step": 190,
|
| 427 |
+
"valid_targets_mean": 1315.6,
|
| 428 |
+
"valid_targets_min": 742
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 0.9848484848484849,
|
| 432 |
+
"grad_norm": 0.8977159403395447,
|
| 433 |
+
"learning_rate": 3.951615312245243e-05,
|
| 434 |
+
"loss": 0.2546,
|
| 435 |
+
"loss_nan_ranks": 0,
|
| 436 |
+
"loss_rank_avg": 0.2525337338447571,
|
| 437 |
+
"step": 195,
|
| 438 |
+
"valid_targets_mean": 1346.2,
|
| 439 |
+
"valid_targets_min": 774
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 1.0101010101010102,
|
| 443 |
+
"grad_norm": 1.021475627213122,
|
| 444 |
+
"learning_rate": 3.9449797020095404e-05,
|
| 445 |
+
"loss": 0.2535,
|
| 446 |
+
"loss_nan_ranks": 0,
|
| 447 |
+
"loss_rank_avg": 0.2486366480588913,
|
| 448 |
+
"step": 200,
|
| 449 |
+
"valid_targets_mean": 1331.2,
|
| 450 |
+
"valid_targets_min": 680
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 1.0353535353535352,
|
| 454 |
+
"grad_norm": 1.0071426224742983,
|
| 455 |
+
"learning_rate": 3.937924147559059e-05,
|
| 456 |
+
"loss": 0.2277,
|
| 457 |
+
"loss_nan_ranks": 0,
|
| 458 |
+
"loss_rank_avg": 0.2366667240858078,
|
| 459 |
+
"step": 205,
|
| 460 |
+
"valid_targets_mean": 1303.9,
|
| 461 |
+
"valid_targets_min": 648
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 1.0606060606060606,
|
| 465 |
+
"grad_norm": 0.863916533755164,
|
| 466 |
+
"learning_rate": 3.9304501722717925e-05,
|
| 467 |
+
"loss": 0.2358,
|
| 468 |
+
"loss_nan_ranks": 0,
|
| 469 |
+
"loss_rank_avg": 0.22564607858657837,
|
| 470 |
+
"step": 210,
|
| 471 |
+
"valid_targets_mean": 1418.2,
|
| 472 |
+
"valid_targets_min": 1067
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 1.0858585858585859,
|
| 476 |
+
"grad_norm": 0.932084360690738,
|
| 477 |
+
"learning_rate": 3.922559389867758e-05,
|
| 478 |
+
"loss": 0.2333,
|
| 479 |
+
"loss_nan_ranks": 0,
|
| 480 |
+
"loss_rank_avg": 0.24001938104629517,
|
| 481 |
+
"step": 215,
|
| 482 |
+
"valid_targets_mean": 1553.2,
|
| 483 |
+
"valid_targets_min": 1094
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 1.1111111111111112,
|
| 487 |
+
"grad_norm": 0.9418003911519435,
|
| 488 |
+
"learning_rate": 3.914253504060585e-05,
|
| 489 |
+
"loss": 0.2289,
|
| 490 |
+
"loss_nan_ranks": 0,
|
| 491 |
+
"loss_rank_avg": 0.2039659321308136,
|
| 492 |
+
"step": 220,
|
| 493 |
+
"valid_targets_mean": 1241.6,
|
| 494 |
+
"valid_targets_min": 594
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 1.1363636363636362,
|
| 498 |
+
"grad_norm": 0.9424926403942966,
|
| 499 |
+
"learning_rate": 3.90553430818965e-05,
|
| 500 |
+
"loss": 0.225,
|
| 501 |
+
"loss_nan_ranks": 0,
|
| 502 |
+
"loss_rank_avg": 0.22819814085960388,
|
| 503 |
+
"step": 225,
|
| 504 |
+
"valid_targets_mean": 1457.8,
|
| 505 |
+
"valid_targets_min": 837
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 1.1616161616161615,
|
| 509 |
+
"grad_norm": 0.8372692329391297,
|
| 510 |
+
"learning_rate": 3.896403684832887e-05,
|
| 511 |
+
"loss": 0.23,
|
| 512 |
+
"loss_nan_ranks": 0,
|
| 513 |
+
"loss_rank_avg": 0.22280089557170868,
|
| 514 |
+
"step": 230,
|
| 515 |
+
"valid_targets_mean": 1298.8,
|
| 516 |
+
"valid_targets_min": 791
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 1.1868686868686869,
|
| 520 |
+
"grad_norm": 0.9634864270568145,
|
| 521 |
+
"learning_rate": 3.886863605400306e-05,
|
| 522 |
+
"loss": 0.2314,
|
| 523 |
+
"loss_nan_ranks": 0,
|
| 524 |
+
"loss_rank_avg": 0.24971917271614075,
|
| 525 |
+
"step": 235,
|
| 526 |
+
"valid_targets_mean": 1264.4,
|
| 527 |
+
"valid_targets_min": 700
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 1.2121212121212122,
|
| 531 |
+
"grad_norm": 0.9062647387121051,
|
| 532 |
+
"learning_rate": 3.876916129708347e-05,
|
| 533 |
+
"loss": 0.2231,
|
| 534 |
+
"loss_nan_ranks": 0,
|
| 535 |
+
"loss_rank_avg": 0.22650766372680664,
|
| 536 |
+
"step": 240,
|
| 537 |
+
"valid_targets_mean": 1429.9,
|
| 538 |
+
"valid_targets_min": 854
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 1.2373737373737375,
|
| 542 |
+
"grad_norm": 0.9679426116681048,
|
| 543 |
+
"learning_rate": 3.866563405535142e-05,
|
| 544 |
+
"loss": 0.2363,
|
| 545 |
+
"loss_nan_ranks": 0,
|
| 546 |
+
"loss_rank_avg": 0.22411300241947174,
|
| 547 |
+
"step": 245,
|
| 548 |
+
"valid_targets_mean": 1249.2,
|
| 549 |
+
"valid_targets_min": 550
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.2626262626262625,
|
| 553 |
+
"grad_norm": 1.5210230333522776,
|
| 554 |
+
"learning_rate": 3.855807668156779e-05,
|
| 555 |
+
"loss": 0.2187,
|
| 556 |
+
"loss_nan_ranks": 0,
|
| 557 |
+
"loss_rank_avg": 0.23495987057685852,
|
| 558 |
+
"step": 250,
|
| 559 |
+
"valid_targets_mean": 1417.0,
|
| 560 |
+
"valid_targets_min": 720
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 1.2878787878787878,
|
| 564 |
+
"grad_norm": 1.0154197633890338,
|
| 565 |
+
"learning_rate": 3.844651239864687e-05,
|
| 566 |
+
"loss": 0.2273,
|
| 567 |
+
"loss_nan_ranks": 0,
|
| 568 |
+
"loss_rank_avg": 0.22711053490638733,
|
| 569 |
+
"step": 255,
|
| 570 |
+
"valid_targets_mean": 1173.8,
|
| 571 |
+
"valid_targets_min": 776
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 1.3131313131313131,
|
| 575 |
+
"grad_norm": 0.9259864099946552,
|
| 576 |
+
"learning_rate": 3.8330965294642186e-05,
|
| 577 |
+
"loss": 0.227,
|
| 578 |
+
"loss_nan_ranks": 0,
|
| 579 |
+
"loss_rank_avg": 0.2507520318031311,
|
| 580 |
+
"step": 260,
|
| 581 |
+
"valid_targets_mean": 1453.4,
|
| 582 |
+
"valid_targets_min": 711
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 1.3383838383838385,
|
| 586 |
+
"grad_norm": 0.8413676808910939,
|
| 587 |
+
"learning_rate": 3.821146031754565e-05,
|
| 588 |
+
"loss": 0.2331,
|
| 589 |
+
"loss_nan_ranks": 0,
|
| 590 |
+
"loss_rank_avg": 0.235780268907547,
|
| 591 |
+
"step": 265,
|
| 592 |
+
"valid_targets_mean": 1401.7,
|
| 593 |
+
"valid_targets_min": 681
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 1.3636363636363638,
|
| 597 |
+
"grad_norm": 0.9876932162935549,
|
| 598 |
+
"learning_rate": 3.808802326990096e-05,
|
| 599 |
+
"loss": 0.2198,
|
| 600 |
+
"loss_nan_ranks": 0,
|
| 601 |
+
"loss_rank_avg": 0.21561799943447113,
|
| 602 |
+
"step": 270,
|
| 603 |
+
"valid_targets_mean": 1162.8,
|
| 604 |
+
"valid_targets_min": 605
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 1.3888888888888888,
|
| 608 |
+
"grad_norm": 1.1186277755619236,
|
| 609 |
+
"learning_rate": 3.7960680803232544e-05,
|
| 610 |
+
"loss": 0.2212,
|
| 611 |
+
"loss_nan_ranks": 0,
|
| 612 |
+
"loss_rank_avg": 0.2476837933063507,
|
| 613 |
+
"step": 275,
|
| 614 |
+
"valid_targets_mean": 1249.6,
|
| 615 |
+
"valid_targets_min": 644
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 1.4141414141414141,
|
| 619 |
+
"grad_norm": 0.9272391389819834,
|
| 620 |
+
"learning_rate": 3.782946041229119e-05,
|
| 621 |
+
"loss": 0.2239,
|
| 622 |
+
"loss_nan_ranks": 0,
|
| 623 |
+
"loss_rank_avg": 0.22536993026733398,
|
| 624 |
+
"step": 280,
|
| 625 |
+
"valid_targets_mean": 1286.6,
|
| 626 |
+
"valid_targets_min": 671
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.4393939393939394,
|
| 630 |
+
"grad_norm": 0.9507970993940866,
|
| 631 |
+
"learning_rate": 3.769439042911758e-05,
|
| 632 |
+
"loss": 0.234,
|
| 633 |
+
"loss_nan_ranks": 0,
|
| 634 |
+
"loss_rank_avg": 0.24206951260566711,
|
| 635 |
+
"step": 285,
|
| 636 |
+
"valid_targets_mean": 1180.0,
|
| 637 |
+
"valid_targets_min": 711
|
| 638 |
+
},
|
| 639 |
+
{
|
| 640 |
+
"epoch": 1.4646464646464645,
|
| 641 |
+
"grad_norm": 0.9667877163253019,
|
| 642 |
+
"learning_rate": 3.755550001692506e-05,
|
| 643 |
+
"loss": 0.2173,
|
| 644 |
+
"loss_nan_ranks": 0,
|
| 645 |
+
"loss_rank_avg": 0.21246126294136047,
|
| 646 |
+
"step": 290,
|
| 647 |
+
"valid_targets_mean": 1220.2,
|
| 648 |
+
"valid_targets_min": 770
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 1.4898989898989898,
|
| 652 |
+
"grad_norm": 0.9116365111809664,
|
| 653 |
+
"learning_rate": 3.7412819163802986e-05,
|
| 654 |
+
"loss": 0.2105,
|
| 655 |
+
"loss_nan_ranks": 0,
|
| 656 |
+
"loss_rank_avg": 0.21166947484016418,
|
| 657 |
+
"step": 295,
|
| 658 |
+
"valid_targets_mean": 1263.8,
|
| 659 |
+
"valid_targets_min": 762
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 1.5151515151515151,
|
| 663 |
+
"grad_norm": 0.8811979745066287,
|
| 664 |
+
"learning_rate": 3.726637867624191e-05,
|
| 665 |
+
"loss": 0.2359,
|
| 666 |
+
"loss_nan_ranks": 0,
|
| 667 |
+
"loss_rank_avg": 0.20912611484527588,
|
| 668 |
+
"step": 300,
|
| 669 |
+
"valid_targets_mean": 1320.4,
|
| 670 |
+
"valid_targets_min": 683
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 1.5404040404040404,
|
| 674 |
+
"grad_norm": 0.9596648525111655,
|
| 675 |
+
"learning_rate": 3.711621017248213e-05,
|
| 676 |
+
"loss": 0.2152,
|
| 677 |
+
"loss_nan_ranks": 0,
|
| 678 |
+
"loss_rank_avg": 0.20625783503055573,
|
| 679 |
+
"step": 305,
|
| 680 |
+
"valid_targets_mean": 1253.4,
|
| 681 |
+
"valid_targets_min": 618
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 1.5656565656565657,
|
| 685 |
+
"grad_norm": 0.9622701229690029,
|
| 686 |
+
"learning_rate": 3.6962346075686876e-05,
|
| 687 |
+
"loss": 0.2259,
|
| 688 |
+
"loss_nan_ranks": 0,
|
| 689 |
+
"loss_rank_avg": 0.2124948799610138,
|
| 690 |
+
"step": 310,
|
| 691 |
+
"valid_targets_mean": 1200.3,
|
| 692 |
+
"valid_targets_min": 655
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 1.5909090909090908,
|
| 696 |
+
"grad_norm": 1.016874652742493,
|
| 697 |
+
"learning_rate": 3.680481960694183e-05,
|
| 698 |
+
"loss": 0.2276,
|
| 699 |
+
"loss_nan_ranks": 0,
|
| 700 |
+
"loss_rank_avg": 0.21283963322639465,
|
| 701 |
+
"step": 315,
|
| 702 |
+
"valid_targets_mean": 1326.4,
|
| 703 |
+
"valid_targets_min": 721
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 1.6161616161616161,
|
| 707 |
+
"grad_norm": 0.8226357783546479,
|
| 708 |
+
"learning_rate": 3.6643664778082254e-05,
|
| 709 |
+
"loss": 0.2275,
|
| 710 |
+
"loss_nan_ranks": 0,
|
| 711 |
+
"loss_rank_avg": 0.20702260732650757,
|
| 712 |
+
"step": 320,
|
| 713 |
+
"valid_targets_mean": 1401.2,
|
| 714 |
+
"valid_targets_min": 868
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 1.6414141414141414,
|
| 718 |
+
"grad_norm": 0.8672807532299297,
|
| 719 |
+
"learning_rate": 3.6478916384349465e-05,
|
| 720 |
+
"loss": 0.2193,
|
| 721 |
+
"loss_nan_ranks": 0,
|
| 722 |
+
"loss_rank_avg": 0.23550966382026672,
|
| 723 |
+
"step": 325,
|
| 724 |
+
"valid_targets_mean": 1560.4,
|
| 725 |
+
"valid_targets_min": 825
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 1.6666666666666665,
|
| 729 |
+
"grad_norm": 0.9712639328964777,
|
| 730 |
+
"learning_rate": 3.631060999687809e-05,
|
| 731 |
+
"loss": 0.2243,
|
| 732 |
+
"loss_nan_ranks": 0,
|
| 733 |
+
"loss_rank_avg": 0.22655721008777618,
|
| 734 |
+
"step": 330,
|
| 735 |
+
"valid_targets_mean": 1239.7,
|
| 736 |
+
"valid_targets_min": 704
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 1.691919191919192,
|
| 740 |
+
"grad_norm": 0.9069646079111703,
|
| 741 |
+
"learning_rate": 3.613878195501586e-05,
|
| 742 |
+
"loss": 0.2132,
|
| 743 |
+
"loss_nan_ranks": 0,
|
| 744 |
+
"loss_rank_avg": 0.20803983509540558,
|
| 745 |
+
"step": 335,
|
| 746 |
+
"valid_targets_mean": 1168.1,
|
| 747 |
+
"valid_targets_min": 670
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 1.7171717171717171,
|
| 751 |
+
"grad_norm": 0.9455557791381117,
|
| 752 |
+
"learning_rate": 3.596346935847752e-05,
|
| 753 |
+
"loss": 0.2148,
|
| 754 |
+
"loss_nan_ranks": 0,
|
| 755 |
+
"loss_rank_avg": 0.21128031611442566,
|
| 756 |
+
"step": 340,
|
| 757 |
+
"valid_targets_mean": 1368.7,
|
| 758 |
+
"valid_targets_min": 753
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 1.7424242424242424,
|
| 762 |
+
"grad_norm": 1.1078047614048518,
|
| 763 |
+
"learning_rate": 3.578471005933454e-05,
|
| 764 |
+
"loss": 0.225,
|
| 765 |
+
"loss_nan_ranks": 0,
|
| 766 |
+
"loss_rank_avg": 0.2151433229446411,
|
| 767 |
+
"step": 345,
|
| 768 |
+
"valid_targets_mean": 1172.9,
|
| 769 |
+
"valid_targets_min": 764
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 1.7676767676767677,
|
| 773 |
+
"grad_norm": 1.025649374731909,
|
| 774 |
+
"learning_rate": 3.5602542653842416e-05,
|
| 775 |
+
"loss": 0.2148,
|
| 776 |
+
"loss_nan_ranks": 0,
|
| 777 |
+
"loss_rank_avg": 0.21121200919151306,
|
| 778 |
+
"step": 350,
|
| 779 |
+
"valid_targets_mean": 1404.9,
|
| 780 |
+
"valid_targets_min": 802
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 1.7929292929292928,
|
| 784 |
+
"grad_norm": 0.9227312319452774,
|
| 785 |
+
"learning_rate": 3.541700647410728e-05,
|
| 786 |
+
"loss": 0.2203,
|
| 787 |
+
"loss_nan_ranks": 0,
|
| 788 |
+
"loss_rank_avg": 0.20654287934303284,
|
| 789 |
+
"step": 355,
|
| 790 |
+
"valid_targets_mean": 1270.9,
|
| 791 |
+
"valid_targets_min": 694
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 1.8181818181818183,
|
| 795 |
+
"grad_norm": 0.8839026808611836,
|
| 796 |
+
"learning_rate": 3.522814157959362e-05,
|
| 797 |
+
"loss": 0.2307,
|
| 798 |
+
"loss_nan_ranks": 0,
|
| 799 |
+
"loss_rank_avg": 0.21429893374443054,
|
| 800 |
+
"step": 360,
|
| 801 |
+
"valid_targets_mean": 1328.3,
|
| 802 |
+
"valid_targets_min": 774
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 1.8434343434343434,
|
| 806 |
+
"grad_norm": 0.8418961695574284,
|
| 807 |
+
"learning_rate": 3.5035988748474974e-05,
|
| 808 |
+
"loss": 0.23,
|
| 809 |
+
"loss_nan_ranks": 0,
|
| 810 |
+
"loss_rank_avg": 0.2303229570388794,
|
| 811 |
+
"step": 365,
|
| 812 |
+
"valid_targets_mean": 1438.8,
|
| 813 |
+
"valid_targets_min": 801
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 1.8686868686868687,
|
| 817 |
+
"grad_norm": 0.8660276681232518,
|
| 818 |
+
"learning_rate": 3.484058946882946e-05,
|
| 819 |
+
"loss": 0.2128,
|
| 820 |
+
"loss_nan_ranks": 0,
|
| 821 |
+
"loss_rank_avg": 0.20196302235126495,
|
| 822 |
+
"step": 370,
|
| 823 |
+
"valid_targets_mean": 1269.9,
|
| 824 |
+
"valid_targets_min": 765
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 1.893939393939394,
|
| 828 |
+
"grad_norm": 0.8556571315590435,
|
| 829 |
+
"learning_rate": 3.4641985929681954e-05,
|
| 830 |
+
"loss": 0.221,
|
| 831 |
+
"loss_nan_ranks": 0,
|
| 832 |
+
"loss_rank_avg": 0.2154424786567688,
|
| 833 |
+
"step": 375,
|
| 834 |
+
"valid_targets_mean": 1228.6,
|
| 835 |
+
"valid_targets_min": 738
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 1.9191919191919191,
|
| 839 |
+
"grad_norm": 0.9057324926130037,
|
| 840 |
+
"learning_rate": 3.4440221011895026e-05,
|
| 841 |
+
"loss": 0.2149,
|
| 842 |
+
"loss_nan_ranks": 0,
|
| 843 |
+
"loss_rank_avg": 0.22812026739120483,
|
| 844 |
+
"step": 380,
|
| 845 |
+
"valid_targets_mean": 1510.7,
|
| 846 |
+
"valid_targets_min": 648
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 1.9444444444444444,
|
| 850 |
+
"grad_norm": 1.22905062391175,
|
| 851 |
+
"learning_rate": 3.423533827891044e-05,
|
| 852 |
+
"loss": 0.2226,
|
| 853 |
+
"loss_nan_ranks": 0,
|
| 854 |
+
"loss_rank_avg": 0.22331665456295013,
|
| 855 |
+
"step": 385,
|
| 856 |
+
"valid_targets_mean": 1256.8,
|
| 857 |
+
"valid_targets_min": 796
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 1.9696969696969697,
|
| 861 |
+
"grad_norm": 0.8864960651317679,
|
| 862 |
+
"learning_rate": 3.402738196734327e-05,
|
| 863 |
+
"loss": 0.2269,
|
| 864 |
+
"loss_nan_ranks": 0,
|
| 865 |
+
"loss_rank_avg": 0.2474365234375,
|
| 866 |
+
"step": 390,
|
| 867 |
+
"valid_targets_mean": 1468.1,
|
| 868 |
+
"valid_targets_min": 808
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 1.9949494949494948,
|
| 872 |
+
"grad_norm": 0.8116444633238107,
|
| 873 |
+
"learning_rate": 3.381639697743073e-05,
|
| 874 |
+
"loss": 0.2196,
|
| 875 |
+
"loss_nan_ranks": 0,
|
| 876 |
+
"loss_rank_avg": 0.21921899914741516,
|
| 877 |
+
"step": 395,
|
| 878 |
+
"valid_targets_mean": 1372.4,
|
| 879 |
+
"valid_targets_min": 696
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 2.0202020202020203,
|
| 883 |
+
"grad_norm": 0.8089562588991992,
|
| 884 |
+
"learning_rate": 3.3602428863337625e-05,
|
| 885 |
+
"loss": 0.1951,
|
| 886 |
+
"loss_nan_ranks": 0,
|
| 887 |
+
"loss_rank_avg": 0.18117868900299072,
|
| 888 |
+
"step": 400,
|
| 889 |
+
"valid_targets_mean": 1378.9,
|
| 890 |
+
"valid_targets_min": 830
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 2.0454545454545454,
|
| 894 |
+
"grad_norm": 0.9722779083533737,
|
| 895 |
+
"learning_rate": 3.338552382332073e-05,
|
| 896 |
+
"loss": 0.1904,
|
| 897 |
+
"loss_nan_ranks": 0,
|
| 898 |
+
"loss_rank_avg": 0.20024555921554565,
|
| 899 |
+
"step": 405,
|
| 900 |
+
"valid_targets_mean": 1251.8,
|
| 901 |
+
"valid_targets_min": 644
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 2.0707070707070705,
|
| 905 |
+
"grad_norm": 0.9539651111813244,
|
| 906 |
+
"learning_rate": 3.3165728689753976e-05,
|
| 907 |
+
"loss": 0.1952,
|
| 908 |
+
"loss_nan_ranks": 0,
|
| 909 |
+
"loss_rank_avg": 0.1934088170528412,
|
| 910 |
+
"step": 410,
|
| 911 |
+
"valid_targets_mean": 1190.8,
|
| 912 |
+
"valid_targets_min": 655
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 2.095959595959596,
|
| 916 |
+
"grad_norm": 0.8845502621948085,
|
| 917 |
+
"learning_rate": 3.2943090919016815e-05,
|
| 918 |
+
"loss": 0.1938,
|
| 919 |
+
"loss_nan_ranks": 0,
|
| 920 |
+
"loss_rank_avg": 0.21735027432441711,
|
| 921 |
+
"step": 415,
|
| 922 |
+
"valid_targets_mean": 1383.0,
|
| 923 |
+
"valid_targets_min": 651
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 2.121212121212121,
|
| 927 |
+
"grad_norm": 0.8702714930026663,
|
| 928 |
+
"learning_rate": 3.2717658581247844e-05,
|
| 929 |
+
"loss": 0.1834,
|
| 930 |
+
"loss_nan_ranks": 0,
|
| 931 |
+
"loss_rank_avg": 0.17540085315704346,
|
| 932 |
+
"step": 420,
|
| 933 |
+
"valid_targets_mean": 1534.4,
|
| 934 |
+
"valid_targets_min": 686
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 2.1464646464646466,
|
| 938 |
+
"grad_norm": 0.8478046646870934,
|
| 939 |
+
"learning_rate": 3.248948034996583e-05,
|
| 940 |
+
"loss": 0.1995,
|
| 941 |
+
"loss_nan_ranks": 0,
|
| 942 |
+
"loss_rank_avg": 0.19789089262485504,
|
| 943 |
+
"step": 425,
|
| 944 |
+
"valid_targets_mean": 1489.8,
|
| 945 |
+
"valid_targets_min": 578
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 2.1717171717171717,
|
| 949 |
+
"grad_norm": 0.8469812735159056,
|
| 950 |
+
"learning_rate": 3.2258605491560606e-05,
|
| 951 |
+
"loss": 0.184,
|
| 952 |
+
"loss_nan_ranks": 0,
|
| 953 |
+
"loss_rank_avg": 0.17873477935791016,
|
| 954 |
+
"step": 430,
|
| 955 |
+
"valid_targets_mean": 1449.3,
|
| 956 |
+
"valid_targets_min": 964
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 2.196969696969697,
|
| 960 |
+
"grad_norm": 1.0152996119033395,
|
| 961 |
+
"learning_rate": 3.2025083854655776e-05,
|
| 962 |
+
"loss": 0.1889,
|
| 963 |
+
"loss_nan_ranks": 0,
|
| 964 |
+
"loss_rank_avg": 0.19385069608688354,
|
| 965 |
+
"step": 435,
|
| 966 |
+
"valid_targets_mean": 1232.6,
|
| 967 |
+
"valid_targets_min": 532
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 2.2222222222222223,
|
| 971 |
+
"grad_norm": 0.9854965513455352,
|
| 972 |
+
"learning_rate": 3.178896585934588e-05,
|
| 973 |
+
"loss": 0.1922,
|
| 974 |
+
"loss_nan_ranks": 0,
|
| 975 |
+
"loss_rank_avg": 0.20682978630065918,
|
| 976 |
+
"step": 440,
|
| 977 |
+
"valid_targets_mean": 1247.1,
|
| 978 |
+
"valid_targets_min": 708
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 2.2474747474747474,
|
| 982 |
+
"grad_norm": 0.8783905199567699,
|
| 983 |
+
"learning_rate": 3.1550302486310076e-05,
|
| 984 |
+
"loss": 0.181,
|
| 985 |
+
"loss_nan_ranks": 0,
|
| 986 |
+
"loss_rank_avg": 0.17547810077667236,
|
| 987 |
+
"step": 445,
|
| 988 |
+
"valid_targets_mean": 1395.0,
|
| 989 |
+
"valid_targets_min": 986
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 2.2727272727272725,
|
| 993 |
+
"grad_norm": 0.7915351995988669,
|
| 994 |
+
"learning_rate": 3.130914526580478e-05,
|
| 995 |
+
"loss": 0.1932,
|
| 996 |
+
"loss_nan_ranks": 0,
|
| 997 |
+
"loss_rank_avg": 0.19163087010383606,
|
| 998 |
+
"step": 450,
|
| 999 |
+
"valid_targets_mean": 1419.6,
|
| 1000 |
+
"valid_targets_min": 550
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"epoch": 2.297979797979798,
|
| 1004 |
+
"grad_norm": 0.8603558279215641,
|
| 1005 |
+
"learning_rate": 3.10655462665377e-05,
|
| 1006 |
+
"loss": 0.1943,
|
| 1007 |
+
"loss_nan_ranks": 0,
|
| 1008 |
+
"loss_rank_avg": 0.18317505717277527,
|
| 1009 |
+
"step": 455,
|
| 1010 |
+
"valid_targets_mean": 1478.6,
|
| 1011 |
+
"valid_targets_min": 796
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 2.323232323232323,
|
| 1015 |
+
"grad_norm": 0.9291992362997976,
|
| 1016 |
+
"learning_rate": 3.0819558084425574e-05,
|
| 1017 |
+
"loss": 0.1858,
|
| 1018 |
+
"loss_nan_ranks": 0,
|
| 1019 |
+
"loss_rank_avg": 0.1851797103881836,
|
| 1020 |
+
"step": 460,
|
| 1021 |
+
"valid_targets_mean": 1252.2,
|
| 1022 |
+
"valid_targets_min": 862
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 2.3484848484848486,
|
| 1026 |
+
"grad_norm": 0.9994111902225407,
|
| 1027 |
+
"learning_rate": 3.0571233831238093e-05,
|
| 1028 |
+
"loss": 0.1912,
|
| 1029 |
+
"loss_nan_ranks": 0,
|
| 1030 |
+
"loss_rank_avg": 0.1833767294883728,
|
| 1031 |
+
"step": 465,
|
| 1032 |
+
"valid_targets_mean": 1134.1,
|
| 1033 |
+
"valid_targets_min": 619
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 2.3737373737373737,
|
| 1037 |
+
"grad_norm": 0.9400802045489894,
|
| 1038 |
+
"learning_rate": 3.032062712313044e-05,
|
| 1039 |
+
"loss": 0.1907,
|
| 1040 |
+
"loss_nan_ranks": 0,
|
| 1041 |
+
"loss_rank_avg": 0.19591230154037476,
|
| 1042 |
+
"step": 470,
|
| 1043 |
+
"valid_targets_mean": 1326.4,
|
| 1044 |
+
"valid_targets_min": 801
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 2.398989898989899,
|
| 1048 |
+
"grad_norm": 0.8710505639917704,
|
| 1049 |
+
"learning_rate": 3.0067792069066902e-05,
|
| 1050 |
+
"loss": 0.1963,
|
| 1051 |
+
"loss_nan_ranks": 0,
|
| 1052 |
+
"loss_rank_avg": 0.21165084838867188,
|
| 1053 |
+
"step": 475,
|
| 1054 |
+
"valid_targets_mean": 1496.6,
|
| 1055 |
+
"valid_targets_min": 774
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 2.4242424242424243,
|
| 1059 |
+
"grad_norm": 0.8977896309267136,
|
| 1060 |
+
"learning_rate": 2.9812783259138133e-05,
|
| 1061 |
+
"loss": 0.2008,
|
| 1062 |
+
"loss_nan_ranks": 0,
|
| 1063 |
+
"loss_rank_avg": 0.20881733298301697,
|
| 1064 |
+
"step": 480,
|
| 1065 |
+
"valid_targets_mean": 1376.1,
|
| 1066 |
+
"valid_targets_min": 600
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 2.4494949494949494,
|
| 1070 |
+
"grad_norm": 0.8422125060200054,
|
| 1071 |
+
"learning_rate": 2.955565575277449e-05,
|
| 1072 |
+
"loss": 0.1868,
|
| 1073 |
+
"loss_nan_ranks": 0,
|
| 1074 |
+
"loss_rank_avg": 0.18488860130310059,
|
| 1075 |
+
"step": 485,
|
| 1076 |
+
"valid_targets_mean": 1432.2,
|
| 1077 |
+
"valid_targets_min": 585
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 2.474747474747475,
|
| 1081 |
+
"grad_norm": 0.841379053094665,
|
| 1082 |
+
"learning_rate": 2.929646506685805e-05,
|
| 1083 |
+
"loss": 0.1896,
|
| 1084 |
+
"loss_nan_ranks": 0,
|
| 1085 |
+
"loss_rank_avg": 0.19385570287704468,
|
| 1086 |
+
"step": 490,
|
| 1087 |
+
"valid_targets_mean": 1452.9,
|
| 1088 |
+
"valid_targets_min": 811
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 2.5,
|
| 1092 |
+
"grad_norm": 0.8681195861479708,
|
| 1093 |
+
"learning_rate": 2.9035267163735856e-05,
|
| 1094 |
+
"loss": 0.1853,
|
| 1095 |
+
"loss_nan_ranks": 0,
|
| 1096 |
+
"loss_rank_avg": 0.18989858031272888,
|
| 1097 |
+
"step": 495,
|
| 1098 |
+
"valid_targets_mean": 1264.6,
|
| 1099 |
+
"valid_targets_min": 674
|
| 1100 |
+
},
|
| 1101 |
+
{
|
| 1102 |
+
"epoch": 2.525252525252525,
|
| 1103 |
+
"grad_norm": 0.9486462794838508,
|
| 1104 |
+
"learning_rate": 2.8772118439136972e-05,
|
| 1105 |
+
"loss": 0.1917,
|
| 1106 |
+
"loss_nan_ranks": 0,
|
| 1107 |
+
"loss_rank_avg": 0.20061013102531433,
|
| 1108 |
+
"step": 500,
|
| 1109 |
+
"valid_targets_mean": 1308.9,
|
| 1110 |
+
"valid_targets_min": 854
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"epoch": 2.5505050505050506,
|
| 1114 |
+
"grad_norm": 1.0120219125127008,
|
| 1115 |
+
"learning_rate": 2.8507075709996015e-05,
|
| 1116 |
+
"loss": 0.2,
|
| 1117 |
+
"loss_nan_ranks": 0,
|
| 1118 |
+
"loss_rank_avg": 0.19788292050361633,
|
| 1119 |
+
"step": 505,
|
| 1120 |
+
"valid_targets_mean": 1336.9,
|
| 1121 |
+
"valid_targets_min": 615
|
| 1122 |
+
},
|
| 1123 |
+
{
|
| 1124 |
+
"epoch": 2.5757575757575757,
|
| 1125 |
+
"grad_norm": 0.8552983942324871,
|
| 1126 |
+
"learning_rate": 2.8240196202185636e-05,
|
| 1127 |
+
"loss": 0.1841,
|
| 1128 |
+
"loss_nan_ranks": 0,
|
| 1129 |
+
"loss_rank_avg": 0.18201503157615662,
|
| 1130 |
+
"step": 510,
|
| 1131 |
+
"valid_targets_mean": 1183.4,
|
| 1132 |
+
"valid_targets_min": 648
|
| 1133 |
+
},
|
| 1134 |
+
{
|
| 1135 |
+
"epoch": 2.601010101010101,
|
| 1136 |
+
"grad_norm": 1.0101472372139235,
|
| 1137 |
+
"learning_rate": 2.797153753816084e-05,
|
| 1138 |
+
"loss": 0.2015,
|
| 1139 |
+
"loss_nan_ranks": 0,
|
| 1140 |
+
"loss_rank_avg": 0.18643571436405182,
|
| 1141 |
+
"step": 515,
|
| 1142 |
+
"valid_targets_mean": 1155.6,
|
| 1143 |
+
"valid_targets_min": 538
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 2.6262626262626263,
|
| 1147 |
+
"grad_norm": 0.8259754112301633,
|
| 1148 |
+
"learning_rate": 2.770115772451758e-05,
|
| 1149 |
+
"loss": 0.1847,
|
| 1150 |
+
"loss_nan_ranks": 0,
|
| 1151 |
+
"loss_rank_avg": 0.20032909512519836,
|
| 1152 |
+
"step": 520,
|
| 1153 |
+
"valid_targets_mean": 1452.1,
|
| 1154 |
+
"valid_targets_min": 640
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 2.6515151515151514,
|
| 1158 |
+
"grad_norm": 1.0080765247154564,
|
| 1159 |
+
"learning_rate": 2.7429115139468443e-05,
|
| 1160 |
+
"loss": 0.1868,
|
| 1161 |
+
"loss_nan_ranks": 0,
|
| 1162 |
+
"loss_rank_avg": 0.2050439417362213,
|
| 1163 |
+
"step": 525,
|
| 1164 |
+
"valid_targets_mean": 1231.2,
|
| 1165 |
+
"valid_targets_min": 678
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 2.676767676767677,
|
| 1169 |
+
"grad_norm": 0.9228666377959548,
|
| 1170 |
+
"learning_rate": 2.7155468520238116e-05,
|
| 1171 |
+
"loss": 0.1955,
|
| 1172 |
+
"loss_nan_ranks": 0,
|
| 1173 |
+
"loss_rank_avg": 0.20735567808151245,
|
| 1174 |
+
"step": 530,
|
| 1175 |
+
"valid_targets_mean": 1336.9,
|
| 1176 |
+
"valid_targets_min": 587
|
| 1177 |
+
},
|
| 1178 |
+
{
|
| 1179 |
+
"epoch": 2.702020202020202,
|
| 1180 |
+
"grad_norm": 0.997304280142903,
|
| 1181 |
+
"learning_rate": 2.6880276950381316e-05,
|
| 1182 |
+
"loss": 0.1881,
|
| 1183 |
+
"loss_nan_ranks": 0,
|
| 1184 |
+
"loss_rank_avg": 0.1983107328414917,
|
| 1185 |
+
"step": 535,
|
| 1186 |
+
"valid_targets_mean": 1249.5,
|
| 1187 |
+
"valid_targets_min": 521
|
| 1188 |
+
},
|
| 1189 |
+
{
|
| 1190 |
+
"epoch": 2.7272727272727275,
|
| 1191 |
+
"grad_norm": 0.9193727742835162,
|
| 1192 |
+
"learning_rate": 2.6603599847025935e-05,
|
| 1193 |
+
"loss": 0.1805,
|
| 1194 |
+
"loss_nan_ranks": 0,
|
| 1195 |
+
"loss_rank_avg": 0.18839475512504578,
|
| 1196 |
+
"step": 540,
|
| 1197 |
+
"valid_targets_mean": 1276.8,
|
| 1198 |
+
"valid_targets_min": 776
|
| 1199 |
+
},
|
| 1200 |
+
{
|
| 1201 |
+
"epoch": 2.7525252525252526,
|
| 1202 |
+
"grad_norm": 0.9459373491774038,
|
| 1203 |
+
"learning_rate": 2.63254969480442e-05,
|
| 1204 |
+
"loss": 0.191,
|
| 1205 |
+
"loss_nan_ranks": 0,
|
| 1206 |
+
"loss_rank_avg": 0.19836702942848206,
|
| 1207 |
+
"step": 545,
|
| 1208 |
+
"valid_targets_mean": 1273.7,
|
| 1209 |
+
"valid_targets_min": 702
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 2.7777777777777777,
|
| 1213 |
+
"grad_norm": 0.8854618406463927,
|
| 1214 |
+
"learning_rate": 2.6046028299154545e-05,
|
| 1215 |
+
"loss": 0.1875,
|
| 1216 |
+
"loss_nan_ranks": 0,
|
| 1217 |
+
"loss_rank_avg": 0.18734903633594513,
|
| 1218 |
+
"step": 550,
|
| 1219 |
+
"valid_targets_mean": 1388.6,
|
| 1220 |
+
"valid_targets_min": 546
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 2.8030303030303028,
|
| 1224 |
+
"grad_norm": 0.7860179708066867,
|
| 1225 |
+
"learning_rate": 2.5765254240957024e-05,
|
| 1226 |
+
"loss": 0.1886,
|
| 1227 |
+
"loss_nan_ranks": 0,
|
| 1228 |
+
"loss_rank_avg": 0.18938644230365753,
|
| 1229 |
+
"step": 555,
|
| 1230 |
+
"valid_targets_mean": 1631.9,
|
| 1231 |
+
"valid_targets_min": 1077
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 2.8282828282828283,
|
| 1235 |
+
"grad_norm": 0.8367854200810775,
|
| 1236 |
+
"learning_rate": 2.5483235395905056e-05,
|
| 1237 |
+
"loss": 0.1867,
|
| 1238 |
+
"loss_nan_ranks": 0,
|
| 1239 |
+
"loss_rank_avg": 0.20430481433868408,
|
| 1240 |
+
"step": 560,
|
| 1241 |
+
"valid_targets_mean": 1437.8,
|
| 1242 |
+
"valid_targets_min": 690
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 2.8535353535353534,
|
| 1246 |
+
"grad_norm": 0.9180703166963079,
|
| 1247 |
+
"learning_rate": 2.5200032655216343e-05,
|
| 1248 |
+
"loss": 0.1894,
|
| 1249 |
+
"loss_nan_ranks": 0,
|
| 1250 |
+
"loss_rank_avg": 0.18853136897087097,
|
| 1251 |
+
"step": 565,
|
| 1252 |
+
"valid_targets_mean": 1259.7,
|
| 1253 |
+
"valid_targets_min": 684
|
| 1254 |
+
},
|
| 1255 |
+
{
|
| 1256 |
+
"epoch": 2.878787878787879,
|
| 1257 |
+
"grad_norm": 0.8164719253098022,
|
| 1258 |
+
"learning_rate": 2.4915707165725694e-05,
|
| 1259 |
+
"loss": 0.1858,
|
| 1260 |
+
"loss_nan_ranks": 0,
|
| 1261 |
+
"loss_rank_avg": 0.18391425907611847,
|
| 1262 |
+
"step": 570,
|
| 1263 |
+
"valid_targets_mean": 1376.6,
|
| 1264 |
+
"valid_targets_min": 802
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"epoch": 2.904040404040404,
|
| 1268 |
+
"grad_norm": 0.9943903226603121,
|
| 1269 |
+
"learning_rate": 2.4630320316682724e-05,
|
| 1270 |
+
"loss": 0.1847,
|
| 1271 |
+
"loss_nan_ranks": 0,
|
| 1272 |
+
"loss_rank_avg": 0.19583845138549805,
|
| 1273 |
+
"step": 575,
|
| 1274 |
+
"valid_targets_mean": 1316.8,
|
| 1275 |
+
"valid_targets_min": 685
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 2.929292929292929,
|
| 1279 |
+
"grad_norm": 0.9662414433511091,
|
| 1280 |
+
"learning_rate": 2.4343933726497183e-05,
|
| 1281 |
+
"loss": 0.1856,
|
| 1282 |
+
"loss_nan_ranks": 0,
|
| 1283 |
+
"loss_rank_avg": 0.17909899353981018,
|
| 1284 |
+
"step": 580,
|
| 1285 |
+
"valid_targets_mean": 1219.6,
|
| 1286 |
+
"valid_targets_min": 603
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 2.9545454545454546,
|
| 1290 |
+
"grad_norm": 0.8264667060320464,
|
| 1291 |
+
"learning_rate": 2.4056609229434812e-05,
|
| 1292 |
+
"loss": 0.1887,
|
| 1293 |
+
"loss_nan_ranks": 0,
|
| 1294 |
+
"loss_rank_avg": 0.1930309534072876,
|
| 1295 |
+
"step": 585,
|
| 1296 |
+
"valid_targets_mean": 1353.8,
|
| 1297 |
+
"valid_targets_min": 751
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 2.9797979797979797,
|
| 1301 |
+
"grad_norm": 0.8672579031747749,
|
| 1302 |
+
"learning_rate": 2.376840886226656e-05,
|
| 1303 |
+
"loss": 0.1867,
|
| 1304 |
+
"loss_nan_ranks": 0,
|
| 1305 |
+
"loss_rank_avg": 0.1810949146747589,
|
| 1306 |
+
"step": 590,
|
| 1307 |
+
"valid_targets_mean": 1360.6,
|
| 1308 |
+
"valid_targets_min": 681
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 3.005050505050505,
|
| 1312 |
+
"grad_norm": 0.8370979896650649,
|
| 1313 |
+
"learning_rate": 2.347939485087416e-05,
|
| 1314 |
+
"loss": 0.1831,
|
| 1315 |
+
"loss_nan_ranks": 0,
|
| 1316 |
+
"loss_rank_avg": 0.16158387064933777,
|
| 1317 |
+
"step": 595,
|
| 1318 |
+
"valid_targets_mean": 1132.1,
|
| 1319 |
+
"valid_targets_min": 475
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 3.0303030303030303,
|
| 1323 |
+
"grad_norm": 0.8281295886895214,
|
| 1324 |
+
"learning_rate": 2.3189629596814788e-05,
|
| 1325 |
+
"loss": 0.157,
|
| 1326 |
+
"loss_nan_ranks": 0,
|
| 1327 |
+
"loss_rank_avg": 0.15015463531017303,
|
| 1328 |
+
"step": 600,
|
| 1329 |
+
"valid_targets_mean": 1357.4,
|
| 1330 |
+
"valid_targets_min": 629
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"epoch": 3.0555555555555554,
|
| 1334 |
+
"grad_norm": 1.0077015146202375,
|
| 1335 |
+
"learning_rate": 2.2899175663847823e-05,
|
| 1336 |
+
"loss": 0.1605,
|
| 1337 |
+
"loss_nan_ranks": 0,
|
| 1338 |
+
"loss_rank_avg": 0.17284418642520905,
|
| 1339 |
+
"step": 605,
|
| 1340 |
+
"valid_targets_mean": 1323.3,
|
| 1341 |
+
"valid_targets_min": 681
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 3.080808080808081,
|
| 1345 |
+
"grad_norm": 0.9055532065630415,
|
| 1346 |
+
"learning_rate": 2.2608095764426602e-05,
|
| 1347 |
+
"loss": 0.1609,
|
| 1348 |
+
"loss_nan_ranks": 0,
|
| 1349 |
+
"loss_rank_avg": 0.172052800655365,
|
| 1350 |
+
"step": 610,
|
| 1351 |
+
"valid_targets_mean": 1438.2,
|
| 1352 |
+
"valid_targets_min": 785
|
| 1353 |
+
},
|
| 1354 |
+
{
|
| 1355 |
+
"epoch": 3.106060606060606,
|
| 1356 |
+
"grad_norm": 0.9289877404583321,
|
| 1357 |
+
"learning_rate": 2.2316452746158063e-05,
|
| 1358 |
+
"loss": 0.1649,
|
| 1359 |
+
"loss_nan_ranks": 0,
|
| 1360 |
+
"loss_rank_avg": 0.18071796000003815,
|
| 1361 |
+
"step": 615,
|
| 1362 |
+
"valid_targets_mean": 1361.3,
|
| 1363 |
+
"valid_targets_min": 618
|
| 1364 |
+
},
|
| 1365 |
+
{
|
| 1366 |
+
"epoch": 3.1313131313131315,
|
| 1367 |
+
"grad_norm": 0.9997329115169467,
|
| 1368 |
+
"learning_rate": 2.2024309578233174e-05,
|
| 1369 |
+
"loss": 0.161,
|
| 1370 |
+
"loss_nan_ranks": 0,
|
| 1371 |
+
"loss_rank_avg": 0.16634033620357513,
|
| 1372 |
+
"step": 620,
|
| 1373 |
+
"valid_targets_mean": 1173.6,
|
| 1374 |
+
"valid_targets_min": 690
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 3.1565656565656566,
|
| 1378 |
+
"grad_norm": 1.009976573995706,
|
| 1379 |
+
"learning_rate": 2.1731729337831173e-05,
|
| 1380 |
+
"loss": 0.1574,
|
| 1381 |
+
"loss_nan_ranks": 0,
|
| 1382 |
+
"loss_rank_avg": 0.16698682308197021,
|
| 1383 |
+
"step": 625,
|
| 1384 |
+
"valid_targets_mean": 1469.7,
|
| 1385 |
+
"valid_targets_min": 677
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 3.1818181818181817,
|
| 1389 |
+
"grad_norm": 0.9404190990393296,
|
| 1390 |
+
"learning_rate": 2.143877519650042e-05,
|
| 1391 |
+
"loss": 0.165,
|
| 1392 |
+
"loss_nan_ranks": 0,
|
| 1393 |
+
"loss_rank_avg": 0.16389097273349762,
|
| 1394 |
+
"step": 630,
|
| 1395 |
+
"valid_targets_mean": 1243.7,
|
| 1396 |
+
"valid_targets_min": 655
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 3.207070707070707,
|
| 1400 |
+
"grad_norm": 0.9313377151581581,
|
| 1401 |
+
"learning_rate": 2.1145510406518928e-05,
|
| 1402 |
+
"loss": 0.1654,
|
| 1403 |
+
"loss_nan_ranks": 0,
|
| 1404 |
+
"loss_rank_avg": 0.17033018171787262,
|
| 1405 |
+
"step": 635,
|
| 1406 |
+
"valid_targets_mean": 1205.6,
|
| 1407 |
+
"valid_targets_min": 742
|
| 1408 |
+
},
|
| 1409 |
+
{
|
| 1410 |
+
"epoch": 3.2323232323232323,
|
| 1411 |
+
"grad_norm": 0.8337581545510251,
|
| 1412 |
+
"learning_rate": 2.0851998287237452e-05,
|
| 1413 |
+
"loss": 0.1603,
|
| 1414 |
+
"loss_nan_ranks": 0,
|
| 1415 |
+
"loss_rank_avg": 0.14411024749279022,
|
| 1416 |
+
"step": 640,
|
| 1417 |
+
"valid_targets_mean": 1329.4,
|
| 1418 |
+
"valid_targets_min": 746
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 3.257575757575758,
|
| 1422 |
+
"grad_norm": 0.8441677147621939,
|
| 1423 |
+
"learning_rate": 2.0558302211408075e-05,
|
| 1424 |
+
"loss": 0.1568,
|
| 1425 |
+
"loss_nan_ranks": 0,
|
| 1426 |
+
"loss_rank_avg": 0.15460258722305298,
|
| 1427 |
+
"step": 645,
|
| 1428 |
+
"valid_targets_mean": 1355.2,
|
| 1429 |
+
"valid_targets_min": 684
|
| 1430 |
+
},
|
| 1431 |
+
{
|
| 1432 |
+
"epoch": 3.282828282828283,
|
| 1433 |
+
"grad_norm": 0.894454117393474,
|
| 1434 |
+
"learning_rate": 2.0264485591501272e-05,
|
| 1435 |
+
"loss": 0.1657,
|
| 1436 |
+
"loss_nan_ranks": 0,
|
| 1437 |
+
"loss_rank_avg": 0.1565285176038742,
|
| 1438 |
+
"step": 650,
|
| 1439 |
+
"valid_targets_mean": 1227.0,
|
| 1440 |
+
"valid_targets_min": 686
|
| 1441 |
+
},
|
| 1442 |
+
{
|
| 1443 |
+
"epoch": 3.308080808080808,
|
| 1444 |
+
"grad_norm": 1.0769409575744318,
|
| 1445 |
+
"learning_rate": 1.9970611866014432e-05,
|
| 1446 |
+
"loss": 0.1626,
|
| 1447 |
+
"loss_nan_ranks": 0,
|
| 1448 |
+
"loss_rank_avg": 0.1580488085746765,
|
| 1449 |
+
"step": 655,
|
| 1450 |
+
"valid_targets_mean": 1152.6,
|
| 1451 |
+
"valid_targets_min": 576
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 3.3333333333333335,
|
| 1455 |
+
"grad_norm": 0.9561591809140133,
|
| 1456 |
+
"learning_rate": 1.967674448577471e-05,
|
| 1457 |
+
"loss": 0.1581,
|
| 1458 |
+
"loss_nan_ranks": 0,
|
| 1459 |
+
"loss_rank_avg": 0.15929345786571503,
|
| 1460 |
+
"step": 660,
|
| 1461 |
+
"valid_targets_mean": 1284.5,
|
| 1462 |
+
"valid_targets_min": 629
|
| 1463 |
+
},
|
| 1464 |
+
{
|
| 1465 |
+
"epoch": 3.3585858585858586,
|
| 1466 |
+
"grad_norm": 0.9519946019411174,
|
| 1467 |
+
"learning_rate": 1.9382946900239247e-05,
|
| 1468 |
+
"loss": 0.1586,
|
| 1469 |
+
"loss_nan_ranks": 0,
|
| 1470 |
+
"loss_rank_avg": 0.1578896939754486,
|
| 1471 |
+
"step": 665,
|
| 1472 |
+
"valid_targets_mean": 1273.5,
|
| 1473 |
+
"valid_targets_min": 841
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 3.3838383838383836,
|
| 1477 |
+
"grad_norm": 0.9445690376209704,
|
| 1478 |
+
"learning_rate": 1.9089282543795692e-05,
|
| 1479 |
+
"loss": 0.171,
|
| 1480 |
+
"loss_nan_ranks": 0,
|
| 1481 |
+
"loss_rank_avg": 0.16323482990264893,
|
| 1482 |
+
"step": 670,
|
| 1483 |
+
"valid_targets_mean": 1237.7,
|
| 1484 |
+
"valid_targets_min": 704
|
| 1485 |
+
},
|
| 1486 |
+
{
|
| 1487 |
+
"epoch": 3.409090909090909,
|
| 1488 |
+
"grad_norm": 0.9125004973109183,
|
| 1489 |
+
"learning_rate": 1.879581482206592e-05,
|
| 1490 |
+
"loss": 0.1549,
|
| 1491 |
+
"loss_nan_ranks": 0,
|
| 1492 |
+
"loss_rank_avg": 0.1543537974357605,
|
| 1493 |
+
"step": 675,
|
| 1494 |
+
"valid_targets_mean": 1212.9,
|
| 1495 |
+
"valid_targets_min": 608
|
| 1496 |
+
},
|
| 1497 |
+
{
|
| 1498 |
+
"epoch": 3.4343434343434343,
|
| 1499 |
+
"grad_norm": 0.862065205565415,
|
| 1500 |
+
"learning_rate": 1.8502607098216056e-05,
|
| 1501 |
+
"loss": 0.1645,
|
| 1502 |
+
"loss_nan_ranks": 0,
|
| 1503 |
+
"loss_rank_avg": 0.17540498077869415,
|
| 1504 |
+
"step": 680,
|
| 1505 |
+
"valid_targets_mean": 1439.5,
|
| 1506 |
+
"valid_targets_min": 626
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 3.45959595959596,
|
| 1510 |
+
"grad_norm": 0.9640325333317653,
|
| 1511 |
+
"learning_rate": 1.8209722679275602e-05,
|
| 1512 |
+
"loss": 0.1636,
|
| 1513 |
+
"loss_nan_ranks": 0,
|
| 1514 |
+
"loss_rank_avg": 0.16301819682121277,
|
| 1515 |
+
"step": 685,
|
| 1516 |
+
"valid_targets_mean": 1403.1,
|
| 1517 |
+
"valid_targets_min": 758
|
| 1518 |
+
},
|
| 1519 |
+
{
|
| 1520 |
+
"epoch": 3.484848484848485,
|
| 1521 |
+
"grad_norm": 0.9118905245785244,
|
| 1522 |
+
"learning_rate": 1.791722480246868e-05,
|
| 1523 |
+
"loss": 0.1615,
|
| 1524 |
+
"loss_nan_ranks": 0,
|
| 1525 |
+
"loss_rank_avg": 0.1672666370868683,
|
| 1526 |
+
"step": 690,
|
| 1527 |
+
"valid_targets_mean": 1300.1,
|
| 1528 |
+
"valid_targets_min": 859
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 3.51010101010101,
|
| 1532 |
+
"grad_norm": 0.879350730391716,
|
| 1533 |
+
"learning_rate": 1.762517662156037e-05,
|
| 1534 |
+
"loss": 0.1592,
|
| 1535 |
+
"loss_nan_ranks": 0,
|
| 1536 |
+
"loss_rank_avg": 0.1608966588973999,
|
| 1537 |
+
"step": 695,
|
| 1538 |
+
"valid_targets_mean": 1377.4,
|
| 1539 |
+
"valid_targets_min": 927
|
| 1540 |
+
},
|
| 1541 |
+
{
|
| 1542 |
+
"epoch": 3.5353535353535355,
|
| 1543 |
+
"grad_norm": 0.9462737198336908,
|
| 1544 |
+
"learning_rate": 1.733364119322109e-05,
|
| 1545 |
+
"loss": 0.1648,
|
| 1546 |
+
"loss_nan_ranks": 0,
|
| 1547 |
+
"loss_rank_avg": 0.17058268189430237,
|
| 1548 |
+
"step": 700,
|
| 1549 |
+
"valid_targets_mean": 1403.2,
|
| 1550 |
+
"valid_targets_min": 609
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 3.5606060606060606,
|
| 1554 |
+
"grad_norm": 0.9043276008484828,
|
| 1555 |
+
"learning_rate": 1.704268146341185e-05,
|
| 1556 |
+
"loss": 0.1683,
|
| 1557 |
+
"loss_nan_ranks": 0,
|
| 1558 |
+
"loss_rank_avg": 0.17930132150650024,
|
| 1559 |
+
"step": 705,
|
| 1560 |
+
"valid_targets_mean": 1315.9,
|
| 1561 |
+
"valid_targets_min": 678
|
| 1562 |
+
},
|
| 1563 |
+
{
|
| 1564 |
+
"epoch": 3.5858585858585856,
|
| 1565 |
+
"grad_norm": 0.8976270383472466,
|
| 1566 |
+
"learning_rate": 1.675236025379355e-05,
|
| 1567 |
+
"loss": 0.1626,
|
| 1568 |
+
"loss_nan_ranks": 0,
|
| 1569 |
+
"loss_rank_avg": 0.15831458568572998,
|
| 1570 |
+
"step": 710,
|
| 1571 |
+
"valid_targets_mean": 1351.8,
|
| 1572 |
+
"valid_targets_min": 626
|
| 1573 |
+
},
|
| 1574 |
+
{
|
| 1575 |
+
"epoch": 3.611111111111111,
|
| 1576 |
+
"grad_norm": 0.9372138654679043,
|
| 1577 |
+
"learning_rate": 1.6462740248162988e-05,
|
| 1578 |
+
"loss": 0.1628,
|
| 1579 |
+
"loss_nan_ranks": 0,
|
| 1580 |
+
"loss_rank_avg": 0.16674670577049255,
|
| 1581 |
+
"step": 715,
|
| 1582 |
+
"valid_targets_mean": 1407.9,
|
| 1583 |
+
"valid_targets_min": 869
|
| 1584 |
+
},
|
| 1585 |
+
{
|
| 1586 |
+
"epoch": 3.6363636363636362,
|
| 1587 |
+
"grad_norm": 0.8889620690389666,
|
| 1588 |
+
"learning_rate": 1.6173883978918682e-05,
|
| 1589 |
+
"loss": 0.1579,
|
| 1590 |
+
"loss_nan_ranks": 0,
|
| 1591 |
+
"loss_rank_avg": 0.16323408484458923,
|
| 1592 |
+
"step": 720,
|
| 1593 |
+
"valid_targets_mean": 1347.6,
|
| 1594 |
+
"valid_targets_min": 714
|
| 1595 |
+
},
|
| 1596 |
+
{
|
| 1597 |
+
"epoch": 3.6616161616161618,
|
| 1598 |
+
"grad_norm": 0.9461049287423077,
|
| 1599 |
+
"learning_rate": 1.5885853813559392e-05,
|
| 1600 |
+
"loss": 0.1606,
|
| 1601 |
+
"loss_nan_ranks": 0,
|
| 1602 |
+
"loss_rank_avg": 0.16170771420001984,
|
| 1603 |
+
"step": 725,
|
| 1604 |
+
"valid_targets_mean": 1151.1,
|
| 1605 |
+
"valid_targets_min": 474
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 3.686868686868687,
|
| 1609 |
+
"grad_norm": 0.9883837352207571,
|
| 1610 |
+
"learning_rate": 1.5598711941218265e-05,
|
| 1611 |
+
"loss": 0.1639,
|
| 1612 |
+
"loss_nan_ranks": 0,
|
| 1613 |
+
"loss_rank_avg": 0.1605217158794403,
|
| 1614 |
+
"step": 730,
|
| 1615 |
+
"valid_targets_mean": 1241.0,
|
| 1616 |
+
"valid_targets_min": 578
|
| 1617 |
+
},
|
| 1618 |
+
{
|
| 1619 |
+
"epoch": 3.712121212121212,
|
| 1620 |
+
"grad_norm": 2.3494111496602836,
|
| 1621 |
+
"learning_rate": 1.531252035923541e-05,
|
| 1622 |
+
"loss": 0.1686,
|
| 1623 |
+
"loss_nan_ranks": 0,
|
| 1624 |
+
"loss_rank_avg": 0.17595025897026062,
|
| 1625 |
+
"step": 735,
|
| 1626 |
+
"valid_targets_mean": 1373.8,
|
| 1627 |
+
"valid_targets_min": 591
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 3.7373737373737375,
|
| 1631 |
+
"grad_norm": 0.9593181868358482,
|
| 1632 |
+
"learning_rate": 1.5027340859771972e-05,
|
| 1633 |
+
"loss": 0.1652,
|
| 1634 |
+
"loss_nan_ranks": 0,
|
| 1635 |
+
"loss_rank_avg": 0.15891680121421814,
|
| 1636 |
+
"step": 740,
|
| 1637 |
+
"valid_targets_mean": 1432.9,
|
| 1638 |
+
"valid_targets_min": 785
|
| 1639 |
+
},
|
| 1640 |
+
{
|
| 1641 |
+
"epoch": 3.7626262626262625,
|
| 1642 |
+
"grad_norm": 1.2303147950630564,
|
| 1643 |
+
"learning_rate": 1.4743235016468474e-05,
|
| 1644 |
+
"loss": 0.1628,
|
| 1645 |
+
"loss_nan_ranks": 0,
|
| 1646 |
+
"loss_rank_avg": 0.15962883830070496,
|
| 1647 |
+
"step": 745,
|
| 1648 |
+
"valid_targets_mean": 1254.1,
|
| 1649 |
+
"valid_targets_min": 640
|
| 1650 |
+
},
|
| 1651 |
+
{
|
| 1652 |
+
"epoch": 3.787878787878788,
|
| 1653 |
+
"grad_norm": 0.868720721287915,
|
| 1654 |
+
"learning_rate": 1.4460264171150296e-05,
|
| 1655 |
+
"loss": 0.1614,
|
| 1656 |
+
"loss_nan_ranks": 0,
|
| 1657 |
+
"loss_rank_avg": 0.16074195504188538,
|
| 1658 |
+
"step": 750,
|
| 1659 |
+
"valid_targets_mean": 1357.2,
|
| 1660 |
+
"valid_targets_min": 915
|
| 1661 |
+
},
|
| 1662 |
+
{
|
| 1663 |
+
"epoch": 3.813131313131313,
|
| 1664 |
+
"grad_norm": 0.8933503401903754,
|
| 1665 |
+
"learning_rate": 1.4178489420583297e-05,
|
| 1666 |
+
"loss": 0.1659,
|
| 1667 |
+
"loss_nan_ranks": 0,
|
| 1668 |
+
"loss_rank_avg": 0.16842246055603027,
|
| 1669 |
+
"step": 755,
|
| 1670 |
+
"valid_targets_mean": 1366.2,
|
| 1671 |
+
"valid_targets_min": 494
|
| 1672 |
+
},
|
| 1673 |
+
{
|
| 1674 |
+
"epoch": 3.8383838383838382,
|
| 1675 |
+
"grad_norm": 0.9117330229229211,
|
| 1676 |
+
"learning_rate": 1.3897971603282278e-05,
|
| 1677 |
+
"loss": 0.1595,
|
| 1678 |
+
"loss_nan_ranks": 0,
|
| 1679 |
+
"loss_rank_avg": 0.15995121002197266,
|
| 1680 |
+
"step": 760,
|
| 1681 |
+
"valid_targets_mean": 1271.9,
|
| 1682 |
+
"valid_targets_min": 709
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 3.8636363636363638,
|
| 1686 |
+
"grad_norm": 0.9015209816689598,
|
| 1687 |
+
"learning_rate": 1.36187712863752e-05,
|
| 1688 |
+
"loss": 0.166,
|
| 1689 |
+
"loss_nan_ranks": 0,
|
| 1690 |
+
"loss_rank_avg": 0.15097013115882874,
|
| 1691 |
+
"step": 765,
|
| 1692 |
+
"valid_targets_mean": 1283.9,
|
| 1693 |
+
"valid_targets_min": 650
|
| 1694 |
+
},
|
| 1695 |
+
{
|
| 1696 |
+
"epoch": 3.888888888888889,
|
| 1697 |
+
"grad_norm": 1.0021456080906517,
|
| 1698 |
+
"learning_rate": 1.3340948752526069e-05,
|
| 1699 |
+
"loss": 0.1599,
|
| 1700 |
+
"loss_nan_ranks": 0,
|
| 1701 |
+
"loss_rank_avg": 0.16016200184822083,
|
| 1702 |
+
"step": 770,
|
| 1703 |
+
"valid_targets_mean": 1304.5,
|
| 1704 |
+
"valid_targets_min": 508
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 3.9141414141414144,
|
| 1708 |
+
"grad_norm": 0.9443204411485612,
|
| 1709 |
+
"learning_rate": 1.3064563986919142e-05,
|
| 1710 |
+
"loss": 0.1596,
|
| 1711 |
+
"loss_nan_ranks": 0,
|
| 1712 |
+
"loss_rank_avg": 0.16480416059494019,
|
| 1713 |
+
"step": 775,
|
| 1714 |
+
"valid_targets_mean": 1187.4,
|
| 1715 |
+
"valid_targets_min": 618
|
| 1716 |
+
},
|
| 1717 |
+
{
|
| 1718 |
+
"epoch": 3.9393939393939394,
|
| 1719 |
+
"grad_norm": 1.0288285211308523,
|
| 1720 |
+
"learning_rate": 1.278967666430745e-05,
|
| 1721 |
+
"loss": 0.1628,
|
| 1722 |
+
"loss_nan_ranks": 0,
|
| 1723 |
+
"loss_rank_avg": 0.16644668579101562,
|
| 1724 |
+
"step": 780,
|
| 1725 |
+
"valid_targets_mean": 1176.1,
|
| 1726 |
+
"valid_targets_min": 711
|
| 1727 |
+
},
|
| 1728 |
+
{
|
| 1729 |
+
"epoch": 3.9646464646464645,
|
| 1730 |
+
"grad_norm": 0.9366989096743141,
|
| 1731 |
+
"learning_rate": 1.2516346136128318e-05,
|
| 1732 |
+
"loss": 0.1641,
|
| 1733 |
+
"loss_nan_ranks": 0,
|
| 1734 |
+
"loss_rank_avg": 0.1586305946111679,
|
| 1735 |
+
"step": 785,
|
| 1736 |
+
"valid_targets_mean": 1275.4,
|
| 1737 |
+
"valid_targets_min": 615
|
| 1738 |
+
},
|
| 1739 |
+
{
|
| 1740 |
+
"epoch": 3.98989898989899,
|
| 1741 |
+
"grad_norm": 1.0032114563953773,
|
| 1742 |
+
"learning_rate": 1.2244631417688632e-05,
|
| 1743 |
+
"loss": 0.1634,
|
| 1744 |
+
"loss_nan_ranks": 0,
|
| 1745 |
+
"loss_rank_avg": 0.16418969631195068,
|
| 1746 |
+
"step": 790,
|
| 1747 |
+
"valid_targets_mean": 1259.9,
|
| 1748 |
+
"valid_targets_min": 784
|
| 1749 |
+
},
|
| 1750 |
+
{
|
| 1751 |
+
"epoch": 4.015151515151516,
|
| 1752 |
+
"grad_norm": 0.8527845312952415,
|
| 1753 |
+
"learning_rate": 1.197459117542278e-05,
|
| 1754 |
+
"loss": 0.1509,
|
| 1755 |
+
"loss_nan_ranks": 0,
|
| 1756 |
+
"loss_rank_avg": 0.14444586634635925,
|
| 1757 |
+
"step": 795,
|
| 1758 |
+
"valid_targets_mean": 1407.8,
|
| 1759 |
+
"valid_targets_min": 683
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 4.040404040404041,
|
| 1763 |
+
"grad_norm": 0.9834828014413456,
|
| 1764 |
+
"learning_rate": 1.170628371422587e-05,
|
| 1765 |
+
"loss": 0.1365,
|
| 1766 |
+
"loss_nan_ranks": 0,
|
| 1767 |
+
"loss_rank_avg": 0.1405264139175415,
|
| 1768 |
+
"step": 800,
|
| 1769 |
+
"valid_targets_mean": 1329.9,
|
| 1770 |
+
"valid_targets_min": 688
|
| 1771 |
+
},
|
| 1772 |
+
{
|
| 1773 |
+
"epoch": 4.065656565656566,
|
| 1774 |
+
"grad_norm": 1.0122303972675173,
|
| 1775 |
+
"learning_rate": 1.1439766964864995e-05,
|
| 1776 |
+
"loss": 0.1454,
|
| 1777 |
+
"loss_nan_ranks": 0,
|
| 1778 |
+
"loss_rank_avg": 0.15851764380931854,
|
| 1779 |
+
"step": 805,
|
| 1780 |
+
"valid_targets_mean": 1417.4,
|
| 1781 |
+
"valid_targets_min": 800
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 4.090909090909091,
|
| 1785 |
+
"grad_norm": 1.0252397884032003,
|
| 1786 |
+
"learning_rate": 1.117509847147128e-05,
|
| 1787 |
+
"loss": 0.1405,
|
| 1788 |
+
"loss_nan_ranks": 0,
|
| 1789 |
+
"loss_rank_avg": 0.13895373046398163,
|
| 1790 |
+
"step": 810,
|
| 1791 |
+
"valid_targets_mean": 1156.9,
|
| 1792 |
+
"valid_targets_min": 574
|
| 1793 |
+
},
|
| 1794 |
+
{
|
| 1795 |
+
"epoch": 4.116161616161616,
|
| 1796 |
+
"grad_norm": 0.8421871414828316,
|
| 1797 |
+
"learning_rate": 1.0912335379115469e-05,
|
| 1798 |
+
"loss": 0.138,
|
| 1799 |
+
"loss_nan_ranks": 0,
|
| 1800 |
+
"loss_rank_avg": 0.1370278298854828,
|
| 1801 |
+
"step": 815,
|
| 1802 |
+
"valid_targets_mean": 1569.4,
|
| 1803 |
+
"valid_targets_min": 668
|
| 1804 |
+
},
|
| 1805 |
+
{
|
| 1806 |
+
"epoch": 4.141414141414141,
|
| 1807 |
+
"grad_norm": 0.9960492717705738,
|
| 1808 |
+
"learning_rate": 1.0651534421469569e-05,
|
| 1809 |
+
"loss": 0.1441,
|
| 1810 |
+
"loss_nan_ranks": 0,
|
| 1811 |
+
"loss_rank_avg": 0.1409623920917511,
|
| 1812 |
+
"step": 820,
|
| 1813 |
+
"valid_targets_mean": 1150.9,
|
| 1814 |
+
"valid_targets_min": 604
|
| 1815 |
+
},
|
| 1816 |
+
{
|
| 1817 |
+
"epoch": 4.166666666666667,
|
| 1818 |
+
"grad_norm": 0.9475930503556128,
|
| 1819 |
+
"learning_rate": 1.0392751908557406e-05,
|
| 1820 |
+
"loss": 0.1423,
|
| 1821 |
+
"loss_nan_ranks": 0,
|
| 1822 |
+
"loss_rank_avg": 0.14038413763046265,
|
| 1823 |
+
"step": 825,
|
| 1824 |
+
"valid_targets_mean": 1251.2,
|
| 1825 |
+
"valid_targets_min": 741
|
| 1826 |
+
},
|
| 1827 |
+
{
|
| 1828 |
+
"epoch": 4.191919191919192,
|
| 1829 |
+
"grad_norm": 0.9077538390467569,
|
| 1830 |
+
"learning_rate": 1.013604371459663e-05,
|
| 1831 |
+
"loss": 0.1385,
|
| 1832 |
+
"loss_nan_ranks": 0,
|
| 1833 |
+
"loss_rank_avg": 0.1355401575565338,
|
| 1834 |
+
"step": 830,
|
| 1835 |
+
"valid_targets_mean": 1393.7,
|
| 1836 |
+
"valid_targets_min": 680
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 4.217171717171717,
|
| 1840 |
+
"grad_norm": 0.9313116277410778,
|
| 1841 |
+
"learning_rate": 9.881465265934802e-06,
|
| 1842 |
+
"loss": 0.1434,
|
| 1843 |
+
"loss_nan_ranks": 0,
|
| 1844 |
+
"loss_rank_avg": 0.13590630888938904,
|
| 1845 |
+
"step": 835,
|
| 1846 |
+
"valid_targets_mean": 1176.8,
|
| 1847 |
+
"valid_targets_min": 785
|
| 1848 |
+
},
|
| 1849 |
+
{
|
| 1850 |
+
"epoch": 4.242424242424242,
|
| 1851 |
+
"grad_norm": 1.0954460592720818,
|
| 1852 |
+
"learning_rate": 9.62907152908215e-06,
|
| 1853 |
+
"loss": 0.1395,
|
| 1854 |
+
"loss_nan_ranks": 0,
|
| 1855 |
+
"loss_rank_avg": 0.14245356619358063,
|
| 1856 |
+
"step": 840,
|
| 1857 |
+
"valid_targets_mean": 1191.3,
|
| 1858 |
+
"valid_targets_min": 619
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 4.267676767676767,
|
| 1862 |
+
"grad_norm": 0.9434679350463996,
|
| 1863 |
+
"learning_rate": 9.378916998843716e-06,
|
| 1864 |
+
"loss": 0.145,
|
| 1865 |
+
"loss_nan_ranks": 0,
|
| 1866 |
+
"loss_rank_avg": 0.1527371108531952,
|
| 1867 |
+
"step": 845,
|
| 1868 |
+
"valid_targets_mean": 1231.9,
|
| 1869 |
+
"valid_targets_min": 714
|
| 1870 |
+
},
|
| 1871 |
+
{
|
| 1872 |
+
"epoch": 4.292929292929293,
|
| 1873 |
+
"grad_norm": 0.9392165090395129,
|
| 1874 |
+
"learning_rate": 9.13105568655322e-06,
|
| 1875 |
+
"loss": 0.1407,
|
| 1876 |
+
"loss_nan_ranks": 0,
|
| 1877 |
+
"loss_rank_avg": 0.14035402238368988,
|
| 1878 |
+
"step": 850,
|
| 1879 |
+
"valid_targets_mean": 1247.8,
|
| 1880 |
+
"valid_targets_min": 494
|
| 1881 |
+
},
|
| 1882 |
+
{
|
| 1883 |
+
"epoch": 4.318181818181818,
|
| 1884 |
+
"grad_norm": 0.9610037453369663,
|
| 1885 |
+
"learning_rate": 8.885541108411386e-06,
|
| 1886 |
+
"loss": 0.1433,
|
| 1887 |
+
"loss_nan_ranks": 0,
|
| 1888 |
+
"loss_rank_avg": 0.13992322981357574,
|
| 1889 |
+
"step": 855,
|
| 1890 |
+
"valid_targets_mean": 1307.4,
|
| 1891 |
+
"valid_targets_min": 681
|
| 1892 |
+
},
|
| 1893 |
+
{
|
| 1894 |
+
"epoch": 4.343434343434343,
|
| 1895 |
+
"grad_norm": 0.9683597353689614,
|
| 1896 |
+
"learning_rate": 8.642426273931202e-06,
|
| 1897 |
+
"loss": 0.146,
|
| 1898 |
+
"loss_nan_ranks": 0,
|
| 1899 |
+
"loss_rank_avg": 0.1510647088289261,
|
| 1900 |
+
"step": 860,
|
| 1901 |
+
"valid_targets_mean": 1492.4,
|
| 1902 |
+
"valid_targets_min": 714
|
| 1903 |
+
},
|
| 1904 |
+
{
|
| 1905 |
+
"epoch": 4.3686868686868685,
|
| 1906 |
+
"grad_norm": 0.9533225821806605,
|
| 1907 |
+
"learning_rate": 8.40176367449247e-06,
|
| 1908 |
+
"loss": 0.1386,
|
| 1909 |
+
"loss_nan_ranks": 0,
|
| 1910 |
+
"loss_rank_avg": 0.1331542581319809,
|
| 1911 |
+
"step": 865,
|
| 1912 |
+
"valid_targets_mean": 1215.2,
|
| 1913 |
+
"valid_targets_min": 576
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 4.393939393939394,
|
| 1917 |
+
"grad_norm": 1.0553941956845185,
|
| 1918 |
+
"learning_rate": 8.16360527200833e-06,
|
| 1919 |
+
"loss": 0.1461,
|
| 1920 |
+
"loss_nan_ranks": 0,
|
| 1921 |
+
"loss_rank_avg": 0.13314183056354523,
|
| 1922 |
+
"step": 870,
|
| 1923 |
+
"valid_targets_mean": 1251.7,
|
| 1924 |
+
"valid_targets_min": 696
|
| 1925 |
+
},
|
| 1926 |
+
{
|
| 1927 |
+
"epoch": 4.41919191919192,
|
| 1928 |
+
"grad_norm": 0.9400873253173821,
|
| 1929 |
+
"learning_rate": 7.928002487706077e-06,
|
| 1930 |
+
"loss": 0.1456,
|
| 1931 |
+
"loss_nan_ranks": 0,
|
| 1932 |
+
"loss_rank_avg": 0.14997591078281403,
|
| 1933 |
+
"step": 875,
|
| 1934 |
+
"valid_targets_mean": 1381.4,
|
| 1935 |
+
"valid_targets_min": 954
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 4.444444444444445,
|
| 1939 |
+
"grad_norm": 0.9551571559692043,
|
| 1940 |
+
"learning_rate": 7.69500619102469e-06,
|
| 1941 |
+
"loss": 0.1423,
|
| 1942 |
+
"loss_nan_ranks": 0,
|
| 1943 |
+
"loss_rank_avg": 0.1366039514541626,
|
| 1944 |
+
"step": 880,
|
| 1945 |
+
"valid_targets_mean": 1127.9,
|
| 1946 |
+
"valid_targets_min": 702
|
| 1947 |
+
},
|
| 1948 |
+
{
|
| 1949 |
+
"epoch": 4.46969696969697,
|
| 1950 |
+
"grad_norm": 3.643078356257917,
|
| 1951 |
+
"learning_rate": 7.464666688631497e-06,
|
| 1952 |
+
"loss": 0.1453,
|
| 1953 |
+
"loss_nan_ranks": 0,
|
| 1954 |
+
"loss_rank_avg": 0.1459706425666809,
|
| 1955 |
+
"step": 885,
|
| 1956 |
+
"valid_targets_mean": 1290.3,
|
| 1957 |
+
"valid_targets_min": 671
|
| 1958 |
+
},
|
| 1959 |
+
{
|
| 1960 |
+
"epoch": 4.494949494949495,
|
| 1961 |
+
"grad_norm": 1.0361986594800512,
|
| 1962 |
+
"learning_rate": 7.237033713560415e-06,
|
| 1963 |
+
"loss": 0.1366,
|
| 1964 |
+
"loss_nan_ranks": 0,
|
| 1965 |
+
"loss_rank_avg": 0.13341154158115387,
|
| 1966 |
+
"step": 890,
|
| 1967 |
+
"valid_targets_mean": 1187.2,
|
| 1968 |
+
"valid_targets_min": 825
|
| 1969 |
+
},
|
| 1970 |
+
{
|
| 1971 |
+
"epoch": 4.52020202020202,
|
| 1972 |
+
"grad_norm": 0.9978450478422115,
|
| 1973 |
+
"learning_rate": 7.01215641447395e-06,
|
| 1974 |
+
"loss": 0.1416,
|
| 1975 |
+
"loss_nan_ranks": 0,
|
| 1976 |
+
"loss_rank_avg": 0.1472000777721405,
|
| 1977 |
+
"step": 895,
|
| 1978 |
+
"valid_targets_mean": 1245.2,
|
| 1979 |
+
"valid_targets_min": 797
|
| 1980 |
+
},
|
| 1981 |
+
{
|
| 1982 |
+
"epoch": 4.545454545454545,
|
| 1983 |
+
"grad_norm": 1.0033638283511224,
|
| 1984 |
+
"learning_rate": 6.790083345051457e-06,
|
| 1985 |
+
"loss": 0.144,
|
| 1986 |
+
"loss_nan_ranks": 0,
|
| 1987 |
+
"loss_rank_avg": 0.16042381525039673,
|
| 1988 |
+
"step": 900,
|
| 1989 |
+
"valid_targets_mean": 1246.5,
|
| 1990 |
+
"valid_targets_min": 655
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 4.570707070707071,
|
| 1994 |
+
"grad_norm": 0.9370414548757213,
|
| 1995 |
+
"learning_rate": 6.570862453505793e-06,
|
| 1996 |
+
"loss": 0.142,
|
| 1997 |
+
"loss_nan_ranks": 0,
|
| 1998 |
+
"loss_rank_avg": 0.1394890397787094,
|
| 1999 |
+
"step": 905,
|
| 2000 |
+
"valid_targets_mean": 1438.2,
|
| 2001 |
+
"valid_targets_min": 677
|
| 2002 |
+
},
|
| 2003 |
+
{
|
| 2004 |
+
"epoch": 4.595959595959596,
|
| 2005 |
+
"grad_norm": 0.8845963118772141,
|
| 2006 |
+
"learning_rate": 6.35454107223074e-06,
|
| 2007 |
+
"loss": 0.1398,
|
| 2008 |
+
"loss_nan_ranks": 0,
|
| 2009 |
+
"loss_rank_avg": 0.1384766846895218,
|
| 2010 |
+
"step": 910,
|
| 2011 |
+
"valid_targets_mean": 1392.9,
|
| 2012 |
+
"valid_targets_min": 592
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 4.621212121212121,
|
| 2016 |
+
"grad_norm": 0.9355477324402229,
|
| 2017 |
+
"learning_rate": 6.141165907581395e-06,
|
| 2018 |
+
"loss": 0.1419,
|
| 2019 |
+
"loss_nan_ranks": 0,
|
| 2020 |
+
"loss_rank_avg": 0.14917227625846863,
|
| 2021 |
+
"step": 915,
|
| 2022 |
+
"valid_targets_mean": 1327.9,
|
| 2023 |
+
"valid_targets_min": 753
|
| 2024 |
+
},
|
| 2025 |
+
{
|
| 2026 |
+
"epoch": 4.646464646464646,
|
| 2027 |
+
"grad_norm": 0.9640466514670939,
|
| 2028 |
+
"learning_rate": 5.9307830297896755e-06,
|
| 2029 |
+
"loss": 0.138,
|
| 2030 |
+
"loss_nan_ranks": 0,
|
| 2031 |
+
"loss_rank_avg": 0.13884782791137695,
|
| 2032 |
+
"step": 920,
|
| 2033 |
+
"valid_targets_mean": 1263.7,
|
| 2034 |
+
"valid_targets_min": 632
|
| 2035 |
+
},
|
| 2036 |
+
{
|
| 2037 |
+
"epoch": 4.671717171717171,
|
| 2038 |
+
"grad_norm": 0.9141945168421931,
|
| 2039 |
+
"learning_rate": 5.723437863017256e-06,
|
| 2040 |
+
"loss": 0.1378,
|
| 2041 |
+
"loss_nan_ranks": 0,
|
| 2042 |
+
"loss_rank_avg": 0.14294667541980743,
|
| 2043 |
+
"step": 925,
|
| 2044 |
+
"valid_targets_mean": 1302.5,
|
| 2045 |
+
"valid_targets_min": 777
|
| 2046 |
+
},
|
| 2047 |
+
{
|
| 2048 |
+
"epoch": 4.696969696969697,
|
| 2049 |
+
"grad_norm": 0.9123065154375142,
|
| 2050 |
+
"learning_rate": 5.519175175547919e-06,
|
| 2051 |
+
"loss": 0.138,
|
| 2052 |
+
"loss_nan_ranks": 0,
|
| 2053 |
+
"loss_rank_avg": 0.1268976479768753,
|
| 2054 |
+
"step": 930,
|
| 2055 |
+
"valid_targets_mean": 1319.0,
|
| 2056 |
+
"valid_targets_min": 661
|
| 2057 |
+
},
|
| 2058 |
+
{
|
| 2059 |
+
"epoch": 4.722222222222222,
|
| 2060 |
+
"grad_norm": 0.8964668435132555,
|
| 2061 |
+
"learning_rate": 5.318039070121557e-06,
|
| 2062 |
+
"loss": 0.1466,
|
| 2063 |
+
"loss_nan_ranks": 0,
|
| 2064 |
+
"loss_rank_avg": 0.14182919263839722,
|
| 2065 |
+
"step": 935,
|
| 2066 |
+
"valid_targets_mean": 1347.6,
|
| 2067 |
+
"valid_targets_min": 804
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 4.747474747474747,
|
| 2071 |
+
"grad_norm": 0.9249960271962788,
|
| 2072 |
+
"learning_rate": 5.120072974411863e-06,
|
| 2073 |
+
"loss": 0.1371,
|
| 2074 |
+
"loss_nan_ranks": 0,
|
| 2075 |
+
"loss_rank_avg": 0.13355281949043274,
|
| 2076 |
+
"step": 940,
|
| 2077 |
+
"valid_targets_mean": 1267.5,
|
| 2078 |
+
"valid_targets_min": 631
|
| 2079 |
+
},
|
| 2080 |
+
{
|
| 2081 |
+
"epoch": 4.7727272727272725,
|
| 2082 |
+
"grad_norm": 0.9555005569091014,
|
| 2083 |
+
"learning_rate": 4.92531963164981e-06,
|
| 2084 |
+
"loss": 0.1408,
|
| 2085 |
+
"loss_nan_ranks": 0,
|
| 2086 |
+
"loss_rank_avg": 0.13473376631736755,
|
| 2087 |
+
"step": 945,
|
| 2088 |
+
"valid_targets_mean": 1280.8,
|
| 2089 |
+
"valid_targets_min": 741
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 4.797979797979798,
|
| 2093 |
+
"grad_norm": 0.9026207825389647,
|
| 2094 |
+
"learning_rate": 4.733821091394841e-06,
|
| 2095 |
+
"loss": 0.1377,
|
| 2096 |
+
"loss_nan_ranks": 0,
|
| 2097 |
+
"loss_rank_avg": 0.12557560205459595,
|
| 2098 |
+
"step": 950,
|
| 2099 |
+
"valid_targets_mean": 1251.2,
|
| 2100 |
+
"valid_targets_min": 639
|
| 2101 |
+
},
|
| 2102 |
+
{
|
| 2103 |
+
"epoch": 4.8232323232323235,
|
| 2104 |
+
"grad_norm": 0.8648311888440021,
|
| 2105 |
+
"learning_rate": 4.5456187004558806e-06,
|
| 2106 |
+
"loss": 0.1341,
|
| 2107 |
+
"loss_nan_ranks": 0,
|
| 2108 |
+
"loss_rank_avg": 0.13172218203544617,
|
| 2109 |
+
"step": 955,
|
| 2110 |
+
"valid_targets_mean": 1288.4,
|
| 2111 |
+
"valid_targets_min": 615
|
| 2112 |
+
},
|
| 2113 |
+
{
|
| 2114 |
+
"epoch": 4.848484848484849,
|
| 2115 |
+
"grad_norm": 0.935270097185908,
|
| 2116 |
+
"learning_rate": 4.360753093964094e-06,
|
| 2117 |
+
"loss": 0.1415,
|
| 2118 |
+
"loss_nan_ranks": 0,
|
| 2119 |
+
"loss_rank_avg": 0.15985289216041565,
|
| 2120 |
+
"step": 960,
|
| 2121 |
+
"valid_targets_mean": 1484.0,
|
| 2122 |
+
"valid_targets_min": 806
|
| 2123 |
+
},
|
| 2124 |
+
{
|
| 2125 |
+
"epoch": 4.873737373737374,
|
| 2126 |
+
"grad_norm": 0.9346939564460294,
|
| 2127 |
+
"learning_rate": 4.179264186599239e-06,
|
| 2128 |
+
"loss": 0.1474,
|
| 2129 |
+
"loss_nan_ranks": 0,
|
| 2130 |
+
"loss_rank_avg": 0.14724518358707428,
|
| 2131 |
+
"step": 965,
|
| 2132 |
+
"valid_targets_mean": 1514.4,
|
| 2133 |
+
"valid_targets_min": 457
|
| 2134 |
+
},
|
| 2135 |
+
{
|
| 2136 |
+
"epoch": 4.898989898989899,
|
| 2137 |
+
"grad_norm": 0.9281283556463727,
|
| 2138 |
+
"learning_rate": 4.001191163971645e-06,
|
| 2139 |
+
"loss": 0.1362,
|
| 2140 |
+
"loss_nan_ranks": 0,
|
| 2141 |
+
"loss_rank_avg": 0.1386679857969284,
|
| 2142 |
+
"step": 970,
|
| 2143 |
+
"valid_targets_mean": 1296.4,
|
| 2144 |
+
"valid_targets_min": 817
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 4.924242424242424,
|
| 2148 |
+
"grad_norm": 0.9213870761453768,
|
| 2149 |
+
"learning_rate": 3.826572474161565e-06,
|
| 2150 |
+
"loss": 0.1436,
|
| 2151 |
+
"loss_nan_ranks": 0,
|
| 2152 |
+
"loss_rank_avg": 0.13845255970954895,
|
| 2153 |
+
"step": 975,
|
| 2154 |
+
"valid_targets_mean": 1287.9,
|
| 2155 |
+
"valid_targets_min": 702
|
| 2156 |
+
},
|
| 2157 |
+
{
|
| 2158 |
+
"epoch": 4.94949494949495,
|
| 2159 |
+
"grad_norm": 1.0036592428841529,
|
| 2160 |
+
"learning_rate": 3.65544581941776e-06,
|
| 2161 |
+
"loss": 0.1378,
|
| 2162 |
+
"loss_nan_ranks": 0,
|
| 2163 |
+
"loss_rank_avg": 0.12950043380260468,
|
| 2164 |
+
"step": 980,
|
| 2165 |
+
"valid_targets_mean": 1237.9,
|
| 2166 |
+
"valid_targets_min": 618
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"epoch": 4.974747474747475,
|
| 2170 |
+
"grad_norm": 0.9657789228628604,
|
| 2171 |
+
"learning_rate": 3.487848148017161e-06,
|
| 2172 |
+
"loss": 0.1428,
|
| 2173 |
+
"loss_nan_ranks": 0,
|
| 2174 |
+
"loss_rank_avg": 0.13668538630008698,
|
| 2175 |
+
"step": 985,
|
| 2176 |
+
"valid_targets_mean": 1134.9,
|
| 2177 |
+
"valid_targets_min": 692
|
| 2178 |
+
},
|
| 2179 |
+
{
|
| 2180 |
+
"epoch": 5.0,
|
| 2181 |
+
"grad_norm": 0.8611796892921691,
|
| 2182 |
+
"learning_rate": 3.3238156462872937e-06,
|
| 2183 |
+
"loss": 0.1371,
|
| 2184 |
+
"loss_nan_ranks": 0,
|
| 2185 |
+
"loss_rank_avg": 0.12768948078155518,
|
| 2186 |
+
"step": 990,
|
| 2187 |
+
"valid_targets_mean": 1368.5,
|
| 2188 |
+
"valid_targets_min": 651
|
| 2189 |
+
},
|
| 2190 |
+
{
|
| 2191 |
+
"epoch": 5.025252525252525,
|
| 2192 |
+
"grad_norm": 0.9261974676714096,
|
| 2193 |
+
"learning_rate": 3.1633837307932037e-06,
|
| 2194 |
+
"loss": 0.1309,
|
| 2195 |
+
"loss_nan_ranks": 0,
|
| 2196 |
+
"loss_rank_avg": 0.13367873430252075,
|
| 2197 |
+
"step": 995,
|
| 2198 |
+
"valid_targets_mean": 1154.2,
|
| 2199 |
+
"valid_targets_min": 618
|
| 2200 |
+
},
|
| 2201 |
+
{
|
| 2202 |
+
"epoch": 5.05050505050505,
|
| 2203 |
+
"grad_norm": 1.0036400719596783,
|
| 2204 |
+
"learning_rate": 3.0065870406906094e-06,
|
| 2205 |
+
"loss": 0.1292,
|
| 2206 |
+
"loss_nan_ranks": 0,
|
| 2207 |
+
"loss_rank_avg": 0.13053901493549347,
|
| 2208 |
+
"step": 1000,
|
| 2209 |
+
"valid_targets_mean": 1190.0,
|
| 2210 |
+
"valid_targets_min": 633
|
| 2211 |
+
},
|
| 2212 |
+
{
|
| 2213 |
+
"epoch": 5.075757575757576,
|
| 2214 |
+
"grad_norm": 0.9363551041241059,
|
| 2215 |
+
"learning_rate": 2.8534594302469142e-06,
|
| 2216 |
+
"loss": 0.1253,
|
| 2217 |
+
"loss_nan_ranks": 0,
|
| 2218 |
+
"loss_rank_avg": 0.12562397122383118,
|
| 2219 |
+
"step": 1005,
|
| 2220 |
+
"valid_targets_mean": 1375.2,
|
| 2221 |
+
"valid_targets_min": 772
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 5.101010101010101,
|
| 2225 |
+
"grad_norm": 1.2700394350667998,
|
| 2226 |
+
"learning_rate": 2.7040339615316315e-06,
|
| 2227 |
+
"loss": 0.1276,
|
| 2228 |
+
"loss_nan_ranks": 0,
|
| 2229 |
+
"loss_rank_avg": 0.1437637358903885,
|
| 2230 |
+
"step": 1010,
|
| 2231 |
+
"valid_targets_mean": 1253.7,
|
| 2232 |
+
"valid_targets_min": 837
|
| 2233 |
+
},
|
| 2234 |
+
{
|
| 2235 |
+
"epoch": 5.126262626262626,
|
| 2236 |
+
"grad_norm": 0.9276952092042188,
|
| 2237 |
+
"learning_rate": 2.5583428972779236e-06,
|
| 2238 |
+
"loss": 0.1323,
|
| 2239 |
+
"loss_nan_ranks": 0,
|
| 2240 |
+
"loss_rank_avg": 0.13029523193836212,
|
| 2241 |
+
"step": 1015,
|
| 2242 |
+
"valid_targets_mean": 1374.9,
|
| 2243 |
+
"valid_targets_min": 771
|
| 2244 |
+
},
|
| 2245 |
+
{
|
| 2246 |
+
"epoch": 5.151515151515151,
|
| 2247 |
+
"grad_norm": 0.962578989323224,
|
| 2248 |
+
"learning_rate": 2.4164176939166883e-06,
|
| 2249 |
+
"loss": 0.1323,
|
| 2250 |
+
"loss_nan_ranks": 0,
|
| 2251 |
+
"loss_rank_avg": 0.12893831729888916,
|
| 2252 |
+
"step": 1020,
|
| 2253 |
+
"valid_targets_mean": 1278.4,
|
| 2254 |
+
"valid_targets_min": 623
|
| 2255 |
+
},
|
| 2256 |
+
{
|
| 2257 |
+
"epoch": 5.1767676767676765,
|
| 2258 |
+
"grad_norm": 0.8740471250815197,
|
| 2259 |
+
"learning_rate": 2.278288994784723e-06,
|
| 2260 |
+
"loss": 0.1353,
|
| 2261 |
+
"loss_nan_ranks": 0,
|
| 2262 |
+
"loss_rank_avg": 0.13151079416275024,
|
| 2263 |
+
"step": 1025,
|
| 2264 |
+
"valid_targets_mean": 1495.8,
|
| 2265 |
+
"valid_targets_min": 695
|
| 2266 |
+
},
|
| 2267 |
+
{
|
| 2268 |
+
"epoch": 5.202020202020202,
|
| 2269 |
+
"grad_norm": 0.8967346790633705,
|
| 2270 |
+
"learning_rate": 2.143986623508478e-06,
|
| 2271 |
+
"loss": 0.1335,
|
| 2272 |
+
"loss_nan_ranks": 0,
|
| 2273 |
+
"loss_rank_avg": 0.15209463238716125,
|
| 2274 |
+
"step": 1030,
|
| 2275 |
+
"valid_targets_mean": 1422.6,
|
| 2276 |
+
"valid_targets_min": 587
|
| 2277 |
+
},
|
| 2278 |
+
{
|
| 2279 |
+
"epoch": 5.2272727272727275,
|
| 2280 |
+
"grad_norm": 0.994338705656964,
|
| 2281 |
+
"learning_rate": 2.0135395775647916e-06,
|
| 2282 |
+
"loss": 0.1302,
|
| 2283 |
+
"loss_nan_ranks": 0,
|
| 2284 |
+
"loss_rank_avg": 0.1367867887020111,
|
| 2285 |
+
"step": 1035,
|
| 2286 |
+
"valid_targets_mean": 1365.3,
|
| 2287 |
+
"valid_targets_min": 648
|
| 2288 |
+
},
|
| 2289 |
+
{
|
| 2290 |
+
"epoch": 5.252525252525253,
|
| 2291 |
+
"grad_norm": 0.9608409928013174,
|
| 2292 |
+
"learning_rate": 1.8869760220199707e-06,
|
| 2293 |
+
"loss": 0.1292,
|
| 2294 |
+
"loss_nan_ranks": 0,
|
| 2295 |
+
"loss_rank_avg": 0.12372744828462601,
|
| 2296 |
+
"step": 1040,
|
| 2297 |
+
"valid_targets_mean": 1244.5,
|
| 2298 |
+
"valid_targets_min": 788
|
| 2299 |
+
},
|
| 2300 |
+
{
|
| 2301 |
+
"epoch": 5.277777777777778,
|
| 2302 |
+
"grad_norm": 0.8629245570874375,
|
| 2303 |
+
"learning_rate": 1.7643232834486347e-06,
|
| 2304 |
+
"loss": 0.1331,
|
| 2305 |
+
"loss_nan_ranks": 0,
|
| 2306 |
+
"loss_rank_avg": 0.12655162811279297,
|
| 2307 |
+
"step": 1045,
|
| 2308 |
+
"valid_targets_mean": 1365.6,
|
| 2309 |
+
"valid_targets_min": 813
|
| 2310 |
+
},
|
| 2311 |
+
{
|
| 2312 |
+
"epoch": 5.303030303030303,
|
| 2313 |
+
"grad_norm": 0.8668280603831705,
|
| 2314 |
+
"learning_rate": 1.6456078440335699e-06,
|
| 2315 |
+
"loss": 0.1284,
|
| 2316 |
+
"loss_nan_ranks": 0,
|
| 2317 |
+
"loss_rank_avg": 0.11772658675909042,
|
| 2318 |
+
"step": 1050,
|
| 2319 |
+
"valid_targets_mean": 1353.5,
|
| 2320 |
+
"valid_targets_min": 891
|
| 2321 |
+
},
|
| 2322 |
+
{
|
| 2323 |
+
"epoch": 5.328282828282829,
|
| 2324 |
+
"grad_norm": 0.9006577141118385,
|
| 2325 |
+
"learning_rate": 1.530855335847916e-06,
|
| 2326 |
+
"loss": 0.1252,
|
| 2327 |
+
"loss_nan_ranks": 0,
|
| 2328 |
+
"loss_rank_avg": 0.12341552972793579,
|
| 2329 |
+
"step": 1055,
|
| 2330 |
+
"valid_targets_mean": 1405.5,
|
| 2331 |
+
"valid_targets_min": 582
|
| 2332 |
+
},
|
| 2333 |
+
{
|
| 2334 |
+
"epoch": 5.353535353535354,
|
| 2335 |
+
"grad_norm": 0.891591633370806,
|
| 2336 |
+
"learning_rate": 1.4200905353209127e-06,
|
| 2337 |
+
"loss": 0.1281,
|
| 2338 |
+
"loss_nan_ranks": 0,
|
| 2339 |
+
"loss_rank_avg": 0.11440576612949371,
|
| 2340 |
+
"step": 1060,
|
| 2341 |
+
"valid_targets_mean": 1307.4,
|
| 2342 |
+
"valid_targets_min": 948
|
| 2343 |
+
},
|
| 2344 |
+
{
|
| 2345 |
+
"epoch": 5.378787878787879,
|
| 2346 |
+
"grad_norm": 0.9342456964635858,
|
| 2347 |
+
"learning_rate": 1.3133373578883557e-06,
|
| 2348 |
+
"loss": 0.1294,
|
| 2349 |
+
"loss_nan_ranks": 0,
|
| 2350 |
+
"loss_rank_avg": 0.130423903465271,
|
| 2351 |
+
"step": 1065,
|
| 2352 |
+
"valid_targets_mean": 1313.1,
|
| 2353 |
+
"valid_targets_min": 618
|
| 2354 |
+
},
|
| 2355 |
+
{
|
| 2356 |
+
"epoch": 5.404040404040404,
|
| 2357 |
+
"grad_norm": 1.0164525546198238,
|
| 2358 |
+
"learning_rate": 1.210618852828962e-06,
|
| 2359 |
+
"loss": 0.1299,
|
| 2360 |
+
"loss_nan_ranks": 0,
|
| 2361 |
+
"loss_rank_avg": 0.11982132494449615,
|
| 2362 |
+
"step": 1070,
|
| 2363 |
+
"valid_targets_mean": 1178.9,
|
| 2364 |
+
"valid_targets_min": 576
|
| 2365 |
+
},
|
| 2366 |
+
{
|
| 2367 |
+
"epoch": 5.429292929292929,
|
| 2368 |
+
"grad_norm": 0.9239002515903104,
|
| 2369 |
+
"learning_rate": 1.111957198287792e-06,
|
| 2370 |
+
"loss": 0.1277,
|
| 2371 |
+
"loss_nan_ranks": 0,
|
| 2372 |
+
"loss_rank_avg": 0.12996883690357208,
|
| 2373 |
+
"step": 1075,
|
| 2374 |
+
"valid_targets_mean": 1293.5,
|
| 2375 |
+
"valid_targets_min": 640
|
| 2376 |
+
},
|
| 2377 |
+
{
|
| 2378 |
+
"epoch": 5.454545454545454,
|
| 2379 |
+
"grad_norm": 0.9511383148715302,
|
| 2380 |
+
"learning_rate": 1.0173736964876867e-06,
|
| 2381 |
+
"loss": 0.1263,
|
| 2382 |
+
"loss_nan_ranks": 0,
|
| 2383 |
+
"loss_rank_avg": 0.12540099024772644,
|
| 2384 |
+
"step": 1080,
|
| 2385 |
+
"valid_targets_mean": 1283.8,
|
| 2386 |
+
"valid_targets_min": 474
|
| 2387 |
+
},
|
| 2388 |
+
{
|
| 2389 |
+
"epoch": 5.47979797979798,
|
| 2390 |
+
"grad_norm": 1.0846233711368571,
|
| 2391 |
+
"learning_rate": 9.268887691298878e-07,
|
| 2392 |
+
"loss": 0.1284,
|
| 2393 |
+
"loss_nan_ranks": 0,
|
| 2394 |
+
"loss_rank_avg": 0.12933316826820374,
|
| 2395 |
+
"step": 1085,
|
| 2396 |
+
"valid_targets_mean": 1257.1,
|
| 2397 |
+
"valid_targets_min": 605
|
| 2398 |
+
},
|
| 2399 |
+
{
|
| 2400 |
+
"epoch": 5.505050505050505,
|
| 2401 |
+
"grad_norm": 0.9384952309399883,
|
| 2402 |
+
"learning_rate": 8.405219529847453e-07,
|
| 2403 |
+
"loss": 0.1277,
|
| 2404 |
+
"loss_nan_ranks": 0,
|
| 2405 |
+
"loss_rank_avg": 0.1350557953119278,
|
| 2406 |
+
"step": 1090,
|
| 2407 |
+
"valid_targets_mean": 1315.2,
|
| 2408 |
+
"valid_targets_min": 629
|
| 2409 |
+
},
|
| 2410 |
+
{
|
| 2411 |
+
"epoch": 5.53030303030303,
|
| 2412 |
+
"grad_norm": 0.9014524057924357,
|
| 2413 |
+
"learning_rate": 7.582918956734909e-07,
|
| 2414 |
+
"loss": 0.1345,
|
| 2415 |
+
"loss_nan_ranks": 0,
|
| 2416 |
+
"loss_rank_avg": 0.12424828857183456,
|
| 2417 |
+
"step": 1095,
|
| 2418 |
+
"valid_targets_mean": 1340.4,
|
| 2419 |
+
"valid_targets_min": 781
|
| 2420 |
+
},
|
| 2421 |
+
{
|
| 2422 |
+
"epoch": 5.555555555555555,
|
| 2423 |
+
"grad_norm": 0.9292653851483377,
|
| 2424 |
+
"learning_rate": 6.802163516419979e-07,
|
| 2425 |
+
"loss": 0.1265,
|
| 2426 |
+
"loss_nan_ranks": 0,
|
| 2427 |
+
"loss_rank_avg": 0.12965571880340576,
|
| 2428 |
+
"step": 1100,
|
| 2429 |
+
"valid_targets_mean": 1274.8,
|
| 2430 |
+
"valid_targets_min": 486
|
| 2431 |
+
},
|
| 2432 |
+
{
|
| 2433 |
+
"epoch": 5.58080808080808,
|
| 2434 |
+
"grad_norm": 0.943887372743222,
|
| 2435 |
+
"learning_rate": 6.063121783273907e-07,
|
| 2436 |
+
"loss": 0.1307,
|
| 2437 |
+
"loss_nan_ranks": 0,
|
| 2438 |
+
"loss_rank_avg": 0.1259051263332367,
|
| 2439 |
+
"step": 1105,
|
| 2440 |
+
"valid_targets_mean": 1327.0,
|
| 2441 |
+
"valid_targets_min": 836
|
| 2442 |
+
},
|
| 2443 |
+
{
|
| 2444 |
+
"epoch": 5.606060606060606,
|
| 2445 |
+
"grad_norm": 0.9737257175600421,
|
| 2446 |
+
"learning_rate": 5.365953325183216e-07,
|
| 2447 |
+
"loss": 0.1277,
|
| 2448 |
+
"loss_nan_ranks": 0,
|
| 2449 |
+
"loss_rank_avg": 0.12629470229148865,
|
| 2450 |
+
"step": 1110,
|
| 2451 |
+
"valid_targets_mean": 1253.1,
|
| 2452 |
+
"valid_targets_min": 762
|
| 2453 |
+
},
|
| 2454 |
+
{
|
| 2455 |
+
"epoch": 5.6313131313131315,
|
| 2456 |
+
"grad_norm": 1.0509566598389861,
|
| 2457 |
+
"learning_rate": 4.7108086690970113e-07,
|
| 2458 |
+
"loss": 0.1323,
|
| 2459 |
+
"loss_nan_ranks": 0,
|
| 2460 |
+
"loss_rank_avg": 0.13950996100902557,
|
| 2461 |
+
"step": 1115,
|
| 2462 |
+
"valid_targets_mean": 1205.4,
|
| 2463 |
+
"valid_targets_min": 655
|
| 2464 |
+
},
|
| 2465 |
+
{
|
| 2466 |
+
"epoch": 5.656565656565657,
|
| 2467 |
+
"grad_norm": 0.8734622130361067,
|
| 2468 |
+
"learning_rate": 4.0978292685265765e-07,
|
| 2469 |
+
"loss": 0.1235,
|
| 2470 |
+
"loss_nan_ranks": 0,
|
| 2471 |
+
"loss_rank_avg": 0.11927177011966705,
|
| 2472 |
+
"step": 1120,
|
| 2473 |
+
"valid_targets_mean": 1288.9,
|
| 2474 |
+
"valid_targets_min": 656
|
| 2475 |
+
},
|
| 2476 |
+
{
|
| 2477 |
+
"epoch": 5.681818181818182,
|
| 2478 |
+
"grad_norm": 1.041895306850947,
|
| 2479 |
+
"learning_rate": 3.5271474730037557e-07,
|
| 2480 |
+
"loss": 0.1302,
|
| 2481 |
+
"loss_nan_ranks": 0,
|
| 2482 |
+
"loss_rank_avg": 0.12915349006652832,
|
| 2483 |
+
"step": 1125,
|
| 2484 |
+
"valid_targets_mean": 1260.8,
|
| 2485 |
+
"valid_targets_min": 804
|
| 2486 |
+
},
|
| 2487 |
+
{
|
| 2488 |
+
"epoch": 5.707070707070707,
|
| 2489 |
+
"grad_norm": 0.9809767376936727,
|
| 2490 |
+
"learning_rate": 2.998886499505171e-07,
|
| 2491 |
+
"loss": 0.127,
|
| 2492 |
+
"loss_nan_ranks": 0,
|
| 2493 |
+
"loss_rank_avg": 0.1269259750843048,
|
| 2494 |
+
"step": 1130,
|
| 2495 |
+
"valid_targets_mean": 1323.3,
|
| 2496 |
+
"valid_targets_min": 741
|
| 2497 |
+
},
|
| 2498 |
+
{
|
| 2499 |
+
"epoch": 5.732323232323233,
|
| 2500 |
+
"grad_norm": 1.2138384974786145,
|
| 2501 |
+
"learning_rate": 2.513160405848303e-07,
|
| 2502 |
+
"loss": 0.1345,
|
| 2503 |
+
"loss_nan_ranks": 0,
|
| 2504 |
+
"loss_rank_avg": 0.14036789536476135,
|
| 2505 |
+
"step": 1135,
|
| 2506 |
+
"valid_targets_mean": 1340.8,
|
| 2507 |
+
"valid_targets_min": 615
|
| 2508 |
+
},
|
| 2509 |
+
{
|
| 2510 |
+
"epoch": 5.757575757575758,
|
| 2511 |
+
"grad_norm": 0.8909820802700256,
|
| 2512 |
+
"learning_rate": 2.0700740660648312e-07,
|
| 2513 |
+
"loss": 0.1328,
|
| 2514 |
+
"loss_nan_ranks": 0,
|
| 2515 |
+
"loss_rank_avg": 0.11737575381994247,
|
| 2516 |
+
"step": 1140,
|
| 2517 |
+
"valid_targets_mean": 1354.6,
|
| 2518 |
+
"valid_targets_min": 864
|
| 2519 |
+
},
|
| 2520 |
+
{
|
| 2521 |
+
"epoch": 5.782828282828283,
|
| 2522 |
+
"grad_norm": 1.0571471194993831,
|
| 2523 |
+
"learning_rate": 1.669723147757263e-07,
|
| 2524 |
+
"loss": 0.1284,
|
| 2525 |
+
"loss_nan_ranks": 0,
|
| 2526 |
+
"loss_rank_avg": 0.12995797395706177,
|
| 2527 |
+
"step": 1145,
|
| 2528 |
+
"valid_targets_mean": 1081.0,
|
| 2529 |
+
"valid_targets_min": 582
|
| 2530 |
+
},
|
| 2531 |
+
{
|
| 2532 |
+
"epoch": 5.808080808080808,
|
| 2533 |
+
"grad_norm": 1.4245132821438702,
|
| 2534 |
+
"learning_rate": 1.312194091443142e-07,
|
| 2535 |
+
"loss": 0.1331,
|
| 2536 |
+
"loss_nan_ranks": 0,
|
| 2537 |
+
"loss_rank_avg": 0.13467878103256226,
|
| 2538 |
+
"step": 1150,
|
| 2539 |
+
"valid_targets_mean": 1349.2,
|
| 2540 |
+
"valid_targets_min": 656
|
| 2541 |
+
},
|
| 2542 |
+
{
|
| 2543 |
+
"epoch": 5.833333333333333,
|
| 2544 |
+
"grad_norm": 0.9507679786850238,
|
| 2545 |
+
"learning_rate": 9.975640918915119e-08,
|
| 2546 |
+
"loss": 0.1306,
|
| 2547 |
+
"loss_nan_ranks": 0,
|
| 2548 |
+
"loss_rank_avg": 0.12804457545280457,
|
| 2549 |
+
"step": 1155,
|
| 2550 |
+
"valid_targets_mean": 1274.2,
|
| 2551 |
+
"valid_targets_min": 574
|
| 2552 |
+
},
|
| 2553 |
+
{
|
| 2554 |
+
"epoch": 5.858585858585858,
|
| 2555 |
+
"grad_norm": 0.9639470109858415,
|
| 2556 |
+
"learning_rate": 7.259010814555378e-08,
|
| 2557 |
+
"loss": 0.1304,
|
| 2558 |
+
"loss_nan_ranks": 0,
|
| 2559 |
+
"loss_rank_avg": 0.12429563701152802,
|
| 2560 |
+
"step": 1160,
|
| 2561 |
+
"valid_targets_mean": 1331.4,
|
| 2562 |
+
"valid_targets_min": 740
|
| 2563 |
+
},
|
| 2564 |
+
{
|
| 2565 |
+
"epoch": 5.883838383838384,
|
| 2566 |
+
"grad_norm": 0.9048090193387625,
|
| 2567 |
+
"learning_rate": 4.972637154052606e-08,
|
| 2568 |
+
"loss": 0.1292,
|
| 2569 |
+
"loss_nan_ranks": 0,
|
| 2570 |
+
"loss_rank_avg": 0.1266717165708542,
|
| 2571 |
+
"step": 1165,
|
| 2572 |
+
"valid_targets_mean": 1540.2,
|
| 2573 |
+
"valid_targets_min": 1033
|
| 2574 |
+
},
|
| 2575 |
+
{
|
| 2576 |
+
"epoch": 5.909090909090909,
|
| 2577 |
+
"grad_norm": 0.9137387217315224,
|
| 2578 |
+
"learning_rate": 3.117013592631501e-08,
|
| 2579 |
+
"loss": 0.1341,
|
| 2580 |
+
"loss_nan_ranks": 0,
|
| 2581 |
+
"loss_rank_avg": 0.13005393743515015,
|
| 2582 |
+
"step": 1170,
|
| 2583 |
+
"valid_targets_mean": 1407.2,
|
| 2584 |
+
"valid_targets_min": 683
|
| 2585 |
+
},
|
| 2586 |
+
{
|
| 2587 |
+
"epoch": 5.934343434343434,
|
| 2588 |
+
"grad_norm": 0.9221913785952132,
|
| 2589 |
+
"learning_rate": 1.6925407814545325e-08,
|
| 2590 |
+
"loss": 0.1267,
|
| 2591 |
+
"loss_nan_ranks": 0,
|
| 2592 |
+
"loss_rank_avg": 0.1224047988653183,
|
| 2593 |
+
"step": 1175,
|
| 2594 |
+
"valid_targets_mean": 1231.8,
|
| 2595 |
+
"valid_targets_min": 782
|
| 2596 |
+
},
|
| 2597 |
+
{
|
| 2598 |
+
"epoch": 5.959595959595959,
|
| 2599 |
+
"grad_norm": 0.89954321451429,
|
| 2600 |
+
"learning_rate": 6.995262811178016e-09,
|
| 2601 |
+
"loss": 0.1297,
|
| 2602 |
+
"loss_nan_ranks": 0,
|
| 2603 |
+
"loss_rank_avg": 0.12393134087324142,
|
| 2604 |
+
"step": 1180,
|
| 2605 |
+
"valid_targets_mean": 1373.0,
|
| 2606 |
+
"valid_targets_min": 746
|
| 2607 |
+
},
|
| 2608 |
+
{
|
| 2609 |
+
"epoch": 5.984848484848484,
|
| 2610 |
+
"grad_norm": 0.9614911698663842,
|
| 2611 |
+
"learning_rate": 1.3818449524416467e-09,
|
| 2612 |
+
"loss": 0.1304,
|
| 2613 |
+
"loss_nan_ranks": 0,
|
| 2614 |
+
"loss_rank_avg": 0.12797527015209198,
|
| 2615 |
+
"step": 1185,
|
| 2616 |
+
"valid_targets_mean": 1194.4,
|
| 2617 |
+
"valid_targets_min": 743
|
| 2618 |
+
},
|
| 2619 |
+
{
|
| 2620 |
+
"epoch": 6.0,
|
| 2621 |
+
"loss_nan_ranks": 0,
|
| 2622 |
+
"loss_rank_avg": 0.133074551820755,
|
| 2623 |
+
"step": 1188,
|
| 2624 |
+
"total_flos": 123574112944128.0,
|
| 2625 |
+
"train_loss": 0.2030692549064906,
|
| 2626 |
+
"train_runtime": 3957.8692,
|
| 2627 |
+
"train_samples_per_second": 4.79,
|
| 2628 |
+
"train_steps_per_second": 0.3,
|
| 2629 |
+
"valid_targets_mean": 1319.8,
|
| 2630 |
+
"valid_targets_min": 875
|
| 2631 |
+
}
|
| 2632 |
+
],
|
| 2633 |
+
"logging_steps": 5,
|
| 2634 |
+
"max_steps": 1188,
|
| 2635 |
+
"num_input_tokens_seen": 0,
|
| 2636 |
+
"num_train_epochs": 6,
|
| 2637 |
+
"save_steps": 100,
|
| 2638 |
+
"stateful_callbacks": {
|
| 2639 |
+
"TrainerControl": {
|
| 2640 |
+
"args": {
|
| 2641 |
+
"should_epoch_stop": false,
|
| 2642 |
+
"should_evaluate": false,
|
| 2643 |
+
"should_log": false,
|
| 2644 |
+
"should_save": true,
|
| 2645 |
+
"should_training_stop": true
|
| 2646 |
+
},
|
| 2647 |
+
"attributes": {}
|
| 2648 |
+
}
|
| 2649 |
+
},
|
| 2650 |
+
"total_flos": 123574112944128.0,
|
| 2651 |
+
"train_batch_size": 1,
|
| 2652 |
+
"trial_name": null,
|
| 2653 |
+
"trial_params": null
|
| 2654 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:67bd93f609301173c1d380511c7edcd9a67297c6f5e72816ca28043ba61fc617
|
| 3 |
+
size 8657
|
training_loss.png
ADDED
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|