penfever
commited on
Commit
·
e27ed9b
0
Parent(s):
Reset repository without checkpoint dirs
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 +288 -0
- trainer_state.json +3204 -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: GLM-4_6-stackexchange-superuser-32ep-32k
|
| 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 |
+
# GLM-4_6-stackexchange-superuser-32ep-32k
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on the penfever/GLM-4.6-stackexchange-superuser-32ep-32k 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=(0.9,0.98) 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: 7.0
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
|
| 54 |
+
|
| 55 |
+
### Framework versions
|
| 56 |
+
|
| 57 |
+
- Transformers 4.56.0
|
| 58 |
+
- Pytorch 2.9.0+cu128
|
| 59 |
+
- Datasets 4.4.1
|
| 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": 0.002928386808870264,
|
| 3 |
+
"achieved_tflops_per_gpu_theoretical": 494.6340661721825,
|
| 4 |
+
"epoch": 7.0,
|
| 5 |
+
"loss_nan_ranks": 0,
|
| 6 |
+
"loss_rank_avg": 0.24434766173362732,
|
| 7 |
+
"mfu_percent": 0.00020695313136892326,
|
| 8 |
+
"mfu_percent_theoretical": 34.956471107574735,
|
| 9 |
+
"total_flos": 459870247321600.0,
|
| 10 |
+
"train_loss": 0.3203928537069713,
|
| 11 |
+
"train_runtime": 9814.9228,
|
| 12 |
+
"train_samples_per_second": 2.332,
|
| 13 |
+
"train_steps_per_second": 0.146,
|
| 14 |
+
"valid_targets_mean": 2891.9,
|
| 15 |
+
"valid_targets_min": 658
|
| 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:b3119a7a7bd62d0ebd4c2db4e1eccf56b9c2801b3b10e2c0cf98d62a01b9b403
|
| 3 |
+
size 4902257696
|
model-00002-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:77466c92df220e31419b978068bc1a54db9d99908ac4542d9da9b6d9777f7a01
|
| 3 |
+
size 4915960368
|
model-00003-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:33dc2b169d7672e16a58c82c5f48a214dd0a8eeb79853e488cd2a6925394247a
|
| 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:df684dd16922838e02ccd761eae30e648c99e293fbeed12fbe728b2bc77f0865
|
| 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": "penfever/GLM-4.6-stackexchange-superuser-32ep-32k",
|
| 8 |
+
"training_type": "SFT",
|
| 9 |
+
"training_parameters": "https://huggingface.co/laion/GLM-4_6-stackexchange-superuser-32ep-32k/blob/main/config.json",
|
| 10 |
+
"wandb_link": "https://wandb.ai/dogml/dc-agent/runs/GLM-4.6-stackexchange-superuser-32ep-32k_hub-model-id_GLM-4.6-stackexchange-superuser-32ep-32k_Q",
|
| 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": 0.002928386808870264,
|
| 3 |
+
"achieved_tflops_per_gpu_theoretical": 494.6340661721825,
|
| 4 |
+
"epoch": 7.0,
|
| 5 |
+
"loss_nan_ranks": 0,
|
| 6 |
+
"loss_rank_avg": 0.24434766173362732,
|
| 7 |
+
"mfu_percent": 0.00020695313136892326,
|
| 8 |
+
"mfu_percent_theoretical": 34.956471107574735,
|
| 9 |
+
"total_flos": 459870247321600.0,
|
| 10 |
+
"train_loss": 0.3203928537069713,
|
| 11 |
+
"train_runtime": 9814.9228,
|
| 12 |
+
"train_samples_per_second": 2.332,
|
| 13 |
+
"train_steps_per_second": 0.146,
|
| 14 |
+
"valid_targets_mean": 2891.9,
|
| 15 |
+
"valid_targets_min": 658
|
| 16 |
+
}
|
trainer_log.jsonl
ADDED
|
@@ -0,0 +1,288 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 5, "total_steps": 1435, "loss": 0.8361, "lr": 1.111111111111111e-06, "epoch": 0.024390243902439025, "percentage": 0.35, "elapsed_time": "0:00:47", "remaining_time": "3:46:53"}
|
| 2 |
+
{"current_steps": 10, "total_steps": 1435, "loss": 0.8084, "lr": 2.5e-06, "epoch": 0.04878048780487805, "percentage": 0.7, "elapsed_time": "0:01:22", "remaining_time": "3:15:42"}
|
| 3 |
+
{"current_steps": 15, "total_steps": 1435, "loss": 0.8018, "lr": 3.88888888888889e-06, "epoch": 0.07317073170731707, "percentage": 1.05, "elapsed_time": "0:01:52", "remaining_time": "2:57:01"}
|
| 4 |
+
{"current_steps": 20, "total_steps": 1435, "loss": 0.7365, "lr": 5.2777777777777785e-06, "epoch": 0.0975609756097561, "percentage": 1.39, "elapsed_time": "0:02:24", "remaining_time": "2:50:49"}
|
| 5 |
+
{"current_steps": 25, "total_steps": 1435, "loss": 0.6356, "lr": 6.666666666666667e-06, "epoch": 0.12195121951219512, "percentage": 1.74, "elapsed_time": "0:02:52", "remaining_time": "2:42:21"}
|
| 6 |
+
{"current_steps": 30, "total_steps": 1435, "loss": 0.5786, "lr": 8.055555555555557e-06, "epoch": 0.14634146341463414, "percentage": 2.09, "elapsed_time": "0:03:22", "remaining_time": "2:38:02"}
|
| 7 |
+
{"current_steps": 35, "total_steps": 1435, "loss": 0.5669, "lr": 9.444444444444445e-06, "epoch": 0.17073170731707318, "percentage": 2.44, "elapsed_time": "0:03:50", "remaining_time": "2:33:52"}
|
| 8 |
+
{"current_steps": 40, "total_steps": 1435, "loss": 0.5178, "lr": 1.0833333333333334e-05, "epoch": 0.1951219512195122, "percentage": 2.79, "elapsed_time": "0:04:29", "remaining_time": "2:36:32"}
|
| 9 |
+
{"current_steps": 45, "total_steps": 1435, "loss": 0.5122, "lr": 1.2222222222222224e-05, "epoch": 0.21951219512195122, "percentage": 3.14, "elapsed_time": "0:05:04", "remaining_time": "2:36:54"}
|
| 10 |
+
{"current_steps": 50, "total_steps": 1435, "loss": 0.5046, "lr": 1.3611111111111113e-05, "epoch": 0.24390243902439024, "percentage": 3.48, "elapsed_time": "0:05:40", "remaining_time": "2:37:09"}
|
| 11 |
+
{"current_steps": 55, "total_steps": 1435, "loss": 0.5042, "lr": 1.5000000000000002e-05, "epoch": 0.2682926829268293, "percentage": 3.83, "elapsed_time": "0:06:14", "remaining_time": "2:36:31"}
|
| 12 |
+
{"current_steps": 60, "total_steps": 1435, "loss": 0.4964, "lr": 1.638888888888889e-05, "epoch": 0.2926829268292683, "percentage": 4.18, "elapsed_time": "0:06:49", "remaining_time": "2:36:28"}
|
| 13 |
+
{"current_steps": 65, "total_steps": 1435, "loss": 0.4878, "lr": 1.7777777777777777e-05, "epoch": 0.3170731707317073, "percentage": 4.53, "elapsed_time": "0:07:22", "remaining_time": "2:35:26"}
|
| 14 |
+
{"current_steps": 70, "total_steps": 1435, "loss": 0.4473, "lr": 1.916666666666667e-05, "epoch": 0.34146341463414637, "percentage": 4.88, "elapsed_time": "0:07:56", "remaining_time": "2:34:53"}
|
| 15 |
+
{"current_steps": 75, "total_steps": 1435, "loss": 0.4557, "lr": 2.0555555555555555e-05, "epoch": 0.36585365853658536, "percentage": 5.23, "elapsed_time": "0:08:25", "remaining_time": "2:32:51"}
|
| 16 |
+
{"current_steps": 80, "total_steps": 1435, "loss": 0.46, "lr": 2.194444444444445e-05, "epoch": 0.3902439024390244, "percentage": 5.57, "elapsed_time": "0:08:57", "remaining_time": "2:31:36"}
|
| 17 |
+
{"current_steps": 85, "total_steps": 1435, "loss": 0.4682, "lr": 2.3333333333333336e-05, "epoch": 0.4146341463414634, "percentage": 5.92, "elapsed_time": "0:09:34", "remaining_time": "2:32:01"}
|
| 18 |
+
{"current_steps": 90, "total_steps": 1435, "loss": 0.4455, "lr": 2.4722222222222226e-05, "epoch": 0.43902439024390244, "percentage": 6.27, "elapsed_time": "0:10:07", "remaining_time": "2:31:23"}
|
| 19 |
+
{"current_steps": 95, "total_steps": 1435, "loss": 0.4531, "lr": 2.6111111111111114e-05, "epoch": 0.4634146341463415, "percentage": 6.62, "elapsed_time": "0:10:42", "remaining_time": "2:31:01"}
|
| 20 |
+
{"current_steps": 100, "total_steps": 1435, "loss": 0.4494, "lr": 2.75e-05, "epoch": 0.4878048780487805, "percentage": 6.97, "elapsed_time": "0:11:11", "remaining_time": "2:29:28"}
|
| 21 |
+
{"current_steps": 105, "total_steps": 1435, "loss": 0.418, "lr": 2.888888888888889e-05, "epoch": 0.5121951219512195, "percentage": 7.32, "elapsed_time": "0:11:44", "remaining_time": "2:28:43"}
|
| 22 |
+
{"current_steps": 110, "total_steps": 1435, "loss": 0.4421, "lr": 3.027777777777778e-05, "epoch": 0.5365853658536586, "percentage": 7.67, "elapsed_time": "0:12:16", "remaining_time": "2:27:57"}
|
| 23 |
+
{"current_steps": 115, "total_steps": 1435, "loss": 0.4504, "lr": 3.1666666666666666e-05, "epoch": 0.5609756097560976, "percentage": 8.01, "elapsed_time": "0:12:49", "remaining_time": "2:27:10"}
|
| 24 |
+
{"current_steps": 120, "total_steps": 1435, "loss": 0.4249, "lr": 3.3055555555555553e-05, "epoch": 0.5853658536585366, "percentage": 8.36, "elapsed_time": "0:13:26", "remaining_time": "2:27:19"}
|
| 25 |
+
{"current_steps": 125, "total_steps": 1435, "loss": 0.4417, "lr": 3.444444444444445e-05, "epoch": 0.6097560975609756, "percentage": 8.71, "elapsed_time": "0:13:51", "remaining_time": "2:25:17"}
|
| 26 |
+
{"current_steps": 130, "total_steps": 1435, "loss": 0.4383, "lr": 3.5833333333333335e-05, "epoch": 0.6341463414634146, "percentage": 9.06, "elapsed_time": "0:14:23", "remaining_time": "2:24:24"}
|
| 27 |
+
{"current_steps": 135, "total_steps": 1435, "loss": 0.4266, "lr": 3.722222222222223e-05, "epoch": 0.6585365853658537, "percentage": 9.41, "elapsed_time": "0:14:56", "remaining_time": "2:23:49"}
|
| 28 |
+
{"current_steps": 140, "total_steps": 1435, "loss": 0.4089, "lr": 3.8611111111111116e-05, "epoch": 0.6829268292682927, "percentage": 9.76, "elapsed_time": "0:15:27", "remaining_time": "2:23:02"}
|
| 29 |
+
{"current_steps": 145, "total_steps": 1435, "loss": 0.4009, "lr": 4e-05, "epoch": 0.7073170731707317, "percentage": 10.1, "elapsed_time": "0:15:59", "remaining_time": "2:22:16"}
|
| 30 |
+
{"current_steps": 150, "total_steps": 1435, "loss": 0.4064, "lr": 3.999851959033532e-05, "epoch": 0.7317073170731707, "percentage": 10.45, "elapsed_time": "0:16:34", "remaining_time": "2:22:00"}
|
| 31 |
+
{"current_steps": 155, "total_steps": 1435, "loss": 0.4104, "lr": 3.999407858050255e-05, "epoch": 0.7560975609756098, "percentage": 10.8, "elapsed_time": "0:17:04", "remaining_time": "2:21:01"}
|
| 32 |
+
{"current_steps": 160, "total_steps": 1435, "loss": 0.4061, "lr": 3.998667762795307e-05, "epoch": 0.7804878048780488, "percentage": 11.15, "elapsed_time": "0:17:41", "remaining_time": "2:20:58"}
|
| 33 |
+
{"current_steps": 165, "total_steps": 1435, "loss": 0.4108, "lr": 3.9976317828331075e-05, "epoch": 0.8048780487804879, "percentage": 11.5, "elapsed_time": "0:18:13", "remaining_time": "2:20:14"}
|
| 34 |
+
{"current_steps": 170, "total_steps": 1435, "loss": 0.4148, "lr": 3.9963000715311284e-05, "epoch": 0.8292682926829268, "percentage": 11.85, "elapsed_time": "0:18:47", "remaining_time": "2:19:46"}
|
| 35 |
+
{"current_steps": 175, "total_steps": 1435, "loss": 0.4097, "lr": 3.9946728260372e-05, "epoch": 0.8536585365853658, "percentage": 12.2, "elapsed_time": "0:19:22", "remaining_time": "2:19:27"}
|
| 36 |
+
{"current_steps": 180, "total_steps": 1435, "loss": 0.4262, "lr": 3.992750287250316e-05, "epoch": 0.8780487804878049, "percentage": 12.54, "elapsed_time": "0:19:51", "remaining_time": "2:18:27"}
|
| 37 |
+
{"current_steps": 185, "total_steps": 1435, "loss": 0.4143, "lr": 3.9905327397849776e-05, "epoch": 0.9024390243902439, "percentage": 12.89, "elapsed_time": "0:20:22", "remaining_time": "2:17:43"}
|
| 38 |
+
{"current_steps": 190, "total_steps": 1435, "loss": 0.4068, "lr": 3.988020511929055e-05, "epoch": 0.926829268292683, "percentage": 13.24, "elapsed_time": "0:20:55", "remaining_time": "2:17:05"}
|
| 39 |
+
{"current_steps": 195, "total_steps": 1435, "loss": 0.4169, "lr": 3.985213975595188e-05, "epoch": 0.9512195121951219, "percentage": 13.59, "elapsed_time": "0:21:26", "remaining_time": "2:16:19"}
|
| 40 |
+
{"current_steps": 200, "total_steps": 1435, "loss": 0.4196, "lr": 3.982113546265727e-05, "epoch": 0.975609756097561, "percentage": 13.94, "elapsed_time": "0:22:03", "remaining_time": "2:16:15"}
|
| 41 |
+
{"current_steps": 205, "total_steps": 1435, "loss": 0.3994, "lr": 3.978719682931227e-05, "epoch": 1.0, "percentage": 14.29, "elapsed_time": "0:23:35", "remaining_time": "2:21:33"}
|
| 42 |
+
{"current_steps": 210, "total_steps": 1435, "loss": 0.3843, "lr": 3.9750328880224964e-05, "epoch": 1.024390243902439, "percentage": 14.63, "elapsed_time": "0:24:05", "remaining_time": "2:20:29"}
|
| 43 |
+
{"current_steps": 215, "total_steps": 1435, "loss": 0.3676, "lr": 3.9710537073362154e-05, "epoch": 1.048780487804878, "percentage": 14.98, "elapsed_time": "0:24:40", "remaining_time": "2:20:02"}
|
| 44 |
+
{"current_steps": 220, "total_steps": 1435, "loss": 0.376, "lr": 3.9667827299541405e-05, "epoch": 1.0731707317073171, "percentage": 15.33, "elapsed_time": "0:25:13", "remaining_time": "2:19:20"}
|
| 45 |
+
{"current_steps": 225, "total_steps": 1435, "loss": 0.3914, "lr": 3.962220588155889e-05, "epoch": 1.0975609756097562, "percentage": 15.68, "elapsed_time": "0:25:50", "remaining_time": "2:18:55"}
|
| 46 |
+
{"current_steps": 230, "total_steps": 1435, "loss": 0.3891, "lr": 3.957367957325344e-05, "epoch": 1.1219512195121952, "percentage": 16.03, "elapsed_time": "0:26:16", "remaining_time": "2:17:38"}
|
| 47 |
+
{"current_steps": 235, "total_steps": 1435, "loss": 0.3805, "lr": 3.952225555850662e-05, "epoch": 1.146341463414634, "percentage": 16.38, "elapsed_time": "0:26:54", "remaining_time": "2:17:23"}
|
| 48 |
+
{"current_steps": 240, "total_steps": 1435, "loss": 0.4021, "lr": 3.9467941450179276e-05, "epoch": 1.170731707317073, "percentage": 16.72, "elapsed_time": "0:27:22", "remaining_time": "2:16:18"}
|
| 49 |
+
{"current_steps": 245, "total_steps": 1435, "loss": 0.3768, "lr": 3.94107452889845e-05, "epoch": 1.1951219512195121, "percentage": 17.07, "elapsed_time": "0:27:55", "remaining_time": "2:15:37"}
|
| 50 |
+
{"current_steps": 250, "total_steps": 1435, "loss": 0.3985, "lr": 3.9350675542297273e-05, "epoch": 1.2195121951219512, "percentage": 17.42, "elapsed_time": "0:28:25", "remaining_time": "2:14:45"}
|
| 51 |
+
{"current_steps": 255, "total_steps": 1435, "loss": 0.3822, "lr": 3.9287741102900956e-05, "epoch": 1.2439024390243902, "percentage": 17.77, "elapsed_time": "0:29:02", "remaining_time": "2:14:24"}
|
| 52 |
+
{"current_steps": 260, "total_steps": 1435, "loss": 0.3531, "lr": 3.922195128767077e-05, "epoch": 1.2682926829268293, "percentage": 18.12, "elapsed_time": "0:29:36", "remaining_time": "2:13:50"}
|
| 53 |
+
{"current_steps": 265, "total_steps": 1435, "loss": 0.3768, "lr": 3.915331583619455e-05, "epoch": 1.2926829268292683, "percentage": 18.47, "elapsed_time": "0:30:13", "remaining_time": "2:13:25"}
|
| 54 |
+
{"current_steps": 270, "total_steps": 1435, "loss": 0.3667, "lr": 3.908184490933087e-05, "epoch": 1.3170731707317074, "percentage": 18.82, "elapsed_time": "0:30:45", "remaining_time": "2:12:42"}
|
| 55 |
+
{"current_steps": 275, "total_steps": 1435, "loss": 0.3852, "lr": 3.90075490877048e-05, "epoch": 1.3414634146341464, "percentage": 19.16, "elapsed_time": "0:31:16", "remaining_time": "2:11:54"}
|
| 56 |
+
{"current_steps": 280, "total_steps": 1435, "loss": 0.3607, "lr": 3.893043937014161e-05, "epoch": 1.3658536585365852, "percentage": 19.51, "elapsed_time": "0:31:45", "remaining_time": "2:11:01"}
|
| 57 |
+
{"current_steps": 285, "total_steps": 1435, "loss": 0.3789, "lr": 3.885052717203839e-05, "epoch": 1.3902439024390243, "percentage": 19.86, "elapsed_time": "0:32:16", "remaining_time": "2:10:14"}
|
| 58 |
+
{"current_steps": 290, "total_steps": 1435, "loss": 0.3593, "lr": 3.876782432367419e-05, "epoch": 1.4146341463414633, "percentage": 20.21, "elapsed_time": "0:32:45", "remaining_time": "2:09:20"}
|
| 59 |
+
{"current_steps": 295, "total_steps": 1435, "loss": 0.3787, "lr": 3.86823430684586e-05, "epoch": 1.4390243902439024, "percentage": 20.56, "elapsed_time": "0:33:23", "remaining_time": "2:09:00"}
|
| 60 |
+
{"current_steps": 300, "total_steps": 1435, "loss": 0.3935, "lr": 3.859409606111927e-05, "epoch": 1.4634146341463414, "percentage": 20.91, "elapsed_time": "0:33:56", "remaining_time": "2:08:25"}
|
| 61 |
+
{"current_steps": 305, "total_steps": 1435, "loss": 0.3699, "lr": 3.850309636582844e-05, "epoch": 1.4878048780487805, "percentage": 21.25, "elapsed_time": "0:34:30", "remaining_time": "2:07:52"}
|
| 62 |
+
{"current_steps": 310, "total_steps": 1435, "loss": 0.3777, "lr": 3.8409357454268954e-05, "epoch": 1.5121951219512195, "percentage": 21.6, "elapsed_time": "0:35:03", "remaining_time": "2:07:12"}
|
| 63 |
+
{"current_steps": 315, "total_steps": 1435, "loss": 0.3883, "lr": 3.831289320363988e-05, "epoch": 1.5365853658536586, "percentage": 21.95, "elapsed_time": "0:35:33", "remaining_time": "2:06:24"}
|
| 64 |
+
{"current_steps": 320, "total_steps": 1435, "loss": 0.3614, "lr": 3.821371789460211e-05, "epoch": 1.5609756097560976, "percentage": 22.3, "elapsed_time": "0:36:05", "remaining_time": "2:05:45"}
|
| 65 |
+
{"current_steps": 325, "total_steps": 1435, "loss": 0.3748, "lr": 3.8111846209164245e-05, "epoch": 1.5853658536585367, "percentage": 22.65, "elapsed_time": "0:36:42", "remaining_time": "2:05:21"}
|
| 66 |
+
{"current_steps": 330, "total_steps": 1435, "loss": 0.3763, "lr": 3.800729322850905e-05, "epoch": 1.6097560975609757, "percentage": 23.0, "elapsed_time": "0:37:13", "remaining_time": "2:04:40"}
|
| 67 |
+
{"current_steps": 335, "total_steps": 1435, "loss": 0.3838, "lr": 3.790007443076083e-05, "epoch": 1.6341463414634148, "percentage": 23.34, "elapsed_time": "0:37:46", "remaining_time": "2:04:02"}
|
| 68 |
+
{"current_steps": 340, "total_steps": 1435, "loss": 0.3559, "lr": 3.779020568869402e-05, "epoch": 1.6585365853658538, "percentage": 23.69, "elapsed_time": "0:38:19", "remaining_time": "2:03:27"}
|
| 69 |
+
{"current_steps": 345, "total_steps": 1435, "loss": 0.3816, "lr": 3.767770326738339e-05, "epoch": 1.6829268292682928, "percentage": 24.04, "elapsed_time": "0:38:55", "remaining_time": "2:03:00"}
|
| 70 |
+
{"current_steps": 350, "total_steps": 1435, "loss": 0.3735, "lr": 3.7562583821796114e-05, "epoch": 1.7073170731707317, "percentage": 24.39, "elapsed_time": "0:39:31", "remaining_time": "2:02:30"}
|
| 71 |
+
{"current_steps": 355, "total_steps": 1435, "loss": 0.3607, "lr": 3.7444864394326186e-05, "epoch": 1.7317073170731707, "percentage": 24.74, "elapsed_time": "0:40:04", "remaining_time": "2:01:54"}
|
| 72 |
+
{"current_steps": 360, "total_steps": 1435, "loss": 0.3591, "lr": 3.732456241227141e-05, "epoch": 1.7560975609756098, "percentage": 25.09, "elapsed_time": "0:40:39", "remaining_time": "2:01:24"}
|
| 73 |
+
{"current_steps": 365, "total_steps": 1435, "loss": 0.3896, "lr": 3.7201695685253476e-05, "epoch": 1.7804878048780488, "percentage": 25.44, "elapsed_time": "0:41:09", "remaining_time": "2:00:39"}
|
| 74 |
+
{"current_steps": 370, "total_steps": 1435, "loss": 0.3927, "lr": 3.7076282402581404e-05, "epoch": 1.8048780487804879, "percentage": 25.78, "elapsed_time": "0:41:41", "remaining_time": "1:59:58"}
|
| 75 |
+
{"current_steps": 375, "total_steps": 1435, "loss": 0.3652, "lr": 3.694834113055877e-05, "epoch": 1.8292682926829267, "percentage": 26.13, "elapsed_time": "0:42:14", "remaining_time": "1:59:23"}
|
| 76 |
+
{"current_steps": 380, "total_steps": 1435, "loss": 0.3603, "lr": 3.681789080973514e-05, "epoch": 1.8536585365853657, "percentage": 26.48, "elapsed_time": "0:42:42", "remaining_time": "1:58:33"}
|
| 77 |
+
{"current_steps": 385, "total_steps": 1435, "loss": 0.3593, "lr": 3.668495075210207e-05, "epoch": 1.8780487804878048, "percentage": 26.83, "elapsed_time": "0:43:19", "remaining_time": "1:58:09"}
|
| 78 |
+
{"current_steps": 390, "total_steps": 1435, "loss": 0.3631, "lr": 3.654954063823419e-05, "epoch": 1.9024390243902438, "percentage": 27.18, "elapsed_time": "0:43:53", "remaining_time": "1:57:36"}
|
| 79 |
+
{"current_steps": 395, "total_steps": 1435, "loss": 0.3838, "lr": 3.641168051437562e-05, "epoch": 1.9268292682926829, "percentage": 27.53, "elapsed_time": "0:44:21", "remaining_time": "1:56:47"}
|
| 80 |
+
{"current_steps": 400, "total_steps": 1435, "loss": 0.3785, "lr": 3.627139078947233e-05, "epoch": 1.951219512195122, "percentage": 27.87, "elapsed_time": "0:44:51", "remaining_time": "1:56:05"}
|
| 81 |
+
{"current_steps": 405, "total_steps": 1435, "loss": 0.3547, "lr": 3.6128692232150775e-05, "epoch": 1.975609756097561, "percentage": 28.22, "elapsed_time": "0:46:25", "remaining_time": "1:58:04"}
|
| 82 |
+
{"current_steps": 410, "total_steps": 1435, "loss": 0.3574, "lr": 3.598360596764331e-05, "epoch": 2.0, "percentage": 28.57, "elapsed_time": "0:47:00", "remaining_time": "1:57:30"}
|
| 83 |
+
{"current_steps": 415, "total_steps": 1435, "loss": 0.346, "lr": 3.583615347466075e-05, "epoch": 2.024390243902439, "percentage": 28.92, "elapsed_time": "0:47:34", "remaining_time": "1:56:55"}
|
| 84 |
+
{"current_steps": 420, "total_steps": 1435, "loss": 0.3131, "lr": 3.568635658221266e-05, "epoch": 2.048780487804878, "percentage": 29.27, "elapsed_time": "0:48:02", "remaining_time": "1:56:06"}
|
| 85 |
+
{"current_steps": 425, "total_steps": 1435, "loss": 0.3289, "lr": 3.553423746637577e-05, "epoch": 2.073170731707317, "percentage": 29.62, "elapsed_time": "0:48:35", "remaining_time": "1:55:28"}
|
| 86 |
+
{"current_steps": 430, "total_steps": 1435, "loss": 0.3556, "lr": 3.537981864701101e-05, "epoch": 2.097560975609756, "percentage": 29.97, "elapsed_time": "0:49:03", "remaining_time": "1:54:39"}
|
| 87 |
+
{"current_steps": 435, "total_steps": 1435, "loss": 0.3533, "lr": 3.5223122984429645e-05, "epoch": 2.1219512195121952, "percentage": 30.31, "elapsed_time": "0:49:36", "remaining_time": "1:54:03"}
|
| 88 |
+
{"current_steps": 440, "total_steps": 1435, "loss": 0.3302, "lr": 3.5064173676008994e-05, "epoch": 2.1463414634146343, "percentage": 30.66, "elapsed_time": "0:50:10", "remaining_time": "1:53:28"}
|
| 89 |
+
{"current_steps": 445, "total_steps": 1435, "loss": 0.3471, "lr": 3.4902994252758295e-05, "epoch": 2.1707317073170733, "percentage": 31.01, "elapsed_time": "0:50:39", "remaining_time": "1:52:42"}
|
| 90 |
+
{"current_steps": 450, "total_steps": 1435, "loss": 0.3171, "lr": 3.473960857583515e-05, "epoch": 2.1951219512195124, "percentage": 31.36, "elapsed_time": "0:51:11", "remaining_time": "1:52:02"}
|
| 91 |
+
{"current_steps": 455, "total_steps": 1435, "loss": 0.347, "lr": 3.457404083301308e-05, "epoch": 2.2195121951219514, "percentage": 31.71, "elapsed_time": "0:51:44", "remaining_time": "1:51:26"}
|
| 92 |
+
{"current_steps": 460, "total_steps": 1435, "loss": 0.3289, "lr": 3.440631553510074e-05, "epoch": 2.2439024390243905, "percentage": 32.06, "elapsed_time": "0:52:17", "remaining_time": "1:50:51"}
|
| 93 |
+
{"current_steps": 465, "total_steps": 1435, "loss": 0.3214, "lr": 3.423645751231334e-05, "epoch": 2.2682926829268295, "percentage": 32.4, "elapsed_time": "0:52:52", "remaining_time": "1:50:17"}
|
| 94 |
+
{"current_steps": 470, "total_steps": 1435, "loss": 0.3219, "lr": 3.4064491910596726e-05, "epoch": 2.292682926829268, "percentage": 32.75, "elapsed_time": "0:53:24", "remaining_time": "1:49:38"}
|
| 95 |
+
{"current_steps": 475, "total_steps": 1435, "loss": 0.3375, "lr": 3.389044418790478e-05, "epoch": 2.317073170731707, "percentage": 33.1, "elapsed_time": "0:53:54", "remaining_time": "1:48:56"}
|
| 96 |
+
{"current_steps": 480, "total_steps": 1435, "loss": 0.337, "lr": 3.371434011043059e-05, "epoch": 2.341463414634146, "percentage": 33.45, "elapsed_time": "0:54:21", "remaining_time": "1:48:08"}
|
| 97 |
+
{"current_steps": 485, "total_steps": 1435, "loss": 0.3149, "lr": 3.353620574879197e-05, "epoch": 2.3658536585365852, "percentage": 33.8, "elapsed_time": "0:54:55", "remaining_time": "1:47:34"}
|
| 98 |
+
{"current_steps": 490, "total_steps": 1435, "loss": 0.3216, "lr": 3.335606747417199e-05, "epoch": 2.3902439024390243, "percentage": 34.15, "elapsed_time": "0:55:29", "remaining_time": "1:47:01"}
|
| 99 |
+
{"current_steps": 495, "total_steps": 1435, "loss": 0.3528, "lr": 3.317395195441492e-05, "epoch": 2.4146341463414633, "percentage": 34.49, "elapsed_time": "0:56:06", "remaining_time": "1:46:33"}
|
| 100 |
+
{"current_steps": 500, "total_steps": 1435, "loss": 0.3328, "lr": 3.29898861500783e-05, "epoch": 2.4390243902439024, "percentage": 34.84, "elapsed_time": "0:56:42", "remaining_time": "1:46:02"}
|
| 101 |
+
{"current_steps": 505, "total_steps": 1435, "loss": 0.3202, "lr": 3.280389731044172e-05, "epoch": 2.4634146341463414, "percentage": 35.19, "elapsed_time": "0:57:19", "remaining_time": "1:45:34"}
|
| 102 |
+
{"current_steps": 510, "total_steps": 1435, "loss": 0.3201, "lr": 3.261601296947274e-05, "epoch": 2.4878048780487805, "percentage": 35.54, "elapsed_time": "0:57:48", "remaining_time": "1:44:50"}
|
| 103 |
+
{"current_steps": 515, "total_steps": 1435, "loss": 0.3346, "lr": 3.242626094175078e-05, "epoch": 2.5121951219512195, "percentage": 35.89, "elapsed_time": "0:58:18", "remaining_time": "1:44:09"}
|
| 104 |
+
{"current_steps": 520, "total_steps": 1435, "loss": 0.318, "lr": 3.223466931834942e-05, "epoch": 2.5365853658536586, "percentage": 36.24, "elapsed_time": "0:58:54", "remaining_time": "1:43:40"}
|
| 105 |
+
{"current_steps": 525, "total_steps": 1435, "loss": 0.336, "lr": 3.204126646267775e-05, "epoch": 2.5609756097560976, "percentage": 36.59, "elapsed_time": "0:59:28", "remaining_time": "1:43:06"}
|
| 106 |
+
{"current_steps": 530, "total_steps": 1435, "loss": 0.3356, "lr": 3.184608100628144e-05, "epoch": 2.5853658536585367, "percentage": 36.93, "elapsed_time": "1:00:02", "remaining_time": "1:42:31"}
|
| 107 |
+
{"current_steps": 535, "total_steps": 1435, "loss": 0.3355, "lr": 3.1649141844604104e-05, "epoch": 2.6097560975609757, "percentage": 37.28, "elapsed_time": "1:00:34", "remaining_time": "1:41:54"}
|
| 108 |
+
{"current_steps": 540, "total_steps": 1435, "loss": 0.3285, "lr": 3.1450478132709564e-05, "epoch": 2.6341463414634148, "percentage": 37.63, "elapsed_time": "1:01:01", "remaining_time": "1:41:09"}
|
| 109 |
+
{"current_steps": 545, "total_steps": 1435, "loss": 0.3151, "lr": 3.125011928096573e-05, "epoch": 2.658536585365854, "percentage": 37.98, "elapsed_time": "1:01:34", "remaining_time": "1:40:32"}
|
| 110 |
+
{"current_steps": 550, "total_steps": 1435, "loss": 0.3253, "lr": 3.1048094950690666e-05, "epoch": 2.682926829268293, "percentage": 38.33, "elapsed_time": "1:02:10", "remaining_time": "1:40:02"}
|
| 111 |
+
{"current_steps": 555, "total_steps": 1435, "loss": 0.3211, "lr": 3.084443504976146e-05, "epoch": 2.7073170731707314, "percentage": 38.68, "elapsed_time": "1:02:46", "remaining_time": "1:39:31"}
|
| 112 |
+
{"current_steps": 560, "total_steps": 1435, "loss": 0.3079, "lr": 3.063916972818668e-05, "epoch": 2.7317073170731705, "percentage": 39.02, "elapsed_time": "1:03:13", "remaining_time": "1:38:47"}
|
| 113 |
+
{"current_steps": 565, "total_steps": 1435, "loss": 0.3296, "lr": 3.0432329373642932e-05, "epoch": 2.7560975609756095, "percentage": 39.37, "elapsed_time": "1:03:48", "remaining_time": "1:38:15"}
|
| 114 |
+
{"current_steps": 570, "total_steps": 1435, "loss": 0.3424, "lr": 3.022394460697619e-05, "epoch": 2.7804878048780486, "percentage": 39.72, "elapsed_time": "1:04:23", "remaining_time": "1:37:42"}
|
| 115 |
+
{"current_steps": 575, "total_steps": 1435, "loss": 0.34, "lr": 3.0014046277668717e-05, "epoch": 2.8048780487804876, "percentage": 40.07, "elapsed_time": "1:04:54", "remaining_time": "1:37:04"}
|
| 116 |
+
{"current_steps": 580, "total_steps": 1435, "loss": 0.3348, "lr": 2.980266545927203e-05, "epoch": 2.8292682926829267, "percentage": 40.42, "elapsed_time": "1:05:28", "remaining_time": "1:36:30"}
|
| 117 |
+
{"current_steps": 585, "total_steps": 1435, "loss": 0.3144, "lr": 2.9589833444806792e-05, "epoch": 2.8536585365853657, "percentage": 40.77, "elapsed_time": "1:05:59", "remaining_time": "1:35:53"}
|
| 118 |
+
{"current_steps": 590, "total_steps": 1435, "loss": 0.3305, "lr": 2.9375581742130114e-05, "epoch": 2.8780487804878048, "percentage": 41.11, "elapsed_time": "1:06:35", "remaining_time": "1:35:22"}
|
| 119 |
+
{"current_steps": 595, "total_steps": 1435, "loss": 0.3246, "lr": 2.9159942069271134e-05, "epoch": 2.902439024390244, "percentage": 41.46, "elapsed_time": "1:07:10", "remaining_time": "1:34:50"}
|
| 120 |
+
{"current_steps": 600, "total_steps": 1435, "loss": 0.3389, "lr": 2.8942946349735418e-05, "epoch": 2.926829268292683, "percentage": 41.81, "elapsed_time": "1:07:35", "remaining_time": "1:34:04"}
|
| 121 |
+
{"current_steps": 605, "total_steps": 1435, "loss": 0.3444, "lr": 2.872462670777902e-05, "epoch": 2.951219512195122, "percentage": 42.16, "elapsed_time": "1:09:04", "remaining_time": "1:34:46"}
|
| 122 |
+
{"current_steps": 610, "total_steps": 1435, "loss": 0.3298, "lr": 2.850501546365272e-05, "epoch": 2.975609756097561, "percentage": 42.51, "elapsed_time": "1:09:37", "remaining_time": "1:34:09"}
|
| 123 |
+
{"current_steps": 615, "total_steps": 1435, "loss": 0.3203, "lr": 2.8284145128817356e-05, "epoch": 3.0, "percentage": 42.86, "elapsed_time": "1:10:07", "remaining_time": "1:33:30"}
|
| 124 |
+
{"current_steps": 620, "total_steps": 1435, "loss": 0.2882, "lr": 2.8062048401130756e-05, "epoch": 3.024390243902439, "percentage": 43.21, "elapsed_time": "1:10:43", "remaining_time": "1:32:58"}
|
| 125 |
+
{"current_steps": 625, "total_steps": 1435, "loss": 0.2966, "lr": 2.7838758160007143e-05, "epoch": 3.048780487804878, "percentage": 43.55, "elapsed_time": "1:11:24", "remaining_time": "1:32:32"}
|
| 126 |
+
{"current_steps": 630, "total_steps": 1435, "loss": 0.2901, "lr": 2.7614307461549608e-05, "epoch": 3.073170731707317, "percentage": 43.9, "elapsed_time": "1:11:56", "remaining_time": "1:31:55"}
|
| 127 |
+
{"current_steps": 635, "total_steps": 1435, "loss": 0.3045, "lr": 2.7388729533656486e-05, "epoch": 3.097560975609756, "percentage": 44.25, "elapsed_time": "1:12:25", "remaining_time": "1:31:14"}
|
| 128 |
+
{"current_steps": 640, "total_steps": 1435, "loss": 0.2904, "lr": 2.716205777110222e-05, "epoch": 3.1219512195121952, "percentage": 44.6, "elapsed_time": "1:13:02", "remaining_time": "1:30:44"}
|
| 129 |
+
{"current_steps": 645, "total_steps": 1435, "loss": 0.3019, "lr": 2.693432573059362e-05, "epoch": 3.1463414634146343, "percentage": 44.95, "elapsed_time": "1:13:26", "remaining_time": "1:29:57"}
|
| 130 |
+
{"current_steps": 650, "total_steps": 1435, "loss": 0.3081, "lr": 2.6705567125802062e-05, "epoch": 3.1707317073170733, "percentage": 45.3, "elapsed_time": "1:13:54", "remaining_time": "1:29:15"}
|
| 131 |
+
{"current_steps": 655, "total_steps": 1435, "loss": 0.2962, "lr": 2.6475815822372477e-05, "epoch": 3.1951219512195124, "percentage": 45.64, "elapsed_time": "1:14:26", "remaining_time": "1:28:39"}
|
| 132 |
+
{"current_steps": 660, "total_steps": 1435, "loss": 0.3042, "lr": 2.624510583290988e-05, "epoch": 3.2195121951219514, "percentage": 45.99, "elapsed_time": "1:15:03", "remaining_time": "1:28:08"}
|
| 133 |
+
{"current_steps": 665, "total_steps": 1435, "loss": 0.2824, "lr": 2.601347131194408e-05, "epoch": 3.2439024390243905, "percentage": 46.34, "elapsed_time": "1:15:40", "remaining_time": "1:27:37"}
|
| 134 |
+
{"current_steps": 670, "total_steps": 1435, "loss": 0.2887, "lr": 2.578094655087343e-05, "epoch": 3.2682926829268295, "percentage": 46.69, "elapsed_time": "1:16:16", "remaining_time": "1:27:05"}
|
| 135 |
+
{"current_steps": 675, "total_steps": 1435, "loss": 0.2758, "lr": 2.5547565972888287e-05, "epoch": 3.292682926829268, "percentage": 47.04, "elapsed_time": "1:16:52", "remaining_time": "1:26:33"}
|
| 136 |
+
{"current_steps": 680, "total_steps": 1435, "loss": 0.2936, "lr": 2.5313364127874974e-05, "epoch": 3.317073170731707, "percentage": 47.39, "elapsed_time": "1:17:25", "remaining_time": "1:25:58"}
|
| 137 |
+
{"current_steps": 685, "total_steps": 1435, "loss": 0.289, "lr": 2.507837568730097e-05, "epoch": 3.341463414634146, "percentage": 47.74, "elapsed_time": "1:17:59", "remaining_time": "1:25:23"}
|
| 138 |
+
{"current_steps": 690, "total_steps": 1435, "loss": 0.3008, "lr": 2.484263543908213e-05, "epoch": 3.3658536585365852, "percentage": 48.08, "elapsed_time": "1:18:26", "remaining_time": "1:24:41"}
|
| 139 |
+
{"current_steps": 695, "total_steps": 1435, "loss": 0.2919, "lr": 2.460617828243263e-05, "epoch": 3.3902439024390243, "percentage": 48.43, "elapsed_time": "1:18:56", "remaining_time": "1:24:03"}
|
| 140 |
+
{"current_steps": 700, "total_steps": 1435, "loss": 0.2898, "lr": 2.4369039222698484e-05, "epoch": 3.4146341463414633, "percentage": 48.78, "elapsed_time": "1:19:26", "remaining_time": "1:23:24"}
|
| 141 |
+
{"current_steps": 705, "total_steps": 1435, "loss": 0.3052, "lr": 2.413125336617526e-05, "epoch": 3.4390243902439024, "percentage": 49.13, "elapsed_time": "1:19:59", "remaining_time": "1:22:49"}
|
| 142 |
+
{"current_steps": 710, "total_steps": 1435, "loss": 0.2925, "lr": 2.3892855914910996e-05, "epoch": 3.4634146341463414, "percentage": 49.48, "elapsed_time": "1:20:31", "remaining_time": "1:22:13"}
|
| 143 |
+
{"current_steps": 715, "total_steps": 1435, "loss": 0.2896, "lr": 2.3653882161494758e-05, "epoch": 3.4878048780487805, "percentage": 49.83, "elapsed_time": "1:21:04", "remaining_time": "1:21:38"}
|
| 144 |
+
{"current_steps": 720, "total_steps": 1435, "loss": 0.2972, "lr": 2.3414367483831972e-05, "epoch": 3.5121951219512195, "percentage": 50.17, "elapsed_time": "1:21:39", "remaining_time": "1:21:05"}
|
| 145 |
+
{"current_steps": 725, "total_steps": 1435, "loss": 0.2909, "lr": 2.3174347339906994e-05, "epoch": 3.5365853658536586, "percentage": 50.52, "elapsed_time": "1:22:09", "remaining_time": "1:20:27"}
|
| 146 |
+
{"current_steps": 730, "total_steps": 1435, "loss": 0.2953, "lr": 2.293385726253392e-05, "epoch": 3.5609756097560976, "percentage": 50.87, "elapsed_time": "1:22:37", "remaining_time": "1:19:47"}
|
| 147 |
+
{"current_steps": 735, "total_steps": 1435, "loss": 0.2895, "lr": 2.2692932854096218e-05, "epoch": 3.5853658536585367, "percentage": 51.22, "elapsed_time": "1:23:06", "remaining_time": "1:19:09"}
|
| 148 |
+
{"current_steps": 740, "total_steps": 1435, "loss": 0.2971, "lr": 2.245160978127616e-05, "epoch": 3.6097560975609757, "percentage": 51.57, "elapsed_time": "1:23:40", "remaining_time": "1:18:35"}
|
| 149 |
+
{"current_steps": 745, "total_steps": 1435, "loss": 0.2993, "lr": 2.220992376977468e-05, "epoch": 3.6341463414634148, "percentage": 51.92, "elapsed_time": "1:24:13", "remaining_time": "1:18:00"}
|
| 150 |
+
{"current_steps": 750, "total_steps": 1435, "loss": 0.2898, "lr": 2.1967910599022508e-05, "epoch": 3.658536585365854, "percentage": 52.26, "elapsed_time": "1:24:45", "remaining_time": "1:17:24"}
|
| 151 |
+
{"current_steps": 755, "total_steps": 1435, "loss": 0.2915, "lr": 2.1725606096883324e-05, "epoch": 3.682926829268293, "percentage": 52.61, "elapsed_time": "1:25:13", "remaining_time": "1:16:45"}
|
| 152 |
+
{"current_steps": 760, "total_steps": 1435, "loss": 0.2876, "lr": 2.1483046134349813e-05, "epoch": 3.7073170731707314, "percentage": 52.96, "elapsed_time": "1:25:47", "remaining_time": "1:16:12"}
|
| 153 |
+
{"current_steps": 765, "total_steps": 1435, "loss": 0.3112, "lr": 2.1240266620233263e-05, "epoch": 3.7317073170731705, "percentage": 53.31, "elapsed_time": "1:26:16", "remaining_time": "1:15:33"}
|
| 154 |
+
{"current_steps": 770, "total_steps": 1435, "loss": 0.2832, "lr": 2.099730349584757e-05, "epoch": 3.7560975609756095, "percentage": 53.66, "elapsed_time": "1:26:49", "remaining_time": "1:14:59"}
|
| 155 |
+
{"current_steps": 775, "total_steps": 1435, "loss": 0.2996, "lr": 2.0754192729688496e-05, "epoch": 3.7804878048780486, "percentage": 54.01, "elapsed_time": "1:27:14", "remaining_time": "1:14:18"}
|
| 156 |
+
{"current_steps": 780, "total_steps": 1435, "loss": 0.2893, "lr": 2.0510970312108804e-05, "epoch": 3.8048780487804876, "percentage": 54.36, "elapsed_time": "1:27:51", "remaining_time": "1:13:46"}
|
| 157 |
+
{"current_steps": 785, "total_steps": 1435, "loss": 0.3032, "lr": 2.026767224999028e-05, "epoch": 3.8292682926829267, "percentage": 54.7, "elapsed_time": "1:28:28", "remaining_time": "1:13:15"}
|
| 158 |
+
{"current_steps": 790, "total_steps": 1435, "loss": 0.2907, "lr": 2.0024334561413167e-05, "epoch": 3.8536585365853657, "percentage": 55.05, "elapsed_time": "1:29:01", "remaining_time": "1:12:40"}
|
| 159 |
+
{"current_steps": 795, "total_steps": 1435, "loss": 0.2978, "lr": 1.9780993270324063e-05, "epoch": 3.8780487804878048, "percentage": 55.4, "elapsed_time": "1:29:34", "remaining_time": "1:12:06"}
|
| 160 |
+
{"current_steps": 800, "total_steps": 1435, "loss": 0.3073, "lr": 1.953768440120289e-05, "epoch": 3.902439024390244, "percentage": 55.75, "elapsed_time": "1:30:08", "remaining_time": "1:11:32"}
|
| 161 |
+
{"current_steps": 805, "total_steps": 1435, "loss": 0.296, "lr": 1.9294443973729768e-05, "epoch": 3.926829268292683, "percentage": 56.1, "elapsed_time": "1:31:40", "remaining_time": "1:11:44"}
|
| 162 |
+
{"current_steps": 810, "total_steps": 1435, "loss": 0.2969, "lr": 1.905130799745268e-05, "epoch": 3.951219512195122, "percentage": 56.45, "elapsed_time": "1:32:10", "remaining_time": "1:11:07"}
|
| 163 |
+
{"current_steps": 815, "total_steps": 1435, "loss": 0.2856, "lr": 1.8808312466456525e-05, "epoch": 3.975609756097561, "percentage": 56.79, "elapsed_time": "1:32:39", "remaining_time": "1:10:29"}
|
| 164 |
+
{"current_steps": 820, "total_steps": 1435, "loss": 0.2977, "lr": 1.856549335403457e-05, "epoch": 4.0, "percentage": 57.14, "elapsed_time": "1:33:15", "remaining_time": "1:09:56"}
|
| 165 |
+
{"current_steps": 825, "total_steps": 1435, "loss": 0.2709, "lr": 1.832288660736288e-05, "epoch": 4.024390243902439, "percentage": 57.49, "elapsed_time": "1:33:48", "remaining_time": "1:09:21"}
|
| 166 |
+
{"current_steps": 830, "total_steps": 1435, "loss": 0.2656, "lr": 1.808052814217871e-05, "epoch": 4.048780487804878, "percentage": 57.84, "elapsed_time": "1:34:17", "remaining_time": "1:08:44"}
|
| 167 |
+
{"current_steps": 835, "total_steps": 1435, "loss": 0.2833, "lr": 1.7838453837463498e-05, "epoch": 4.073170731707317, "percentage": 58.19, "elapsed_time": "1:34:49", "remaining_time": "1:08:08"}
|
| 168 |
+
{"current_steps": 840, "total_steps": 1435, "loss": 0.2617, "lr": 1.7596699530131234e-05, "epoch": 4.097560975609756, "percentage": 58.54, "elapsed_time": "1:35:25", "remaining_time": "1:07:35"}
|
| 169 |
+
{"current_steps": 845, "total_steps": 1435, "loss": 0.2681, "lr": 1.735530100972326e-05, "epoch": 4.121951219512195, "percentage": 58.89, "elapsed_time": "1:36:01", "remaining_time": "1:07:02"}
|
| 170 |
+
{"current_steps": 850, "total_steps": 1435, "loss": 0.2808, "lr": 1.711429401310981e-05, "epoch": 4.146341463414634, "percentage": 59.23, "elapsed_time": "1:36:29", "remaining_time": "1:06:24"}
|
| 171 |
+
{"current_steps": 855, "total_steps": 1435, "loss": 0.2702, "lr": 1.687371421919961e-05, "epoch": 4.170731707317073, "percentage": 59.58, "elapsed_time": "1:36:59", "remaining_time": "1:05:47"}
|
| 172 |
+
{"current_steps": 860, "total_steps": 1435, "loss": 0.283, "lr": 1.6633597243657855e-05, "epoch": 4.195121951219512, "percentage": 59.93, "elapsed_time": "1:37:29", "remaining_time": "1:05:11"}
|
| 173 |
+
{"current_steps": 865, "total_steps": 1435, "loss": 0.2692, "lr": 1.6393978633633668e-05, "epoch": 4.219512195121951, "percentage": 60.28, "elapsed_time": "1:38:01", "remaining_time": "1:04:35"}
|
| 174 |
+
{"current_steps": 870, "total_steps": 1435, "loss": 0.2949, "lr": 1.6154893862497673e-05, "epoch": 4.2439024390243905, "percentage": 60.63, "elapsed_time": "1:38:31", "remaining_time": "1:03:58"}
|
| 175 |
+
{"current_steps": 875, "total_steps": 1435, "loss": 0.2598, "lr": 1.5916378324590437e-05, "epoch": 4.2682926829268295, "percentage": 60.98, "elapsed_time": "1:39:04", "remaining_time": "1:03:24"}
|
| 176 |
+
{"current_steps": 880, "total_steps": 1435, "loss": 0.267, "lr": 1.5678467329982717e-05, "epoch": 4.2926829268292686, "percentage": 61.32, "elapsed_time": "1:39:43", "remaining_time": "1:02:53"}
|
| 177 |
+
{"current_steps": 885, "total_steps": 1435, "loss": 0.2786, "lr": 1.54411960992481e-05, "epoch": 4.317073170731708, "percentage": 61.67, "elapsed_time": "1:40:11", "remaining_time": "1:02:15"}
|
| 178 |
+
{"current_steps": 890, "total_steps": 1435, "loss": 0.2797, "lr": 1.5204599758248884e-05, "epoch": 4.341463414634147, "percentage": 62.02, "elapsed_time": "1:40:35", "remaining_time": "1:01:36"}
|
| 179 |
+
{"current_steps": 895, "total_steps": 1435, "loss": 0.2648, "lr": 1.4968713332936063e-05, "epoch": 4.365853658536586, "percentage": 62.37, "elapsed_time": "1:41:06", "remaining_time": "1:01:00"}
|
| 180 |
+
{"current_steps": 900, "total_steps": 1435, "loss": 0.2589, "lr": 1.473357174416401e-05, "epoch": 4.390243902439025, "percentage": 62.72, "elapsed_time": "1:41:38", "remaining_time": "1:00:24"}
|
| 181 |
+
{"current_steps": 905, "total_steps": 1435, "loss": 0.2616, "lr": 1.4499209802520791e-05, "epoch": 4.414634146341464, "percentage": 63.07, "elapsed_time": "1:42:12", "remaining_time": "0:59:51"}
|
| 182 |
+
{"current_steps": 910, "total_steps": 1435, "loss": 0.2664, "lr": 1.426566220317474e-05, "epoch": 4.439024390243903, "percentage": 63.41, "elapsed_time": "1:42:45", "remaining_time": "0:59:16"}
|
| 183 |
+
{"current_steps": 915, "total_steps": 1435, "loss": 0.2661, "lr": 1.4032963520738183e-05, "epoch": 4.463414634146342, "percentage": 63.76, "elapsed_time": "1:43:17", "remaining_time": "0:58:42"}
|
| 184 |
+
{"current_steps": 920, "total_steps": 1435, "loss": 0.2625, "lr": 1.3801148204148983e-05, "epoch": 4.487804878048781, "percentage": 64.11, "elapsed_time": "1:43:47", "remaining_time": "0:58:05"}
|
| 185 |
+
{"current_steps": 925, "total_steps": 1435, "loss": 0.2732, "lr": 1.357025057157062e-05, "epoch": 4.512195121951219, "percentage": 64.46, "elapsed_time": "1:44:16", "remaining_time": "0:57:29"}
|
| 186 |
+
{"current_steps": 930, "total_steps": 1435, "loss": 0.2593, "lr": 1.3340304805311802e-05, "epoch": 4.536585365853659, "percentage": 64.81, "elapsed_time": "1:44:41", "remaining_time": "0:56:50"}
|
| 187 |
+
{"current_steps": 935, "total_steps": 1435, "loss": 0.2576, "lr": 1.3111344946765977e-05, "epoch": 4.560975609756097, "percentage": 65.16, "elapsed_time": "1:45:14", "remaining_time": "0:56:16"}
|
| 188 |
+
{"current_steps": 940, "total_steps": 1435, "loss": 0.276, "lr": 1.2883404891371907e-05, "epoch": 4.585365853658536, "percentage": 65.51, "elapsed_time": "1:45:42", "remaining_time": "0:55:39"}
|
| 189 |
+
{"current_steps": 945, "total_steps": 1435, "loss": 0.2621, "lr": 1.2656518383595681e-05, "epoch": 4.609756097560975, "percentage": 65.85, "elapsed_time": "1:46:21", "remaining_time": "0:55:08"}
|
| 190 |
+
{"current_steps": 950, "total_steps": 1435, "loss": 0.2676, "lr": 1.243071901193519e-05, "epoch": 4.634146341463414, "percentage": 66.2, "elapsed_time": "1:46:55", "remaining_time": "0:54:35"}
|
| 191 |
+
{"current_steps": 955, "total_steps": 1435, "loss": 0.2661, "lr": 1.2206040203947645e-05, "epoch": 4.658536585365853, "percentage": 66.55, "elapsed_time": "1:47:28", "remaining_time": "0:54:00"}
|
| 192 |
+
{"current_steps": 960, "total_steps": 1435, "loss": 0.2624, "lr": 1.1982515221300917e-05, "epoch": 4.682926829268292, "percentage": 66.9, "elapsed_time": "1:48:05", "remaining_time": "0:53:28"}
|
| 193 |
+
{"current_steps": 965, "total_steps": 1435, "loss": 0.2558, "lr": 1.1760177154849473e-05, "epoch": 4.7073170731707314, "percentage": 67.25, "elapsed_time": "1:48:32", "remaining_time": "0:52:51"}
|
| 194 |
+
{"current_steps": 970, "total_steps": 1435, "loss": 0.2636, "lr": 1.1539058919735557e-05, "epoch": 4.7317073170731705, "percentage": 67.6, "elapsed_time": "1:49:00", "remaining_time": "0:52:15"}
|
| 195 |
+
{"current_steps": 975, "total_steps": 1435, "loss": 0.2684, "lr": 1.1319193250516387e-05, "epoch": 4.7560975609756095, "percentage": 67.94, "elapsed_time": "1:49:31", "remaining_time": "0:51:40"}
|
| 196 |
+
{"current_steps": 980, "total_steps": 1435, "loss": 0.2707, "lr": 1.1100612696318143e-05, "epoch": 4.780487804878049, "percentage": 68.29, "elapsed_time": "1:50:02", "remaining_time": "0:51:05"}
|
| 197 |
+
{"current_steps": 985, "total_steps": 1435, "loss": 0.2746, "lr": 1.0883349616017312e-05, "epoch": 4.804878048780488, "percentage": 68.64, "elapsed_time": "1:50:40", "remaining_time": "0:50:33"}
|
| 198 |
+
{"current_steps": 990, "total_steps": 1435, "loss": 0.2476, "lr": 1.0667436173450278e-05, "epoch": 4.829268292682927, "percentage": 68.99, "elapsed_time": "1:51:12", "remaining_time": "0:49:59"}
|
| 199 |
+
{"current_steps": 995, "total_steps": 1435, "loss": 0.2621, "lr": 1.0452904332651745e-05, "epoch": 4.853658536585366, "percentage": 69.34, "elapsed_time": "1:51:47", "remaining_time": "0:49:26"}
|
| 200 |
+
{"current_steps": 1000, "total_steps": 1435, "loss": 0.265, "lr": 1.0239785853122784e-05, "epoch": 4.878048780487805, "percentage": 69.69, "elapsed_time": "1:52:26", "remaining_time": "0:48:54"}
|
| 201 |
+
{"current_steps": 1005, "total_steps": 1435, "loss": 0.2654, "lr": 1.0028112285129058e-05, "epoch": 4.902439024390244, "percentage": 70.03, "elapsed_time": "1:54:15", "remaining_time": "0:48:53"}
|
| 202 |
+
{"current_steps": 1010, "total_steps": 1435, "loss": 0.2616, "lr": 9.81791496503015e-06, "epoch": 4.926829268292683, "percentage": 70.38, "elapsed_time": "1:54:46", "remaining_time": "0:48:17"}
|
| 203 |
+
{"current_steps": 1015, "total_steps": 1435, "loss": 0.2582, "lr": 9.60922501064049e-06, "epoch": 4.951219512195122, "percentage": 70.73, "elapsed_time": "1:55:17", "remaining_time": "0:47:42"}
|
| 204 |
+
{"current_steps": 1020, "total_steps": 1435, "loss": 0.2536, "lr": 9.402073316622609e-06, "epoch": 4.975609756097561, "percentage": 71.08, "elapsed_time": "1:55:52", "remaining_time": "0:47:08"}
|
| 205 |
+
{"current_steps": 1025, "total_steps": 1435, "loss": 0.2622, "lr": 9.196490549913486e-06, "epoch": 5.0, "percentage": 71.43, "elapsed_time": "1:56:22", "remaining_time": "0:46:33"}
|
| 206 |
+
{"current_steps": 1030, "total_steps": 1435, "loss": 0.2405, "lr": 8.992507145184613e-06, "epoch": 5.024390243902439, "percentage": 71.78, "elapsed_time": "1:56:56", "remaining_time": "0:45:59"}
|
| 207 |
+
{"current_steps": 1035, "total_steps": 1435, "loss": 0.2438, "lr": 8.79015330033635e-06, "epoch": 5.048780487804878, "percentage": 72.13, "elapsed_time": "1:57:27", "remaining_time": "0:45:23"}
|
| 208 |
+
{"current_steps": 1040, "total_steps": 1435, "loss": 0.2436, "lr": 8.589458972027483e-06, "epoch": 5.073170731707317, "percentage": 72.47, "elapsed_time": "1:58:01", "remaining_time": "0:44:49"}
|
| 209 |
+
{"current_steps": 1045, "total_steps": 1435, "loss": 0.2453, "lr": 8.390453871240307e-06, "epoch": 5.097560975609756, "percentage": 72.82, "elapsed_time": "1:58:26", "remaining_time": "0:44:12"}
|
| 210 |
+
{"current_steps": 1050, "total_steps": 1435, "loss": 0.2446, "lr": 8.193167458882292e-06, "epoch": 5.121951219512195, "percentage": 73.17, "elapsed_time": "1:58:59", "remaining_time": "0:43:37"}
|
| 211 |
+
{"current_steps": 1055, "total_steps": 1435, "loss": 0.2452, "lr": 7.9976289414246e-06, "epoch": 5.146341463414634, "percentage": 73.52, "elapsed_time": "1:59:31", "remaining_time": "0:43:02"}
|
| 212 |
+
{"current_steps": 1060, "total_steps": 1435, "loss": 0.2373, "lr": 7.803867266578329e-06, "epoch": 5.170731707317073, "percentage": 73.87, "elapsed_time": "2:00:03", "remaining_time": "0:42:28"}
|
| 213 |
+
{"current_steps": 1065, "total_steps": 1435, "loss": 0.2536, "lr": 7.611911119009092e-06, "epoch": 5.195121951219512, "percentage": 74.22, "elapsed_time": "2:00:38", "remaining_time": "0:41:54"}
|
| 214 |
+
{"current_steps": 1070, "total_steps": 1435, "loss": 0.2544, "lr": 7.4217889160904824e-06, "epoch": 5.219512195121951, "percentage": 74.56, "elapsed_time": "2:01:09", "remaining_time": "0:41:19"}
|
| 215 |
+
{"current_steps": 1075, "total_steps": 1435, "loss": 0.2452, "lr": 7.233528803697185e-06, "epoch": 5.2439024390243905, "percentage": 74.91, "elapsed_time": "2:01:40", "remaining_time": "0:40:44"}
|
| 216 |
+
{"current_steps": 1080, "total_steps": 1435, "loss": 0.2497, "lr": 7.0471586520381796e-06, "epoch": 5.2682926829268295, "percentage": 75.26, "elapsed_time": "2:02:13", "remaining_time": "0:40:10"}
|
| 217 |
+
{"current_steps": 1085, "total_steps": 1435, "loss": 0.2494, "lr": 6.8627060515308275e-06, "epoch": 5.2926829268292686, "percentage": 75.61, "elapsed_time": "2:02:45", "remaining_time": "0:39:35"}
|
| 218 |
+
{"current_steps": 1090, "total_steps": 1435, "loss": 0.2514, "lr": 6.6801983087163944e-06, "epoch": 5.317073170731708, "percentage": 75.96, "elapsed_time": "2:03:17", "remaining_time": "0:39:01"}
|
| 219 |
+
{"current_steps": 1095, "total_steps": 1435, "loss": 0.2406, "lr": 6.499662442217496e-06, "epoch": 5.341463414634147, "percentage": 76.31, "elapsed_time": "2:03:52", "remaining_time": "0:38:27"}
|
| 220 |
+
{"current_steps": 1100, "total_steps": 1435, "loss": 0.2506, "lr": 6.3211251787383146e-06, "epoch": 5.365853658536586, "percentage": 76.66, "elapsed_time": "2:04:25", "remaining_time": "0:37:53"}
|
| 221 |
+
{"current_steps": 1105, "total_steps": 1435, "loss": 0.2786, "lr": 6.144612949107858e-06, "epoch": 5.390243902439025, "percentage": 77.0, "elapsed_time": "2:04:57", "remaining_time": "0:37:18"}
|
| 222 |
+
{"current_steps": 1110, "total_steps": 1435, "loss": 0.2648, "lr": 5.970151884367206e-06, "epoch": 5.414634146341464, "percentage": 77.35, "elapsed_time": "2:05:23", "remaining_time": "0:36:42"}
|
| 223 |
+
{"current_steps": 1115, "total_steps": 1435, "loss": 0.2537, "lr": 5.7977678119010025e-06, "epoch": 5.439024390243903, "percentage": 77.7, "elapsed_time": "2:05:59", "remaining_time": "0:36:09"}
|
| 224 |
+
{"current_steps": 1120, "total_steps": 1435, "loss": 0.2409, "lr": 5.627486251613934e-06, "epoch": 5.463414634146342, "percentage": 78.05, "elapsed_time": "2:06:27", "remaining_time": "0:35:33"}
|
| 225 |
+
{"current_steps": 1125, "total_steps": 1435, "loss": 0.2649, "lr": 5.4593324121527554e-06, "epoch": 5.487804878048781, "percentage": 78.4, "elapsed_time": "2:06:59", "remaining_time": "0:34:59"}
|
| 226 |
+
{"current_steps": 1130, "total_steps": 1435, "loss": 0.252, "lr": 5.293331187174369e-06, "epoch": 5.512195121951219, "percentage": 78.75, "elapsed_time": "2:07:26", "remaining_time": "0:34:23"}
|
| 227 |
+
{"current_steps": 1135, "total_steps": 1435, "loss": 0.2579, "lr": 5.129507151660566e-06, "epoch": 5.536585365853659, "percentage": 79.09, "elapsed_time": "2:07:57", "remaining_time": "0:33:49"}
|
| 228 |
+
{"current_steps": 1140, "total_steps": 1435, "loss": 0.2434, "lr": 4.967884558279894e-06, "epoch": 5.560975609756097, "percentage": 79.44, "elapsed_time": "2:08:36", "remaining_time": "0:33:16"}
|
| 229 |
+
{"current_steps": 1145, "total_steps": 1435, "loss": 0.2543, "lr": 4.808487333797272e-06, "epoch": 5.585365853658536, "percentage": 79.79, "elapsed_time": "2:09:02", "remaining_time": "0:32:40"}
|
| 230 |
+
{"current_steps": 1150, "total_steps": 1435, "loss": 0.2622, "lr": 4.651339075531873e-06, "epoch": 5.609756097560975, "percentage": 80.14, "elapsed_time": "2:09:38", "remaining_time": "0:32:07"}
|
| 231 |
+
{"current_steps": 1155, "total_steps": 1435, "loss": 0.248, "lr": 4.496463047863728e-06, "epoch": 5.634146341463414, "percentage": 80.49, "elapsed_time": "2:10:11", "remaining_time": "0:31:33"}
|
| 232 |
+
{"current_steps": 1160, "total_steps": 1435, "loss": 0.2457, "lr": 4.343882178789649e-06, "epoch": 5.658536585365853, "percentage": 80.84, "elapsed_time": "2:10:43", "remaining_time": "0:30:59"}
|
| 233 |
+
{"current_steps": 1165, "total_steps": 1435, "loss": 0.2536, "lr": 4.193619056528968e-06, "epoch": 5.682926829268292, "percentage": 81.18, "elapsed_time": "2:11:15", "remaining_time": "0:30:25"}
|
| 234 |
+
{"current_steps": 1170, "total_steps": 1435, "loss": 0.2331, "lr": 4.045695926179518e-06, "epoch": 5.7073170731707314, "percentage": 81.53, "elapsed_time": "2:11:45", "remaining_time": "0:29:50"}
|
| 235 |
+
{"current_steps": 1175, "total_steps": 1435, "loss": 0.2461, "lr": 3.900134686424497e-06, "epoch": 5.7317073170731705, "percentage": 81.88, "elapsed_time": "2:12:18", "remaining_time": "0:29:16"}
|
| 236 |
+
{"current_steps": 1180, "total_steps": 1435, "loss": 0.2532, "lr": 3.756956886290497e-06, "epoch": 5.7560975609756095, "percentage": 82.23, "elapsed_time": "2:12:52", "remaining_time": "0:28:42"}
|
| 237 |
+
{"current_steps": 1185, "total_steps": 1435, "loss": 0.244, "lr": 3.6161837219574423e-06, "epoch": 5.780487804878049, "percentage": 82.58, "elapsed_time": "2:13:28", "remaining_time": "0:28:09"}
|
| 238 |
+
{"current_steps": 1190, "total_steps": 1435, "loss": 0.2452, "lr": 3.477836033620623e-06, "epoch": 5.804878048780488, "percentage": 82.93, "elapsed_time": "2:14:01", "remaining_time": "0:27:35"}
|
| 239 |
+
{"current_steps": 1195, "total_steps": 1435, "loss": 0.2456, "lr": 3.3419343024055385e-06, "epoch": 5.829268292682927, "percentage": 83.28, "elapsed_time": "2:14:36", "remaining_time": "0:27:02"}
|
| 240 |
+
{"current_steps": 1200, "total_steps": 1435, "loss": 0.2436, "lr": 3.208498647335818e-06, "epoch": 5.853658536585366, "percentage": 83.62, "elapsed_time": "2:15:10", "remaining_time": "0:26:28"}
|
| 241 |
+
{"current_steps": 1205, "total_steps": 1435, "loss": 0.2497, "lr": 3.0775488223547946e-06, "epoch": 5.878048780487805, "percentage": 83.97, "elapsed_time": "2:16:41", "remaining_time": "0:26:05"}
|
| 242 |
+
{"current_steps": 1210, "total_steps": 1435, "loss": 0.2358, "lr": 2.949104213401126e-06, "epoch": 5.902439024390244, "percentage": 84.32, "elapsed_time": "2:17:18", "remaining_time": "0:25:31"}
|
| 243 |
+
{"current_steps": 1215, "total_steps": 1435, "loss": 0.2607, "lr": 2.8231838355388564e-06, "epoch": 5.926829268292683, "percentage": 84.67, "elapsed_time": "2:17:47", "remaining_time": "0:24:56"}
|
| 244 |
+
{"current_steps": 1220, "total_steps": 1435, "loss": 0.2592, "lr": 2.6998063301424183e-06, "epoch": 5.951219512195122, "percentage": 85.02, "elapsed_time": "2:18:15", "remaining_time": "0:24:21"}
|
| 245 |
+
{"current_steps": 1225, "total_steps": 1435, "loss": 0.2397, "lr": 2.5789899621369576e-06, "epoch": 5.975609756097561, "percentage": 85.37, "elapsed_time": "2:18:47", "remaining_time": "0:23:47"}
|
| 246 |
+
{"current_steps": 1230, "total_steps": 1435, "loss": 0.2363, "lr": 2.4607526172943573e-06, "epoch": 6.0, "percentage": 85.71, "elapsed_time": "2:19:24", "remaining_time": "0:23:14"}
|
| 247 |
+
{"current_steps": 1235, "total_steps": 1435, "loss": 0.231, "lr": 2.345111799585418e-06, "epoch": 6.024390243902439, "percentage": 86.06, "elapsed_time": "2:20:00", "remaining_time": "0:22:40"}
|
| 248 |
+
{"current_steps": 1240, "total_steps": 1435, "loss": 0.2403, "lr": 2.2320846285885536e-06, "epoch": 6.048780487804878, "percentage": 86.41, "elapsed_time": "2:20:30", "remaining_time": "0:22:05"}
|
| 249 |
+
{"current_steps": 1245, "total_steps": 1435, "loss": 0.2407, "lr": 2.1216878369554018e-06, "epoch": 6.073170731707317, "percentage": 86.76, "elapsed_time": "2:21:06", "remaining_time": "0:21:32"}
|
| 250 |
+
{"current_steps": 1250, "total_steps": 1435, "loss": 0.2312, "lr": 2.0139377679336914e-06, "epoch": 6.097560975609756, "percentage": 87.11, "elapsed_time": "2:21:37", "remaining_time": "0:20:57"}
|
| 251 |
+
{"current_steps": 1255, "total_steps": 1435, "loss": 0.2404, "lr": 1.908850372947775e-06, "epoch": 6.121951219512195, "percentage": 87.46, "elapsed_time": "2:22:14", "remaining_time": "0:20:24"}
|
| 252 |
+
{"current_steps": 1260, "total_steps": 1435, "loss": 0.2417, "lr": 1.8064412092371687e-06, "epoch": 6.146341463414634, "percentage": 87.8, "elapsed_time": "2:22:45", "remaining_time": "0:19:49"}
|
| 253 |
+
{"current_steps": 1265, "total_steps": 1435, "loss": 0.2408, "lr": 1.7067254375534426e-06, "epoch": 6.170731707317073, "percentage": 88.15, "elapsed_time": "2:23:15", "remaining_time": "0:19:15"}
|
| 254 |
+
{"current_steps": 1270, "total_steps": 1435, "loss": 0.2446, "lr": 1.6097178199158147e-06, "epoch": 6.195121951219512, "percentage": 88.5, "elapsed_time": "2:23:50", "remaining_time": "0:18:41"}
|
| 255 |
+
{"current_steps": 1275, "total_steps": 1435, "loss": 0.2331, "lr": 1.5154327174257487e-06, "epoch": 6.219512195121951, "percentage": 88.85, "elapsed_time": "2:24:18", "remaining_time": "0:18:06"}
|
| 256 |
+
{"current_steps": 1280, "total_steps": 1435, "loss": 0.2454, "lr": 1.4238840881409411e-06, "epoch": 6.2439024390243905, "percentage": 89.2, "elapsed_time": "2:24:56", "remaining_time": "0:17:33"}
|
| 257 |
+
{"current_steps": 1285, "total_steps": 1435, "loss": 0.2436, "lr": 1.3350854850089556e-06, "epoch": 6.2682926829268295, "percentage": 89.55, "elapsed_time": "2:25:27", "remaining_time": "0:16:58"}
|
| 258 |
+
{"current_steps": 1290, "total_steps": 1435, "loss": 0.2494, "lr": 1.2490500538608186e-06, "epoch": 6.2926829268292686, "percentage": 89.9, "elapsed_time": "2:25:55", "remaining_time": "0:16:24"}
|
| 259 |
+
{"current_steps": 1295, "total_steps": 1435, "loss": 0.2477, "lr": 1.1657905314649054e-06, "epoch": 6.317073170731708, "percentage": 90.24, "elapsed_time": "2:26:27", "remaining_time": "0:15:50"}
|
| 260 |
+
{"current_steps": 1300, "total_steps": 1435, "loss": 0.2414, "lr": 1.0853192436413761e-06, "epoch": 6.341463414634147, "percentage": 90.59, "elapsed_time": "2:26:57", "remaining_time": "0:15:15"}
|
| 261 |
+
{"current_steps": 1305, "total_steps": 1435, "loss": 0.2386, "lr": 1.0076481034374597e-06, "epoch": 6.365853658536586, "percentage": 90.94, "elapsed_time": "2:27:36", "remaining_time": "0:14:42"}
|
| 262 |
+
{"current_steps": 1310, "total_steps": 1435, "loss": 0.2396, "lr": 9.327886093638217e-07, "epoch": 6.390243902439025, "percentage": 91.29, "elapsed_time": "2:28:12", "remaining_time": "0:14:08"}
|
| 263 |
+
{"current_steps": 1315, "total_steps": 1435, "loss": 0.2352, "lr": 8.607518436923024e-07, "epoch": 6.414634146341464, "percentage": 91.64, "elapsed_time": "2:28:43", "remaining_time": "0:13:34"}
|
| 264 |
+
{"current_steps": 1320, "total_steps": 1435, "loss": 0.2365, "lr": 7.915484708153221e-07, "epoch": 6.439024390243903, "percentage": 91.99, "elapsed_time": "2:29:14", "remaining_time": "0:13:00"}
|
| 265 |
+
{"current_steps": 1325, "total_steps": 1435, "loss": 0.2262, "lr": 7.251887356670795e-07, "epoch": 6.463414634146342, "percentage": 92.33, "elapsed_time": "2:29:48", "remaining_time": "0:12:26"}
|
| 266 |
+
{"current_steps": 1330, "total_steps": 1435, "loss": 0.2411, "lr": 6.616824622069029e-07, "epoch": 6.487804878048781, "percentage": 92.68, "elapsed_time": "2:30:21", "remaining_time": "0:11:52"}
|
| 267 |
+
{"current_steps": 1335, "total_steps": 1435, "loss": 0.2348, "lr": 6.010390519648956e-07, "epoch": 6.512195121951219, "percentage": 93.03, "elapsed_time": "2:30:56", "remaining_time": "0:11:18"}
|
| 268 |
+
{"current_steps": 1340, "total_steps": 1435, "loss": 0.2437, "lr": 5.432674826501116e-07, "epoch": 6.536585365853659, "percentage": 93.38, "elapsed_time": "2:31:28", "remaining_time": "0:10:44"}
|
| 269 |
+
{"current_steps": 1345, "total_steps": 1435, "loss": 0.2404, "lr": 4.883763068215142e-07, "epoch": 6.560975609756097, "percentage": 93.73, "elapsed_time": "2:31:58", "remaining_time": "0:10:10"}
|
| 270 |
+
{"current_steps": 1350, "total_steps": 1435, "loss": 0.244, "lr": 4.363736506218197e-07, "epoch": 6.585365853658536, "percentage": 94.08, "elapsed_time": "2:32:28", "remaining_time": "0:09:36"}
|
| 271 |
+
{"current_steps": 1355, "total_steps": 1435, "loss": 0.2422, "lr": 3.8726721257451137e-07, "epoch": 6.609756097560975, "percentage": 94.43, "elapsed_time": "2:32:59", "remaining_time": "0:09:01"}
|
| 272 |
+
{"current_steps": 1360, "total_steps": 1435, "loss": 0.2375, "lr": 3.410642624441352e-07, "epoch": 6.634146341463414, "percentage": 94.77, "elapsed_time": "2:33:29", "remaining_time": "0:08:27"}
|
| 273 |
+
{"current_steps": 1365, "total_steps": 1435, "loss": 0.2312, "lr": 2.977716401600894e-07, "epoch": 6.658536585365853, "percentage": 95.12, "elapsed_time": "2:33:56", "remaining_time": "0:07:53"}
|
| 274 |
+
{"current_steps": 1370, "total_steps": 1435, "loss": 0.2184, "lr": 2.573957548040107e-07, "epoch": 6.682926829268292, "percentage": 95.47, "elapsed_time": "2:34:28", "remaining_time": "0:07:19"}
|
| 275 |
+
{"current_steps": 1375, "total_steps": 1435, "loss": 0.2417, "lr": 2.1994258366099253e-07, "epoch": 6.7073170731707314, "percentage": 95.82, "elapsed_time": "2:34:59", "remaining_time": "0:06:45"}
|
| 276 |
+
{"current_steps": 1380, "total_steps": 1435, "loss": 0.2674, "lr": 1.854176713346867e-07, "epoch": 6.7317073170731705, "percentage": 96.17, "elapsed_time": "2:35:28", "remaining_time": "0:06:11"}
|
| 277 |
+
{"current_steps": 1385, "total_steps": 1435, "loss": 0.2371, "lr": 1.538261289264842e-07, "epoch": 6.7560975609756095, "percentage": 96.52, "elapsed_time": "2:36:01", "remaining_time": "0:05:37"}
|
| 278 |
+
{"current_steps": 1390, "total_steps": 1435, "loss": 0.2609, "lr": 1.2517263327884944e-07, "epoch": 6.780487804878049, "percentage": 96.86, "elapsed_time": "2:36:38", "remaining_time": "0:05:04"}
|
| 279 |
+
{"current_steps": 1395, "total_steps": 1435, "loss": 0.2384, "lr": 9.94614262829785e-08, "epoch": 6.804878048780488, "percentage": 97.21, "elapsed_time": "2:37:11", "remaining_time": "0:04:30"}
|
| 280 |
+
{"current_steps": 1400, "total_steps": 1435, "loss": 0.2448, "lr": 7.669631425079705e-08, "epoch": 6.829268292682927, "percentage": 97.56, "elapsed_time": "2:37:42", "remaining_time": "0:03:56"}
|
| 281 |
+
{"current_steps": 1405, "total_steps": 1435, "loss": 0.235, "lr": 5.6880667351497664e-08, "epoch": 6.853658536585366, "percentage": 97.91, "elapsed_time": "2:39:18", "remaining_time": "0:03:24"}
|
| 282 |
+
{"current_steps": 1410, "total_steps": 1435, "loss": 0.2342, "lr": 4.00174191125946e-08, "epoch": 6.878048780487805, "percentage": 98.26, "elapsed_time": "2:39:54", "remaining_time": "0:02:50"}
|
| 283 |
+
{"current_steps": 1415, "total_steps": 1435, "loss": 0.2368, "lr": 2.6109065985655547e-08, "epoch": 6.902439024390244, "percentage": 98.61, "elapsed_time": "2:40:26", "remaining_time": "0:02:16"}
|
| 284 |
+
{"current_steps": 1420, "total_steps": 1435, "loss": 0.2396, "lr": 1.515766697672172e-08, "epoch": 6.926829268292683, "percentage": 98.95, "elapsed_time": "2:40:54", "remaining_time": "0:01:41"}
|
| 285 |
+
{"current_steps": 1425, "total_steps": 1435, "loss": 0.2342, "lr": 7.16484334148504e-09, "epoch": 6.951219512195122, "percentage": 99.3, "elapsed_time": "2:41:26", "remaining_time": "0:01:07"}
|
| 286 |
+
{"current_steps": 1430, "total_steps": 1435, "loss": 0.2378, "lr": 2.1317783452823315e-09, "epoch": 6.975609756097561, "percentage": 99.65, "elapsed_time": "2:41:58", "remaining_time": "0:00:33"}
|
| 287 |
+
{"current_steps": 1435, "total_steps": 1435, "loss": 0.2521, "lr": 5.921708791767344e-11, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "2:42:30", "remaining_time": "0:00:00"}
|
| 288 |
+
{"current_steps": 1435, "total_steps": 1435, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "2:43:33", "remaining_time": "0:00:00"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,3204 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 7.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 1435,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.024390243902439025,
|
| 14 |
+
"grad_norm": 11.487528759401481,
|
| 15 |
+
"learning_rate": 1.111111111111111e-06,
|
| 16 |
+
"loss": 0.8361,
|
| 17 |
+
"loss_nan_ranks": 0,
|
| 18 |
+
"loss_rank_avg": 0.7365100383758545,
|
| 19 |
+
"step": 5,
|
| 20 |
+
"valid_targets_mean": 3762.9,
|
| 21 |
+
"valid_targets_min": 1347
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.04878048780487805,
|
| 25 |
+
"grad_norm": 9.475522028864606,
|
| 26 |
+
"learning_rate": 2.5e-06,
|
| 27 |
+
"loss": 0.8084,
|
| 28 |
+
"loss_nan_ranks": 0,
|
| 29 |
+
"loss_rank_avg": 0.780247688293457,
|
| 30 |
+
"step": 10,
|
| 31 |
+
"valid_targets_mean": 4102.0,
|
| 32 |
+
"valid_targets_min": 1132
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.07317073170731707,
|
| 36 |
+
"grad_norm": 7.04279574223532,
|
| 37 |
+
"learning_rate": 3.88888888888889e-06,
|
| 38 |
+
"loss": 0.8018,
|
| 39 |
+
"loss_nan_ranks": 0,
|
| 40 |
+
"loss_rank_avg": 0.8029437065124512,
|
| 41 |
+
"step": 15,
|
| 42 |
+
"valid_targets_mean": 2743.9,
|
| 43 |
+
"valid_targets_min": 1037
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 0.0975609756097561,
|
| 47 |
+
"grad_norm": 3.837408273985971,
|
| 48 |
+
"learning_rate": 5.2777777777777785e-06,
|
| 49 |
+
"loss": 0.7365,
|
| 50 |
+
"loss_nan_ranks": 0,
|
| 51 |
+
"loss_rank_avg": 0.7130635380744934,
|
| 52 |
+
"step": 20,
|
| 53 |
+
"valid_targets_mean": 3803.7,
|
| 54 |
+
"valid_targets_min": 1728
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.12195121951219512,
|
| 58 |
+
"grad_norm": 2.623752522634304,
|
| 59 |
+
"learning_rate": 6.666666666666667e-06,
|
| 60 |
+
"loss": 0.6356,
|
| 61 |
+
"loss_nan_ranks": 0,
|
| 62 |
+
"loss_rank_avg": 0.5704323053359985,
|
| 63 |
+
"step": 25,
|
| 64 |
+
"valid_targets_mean": 3090.2,
|
| 65 |
+
"valid_targets_min": 15
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.14634146341463414,
|
| 69 |
+
"grad_norm": 1.5000325065486164,
|
| 70 |
+
"learning_rate": 8.055555555555557e-06,
|
| 71 |
+
"loss": 0.5786,
|
| 72 |
+
"loss_nan_ranks": 0,
|
| 73 |
+
"loss_rank_avg": 0.5754331946372986,
|
| 74 |
+
"step": 30,
|
| 75 |
+
"valid_targets_mean": 2901.2,
|
| 76 |
+
"valid_targets_min": 444
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.17073170731707318,
|
| 80 |
+
"grad_norm": 1.0195672514305119,
|
| 81 |
+
"learning_rate": 9.444444444444445e-06,
|
| 82 |
+
"loss": 0.5669,
|
| 83 |
+
"loss_nan_ranks": 0,
|
| 84 |
+
"loss_rank_avg": 0.5453179478645325,
|
| 85 |
+
"step": 35,
|
| 86 |
+
"valid_targets_mean": 3570.7,
|
| 87 |
+
"valid_targets_min": 1386
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.1951219512195122,
|
| 91 |
+
"grad_norm": 0.7667691926950433,
|
| 92 |
+
"learning_rate": 1.0833333333333334e-05,
|
| 93 |
+
"loss": 0.5178,
|
| 94 |
+
"loss_nan_ranks": 0,
|
| 95 |
+
"loss_rank_avg": 0.4652627110481262,
|
| 96 |
+
"step": 40,
|
| 97 |
+
"valid_targets_mean": 4426.4,
|
| 98 |
+
"valid_targets_min": 1435
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.21951219512195122,
|
| 102 |
+
"grad_norm": 0.8476292747424702,
|
| 103 |
+
"learning_rate": 1.2222222222222224e-05,
|
| 104 |
+
"loss": 0.5122,
|
| 105 |
+
"loss_nan_ranks": 0,
|
| 106 |
+
"loss_rank_avg": 0.4817873239517212,
|
| 107 |
+
"step": 45,
|
| 108 |
+
"valid_targets_mean": 3324.3,
|
| 109 |
+
"valid_targets_min": 973
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.24390243902439024,
|
| 113 |
+
"grad_norm": 0.769487975286158,
|
| 114 |
+
"learning_rate": 1.3611111111111113e-05,
|
| 115 |
+
"loss": 0.5046,
|
| 116 |
+
"loss_nan_ranks": 0,
|
| 117 |
+
"loss_rank_avg": 0.4777624309062958,
|
| 118 |
+
"step": 50,
|
| 119 |
+
"valid_targets_mean": 3475.6,
|
| 120 |
+
"valid_targets_min": 946
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.2682926829268293,
|
| 124 |
+
"grad_norm": 0.8003810670887064,
|
| 125 |
+
"learning_rate": 1.5000000000000002e-05,
|
| 126 |
+
"loss": 0.5042,
|
| 127 |
+
"loss_nan_ranks": 0,
|
| 128 |
+
"loss_rank_avg": 0.4954460859298706,
|
| 129 |
+
"step": 55,
|
| 130 |
+
"valid_targets_mean": 3635.2,
|
| 131 |
+
"valid_targets_min": 1205
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 0.2926829268292683,
|
| 135 |
+
"grad_norm": 0.771135490268948,
|
| 136 |
+
"learning_rate": 1.638888888888889e-05,
|
| 137 |
+
"loss": 0.4964,
|
| 138 |
+
"loss_nan_ranks": 0,
|
| 139 |
+
"loss_rank_avg": 0.4748877286911011,
|
| 140 |
+
"step": 60,
|
| 141 |
+
"valid_targets_mean": 3454.8,
|
| 142 |
+
"valid_targets_min": 841
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.3170731707317073,
|
| 146 |
+
"grad_norm": 0.8492751703287535,
|
| 147 |
+
"learning_rate": 1.7777777777777777e-05,
|
| 148 |
+
"loss": 0.4878,
|
| 149 |
+
"loss_nan_ranks": 0,
|
| 150 |
+
"loss_rank_avg": 0.5011531114578247,
|
| 151 |
+
"step": 65,
|
| 152 |
+
"valid_targets_mean": 2957.6,
|
| 153 |
+
"valid_targets_min": 582
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.34146341463414637,
|
| 157 |
+
"grad_norm": 0.7716257577706961,
|
| 158 |
+
"learning_rate": 1.916666666666667e-05,
|
| 159 |
+
"loss": 0.4473,
|
| 160 |
+
"loss_nan_ranks": 0,
|
| 161 |
+
"loss_rank_avg": 0.47079670429229736,
|
| 162 |
+
"step": 70,
|
| 163 |
+
"valid_targets_mean": 3449.3,
|
| 164 |
+
"valid_targets_min": 853
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.36585365853658536,
|
| 168 |
+
"grad_norm": 0.8434747864822957,
|
| 169 |
+
"learning_rate": 2.0555555555555555e-05,
|
| 170 |
+
"loss": 0.4557,
|
| 171 |
+
"loss_nan_ranks": 0,
|
| 172 |
+
"loss_rank_avg": 0.43814384937286377,
|
| 173 |
+
"step": 75,
|
| 174 |
+
"valid_targets_mean": 3228.6,
|
| 175 |
+
"valid_targets_min": 414
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 0.3902439024390244,
|
| 179 |
+
"grad_norm": 0.7458155064497034,
|
| 180 |
+
"learning_rate": 2.194444444444445e-05,
|
| 181 |
+
"loss": 0.46,
|
| 182 |
+
"loss_nan_ranks": 0,
|
| 183 |
+
"loss_rank_avg": 0.44705730676651,
|
| 184 |
+
"step": 80,
|
| 185 |
+
"valid_targets_mean": 3524.7,
|
| 186 |
+
"valid_targets_min": 875
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.4146341463414634,
|
| 190 |
+
"grad_norm": 0.8049876326023591,
|
| 191 |
+
"learning_rate": 2.3333333333333336e-05,
|
| 192 |
+
"loss": 0.4682,
|
| 193 |
+
"loss_nan_ranks": 0,
|
| 194 |
+
"loss_rank_avg": 0.5294123888015747,
|
| 195 |
+
"step": 85,
|
| 196 |
+
"valid_targets_mean": 3489.1,
|
| 197 |
+
"valid_targets_min": 899
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 0.43902439024390244,
|
| 201 |
+
"grad_norm": 0.6716168920810122,
|
| 202 |
+
"learning_rate": 2.4722222222222226e-05,
|
| 203 |
+
"loss": 0.4455,
|
| 204 |
+
"loss_nan_ranks": 0,
|
| 205 |
+
"loss_rank_avg": 0.4092828929424286,
|
| 206 |
+
"step": 90,
|
| 207 |
+
"valid_targets_mean": 3573.4,
|
| 208 |
+
"valid_targets_min": 979
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 0.4634146341463415,
|
| 212 |
+
"grad_norm": 0.7612668390820156,
|
| 213 |
+
"learning_rate": 2.6111111111111114e-05,
|
| 214 |
+
"loss": 0.4531,
|
| 215 |
+
"loss_nan_ranks": 0,
|
| 216 |
+
"loss_rank_avg": 0.478001207113266,
|
| 217 |
+
"step": 95,
|
| 218 |
+
"valid_targets_mean": 3585.0,
|
| 219 |
+
"valid_targets_min": 878
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.4878048780487805,
|
| 223 |
+
"grad_norm": 0.8720193134806395,
|
| 224 |
+
"learning_rate": 2.75e-05,
|
| 225 |
+
"loss": 0.4494,
|
| 226 |
+
"loss_nan_ranks": 0,
|
| 227 |
+
"loss_rank_avg": 0.4325084090232849,
|
| 228 |
+
"step": 100,
|
| 229 |
+
"valid_targets_mean": 2660.9,
|
| 230 |
+
"valid_targets_min": 15
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.5121951219512195,
|
| 234 |
+
"grad_norm": 0.9243802248475099,
|
| 235 |
+
"learning_rate": 2.888888888888889e-05,
|
| 236 |
+
"loss": 0.418,
|
| 237 |
+
"loss_nan_ranks": 0,
|
| 238 |
+
"loss_rank_avg": 0.4396073818206787,
|
| 239 |
+
"step": 105,
|
| 240 |
+
"valid_targets_mean": 2434.6,
|
| 241 |
+
"valid_targets_min": 772
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.5365853658536586,
|
| 245 |
+
"grad_norm": 0.7410305143235792,
|
| 246 |
+
"learning_rate": 3.027777777777778e-05,
|
| 247 |
+
"loss": 0.4421,
|
| 248 |
+
"loss_nan_ranks": 0,
|
| 249 |
+
"loss_rank_avg": 0.39146214723587036,
|
| 250 |
+
"step": 110,
|
| 251 |
+
"valid_targets_mean": 3399.3,
|
| 252 |
+
"valid_targets_min": 265
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.5609756097560976,
|
| 256 |
+
"grad_norm": 0.9932166784633583,
|
| 257 |
+
"learning_rate": 3.1666666666666666e-05,
|
| 258 |
+
"loss": 0.4504,
|
| 259 |
+
"loss_nan_ranks": 0,
|
| 260 |
+
"loss_rank_avg": 0.44398099184036255,
|
| 261 |
+
"step": 115,
|
| 262 |
+
"valid_targets_mean": 3370.4,
|
| 263 |
+
"valid_targets_min": 993
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 0.5853658536585366,
|
| 267 |
+
"grad_norm": 0.7226380775954716,
|
| 268 |
+
"learning_rate": 3.3055555555555553e-05,
|
| 269 |
+
"loss": 0.4249,
|
| 270 |
+
"loss_nan_ranks": 0,
|
| 271 |
+
"loss_rank_avg": 0.3628934323787689,
|
| 272 |
+
"step": 120,
|
| 273 |
+
"valid_targets_mean": 3499.3,
|
| 274 |
+
"valid_targets_min": 477
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.6097560975609756,
|
| 278 |
+
"grad_norm": 0.8823777151936405,
|
| 279 |
+
"learning_rate": 3.444444444444445e-05,
|
| 280 |
+
"loss": 0.4417,
|
| 281 |
+
"loss_nan_ranks": 0,
|
| 282 |
+
"loss_rank_avg": 0.41109269857406616,
|
| 283 |
+
"step": 125,
|
| 284 |
+
"valid_targets_mean": 2774.8,
|
| 285 |
+
"valid_targets_min": 15
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.6341463414634146,
|
| 289 |
+
"grad_norm": 0.7500022204056533,
|
| 290 |
+
"learning_rate": 3.5833333333333335e-05,
|
| 291 |
+
"loss": 0.4383,
|
| 292 |
+
"loss_nan_ranks": 0,
|
| 293 |
+
"loss_rank_avg": 0.4249718189239502,
|
| 294 |
+
"step": 130,
|
| 295 |
+
"valid_targets_mean": 3250.6,
|
| 296 |
+
"valid_targets_min": 1490
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.6585365853658537,
|
| 300 |
+
"grad_norm": 0.7608537033688073,
|
| 301 |
+
"learning_rate": 3.722222222222223e-05,
|
| 302 |
+
"loss": 0.4266,
|
| 303 |
+
"loss_nan_ranks": 0,
|
| 304 |
+
"loss_rank_avg": 0.41326218843460083,
|
| 305 |
+
"step": 135,
|
| 306 |
+
"valid_targets_mean": 3088.5,
|
| 307 |
+
"valid_targets_min": 539
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 0.6829268292682927,
|
| 311 |
+
"grad_norm": 0.8309125080829076,
|
| 312 |
+
"learning_rate": 3.8611111111111116e-05,
|
| 313 |
+
"loss": 0.4089,
|
| 314 |
+
"loss_nan_ranks": 0,
|
| 315 |
+
"loss_rank_avg": 0.4202869236469269,
|
| 316 |
+
"step": 140,
|
| 317 |
+
"valid_targets_mean": 3053.9,
|
| 318 |
+
"valid_targets_min": 15
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.7073170731707317,
|
| 322 |
+
"grad_norm": 0.7091166521276581,
|
| 323 |
+
"learning_rate": 4e-05,
|
| 324 |
+
"loss": 0.4009,
|
| 325 |
+
"loss_nan_ranks": 0,
|
| 326 |
+
"loss_rank_avg": 0.3712766766548157,
|
| 327 |
+
"step": 145,
|
| 328 |
+
"valid_targets_mean": 4122.2,
|
| 329 |
+
"valid_targets_min": 1176
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 0.7317073170731707,
|
| 333 |
+
"grad_norm": 0.7272991052058403,
|
| 334 |
+
"learning_rate": 3.999851959033532e-05,
|
| 335 |
+
"loss": 0.4064,
|
| 336 |
+
"loss_nan_ranks": 0,
|
| 337 |
+
"loss_rank_avg": 0.4357445240020752,
|
| 338 |
+
"step": 150,
|
| 339 |
+
"valid_targets_mean": 3601.1,
|
| 340 |
+
"valid_targets_min": 886
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 0.7560975609756098,
|
| 344 |
+
"grad_norm": 0.7530784025869104,
|
| 345 |
+
"learning_rate": 3.999407858050255e-05,
|
| 346 |
+
"loss": 0.4104,
|
| 347 |
+
"loss_nan_ranks": 0,
|
| 348 |
+
"loss_rank_avg": 0.4047582745552063,
|
| 349 |
+
"step": 155,
|
| 350 |
+
"valid_targets_mean": 2777.0,
|
| 351 |
+
"valid_targets_min": 976
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.7804878048780488,
|
| 355 |
+
"grad_norm": 0.5809719279424417,
|
| 356 |
+
"learning_rate": 3.998667762795307e-05,
|
| 357 |
+
"loss": 0.4061,
|
| 358 |
+
"loss_nan_ranks": 0,
|
| 359 |
+
"loss_rank_avg": 0.3885638117790222,
|
| 360 |
+
"step": 160,
|
| 361 |
+
"valid_targets_mean": 5063.3,
|
| 362 |
+
"valid_targets_min": 1079
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.8048780487804879,
|
| 366 |
+
"grad_norm": 0.7354864856165856,
|
| 367 |
+
"learning_rate": 3.9976317828331075e-05,
|
| 368 |
+
"loss": 0.4108,
|
| 369 |
+
"loss_nan_ranks": 0,
|
| 370 |
+
"loss_rank_avg": 0.4471714496612549,
|
| 371 |
+
"step": 165,
|
| 372 |
+
"valid_targets_mean": 3957.6,
|
| 373 |
+
"valid_targets_min": 470
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.8292682926829268,
|
| 377 |
+
"grad_norm": 0.8186760526901421,
|
| 378 |
+
"learning_rate": 3.9963000715311284e-05,
|
| 379 |
+
"loss": 0.4148,
|
| 380 |
+
"loss_nan_ranks": 0,
|
| 381 |
+
"loss_rank_avg": 0.47168421745300293,
|
| 382 |
+
"step": 170,
|
| 383 |
+
"valid_targets_mean": 2868.2,
|
| 384 |
+
"valid_targets_min": 916
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 0.8536585365853658,
|
| 388 |
+
"grad_norm": 0.8249337383629396,
|
| 389 |
+
"learning_rate": 3.9946728260372e-05,
|
| 390 |
+
"loss": 0.4097,
|
| 391 |
+
"loss_nan_ranks": 0,
|
| 392 |
+
"loss_rank_avg": 0.4015315771102905,
|
| 393 |
+
"step": 175,
|
| 394 |
+
"valid_targets_mean": 3402.2,
|
| 395 |
+
"valid_targets_min": 475
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.8780487804878049,
|
| 399 |
+
"grad_norm": 0.802745972860082,
|
| 400 |
+
"learning_rate": 3.992750287250316e-05,
|
| 401 |
+
"loss": 0.4262,
|
| 402 |
+
"loss_nan_ranks": 0,
|
| 403 |
+
"loss_rank_avg": 0.46255892515182495,
|
| 404 |
+
"step": 180,
|
| 405 |
+
"valid_targets_mean": 3201.5,
|
| 406 |
+
"valid_targets_min": 467
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 0.9024390243902439,
|
| 410 |
+
"grad_norm": 0.8369027610414674,
|
| 411 |
+
"learning_rate": 3.9905327397849776e-05,
|
| 412 |
+
"loss": 0.4143,
|
| 413 |
+
"loss_nan_ranks": 0,
|
| 414 |
+
"loss_rank_avg": 0.438213050365448,
|
| 415 |
+
"step": 185,
|
| 416 |
+
"valid_targets_mean": 2837.9,
|
| 417 |
+
"valid_targets_min": 1004
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.926829268292683,
|
| 421 |
+
"grad_norm": 0.7620682825729357,
|
| 422 |
+
"learning_rate": 3.988020511929055e-05,
|
| 423 |
+
"loss": 0.4068,
|
| 424 |
+
"loss_nan_ranks": 0,
|
| 425 |
+
"loss_rank_avg": 0.3820480406284332,
|
| 426 |
+
"step": 190,
|
| 427 |
+
"valid_targets_mean": 3607.6,
|
| 428 |
+
"valid_targets_min": 15
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 0.9512195121951219,
|
| 432 |
+
"grad_norm": 0.8231019760594912,
|
| 433 |
+
"learning_rate": 3.985213975595188e-05,
|
| 434 |
+
"loss": 0.4169,
|
| 435 |
+
"loss_nan_ranks": 0,
|
| 436 |
+
"loss_rank_avg": 0.4414719045162201,
|
| 437 |
+
"step": 195,
|
| 438 |
+
"valid_targets_mean": 2511.9,
|
| 439 |
+
"valid_targets_min": 363
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 0.975609756097561,
|
| 443 |
+
"grad_norm": 0.7380667621345177,
|
| 444 |
+
"learning_rate": 3.982113546265727e-05,
|
| 445 |
+
"loss": 0.4196,
|
| 446 |
+
"loss_nan_ranks": 0,
|
| 447 |
+
"loss_rank_avg": 0.4193473160266876,
|
| 448 |
+
"step": 200,
|
| 449 |
+
"valid_targets_mean": 3748.1,
|
| 450 |
+
"valid_targets_min": 692
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 1.0,
|
| 454 |
+
"grad_norm": 0.7458650521840304,
|
| 455 |
+
"learning_rate": 3.978719682931227e-05,
|
| 456 |
+
"loss": 0.3994,
|
| 457 |
+
"loss_nan_ranks": 0,
|
| 458 |
+
"loss_rank_avg": 0.3914061188697815,
|
| 459 |
+
"step": 205,
|
| 460 |
+
"valid_targets_mean": 3714.5,
|
| 461 |
+
"valid_targets_min": 1568
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 1.024390243902439,
|
| 465 |
+
"grad_norm": 0.8139396617003434,
|
| 466 |
+
"learning_rate": 3.9750328880224964e-05,
|
| 467 |
+
"loss": 0.3843,
|
| 468 |
+
"loss_nan_ranks": 0,
|
| 469 |
+
"loss_rank_avg": 0.3921425938606262,
|
| 470 |
+
"step": 210,
|
| 471 |
+
"valid_targets_mean": 2894.5,
|
| 472 |
+
"valid_targets_min": 1142
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 1.048780487804878,
|
| 476 |
+
"grad_norm": 0.920561844317153,
|
| 477 |
+
"learning_rate": 3.9710537073362154e-05,
|
| 478 |
+
"loss": 0.3676,
|
| 479 |
+
"loss_nan_ranks": 0,
|
| 480 |
+
"loss_rank_avg": 0.37253957986831665,
|
| 481 |
+
"step": 215,
|
| 482 |
+
"valid_targets_mean": 2493.4,
|
| 483 |
+
"valid_targets_min": 1141
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 1.0731707317073171,
|
| 487 |
+
"grad_norm": 0.8730069289304332,
|
| 488 |
+
"learning_rate": 3.9667827299541405e-05,
|
| 489 |
+
"loss": 0.376,
|
| 490 |
+
"loss_nan_ranks": 0,
|
| 491 |
+
"loss_rank_avg": 0.3857506215572357,
|
| 492 |
+
"step": 220,
|
| 493 |
+
"valid_targets_mean": 2558.9,
|
| 494 |
+
"valid_targets_min": 848
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 1.0975609756097562,
|
| 498 |
+
"grad_norm": 0.6229292309392103,
|
| 499 |
+
"learning_rate": 3.962220588155889e-05,
|
| 500 |
+
"loss": 0.3914,
|
| 501 |
+
"loss_nan_ranks": 0,
|
| 502 |
+
"loss_rank_avg": 0.3528486490249634,
|
| 503 |
+
"step": 225,
|
| 504 |
+
"valid_targets_mean": 4876.5,
|
| 505 |
+
"valid_targets_min": 15
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 1.1219512195121952,
|
| 509 |
+
"grad_norm": 1.0416514376225245,
|
| 510 |
+
"learning_rate": 3.957367957325344e-05,
|
| 511 |
+
"loss": 0.3891,
|
| 512 |
+
"loss_nan_ranks": 0,
|
| 513 |
+
"loss_rank_avg": 0.40384507179260254,
|
| 514 |
+
"step": 230,
|
| 515 |
+
"valid_targets_mean": 2797.6,
|
| 516 |
+
"valid_targets_min": 654
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 1.146341463414634,
|
| 520 |
+
"grad_norm": 0.8974767692382145,
|
| 521 |
+
"learning_rate": 3.952225555850662e-05,
|
| 522 |
+
"loss": 0.3805,
|
| 523 |
+
"loss_nan_ranks": 0,
|
| 524 |
+
"loss_rank_avg": 0.41643357276916504,
|
| 525 |
+
"step": 235,
|
| 526 |
+
"valid_targets_mean": 3033.7,
|
| 527 |
+
"valid_targets_min": 1141
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 1.170731707317073,
|
| 531 |
+
"grad_norm": 0.6882577926862582,
|
| 532 |
+
"learning_rate": 3.9467941450179276e-05,
|
| 533 |
+
"loss": 0.4021,
|
| 534 |
+
"loss_nan_ranks": 0,
|
| 535 |
+
"loss_rank_avg": 0.34199321269989014,
|
| 536 |
+
"step": 240,
|
| 537 |
+
"valid_targets_mean": 3899.6,
|
| 538 |
+
"valid_targets_min": 947
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 1.1951219512195121,
|
| 542 |
+
"grad_norm": 0.7598060326395756,
|
| 543 |
+
"learning_rate": 3.94107452889845e-05,
|
| 544 |
+
"loss": 0.3768,
|
| 545 |
+
"loss_nan_ranks": 0,
|
| 546 |
+
"loss_rank_avg": 0.3925563097000122,
|
| 547 |
+
"step": 245,
|
| 548 |
+
"valid_targets_mean": 3416.5,
|
| 549 |
+
"valid_targets_min": 976
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.2195121951219512,
|
| 553 |
+
"grad_norm": 0.7953917356483156,
|
| 554 |
+
"learning_rate": 3.9350675542297273e-05,
|
| 555 |
+
"loss": 0.3985,
|
| 556 |
+
"loss_nan_ranks": 0,
|
| 557 |
+
"loss_rank_avg": 0.3889926075935364,
|
| 558 |
+
"step": 250,
|
| 559 |
+
"valid_targets_mean": 3197.0,
|
| 560 |
+
"valid_targets_min": 960
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 1.2439024390243902,
|
| 564 |
+
"grad_norm": 0.8560153490249861,
|
| 565 |
+
"learning_rate": 3.9287741102900956e-05,
|
| 566 |
+
"loss": 0.3822,
|
| 567 |
+
"loss_nan_ranks": 0,
|
| 568 |
+
"loss_rank_avg": 0.3994605541229248,
|
| 569 |
+
"step": 255,
|
| 570 |
+
"valid_targets_mean": 2937.1,
|
| 571 |
+
"valid_targets_min": 576
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 1.2682926829268293,
|
| 575 |
+
"grad_norm": 0.7105463458999842,
|
| 576 |
+
"learning_rate": 3.922195128767077e-05,
|
| 577 |
+
"loss": 0.3531,
|
| 578 |
+
"loss_nan_ranks": 0,
|
| 579 |
+
"loss_rank_avg": 0.32579752802848816,
|
| 580 |
+
"step": 260,
|
| 581 |
+
"valid_targets_mean": 3560.3,
|
| 582 |
+
"valid_targets_min": 363
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 1.2926829268292683,
|
| 586 |
+
"grad_norm": 0.7542653042504447,
|
| 587 |
+
"learning_rate": 3.915331583619455e-05,
|
| 588 |
+
"loss": 0.3768,
|
| 589 |
+
"loss_nan_ranks": 0,
|
| 590 |
+
"loss_rank_avg": 0.3614310324192047,
|
| 591 |
+
"step": 265,
|
| 592 |
+
"valid_targets_mean": 3289.0,
|
| 593 |
+
"valid_targets_min": 849
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 1.3170731707317074,
|
| 597 |
+
"grad_norm": 0.8497951456582137,
|
| 598 |
+
"learning_rate": 3.908184490933087e-05,
|
| 599 |
+
"loss": 0.3667,
|
| 600 |
+
"loss_nan_ranks": 0,
|
| 601 |
+
"loss_rank_avg": 0.3782227337360382,
|
| 602 |
+
"step": 270,
|
| 603 |
+
"valid_targets_mean": 2581.6,
|
| 604 |
+
"valid_targets_min": 696
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 1.3414634146341464,
|
| 608 |
+
"grad_norm": 0.7719791862885925,
|
| 609 |
+
"learning_rate": 3.90075490877048e-05,
|
| 610 |
+
"loss": 0.3852,
|
| 611 |
+
"loss_nan_ranks": 0,
|
| 612 |
+
"loss_rank_avg": 0.37844318151474,
|
| 613 |
+
"step": 275,
|
| 614 |
+
"valid_targets_mean": 3066.4,
|
| 615 |
+
"valid_targets_min": 15
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 1.3658536585365852,
|
| 619 |
+
"grad_norm": 0.7223338146517535,
|
| 620 |
+
"learning_rate": 3.893043937014161e-05,
|
| 621 |
+
"loss": 0.3607,
|
| 622 |
+
"loss_nan_ranks": 0,
|
| 623 |
+
"loss_rank_avg": 0.36418038606643677,
|
| 624 |
+
"step": 280,
|
| 625 |
+
"valid_targets_mean": 3117.9,
|
| 626 |
+
"valid_targets_min": 940
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.3902439024390243,
|
| 630 |
+
"grad_norm": 0.7019756644424542,
|
| 631 |
+
"learning_rate": 3.885052717203839e-05,
|
| 632 |
+
"loss": 0.3789,
|
| 633 |
+
"loss_nan_ranks": 0,
|
| 634 |
+
"loss_rank_avg": 0.39389437437057495,
|
| 635 |
+
"step": 285,
|
| 636 |
+
"valid_targets_mean": 3810.8,
|
| 637 |
+
"valid_targets_min": 989
|
| 638 |
+
},
|
| 639 |
+
{
|
| 640 |
+
"epoch": 1.4146341463414633,
|
| 641 |
+
"grad_norm": 0.7126900107048149,
|
| 642 |
+
"learning_rate": 3.876782432367419e-05,
|
| 643 |
+
"loss": 0.3593,
|
| 644 |
+
"loss_nan_ranks": 0,
|
| 645 |
+
"loss_rank_avg": 0.3678337335586548,
|
| 646 |
+
"step": 290,
|
| 647 |
+
"valid_targets_mean": 3401.9,
|
| 648 |
+
"valid_targets_min": 417
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 1.4390243902439024,
|
| 652 |
+
"grad_norm": 0.6043008862137972,
|
| 653 |
+
"learning_rate": 3.86823430684586e-05,
|
| 654 |
+
"loss": 0.3787,
|
| 655 |
+
"loss_nan_ranks": 0,
|
| 656 |
+
"loss_rank_avg": 0.3658294081687927,
|
| 657 |
+
"step": 295,
|
| 658 |
+
"valid_targets_mean": 4910.9,
|
| 659 |
+
"valid_targets_min": 1152
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 1.4634146341463414,
|
| 663 |
+
"grad_norm": 0.9549115770574411,
|
| 664 |
+
"learning_rate": 3.859409606111927e-05,
|
| 665 |
+
"loss": 0.3935,
|
| 666 |
+
"loss_nan_ranks": 0,
|
| 667 |
+
"loss_rank_avg": 0.41088318824768066,
|
| 668 |
+
"step": 300,
|
| 669 |
+
"valid_targets_mean": 3028.8,
|
| 670 |
+
"valid_targets_min": 288
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 1.4878048780487805,
|
| 674 |
+
"grad_norm": 0.8424403005867168,
|
| 675 |
+
"learning_rate": 3.850309636582844e-05,
|
| 676 |
+
"loss": 0.3699,
|
| 677 |
+
"loss_nan_ranks": 0,
|
| 678 |
+
"loss_rank_avg": 0.34833067655563354,
|
| 679 |
+
"step": 305,
|
| 680 |
+
"valid_targets_mean": 4002.8,
|
| 681 |
+
"valid_targets_min": 1645
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 1.5121951219512195,
|
| 685 |
+
"grad_norm": 0.6306861230305417,
|
| 686 |
+
"learning_rate": 3.8409357454268954e-05,
|
| 687 |
+
"loss": 0.3777,
|
| 688 |
+
"loss_nan_ranks": 0,
|
| 689 |
+
"loss_rank_avg": 0.37073996663093567,
|
| 690 |
+
"step": 310,
|
| 691 |
+
"valid_targets_mean": 5012.4,
|
| 692 |
+
"valid_targets_min": 1119
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 1.5365853658536586,
|
| 696 |
+
"grad_norm": 0.7155539048246429,
|
| 697 |
+
"learning_rate": 3.831289320363988e-05,
|
| 698 |
+
"loss": 0.3883,
|
| 699 |
+
"loss_nan_ranks": 0,
|
| 700 |
+
"loss_rank_avg": 0.37950462102890015,
|
| 701 |
+
"step": 315,
|
| 702 |
+
"valid_targets_mean": 4102.6,
|
| 703 |
+
"valid_targets_min": 265
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 1.5609756097560976,
|
| 707 |
+
"grad_norm": 0.7974667376832275,
|
| 708 |
+
"learning_rate": 3.821371789460211e-05,
|
| 709 |
+
"loss": 0.3614,
|
| 710 |
+
"loss_nan_ranks": 0,
|
| 711 |
+
"loss_rank_avg": 0.36880871653556824,
|
| 712 |
+
"step": 320,
|
| 713 |
+
"valid_targets_mean": 3079.6,
|
| 714 |
+
"valid_targets_min": 959
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 1.5853658536585367,
|
| 718 |
+
"grad_norm": 0.8043178482245835,
|
| 719 |
+
"learning_rate": 3.8111846209164245e-05,
|
| 720 |
+
"loss": 0.3748,
|
| 721 |
+
"loss_nan_ranks": 0,
|
| 722 |
+
"loss_rank_avg": 0.40152832865715027,
|
| 723 |
+
"step": 325,
|
| 724 |
+
"valid_targets_mean": 2942.4,
|
| 725 |
+
"valid_targets_min": 1052
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 1.6097560975609757,
|
| 729 |
+
"grad_norm": 0.7724860293036107,
|
| 730 |
+
"learning_rate": 3.800729322850905e-05,
|
| 731 |
+
"loss": 0.3763,
|
| 732 |
+
"loss_nan_ranks": 0,
|
| 733 |
+
"loss_rank_avg": 0.39380210638046265,
|
| 734 |
+
"step": 330,
|
| 735 |
+
"valid_targets_mean": 3036.5,
|
| 736 |
+
"valid_targets_min": 886
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 1.6341463414634148,
|
| 740 |
+
"grad_norm": 0.8482463253190202,
|
| 741 |
+
"learning_rate": 3.790007443076083e-05,
|
| 742 |
+
"loss": 0.3838,
|
| 743 |
+
"loss_nan_ranks": 0,
|
| 744 |
+
"loss_rank_avg": 0.3798723816871643,
|
| 745 |
+
"step": 335,
|
| 746 |
+
"valid_targets_mean": 3018.6,
|
| 747 |
+
"valid_targets_min": 15
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 1.6585365853658538,
|
| 751 |
+
"grad_norm": 0.8833799570209917,
|
| 752 |
+
"learning_rate": 3.779020568869402e-05,
|
| 753 |
+
"loss": 0.3559,
|
| 754 |
+
"loss_nan_ranks": 0,
|
| 755 |
+
"loss_rank_avg": 0.36824825406074524,
|
| 756 |
+
"step": 340,
|
| 757 |
+
"valid_targets_mean": 2802.5,
|
| 758 |
+
"valid_targets_min": 711
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 1.6829268292682928,
|
| 762 |
+
"grad_norm": 0.6829517524240788,
|
| 763 |
+
"learning_rate": 3.767770326738339e-05,
|
| 764 |
+
"loss": 0.3816,
|
| 765 |
+
"loss_nan_ranks": 0,
|
| 766 |
+
"loss_rank_avg": 0.3737407326698303,
|
| 767 |
+
"step": 345,
|
| 768 |
+
"valid_targets_mean": 4252.8,
|
| 769 |
+
"valid_targets_min": 876
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 1.7073170731707317,
|
| 773 |
+
"grad_norm": 0.6903358415372074,
|
| 774 |
+
"learning_rate": 3.7562583821796114e-05,
|
| 775 |
+
"loss": 0.3735,
|
| 776 |
+
"loss_nan_ranks": 0,
|
| 777 |
+
"loss_rank_avg": 0.36414116621017456,
|
| 778 |
+
"step": 350,
|
| 779 |
+
"valid_targets_mean": 3665.8,
|
| 780 |
+
"valid_targets_min": 660
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 1.7317073170731707,
|
| 784 |
+
"grad_norm": 0.6233603443152537,
|
| 785 |
+
"learning_rate": 3.7444864394326186e-05,
|
| 786 |
+
"loss": 0.3607,
|
| 787 |
+
"loss_nan_ranks": 0,
|
| 788 |
+
"loss_rank_avg": 0.3237985670566559,
|
| 789 |
+
"step": 355,
|
| 790 |
+
"valid_targets_mean": 4911.9,
|
| 791 |
+
"valid_targets_min": 711
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 1.7560975609756098,
|
| 795 |
+
"grad_norm": 0.9214069599336896,
|
| 796 |
+
"learning_rate": 3.732456241227141e-05,
|
| 797 |
+
"loss": 0.3591,
|
| 798 |
+
"loss_nan_ranks": 0,
|
| 799 |
+
"loss_rank_avg": 0.3726973533630371,
|
| 800 |
+
"step": 360,
|
| 801 |
+
"valid_targets_mean": 3513.8,
|
| 802 |
+
"valid_targets_min": 1456
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 1.7804878048780488,
|
| 806 |
+
"grad_norm": 0.7500860882422733,
|
| 807 |
+
"learning_rate": 3.7201695685253476e-05,
|
| 808 |
+
"loss": 0.3896,
|
| 809 |
+
"loss_nan_ranks": 0,
|
| 810 |
+
"loss_rank_avg": 0.3697166442871094,
|
| 811 |
+
"step": 365,
|
| 812 |
+
"valid_targets_mean": 3385.0,
|
| 813 |
+
"valid_targets_min": 825
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 1.8048780487804879,
|
| 817 |
+
"grad_norm": 0.8780041171925682,
|
| 818 |
+
"learning_rate": 3.7076282402581404e-05,
|
| 819 |
+
"loss": 0.3927,
|
| 820 |
+
"loss_nan_ranks": 0,
|
| 821 |
+
"loss_rank_avg": 0.41772669553756714,
|
| 822 |
+
"step": 370,
|
| 823 |
+
"valid_targets_mean": 2651.1,
|
| 824 |
+
"valid_targets_min": 1157
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 1.8292682926829267,
|
| 828 |
+
"grad_norm": 0.7547594930022417,
|
| 829 |
+
"learning_rate": 3.694834113055877e-05,
|
| 830 |
+
"loss": 0.3652,
|
| 831 |
+
"loss_nan_ranks": 0,
|
| 832 |
+
"loss_rank_avg": 0.3808954358100891,
|
| 833 |
+
"step": 375,
|
| 834 |
+
"valid_targets_mean": 3378.3,
|
| 835 |
+
"valid_targets_min": 865
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 1.8536585365853657,
|
| 839 |
+
"grad_norm": 1.062524119548778,
|
| 840 |
+
"learning_rate": 3.681789080973514e-05,
|
| 841 |
+
"loss": 0.3603,
|
| 842 |
+
"loss_nan_ranks": 0,
|
| 843 |
+
"loss_rank_avg": 0.37782055139541626,
|
| 844 |
+
"step": 380,
|
| 845 |
+
"valid_targets_mean": 2781.2,
|
| 846 |
+
"valid_targets_min": 448
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 1.8780487804878048,
|
| 850 |
+
"grad_norm": 0.7747602704814769,
|
| 851 |
+
"learning_rate": 3.668495075210207e-05,
|
| 852 |
+
"loss": 0.3593,
|
| 853 |
+
"loss_nan_ranks": 0,
|
| 854 |
+
"loss_rank_avg": 0.3768714666366577,
|
| 855 |
+
"step": 385,
|
| 856 |
+
"valid_targets_mean": 3837.8,
|
| 857 |
+
"valid_targets_min": 1132
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 1.9024390243902438,
|
| 861 |
+
"grad_norm": 0.6379661220392324,
|
| 862 |
+
"learning_rate": 3.654954063823419e-05,
|
| 863 |
+
"loss": 0.3631,
|
| 864 |
+
"loss_nan_ranks": 0,
|
| 865 |
+
"loss_rank_avg": 0.3241764307022095,
|
| 866 |
+
"step": 390,
|
| 867 |
+
"valid_targets_mean": 3892.8,
|
| 868 |
+
"valid_targets_min": 1626
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 1.9268292682926829,
|
| 872 |
+
"grad_norm": 0.8306626736395537,
|
| 873 |
+
"learning_rate": 3.641168051437562e-05,
|
| 874 |
+
"loss": 0.3838,
|
| 875 |
+
"loss_nan_ranks": 0,
|
| 876 |
+
"loss_rank_avg": 0.3675532937049866,
|
| 877 |
+
"step": 395,
|
| 878 |
+
"valid_targets_mean": 3192.4,
|
| 879 |
+
"valid_targets_min": 916
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 1.951219512195122,
|
| 883 |
+
"grad_norm": 0.6795328481586967,
|
| 884 |
+
"learning_rate": 3.627139078947233e-05,
|
| 885 |
+
"loss": 0.3785,
|
| 886 |
+
"loss_nan_ranks": 0,
|
| 887 |
+
"loss_rank_avg": 0.3840370774269104,
|
| 888 |
+
"step": 400,
|
| 889 |
+
"valid_targets_mean": 4188.1,
|
| 890 |
+
"valid_targets_min": 1483
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 1.975609756097561,
|
| 894 |
+
"grad_norm": 0.6384377969297063,
|
| 895 |
+
"learning_rate": 3.6128692232150775e-05,
|
| 896 |
+
"loss": 0.3547,
|
| 897 |
+
"loss_nan_ranks": 0,
|
| 898 |
+
"loss_rank_avg": 0.3258434534072876,
|
| 899 |
+
"step": 405,
|
| 900 |
+
"valid_targets_mean": 3781.2,
|
| 901 |
+
"valid_targets_min": 492
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 2.0,
|
| 905 |
+
"grad_norm": 0.6449462111499721,
|
| 906 |
+
"learning_rate": 3.598360596764331e-05,
|
| 907 |
+
"loss": 0.3574,
|
| 908 |
+
"loss_nan_ranks": 0,
|
| 909 |
+
"loss_rank_avg": 0.3393850326538086,
|
| 910 |
+
"step": 410,
|
| 911 |
+
"valid_targets_mean": 4006.3,
|
| 912 |
+
"valid_targets_min": 719
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 2.024390243902439,
|
| 916 |
+
"grad_norm": 0.8321218841560414,
|
| 917 |
+
"learning_rate": 3.583615347466075e-05,
|
| 918 |
+
"loss": 0.346,
|
| 919 |
+
"loss_nan_ranks": 0,
|
| 920 |
+
"loss_rank_avg": 0.3338969945907593,
|
| 921 |
+
"step": 415,
|
| 922 |
+
"valid_targets_mean": 2771.9,
|
| 923 |
+
"valid_targets_min": 928
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 2.048780487804878,
|
| 927 |
+
"grad_norm": 0.7320573520455086,
|
| 928 |
+
"learning_rate": 3.568635658221266e-05,
|
| 929 |
+
"loss": 0.3131,
|
| 930 |
+
"loss_nan_ranks": 0,
|
| 931 |
+
"loss_rank_avg": 0.31023988127708435,
|
| 932 |
+
"step": 420,
|
| 933 |
+
"valid_targets_mean": 3438.1,
|
| 934 |
+
"valid_targets_min": 1040
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 2.073170731707317,
|
| 938 |
+
"grad_norm": 0.8445720664474741,
|
| 939 |
+
"learning_rate": 3.553423746637577e-05,
|
| 940 |
+
"loss": 0.3289,
|
| 941 |
+
"loss_nan_ranks": 0,
|
| 942 |
+
"loss_rank_avg": 0.3350527584552765,
|
| 943 |
+
"step": 425,
|
| 944 |
+
"valid_targets_mean": 2859.0,
|
| 945 |
+
"valid_targets_min": 15
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 2.097560975609756,
|
| 949 |
+
"grad_norm": 0.9479920623957632,
|
| 950 |
+
"learning_rate": 3.537981864701101e-05,
|
| 951 |
+
"loss": 0.3556,
|
| 952 |
+
"loss_nan_ranks": 0,
|
| 953 |
+
"loss_rank_avg": 0.39427098631858826,
|
| 954 |
+
"step": 430,
|
| 955 |
+
"valid_targets_mean": 2811.9,
|
| 956 |
+
"valid_targets_min": 760
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 2.1219512195121952,
|
| 960 |
+
"grad_norm": 0.740296255448551,
|
| 961 |
+
"learning_rate": 3.5223122984429645e-05,
|
| 962 |
+
"loss": 0.3533,
|
| 963 |
+
"loss_nan_ranks": 0,
|
| 964 |
+
"loss_rank_avg": 0.3620370626449585,
|
| 965 |
+
"step": 435,
|
| 966 |
+
"valid_targets_mean": 3927.2,
|
| 967 |
+
"valid_targets_min": 1332
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 2.1463414634146343,
|
| 971 |
+
"grad_norm": 0.8475846605532067,
|
| 972 |
+
"learning_rate": 3.5064173676008994e-05,
|
| 973 |
+
"loss": 0.3302,
|
| 974 |
+
"loss_nan_ranks": 0,
|
| 975 |
+
"loss_rank_avg": 0.3536580502986908,
|
| 976 |
+
"step": 440,
|
| 977 |
+
"valid_targets_mean": 3192.6,
|
| 978 |
+
"valid_targets_min": 15
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 2.1707317073170733,
|
| 982 |
+
"grad_norm": 0.7927213460960987,
|
| 983 |
+
"learning_rate": 3.4902994252758295e-05,
|
| 984 |
+
"loss": 0.3471,
|
| 985 |
+
"loss_nan_ranks": 0,
|
| 986 |
+
"loss_rank_avg": 0.35433822870254517,
|
| 987 |
+
"step": 445,
|
| 988 |
+
"valid_targets_mean": 3070.1,
|
| 989 |
+
"valid_targets_min": 1186
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 2.1951219512195124,
|
| 993 |
+
"grad_norm": 0.7610761241152856,
|
| 994 |
+
"learning_rate": 3.473960857583515e-05,
|
| 995 |
+
"loss": 0.3171,
|
| 996 |
+
"loss_nan_ranks": 0,
|
| 997 |
+
"loss_rank_avg": 0.32693955302238464,
|
| 998 |
+
"step": 450,
|
| 999 |
+
"valid_targets_mean": 3352.6,
|
| 1000 |
+
"valid_targets_min": 470
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"epoch": 2.2195121951219514,
|
| 1004 |
+
"grad_norm": 0.7661120709390085,
|
| 1005 |
+
"learning_rate": 3.457404083301308e-05,
|
| 1006 |
+
"loss": 0.347,
|
| 1007 |
+
"loss_nan_ranks": 0,
|
| 1008 |
+
"loss_rank_avg": 0.39784368872642517,
|
| 1009 |
+
"step": 455,
|
| 1010 |
+
"valid_targets_mean": 2986.9,
|
| 1011 |
+
"valid_targets_min": 659
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 2.2439024390243905,
|
| 1015 |
+
"grad_norm": 0.7246543900328846,
|
| 1016 |
+
"learning_rate": 3.440631553510074e-05,
|
| 1017 |
+
"loss": 0.3289,
|
| 1018 |
+
"loss_nan_ranks": 0,
|
| 1019 |
+
"loss_rank_avg": 0.34927499294281006,
|
| 1020 |
+
"step": 460,
|
| 1021 |
+
"valid_targets_mean": 4064.9,
|
| 1022 |
+
"valid_targets_min": 895
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 2.2682926829268295,
|
| 1026 |
+
"grad_norm": 0.8008639860765635,
|
| 1027 |
+
"learning_rate": 3.423645751231334e-05,
|
| 1028 |
+
"loss": 0.3214,
|
| 1029 |
+
"loss_nan_ranks": 0,
|
| 1030 |
+
"loss_rank_avg": 0.31427597999572754,
|
| 1031 |
+
"step": 465,
|
| 1032 |
+
"valid_targets_mean": 3223.2,
|
| 1033 |
+
"valid_targets_min": 948
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 2.292682926829268,
|
| 1037 |
+
"grad_norm": 0.8738414902443441,
|
| 1038 |
+
"learning_rate": 3.4064491910596726e-05,
|
| 1039 |
+
"loss": 0.3219,
|
| 1040 |
+
"loss_nan_ranks": 0,
|
| 1041 |
+
"loss_rank_avg": 0.34688445925712585,
|
| 1042 |
+
"step": 470,
|
| 1043 |
+
"valid_targets_mean": 2696.8,
|
| 1044 |
+
"valid_targets_min": 414
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 2.317073170731707,
|
| 1048 |
+
"grad_norm": 0.8678786719122115,
|
| 1049 |
+
"learning_rate": 3.389044418790478e-05,
|
| 1050 |
+
"loss": 0.3375,
|
| 1051 |
+
"loss_nan_ranks": 0,
|
| 1052 |
+
"loss_rank_avg": 0.36265698075294495,
|
| 1053 |
+
"step": 475,
|
| 1054 |
+
"valid_targets_mean": 3027.2,
|
| 1055 |
+
"valid_targets_min": 827
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 2.341463414634146,
|
| 1059 |
+
"grad_norm": 0.8786827707032558,
|
| 1060 |
+
"learning_rate": 3.371434011043059e-05,
|
| 1061 |
+
"loss": 0.337,
|
| 1062 |
+
"loss_nan_ranks": 0,
|
| 1063 |
+
"loss_rank_avg": 0.3238053321838379,
|
| 1064 |
+
"step": 480,
|
| 1065 |
+
"valid_targets_mean": 3018.0,
|
| 1066 |
+
"valid_targets_min": 879
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 2.3658536585365852,
|
| 1070 |
+
"grad_norm": 0.7675111501407975,
|
| 1071 |
+
"learning_rate": 3.353620574879197e-05,
|
| 1072 |
+
"loss": 0.3149,
|
| 1073 |
+
"loss_nan_ranks": 0,
|
| 1074 |
+
"loss_rank_avg": 0.33381664752960205,
|
| 1075 |
+
"step": 485,
|
| 1076 |
+
"valid_targets_mean": 3482.8,
|
| 1077 |
+
"valid_targets_min": 822
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 2.3902439024390243,
|
| 1081 |
+
"grad_norm": 0.6390042122755262,
|
| 1082 |
+
"learning_rate": 3.335606747417199e-05,
|
| 1083 |
+
"loss": 0.3216,
|
| 1084 |
+
"loss_nan_ranks": 0,
|
| 1085 |
+
"loss_rank_avg": 0.2951709032058716,
|
| 1086 |
+
"step": 490,
|
| 1087 |
+
"valid_targets_mean": 4398.2,
|
| 1088 |
+
"valid_targets_min": 778
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 2.4146341463414633,
|
| 1092 |
+
"grad_norm": 0.8212805538188749,
|
| 1093 |
+
"learning_rate": 3.317395195441492e-05,
|
| 1094 |
+
"loss": 0.3528,
|
| 1095 |
+
"loss_nan_ranks": 0,
|
| 1096 |
+
"loss_rank_avg": 0.3706200122833252,
|
| 1097 |
+
"step": 495,
|
| 1098 |
+
"valid_targets_mean": 2767.0,
|
| 1099 |
+
"valid_targets_min": 15
|
| 1100 |
+
},
|
| 1101 |
+
{
|
| 1102 |
+
"epoch": 2.4390243902439024,
|
| 1103 |
+
"grad_norm": 0.8090900974135942,
|
| 1104 |
+
"learning_rate": 3.29898861500783e-05,
|
| 1105 |
+
"loss": 0.3328,
|
| 1106 |
+
"loss_nan_ranks": 0,
|
| 1107 |
+
"loss_rank_avg": 0.3654935956001282,
|
| 1108 |
+
"step": 500,
|
| 1109 |
+
"valid_targets_mean": 3085.2,
|
| 1110 |
+
"valid_targets_min": 242
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"epoch": 2.4634146341463414,
|
| 1114 |
+
"grad_norm": 0.7178716047967076,
|
| 1115 |
+
"learning_rate": 3.280389731044172e-05,
|
| 1116 |
+
"loss": 0.3202,
|
| 1117 |
+
"loss_nan_ranks": 0,
|
| 1118 |
+
"loss_rank_avg": 0.32301709055900574,
|
| 1119 |
+
"step": 505,
|
| 1120 |
+
"valid_targets_mean": 3715.7,
|
| 1121 |
+
"valid_targets_min": 716
|
| 1122 |
+
},
|
| 1123 |
+
{
|
| 1124 |
+
"epoch": 2.4878048780487805,
|
| 1125 |
+
"grad_norm": 0.7793422281432595,
|
| 1126 |
+
"learning_rate": 3.261601296947274e-05,
|
| 1127 |
+
"loss": 0.3201,
|
| 1128 |
+
"loss_nan_ranks": 0,
|
| 1129 |
+
"loss_rank_avg": 0.335943341255188,
|
| 1130 |
+
"step": 510,
|
| 1131 |
+
"valid_targets_mean": 3158.2,
|
| 1132 |
+
"valid_targets_min": 734
|
| 1133 |
+
},
|
| 1134 |
+
{
|
| 1135 |
+
"epoch": 2.5121951219512195,
|
| 1136 |
+
"grad_norm": 0.7681138811218,
|
| 1137 |
+
"learning_rate": 3.242626094175078e-05,
|
| 1138 |
+
"loss": 0.3346,
|
| 1139 |
+
"loss_nan_ranks": 0,
|
| 1140 |
+
"loss_rank_avg": 0.35204848647117615,
|
| 1141 |
+
"step": 515,
|
| 1142 |
+
"valid_targets_mean": 3170.2,
|
| 1143 |
+
"valid_targets_min": 1079
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 2.5365853658536586,
|
| 1147 |
+
"grad_norm": 0.6712571944834722,
|
| 1148 |
+
"learning_rate": 3.223466931834942e-05,
|
| 1149 |
+
"loss": 0.318,
|
| 1150 |
+
"loss_nan_ranks": 0,
|
| 1151 |
+
"loss_rank_avg": 0.29909318685531616,
|
| 1152 |
+
"step": 520,
|
| 1153 |
+
"valid_targets_mean": 4161.2,
|
| 1154 |
+
"valid_targets_min": 766
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 2.5609756097560976,
|
| 1158 |
+
"grad_norm": 0.8147312751968008,
|
| 1159 |
+
"learning_rate": 3.204126646267775e-05,
|
| 1160 |
+
"loss": 0.336,
|
| 1161 |
+
"loss_nan_ranks": 0,
|
| 1162 |
+
"loss_rank_avg": 0.3322216272354126,
|
| 1163 |
+
"step": 525,
|
| 1164 |
+
"valid_targets_mean": 3378.3,
|
| 1165 |
+
"valid_targets_min": 443
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 2.5853658536585367,
|
| 1169 |
+
"grad_norm": 0.9657053285042281,
|
| 1170 |
+
"learning_rate": 3.184608100628144e-05,
|
| 1171 |
+
"loss": 0.3356,
|
| 1172 |
+
"loss_nan_ranks": 0,
|
| 1173 |
+
"loss_rank_avg": 0.3430883288383484,
|
| 1174 |
+
"step": 530,
|
| 1175 |
+
"valid_targets_mean": 3151.1,
|
| 1176 |
+
"valid_targets_min": 1443
|
| 1177 |
+
},
|
| 1178 |
+
{
|
| 1179 |
+
"epoch": 2.6097560975609757,
|
| 1180 |
+
"grad_norm": 0.8322031702520009,
|
| 1181 |
+
"learning_rate": 3.1649141844604104e-05,
|
| 1182 |
+
"loss": 0.3355,
|
| 1183 |
+
"loss_nan_ranks": 0,
|
| 1184 |
+
"loss_rank_avg": 0.338076114654541,
|
| 1185 |
+
"step": 535,
|
| 1186 |
+
"valid_targets_mean": 3503.4,
|
| 1187 |
+
"valid_targets_min": 1613
|
| 1188 |
+
},
|
| 1189 |
+
{
|
| 1190 |
+
"epoch": 2.6341463414634148,
|
| 1191 |
+
"grad_norm": 0.6205044905999079,
|
| 1192 |
+
"learning_rate": 3.1450478132709564e-05,
|
| 1193 |
+
"loss": 0.3285,
|
| 1194 |
+
"loss_nan_ranks": 0,
|
| 1195 |
+
"loss_rank_avg": 0.27576902508735657,
|
| 1196 |
+
"step": 540,
|
| 1197 |
+
"valid_targets_mean": 3844.5,
|
| 1198 |
+
"valid_targets_min": 1855
|
| 1199 |
+
},
|
| 1200 |
+
{
|
| 1201 |
+
"epoch": 2.658536585365854,
|
| 1202 |
+
"grad_norm": 0.6286837078803078,
|
| 1203 |
+
"learning_rate": 3.125011928096573e-05,
|
| 1204 |
+
"loss": 0.3151,
|
| 1205 |
+
"loss_nan_ranks": 0,
|
| 1206 |
+
"loss_rank_avg": 0.3034632205963135,
|
| 1207 |
+
"step": 545,
|
| 1208 |
+
"valid_targets_mean": 4288.0,
|
| 1209 |
+
"valid_targets_min": 719
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 2.682926829268293,
|
| 1213 |
+
"grad_norm": 0.6004872520430579,
|
| 1214 |
+
"learning_rate": 3.1048094950690666e-05,
|
| 1215 |
+
"loss": 0.3253,
|
| 1216 |
+
"loss_nan_ranks": 0,
|
| 1217 |
+
"loss_rank_avg": 0.31010162830352783,
|
| 1218 |
+
"step": 550,
|
| 1219 |
+
"valid_targets_mean": 4788.6,
|
| 1220 |
+
"valid_targets_min": 1098
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 2.7073170731707314,
|
| 1224 |
+
"grad_norm": 0.7437431500245776,
|
| 1225 |
+
"learning_rate": 3.084443504976146e-05,
|
| 1226 |
+
"loss": 0.3211,
|
| 1227 |
+
"loss_nan_ranks": 0,
|
| 1228 |
+
"loss_rank_avg": 0.3372463881969452,
|
| 1229 |
+
"step": 555,
|
| 1230 |
+
"valid_targets_mean": 3434.3,
|
| 1231 |
+
"valid_targets_min": 706
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 2.7317073170731705,
|
| 1235 |
+
"grad_norm": 0.7853234418992919,
|
| 1236 |
+
"learning_rate": 3.063916972818668e-05,
|
| 1237 |
+
"loss": 0.3079,
|
| 1238 |
+
"loss_nan_ranks": 0,
|
| 1239 |
+
"loss_rank_avg": 0.32306212186813354,
|
| 1240 |
+
"step": 560,
|
| 1241 |
+
"valid_targets_mean": 3142.7,
|
| 1242 |
+
"valid_targets_min": 509
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 2.7560975609756095,
|
| 1246 |
+
"grad_norm": 0.7334837795099509,
|
| 1247 |
+
"learning_rate": 3.0432329373642932e-05,
|
| 1248 |
+
"loss": 0.3296,
|
| 1249 |
+
"loss_nan_ranks": 0,
|
| 1250 |
+
"loss_rank_avg": 0.35558754205703735,
|
| 1251 |
+
"step": 565,
|
| 1252 |
+
"valid_targets_mean": 3550.8,
|
| 1253 |
+
"valid_targets_min": 951
|
| 1254 |
+
},
|
| 1255 |
+
{
|
| 1256 |
+
"epoch": 2.7804878048780486,
|
| 1257 |
+
"grad_norm": 0.7080533587312593,
|
| 1258 |
+
"learning_rate": 3.022394460697619e-05,
|
| 1259 |
+
"loss": 0.3424,
|
| 1260 |
+
"loss_nan_ranks": 0,
|
| 1261 |
+
"loss_rank_avg": 0.33535170555114746,
|
| 1262 |
+
"step": 570,
|
| 1263 |
+
"valid_targets_mean": 3713.6,
|
| 1264 |
+
"valid_targets_min": 947
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"epoch": 2.8048780487804876,
|
| 1268 |
+
"grad_norm": 0.73150297718836,
|
| 1269 |
+
"learning_rate": 3.0014046277668717e-05,
|
| 1270 |
+
"loss": 0.34,
|
| 1271 |
+
"loss_nan_ranks": 0,
|
| 1272 |
+
"loss_rank_avg": 0.3074615001678467,
|
| 1273 |
+
"step": 575,
|
| 1274 |
+
"valid_targets_mean": 3663.5,
|
| 1275 |
+
"valid_targets_min": 215
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 2.8292682926829267,
|
| 1279 |
+
"grad_norm": 0.6590534931503084,
|
| 1280 |
+
"learning_rate": 2.980266545927203e-05,
|
| 1281 |
+
"loss": 0.3348,
|
| 1282 |
+
"loss_nan_ranks": 0,
|
| 1283 |
+
"loss_rank_avg": 0.32705825567245483,
|
| 1284 |
+
"step": 580,
|
| 1285 |
+
"valid_targets_mean": 4970.6,
|
| 1286 |
+
"valid_targets_min": 1788
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 2.8536585365853657,
|
| 1290 |
+
"grad_norm": 0.6817244060162384,
|
| 1291 |
+
"learning_rate": 2.9589833444806792e-05,
|
| 1292 |
+
"loss": 0.3144,
|
| 1293 |
+
"loss_nan_ranks": 0,
|
| 1294 |
+
"loss_rank_avg": 0.30664777755737305,
|
| 1295 |
+
"step": 585,
|
| 1296 |
+
"valid_targets_mean": 3579.2,
|
| 1297 |
+
"valid_targets_min": 917
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 2.8780487804878048,
|
| 1301 |
+
"grad_norm": 0.7336497853782242,
|
| 1302 |
+
"learning_rate": 2.9375581742130114e-05,
|
| 1303 |
+
"loss": 0.3305,
|
| 1304 |
+
"loss_nan_ranks": 0,
|
| 1305 |
+
"loss_rank_avg": 0.3490193486213684,
|
| 1306 |
+
"step": 590,
|
| 1307 |
+
"valid_targets_mean": 3624.7,
|
| 1308 |
+
"valid_targets_min": 876
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 2.902439024390244,
|
| 1312 |
+
"grad_norm": 0.7790909299976445,
|
| 1313 |
+
"learning_rate": 2.9159942069271134e-05,
|
| 1314 |
+
"loss": 0.3246,
|
| 1315 |
+
"loss_nan_ranks": 0,
|
| 1316 |
+
"loss_rank_avg": 0.3473791778087616,
|
| 1317 |
+
"step": 595,
|
| 1318 |
+
"valid_targets_mean": 3575.1,
|
| 1319 |
+
"valid_targets_min": 532
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 2.926829268292683,
|
| 1323 |
+
"grad_norm": 0.8701084213390046,
|
| 1324 |
+
"learning_rate": 2.8942946349735418e-05,
|
| 1325 |
+
"loss": 0.3389,
|
| 1326 |
+
"loss_nan_ranks": 0,
|
| 1327 |
+
"loss_rank_avg": 0.3636641800403595,
|
| 1328 |
+
"step": 600,
|
| 1329 |
+
"valid_targets_mean": 3125.3,
|
| 1330 |
+
"valid_targets_min": 1655
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"epoch": 2.951219512195122,
|
| 1334 |
+
"grad_norm": 0.6582306859910523,
|
| 1335 |
+
"learning_rate": 2.872462670777902e-05,
|
| 1336 |
+
"loss": 0.3444,
|
| 1337 |
+
"loss_nan_ranks": 0,
|
| 1338 |
+
"loss_rank_avg": 0.34115156531333923,
|
| 1339 |
+
"step": 605,
|
| 1340 |
+
"valid_targets_mean": 4006.7,
|
| 1341 |
+
"valid_targets_min": 856
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 2.975609756097561,
|
| 1345 |
+
"grad_norm": 0.6682235966360865,
|
| 1346 |
+
"learning_rate": 2.850501546365272e-05,
|
| 1347 |
+
"loss": 0.3298,
|
| 1348 |
+
"loss_nan_ranks": 0,
|
| 1349 |
+
"loss_rank_avg": 0.2904140055179596,
|
| 1350 |
+
"step": 610,
|
| 1351 |
+
"valid_targets_mean": 4037.1,
|
| 1352 |
+
"valid_targets_min": 1157
|
| 1353 |
+
},
|
| 1354 |
+
{
|
| 1355 |
+
"epoch": 3.0,
|
| 1356 |
+
"grad_norm": 0.7895951757040935,
|
| 1357 |
+
"learning_rate": 2.8284145128817356e-05,
|
| 1358 |
+
"loss": 0.3203,
|
| 1359 |
+
"loss_nan_ranks": 0,
|
| 1360 |
+
"loss_rank_avg": 0.354103684425354,
|
| 1361 |
+
"step": 615,
|
| 1362 |
+
"valid_targets_mean": 3262.8,
|
| 1363 |
+
"valid_targets_min": 841
|
| 1364 |
+
},
|
| 1365 |
+
{
|
| 1366 |
+
"epoch": 3.024390243902439,
|
| 1367 |
+
"grad_norm": 0.6974883146545042,
|
| 1368 |
+
"learning_rate": 2.8062048401130756e-05,
|
| 1369 |
+
"loss": 0.2882,
|
| 1370 |
+
"loss_nan_ranks": 0,
|
| 1371 |
+
"loss_rank_avg": 0.24095089733600616,
|
| 1372 |
+
"step": 620,
|
| 1373 |
+
"valid_targets_mean": 3347.9,
|
| 1374 |
+
"valid_targets_min": 883
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 3.048780487804878,
|
| 1378 |
+
"grad_norm": 0.7109250659036205,
|
| 1379 |
+
"learning_rate": 2.7838758160007143e-05,
|
| 1380 |
+
"loss": 0.2966,
|
| 1381 |
+
"loss_nan_ranks": 0,
|
| 1382 |
+
"loss_rank_avg": 0.2862807512283325,
|
| 1383 |
+
"step": 625,
|
| 1384 |
+
"valid_targets_mean": 4033.4,
|
| 1385 |
+
"valid_targets_min": 1140
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 3.073170731707317,
|
| 1389 |
+
"grad_norm": 0.7946160604885082,
|
| 1390 |
+
"learning_rate": 2.7614307461549608e-05,
|
| 1391 |
+
"loss": 0.2901,
|
| 1392 |
+
"loss_nan_ranks": 0,
|
| 1393 |
+
"loss_rank_avg": 0.29598280787467957,
|
| 1394 |
+
"step": 630,
|
| 1395 |
+
"valid_targets_mean": 3057.0,
|
| 1396 |
+
"valid_targets_min": 1115
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 3.097560975609756,
|
| 1400 |
+
"grad_norm": 0.7097254573358867,
|
| 1401 |
+
"learning_rate": 2.7388729533656486e-05,
|
| 1402 |
+
"loss": 0.3045,
|
| 1403 |
+
"loss_nan_ranks": 0,
|
| 1404 |
+
"loss_rank_avg": 0.3431246876716614,
|
| 1405 |
+
"step": 635,
|
| 1406 |
+
"valid_targets_mean": 4266.8,
|
| 1407 |
+
"valid_targets_min": 1238
|
| 1408 |
+
},
|
| 1409 |
+
{
|
| 1410 |
+
"epoch": 3.1219512195121952,
|
| 1411 |
+
"grad_norm": 0.6657050549479481,
|
| 1412 |
+
"learning_rate": 2.716205777110222e-05,
|
| 1413 |
+
"loss": 0.2904,
|
| 1414 |
+
"loss_nan_ranks": 0,
|
| 1415 |
+
"loss_rank_avg": 0.2793746590614319,
|
| 1416 |
+
"step": 640,
|
| 1417 |
+
"valid_targets_mean": 4308.1,
|
| 1418 |
+
"valid_targets_min": 1604
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 3.1463414634146343,
|
| 1422 |
+
"grad_norm": 0.8163459205438388,
|
| 1423 |
+
"learning_rate": 2.693432573059362e-05,
|
| 1424 |
+
"loss": 0.3019,
|
| 1425 |
+
"loss_nan_ranks": 0,
|
| 1426 |
+
"loss_rank_avg": 0.3036867678165436,
|
| 1427 |
+
"step": 645,
|
| 1428 |
+
"valid_targets_mean": 3326.4,
|
| 1429 |
+
"valid_targets_min": 1119
|
| 1430 |
+
},
|
| 1431 |
+
{
|
| 1432 |
+
"epoch": 3.1707317073170733,
|
| 1433 |
+
"grad_norm": 0.7669109525500525,
|
| 1434 |
+
"learning_rate": 2.6705567125802062e-05,
|
| 1435 |
+
"loss": 0.3081,
|
| 1436 |
+
"loss_nan_ranks": 0,
|
| 1437 |
+
"loss_rank_avg": 0.3797120451927185,
|
| 1438 |
+
"step": 650,
|
| 1439 |
+
"valid_targets_mean": 3517.2,
|
| 1440 |
+
"valid_targets_min": 1445
|
| 1441 |
+
},
|
| 1442 |
+
{
|
| 1443 |
+
"epoch": 3.1951219512195124,
|
| 1444 |
+
"grad_norm": 0.7809371072538767,
|
| 1445 |
+
"learning_rate": 2.6475815822372477e-05,
|
| 1446 |
+
"loss": 0.2962,
|
| 1447 |
+
"loss_nan_ranks": 0,
|
| 1448 |
+
"loss_rank_avg": 0.2904462516307831,
|
| 1449 |
+
"step": 655,
|
| 1450 |
+
"valid_targets_mean": 3374.4,
|
| 1451 |
+
"valid_targets_min": 752
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 3.2195121951219514,
|
| 1455 |
+
"grad_norm": 0.8873754094152563,
|
| 1456 |
+
"learning_rate": 2.624510583290988e-05,
|
| 1457 |
+
"loss": 0.3042,
|
| 1458 |
+
"loss_nan_ranks": 0,
|
| 1459 |
+
"loss_rank_avg": 0.2988511919975281,
|
| 1460 |
+
"step": 660,
|
| 1461 |
+
"valid_targets_mean": 2854.0,
|
| 1462 |
+
"valid_targets_min": 283
|
| 1463 |
+
},
|
| 1464 |
+
{
|
| 1465 |
+
"epoch": 3.2439024390243905,
|
| 1466 |
+
"grad_norm": 0.6937976107448536,
|
| 1467 |
+
"learning_rate": 2.601347131194408e-05,
|
| 1468 |
+
"loss": 0.2824,
|
| 1469 |
+
"loss_nan_ranks": 0,
|
| 1470 |
+
"loss_rank_avg": 0.2786598205566406,
|
| 1471 |
+
"step": 665,
|
| 1472 |
+
"valid_targets_mean": 3895.2,
|
| 1473 |
+
"valid_targets_min": 848
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 3.2682926829268295,
|
| 1477 |
+
"grad_norm": 0.6938504187586086,
|
| 1478 |
+
"learning_rate": 2.578094655087343e-05,
|
| 1479 |
+
"loss": 0.2887,
|
| 1480 |
+
"loss_nan_ranks": 0,
|
| 1481 |
+
"loss_rank_avg": 0.284922331571579,
|
| 1482 |
+
"step": 670,
|
| 1483 |
+
"valid_targets_mean": 3660.7,
|
| 1484 |
+
"valid_targets_min": 376
|
| 1485 |
+
},
|
| 1486 |
+
{
|
| 1487 |
+
"epoch": 3.292682926829268,
|
| 1488 |
+
"grad_norm": 0.6657085168651424,
|
| 1489 |
+
"learning_rate": 2.5547565972888287e-05,
|
| 1490 |
+
"loss": 0.2758,
|
| 1491 |
+
"loss_nan_ranks": 0,
|
| 1492 |
+
"loss_rank_avg": 0.2657183110713959,
|
| 1493 |
+
"step": 675,
|
| 1494 |
+
"valid_targets_mean": 4128.4,
|
| 1495 |
+
"valid_targets_min": 1404
|
| 1496 |
+
},
|
| 1497 |
+
{
|
| 1498 |
+
"epoch": 3.317073170731707,
|
| 1499 |
+
"grad_norm": 0.7187359550353202,
|
| 1500 |
+
"learning_rate": 2.5313364127874974e-05,
|
| 1501 |
+
"loss": 0.2936,
|
| 1502 |
+
"loss_nan_ranks": 0,
|
| 1503 |
+
"loss_rank_avg": 0.27557191252708435,
|
| 1504 |
+
"step": 680,
|
| 1505 |
+
"valid_targets_mean": 3624.4,
|
| 1506 |
+
"valid_targets_min": 796
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 3.341463414634146,
|
| 1510 |
+
"grad_norm": 0.7875009925701425,
|
| 1511 |
+
"learning_rate": 2.507837568730097e-05,
|
| 1512 |
+
"loss": 0.289,
|
| 1513 |
+
"loss_nan_ranks": 0,
|
| 1514 |
+
"loss_rank_avg": 0.3072514533996582,
|
| 1515 |
+
"step": 685,
|
| 1516 |
+
"valid_targets_mean": 3990.4,
|
| 1517 |
+
"valid_targets_min": 15
|
| 1518 |
+
},
|
| 1519 |
+
{
|
| 1520 |
+
"epoch": 3.3658536585365852,
|
| 1521 |
+
"grad_norm": 0.842619447531655,
|
| 1522 |
+
"learning_rate": 2.484263543908213e-05,
|
| 1523 |
+
"loss": 0.3008,
|
| 1524 |
+
"loss_nan_ranks": 0,
|
| 1525 |
+
"loss_rank_avg": 0.3235273063182831,
|
| 1526 |
+
"step": 690,
|
| 1527 |
+
"valid_targets_mean": 2521.5,
|
| 1528 |
+
"valid_targets_min": 1158
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 3.3902439024390243,
|
| 1532 |
+
"grad_norm": 0.7753973868751888,
|
| 1533 |
+
"learning_rate": 2.460617828243263e-05,
|
| 1534 |
+
"loss": 0.2919,
|
| 1535 |
+
"loss_nan_ranks": 0,
|
| 1536 |
+
"loss_rank_avg": 0.27399516105651855,
|
| 1537 |
+
"step": 695,
|
| 1538 |
+
"valid_targets_mean": 3223.4,
|
| 1539 |
+
"valid_targets_min": 899
|
| 1540 |
+
},
|
| 1541 |
+
{
|
| 1542 |
+
"epoch": 3.4146341463414633,
|
| 1543 |
+
"grad_norm": 0.7336548815168598,
|
| 1544 |
+
"learning_rate": 2.4369039222698484e-05,
|
| 1545 |
+
"loss": 0.2898,
|
| 1546 |
+
"loss_nan_ranks": 0,
|
| 1547 |
+
"loss_rank_avg": 0.2887844443321228,
|
| 1548 |
+
"step": 700,
|
| 1549 |
+
"valid_targets_mean": 3239.1,
|
| 1550 |
+
"valid_targets_min": 979
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 3.4390243902439024,
|
| 1554 |
+
"grad_norm": 0.7641087596057364,
|
| 1555 |
+
"learning_rate": 2.413125336617526e-05,
|
| 1556 |
+
"loss": 0.3052,
|
| 1557 |
+
"loss_nan_ranks": 0,
|
| 1558 |
+
"loss_rank_avg": 0.30372944474220276,
|
| 1559 |
+
"step": 705,
|
| 1560 |
+
"valid_targets_mean": 3645.4,
|
| 1561 |
+
"valid_targets_min": 1803
|
| 1562 |
+
},
|
| 1563 |
+
{
|
| 1564 |
+
"epoch": 3.4634146341463414,
|
| 1565 |
+
"grad_norm": 0.7436323943905782,
|
| 1566 |
+
"learning_rate": 2.3892855914910996e-05,
|
| 1567 |
+
"loss": 0.2925,
|
| 1568 |
+
"loss_nan_ranks": 0,
|
| 1569 |
+
"loss_rank_avg": 0.2785486578941345,
|
| 1570 |
+
"step": 710,
|
| 1571 |
+
"valid_targets_mean": 3915.2,
|
| 1572 |
+
"valid_targets_min": 1063
|
| 1573 |
+
},
|
| 1574 |
+
{
|
| 1575 |
+
"epoch": 3.4878048780487805,
|
| 1576 |
+
"grad_norm": 0.7111257893891988,
|
| 1577 |
+
"learning_rate": 2.3653882161494758e-05,
|
| 1578 |
+
"loss": 0.2896,
|
| 1579 |
+
"loss_nan_ranks": 0,
|
| 1580 |
+
"loss_rank_avg": 0.2819863557815552,
|
| 1581 |
+
"step": 715,
|
| 1582 |
+
"valid_targets_mean": 3914.8,
|
| 1583 |
+
"valid_targets_min": 1277
|
| 1584 |
+
},
|
| 1585 |
+
{
|
| 1586 |
+
"epoch": 3.5121951219512195,
|
| 1587 |
+
"grad_norm": 0.7237969701861009,
|
| 1588 |
+
"learning_rate": 2.3414367483831972e-05,
|
| 1589 |
+
"loss": 0.2972,
|
| 1590 |
+
"loss_nan_ranks": 0,
|
| 1591 |
+
"loss_rank_avg": 0.2876496911048889,
|
| 1592 |
+
"step": 720,
|
| 1593 |
+
"valid_targets_mean": 3642.9,
|
| 1594 |
+
"valid_targets_min": 575
|
| 1595 |
+
},
|
| 1596 |
+
{
|
| 1597 |
+
"epoch": 3.5365853658536586,
|
| 1598 |
+
"grad_norm": 0.750501060308758,
|
| 1599 |
+
"learning_rate": 2.3174347339906994e-05,
|
| 1600 |
+
"loss": 0.2909,
|
| 1601 |
+
"loss_nan_ranks": 0,
|
| 1602 |
+
"loss_rank_avg": 0.31642240285873413,
|
| 1603 |
+
"step": 725,
|
| 1604 |
+
"valid_targets_mean": 3697.5,
|
| 1605 |
+
"valid_targets_min": 917
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 3.5609756097560976,
|
| 1609 |
+
"grad_norm": 0.7241041312746126,
|
| 1610 |
+
"learning_rate": 2.293385726253392e-05,
|
| 1611 |
+
"loss": 0.2953,
|
| 1612 |
+
"loss_nan_ranks": 0,
|
| 1613 |
+
"loss_rank_avg": 0.2714157700538635,
|
| 1614 |
+
"step": 730,
|
| 1615 |
+
"valid_targets_mean": 3771.2,
|
| 1616 |
+
"valid_targets_min": 723
|
| 1617 |
+
},
|
| 1618 |
+
{
|
| 1619 |
+
"epoch": 3.5853658536585367,
|
| 1620 |
+
"grad_norm": 0.6954133761615647,
|
| 1621 |
+
"learning_rate": 2.2692932854096218e-05,
|
| 1622 |
+
"loss": 0.2895,
|
| 1623 |
+
"loss_nan_ranks": 0,
|
| 1624 |
+
"loss_rank_avg": 0.25798699259757996,
|
| 1625 |
+
"step": 735,
|
| 1626 |
+
"valid_targets_mean": 3402.4,
|
| 1627 |
+
"valid_targets_min": 1080
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 3.6097560975609757,
|
| 1631 |
+
"grad_norm": 0.7417839254349834,
|
| 1632 |
+
"learning_rate": 2.245160978127616e-05,
|
| 1633 |
+
"loss": 0.2971,
|
| 1634 |
+
"loss_nan_ranks": 0,
|
| 1635 |
+
"loss_rank_avg": 0.28403568267822266,
|
| 1636 |
+
"step": 740,
|
| 1637 |
+
"valid_targets_mean": 3251.5,
|
| 1638 |
+
"valid_targets_min": 841
|
| 1639 |
+
},
|
| 1640 |
+
{
|
| 1641 |
+
"epoch": 3.6341463414634148,
|
| 1642 |
+
"grad_norm": 0.7403025968890654,
|
| 1643 |
+
"learning_rate": 2.220992376977468e-05,
|
| 1644 |
+
"loss": 0.2993,
|
| 1645 |
+
"loss_nan_ranks": 0,
|
| 1646 |
+
"loss_rank_avg": 0.32009467482566833,
|
| 1647 |
+
"step": 745,
|
| 1648 |
+
"valid_targets_mean": 3620.8,
|
| 1649 |
+
"valid_targets_min": 1178
|
| 1650 |
+
},
|
| 1651 |
+
{
|
| 1652 |
+
"epoch": 3.658536585365854,
|
| 1653 |
+
"grad_norm": 0.9161578181958758,
|
| 1654 |
+
"learning_rate": 2.1967910599022508e-05,
|
| 1655 |
+
"loss": 0.2898,
|
| 1656 |
+
"loss_nan_ranks": 0,
|
| 1657 |
+
"loss_rank_avg": 0.331581711769104,
|
| 1658 |
+
"step": 750,
|
| 1659 |
+
"valid_targets_mean": 2408.2,
|
| 1660 |
+
"valid_targets_min": 507
|
| 1661 |
+
},
|
| 1662 |
+
{
|
| 1663 |
+
"epoch": 3.682926829268293,
|
| 1664 |
+
"grad_norm": 0.881155980649594,
|
| 1665 |
+
"learning_rate": 2.1725606096883324e-05,
|
| 1666 |
+
"loss": 0.2915,
|
| 1667 |
+
"loss_nan_ranks": 0,
|
| 1668 |
+
"loss_rank_avg": 0.29733753204345703,
|
| 1669 |
+
"step": 755,
|
| 1670 |
+
"valid_targets_mean": 2705.3,
|
| 1671 |
+
"valid_targets_min": 257
|
| 1672 |
+
},
|
| 1673 |
+
{
|
| 1674 |
+
"epoch": 3.7073170731707314,
|
| 1675 |
+
"grad_norm": 0.7297940343575094,
|
| 1676 |
+
"learning_rate": 2.1483046134349813e-05,
|
| 1677 |
+
"loss": 0.2876,
|
| 1678 |
+
"loss_nan_ranks": 0,
|
| 1679 |
+
"loss_rank_avg": 0.28595206141471863,
|
| 1680 |
+
"step": 760,
|
| 1681 |
+
"valid_targets_mean": 4102.2,
|
| 1682 |
+
"valid_targets_min": 318
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 3.7317073170731705,
|
| 1686 |
+
"grad_norm": 0.8649348588673672,
|
| 1687 |
+
"learning_rate": 2.1240266620233263e-05,
|
| 1688 |
+
"loss": 0.3112,
|
| 1689 |
+
"loss_nan_ranks": 0,
|
| 1690 |
+
"loss_rank_avg": 0.31264781951904297,
|
| 1691 |
+
"step": 765,
|
| 1692 |
+
"valid_targets_mean": 2636.3,
|
| 1693 |
+
"valid_targets_min": 772
|
| 1694 |
+
},
|
| 1695 |
+
{
|
| 1696 |
+
"epoch": 3.7560975609756095,
|
| 1697 |
+
"grad_norm": 0.7040450574601868,
|
| 1698 |
+
"learning_rate": 2.099730349584757e-05,
|
| 1699 |
+
"loss": 0.2832,
|
| 1700 |
+
"loss_nan_ranks": 0,
|
| 1701 |
+
"loss_rank_avg": 0.3125355541706085,
|
| 1702 |
+
"step": 770,
|
| 1703 |
+
"valid_targets_mean": 3862.3,
|
| 1704 |
+
"valid_targets_min": 867
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 3.7804878048780486,
|
| 1708 |
+
"grad_norm": 0.6737989713489716,
|
| 1709 |
+
"learning_rate": 2.0754192729688496e-05,
|
| 1710 |
+
"loss": 0.2996,
|
| 1711 |
+
"loss_nan_ranks": 0,
|
| 1712 |
+
"loss_rank_avg": 0.2767524719238281,
|
| 1713 |
+
"step": 775,
|
| 1714 |
+
"valid_targets_mean": 3927.2,
|
| 1715 |
+
"valid_targets_min": 1667
|
| 1716 |
+
},
|
| 1717 |
+
{
|
| 1718 |
+
"epoch": 3.8048780487804876,
|
| 1719 |
+
"grad_norm": 0.745892500316203,
|
| 1720 |
+
"learning_rate": 2.0510970312108804e-05,
|
| 1721 |
+
"loss": 0.2893,
|
| 1722 |
+
"loss_nan_ranks": 0,
|
| 1723 |
+
"loss_rank_avg": 0.30204904079437256,
|
| 1724 |
+
"step": 780,
|
| 1725 |
+
"valid_targets_mean": 3651.2,
|
| 1726 |
+
"valid_targets_min": 1125
|
| 1727 |
+
},
|
| 1728 |
+
{
|
| 1729 |
+
"epoch": 3.8292682926829267,
|
| 1730 |
+
"grad_norm": 0.9046132327931361,
|
| 1731 |
+
"learning_rate": 2.026767224999028e-05,
|
| 1732 |
+
"loss": 0.3032,
|
| 1733 |
+
"loss_nan_ranks": 0,
|
| 1734 |
+
"loss_rank_avg": 0.3154948353767395,
|
| 1735 |
+
"step": 785,
|
| 1736 |
+
"valid_targets_mean": 2786.5,
|
| 1737 |
+
"valid_targets_min": 15
|
| 1738 |
+
},
|
| 1739 |
+
{
|
| 1740 |
+
"epoch": 3.8536585365853657,
|
| 1741 |
+
"grad_norm": 0.7325036224094065,
|
| 1742 |
+
"learning_rate": 2.0024334561413167e-05,
|
| 1743 |
+
"loss": 0.2907,
|
| 1744 |
+
"loss_nan_ranks": 0,
|
| 1745 |
+
"loss_rank_avg": 0.29411929845809937,
|
| 1746 |
+
"step": 790,
|
| 1747 |
+
"valid_targets_mean": 3472.8,
|
| 1748 |
+
"valid_targets_min": 827
|
| 1749 |
+
},
|
| 1750 |
+
{
|
| 1751 |
+
"epoch": 3.8780487804878048,
|
| 1752 |
+
"grad_norm": 0.6498743836905022,
|
| 1753 |
+
"learning_rate": 1.9780993270324063e-05,
|
| 1754 |
+
"loss": 0.2978,
|
| 1755 |
+
"loss_nan_ranks": 0,
|
| 1756 |
+
"loss_rank_avg": 0.29405295848846436,
|
| 1757 |
+
"step": 795,
|
| 1758 |
+
"valid_targets_mean": 3882.9,
|
| 1759 |
+
"valid_targets_min": 803
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 3.902439024390244,
|
| 1763 |
+
"grad_norm": 0.7094727814399049,
|
| 1764 |
+
"learning_rate": 1.953768440120289e-05,
|
| 1765 |
+
"loss": 0.3073,
|
| 1766 |
+
"loss_nan_ranks": 0,
|
| 1767 |
+
"loss_rank_avg": 0.3063426613807678,
|
| 1768 |
+
"step": 800,
|
| 1769 |
+
"valid_targets_mean": 3734.4,
|
| 1770 |
+
"valid_targets_min": 1149
|
| 1771 |
+
},
|
| 1772 |
+
{
|
| 1773 |
+
"epoch": 3.926829268292683,
|
| 1774 |
+
"grad_norm": 0.6952694500011949,
|
| 1775 |
+
"learning_rate": 1.9294443973729768e-05,
|
| 1776 |
+
"loss": 0.296,
|
| 1777 |
+
"loss_nan_ranks": 0,
|
| 1778 |
+
"loss_rank_avg": 0.27972686290740967,
|
| 1779 |
+
"step": 805,
|
| 1780 |
+
"valid_targets_mean": 4442.4,
|
| 1781 |
+
"valid_targets_min": 916
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 3.951219512195122,
|
| 1785 |
+
"grad_norm": 0.7839669200280891,
|
| 1786 |
+
"learning_rate": 1.905130799745268e-05,
|
| 1787 |
+
"loss": 0.2969,
|
| 1788 |
+
"loss_nan_ranks": 0,
|
| 1789 |
+
"loss_rank_avg": 0.31134629249572754,
|
| 1790 |
+
"step": 810,
|
| 1791 |
+
"valid_targets_mean": 3801.6,
|
| 1792 |
+
"valid_targets_min": 1288
|
| 1793 |
+
},
|
| 1794 |
+
{
|
| 1795 |
+
"epoch": 3.975609756097561,
|
| 1796 |
+
"grad_norm": 0.9512260820024343,
|
| 1797 |
+
"learning_rate": 1.8808312466456525e-05,
|
| 1798 |
+
"loss": 0.2856,
|
| 1799 |
+
"loss_nan_ranks": 0,
|
| 1800 |
+
"loss_rank_avg": 0.2893509864807129,
|
| 1801 |
+
"step": 815,
|
| 1802 |
+
"valid_targets_mean": 2878.5,
|
| 1803 |
+
"valid_targets_min": 719
|
| 1804 |
+
},
|
| 1805 |
+
{
|
| 1806 |
+
"epoch": 4.0,
|
| 1807 |
+
"grad_norm": 0.9409702055658681,
|
| 1808 |
+
"learning_rate": 1.856549335403457e-05,
|
| 1809 |
+
"loss": 0.2977,
|
| 1810 |
+
"loss_nan_ranks": 0,
|
| 1811 |
+
"loss_rank_avg": 0.252194344997406,
|
| 1812 |
+
"step": 820,
|
| 1813 |
+
"valid_targets_mean": 2933.2,
|
| 1814 |
+
"valid_targets_min": 15
|
| 1815 |
+
},
|
| 1816 |
+
{
|
| 1817 |
+
"epoch": 4.024390243902439,
|
| 1818 |
+
"grad_norm": 0.776260250287857,
|
| 1819 |
+
"learning_rate": 1.832288660736288e-05,
|
| 1820 |
+
"loss": 0.2709,
|
| 1821 |
+
"loss_nan_ranks": 0,
|
| 1822 |
+
"loss_rank_avg": 0.2807005047798157,
|
| 1823 |
+
"step": 825,
|
| 1824 |
+
"valid_targets_mean": 3608.9,
|
| 1825 |
+
"valid_targets_min": 576
|
| 1826 |
+
},
|
| 1827 |
+
{
|
| 1828 |
+
"epoch": 4.048780487804878,
|
| 1829 |
+
"grad_norm": 0.9103236999012465,
|
| 1830 |
+
"learning_rate": 1.808052814217871e-05,
|
| 1831 |
+
"loss": 0.2656,
|
| 1832 |
+
"loss_nan_ranks": 0,
|
| 1833 |
+
"loss_rank_avg": 0.25947239995002747,
|
| 1834 |
+
"step": 830,
|
| 1835 |
+
"valid_targets_mean": 2974.0,
|
| 1836 |
+
"valid_targets_min": 795
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 4.073170731707317,
|
| 1840 |
+
"grad_norm": 0.8207458807710281,
|
| 1841 |
+
"learning_rate": 1.7838453837463498e-05,
|
| 1842 |
+
"loss": 0.2833,
|
| 1843 |
+
"loss_nan_ranks": 0,
|
| 1844 |
+
"loss_rank_avg": 0.27700158953666687,
|
| 1845 |
+
"step": 835,
|
| 1846 |
+
"valid_targets_mean": 3059.9,
|
| 1847 |
+
"valid_targets_min": 257
|
| 1848 |
+
},
|
| 1849 |
+
{
|
| 1850 |
+
"epoch": 4.097560975609756,
|
| 1851 |
+
"grad_norm": 0.8039571548469557,
|
| 1852 |
+
"learning_rate": 1.7596699530131234e-05,
|
| 1853 |
+
"loss": 0.2617,
|
| 1854 |
+
"loss_nan_ranks": 0,
|
| 1855 |
+
"loss_rank_avg": 0.27044573426246643,
|
| 1856 |
+
"step": 840,
|
| 1857 |
+
"valid_targets_mean": 3390.8,
|
| 1858 |
+
"valid_targets_min": 1003
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 4.121951219512195,
|
| 1862 |
+
"grad_norm": 0.9264411779501436,
|
| 1863 |
+
"learning_rate": 1.735530100972326e-05,
|
| 1864 |
+
"loss": 0.2681,
|
| 1865 |
+
"loss_nan_ranks": 0,
|
| 1866 |
+
"loss_rank_avg": 0.26993459463119507,
|
| 1867 |
+
"step": 845,
|
| 1868 |
+
"valid_targets_mean": 3243.6,
|
| 1869 |
+
"valid_targets_min": 899
|
| 1870 |
+
},
|
| 1871 |
+
{
|
| 1872 |
+
"epoch": 4.146341463414634,
|
| 1873 |
+
"grad_norm": 0.7529964631351728,
|
| 1874 |
+
"learning_rate": 1.711429401310981e-05,
|
| 1875 |
+
"loss": 0.2808,
|
| 1876 |
+
"loss_nan_ranks": 0,
|
| 1877 |
+
"loss_rank_avg": 0.27355536818504333,
|
| 1878 |
+
"step": 850,
|
| 1879 |
+
"valid_targets_mean": 4023.1,
|
| 1880 |
+
"valid_targets_min": 737
|
| 1881 |
+
},
|
| 1882 |
+
{
|
| 1883 |
+
"epoch": 4.170731707317073,
|
| 1884 |
+
"grad_norm": 0.731074690052081,
|
| 1885 |
+
"learning_rate": 1.687371421919961e-05,
|
| 1886 |
+
"loss": 0.2702,
|
| 1887 |
+
"loss_nan_ranks": 0,
|
| 1888 |
+
"loss_rank_avg": 0.28618645668029785,
|
| 1889 |
+
"step": 855,
|
| 1890 |
+
"valid_targets_mean": 3938.9,
|
| 1891 |
+
"valid_targets_min": 1832
|
| 1892 |
+
},
|
| 1893 |
+
{
|
| 1894 |
+
"epoch": 4.195121951219512,
|
| 1895 |
+
"grad_norm": 0.800079732721868,
|
| 1896 |
+
"learning_rate": 1.6633597243657855e-05,
|
| 1897 |
+
"loss": 0.283,
|
| 1898 |
+
"loss_nan_ranks": 0,
|
| 1899 |
+
"loss_rank_avg": 0.27056562900543213,
|
| 1900 |
+
"step": 860,
|
| 1901 |
+
"valid_targets_mean": 3650.1,
|
| 1902 |
+
"valid_targets_min": 1942
|
| 1903 |
+
},
|
| 1904 |
+
{
|
| 1905 |
+
"epoch": 4.219512195121951,
|
| 1906 |
+
"grad_norm": 0.7533482927823113,
|
| 1907 |
+
"learning_rate": 1.6393978633633668e-05,
|
| 1908 |
+
"loss": 0.2692,
|
| 1909 |
+
"loss_nan_ranks": 0,
|
| 1910 |
+
"loss_rank_avg": 0.2656148076057434,
|
| 1911 |
+
"step": 865,
|
| 1912 |
+
"valid_targets_mean": 3817.5,
|
| 1913 |
+
"valid_targets_min": 1813
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 4.2439024390243905,
|
| 1917 |
+
"grad_norm": 0.827289388678526,
|
| 1918 |
+
"learning_rate": 1.6154893862497673e-05,
|
| 1919 |
+
"loss": 0.2949,
|
| 1920 |
+
"loss_nan_ranks": 0,
|
| 1921 |
+
"loss_rank_avg": 0.31596875190734863,
|
| 1922 |
+
"step": 870,
|
| 1923 |
+
"valid_targets_mean": 3127.2,
|
| 1924 |
+
"valid_targets_min": 15
|
| 1925 |
+
},
|
| 1926 |
+
{
|
| 1927 |
+
"epoch": 4.2682926829268295,
|
| 1928 |
+
"grad_norm": 0.7369615846193128,
|
| 1929 |
+
"learning_rate": 1.5916378324590437e-05,
|
| 1930 |
+
"loss": 0.2598,
|
| 1931 |
+
"loss_nan_ranks": 0,
|
| 1932 |
+
"loss_rank_avg": 0.2373199164867401,
|
| 1933 |
+
"step": 875,
|
| 1934 |
+
"valid_targets_mean": 4179.9,
|
| 1935 |
+
"valid_targets_min": 1584
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 4.2926829268292686,
|
| 1939 |
+
"grad_norm": 1.187298637557265,
|
| 1940 |
+
"learning_rate": 1.5678467329982717e-05,
|
| 1941 |
+
"loss": 0.267,
|
| 1942 |
+
"loss_nan_ranks": 0,
|
| 1943 |
+
"loss_rank_avg": 0.2759140729904175,
|
| 1944 |
+
"step": 880,
|
| 1945 |
+
"valid_targets_mean": 2973.3,
|
| 1946 |
+
"valid_targets_min": 228
|
| 1947 |
+
},
|
| 1948 |
+
{
|
| 1949 |
+
"epoch": 4.317073170731708,
|
| 1950 |
+
"grad_norm": 0.8246031829017411,
|
| 1951 |
+
"learning_rate": 1.54411960992481e-05,
|
| 1952 |
+
"loss": 0.2786,
|
| 1953 |
+
"loss_nan_ranks": 0,
|
| 1954 |
+
"loss_rank_avg": 0.2655995190143585,
|
| 1955 |
+
"step": 885,
|
| 1956 |
+
"valid_targets_mean": 3138.6,
|
| 1957 |
+
"valid_targets_min": 474
|
| 1958 |
+
},
|
| 1959 |
+
{
|
| 1960 |
+
"epoch": 4.341463414634147,
|
| 1961 |
+
"grad_norm": 0.8451062461907763,
|
| 1962 |
+
"learning_rate": 1.5204599758248884e-05,
|
| 1963 |
+
"loss": 0.2797,
|
| 1964 |
+
"loss_nan_ranks": 0,
|
| 1965 |
+
"loss_rank_avg": 0.30422964692115784,
|
| 1966 |
+
"step": 890,
|
| 1967 |
+
"valid_targets_mean": 3195.1,
|
| 1968 |
+
"valid_targets_min": 612
|
| 1969 |
+
},
|
| 1970 |
+
{
|
| 1971 |
+
"epoch": 4.365853658536586,
|
| 1972 |
+
"grad_norm": 0.9965472168956042,
|
| 1973 |
+
"learning_rate": 1.4968713332936063e-05,
|
| 1974 |
+
"loss": 0.2648,
|
| 1975 |
+
"loss_nan_ranks": 0,
|
| 1976 |
+
"loss_rank_avg": 0.2871067523956299,
|
| 1977 |
+
"step": 895,
|
| 1978 |
+
"valid_targets_mean": 3281.6,
|
| 1979 |
+
"valid_targets_min": 1371
|
| 1980 |
+
},
|
| 1981 |
+
{
|
| 1982 |
+
"epoch": 4.390243902439025,
|
| 1983 |
+
"grad_norm": 0.826560392213051,
|
| 1984 |
+
"learning_rate": 1.473357174416401e-05,
|
| 1985 |
+
"loss": 0.2589,
|
| 1986 |
+
"loss_nan_ranks": 0,
|
| 1987 |
+
"loss_rank_avg": 0.2745562493801117,
|
| 1988 |
+
"step": 900,
|
| 1989 |
+
"valid_targets_mean": 3754.0,
|
| 1990 |
+
"valid_targets_min": 1695
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 4.414634146341464,
|
| 1994 |
+
"grad_norm": 0.773956566336489,
|
| 1995 |
+
"learning_rate": 1.4499209802520791e-05,
|
| 1996 |
+
"loss": 0.2616,
|
| 1997 |
+
"loss_nan_ranks": 0,
|
| 1998 |
+
"loss_rank_avg": 0.2717684209346771,
|
| 1999 |
+
"step": 905,
|
| 2000 |
+
"valid_targets_mean": 3665.7,
|
| 2001 |
+
"valid_targets_min": 15
|
| 2002 |
+
},
|
| 2003 |
+
{
|
| 2004 |
+
"epoch": 4.439024390243903,
|
| 2005 |
+
"grad_norm": 0.8542711399057813,
|
| 2006 |
+
"learning_rate": 1.426566220317474e-05,
|
| 2007 |
+
"loss": 0.2664,
|
| 2008 |
+
"loss_nan_ranks": 0,
|
| 2009 |
+
"loss_rank_avg": 0.2737499475479126,
|
| 2010 |
+
"step": 910,
|
| 2011 |
+
"valid_targets_mean": 3421.7,
|
| 2012 |
+
"valid_targets_min": 830
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 4.463414634146342,
|
| 2016 |
+
"grad_norm": 0.7962556850092083,
|
| 2017 |
+
"learning_rate": 1.4032963520738183e-05,
|
| 2018 |
+
"loss": 0.2661,
|
| 2019 |
+
"loss_nan_ranks": 0,
|
| 2020 |
+
"loss_rank_avg": 0.2802625596523285,
|
| 2021 |
+
"step": 915,
|
| 2022 |
+
"valid_targets_mean": 3547.3,
|
| 2023 |
+
"valid_targets_min": 1008
|
| 2024 |
+
},
|
| 2025 |
+
{
|
| 2026 |
+
"epoch": 4.487804878048781,
|
| 2027 |
+
"grad_norm": 0.7955484777521536,
|
| 2028 |
+
"learning_rate": 1.3801148204148983e-05,
|
| 2029 |
+
"loss": 0.2625,
|
| 2030 |
+
"loss_nan_ranks": 0,
|
| 2031 |
+
"loss_rank_avg": 0.2767943739891052,
|
| 2032 |
+
"step": 920,
|
| 2033 |
+
"valid_targets_mean": 3616.8,
|
| 2034 |
+
"valid_targets_min": 773
|
| 2035 |
+
},
|
| 2036 |
+
{
|
| 2037 |
+
"epoch": 4.512195121951219,
|
| 2038 |
+
"grad_norm": 0.8832279494046948,
|
| 2039 |
+
"learning_rate": 1.357025057157062e-05,
|
| 2040 |
+
"loss": 0.2732,
|
| 2041 |
+
"loss_nan_ranks": 0,
|
| 2042 |
+
"loss_rank_avg": 0.2521354854106903,
|
| 2043 |
+
"step": 925,
|
| 2044 |
+
"valid_targets_mean": 3143.2,
|
| 2045 |
+
"valid_targets_min": 359
|
| 2046 |
+
},
|
| 2047 |
+
{
|
| 2048 |
+
"epoch": 4.536585365853659,
|
| 2049 |
+
"grad_norm": 0.8306588428706537,
|
| 2050 |
+
"learning_rate": 1.3340304805311802e-05,
|
| 2051 |
+
"loss": 0.2593,
|
| 2052 |
+
"loss_nan_ranks": 0,
|
| 2053 |
+
"loss_rank_avg": 0.2435213327407837,
|
| 2054 |
+
"step": 930,
|
| 2055 |
+
"valid_targets_mean": 2687.6,
|
| 2056 |
+
"valid_targets_min": 15
|
| 2057 |
+
},
|
| 2058 |
+
{
|
| 2059 |
+
"epoch": 4.560975609756097,
|
| 2060 |
+
"grad_norm": 0.9185238023912488,
|
| 2061 |
+
"learning_rate": 1.3111344946765977e-05,
|
| 2062 |
+
"loss": 0.2576,
|
| 2063 |
+
"loss_nan_ranks": 0,
|
| 2064 |
+
"loss_rank_avg": 0.2888595461845398,
|
| 2065 |
+
"step": 935,
|
| 2066 |
+
"valid_targets_mean": 2984.8,
|
| 2067 |
+
"valid_targets_min": 1098
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 4.585365853658536,
|
| 2071 |
+
"grad_norm": 0.7784668165576322,
|
| 2072 |
+
"learning_rate": 1.2883404891371907e-05,
|
| 2073 |
+
"loss": 0.276,
|
| 2074 |
+
"loss_nan_ranks": 0,
|
| 2075 |
+
"loss_rank_avg": 0.26759079098701477,
|
| 2076 |
+
"step": 940,
|
| 2077 |
+
"valid_targets_mean": 3324.6,
|
| 2078 |
+
"valid_targets_min": 283
|
| 2079 |
+
},
|
| 2080 |
+
{
|
| 2081 |
+
"epoch": 4.609756097560975,
|
| 2082 |
+
"grad_norm": 0.7198225881137529,
|
| 2083 |
+
"learning_rate": 1.2656518383595681e-05,
|
| 2084 |
+
"loss": 0.2621,
|
| 2085 |
+
"loss_nan_ranks": 0,
|
| 2086 |
+
"loss_rank_avg": 0.26038920879364014,
|
| 2087 |
+
"step": 945,
|
| 2088 |
+
"valid_targets_mean": 3841.4,
|
| 2089 |
+
"valid_targets_min": 1226
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 4.634146341463414,
|
| 2093 |
+
"grad_norm": 0.8067268967379502,
|
| 2094 |
+
"learning_rate": 1.243071901193519e-05,
|
| 2095 |
+
"loss": 0.2676,
|
| 2096 |
+
"loss_nan_ranks": 0,
|
| 2097 |
+
"loss_rank_avg": 0.2618296444416046,
|
| 2098 |
+
"step": 950,
|
| 2099 |
+
"valid_targets_mean": 3059.1,
|
| 2100 |
+
"valid_targets_min": 1288
|
| 2101 |
+
},
|
| 2102 |
+
{
|
| 2103 |
+
"epoch": 4.658536585365853,
|
| 2104 |
+
"grad_norm": 0.7371365951689539,
|
| 2105 |
+
"learning_rate": 1.2206040203947645e-05,
|
| 2106 |
+
"loss": 0.2661,
|
| 2107 |
+
"loss_nan_ranks": 0,
|
| 2108 |
+
"loss_rank_avg": 0.25615987181663513,
|
| 2109 |
+
"step": 955,
|
| 2110 |
+
"valid_targets_mean": 4461.9,
|
| 2111 |
+
"valid_targets_min": 448
|
| 2112 |
+
},
|
| 2113 |
+
{
|
| 2114 |
+
"epoch": 4.682926829268292,
|
| 2115 |
+
"grad_norm": 0.7267519757978881,
|
| 2116 |
+
"learning_rate": 1.1982515221300917e-05,
|
| 2117 |
+
"loss": 0.2624,
|
| 2118 |
+
"loss_nan_ranks": 0,
|
| 2119 |
+
"loss_rank_avg": 0.24453848600387573,
|
| 2120 |
+
"step": 960,
|
| 2121 |
+
"valid_targets_mean": 3733.6,
|
| 2122 |
+
"valid_targets_min": 1445
|
| 2123 |
+
},
|
| 2124 |
+
{
|
| 2125 |
+
"epoch": 4.7073170731707314,
|
| 2126 |
+
"grad_norm": 0.7178491229060002,
|
| 2127 |
+
"learning_rate": 1.1760177154849473e-05,
|
| 2128 |
+
"loss": 0.2558,
|
| 2129 |
+
"loss_nan_ranks": 0,
|
| 2130 |
+
"loss_rank_avg": 0.23430632054805756,
|
| 2131 |
+
"step": 965,
|
| 2132 |
+
"valid_targets_mean": 3454.4,
|
| 2133 |
+
"valid_targets_min": 647
|
| 2134 |
+
},
|
| 2135 |
+
{
|
| 2136 |
+
"epoch": 4.7317073170731705,
|
| 2137 |
+
"grad_norm": 0.8635688252339446,
|
| 2138 |
+
"learning_rate": 1.1539058919735557e-05,
|
| 2139 |
+
"loss": 0.2636,
|
| 2140 |
+
"loss_nan_ranks": 0,
|
| 2141 |
+
"loss_rank_avg": 0.2552710175514221,
|
| 2142 |
+
"step": 970,
|
| 2143 |
+
"valid_targets_mean": 3115.4,
|
| 2144 |
+
"valid_targets_min": 260
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 4.7560975609756095,
|
| 2148 |
+
"grad_norm": 0.8178807633478934,
|
| 2149 |
+
"learning_rate": 1.1319193250516387e-05,
|
| 2150 |
+
"loss": 0.2684,
|
| 2151 |
+
"loss_nan_ranks": 0,
|
| 2152 |
+
"loss_rank_avg": 0.26949605345726013,
|
| 2153 |
+
"step": 975,
|
| 2154 |
+
"valid_targets_mean": 3029.0,
|
| 2155 |
+
"valid_targets_min": 1160
|
| 2156 |
+
},
|
| 2157 |
+
{
|
| 2158 |
+
"epoch": 4.780487804878049,
|
| 2159 |
+
"grad_norm": 0.8606877647771227,
|
| 2160 |
+
"learning_rate": 1.1100612696318143e-05,
|
| 2161 |
+
"loss": 0.2707,
|
| 2162 |
+
"loss_nan_ranks": 0,
|
| 2163 |
+
"loss_rank_avg": 0.2672426998615265,
|
| 2164 |
+
"step": 980,
|
| 2165 |
+
"valid_targets_mean": 2994.4,
|
| 2166 |
+
"valid_targets_min": 597
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"epoch": 4.804878048780488,
|
| 2170 |
+
"grad_norm": 0.8363734717967222,
|
| 2171 |
+
"learning_rate": 1.0883349616017312e-05,
|
| 2172 |
+
"loss": 0.2746,
|
| 2173 |
+
"loss_nan_ranks": 0,
|
| 2174 |
+
"loss_rank_avg": 0.2739032506942749,
|
| 2175 |
+
"step": 985,
|
| 2176 |
+
"valid_targets_mean": 2968.4,
|
| 2177 |
+
"valid_targets_min": 426
|
| 2178 |
+
},
|
| 2179 |
+
{
|
| 2180 |
+
"epoch": 4.829268292682927,
|
| 2181 |
+
"grad_norm": 0.7709748619894506,
|
| 2182 |
+
"learning_rate": 1.0667436173450278e-05,
|
| 2183 |
+
"loss": 0.2476,
|
| 2184 |
+
"loss_nan_ranks": 0,
|
| 2185 |
+
"loss_rank_avg": 0.26799261569976807,
|
| 2186 |
+
"step": 990,
|
| 2187 |
+
"valid_targets_mean": 3660.3,
|
| 2188 |
+
"valid_targets_min": 1059
|
| 2189 |
+
},
|
| 2190 |
+
{
|
| 2191 |
+
"epoch": 4.853658536585366,
|
| 2192 |
+
"grad_norm": 0.8172048769220687,
|
| 2193 |
+
"learning_rate": 1.0452904332651745e-05,
|
| 2194 |
+
"loss": 0.2621,
|
| 2195 |
+
"loss_nan_ranks": 0,
|
| 2196 |
+
"loss_rank_avg": 0.25125956535339355,
|
| 2197 |
+
"step": 995,
|
| 2198 |
+
"valid_targets_mean": 2627.2,
|
| 2199 |
+
"valid_targets_min": 15
|
| 2200 |
+
},
|
| 2201 |
+
{
|
| 2202 |
+
"epoch": 4.878048780487805,
|
| 2203 |
+
"grad_norm": 0.7823743455001714,
|
| 2204 |
+
"learning_rate": 1.0239785853122784e-05,
|
| 2205 |
+
"loss": 0.265,
|
| 2206 |
+
"loss_nan_ranks": 0,
|
| 2207 |
+
"loss_rank_avg": 0.265064537525177,
|
| 2208 |
+
"step": 1000,
|
| 2209 |
+
"valid_targets_mean": 3875.0,
|
| 2210 |
+
"valid_targets_min": 15
|
| 2211 |
+
},
|
| 2212 |
+
{
|
| 2213 |
+
"epoch": 4.902439024390244,
|
| 2214 |
+
"grad_norm": 0.7650125864589816,
|
| 2215 |
+
"learning_rate": 1.0028112285129058e-05,
|
| 2216 |
+
"loss": 0.2654,
|
| 2217 |
+
"loss_nan_ranks": 0,
|
| 2218 |
+
"loss_rank_avg": 0.29131659865379333,
|
| 2219 |
+
"step": 1005,
|
| 2220 |
+
"valid_targets_mean": 3470.4,
|
| 2221 |
+
"valid_targets_min": 786
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 4.926829268292683,
|
| 2225 |
+
"grad_norm": 0.668827826218542,
|
| 2226 |
+
"learning_rate": 9.81791496503015e-06,
|
| 2227 |
+
"loss": 0.2616,
|
| 2228 |
+
"loss_nan_ranks": 0,
|
| 2229 |
+
"loss_rank_avg": 0.2571777105331421,
|
| 2230 |
+
"step": 1010,
|
| 2231 |
+
"valid_targets_mean": 4372.1,
|
| 2232 |
+
"valid_targets_min": 1355
|
| 2233 |
+
},
|
| 2234 |
+
{
|
| 2235 |
+
"epoch": 4.951219512195122,
|
| 2236 |
+
"grad_norm": 0.6873823999708377,
|
| 2237 |
+
"learning_rate": 9.60922501064049e-06,
|
| 2238 |
+
"loss": 0.2582,
|
| 2239 |
+
"loss_nan_ranks": 0,
|
| 2240 |
+
"loss_rank_avg": 0.2555577754974365,
|
| 2241 |
+
"step": 1015,
|
| 2242 |
+
"valid_targets_mean": 4297.0,
|
| 2243 |
+
"valid_targets_min": 1361
|
| 2244 |
+
},
|
| 2245 |
+
{
|
| 2246 |
+
"epoch": 4.975609756097561,
|
| 2247 |
+
"grad_norm": 0.7801780285443586,
|
| 2248 |
+
"learning_rate": 9.402073316622609e-06,
|
| 2249 |
+
"loss": 0.2536,
|
| 2250 |
+
"loss_nan_ranks": 0,
|
| 2251 |
+
"loss_rank_avg": 0.24865934252738953,
|
| 2252 |
+
"step": 1020,
|
| 2253 |
+
"valid_targets_mean": 3150.4,
|
| 2254 |
+
"valid_targets_min": 875
|
| 2255 |
+
},
|
| 2256 |
+
{
|
| 2257 |
+
"epoch": 5.0,
|
| 2258 |
+
"grad_norm": 0.7967802474346398,
|
| 2259 |
+
"learning_rate": 9.196490549913486e-06,
|
| 2260 |
+
"loss": 0.2622,
|
| 2261 |
+
"loss_nan_ranks": 0,
|
| 2262 |
+
"loss_rank_avg": 0.2609595060348511,
|
| 2263 |
+
"step": 1025,
|
| 2264 |
+
"valid_targets_mean": 3708.4,
|
| 2265 |
+
"valid_targets_min": 1052
|
| 2266 |
+
},
|
| 2267 |
+
{
|
| 2268 |
+
"epoch": 5.024390243902439,
|
| 2269 |
+
"grad_norm": 0.6513129597791458,
|
| 2270 |
+
"learning_rate": 8.992507145184613e-06,
|
| 2271 |
+
"loss": 0.2405,
|
| 2272 |
+
"loss_nan_ranks": 0,
|
| 2273 |
+
"loss_rank_avg": 0.2445092499256134,
|
| 2274 |
+
"step": 1030,
|
| 2275 |
+
"valid_targets_mean": 4137.7,
|
| 2276 |
+
"valid_targets_min": 448
|
| 2277 |
+
},
|
| 2278 |
+
{
|
| 2279 |
+
"epoch": 5.048780487804878,
|
| 2280 |
+
"grad_norm": 0.9278929525940717,
|
| 2281 |
+
"learning_rate": 8.79015330033635e-06,
|
| 2282 |
+
"loss": 0.2438,
|
| 2283 |
+
"loss_nan_ranks": 0,
|
| 2284 |
+
"loss_rank_avg": 0.24177995324134827,
|
| 2285 |
+
"step": 1035,
|
| 2286 |
+
"valid_targets_mean": 3097.0,
|
| 2287 |
+
"valid_targets_min": 1277
|
| 2288 |
+
},
|
| 2289 |
+
{
|
| 2290 |
+
"epoch": 5.073170731707317,
|
| 2291 |
+
"grad_norm": 1.552193652315139,
|
| 2292 |
+
"learning_rate": 8.589458972027483e-06,
|
| 2293 |
+
"loss": 0.2436,
|
| 2294 |
+
"loss_nan_ranks": 0,
|
| 2295 |
+
"loss_rank_avg": 0.24827489256858826,
|
| 2296 |
+
"step": 1040,
|
| 2297 |
+
"valid_targets_mean": 3416.3,
|
| 2298 |
+
"valid_targets_min": 1001
|
| 2299 |
+
},
|
| 2300 |
+
{
|
| 2301 |
+
"epoch": 5.097560975609756,
|
| 2302 |
+
"grad_norm": 0.7093858199198262,
|
| 2303 |
+
"learning_rate": 8.390453871240307e-06,
|
| 2304 |
+
"loss": 0.2453,
|
| 2305 |
+
"loss_nan_ranks": 0,
|
| 2306 |
+
"loss_rank_avg": 0.23724865913391113,
|
| 2307 |
+
"step": 1045,
|
| 2308 |
+
"valid_targets_mean": 4210.4,
|
| 2309 |
+
"valid_targets_min": 1619
|
| 2310 |
+
},
|
| 2311 |
+
{
|
| 2312 |
+
"epoch": 5.121951219512195,
|
| 2313 |
+
"grad_norm": 1.0012021920667462,
|
| 2314 |
+
"learning_rate": 8.193167458882292e-06,
|
| 2315 |
+
"loss": 0.2446,
|
| 2316 |
+
"loss_nan_ranks": 0,
|
| 2317 |
+
"loss_rank_avg": 0.27012312412261963,
|
| 2318 |
+
"step": 1050,
|
| 2319 |
+
"valid_targets_mean": 2548.9,
|
| 2320 |
+
"valid_targets_min": 641
|
| 2321 |
+
},
|
| 2322 |
+
{
|
| 2323 |
+
"epoch": 5.146341463414634,
|
| 2324 |
+
"grad_norm": 0.8690910331604649,
|
| 2325 |
+
"learning_rate": 7.9976289414246e-06,
|
| 2326 |
+
"loss": 0.2452,
|
| 2327 |
+
"loss_nan_ranks": 0,
|
| 2328 |
+
"loss_rank_avg": 0.2542031705379486,
|
| 2329 |
+
"step": 1055,
|
| 2330 |
+
"valid_targets_mean": 2743.4,
|
| 2331 |
+
"valid_targets_min": 744
|
| 2332 |
+
},
|
| 2333 |
+
{
|
| 2334 |
+
"epoch": 5.170731707317073,
|
| 2335 |
+
"grad_norm": 1.044901979443724,
|
| 2336 |
+
"learning_rate": 7.803867266578329e-06,
|
| 2337 |
+
"loss": 0.2373,
|
| 2338 |
+
"loss_nan_ranks": 0,
|
| 2339 |
+
"loss_rank_avg": 0.25191807746887207,
|
| 2340 |
+
"step": 1060,
|
| 2341 |
+
"valid_targets_mean": 3127.7,
|
| 2342 |
+
"valid_targets_min": 906
|
| 2343 |
+
},
|
| 2344 |
+
{
|
| 2345 |
+
"epoch": 5.195121951219512,
|
| 2346 |
+
"grad_norm": 0.9050120681858465,
|
| 2347 |
+
"learning_rate": 7.611911119009092e-06,
|
| 2348 |
+
"loss": 0.2536,
|
| 2349 |
+
"loss_nan_ranks": 0,
|
| 2350 |
+
"loss_rank_avg": 0.2629399001598358,
|
| 2351 |
+
"step": 1065,
|
| 2352 |
+
"valid_targets_mean": 3758.2,
|
| 2353 |
+
"valid_targets_min": 376
|
| 2354 |
+
},
|
| 2355 |
+
{
|
| 2356 |
+
"epoch": 5.219512195121951,
|
| 2357 |
+
"grad_norm": 0.9283099215477023,
|
| 2358 |
+
"learning_rate": 7.4217889160904824e-06,
|
| 2359 |
+
"loss": 0.2544,
|
| 2360 |
+
"loss_nan_ranks": 0,
|
| 2361 |
+
"loss_rank_avg": 0.2586513161659241,
|
| 2362 |
+
"step": 1070,
|
| 2363 |
+
"valid_targets_mean": 2433.7,
|
| 2364 |
+
"valid_targets_min": 228
|
| 2365 |
+
},
|
| 2366 |
+
{
|
| 2367 |
+
"epoch": 5.2439024390243905,
|
| 2368 |
+
"grad_norm": 0.8259428205883735,
|
| 2369 |
+
"learning_rate": 7.233528803697185e-06,
|
| 2370 |
+
"loss": 0.2452,
|
| 2371 |
+
"loss_nan_ranks": 0,
|
| 2372 |
+
"loss_rank_avg": 0.24752004444599152,
|
| 2373 |
+
"step": 1075,
|
| 2374 |
+
"valid_targets_mean": 3368.4,
|
| 2375 |
+
"valid_targets_min": 741
|
| 2376 |
+
},
|
| 2377 |
+
{
|
| 2378 |
+
"epoch": 5.2682926829268295,
|
| 2379 |
+
"grad_norm": 0.7209136325847043,
|
| 2380 |
+
"learning_rate": 7.0471586520381796e-06,
|
| 2381 |
+
"loss": 0.2497,
|
| 2382 |
+
"loss_nan_ranks": 0,
|
| 2383 |
+
"loss_rank_avg": 0.23628446459770203,
|
| 2384 |
+
"step": 1080,
|
| 2385 |
+
"valid_targets_mean": 4003.1,
|
| 2386 |
+
"valid_targets_min": 730
|
| 2387 |
+
},
|
| 2388 |
+
{
|
| 2389 |
+
"epoch": 5.2926829268292686,
|
| 2390 |
+
"grad_norm": 0.7406882461573,
|
| 2391 |
+
"learning_rate": 6.8627060515308275e-06,
|
| 2392 |
+
"loss": 0.2494,
|
| 2393 |
+
"loss_nan_ranks": 0,
|
| 2394 |
+
"loss_rank_avg": 0.23052799701690674,
|
| 2395 |
+
"step": 1085,
|
| 2396 |
+
"valid_targets_mean": 3915.6,
|
| 2397 |
+
"valid_targets_min": 895
|
| 2398 |
+
},
|
| 2399 |
+
{
|
| 2400 |
+
"epoch": 5.317073170731708,
|
| 2401 |
+
"grad_norm": 0.9022661536003552,
|
| 2402 |
+
"learning_rate": 6.6801983087163944e-06,
|
| 2403 |
+
"loss": 0.2514,
|
| 2404 |
+
"loss_nan_ranks": 0,
|
| 2405 |
+
"loss_rank_avg": 0.2609993815422058,
|
| 2406 |
+
"step": 1090,
|
| 2407 |
+
"valid_targets_mean": 3229.1,
|
| 2408 |
+
"valid_targets_min": 1347
|
| 2409 |
+
},
|
| 2410 |
+
{
|
| 2411 |
+
"epoch": 5.341463414634147,
|
| 2412 |
+
"grad_norm": 0.6825772427499014,
|
| 2413 |
+
"learning_rate": 6.499662442217496e-06,
|
| 2414 |
+
"loss": 0.2406,
|
| 2415 |
+
"loss_nan_ranks": 0,
|
| 2416 |
+
"loss_rank_avg": 0.22986085712909698,
|
| 2417 |
+
"step": 1095,
|
| 2418 |
+
"valid_targets_mean": 4128.3,
|
| 2419 |
+
"valid_targets_min": 808
|
| 2420 |
+
},
|
| 2421 |
+
{
|
| 2422 |
+
"epoch": 5.365853658536586,
|
| 2423 |
+
"grad_norm": 0.9787201186348055,
|
| 2424 |
+
"learning_rate": 6.3211251787383146e-06,
|
| 2425 |
+
"loss": 0.2506,
|
| 2426 |
+
"loss_nan_ranks": 0,
|
| 2427 |
+
"loss_rank_avg": 0.26659125089645386,
|
| 2428 |
+
"step": 1100,
|
| 2429 |
+
"valid_targets_mean": 2601.8,
|
| 2430 |
+
"valid_targets_min": 778
|
| 2431 |
+
},
|
| 2432 |
+
{
|
| 2433 |
+
"epoch": 5.390243902439025,
|
| 2434 |
+
"grad_norm": 0.7673661220615522,
|
| 2435 |
+
"learning_rate": 6.144612949107858e-06,
|
| 2436 |
+
"loss": 0.2786,
|
| 2437 |
+
"loss_nan_ranks": 0,
|
| 2438 |
+
"loss_rank_avg": 0.24559593200683594,
|
| 2439 |
+
"step": 1105,
|
| 2440 |
+
"valid_targets_mean": 4265.2,
|
| 2441 |
+
"valid_targets_min": 1373
|
| 2442 |
+
},
|
| 2443 |
+
{
|
| 2444 |
+
"epoch": 5.414634146341464,
|
| 2445 |
+
"grad_norm": 0.9843589364752354,
|
| 2446 |
+
"learning_rate": 5.970151884367206e-06,
|
| 2447 |
+
"loss": 0.2648,
|
| 2448 |
+
"loss_nan_ranks": 0,
|
| 2449 |
+
"loss_rank_avg": 0.2827834486961365,
|
| 2450 |
+
"step": 1110,
|
| 2451 |
+
"valid_targets_mean": 2506.9,
|
| 2452 |
+
"valid_targets_min": 15
|
| 2453 |
+
},
|
| 2454 |
+
{
|
| 2455 |
+
"epoch": 5.439024390243903,
|
| 2456 |
+
"grad_norm": 0.7949717862044275,
|
| 2457 |
+
"learning_rate": 5.7977678119010025e-06,
|
| 2458 |
+
"loss": 0.2537,
|
| 2459 |
+
"loss_nan_ranks": 0,
|
| 2460 |
+
"loss_rank_avg": 0.24906060099601746,
|
| 2461 |
+
"step": 1115,
|
| 2462 |
+
"valid_targets_mean": 3294.9,
|
| 2463 |
+
"valid_targets_min": 444
|
| 2464 |
+
},
|
| 2465 |
+
{
|
| 2466 |
+
"epoch": 5.463414634146342,
|
| 2467 |
+
"grad_norm": 0.9750761574373105,
|
| 2468 |
+
"learning_rate": 5.627486251613934e-06,
|
| 2469 |
+
"loss": 0.2409,
|
| 2470 |
+
"loss_nan_ranks": 0,
|
| 2471 |
+
"loss_rank_avg": 0.24433453381061554,
|
| 2472 |
+
"step": 1120,
|
| 2473 |
+
"valid_targets_mean": 2488.4,
|
| 2474 |
+
"valid_targets_min": 215
|
| 2475 |
+
},
|
| 2476 |
+
{
|
| 2477 |
+
"epoch": 5.487804878048781,
|
| 2478 |
+
"grad_norm": 0.8567488259221477,
|
| 2479 |
+
"learning_rate": 5.4593324121527554e-06,
|
| 2480 |
+
"loss": 0.2649,
|
| 2481 |
+
"loss_nan_ranks": 0,
|
| 2482 |
+
"loss_rank_avg": 0.26337265968322754,
|
| 2483 |
+
"step": 1125,
|
| 2484 |
+
"valid_targets_mean": 3024.3,
|
| 2485 |
+
"valid_targets_min": 959
|
| 2486 |
+
},
|
| 2487 |
+
{
|
| 2488 |
+
"epoch": 5.512195121951219,
|
| 2489 |
+
"grad_norm": 0.812251328892105,
|
| 2490 |
+
"learning_rate": 5.293331187174369e-06,
|
| 2491 |
+
"loss": 0.252,
|
| 2492 |
+
"loss_nan_ranks": 0,
|
| 2493 |
+
"loss_rank_avg": 0.23273511230945587,
|
| 2494 |
+
"step": 1130,
|
| 2495 |
+
"valid_targets_mean": 2921.6,
|
| 2496 |
+
"valid_targets_min": 347
|
| 2497 |
+
},
|
| 2498 |
+
{
|
| 2499 |
+
"epoch": 5.536585365853659,
|
| 2500 |
+
"grad_norm": 1.075912086276383,
|
| 2501 |
+
"learning_rate": 5.129507151660566e-06,
|
| 2502 |
+
"loss": 0.2579,
|
| 2503 |
+
"loss_nan_ranks": 0,
|
| 2504 |
+
"loss_rank_avg": 0.26345235109329224,
|
| 2505 |
+
"step": 1135,
|
| 2506 |
+
"valid_targets_mean": 2968.8,
|
| 2507 |
+
"valid_targets_min": 645
|
| 2508 |
+
},
|
| 2509 |
+
{
|
| 2510 |
+
"epoch": 5.560975609756097,
|
| 2511 |
+
"grad_norm": 0.7590504022526489,
|
| 2512 |
+
"learning_rate": 4.967884558279894e-06,
|
| 2513 |
+
"loss": 0.2434,
|
| 2514 |
+
"loss_nan_ranks": 0,
|
| 2515 |
+
"loss_rank_avg": 0.22883421182632446,
|
| 2516 |
+
"step": 1140,
|
| 2517 |
+
"valid_targets_mean": 3830.3,
|
| 2518 |
+
"valid_targets_min": 477
|
| 2519 |
+
},
|
| 2520 |
+
{
|
| 2521 |
+
"epoch": 5.585365853658536,
|
| 2522 |
+
"grad_norm": 0.9309391468937491,
|
| 2523 |
+
"learning_rate": 4.808487333797272e-06,
|
| 2524 |
+
"loss": 0.2543,
|
| 2525 |
+
"loss_nan_ranks": 0,
|
| 2526 |
+
"loss_rank_avg": 0.26027998328208923,
|
| 2527 |
+
"step": 1145,
|
| 2528 |
+
"valid_targets_mean": 2935.4,
|
| 2529 |
+
"valid_targets_min": 1080
|
| 2530 |
+
},
|
| 2531 |
+
{
|
| 2532 |
+
"epoch": 5.609756097560975,
|
| 2533 |
+
"grad_norm": 0.9093755260374964,
|
| 2534 |
+
"learning_rate": 4.651339075531873e-06,
|
| 2535 |
+
"loss": 0.2622,
|
| 2536 |
+
"loss_nan_ranks": 0,
|
| 2537 |
+
"loss_rank_avg": 0.2955099642276764,
|
| 2538 |
+
"step": 1150,
|
| 2539 |
+
"valid_targets_mean": 2912.1,
|
| 2540 |
+
"valid_targets_min": 1208
|
| 2541 |
+
},
|
| 2542 |
+
{
|
| 2543 |
+
"epoch": 5.634146341463414,
|
| 2544 |
+
"grad_norm": 0.7573696056760568,
|
| 2545 |
+
"learning_rate": 4.496463047863728e-06,
|
| 2546 |
+
"loss": 0.248,
|
| 2547 |
+
"loss_nan_ranks": 0,
|
| 2548 |
+
"loss_rank_avg": 0.24394544959068298,
|
| 2549 |
+
"step": 1155,
|
| 2550 |
+
"valid_targets_mean": 3498.8,
|
| 2551 |
+
"valid_targets_min": 1321
|
| 2552 |
+
},
|
| 2553 |
+
{
|
| 2554 |
+
"epoch": 5.658536585365853,
|
| 2555 |
+
"grad_norm": 0.766437897262525,
|
| 2556 |
+
"learning_rate": 4.343882178789649e-06,
|
| 2557 |
+
"loss": 0.2457,
|
| 2558 |
+
"loss_nan_ranks": 0,
|
| 2559 |
+
"loss_rank_avg": 0.25831907987594604,
|
| 2560 |
+
"step": 1160,
|
| 2561 |
+
"valid_targets_mean": 3925.3,
|
| 2562 |
+
"valid_targets_min": 1203
|
| 2563 |
+
},
|
| 2564 |
+
{
|
| 2565 |
+
"epoch": 5.682926829268292,
|
| 2566 |
+
"grad_norm": 0.685642357911014,
|
| 2567 |
+
"learning_rate": 4.193619056528968e-06,
|
| 2568 |
+
"loss": 0.2536,
|
| 2569 |
+
"loss_nan_ranks": 0,
|
| 2570 |
+
"loss_rank_avg": 0.23799964785575867,
|
| 2571 |
+
"step": 1165,
|
| 2572 |
+
"valid_targets_mean": 4780.6,
|
| 2573 |
+
"valid_targets_min": 1015
|
| 2574 |
+
},
|
| 2575 |
+
{
|
| 2576 |
+
"epoch": 5.7073170731707314,
|
| 2577 |
+
"grad_norm": 0.8782575976505613,
|
| 2578 |
+
"learning_rate": 4.045695926179518e-06,
|
| 2579 |
+
"loss": 0.2331,
|
| 2580 |
+
"loss_nan_ranks": 0,
|
| 2581 |
+
"loss_rank_avg": 0.25392627716064453,
|
| 2582 |
+
"step": 1170,
|
| 2583 |
+
"valid_targets_mean": 3876.3,
|
| 2584 |
+
"valid_targets_min": 15
|
| 2585 |
+
},
|
| 2586 |
+
{
|
| 2587 |
+
"epoch": 5.7317073170731705,
|
| 2588 |
+
"grad_norm": 0.6746053110171998,
|
| 2589 |
+
"learning_rate": 3.900134686424497e-06,
|
| 2590 |
+
"loss": 0.2461,
|
| 2591 |
+
"loss_nan_ranks": 0,
|
| 2592 |
+
"loss_rank_avg": 0.22202837467193604,
|
| 2593 |
+
"step": 1175,
|
| 2594 |
+
"valid_targets_mean": 4104.9,
|
| 2595 |
+
"valid_targets_min": 1062
|
| 2596 |
+
},
|
| 2597 |
+
{
|
| 2598 |
+
"epoch": 5.7560975609756095,
|
| 2599 |
+
"grad_norm": 0.808869320274757,
|
| 2600 |
+
"learning_rate": 3.756956886290497e-06,
|
| 2601 |
+
"loss": 0.2532,
|
| 2602 |
+
"loss_nan_ranks": 0,
|
| 2603 |
+
"loss_rank_avg": 0.26272523403167725,
|
| 2604 |
+
"step": 1180,
|
| 2605 |
+
"valid_targets_mean": 3688.8,
|
| 2606 |
+
"valid_targets_min": 1201
|
| 2607 |
+
},
|
| 2608 |
+
{
|
| 2609 |
+
"epoch": 5.780487804878049,
|
| 2610 |
+
"grad_norm": 0.8464273251163792,
|
| 2611 |
+
"learning_rate": 3.6161837219574423e-06,
|
| 2612 |
+
"loss": 0.244,
|
| 2613 |
+
"loss_nan_ranks": 0,
|
| 2614 |
+
"loss_rank_avg": 0.26603326201438904,
|
| 2615 |
+
"step": 1185,
|
| 2616 |
+
"valid_targets_mean": 2798.3,
|
| 2617 |
+
"valid_targets_min": 1006
|
| 2618 |
+
},
|
| 2619 |
+
{
|
| 2620 |
+
"epoch": 5.804878048780488,
|
| 2621 |
+
"grad_norm": 0.9647474178559449,
|
| 2622 |
+
"learning_rate": 3.477836033620623e-06,
|
| 2623 |
+
"loss": 0.2452,
|
| 2624 |
+
"loss_nan_ranks": 0,
|
| 2625 |
+
"loss_rank_avg": 0.26358962059020996,
|
| 2626 |
+
"step": 1190,
|
| 2627 |
+
"valid_targets_mean": 2401.4,
|
| 2628 |
+
"valid_targets_min": 383
|
| 2629 |
+
},
|
| 2630 |
+
{
|
| 2631 |
+
"epoch": 5.829268292682927,
|
| 2632 |
+
"grad_norm": 0.9304341033869954,
|
| 2633 |
+
"learning_rate": 3.3419343024055385e-06,
|
| 2634 |
+
"loss": 0.2456,
|
| 2635 |
+
"loss_nan_ranks": 0,
|
| 2636 |
+
"loss_rank_avg": 0.2455274760723114,
|
| 2637 |
+
"step": 1195,
|
| 2638 |
+
"valid_targets_mean": 2808.2,
|
| 2639 |
+
"valid_targets_min": 940
|
| 2640 |
+
},
|
| 2641 |
+
{
|
| 2642 |
+
"epoch": 5.853658536585366,
|
| 2643 |
+
"grad_norm": 0.890111073772623,
|
| 2644 |
+
"learning_rate": 3.208498647335818e-06,
|
| 2645 |
+
"loss": 0.2436,
|
| 2646 |
+
"loss_nan_ranks": 0,
|
| 2647 |
+
"loss_rank_avg": 0.2638408839702606,
|
| 2648 |
+
"step": 1200,
|
| 2649 |
+
"valid_targets_mean": 3505.1,
|
| 2650 |
+
"valid_targets_min": 284
|
| 2651 |
+
},
|
| 2652 |
+
{
|
| 2653 |
+
"epoch": 5.878048780487805,
|
| 2654 |
+
"grad_norm": 0.7108698871221218,
|
| 2655 |
+
"learning_rate": 3.0775488223547946e-06,
|
| 2656 |
+
"loss": 0.2497,
|
| 2657 |
+
"loss_nan_ranks": 0,
|
| 2658 |
+
"loss_rank_avg": 0.25884100794792175,
|
| 2659 |
+
"step": 1205,
|
| 2660 |
+
"valid_targets_mean": 4374.9,
|
| 2661 |
+
"valid_targets_min": 859
|
| 2662 |
+
},
|
| 2663 |
+
{
|
| 2664 |
+
"epoch": 5.902439024390244,
|
| 2665 |
+
"grad_norm": 0.7134129262752172,
|
| 2666 |
+
"learning_rate": 2.949104213401126e-06,
|
| 2667 |
+
"loss": 0.2358,
|
| 2668 |
+
"loss_nan_ranks": 0,
|
| 2669 |
+
"loss_rank_avg": 0.23458099365234375,
|
| 2670 |
+
"step": 1210,
|
| 2671 |
+
"valid_targets_mean": 4402.4,
|
| 2672 |
+
"valid_targets_min": 960
|
| 2673 |
+
},
|
| 2674 |
+
{
|
| 2675 |
+
"epoch": 5.926829268292683,
|
| 2676 |
+
"grad_norm": 0.766327851314873,
|
| 2677 |
+
"learning_rate": 2.8231838355388564e-06,
|
| 2678 |
+
"loss": 0.2607,
|
| 2679 |
+
"loss_nan_ranks": 0,
|
| 2680 |
+
"loss_rank_avg": 0.26184824109077454,
|
| 2681 |
+
"step": 1215,
|
| 2682 |
+
"valid_targets_mean": 3815.8,
|
| 2683 |
+
"valid_targets_min": 893
|
| 2684 |
+
},
|
| 2685 |
+
{
|
| 2686 |
+
"epoch": 5.951219512195122,
|
| 2687 |
+
"grad_norm": 1.1353404399035876,
|
| 2688 |
+
"learning_rate": 2.6998063301424183e-06,
|
| 2689 |
+
"loss": 0.2592,
|
| 2690 |
+
"loss_nan_ranks": 0,
|
| 2691 |
+
"loss_rank_avg": 0.25338470935821533,
|
| 2692 |
+
"step": 1220,
|
| 2693 |
+
"valid_targets_mean": 2824.6,
|
| 2694 |
+
"valid_targets_min": 15
|
| 2695 |
+
},
|
| 2696 |
+
{
|
| 2697 |
+
"epoch": 5.975609756097561,
|
| 2698 |
+
"grad_norm": 0.8927504722814279,
|
| 2699 |
+
"learning_rate": 2.5789899621369576e-06,
|
| 2700 |
+
"loss": 0.2397,
|
| 2701 |
+
"loss_nan_ranks": 0,
|
| 2702 |
+
"loss_rank_avg": 0.24313412606716156,
|
| 2703 |
+
"step": 1225,
|
| 2704 |
+
"valid_targets_mean": 3381.8,
|
| 2705 |
+
"valid_targets_min": 317
|
| 2706 |
+
},
|
| 2707 |
+
{
|
| 2708 |
+
"epoch": 6.0,
|
| 2709 |
+
"grad_norm": 0.5993805237959021,
|
| 2710 |
+
"learning_rate": 2.4607526172943573e-06,
|
| 2711 |
+
"loss": 0.2363,
|
| 2712 |
+
"loss_nan_ranks": 0,
|
| 2713 |
+
"loss_rank_avg": 0.22973109781742096,
|
| 2714 |
+
"step": 1230,
|
| 2715 |
+
"valid_targets_mean": 5376.5,
|
| 2716 |
+
"valid_targets_min": 1426
|
| 2717 |
+
},
|
| 2718 |
+
{
|
| 2719 |
+
"epoch": 6.024390243902439,
|
| 2720 |
+
"grad_norm": 0.8354731757428007,
|
| 2721 |
+
"learning_rate": 2.345111799585418e-06,
|
| 2722 |
+
"loss": 0.231,
|
| 2723 |
+
"loss_nan_ranks": 0,
|
| 2724 |
+
"loss_rank_avg": 0.2252325713634491,
|
| 2725 |
+
"step": 1235,
|
| 2726 |
+
"valid_targets_mean": 3432.8,
|
| 2727 |
+
"valid_targets_min": 15
|
| 2728 |
+
},
|
| 2729 |
+
{
|
| 2730 |
+
"epoch": 6.048780487804878,
|
| 2731 |
+
"grad_norm": 0.6750361987361632,
|
| 2732 |
+
"learning_rate": 2.2320846285885536e-06,
|
| 2733 |
+
"loss": 0.2403,
|
| 2734 |
+
"loss_nan_ranks": 0,
|
| 2735 |
+
"loss_rank_avg": 0.18881835043430328,
|
| 2736 |
+
"step": 1240,
|
| 2737 |
+
"valid_targets_mean": 4703.5,
|
| 2738 |
+
"valid_targets_min": 909
|
| 2739 |
+
},
|
| 2740 |
+
{
|
| 2741 |
+
"epoch": 6.073170731707317,
|
| 2742 |
+
"grad_norm": 0.8147913212830856,
|
| 2743 |
+
"learning_rate": 2.1216878369554018e-06,
|
| 2744 |
+
"loss": 0.2407,
|
| 2745 |
+
"loss_nan_ranks": 0,
|
| 2746 |
+
"loss_rank_avg": 0.23672699928283691,
|
| 2747 |
+
"step": 1245,
|
| 2748 |
+
"valid_targets_mean": 3134.4,
|
| 2749 |
+
"valid_targets_min": 730
|
| 2750 |
+
},
|
| 2751 |
+
{
|
| 2752 |
+
"epoch": 6.097560975609756,
|
| 2753 |
+
"grad_norm": 0.7466076107590293,
|
| 2754 |
+
"learning_rate": 2.0139377679336914e-06,
|
| 2755 |
+
"loss": 0.2312,
|
| 2756 |
+
"loss_nan_ranks": 0,
|
| 2757 |
+
"loss_rank_avg": 0.22420379519462585,
|
| 2758 |
+
"step": 1250,
|
| 2759 |
+
"valid_targets_mean": 3622.1,
|
| 2760 |
+
"valid_targets_min": 424
|
| 2761 |
+
},
|
| 2762 |
+
{
|
| 2763 |
+
"epoch": 6.121951219512195,
|
| 2764 |
+
"grad_norm": 0.7651624761198161,
|
| 2765 |
+
"learning_rate": 1.908850372947775e-06,
|
| 2766 |
+
"loss": 0.2404,
|
| 2767 |
+
"loss_nan_ranks": 0,
|
| 2768 |
+
"loss_rank_avg": 0.2247518002986908,
|
| 2769 |
+
"step": 1255,
|
| 2770 |
+
"valid_targets_mean": 4336.2,
|
| 2771 |
+
"valid_targets_min": 641
|
| 2772 |
+
},
|
| 2773 |
+
{
|
| 2774 |
+
"epoch": 6.146341463414634,
|
| 2775 |
+
"grad_norm": 1.0311971502086403,
|
| 2776 |
+
"learning_rate": 1.8064412092371687e-06,
|
| 2777 |
+
"loss": 0.2417,
|
| 2778 |
+
"loss_nan_ranks": 0,
|
| 2779 |
+
"loss_rank_avg": 0.23574134707450867,
|
| 2780 |
+
"step": 1260,
|
| 2781 |
+
"valid_targets_mean": 2097.2,
|
| 2782 |
+
"valid_targets_min": 15
|
| 2783 |
+
},
|
| 2784 |
+
{
|
| 2785 |
+
"epoch": 6.170731707317073,
|
| 2786 |
+
"grad_norm": 0.8187942030961283,
|
| 2787 |
+
"learning_rate": 1.7067254375534426e-06,
|
| 2788 |
+
"loss": 0.2408,
|
| 2789 |
+
"loss_nan_ranks": 0,
|
| 2790 |
+
"loss_rank_avg": 0.22960010170936584,
|
| 2791 |
+
"step": 1265,
|
| 2792 |
+
"valid_targets_mean": 3018.4,
|
| 2793 |
+
"valid_targets_min": 1903
|
| 2794 |
+
},
|
| 2795 |
+
{
|
| 2796 |
+
"epoch": 6.195121951219512,
|
| 2797 |
+
"grad_norm": 1.029146328727017,
|
| 2798 |
+
"learning_rate": 1.6097178199158147e-06,
|
| 2799 |
+
"loss": 0.2446,
|
| 2800 |
+
"loss_nan_ranks": 0,
|
| 2801 |
+
"loss_rank_avg": 0.23877152800559998,
|
| 2802 |
+
"step": 1270,
|
| 2803 |
+
"valid_targets_mean": 3062.9,
|
| 2804 |
+
"valid_targets_min": 15
|
| 2805 |
+
},
|
| 2806 |
+
{
|
| 2807 |
+
"epoch": 6.219512195121951,
|
| 2808 |
+
"grad_norm": 0.8154855502925126,
|
| 2809 |
+
"learning_rate": 1.5154327174257487e-06,
|
| 2810 |
+
"loss": 0.2331,
|
| 2811 |
+
"loss_nan_ranks": 0,
|
| 2812 |
+
"loss_rank_avg": 0.2658793330192566,
|
| 2813 |
+
"step": 1275,
|
| 2814 |
+
"valid_targets_mean": 3184.2,
|
| 2815 |
+
"valid_targets_min": 879
|
| 2816 |
+
},
|
| 2817 |
+
{
|
| 2818 |
+
"epoch": 6.2439024390243905,
|
| 2819 |
+
"grad_norm": 0.8092122258788375,
|
| 2820 |
+
"learning_rate": 1.4238840881409411e-06,
|
| 2821 |
+
"loss": 0.2454,
|
| 2822 |
+
"loss_nan_ranks": 0,
|
| 2823 |
+
"loss_rank_avg": 0.25030407309532166,
|
| 2824 |
+
"step": 1280,
|
| 2825 |
+
"valid_targets_mean": 3467.3,
|
| 2826 |
+
"valid_targets_min": 979
|
| 2827 |
+
},
|
| 2828 |
+
{
|
| 2829 |
+
"epoch": 6.2682926829268295,
|
| 2830 |
+
"grad_norm": 0.7990164724748857,
|
| 2831 |
+
"learning_rate": 1.3350854850089556e-06,
|
| 2832 |
+
"loss": 0.2436,
|
| 2833 |
+
"loss_nan_ranks": 0,
|
| 2834 |
+
"loss_rank_avg": 0.24833282828330994,
|
| 2835 |
+
"step": 1285,
|
| 2836 |
+
"valid_targets_mean": 3502.2,
|
| 2837 |
+
"valid_targets_min": 947
|
| 2838 |
+
},
|
| 2839 |
+
{
|
| 2840 |
+
"epoch": 6.2926829268292686,
|
| 2841 |
+
"grad_norm": 0.9741101055525349,
|
| 2842 |
+
"learning_rate": 1.2490500538608186e-06,
|
| 2843 |
+
"loss": 0.2494,
|
| 2844 |
+
"loss_nan_ranks": 0,
|
| 2845 |
+
"loss_rank_avg": 0.23695826530456543,
|
| 2846 |
+
"step": 1290,
|
| 2847 |
+
"valid_targets_mean": 3103.2,
|
| 2848 |
+
"valid_targets_min": 734
|
| 2849 |
+
},
|
| 2850 |
+
{
|
| 2851 |
+
"epoch": 6.317073170731708,
|
| 2852 |
+
"grad_norm": 0.7866383371157202,
|
| 2853 |
+
"learning_rate": 1.1657905314649054e-06,
|
| 2854 |
+
"loss": 0.2477,
|
| 2855 |
+
"loss_nan_ranks": 0,
|
| 2856 |
+
"loss_rank_avg": 0.23404628038406372,
|
| 2857 |
+
"step": 1295,
|
| 2858 |
+
"valid_targets_mean": 3434.3,
|
| 2859 |
+
"valid_targets_min": 518
|
| 2860 |
+
},
|
| 2861 |
+
{
|
| 2862 |
+
"epoch": 6.341463414634147,
|
| 2863 |
+
"grad_norm": 1.052443778688222,
|
| 2864 |
+
"learning_rate": 1.0853192436413761e-06,
|
| 2865 |
+
"loss": 0.2414,
|
| 2866 |
+
"loss_nan_ranks": 0,
|
| 2867 |
+
"loss_rank_avg": 0.26550811529159546,
|
| 2868 |
+
"step": 1300,
|
| 2869 |
+
"valid_targets_mean": 2595.0,
|
| 2870 |
+
"valid_targets_min": 15
|
| 2871 |
+
},
|
| 2872 |
+
{
|
| 2873 |
+
"epoch": 6.365853658536586,
|
| 2874 |
+
"grad_norm": 0.7368539211291545,
|
| 2875 |
+
"learning_rate": 1.0076481034374597e-06,
|
| 2876 |
+
"loss": 0.2386,
|
| 2877 |
+
"loss_nan_ranks": 0,
|
| 2878 |
+
"loss_rank_avg": 0.22750580310821533,
|
| 2879 |
+
"step": 1305,
|
| 2880 |
+
"valid_targets_mean": 4232.3,
|
| 2881 |
+
"valid_targets_min": 1352
|
| 2882 |
+
},
|
| 2883 |
+
{
|
| 2884 |
+
"epoch": 6.390243902439025,
|
| 2885 |
+
"grad_norm": 0.8172404431791918,
|
| 2886 |
+
"learning_rate": 9.327886093638217e-07,
|
| 2887 |
+
"loss": 0.2396,
|
| 2888 |
+
"loss_nan_ranks": 0,
|
| 2889 |
+
"loss_rank_avg": 0.228601336479187,
|
| 2890 |
+
"step": 1310,
|
| 2891 |
+
"valid_targets_mean": 3308.4,
|
| 2892 |
+
"valid_targets_min": 745
|
| 2893 |
+
},
|
| 2894 |
+
{
|
| 2895 |
+
"epoch": 6.414634146341464,
|
| 2896 |
+
"grad_norm": 0.9556714377855368,
|
| 2897 |
+
"learning_rate": 8.607518436923024e-07,
|
| 2898 |
+
"loss": 0.2352,
|
| 2899 |
+
"loss_nan_ranks": 0,
|
| 2900 |
+
"loss_rank_avg": 0.22058895230293274,
|
| 2901 |
+
"step": 1315,
|
| 2902 |
+
"valid_targets_mean": 3972.5,
|
| 2903 |
+
"valid_targets_min": 1721
|
| 2904 |
+
},
|
| 2905 |
+
{
|
| 2906 |
+
"epoch": 6.439024390243903,
|
| 2907 |
+
"grad_norm": 0.8574584113032061,
|
| 2908 |
+
"learning_rate": 7.915484708153221e-07,
|
| 2909 |
+
"loss": 0.2365,
|
| 2910 |
+
"loss_nan_ranks": 0,
|
| 2911 |
+
"loss_rank_avg": 0.23830386996269226,
|
| 2912 |
+
"step": 1320,
|
| 2913 |
+
"valid_targets_mean": 3130.8,
|
| 2914 |
+
"valid_targets_min": 244
|
| 2915 |
+
},
|
| 2916 |
+
{
|
| 2917 |
+
"epoch": 6.463414634146342,
|
| 2918 |
+
"grad_norm": 0.7867469974906987,
|
| 2919 |
+
"learning_rate": 7.251887356670795e-07,
|
| 2920 |
+
"loss": 0.2262,
|
| 2921 |
+
"loss_nan_ranks": 0,
|
| 2922 |
+
"loss_rank_avg": 0.2254469245672226,
|
| 2923 |
+
"step": 1325,
|
| 2924 |
+
"valid_targets_mean": 3359.5,
|
| 2925 |
+
"valid_targets_min": 880
|
| 2926 |
+
},
|
| 2927 |
+
{
|
| 2928 |
+
"epoch": 6.487804878048781,
|
| 2929 |
+
"grad_norm": 0.7986596207181103,
|
| 2930 |
+
"learning_rate": 6.616824622069029e-07,
|
| 2931 |
+
"loss": 0.2411,
|
| 2932 |
+
"loss_nan_ranks": 0,
|
| 2933 |
+
"loss_rank_avg": 0.22942882776260376,
|
| 2934 |
+
"step": 1330,
|
| 2935 |
+
"valid_targets_mean": 3246.1,
|
| 2936 |
+
"valid_targets_min": 15
|
| 2937 |
+
},
|
| 2938 |
+
{
|
| 2939 |
+
"epoch": 6.512195121951219,
|
| 2940 |
+
"grad_norm": 0.8394244430546116,
|
| 2941 |
+
"learning_rate": 6.010390519648956e-07,
|
| 2942 |
+
"loss": 0.2348,
|
| 2943 |
+
"loss_nan_ranks": 0,
|
| 2944 |
+
"loss_rank_avg": 0.23827606439590454,
|
| 2945 |
+
"step": 1335,
|
| 2946 |
+
"valid_targets_mean": 3922.2,
|
| 2947 |
+
"valid_targets_min": 748
|
| 2948 |
+
},
|
| 2949 |
+
{
|
| 2950 |
+
"epoch": 6.536585365853659,
|
| 2951 |
+
"grad_norm": 1.0223514496941088,
|
| 2952 |
+
"learning_rate": 5.432674826501116e-07,
|
| 2953 |
+
"loss": 0.2437,
|
| 2954 |
+
"loss_nan_ranks": 0,
|
| 2955 |
+
"loss_rank_avg": 0.2501652240753174,
|
| 2956 |
+
"step": 1340,
|
| 2957 |
+
"valid_targets_mean": 2854.8,
|
| 2958 |
+
"valid_targets_min": 730
|
| 2959 |
+
},
|
| 2960 |
+
{
|
| 2961 |
+
"epoch": 6.560975609756097,
|
| 2962 |
+
"grad_norm": 0.8493598124019298,
|
| 2963 |
+
"learning_rate": 4.883763068215142e-07,
|
| 2964 |
+
"loss": 0.2404,
|
| 2965 |
+
"loss_nan_ranks": 0,
|
| 2966 |
+
"loss_rank_avg": 0.2515867352485657,
|
| 2967 |
+
"step": 1345,
|
| 2968 |
+
"valid_targets_mean": 3138.7,
|
| 2969 |
+
"valid_targets_min": 638
|
| 2970 |
+
},
|
| 2971 |
+
{
|
| 2972 |
+
"epoch": 6.585365853658536,
|
| 2973 |
+
"grad_norm": 0.9193382117725917,
|
| 2974 |
+
"learning_rate": 4.363736506218197e-07,
|
| 2975 |
+
"loss": 0.244,
|
| 2976 |
+
"loss_nan_ranks": 0,
|
| 2977 |
+
"loss_rank_avg": 0.26839739084243774,
|
| 2978 |
+
"step": 1350,
|
| 2979 |
+
"valid_targets_mean": 2877.6,
|
| 2980 |
+
"valid_targets_min": 15
|
| 2981 |
+
},
|
| 2982 |
+
{
|
| 2983 |
+
"epoch": 6.609756097560975,
|
| 2984 |
+
"grad_norm": 0.8621845943305007,
|
| 2985 |
+
"learning_rate": 3.8726721257451137e-07,
|
| 2986 |
+
"loss": 0.2422,
|
| 2987 |
+
"loss_nan_ranks": 0,
|
| 2988 |
+
"loss_rank_avg": 0.23818087577819824,
|
| 2989 |
+
"step": 1355,
|
| 2990 |
+
"valid_targets_mean": 3133.2,
|
| 2991 |
+
"valid_targets_min": 699
|
| 2992 |
+
},
|
| 2993 |
+
{
|
| 2994 |
+
"epoch": 6.634146341463414,
|
| 2995 |
+
"grad_norm": 0.9578375613810739,
|
| 2996 |
+
"learning_rate": 3.410642624441352e-07,
|
| 2997 |
+
"loss": 0.2375,
|
| 2998 |
+
"loss_nan_ranks": 0,
|
| 2999 |
+
"loss_rank_avg": 0.24605871737003326,
|
| 3000 |
+
"step": 1360,
|
| 3001 |
+
"valid_targets_mean": 2749.3,
|
| 3002 |
+
"valid_targets_min": 383
|
| 3003 |
+
},
|
| 3004 |
+
{
|
| 3005 |
+
"epoch": 6.658536585365853,
|
| 3006 |
+
"grad_norm": 0.8904495992448669,
|
| 3007 |
+
"learning_rate": 2.977716401600894e-07,
|
| 3008 |
+
"loss": 0.2312,
|
| 3009 |
+
"loss_nan_ranks": 0,
|
| 3010 |
+
"loss_rank_avg": 0.24474391341209412,
|
| 3011 |
+
"step": 1365,
|
| 3012 |
+
"valid_targets_mean": 2796.8,
|
| 3013 |
+
"valid_targets_min": 954
|
| 3014 |
+
},
|
| 3015 |
+
{
|
| 3016 |
+
"epoch": 6.682926829268292,
|
| 3017 |
+
"grad_norm": 0.8518441087464355,
|
| 3018 |
+
"learning_rate": 2.573957548040107e-07,
|
| 3019 |
+
"loss": 0.2184,
|
| 3020 |
+
"loss_nan_ranks": 0,
|
| 3021 |
+
"loss_rank_avg": 0.19270995259284973,
|
| 3022 |
+
"step": 1370,
|
| 3023 |
+
"valid_targets_mean": 3499.1,
|
| 3024 |
+
"valid_targets_min": 893
|
| 3025 |
+
},
|
| 3026 |
+
{
|
| 3027 |
+
"epoch": 6.7073170731707314,
|
| 3028 |
+
"grad_norm": 0.7685128175135679,
|
| 3029 |
+
"learning_rate": 2.1994258366099253e-07,
|
| 3030 |
+
"loss": 0.2417,
|
| 3031 |
+
"loss_nan_ranks": 0,
|
| 3032 |
+
"loss_rank_avg": 0.24854759871959686,
|
| 3033 |
+
"step": 1375,
|
| 3034 |
+
"valid_targets_mean": 3583.8,
|
| 3035 |
+
"valid_targets_min": 744
|
| 3036 |
+
},
|
| 3037 |
+
{
|
| 3038 |
+
"epoch": 6.7317073170731705,
|
| 3039 |
+
"grad_norm": 0.8337143588524125,
|
| 3040 |
+
"learning_rate": 1.854176713346867e-07,
|
| 3041 |
+
"loss": 0.2674,
|
| 3042 |
+
"loss_nan_ranks": 0,
|
| 3043 |
+
"loss_rank_avg": 0.2495569884777069,
|
| 3044 |
+
"step": 1380,
|
| 3045 |
+
"valid_targets_mean": 3424.1,
|
| 3046 |
+
"valid_targets_min": 755
|
| 3047 |
+
},
|
| 3048 |
+
{
|
| 3049 |
+
"epoch": 6.7560975609756095,
|
| 3050 |
+
"grad_norm": 0.8172528668416672,
|
| 3051 |
+
"learning_rate": 1.538261289264842e-07,
|
| 3052 |
+
"loss": 0.2371,
|
| 3053 |
+
"loss_nan_ranks": 0,
|
| 3054 |
+
"loss_rank_avg": 0.2521843910217285,
|
| 3055 |
+
"step": 1385,
|
| 3056 |
+
"valid_targets_mean": 3401.9,
|
| 3057 |
+
"valid_targets_min": 1633
|
| 3058 |
+
},
|
| 3059 |
+
{
|
| 3060 |
+
"epoch": 6.780487804878049,
|
| 3061 |
+
"grad_norm": 0.7445112746003925,
|
| 3062 |
+
"learning_rate": 1.2517263327884944e-07,
|
| 3063 |
+
"loss": 0.2609,
|
| 3064 |
+
"loss_nan_ranks": 0,
|
| 3065 |
+
"loss_rank_avg": 0.2370169758796692,
|
| 3066 |
+
"step": 1390,
|
| 3067 |
+
"valid_targets_mean": 3845.2,
|
| 3068 |
+
"valid_targets_min": 474
|
| 3069 |
+
},
|
| 3070 |
+
{
|
| 3071 |
+
"epoch": 6.804878048780488,
|
| 3072 |
+
"grad_norm": 0.7797928451134836,
|
| 3073 |
+
"learning_rate": 9.94614262829785e-08,
|
| 3074 |
+
"loss": 0.2384,
|
| 3075 |
+
"loss_nan_ranks": 0,
|
| 3076 |
+
"loss_rank_avg": 0.23094391822814941,
|
| 3077 |
+
"step": 1395,
|
| 3078 |
+
"valid_targets_mean": 3594.2,
|
| 3079 |
+
"valid_targets_min": 1001
|
| 3080 |
+
},
|
| 3081 |
+
{
|
| 3082 |
+
"epoch": 6.829268292682927,
|
| 3083 |
+
"grad_norm": 0.8197547024772956,
|
| 3084 |
+
"learning_rate": 7.669631425079705e-08,
|
| 3085 |
+
"loss": 0.2448,
|
| 3086 |
+
"loss_nan_ranks": 0,
|
| 3087 |
+
"loss_rank_avg": 0.23373377323150635,
|
| 3088 |
+
"step": 1400,
|
| 3089 |
+
"valid_targets_mean": 3304.5,
|
| 3090 |
+
"valid_targets_min": 959
|
| 3091 |
+
},
|
| 3092 |
+
{
|
| 3093 |
+
"epoch": 6.853658536585366,
|
| 3094 |
+
"grad_norm": 0.819098164874208,
|
| 3095 |
+
"learning_rate": 5.6880667351497664e-08,
|
| 3096 |
+
"loss": 0.235,
|
| 3097 |
+
"loss_nan_ranks": 0,
|
| 3098 |
+
"loss_rank_avg": 0.2553420662879944,
|
| 3099 |
+
"step": 1405,
|
| 3100 |
+
"valid_targets_mean": 3185.7,
|
| 3101 |
+
"valid_targets_min": 1009
|
| 3102 |
+
},
|
| 3103 |
+
{
|
| 3104 |
+
"epoch": 6.878048780487805,
|
| 3105 |
+
"grad_norm": 0.7376496931499309,
|
| 3106 |
+
"learning_rate": 4.00174191125946e-08,
|
| 3107 |
+
"loss": 0.2342,
|
| 3108 |
+
"loss_nan_ranks": 0,
|
| 3109 |
+
"loss_rank_avg": 0.24166685342788696,
|
| 3110 |
+
"step": 1410,
|
| 3111 |
+
"valid_targets_mean": 4154.6,
|
| 3112 |
+
"valid_targets_min": 1356
|
| 3113 |
+
},
|
| 3114 |
+
{
|
| 3115 |
+
"epoch": 6.902439024390244,
|
| 3116 |
+
"grad_norm": 0.7007641583033006,
|
| 3117 |
+
"learning_rate": 2.6109065985655547e-08,
|
| 3118 |
+
"loss": 0.2368,
|
| 3119 |
+
"loss_nan_ranks": 0,
|
| 3120 |
+
"loss_rank_avg": 0.22494983673095703,
|
| 3121 |
+
"step": 1415,
|
| 3122 |
+
"valid_targets_mean": 4674.7,
|
| 3123 |
+
"valid_targets_min": 1114
|
| 3124 |
+
},
|
| 3125 |
+
{
|
| 3126 |
+
"epoch": 6.926829268292683,
|
| 3127 |
+
"grad_norm": 0.9573315937952928,
|
| 3128 |
+
"learning_rate": 1.515766697672172e-08,
|
| 3129 |
+
"loss": 0.2396,
|
| 3130 |
+
"loss_nan_ranks": 0,
|
| 3131 |
+
"loss_rank_avg": 0.2521101236343384,
|
| 3132 |
+
"step": 1420,
|
| 3133 |
+
"valid_targets_mean": 3319.0,
|
| 3134 |
+
"valid_targets_min": 1386
|
| 3135 |
+
},
|
| 3136 |
+
{
|
| 3137 |
+
"epoch": 6.951219512195122,
|
| 3138 |
+
"grad_norm": 0.7016789049970602,
|
| 3139 |
+
"learning_rate": 7.16484334148504e-09,
|
| 3140 |
+
"loss": 0.2342,
|
| 3141 |
+
"loss_nan_ranks": 0,
|
| 3142 |
+
"loss_rank_avg": 0.2223004400730133,
|
| 3143 |
+
"step": 1425,
|
| 3144 |
+
"valid_targets_mean": 4016.6,
|
| 3145 |
+
"valid_targets_min": 928
|
| 3146 |
+
},
|
| 3147 |
+
{
|
| 3148 |
+
"epoch": 6.975609756097561,
|
| 3149 |
+
"grad_norm": 0.8796275429117553,
|
| 3150 |
+
"learning_rate": 2.1317783452823315e-09,
|
| 3151 |
+
"loss": 0.2378,
|
| 3152 |
+
"loss_nan_ranks": 0,
|
| 3153 |
+
"loss_rank_avg": 0.2460535764694214,
|
| 3154 |
+
"step": 1430,
|
| 3155 |
+
"valid_targets_mean": 2961.6,
|
| 3156 |
+
"valid_targets_min": 1039
|
| 3157 |
+
},
|
| 3158 |
+
{
|
| 3159 |
+
"epoch": 7.0,
|
| 3160 |
+
"grad_norm": 0.8974037466412109,
|
| 3161 |
+
"learning_rate": 5.921708791767344e-11,
|
| 3162 |
+
"loss": 0.2521,
|
| 3163 |
+
"loss_nan_ranks": 0,
|
| 3164 |
+
"loss_rank_avg": 0.24434766173362732,
|
| 3165 |
+
"step": 1435,
|
| 3166 |
+
"valid_targets_mean": 2891.9,
|
| 3167 |
+
"valid_targets_min": 658
|
| 3168 |
+
},
|
| 3169 |
+
{
|
| 3170 |
+
"epoch": 7.0,
|
| 3171 |
+
"loss_nan_ranks": 0,
|
| 3172 |
+
"loss_rank_avg": 0.24434766173362732,
|
| 3173 |
+
"step": 1435,
|
| 3174 |
+
"total_flos": 459870247321600.0,
|
| 3175 |
+
"train_loss": 0.3203928537069713,
|
| 3176 |
+
"train_runtime": 9814.9228,
|
| 3177 |
+
"train_samples_per_second": 2.332,
|
| 3178 |
+
"train_steps_per_second": 0.146,
|
| 3179 |
+
"valid_targets_mean": 2891.9,
|
| 3180 |
+
"valid_targets_min": 658
|
| 3181 |
+
}
|
| 3182 |
+
],
|
| 3183 |
+
"logging_steps": 5,
|
| 3184 |
+
"max_steps": 1435,
|
| 3185 |
+
"num_input_tokens_seen": 0,
|
| 3186 |
+
"num_train_epochs": 7,
|
| 3187 |
+
"save_steps": 200,
|
| 3188 |
+
"stateful_callbacks": {
|
| 3189 |
+
"TrainerControl": {
|
| 3190 |
+
"args": {
|
| 3191 |
+
"should_epoch_stop": false,
|
| 3192 |
+
"should_evaluate": false,
|
| 3193 |
+
"should_log": false,
|
| 3194 |
+
"should_save": true,
|
| 3195 |
+
"should_training_stop": true
|
| 3196 |
+
},
|
| 3197 |
+
"attributes": {}
|
| 3198 |
+
}
|
| 3199 |
+
},
|
| 3200 |
+
"total_flos": 459870247321600.0,
|
| 3201 |
+
"train_batch_size": 1,
|
| 3202 |
+
"trial_name": null,
|
| 3203 |
+
"trial_params": null
|
| 3204 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c3e2f04ef077bc3f818f1df077fcf3f981bd7ad3e1921a112ea0a18268201990
|
| 3 |
+
size 8785
|
training_loss.png
ADDED
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|