Model save
Browse files- .gitattributes +1 -0
- README.md +60 -0
- added_tokens.json +28 -0
- chat_template.jinja +89 -0
- config.json +30 -0
- generation_config.json +13 -0
- merges.txt +0 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +317 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +240 -0
- trainer_log.jsonl +445 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* 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
|
|
|
|
|
|
| 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/Qwen3-1.7B
|
| 5 |
+
tags:
|
| 6 |
+
- llama-factory
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
model-index:
|
| 9 |
+
- name: Qwen3-1.7B-SFT-TinyV_Reasoning_Balanced_v2.1_Qwen3-LR1.0e-5-EPOCHS2
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# Qwen3-1.7B-SFT-TinyV_Reasoning_Balanced_v2.1_Qwen3-LR1.0e-5-EPOCHS2
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [Qwen/Qwen3-1.7B](https://huggingface.co/Qwen/Qwen3-1.7B) on an unknown dataset.
|
| 19 |
+
|
| 20 |
+
## Model description
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Intended uses & limitations
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training and evaluation data
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training procedure
|
| 33 |
+
|
| 34 |
+
### Training hyperparameters
|
| 35 |
+
|
| 36 |
+
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 1e-05
|
| 38 |
+
- train_batch_size: 8
|
| 39 |
+
- eval_batch_size: 8
|
| 40 |
+
- seed: 42
|
| 41 |
+
- distributed_type: multi-GPU
|
| 42 |
+
- num_devices: 8
|
| 43 |
+
- gradient_accumulation_steps: 8
|
| 44 |
+
- total_train_batch_size: 512
|
| 45 |
+
- total_eval_batch_size: 64
|
| 46 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 47 |
+
- lr_scheduler_type: cosine
|
| 48 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 49 |
+
- num_epochs: 2.0
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
|
| 54 |
+
|
| 55 |
+
### Framework versions
|
| 56 |
+
|
| 57 |
+
- Transformers 4.52.4
|
| 58 |
+
- Pytorch 2.7.1+cu126
|
| 59 |
+
- Datasets 3.6.0
|
| 60 |
+
- Tokenizers 0.21.1
|
added_tokens.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</think>": 151668,
|
| 3 |
+
"</tool_call>": 151658,
|
| 4 |
+
"</tool_response>": 151666,
|
| 5 |
+
"<think>": 151667,
|
| 6 |
+
"<tool_call>": 151657,
|
| 7 |
+
"<tool_response>": 151665,
|
| 8 |
+
"<|box_end|>": 151649,
|
| 9 |
+
"<|box_start|>": 151648,
|
| 10 |
+
"<|endoftext|>": 151643,
|
| 11 |
+
"<|file_sep|>": 151664,
|
| 12 |
+
"<|fim_middle|>": 151660,
|
| 13 |
+
"<|fim_pad|>": 151662,
|
| 14 |
+
"<|fim_prefix|>": 151659,
|
| 15 |
+
"<|fim_suffix|>": 151661,
|
| 16 |
+
"<|im_end|>": 151645,
|
| 17 |
+
"<|im_start|>": 151644,
|
| 18 |
+
"<|image_pad|>": 151655,
|
| 19 |
+
"<|object_ref_end|>": 151647,
|
| 20 |
+
"<|object_ref_start|>": 151646,
|
| 21 |
+
"<|quad_end|>": 151651,
|
| 22 |
+
"<|quad_start|>": 151650,
|
| 23 |
+
"<|repo_name|>": 151663,
|
| 24 |
+
"<|video_pad|>": 151656,
|
| 25 |
+
"<|vision_end|>": 151653,
|
| 26 |
+
"<|vision_pad|>": 151654,
|
| 27 |
+
"<|vision_start|>": 151652
|
| 28 |
+
}
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,89 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0].role == 'system' %}
|
| 4 |
+
{{- messages[0].content + '\n\n' }}
|
| 5 |
+
{%- endif %}
|
| 6 |
+
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
| 7 |
+
{%- for tool in tools %}
|
| 8 |
+
{{- "\n" }}
|
| 9 |
+
{{- tool | tojson }}
|
| 10 |
+
{%- endfor %}
|
| 11 |
+
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
| 12 |
+
{%- else %}
|
| 13 |
+
{%- if messages[0].role == 'system' %}
|
| 14 |
+
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
| 15 |
+
{%- endif %}
|
| 16 |
+
{%- endif %}
|
| 17 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 18 |
+
{%- for message in messages[::-1] %}
|
| 19 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 20 |
+
{%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
| 21 |
+
{%- set ns.multi_step_tool = false %}
|
| 22 |
+
{%- set ns.last_query_index = index %}
|
| 23 |
+
{%- endif %}
|
| 24 |
+
{%- endfor %}
|
| 25 |
+
{%- for message in messages %}
|
| 26 |
+
{%- if message.content is string %}
|
| 27 |
+
{%- set content = message.content %}
|
| 28 |
+
{%- else %}
|
| 29 |
+
{%- set content = '' %}
|
| 30 |
+
{%- endif %}
|
| 31 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
| 32 |
+
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 33 |
+
{%- elif message.role == "assistant" %}
|
| 34 |
+
{%- set reasoning_content = '' %}
|
| 35 |
+
{%- if message.reasoning_content is string %}
|
| 36 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 37 |
+
{%- else %}
|
| 38 |
+
{%- if '</think>' in content %}
|
| 39 |
+
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 40 |
+
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
| 41 |
+
{%- endif %}
|
| 42 |
+
{%- endif %}
|
| 43 |
+
{%- if loop.index0 > ns.last_query_index %}
|
| 44 |
+
{%- if loop.last or (not loop.last and reasoning_content) %}
|
| 45 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
| 46 |
+
{%- else %}
|
| 47 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 48 |
+
{%- endif %}
|
| 49 |
+
{%- else %}
|
| 50 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 51 |
+
{%- endif %}
|
| 52 |
+
{%- if message.tool_calls %}
|
| 53 |
+
{%- for tool_call in message.tool_calls %}
|
| 54 |
+
{%- if (loop.first and content) or (not loop.first) %}
|
| 55 |
+
{{- '\n' }}
|
| 56 |
+
{%- endif %}
|
| 57 |
+
{%- if tool_call.function %}
|
| 58 |
+
{%- set tool_call = tool_call.function %}
|
| 59 |
+
{%- endif %}
|
| 60 |
+
{{- '<tool_call>\n{"name": "' }}
|
| 61 |
+
{{- tool_call.name }}
|
| 62 |
+
{{- '", "arguments": ' }}
|
| 63 |
+
{%- if tool_call.arguments is string %}
|
| 64 |
+
{{- tool_call.arguments }}
|
| 65 |
+
{%- else %}
|
| 66 |
+
{{- tool_call.arguments | tojson }}
|
| 67 |
+
{%- endif %}
|
| 68 |
+
{{- '}\n</tool_call>' }}
|
| 69 |
+
{%- endfor %}
|
| 70 |
+
{%- endif %}
|
| 71 |
+
{{- '<|im_end|>\n' }}
|
| 72 |
+
{%- elif message.role == "tool" %}
|
| 73 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 74 |
+
{{- '<|im_start|>user' }}
|
| 75 |
+
{%- endif %}
|
| 76 |
+
{{- '\n<tool_response>\n' }}
|
| 77 |
+
{{- content }}
|
| 78 |
+
{{- '\n</tool_response>' }}
|
| 79 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 80 |
+
{{- '<|im_end|>\n' }}
|
| 81 |
+
{%- endif %}
|
| 82 |
+
{%- endif %}
|
| 83 |
+
{%- endfor %}
|
| 84 |
+
{%- if add_generation_prompt %}
|
| 85 |
+
{{- '<|im_start|>assistant\n' }}
|
| 86 |
+
{%- if enable_thinking is defined and enable_thinking is false %}
|
| 87 |
+
{{- '<think>\n\n</think>\n\n' }}
|
| 88 |
+
{%- endif %}
|
| 89 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151643,
|
| 8 |
+
"eos_token_id": 151645,
|
| 9 |
+
"head_dim": 128,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 2048,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 6144,
|
| 14 |
+
"max_position_embeddings": 40960,
|
| 15 |
+
"max_window_layers": 28,
|
| 16 |
+
"model_type": "qwen3",
|
| 17 |
+
"num_attention_heads": 16,
|
| 18 |
+
"num_hidden_layers": 28,
|
| 19 |
+
"num_key_value_heads": 8,
|
| 20 |
+
"rms_norm_eps": 1e-06,
|
| 21 |
+
"rope_scaling": null,
|
| 22 |
+
"rope_theta": 1000000,
|
| 23 |
+
"sliding_window": null,
|
| 24 |
+
"tie_word_embeddings": true,
|
| 25 |
+
"torch_dtype": "float32",
|
| 26 |
+
"transformers_version": "4.52.4",
|
| 27 |
+
"use_cache": false,
|
| 28 |
+
"use_sliding_window": false,
|
| 29 |
+
"vocab_size": 151936
|
| 30 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 151643,
|
| 9 |
+
"temperature": 0.6,
|
| 10 |
+
"top_k": 20,
|
| 11 |
+
"top_p": 0.95,
|
| 12 |
+
"transformers_version": "4.52.4"
|
| 13 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b0324b00145742e2edf887b3658b66c0e736485de40bdd34a6d33ce9711f7188
|
| 3 |
+
size 4969539560
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:168f5e70d266cf62b121c5134ff0277d36148b7e8dc85c46c13a243d4ba47b3e
|
| 3 |
+
size 1912795688
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,317 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 6882299904
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 7 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 8 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 9 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 10 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 11 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 12 |
+
"model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 18 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 19 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 20 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 21 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 22 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 23 |
+
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 24 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 29 |
+
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 30 |
+
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 31 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 32 |
+
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 33 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 34 |
+
"model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 35 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 36 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 37 |
+
"model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 38 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 39 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 40 |
+
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 41 |
+
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 42 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 43 |
+
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 44 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 45 |
+
"model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 46 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 47 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 48 |
+
"model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 49 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 50 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 51 |
+
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 52 |
+
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 53 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 54 |
+
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 55 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 56 |
+
"model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 57 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 58 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 59 |
+
"model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 60 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 61 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 62 |
+
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 63 |
+
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 64 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 65 |
+
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 66 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 67 |
+
"model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 68 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 69 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 70 |
+
"model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 71 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 72 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 73 |
+
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 74 |
+
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 75 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 76 |
+
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 77 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 78 |
+
"model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 79 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 80 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 81 |
+
"model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 82 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 83 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 84 |
+
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 85 |
+
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 86 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 87 |
+
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 88 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 89 |
+
"model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 90 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 91 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 92 |
+
"model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 93 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 94 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 95 |
+
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 96 |
+
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 97 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 98 |
+
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 99 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 100 |
+
"model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 101 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 102 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 103 |
+
"model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 104 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 105 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 106 |
+
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 107 |
+
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 108 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 109 |
+
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 110 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 111 |
+
"model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 112 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 113 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 114 |
+
"model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 115 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 116 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 117 |
+
"model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 118 |
+
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 119 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 120 |
+
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 121 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 122 |
+
"model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 123 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 124 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 125 |
+
"model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 126 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 127 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 128 |
+
"model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 129 |
+
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 130 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 131 |
+
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 132 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 133 |
+
"model.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 134 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 135 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 136 |
+
"model.layers.19.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 137 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 138 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 139 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 140 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 141 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 142 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 143 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 144 |
+
"model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 145 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 146 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 147 |
+
"model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 148 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 149 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 150 |
+
"model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 151 |
+
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 152 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 153 |
+
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 154 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 155 |
+
"model.layers.20.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 156 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 157 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 158 |
+
"model.layers.20.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 159 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 160 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 161 |
+
"model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 162 |
+
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 163 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 164 |
+
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 165 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 166 |
+
"model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 167 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 168 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 169 |
+
"model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 170 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 171 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 172 |
+
"model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 173 |
+
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 174 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 175 |
+
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 176 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 177 |
+
"model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 178 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 179 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 180 |
+
"model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 181 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 182 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 183 |
+
"model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 184 |
+
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 185 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 186 |
+
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 187 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 188 |
+
"model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 189 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 190 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 191 |
+
"model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 192 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 193 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 194 |
+
"model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 195 |
+
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 196 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 197 |
+
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 198 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 199 |
+
"model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 200 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 201 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 202 |
+
"model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 203 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 204 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 205 |
+
"model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 206 |
+
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 207 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 208 |
+
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 209 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 210 |
+
"model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 211 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 212 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 213 |
+
"model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 214 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 215 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 216 |
+
"model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 217 |
+
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 218 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 219 |
+
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 220 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 221 |
+
"model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 222 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 223 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 224 |
+
"model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 225 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 226 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 227 |
+
"model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 228 |
+
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 229 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 230 |
+
"model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 231 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 232 |
+
"model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 233 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 234 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 235 |
+
"model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 236 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 237 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 238 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 239 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 240 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 241 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 242 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 243 |
+
"model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 244 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 245 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 246 |
+
"model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 247 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 248 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 249 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 250 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 251 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 252 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 253 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 254 |
+
"model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 255 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 256 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 257 |
+
"model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 258 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 259 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 260 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 261 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 262 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 263 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 264 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 265 |
+
"model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 266 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 267 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 268 |
+
"model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 269 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 270 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 271 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 272 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 273 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 274 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 275 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 276 |
+
"model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 277 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 278 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 279 |
+
"model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 280 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 281 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 282 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 283 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 284 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 285 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 286 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 287 |
+
"model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 288 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 289 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 290 |
+
"model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 291 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 292 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 293 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 294 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 295 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 296 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 297 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 298 |
+
"model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 299 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 300 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 301 |
+
"model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 302 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 303 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 304 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 305 |
+
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 306 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 307 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 308 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 309 |
+
"model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 310 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 311 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 312 |
+
"model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 313 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 314 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 315 |
+
"model.norm.weight": "model-00002-of-00002.safetensors"
|
| 316 |
+
}
|
| 317 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
| 3 |
+
size 11422654
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,240 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
},
|
| 181 |
+
"151665": {
|
| 182 |
+
"content": "<tool_response>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"151666": {
|
| 190 |
+
"content": "</tool_response>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
+
},
|
| 197 |
+
"151667": {
|
| 198 |
+
"content": "<think>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": false
|
| 204 |
+
},
|
| 205 |
+
"151668": {
|
| 206 |
+
"content": "</think>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
+
}
|
| 213 |
+
},
|
| 214 |
+
"additional_special_tokens": [
|
| 215 |
+
"<|im_start|>",
|
| 216 |
+
"<|im_end|>",
|
| 217 |
+
"<|object_ref_start|>",
|
| 218 |
+
"<|object_ref_end|>",
|
| 219 |
+
"<|box_start|>",
|
| 220 |
+
"<|box_end|>",
|
| 221 |
+
"<|quad_start|>",
|
| 222 |
+
"<|quad_end|>",
|
| 223 |
+
"<|vision_start|>",
|
| 224 |
+
"<|vision_end|>",
|
| 225 |
+
"<|vision_pad|>",
|
| 226 |
+
"<|image_pad|>",
|
| 227 |
+
"<|video_pad|>"
|
| 228 |
+
],
|
| 229 |
+
"bos_token": null,
|
| 230 |
+
"clean_up_tokenization_spaces": false,
|
| 231 |
+
"eos_token": "<|im_end|>",
|
| 232 |
+
"errors": "replace",
|
| 233 |
+
"extra_special_tokens": {},
|
| 234 |
+
"model_max_length": 131072,
|
| 235 |
+
"pad_token": "<|endoftext|>",
|
| 236 |
+
"padding_side": "right",
|
| 237 |
+
"split_special_tokens": false,
|
| 238 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 239 |
+
"unk_token": null
|
| 240 |
+
}
|
trainer_log.jsonl
ADDED
|
@@ -0,0 +1,445 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 1, "total_steps": 444, "loss": 1.9359, "lr": 0.0, "epoch": 0.004517221908526256, "percentage": 0.23, "elapsed_time": "0:00:04", "remaining_time": "0:34:24"}
|
| 2 |
+
{"current_steps": 2, "total_steps": 444, "loss": 1.9035, "lr": 2.2222222222222224e-07, "epoch": 0.009034443817052512, "percentage": 0.45, "elapsed_time": "0:00:07", "remaining_time": "0:29:09"}
|
| 3 |
+
{"current_steps": 3, "total_steps": 444, "loss": 1.872, "lr": 4.444444444444445e-07, "epoch": 0.01355166572557877, "percentage": 0.68, "elapsed_time": "0:00:11", "remaining_time": "0:27:22"}
|
| 4 |
+
{"current_steps": 4, "total_steps": 444, "loss": 1.8759, "lr": 6.666666666666667e-07, "epoch": 0.018068887634105024, "percentage": 0.9, "elapsed_time": "0:00:14", "remaining_time": "0:26:19"}
|
| 5 |
+
{"current_steps": 5, "total_steps": 444, "loss": 1.8433, "lr": 8.88888888888889e-07, "epoch": 0.02258610954263128, "percentage": 1.13, "elapsed_time": "0:00:17", "remaining_time": "0:25:50"}
|
| 6 |
+
{"current_steps": 6, "total_steps": 444, "loss": 1.8224, "lr": 1.111111111111111e-06, "epoch": 0.02710333145115754, "percentage": 1.35, "elapsed_time": "0:00:20", "remaining_time": "0:25:29"}
|
| 7 |
+
{"current_steps": 7, "total_steps": 444, "loss": 1.7881, "lr": 1.3333333333333334e-06, "epoch": 0.03162055335968379, "percentage": 1.58, "elapsed_time": "0:00:25", "remaining_time": "0:26:01"}
|
| 8 |
+
{"current_steps": 8, "total_steps": 444, "loss": 1.5911, "lr": 1.5555555555555558e-06, "epoch": 0.03613777526821005, "percentage": 1.8, "elapsed_time": "0:00:28", "remaining_time": "0:25:44"}
|
| 9 |
+
{"current_steps": 9, "total_steps": 444, "loss": 1.5803, "lr": 1.777777777777778e-06, "epoch": 0.040654997176736304, "percentage": 2.03, "elapsed_time": "0:00:31", "remaining_time": "0:25:26"}
|
| 10 |
+
{"current_steps": 10, "total_steps": 444, "loss": 1.3045, "lr": 2.0000000000000003e-06, "epoch": 0.04517221908526256, "percentage": 2.25, "elapsed_time": "0:00:34", "remaining_time": "0:25:13"}
|
| 11 |
+
{"current_steps": 11, "total_steps": 444, "loss": 1.2981, "lr": 2.222222222222222e-06, "epoch": 0.049689440993788817, "percentage": 2.48, "elapsed_time": "0:00:38", "remaining_time": "0:25:05"}
|
| 12 |
+
{"current_steps": 12, "total_steps": 444, "loss": 1.2347, "lr": 2.4444444444444447e-06, "epoch": 0.05420666290231508, "percentage": 2.7, "elapsed_time": "0:00:41", "remaining_time": "0:24:59"}
|
| 13 |
+
{"current_steps": 13, "total_steps": 444, "loss": 1.2005, "lr": 2.666666666666667e-06, "epoch": 0.058723884810841336, "percentage": 2.93, "elapsed_time": "0:00:45", "remaining_time": "0:24:55"}
|
| 14 |
+
{"current_steps": 14, "total_steps": 444, "loss": 0.8885, "lr": 2.888888888888889e-06, "epoch": 0.06324110671936758, "percentage": 3.15, "elapsed_time": "0:00:48", "remaining_time": "0:24:47"}
|
| 15 |
+
{"current_steps": 15, "total_steps": 444, "loss": 0.8686, "lr": 3.1111111111111116e-06, "epoch": 0.06775832862789384, "percentage": 3.38, "elapsed_time": "0:00:51", "remaining_time": "0:24:43"}
|
| 16 |
+
{"current_steps": 16, "total_steps": 444, "loss": 0.8102, "lr": 3.3333333333333333e-06, "epoch": 0.0722755505364201, "percentage": 3.6, "elapsed_time": "0:00:55", "remaining_time": "0:24:36"}
|
| 17 |
+
{"current_steps": 17, "total_steps": 444, "loss": 0.7657, "lr": 3.555555555555556e-06, "epoch": 0.07679277244494635, "percentage": 3.83, "elapsed_time": "0:00:58", "remaining_time": "0:24:32"}
|
| 18 |
+
{"current_steps": 18, "total_steps": 444, "loss": 0.7018, "lr": 3.777777777777778e-06, "epoch": 0.08130999435347261, "percentage": 4.05, "elapsed_time": "0:01:02", "remaining_time": "0:24:31"}
|
| 19 |
+
{"current_steps": 19, "total_steps": 444, "loss": 0.7027, "lr": 4.000000000000001e-06, "epoch": 0.08582721626199886, "percentage": 4.28, "elapsed_time": "0:01:05", "remaining_time": "0:24:25"}
|
| 20 |
+
{"current_steps": 20, "total_steps": 444, "loss": 0.6736, "lr": 4.222222222222223e-06, "epoch": 0.09034443817052512, "percentage": 4.5, "elapsed_time": "0:01:08", "remaining_time": "0:24:13"}
|
| 21 |
+
{"current_steps": 21, "total_steps": 444, "loss": 0.6412, "lr": 4.444444444444444e-06, "epoch": 0.09486166007905138, "percentage": 4.73, "elapsed_time": "0:01:12", "remaining_time": "0:24:13"}
|
| 22 |
+
{"current_steps": 22, "total_steps": 444, "loss": 0.6275, "lr": 4.666666666666667e-06, "epoch": 0.09937888198757763, "percentage": 4.95, "elapsed_time": "0:01:15", "remaining_time": "0:24:06"}
|
| 23 |
+
{"current_steps": 23, "total_steps": 444, "loss": 0.6058, "lr": 4.888888888888889e-06, "epoch": 0.1038961038961039, "percentage": 5.18, "elapsed_time": "0:01:19", "remaining_time": "0:24:11"}
|
| 24 |
+
{"current_steps": 24, "total_steps": 444, "loss": 0.5847, "lr": 5.1111111111111115e-06, "epoch": 0.10841332580463016, "percentage": 5.41, "elapsed_time": "0:01:22", "remaining_time": "0:24:07"}
|
| 25 |
+
{"current_steps": 25, "total_steps": 444, "loss": 0.5557, "lr": 5.333333333333334e-06, "epoch": 0.11293054771315642, "percentage": 5.63, "elapsed_time": "0:01:26", "remaining_time": "0:24:02"}
|
| 26 |
+
{"current_steps": 26, "total_steps": 444, "loss": 0.5552, "lr": 5.555555555555557e-06, "epoch": 0.11744776962168267, "percentage": 5.86, "elapsed_time": "0:01:29", "remaining_time": "0:23:56"}
|
| 27 |
+
{"current_steps": 27, "total_steps": 444, "loss": 0.5313, "lr": 5.777777777777778e-06, "epoch": 0.12196499153020893, "percentage": 6.08, "elapsed_time": "0:01:32", "remaining_time": "0:23:50"}
|
| 28 |
+
{"current_steps": 28, "total_steps": 444, "loss": 0.4959, "lr": 6e-06, "epoch": 0.12648221343873517, "percentage": 6.31, "elapsed_time": "0:01:35", "remaining_time": "0:23:44"}
|
| 29 |
+
{"current_steps": 29, "total_steps": 444, "loss": 0.4862, "lr": 6.222222222222223e-06, "epoch": 0.13099943534726144, "percentage": 6.53, "elapsed_time": "0:01:39", "remaining_time": "0:23:41"}
|
| 30 |
+
{"current_steps": 30, "total_steps": 444, "loss": 0.4671, "lr": 6.444444444444445e-06, "epoch": 0.13551665725578768, "percentage": 6.76, "elapsed_time": "0:01:42", "remaining_time": "0:23:35"}
|
| 31 |
+
{"current_steps": 31, "total_steps": 444, "loss": 0.4829, "lr": 6.666666666666667e-06, "epoch": 0.14003387916431395, "percentage": 6.98, "elapsed_time": "0:01:46", "remaining_time": "0:23:32"}
|
| 32 |
+
{"current_steps": 32, "total_steps": 444, "loss": 0.4521, "lr": 6.88888888888889e-06, "epoch": 0.1445511010728402, "percentage": 7.21, "elapsed_time": "0:01:49", "remaining_time": "0:23:29"}
|
| 33 |
+
{"current_steps": 33, "total_steps": 444, "loss": 0.4521, "lr": 7.111111111111112e-06, "epoch": 0.14906832298136646, "percentage": 7.43, "elapsed_time": "0:01:52", "remaining_time": "0:23:24"}
|
| 34 |
+
{"current_steps": 34, "total_steps": 444, "loss": 0.4435, "lr": 7.333333333333333e-06, "epoch": 0.1535855448898927, "percentage": 7.66, "elapsed_time": "0:01:56", "remaining_time": "0:23:20"}
|
| 35 |
+
{"current_steps": 35, "total_steps": 444, "loss": 0.4279, "lr": 7.555555555555556e-06, "epoch": 0.15810276679841898, "percentage": 7.88, "elapsed_time": "0:01:59", "remaining_time": "0:23:16"}
|
| 36 |
+
{"current_steps": 36, "total_steps": 444, "loss": 0.4181, "lr": 7.77777777777778e-06, "epoch": 0.16261998870694522, "percentage": 8.11, "elapsed_time": "0:02:02", "remaining_time": "0:23:11"}
|
| 37 |
+
{"current_steps": 37, "total_steps": 444, "loss": 0.4247, "lr": 8.000000000000001e-06, "epoch": 0.1671372106154715, "percentage": 8.33, "elapsed_time": "0:02:06", "remaining_time": "0:23:06"}
|
| 38 |
+
{"current_steps": 38, "total_steps": 444, "loss": 0.4123, "lr": 8.222222222222222e-06, "epoch": 0.17165443252399773, "percentage": 8.56, "elapsed_time": "0:02:09", "remaining_time": "0:23:01"}
|
| 39 |
+
{"current_steps": 39, "total_steps": 444, "loss": 0.395, "lr": 8.444444444444446e-06, "epoch": 0.176171654432524, "percentage": 8.78, "elapsed_time": "0:02:12", "remaining_time": "0:22:56"}
|
| 40 |
+
{"current_steps": 40, "total_steps": 444, "loss": 0.3852, "lr": 8.666666666666668e-06, "epoch": 0.18068887634105024, "percentage": 9.01, "elapsed_time": "0:02:15", "remaining_time": "0:22:52"}
|
| 41 |
+
{"current_steps": 41, "total_steps": 444, "loss": 0.3914, "lr": 8.888888888888888e-06, "epoch": 0.1852060982495765, "percentage": 9.23, "elapsed_time": "0:02:18", "remaining_time": "0:22:45"}
|
| 42 |
+
{"current_steps": 42, "total_steps": 444, "loss": 0.3722, "lr": 9.111111111111112e-06, "epoch": 0.18972332015810275, "percentage": 9.46, "elapsed_time": "0:02:22", "remaining_time": "0:22:41"}
|
| 43 |
+
{"current_steps": 43, "total_steps": 444, "loss": 0.3632, "lr": 9.333333333333334e-06, "epoch": 0.19424054206662902, "percentage": 9.68, "elapsed_time": "0:02:25", "remaining_time": "0:22:38"}
|
| 44 |
+
{"current_steps": 44, "total_steps": 444, "loss": 0.3827, "lr": 9.555555555555556e-06, "epoch": 0.19875776397515527, "percentage": 9.91, "elapsed_time": "0:02:29", "remaining_time": "0:22:34"}
|
| 45 |
+
{"current_steps": 45, "total_steps": 444, "loss": 0.3779, "lr": 9.777777777777779e-06, "epoch": 0.20327498588368154, "percentage": 10.14, "elapsed_time": "0:02:32", "remaining_time": "0:22:29"}
|
| 46 |
+
{"current_steps": 46, "total_steps": 444, "loss": 0.3632, "lr": 1e-05, "epoch": 0.2077922077922078, "percentage": 10.36, "elapsed_time": "0:02:35", "remaining_time": "0:22:26"}
|
| 47 |
+
{"current_steps": 47, "total_steps": 444, "loss": 0.3567, "lr": 9.999845014267928e-06, "epoch": 0.21230942970073405, "percentage": 10.59, "elapsed_time": "0:02:38", "remaining_time": "0:22:22"}
|
| 48 |
+
{"current_steps": 48, "total_steps": 444, "loss": 0.3489, "lr": 9.999380066679943e-06, "epoch": 0.21682665160926032, "percentage": 10.81, "elapsed_time": "0:02:42", "remaining_time": "0:22:19"}
|
| 49 |
+
{"current_steps": 49, "total_steps": 444, "loss": 0.3631, "lr": 9.998605186060138e-06, "epoch": 0.22134387351778656, "percentage": 11.04, "elapsed_time": "0:02:45", "remaining_time": "0:22:15"}
|
| 50 |
+
{"current_steps": 50, "total_steps": 444, "loss": 0.3407, "lr": 9.997520420446694e-06, "epoch": 0.22586109542631283, "percentage": 11.26, "elapsed_time": "0:02:49", "remaining_time": "0:22:13"}
|
| 51 |
+
{"current_steps": 51, "total_steps": 444, "loss": 0.356, "lr": 9.996125837088883e-06, "epoch": 0.23037831733483907, "percentage": 11.49, "elapsed_time": "0:02:52", "remaining_time": "0:22:09"}
|
| 52 |
+
{"current_steps": 52, "total_steps": 444, "loss": 0.3356, "lr": 9.99442152244292e-06, "epoch": 0.23489553924336534, "percentage": 11.71, "elapsed_time": "0:02:55", "remaining_time": "0:22:03"}
|
| 53 |
+
{"current_steps": 53, "total_steps": 444, "loss": 0.3518, "lr": 9.992407582166582e-06, "epoch": 0.23941276115189158, "percentage": 11.94, "elapsed_time": "0:02:58", "remaining_time": "0:21:59"}
|
| 54 |
+
{"current_steps": 54, "total_steps": 444, "loss": 0.3272, "lr": 9.990084141112674e-06, "epoch": 0.24392998306041785, "percentage": 12.16, "elapsed_time": "0:03:02", "remaining_time": "0:21:58"}
|
| 55 |
+
{"current_steps": 55, "total_steps": 444, "loss": 0.3391, "lr": 9.98745134332128e-06, "epoch": 0.2484472049689441, "percentage": 12.39, "elapsed_time": "0:03:05", "remaining_time": "0:21:53"}
|
| 56 |
+
{"current_steps": 56, "total_steps": 444, "loss": 0.3439, "lr": 9.984509352010839e-06, "epoch": 0.25296442687747034, "percentage": 12.61, "elapsed_time": "0:03:09", "remaining_time": "0:21:49"}
|
| 57 |
+
{"current_steps": 57, "total_steps": 444, "loss": 0.3248, "lr": 9.981258349568018e-06, "epoch": 0.2574816487859966, "percentage": 12.84, "elapsed_time": "0:03:12", "remaining_time": "0:21:45"}
|
| 58 |
+
{"current_steps": 58, "total_steps": 444, "loss": 0.337, "lr": 9.97769853753642e-06, "epoch": 0.2619988706945229, "percentage": 13.06, "elapsed_time": "0:03:15", "remaining_time": "0:21:41"}
|
| 59 |
+
{"current_steps": 59, "total_steps": 444, "loss": 0.3275, "lr": 9.973830136604068e-06, "epoch": 0.26651609260304915, "percentage": 13.29, "elapsed_time": "0:03:19", "remaining_time": "0:21:39"}
|
| 60 |
+
{"current_steps": 60, "total_steps": 444, "loss": 0.3329, "lr": 9.969653386589749e-06, "epoch": 0.27103331451157536, "percentage": 13.51, "elapsed_time": "0:03:22", "remaining_time": "0:21:37"}
|
| 61 |
+
{"current_steps": 61, "total_steps": 444, "loss": 0.3306, "lr": 9.965168546428122e-06, "epoch": 0.27555053642010163, "percentage": 13.74, "elapsed_time": "0:03:26", "remaining_time": "0:21:34"}
|
| 62 |
+
{"current_steps": 62, "total_steps": 444, "loss": 0.3208, "lr": 9.960375894153682e-06, "epoch": 0.2800677583286279, "percentage": 13.96, "elapsed_time": "0:03:29", "remaining_time": "0:21:30"}
|
| 63 |
+
{"current_steps": 63, "total_steps": 444, "loss": 0.3301, "lr": 9.955275726883517e-06, "epoch": 0.2845849802371542, "percentage": 14.19, "elapsed_time": "0:03:32", "remaining_time": "0:21:27"}
|
| 64 |
+
{"current_steps": 64, "total_steps": 444, "loss": 0.3123, "lr": 9.949868360798893e-06, "epoch": 0.2891022021456804, "percentage": 14.41, "elapsed_time": "0:03:36", "remaining_time": "0:21:23"}
|
| 65 |
+
{"current_steps": 65, "total_steps": 444, "loss": 0.3123, "lr": 9.944154131125643e-06, "epoch": 0.29361942405420666, "percentage": 14.64, "elapsed_time": "0:03:39", "remaining_time": "0:21:18"}
|
| 66 |
+
{"current_steps": 66, "total_steps": 444, "loss": 0.3197, "lr": 9.938133392113399e-06, "epoch": 0.2981366459627329, "percentage": 14.86, "elapsed_time": "0:03:42", "remaining_time": "0:21:14"}
|
| 67 |
+
{"current_steps": 67, "total_steps": 444, "loss": 0.3093, "lr": 9.931806517013612e-06, "epoch": 0.3026538678712592, "percentage": 15.09, "elapsed_time": "0:03:45", "remaining_time": "0:21:10"}
|
| 68 |
+
{"current_steps": 68, "total_steps": 444, "loss": 0.3173, "lr": 9.925173898056436e-06, "epoch": 0.3071710897797854, "percentage": 15.32, "elapsed_time": "0:03:49", "remaining_time": "0:21:06"}
|
| 69 |
+
{"current_steps": 69, "total_steps": 444, "loss": 0.3161, "lr": 9.918235946426389e-06, "epoch": 0.3116883116883117, "percentage": 15.54, "elapsed_time": "0:03:52", "remaining_time": "0:21:02"}
|
| 70 |
+
{"current_steps": 70, "total_steps": 444, "loss": 0.3114, "lr": 9.910993092236878e-06, "epoch": 0.31620553359683795, "percentage": 15.77, "elapsed_time": "0:03:55", "remaining_time": "0:20:59"}
|
| 71 |
+
{"current_steps": 71, "total_steps": 444, "loss": 0.3214, "lr": 9.903445784503525e-06, "epoch": 0.3207227555053642, "percentage": 15.99, "elapsed_time": "0:03:58", "remaining_time": "0:20:55"}
|
| 72 |
+
{"current_steps": 72, "total_steps": 444, "loss": 0.3054, "lr": 9.895594491116336e-06, "epoch": 0.32523997741389044, "percentage": 16.22, "elapsed_time": "0:04:02", "remaining_time": "0:20:51"}
|
| 73 |
+
{"current_steps": 73, "total_steps": 444, "loss": 0.3003, "lr": 9.887439698810694e-06, "epoch": 0.3297571993224167, "percentage": 16.44, "elapsed_time": "0:04:05", "remaining_time": "0:20:47"}
|
| 74 |
+
{"current_steps": 74, "total_steps": 444, "loss": 0.3126, "lr": 9.878981913137178e-06, "epoch": 0.334274421230943, "percentage": 16.67, "elapsed_time": "0:04:08", "remaining_time": "0:20:43"}
|
| 75 |
+
{"current_steps": 75, "total_steps": 444, "loss": 0.3022, "lr": 9.870221658430233e-06, "epoch": 0.33879164313946925, "percentage": 16.89, "elapsed_time": "0:04:12", "remaining_time": "0:20:39"}
|
| 76 |
+
{"current_steps": 76, "total_steps": 444, "loss": 0.3035, "lr": 9.861159477775653e-06, "epoch": 0.34330886504799546, "percentage": 17.12, "elapsed_time": "0:04:15", "remaining_time": "0:20:35"}
|
| 77 |
+
{"current_steps": 77, "total_steps": 444, "loss": 0.2932, "lr": 9.851795932976919e-06, "epoch": 0.34782608695652173, "percentage": 17.34, "elapsed_time": "0:04:18", "remaining_time": "0:20:31"}
|
| 78 |
+
{"current_steps": 78, "total_steps": 444, "loss": 0.2986, "lr": 9.84213160452037e-06, "epoch": 0.352343308865048, "percentage": 17.57, "elapsed_time": "0:04:21", "remaining_time": "0:20:29"}
|
| 79 |
+
{"current_steps": 79, "total_steps": 444, "loss": 0.2981, "lr": 9.832167091539215e-06, "epoch": 0.35686053077357427, "percentage": 17.79, "elapsed_time": "0:04:25", "remaining_time": "0:20:26"}
|
| 80 |
+
{"current_steps": 80, "total_steps": 444, "loss": 0.3027, "lr": 9.821903011776385e-06, "epoch": 0.3613777526821005, "percentage": 18.02, "elapsed_time": "0:04:28", "remaining_time": "0:20:23"}
|
| 81 |
+
{"current_steps": 81, "total_steps": 444, "loss": 0.308, "lr": 9.811340001546252e-06, "epoch": 0.36589497459062675, "percentage": 18.24, "elapsed_time": "0:04:32", "remaining_time": "0:20:19"}
|
| 82 |
+
{"current_steps": 82, "total_steps": 444, "loss": 0.3042, "lr": 9.800478715695165e-06, "epoch": 0.370412196499153, "percentage": 18.47, "elapsed_time": "0:04:35", "remaining_time": "0:20:17"}
|
| 83 |
+
{"current_steps": 83, "total_steps": 444, "loss": 0.3074, "lr": 9.789319827560854e-06, "epoch": 0.3749294184076793, "percentage": 18.69, "elapsed_time": "0:04:39", "remaining_time": "0:20:14"}
|
| 84 |
+
{"current_steps": 84, "total_steps": 444, "loss": 0.2981, "lr": 9.777864028930705e-06, "epoch": 0.3794466403162055, "percentage": 18.92, "elapsed_time": "0:04:42", "remaining_time": "0:20:10"}
|
| 85 |
+
{"current_steps": 85, "total_steps": 444, "loss": 0.289, "lr": 9.766112029998847e-06, "epoch": 0.3839638622247318, "percentage": 19.14, "elapsed_time": "0:04:45", "remaining_time": "0:20:06"}
|
| 86 |
+
{"current_steps": 86, "total_steps": 444, "loss": 0.2962, "lr": 9.754064559322147e-06, "epoch": 0.38848108413325805, "percentage": 19.37, "elapsed_time": "0:04:49", "remaining_time": "0:20:03"}
|
| 87 |
+
{"current_steps": 87, "total_steps": 444, "loss": 0.2881, "lr": 9.741722363775029e-06, "epoch": 0.3929983060417843, "percentage": 19.59, "elapsed_time": "0:04:52", "remaining_time": "0:20:00"}
|
| 88 |
+
{"current_steps": 88, "total_steps": 444, "loss": 0.2868, "lr": 9.729086208503174e-06, "epoch": 0.39751552795031053, "percentage": 19.82, "elapsed_time": "0:04:55", "remaining_time": "0:19:56"}
|
| 89 |
+
{"current_steps": 89, "total_steps": 444, "loss": 0.2846, "lr": 9.716156876876096e-06, "epoch": 0.4020327498588368, "percentage": 20.05, "elapsed_time": "0:04:59", "remaining_time": "0:19:52"}
|
| 90 |
+
{"current_steps": 90, "total_steps": 444, "loss": 0.2861, "lr": 9.70293517043857e-06, "epoch": 0.40654997176736307, "percentage": 20.27, "elapsed_time": "0:05:02", "remaining_time": "0:19:49"}
|
| 91 |
+
{"current_steps": 91, "total_steps": 444, "loss": 0.3019, "lr": 9.689421908860928e-06, "epoch": 0.41106719367588934, "percentage": 20.5, "elapsed_time": "0:05:06", "remaining_time": "0:19:47"}
|
| 92 |
+
{"current_steps": 92, "total_steps": 444, "loss": 0.2908, "lr": 9.675617929888271e-06, "epoch": 0.4155844155844156, "percentage": 20.72, "elapsed_time": "0:05:09", "remaining_time": "0:19:43"}
|
| 93 |
+
{"current_steps": 93, "total_steps": 444, "loss": 0.2948, "lr": 9.66152408928851e-06, "epoch": 0.4201016374929418, "percentage": 20.95, "elapsed_time": "0:05:12", "remaining_time": "0:19:40"}
|
| 94 |
+
{"current_steps": 94, "total_steps": 444, "loss": 0.2793, "lr": 9.64714126079933e-06, "epoch": 0.4246188594014681, "percentage": 21.17, "elapsed_time": "0:05:16", "remaining_time": "0:19:37"}
|
| 95 |
+
{"current_steps": 95, "total_steps": 444, "loss": 0.2994, "lr": 9.632470336074009e-06, "epoch": 0.42913608130999437, "percentage": 21.4, "elapsed_time": "0:05:19", "remaining_time": "0:19:35"}
|
| 96 |
+
{"current_steps": 96, "total_steps": 444, "loss": 0.3019, "lr": 9.617512224626153e-06, "epoch": 0.43365330321852064, "percentage": 21.62, "elapsed_time": "0:05:23", "remaining_time": "0:19:32"}
|
| 97 |
+
{"current_steps": 97, "total_steps": 444, "loss": 0.2896, "lr": 9.602267853773301e-06, "epoch": 0.43817052512704685, "percentage": 21.85, "elapsed_time": "0:05:26", "remaining_time": "0:19:28"}
|
| 98 |
+
{"current_steps": 98, "total_steps": 444, "loss": 0.2839, "lr": 9.586738168579446e-06, "epoch": 0.4426877470355731, "percentage": 22.07, "elapsed_time": "0:05:29", "remaining_time": "0:19:24"}
|
| 99 |
+
{"current_steps": 99, "total_steps": 444, "loss": 0.2755, "lr": 9.570924131796437e-06, "epoch": 0.4472049689440994, "percentage": 22.3, "elapsed_time": "0:05:33", "remaining_time": "0:19:20"}
|
| 100 |
+
{"current_steps": 100, "total_steps": 444, "loss": 0.2762, "lr": 9.554826723804304e-06, "epoch": 0.45172219085262566, "percentage": 22.52, "elapsed_time": "0:05:36", "remaining_time": "0:19:17"}
|
| 101 |
+
{"current_steps": 101, "total_steps": 444, "loss": 0.276, "lr": 9.538446942550468e-06, "epoch": 0.4562394127611519, "percentage": 22.75, "elapsed_time": "0:05:39", "remaining_time": "0:19:14"}
|
| 102 |
+
{"current_steps": 102, "total_steps": 444, "loss": 0.2895, "lr": 9.521785803487888e-06, "epoch": 0.46075663466967814, "percentage": 22.97, "elapsed_time": "0:05:42", "remaining_time": "0:19:10"}
|
| 103 |
+
{"current_steps": 103, "total_steps": 444, "loss": 0.2816, "lr": 9.504844339512096e-06, "epoch": 0.4652738565782044, "percentage": 23.2, "elapsed_time": "0:05:46", "remaining_time": "0:19:06"}
|
| 104 |
+
{"current_steps": 104, "total_steps": 444, "loss": 0.2895, "lr": 9.487623600897172e-06, "epoch": 0.4697910784867307, "percentage": 23.42, "elapsed_time": "0:05:49", "remaining_time": "0:19:02"}
|
| 105 |
+
{"current_steps": 105, "total_steps": 444, "loss": 0.2816, "lr": 9.470124655230627e-06, "epoch": 0.4743083003952569, "percentage": 23.65, "elapsed_time": "0:05:52", "remaining_time": "0:18:58"}
|
| 106 |
+
{"current_steps": 106, "total_steps": 444, "loss": 0.2798, "lr": 9.452348587347224e-06, "epoch": 0.47882552230378317, "percentage": 23.87, "elapsed_time": "0:05:55", "remaining_time": "0:18:54"}
|
| 107 |
+
{"current_steps": 107, "total_steps": 444, "loss": 0.2819, "lr": 9.434296499261719e-06, "epoch": 0.48334274421230944, "percentage": 24.1, "elapsed_time": "0:05:59", "remaining_time": "0:18:51"}
|
| 108 |
+
{"current_steps": 108, "total_steps": 444, "loss": 0.2632, "lr": 9.415969510100549e-06, "epoch": 0.4878599661208357, "percentage": 24.32, "elapsed_time": "0:06:02", "remaining_time": "0:18:47"}
|
| 109 |
+
{"current_steps": 109, "total_steps": 444, "loss": 0.2864, "lr": 9.397368756032445e-06, "epoch": 0.4923771880293619, "percentage": 24.55, "elapsed_time": "0:06:05", "remaining_time": "0:18:44"}
|
| 110 |
+
{"current_steps": 110, "total_steps": 444, "loss": 0.2959, "lr": 9.378495390198005e-06, "epoch": 0.4968944099378882, "percentage": 24.77, "elapsed_time": "0:06:09", "remaining_time": "0:18:40"}
|
| 111 |
+
{"current_steps": 111, "total_steps": 444, "loss": 0.2782, "lr": 9.359350582638193e-06, "epoch": 0.5014116318464145, "percentage": 25.0, "elapsed_time": "0:06:12", "remaining_time": "0:18:37"}
|
| 112 |
+
{"current_steps": 112, "total_steps": 444, "loss": 0.2729, "lr": 9.339935520221816e-06, "epoch": 0.5059288537549407, "percentage": 25.23, "elapsed_time": "0:06:15", "remaining_time": "0:18:34"}
|
| 113 |
+
{"current_steps": 113, "total_steps": 444, "loss": 0.2773, "lr": 9.32025140657194e-06, "epoch": 0.510446075663467, "percentage": 25.45, "elapsed_time": "0:06:19", "remaining_time": "0:18:30"}
|
| 114 |
+
{"current_steps": 114, "total_steps": 444, "loss": 0.2823, "lr": 9.30029946199127e-06, "epoch": 0.5149632975719932, "percentage": 25.68, "elapsed_time": "0:06:22", "remaining_time": "0:18:28"}
|
| 115 |
+
{"current_steps": 115, "total_steps": 444, "loss": 0.2708, "lr": 9.280080923386501e-06, "epoch": 0.5194805194805194, "percentage": 25.9, "elapsed_time": "0:06:26", "remaining_time": "0:18:25"}
|
| 116 |
+
{"current_steps": 116, "total_steps": 444, "loss": 0.2769, "lr": 9.259597044191635e-06, "epoch": 0.5239977413890458, "percentage": 26.13, "elapsed_time": "0:06:29", "remaining_time": "0:18:21"}
|
| 117 |
+
{"current_steps": 117, "total_steps": 444, "loss": 0.2746, "lr": 9.238849094290279e-06, "epoch": 0.528514963297572, "percentage": 26.35, "elapsed_time": "0:06:33", "remaining_time": "0:18:18"}
|
| 118 |
+
{"current_steps": 118, "total_steps": 444, "loss": 0.2802, "lr": 9.217838359936914e-06, "epoch": 0.5330321852060983, "percentage": 26.58, "elapsed_time": "0:06:36", "remaining_time": "0:18:16"}
|
| 119 |
+
{"current_steps": 119, "total_steps": 444, "loss": 0.2781, "lr": 9.196566143677157e-06, "epoch": 0.5375494071146245, "percentage": 26.8, "elapsed_time": "0:06:40", "remaining_time": "0:18:13"}
|
| 120 |
+
{"current_steps": 120, "total_steps": 444, "loss": 0.2763, "lr": 9.175033764267013e-06, "epoch": 0.5420666290231507, "percentage": 27.03, "elapsed_time": "0:06:43", "remaining_time": "0:18:09"}
|
| 121 |
+
{"current_steps": 121, "total_steps": 444, "loss": 0.2695, "lr": 9.153242556591115e-06, "epoch": 0.546583850931677, "percentage": 27.25, "elapsed_time": "0:06:46", "remaining_time": "0:18:05"}
|
| 122 |
+
{"current_steps": 122, "total_steps": 444, "loss": 0.295, "lr": 9.131193871579975e-06, "epoch": 0.5511010728402033, "percentage": 27.48, "elapsed_time": "0:06:50", "remaining_time": "0:18:02"}
|
| 123 |
+
{"current_steps": 123, "total_steps": 444, "loss": 0.2791, "lr": 9.108889076126226e-06, "epoch": 0.5556182947487295, "percentage": 27.7, "elapsed_time": "0:06:53", "remaining_time": "0:17:59"}
|
| 124 |
+
{"current_steps": 124, "total_steps": 444, "loss": 0.2802, "lr": 9.08632955299989e-06, "epoch": 0.5601355166572558, "percentage": 27.93, "elapsed_time": "0:06:56", "remaining_time": "0:17:55"}
|
| 125 |
+
{"current_steps": 125, "total_steps": 444, "loss": 0.2672, "lr": 9.06351670076265e-06, "epoch": 0.564652738565782, "percentage": 28.15, "elapsed_time": "0:06:59", "remaining_time": "0:17:51"}
|
| 126 |
+
{"current_steps": 126, "total_steps": 444, "loss": 0.2715, "lr": 9.040451933681148e-06, "epoch": 0.5691699604743083, "percentage": 28.38, "elapsed_time": "0:07:03", "remaining_time": "0:17:47"}
|
| 127 |
+
{"current_steps": 127, "total_steps": 444, "loss": 0.2797, "lr": 9.017136681639307e-06, "epoch": 0.5736871823828346, "percentage": 28.6, "elapsed_time": "0:07:06", "remaining_time": "0:17:44"}
|
| 128 |
+
{"current_steps": 128, "total_steps": 444, "loss": 0.2661, "lr": 8.99357239004969e-06, "epoch": 0.5782044042913608, "percentage": 28.83, "elapsed_time": "0:07:09", "remaining_time": "0:17:40"}
|
| 129 |
+
{"current_steps": 129, "total_steps": 444, "loss": 0.263, "lr": 8.969760519763891e-06, "epoch": 0.5827216261998871, "percentage": 29.05, "elapsed_time": "0:07:13", "remaining_time": "0:17:37"}
|
| 130 |
+
{"current_steps": 130, "total_steps": 444, "loss": 0.2768, "lr": 8.94570254698197e-06, "epoch": 0.5872388481084133, "percentage": 29.28, "elapsed_time": "0:07:16", "remaining_time": "0:17:34"}
|
| 131 |
+
{"current_steps": 131, "total_steps": 444, "loss": 0.2657, "lr": 8.921399963160934e-06, "epoch": 0.5917560700169395, "percentage": 29.5, "elapsed_time": "0:07:19", "remaining_time": "0:17:30"}
|
| 132 |
+
{"current_steps": 132, "total_steps": 444, "loss": 0.2753, "lr": 8.89685427492228e-06, "epoch": 0.5962732919254659, "percentage": 29.73, "elapsed_time": "0:07:23", "remaining_time": "0:17:27"}
|
| 133 |
+
{"current_steps": 133, "total_steps": 444, "loss": 0.2859, "lr": 8.872067003958597e-06, "epoch": 0.6007905138339921, "percentage": 29.95, "elapsed_time": "0:07:26", "remaining_time": "0:17:24"}
|
| 134 |
+
{"current_steps": 134, "total_steps": 444, "loss": 0.2686, "lr": 8.847039686939218e-06, "epoch": 0.6053077357425184, "percentage": 30.18, "elapsed_time": "0:07:29", "remaining_time": "0:17:20"}
|
| 135 |
+
{"current_steps": 135, "total_steps": 444, "loss": 0.2625, "lr": 8.82177387541496e-06, "epoch": 0.6098249576510446, "percentage": 30.41, "elapsed_time": "0:07:33", "remaining_time": "0:17:17"}
|
| 136 |
+
{"current_steps": 136, "total_steps": 444, "loss": 0.2734, "lr": 8.796271135721944e-06, "epoch": 0.6143421795595708, "percentage": 30.63, "elapsed_time": "0:07:36", "remaining_time": "0:17:13"}
|
| 137 |
+
{"current_steps": 137, "total_steps": 444, "loss": 0.2627, "lr": 8.770533048884483e-06, "epoch": 0.6188594014680971, "percentage": 30.86, "elapsed_time": "0:07:39", "remaining_time": "0:17:09"}
|
| 138 |
+
{"current_steps": 138, "total_steps": 444, "loss": 0.2738, "lr": 8.744561210517067e-06, "epoch": 0.6233766233766234, "percentage": 31.08, "elapsed_time": "0:07:42", "remaining_time": "0:17:06"}
|
| 139 |
+
{"current_steps": 139, "total_steps": 444, "loss": 0.2652, "lr": 8.71835723072545e-06, "epoch": 0.6278938452851497, "percentage": 31.31, "elapsed_time": "0:07:46", "remaining_time": "0:17:03"}
|
| 140 |
+
{"current_steps": 140, "total_steps": 444, "loss": 0.2764, "lr": 8.691922734006828e-06, "epoch": 0.6324110671936759, "percentage": 31.53, "elapsed_time": "0:07:49", "remaining_time": "0:16:59"}
|
| 141 |
+
{"current_steps": 141, "total_steps": 444, "loss": 0.2587, "lr": 8.665259359149132e-06, "epoch": 0.6369282891022021, "percentage": 31.76, "elapsed_time": "0:07:52", "remaining_time": "0:16:56"}
|
| 142 |
+
{"current_steps": 142, "total_steps": 444, "loss": 0.2635, "lr": 8.638368759129433e-06, "epoch": 0.6414455110107284, "percentage": 31.98, "elapsed_time": "0:07:56", "remaining_time": "0:16:52"}
|
| 143 |
+
{"current_steps": 143, "total_steps": 444, "loss": 0.2555, "lr": 8.611252601011457e-06, "epoch": 0.6459627329192547, "percentage": 32.21, "elapsed_time": "0:07:59", "remaining_time": "0:16:49"}
|
| 144 |
+
{"current_steps": 144, "total_steps": 444, "loss": 0.2843, "lr": 8.583912565842258e-06, "epoch": 0.6504799548277809, "percentage": 32.43, "elapsed_time": "0:08:02", "remaining_time": "0:16:45"}
|
| 145 |
+
{"current_steps": 145, "total_steps": 444, "loss": 0.2762, "lr": 8.556350348547978e-06, "epoch": 0.6549971767363072, "percentage": 32.66, "elapsed_time": "0:08:06", "remaining_time": "0:16:42"}
|
| 146 |
+
{"current_steps": 146, "total_steps": 444, "loss": 0.2637, "lr": 8.528567657828785e-06, "epoch": 0.6595143986448334, "percentage": 32.88, "elapsed_time": "0:08:09", "remaining_time": "0:16:39"}
|
| 147 |
+
{"current_steps": 147, "total_steps": 444, "loss": 0.2737, "lr": 8.500566216052948e-06, "epoch": 0.6640316205533597, "percentage": 33.11, "elapsed_time": "0:08:13", "remaining_time": "0:16:36"}
|
| 148 |
+
{"current_steps": 148, "total_steps": 444, "loss": 0.2623, "lr": 8.472347759150044e-06, "epoch": 0.668548842461886, "percentage": 33.33, "elapsed_time": "0:08:16", "remaining_time": "0:16:32"}
|
| 149 |
+
{"current_steps": 149, "total_steps": 444, "loss": 0.2708, "lr": 8.443914036503356e-06, "epoch": 0.6730660643704122, "percentage": 33.56, "elapsed_time": "0:08:19", "remaining_time": "0:16:29"}
|
| 150 |
+
{"current_steps": 150, "total_steps": 444, "loss": 0.258, "lr": 8.415266810841412e-06, "epoch": 0.6775832862789385, "percentage": 33.78, "elapsed_time": "0:08:23", "remaining_time": "0:16:26"}
|
| 151 |
+
{"current_steps": 151, "total_steps": 444, "loss": 0.2674, "lr": 8.386407858128707e-06, "epoch": 0.6821005081874647, "percentage": 34.01, "elapsed_time": "0:08:26", "remaining_time": "0:16:22"}
|
| 152 |
+
{"current_steps": 152, "total_steps": 444, "loss": 0.2702, "lr": 8.357338967455605e-06, "epoch": 0.6866177300959909, "percentage": 34.23, "elapsed_time": "0:08:29", "remaining_time": "0:16:19"}
|
| 153 |
+
{"current_steps": 153, "total_steps": 444, "loss": 0.2619, "lr": 8.32806194092743e-06, "epoch": 0.6911349520045172, "percentage": 34.46, "elapsed_time": "0:08:33", "remaining_time": "0:16:16"}
|
| 154 |
+
{"current_steps": 154, "total_steps": 444, "loss": 0.2534, "lr": 8.298578593552737e-06, "epoch": 0.6956521739130435, "percentage": 34.68, "elapsed_time": "0:08:36", "remaining_time": "0:16:13"}
|
| 155 |
+
{"current_steps": 155, "total_steps": 444, "loss": 0.2698, "lr": 8.268890753130794e-06, "epoch": 0.7001693958215698, "percentage": 34.91, "elapsed_time": "0:08:40", "remaining_time": "0:16:10"}
|
| 156 |
+
{"current_steps": 156, "total_steps": 444, "loss": 0.2599, "lr": 8.239000260138277e-06, "epoch": 0.704686617730096, "percentage": 35.14, "elapsed_time": "0:08:43", "remaining_time": "0:16:07"}
|
| 157 |
+
{"current_steps": 157, "total_steps": 444, "loss": 0.2678, "lr": 8.208908967615159e-06, "epoch": 0.7092038396386222, "percentage": 35.36, "elapsed_time": "0:08:47", "remaining_time": "0:16:03"}
|
| 158 |
+
{"current_steps": 158, "total_steps": 444, "loss": 0.2712, "lr": 8.178618741049841e-06, "epoch": 0.7137210615471485, "percentage": 35.59, "elapsed_time": "0:08:50", "remaining_time": "0:16:00"}
|
| 159 |
+
{"current_steps": 159, "total_steps": 444, "loss": 0.2635, "lr": 8.148131458263499e-06, "epoch": 0.7182382834556748, "percentage": 35.81, "elapsed_time": "0:08:54", "remaining_time": "0:15:57"}
|
| 160 |
+
{"current_steps": 160, "total_steps": 444, "loss": 0.2688, "lr": 8.117449009293668e-06, "epoch": 0.722755505364201, "percentage": 36.04, "elapsed_time": "0:08:57", "remaining_time": "0:15:53"}
|
| 161 |
+
{"current_steps": 161, "total_steps": 444, "loss": 0.2723, "lr": 8.086573296277078e-06, "epoch": 0.7272727272727273, "percentage": 36.26, "elapsed_time": "0:09:00", "remaining_time": "0:15:50"}
|
| 162 |
+
{"current_steps": 162, "total_steps": 444, "loss": 0.262, "lr": 8.055506233331718e-06, "epoch": 0.7317899491812535, "percentage": 36.49, "elapsed_time": "0:09:03", "remaining_time": "0:15:46"}
|
| 163 |
+
{"current_steps": 163, "total_steps": 444, "loss": 0.2654, "lr": 8.024249746438189e-06, "epoch": 0.7363071710897798, "percentage": 36.71, "elapsed_time": "0:09:07", "remaining_time": "0:15:43"}
|
| 164 |
+
{"current_steps": 164, "total_steps": 444, "loss": 0.2656, "lr": 7.99280577332029e-06, "epoch": 0.740824392998306, "percentage": 36.94, "elapsed_time": "0:09:10", "remaining_time": "0:15:39"}
|
| 165 |
+
{"current_steps": 165, "total_steps": 444, "loss": 0.2662, "lr": 7.961176263324902e-06, "epoch": 0.7453416149068323, "percentage": 37.16, "elapsed_time": "0:09:13", "remaining_time": "0:15:36"}
|
| 166 |
+
{"current_steps": 166, "total_steps": 444, "loss": 0.257, "lr": 7.929363177301124e-06, "epoch": 0.7498588368153586, "percentage": 37.39, "elapsed_time": "0:09:17", "remaining_time": "0:15:32"}
|
| 167 |
+
{"current_steps": 167, "total_steps": 444, "loss": 0.2547, "lr": 7.897368487478733e-06, "epoch": 0.7543760587238848, "percentage": 37.61, "elapsed_time": "0:09:20", "remaining_time": "0:15:29"}
|
| 168 |
+
{"current_steps": 168, "total_steps": 444, "loss": 0.2605, "lr": 7.865194177345894e-06, "epoch": 0.758893280632411, "percentage": 37.84, "elapsed_time": "0:09:23", "remaining_time": "0:15:25"}
|
| 169 |
+
{"current_steps": 169, "total_steps": 444, "loss": 0.2513, "lr": 7.832842241526212e-06, "epoch": 0.7634105025409373, "percentage": 38.06, "elapsed_time": "0:09:27", "remaining_time": "0:15:22"}
|
| 170 |
+
{"current_steps": 170, "total_steps": 444, "loss": 0.27, "lr": 7.800314685655072e-06, "epoch": 0.7679277244494636, "percentage": 38.29, "elapsed_time": "0:09:30", "remaining_time": "0:15:19"}
|
| 171 |
+
{"current_steps": 171, "total_steps": 444, "loss": 0.257, "lr": 7.767613526255296e-06, "epoch": 0.7724449463579899, "percentage": 38.51, "elapsed_time": "0:09:33", "remaining_time": "0:15:15"}
|
| 172 |
+
{"current_steps": 172, "total_steps": 444, "loss": 0.2711, "lr": 7.734740790612137e-06, "epoch": 0.7769621682665161, "percentage": 38.74, "elapsed_time": "0:09:36", "remaining_time": "0:15:12"}
|
| 173 |
+
{"current_steps": 173, "total_steps": 444, "loss": 0.2395, "lr": 7.70169851664759e-06, "epoch": 0.7814793901750423, "percentage": 38.96, "elapsed_time": "0:09:40", "remaining_time": "0:15:09"}
|
| 174 |
+
{"current_steps": 174, "total_steps": 444, "loss": 0.2784, "lr": 7.668488752794067e-06, "epoch": 0.7859966120835686, "percentage": 39.19, "elapsed_time": "0:09:43", "remaining_time": "0:15:06"}
|
| 175 |
+
{"current_steps": 175, "total_steps": 444, "loss": 0.2601, "lr": 7.635113557867395e-06, "epoch": 0.7905138339920948, "percentage": 39.41, "elapsed_time": "0:09:47", "remaining_time": "0:15:02"}
|
| 176 |
+
{"current_steps": 176, "total_steps": 444, "loss": 0.2502, "lr": 7.6015750009391776e-06, "epoch": 0.7950310559006211, "percentage": 39.64, "elapsed_time": "0:09:50", "remaining_time": "0:14:59"}
|
| 177 |
+
{"current_steps": 177, "total_steps": 444, "loss": 0.2479, "lr": 7.5678751612085344e-06, "epoch": 0.7995482778091474, "percentage": 39.86, "elapsed_time": "0:09:54", "remaining_time": "0:14:56"}
|
| 178 |
+
{"current_steps": 178, "total_steps": 444, "loss": 0.2606, "lr": 7.5340161278732e-06, "epoch": 0.8040654997176736, "percentage": 40.09, "elapsed_time": "0:09:57", "remaining_time": "0:14:52"}
|
| 179 |
+
{"current_steps": 179, "total_steps": 444, "loss": 0.2615, "lr": 7.500000000000001e-06, "epoch": 0.8085827216261999, "percentage": 40.32, "elapsed_time": "0:10:00", "remaining_time": "0:14:48"}
|
| 180 |
+
{"current_steps": 180, "total_steps": 444, "loss": 0.2564, "lr": 7.465828886394729e-06, "epoch": 0.8130999435347261, "percentage": 40.54, "elapsed_time": "0:10:03", "remaining_time": "0:14:45"}
|
| 181 |
+
{"current_steps": 181, "total_steps": 444, "loss": 0.2576, "lr": 7.431504905471407e-06, "epoch": 0.8176171654432524, "percentage": 40.77, "elapsed_time": "0:10:07", "remaining_time": "0:14:43"}
|
| 182 |
+
{"current_steps": 182, "total_steps": 444, "loss": 0.2515, "lr": 7.397030185120962e-06, "epoch": 0.8221343873517787, "percentage": 40.99, "elapsed_time": "0:10:11", "remaining_time": "0:14:39"}
|
| 183 |
+
{"current_steps": 183, "total_steps": 444, "loss": 0.255, "lr": 7.362406862579299e-06, "epoch": 0.8266516092603049, "percentage": 41.22, "elapsed_time": "0:10:14", "remaining_time": "0:14:36"}
|
| 184 |
+
{"current_steps": 184, "total_steps": 444, "loss": 0.2559, "lr": 7.327637084294818e-06, "epoch": 0.8311688311688312, "percentage": 41.44, "elapsed_time": "0:10:17", "remaining_time": "0:14:32"}
|
| 185 |
+
{"current_steps": 185, "total_steps": 444, "loss": 0.2447, "lr": 7.29272300579533e-06, "epoch": 0.8356860530773574, "percentage": 41.67, "elapsed_time": "0:10:21", "remaining_time": "0:14:29"}
|
| 186 |
+
{"current_steps": 186, "total_steps": 444, "loss": 0.261, "lr": 7.257666791554448e-06, "epoch": 0.8402032749858837, "percentage": 41.89, "elapsed_time": "0:10:24", "remaining_time": "0:14:25"}
|
| 187 |
+
{"current_steps": 187, "total_steps": 444, "loss": 0.2523, "lr": 7.22247061485738e-06, "epoch": 0.84472049689441, "percentage": 42.12, "elapsed_time": "0:10:27", "remaining_time": "0:14:22"}
|
| 188 |
+
{"current_steps": 188, "total_steps": 444, "loss": 0.2547, "lr": 7.187136657666208e-06, "epoch": 0.8492377188029362, "percentage": 42.34, "elapsed_time": "0:10:31", "remaining_time": "0:14:19"}
|
| 189 |
+
{"current_steps": 189, "total_steps": 444, "loss": 0.2435, "lr": 7.151667110484626e-06, "epoch": 0.8537549407114624, "percentage": 42.57, "elapsed_time": "0:10:34", "remaining_time": "0:14:16"}
|
| 190 |
+
{"current_steps": 190, "total_steps": 444, "loss": 0.2455, "lr": 7.1160641722221255e-06, "epoch": 0.8582721626199887, "percentage": 42.79, "elapsed_time": "0:10:37", "remaining_time": "0:14:12"}
|
| 191 |
+
{"current_steps": 191, "total_steps": 444, "loss": 0.2641, "lr": 7.080330050057687e-06, "epoch": 0.862789384528515, "percentage": 43.02, "elapsed_time": "0:10:41", "remaining_time": "0:14:09"}
|
| 192 |
+
{"current_steps": 192, "total_steps": 444, "loss": 0.2403, "lr": 7.044466959302945e-06, "epoch": 0.8673066064370413, "percentage": 43.24, "elapsed_time": "0:10:44", "remaining_time": "0:14:06"}
|
| 193 |
+
{"current_steps": 193, "total_steps": 444, "loss": 0.2623, "lr": 7.008477123264849e-06, "epoch": 0.8718238283455675, "percentage": 43.47, "elapsed_time": "0:10:48", "remaining_time": "0:14:02"}
|
| 194 |
+
{"current_steps": 194, "total_steps": 444, "loss": 0.2471, "lr": 6.972362773107832e-06, "epoch": 0.8763410502540937, "percentage": 43.69, "elapsed_time": "0:10:51", "remaining_time": "0:13:59"}
|
| 195 |
+
{"current_steps": 195, "total_steps": 444, "loss": 0.2489, "lr": 6.936126147715494e-06, "epoch": 0.88085827216262, "percentage": 43.92, "elapsed_time": "0:10:54", "remaining_time": "0:13:56"}
|
| 196 |
+
{"current_steps": 196, "total_steps": 444, "loss": 0.2445, "lr": 6.8997694935518e-06, "epoch": 0.8853754940711462, "percentage": 44.14, "elapsed_time": "0:10:58", "remaining_time": "0:13:53"}
|
| 197 |
+
{"current_steps": 197, "total_steps": 444, "loss": 0.248, "lr": 6.863295064521816e-06, "epoch": 0.8898927159796725, "percentage": 44.37, "elapsed_time": "0:11:01", "remaining_time": "0:13:49"}
|
| 198 |
+
{"current_steps": 198, "total_steps": 444, "loss": 0.2525, "lr": 6.8267051218319766e-06, "epoch": 0.8944099378881988, "percentage": 44.59, "elapsed_time": "0:11:05", "remaining_time": "0:13:46"}
|
| 199 |
+
{"current_steps": 199, "total_steps": 444, "loss": 0.2512, "lr": 6.7900019338499005e-06, "epoch": 0.898927159796725, "percentage": 44.82, "elapsed_time": "0:11:08", "remaining_time": "0:13:43"}
|
| 200 |
+
{"current_steps": 200, "total_steps": 444, "loss": 0.252, "lr": 6.753187775963773e-06, "epoch": 0.9034443817052513, "percentage": 45.05, "elapsed_time": "0:11:12", "remaining_time": "0:13:39"}
|
| 201 |
+
{"current_steps": 201, "total_steps": 444, "loss": 0.261, "lr": 6.716264930441279e-06, "epoch": 0.9079616036137775, "percentage": 45.27, "elapsed_time": "0:11:15", "remaining_time": "0:13:36"}
|
| 202 |
+
{"current_steps": 202, "total_steps": 444, "loss": 0.2593, "lr": 6.6792356862881144e-06, "epoch": 0.9124788255223037, "percentage": 45.5, "elapsed_time": "0:11:18", "remaining_time": "0:13:32"}
|
| 203 |
+
{"current_steps": 203, "total_steps": 444, "loss": 0.2514, "lr": 6.6421023391060845e-06, "epoch": 0.9169960474308301, "percentage": 45.72, "elapsed_time": "0:11:21", "remaining_time": "0:13:29"}
|
| 204 |
+
{"current_steps": 204, "total_steps": 444, "loss": 0.2649, "lr": 6.60486719095079e-06, "epoch": 0.9215132693393563, "percentage": 45.95, "elapsed_time": "0:11:24", "remaining_time": "0:13:25"}
|
| 205 |
+
{"current_steps": 205, "total_steps": 444, "loss": 0.2611, "lr": 6.567532550188908e-06, "epoch": 0.9260304912478825, "percentage": 46.17, "elapsed_time": "0:11:28", "remaining_time": "0:13:22"}
|
| 206 |
+
{"current_steps": 206, "total_steps": 444, "loss": 0.255, "lr": 6.530100731355089e-06, "epoch": 0.9305477131564088, "percentage": 46.4, "elapsed_time": "0:11:31", "remaining_time": "0:13:19"}
|
| 207 |
+
{"current_steps": 207, "total_steps": 444, "loss": 0.2495, "lr": 6.492574055008474e-06, "epoch": 0.935064935064935, "percentage": 46.62, "elapsed_time": "0:11:34", "remaining_time": "0:13:15"}
|
| 208 |
+
{"current_steps": 208, "total_steps": 444, "loss": 0.2407, "lr": 6.454954847588824e-06, "epoch": 0.9395821569734614, "percentage": 46.85, "elapsed_time": "0:11:38", "remaining_time": "0:13:12"}
|
| 209 |
+
{"current_steps": 209, "total_steps": 444, "loss": 0.2615, "lr": 6.417245441272299e-06, "epoch": 0.9440993788819876, "percentage": 47.07, "elapsed_time": "0:11:41", "remaining_time": "0:13:08"}
|
| 210 |
+
{"current_steps": 210, "total_steps": 444, "loss": 0.2493, "lr": 6.3794481738268765e-06, "epoch": 0.9486166007905138, "percentage": 47.3, "elapsed_time": "0:11:44", "remaining_time": "0:13:05"}
|
| 211 |
+
{"current_steps": 211, "total_steps": 444, "loss": 0.2629, "lr": 6.341565388467425e-06, "epoch": 0.9531338226990401, "percentage": 47.52, "elapsed_time": "0:11:48", "remaining_time": "0:13:01"}
|
| 212 |
+
{"current_steps": 212, "total_steps": 444, "loss": 0.2462, "lr": 6.30359943371043e-06, "epoch": 0.9576510446075663, "percentage": 47.75, "elapsed_time": "0:11:51", "remaining_time": "0:12:58"}
|
| 213 |
+
{"current_steps": 213, "total_steps": 444, "loss": 0.2419, "lr": 6.265552663228411e-06, "epoch": 0.9621682665160926, "percentage": 47.97, "elapsed_time": "0:11:54", "remaining_time": "0:12:55"}
|
| 214 |
+
{"current_steps": 214, "total_steps": 444, "loss": 0.2474, "lr": 6.227427435703997e-06, "epoch": 0.9666854884246189, "percentage": 48.2, "elapsed_time": "0:11:57", "remaining_time": "0:12:51"}
|
| 215 |
+
{"current_steps": 215, "total_steps": 444, "loss": 0.2716, "lr": 6.189226114683708e-06, "epoch": 0.9712027103331451, "percentage": 48.42, "elapsed_time": "0:12:01", "remaining_time": "0:12:48"}
|
| 216 |
+
{"current_steps": 216, "total_steps": 444, "loss": 0.2519, "lr": 6.150951068431424e-06, "epoch": 0.9757199322416714, "percentage": 48.65, "elapsed_time": "0:12:04", "remaining_time": "0:12:44"}
|
| 217 |
+
{"current_steps": 217, "total_steps": 444, "loss": 0.2455, "lr": 6.112604669781572e-06, "epoch": 0.9802371541501976, "percentage": 48.87, "elapsed_time": "0:12:07", "remaining_time": "0:12:41"}
|
| 218 |
+
{"current_steps": 218, "total_steps": 444, "loss": 0.2508, "lr": 6.0741892959920205e-06, "epoch": 0.9847543760587238, "percentage": 49.1, "elapsed_time": "0:12:10", "remaining_time": "0:12:37"}
|
| 219 |
+
{"current_steps": 219, "total_steps": 444, "loss": 0.2433, "lr": 6.035707328596698e-06, "epoch": 0.9892715979672502, "percentage": 49.32, "elapsed_time": "0:12:14", "remaining_time": "0:12:34"}
|
| 220 |
+
{"current_steps": 220, "total_steps": 444, "loss": 0.2481, "lr": 5.997161153257963e-06, "epoch": 0.9937888198757764, "percentage": 49.55, "elapsed_time": "0:12:17", "remaining_time": "0:12:31"}
|
| 221 |
+
{"current_steps": 221, "total_steps": 444, "loss": 0.2419, "lr": 5.958553159618693e-06, "epoch": 0.9983060417843026, "percentage": 49.77, "elapsed_time": "0:12:21", "remaining_time": "0:12:27"}
|
| 222 |
+
{"current_steps": 222, "total_steps": 444, "loss": 0.2324, "lr": 5.919885741154155e-06, "epoch": 1.0, "percentage": 50.0, "elapsed_time": "0:12:22", "remaining_time": "0:12:22"}
|
| 223 |
+
{"current_steps": 223, "total_steps": 444, "loss": 0.2127, "lr": 5.88116129502361e-06, "epoch": 1.0045172219085263, "percentage": 50.23, "elapsed_time": "0:12:25", "remaining_time": "0:12:19"}
|
| 224 |
+
{"current_steps": 224, "total_steps": 444, "loss": 0.2252, "lr": 5.842382221921711e-06, "epoch": 1.0090344438170524, "percentage": 50.45, "elapsed_time": "0:12:29", "remaining_time": "0:12:15"}
|
| 225 |
+
{"current_steps": 225, "total_steps": 444, "loss": 0.2338, "lr": 5.803550925929673e-06, "epoch": 1.0135516657255788, "percentage": 50.68, "elapsed_time": "0:12:32", "remaining_time": "0:12:12"}
|
| 226 |
+
{"current_steps": 226, "total_steps": 444, "loss": 0.233, "lr": 5.764669814366231e-06, "epoch": 1.018068887634105, "percentage": 50.9, "elapsed_time": "0:12:35", "remaining_time": "0:12:09"}
|
| 227 |
+
{"current_steps": 227, "total_steps": 444, "loss": 0.2295, "lr": 5.725741297638399e-06, "epoch": 1.0225861095426312, "percentage": 51.13, "elapsed_time": "0:12:39", "remaining_time": "0:12:06"}
|
| 228 |
+
{"current_steps": 228, "total_steps": 444, "loss": 0.2257, "lr": 5.686767789092041e-06, "epoch": 1.0271033314511575, "percentage": 51.35, "elapsed_time": "0:12:43", "remaining_time": "0:12:02"}
|
| 229 |
+
{"current_steps": 229, "total_steps": 444, "loss": 0.2233, "lr": 5.647751704862263e-06, "epoch": 1.0316205533596838, "percentage": 51.58, "elapsed_time": "0:12:46", "remaining_time": "0:11:59"}
|
| 230 |
+
{"current_steps": 230, "total_steps": 444, "loss": 0.2251, "lr": 5.608695463723614e-06, "epoch": 1.0361377752682102, "percentage": 51.8, "elapsed_time": "0:12:49", "remaining_time": "0:11:56"}
|
| 231 |
+
{"current_steps": 231, "total_steps": 444, "loss": 0.2254, "lr": 5.56960148694014e-06, "epoch": 1.0406549971767363, "percentage": 52.03, "elapsed_time": "0:12:53", "remaining_time": "0:11:52"}
|
| 232 |
+
{"current_steps": 232, "total_steps": 444, "loss": 0.2197, "lr": 5.530472198115291e-06, "epoch": 1.0451722190852626, "percentage": 52.25, "elapsed_time": "0:12:56", "remaining_time": "0:11:49"}
|
| 233 |
+
{"current_steps": 233, "total_steps": 444, "loss": 0.2176, "lr": 5.4913100230416536e-06, "epoch": 1.049689440993789, "percentage": 52.48, "elapsed_time": "0:12:59", "remaining_time": "0:11:46"}
|
| 234 |
+
{"current_steps": 234, "total_steps": 444, "loss": 0.2235, "lr": 5.45211738955058e-06, "epoch": 1.054206662902315, "percentage": 52.7, "elapsed_time": "0:13:02", "remaining_time": "0:11:42"}
|
| 235 |
+
{"current_steps": 235, "total_steps": 444, "loss": 0.2239, "lr": 5.412896727361663e-06, "epoch": 1.0587238848108413, "percentage": 52.93, "elapsed_time": "0:13:06", "remaining_time": "0:11:39"}
|
| 236 |
+
{"current_steps": 236, "total_steps": 444, "loss": 0.2265, "lr": 5.373650467932122e-06, "epoch": 1.0632411067193677, "percentage": 53.15, "elapsed_time": "0:13:09", "remaining_time": "0:11:35"}
|
| 237 |
+
{"current_steps": 237, "total_steps": 444, "loss": 0.2227, "lr": 5.334381044306057e-06, "epoch": 1.0677583286278938, "percentage": 53.38, "elapsed_time": "0:13:12", "remaining_time": "0:11:32"}
|
| 238 |
+
{"current_steps": 238, "total_steps": 444, "loss": 0.2341, "lr": 5.2950908909636144e-06, "epoch": 1.07227555053642, "percentage": 53.6, "elapsed_time": "0:13:15", "remaining_time": "0:11:28"}
|
| 239 |
+
{"current_steps": 239, "total_steps": 444, "loss": 0.2164, "lr": 5.255782443670068e-06, "epoch": 1.0767927724449464, "percentage": 53.83, "elapsed_time": "0:13:19", "remaining_time": "0:11:25"}
|
| 240 |
+
{"current_steps": 240, "total_steps": 444, "loss": 0.2276, "lr": 5.216458139324806e-06, "epoch": 1.0813099943534725, "percentage": 54.05, "elapsed_time": "0:13:22", "remaining_time": "0:11:22"}
|
| 241 |
+
{"current_steps": 241, "total_steps": 444, "loss": 0.2209, "lr": 5.177120415810271e-06, "epoch": 1.0858272162619989, "percentage": 54.28, "elapsed_time": "0:13:25", "remaining_time": "0:11:18"}
|
| 242 |
+
{"current_steps": 242, "total_steps": 444, "loss": 0.2211, "lr": 5.137771711840811e-06, "epoch": 1.0903444381705252, "percentage": 54.5, "elapsed_time": "0:13:29", "remaining_time": "0:11:15"}
|
| 243 |
+
{"current_steps": 243, "total_steps": 444, "loss": 0.2099, "lr": 5.098414466811504e-06, "epoch": 1.0948616600790513, "percentage": 54.73, "elapsed_time": "0:13:32", "remaining_time": "0:11:11"}
|
| 244 |
+
{"current_steps": 244, "total_steps": 444, "loss": 0.221, "lr": 5.059051120646924e-06, "epoch": 1.0993788819875776, "percentage": 54.95, "elapsed_time": "0:13:35", "remaining_time": "0:11:08"}
|
| 245 |
+
{"current_steps": 245, "total_steps": 444, "loss": 0.2211, "lr": 5.019684113649877e-06, "epoch": 1.103896103896104, "percentage": 55.18, "elapsed_time": "0:13:39", "remaining_time": "0:11:05"}
|
| 246 |
+
{"current_steps": 246, "total_steps": 444, "loss": 0.2177, "lr": 4.980315886350125e-06, "epoch": 1.1084133258046303, "percentage": 55.41, "elapsed_time": "0:13:42", "remaining_time": "0:11:02"}
|
| 247 |
+
{"current_steps": 247, "total_steps": 444, "loss": 0.2119, "lr": 4.940948879353078e-06, "epoch": 1.1129305477131564, "percentage": 55.63, "elapsed_time": "0:13:46", "remaining_time": "0:10:58"}
|
| 248 |
+
{"current_steps": 248, "total_steps": 444, "loss": 0.2244, "lr": 4.9015855331884984e-06, "epoch": 1.1174477696216827, "percentage": 55.86, "elapsed_time": "0:13:49", "remaining_time": "0:10:55"}
|
| 249 |
+
{"current_steps": 249, "total_steps": 444, "loss": 0.2175, "lr": 4.862228288159191e-06, "epoch": 1.121964991530209, "percentage": 56.08, "elapsed_time": "0:13:53", "remaining_time": "0:10:52"}
|
| 250 |
+
{"current_steps": 250, "total_steps": 444, "loss": 0.2172, "lr": 4.822879584189732e-06, "epoch": 1.1264822134387351, "percentage": 56.31, "elapsed_time": "0:13:56", "remaining_time": "0:10:48"}
|
| 251 |
+
{"current_steps": 251, "total_steps": 444, "loss": 0.2163, "lr": 4.783541860675195e-06, "epoch": 1.1309994353472614, "percentage": 56.53, "elapsed_time": "0:13:59", "remaining_time": "0:10:45"}
|
| 252 |
+
{"current_steps": 252, "total_steps": 444, "loss": 0.224, "lr": 4.744217556329935e-06, "epoch": 1.1355166572557878, "percentage": 56.76, "elapsed_time": "0:14:03", "remaining_time": "0:10:42"}
|
| 253 |
+
{"current_steps": 253, "total_steps": 444, "loss": 0.2138, "lr": 4.704909109036387e-06, "epoch": 1.1400338791643139, "percentage": 56.98, "elapsed_time": "0:14:06", "remaining_time": "0:10:38"}
|
| 254 |
+
{"current_steps": 254, "total_steps": 444, "loss": 0.22, "lr": 4.6656189556939446e-06, "epoch": 1.1445511010728402, "percentage": 57.21, "elapsed_time": "0:14:09", "remaining_time": "0:10:35"}
|
| 255 |
+
{"current_steps": 255, "total_steps": 444, "loss": 0.2353, "lr": 4.626349532067879e-06, "epoch": 1.1490683229813665, "percentage": 57.43, "elapsed_time": "0:14:13", "remaining_time": "0:10:32"}
|
| 256 |
+
{"current_steps": 256, "total_steps": 444, "loss": 0.224, "lr": 4.587103272638339e-06, "epoch": 1.1535855448898926, "percentage": 57.66, "elapsed_time": "0:14:16", "remaining_time": "0:10:28"}
|
| 257 |
+
{"current_steps": 257, "total_steps": 444, "loss": 0.2178, "lr": 4.5478826104494225e-06, "epoch": 1.158102766798419, "percentage": 57.88, "elapsed_time": "0:14:19", "remaining_time": "0:10:25"}
|
| 258 |
+
{"current_steps": 258, "total_steps": 444, "loss": 0.2319, "lr": 4.508689976958348e-06, "epoch": 1.1626199887069453, "percentage": 58.11, "elapsed_time": "0:14:23", "remaining_time": "0:10:22"}
|
| 259 |
+
{"current_steps": 259, "total_steps": 444, "loss": 0.2305, "lr": 4.46952780188471e-06, "epoch": 1.1671372106154716, "percentage": 58.33, "elapsed_time": "0:14:26", "remaining_time": "0:10:18"}
|
| 260 |
+
{"current_steps": 260, "total_steps": 444, "loss": 0.2231, "lr": 4.4303985130598615e-06, "epoch": 1.1716544325239977, "percentage": 58.56, "elapsed_time": "0:14:29", "remaining_time": "0:10:15"}
|
| 261 |
+
{"current_steps": 261, "total_steps": 444, "loss": 0.2132, "lr": 4.391304536276389e-06, "epoch": 1.176171654432524, "percentage": 58.78, "elapsed_time": "0:14:32", "remaining_time": "0:10:12"}
|
| 262 |
+
{"current_steps": 262, "total_steps": 444, "loss": 0.2181, "lr": 4.352248295137739e-06, "epoch": 1.1806888763410504, "percentage": 59.01, "elapsed_time": "0:14:36", "remaining_time": "0:10:08"}
|
| 263 |
+
{"current_steps": 263, "total_steps": 444, "loss": 0.2205, "lr": 4.313232210907959e-06, "epoch": 1.1852060982495765, "percentage": 59.23, "elapsed_time": "0:14:39", "remaining_time": "0:10:05"}
|
| 264 |
+
{"current_steps": 264, "total_steps": 444, "loss": 0.2192, "lr": 4.274258702361604e-06, "epoch": 1.1897233201581028, "percentage": 59.46, "elapsed_time": "0:14:43", "remaining_time": "0:10:02"}
|
| 265 |
+
{"current_steps": 265, "total_steps": 444, "loss": 0.2155, "lr": 4.23533018563377e-06, "epoch": 1.194240542066629, "percentage": 59.68, "elapsed_time": "0:14:46", "remaining_time": "0:09:58"}
|
| 266 |
+
{"current_steps": 266, "total_steps": 444, "loss": 0.2136, "lr": 4.196449074070329e-06, "epoch": 1.1987577639751552, "percentage": 59.91, "elapsed_time": "0:14:50", "remaining_time": "0:09:55"}
|
| 267 |
+
{"current_steps": 267, "total_steps": 444, "loss": 0.2128, "lr": 4.15761777807829e-06, "epoch": 1.2032749858836815, "percentage": 60.14, "elapsed_time": "0:14:53", "remaining_time": "0:09:52"}
|
| 268 |
+
{"current_steps": 268, "total_steps": 444, "loss": 0.213, "lr": 4.118838704976392e-06, "epoch": 1.2077922077922079, "percentage": 60.36, "elapsed_time": "0:14:56", "remaining_time": "0:09:48"}
|
| 269 |
+
{"current_steps": 269, "total_steps": 444, "loss": 0.2186, "lr": 4.080114258845846e-06, "epoch": 1.212309429700734, "percentage": 60.59, "elapsed_time": "0:15:00", "remaining_time": "0:09:45"}
|
| 270 |
+
{"current_steps": 270, "total_steps": 444, "loss": 0.2208, "lr": 4.041446840381309e-06, "epoch": 1.2168266516092603, "percentage": 60.81, "elapsed_time": "0:15:04", "remaining_time": "0:09:42"}
|
| 271 |
+
{"current_steps": 271, "total_steps": 444, "loss": 0.2183, "lr": 4.002838846742039e-06, "epoch": 1.2213438735177866, "percentage": 61.04, "elapsed_time": "0:15:07", "remaining_time": "0:09:39"}
|
| 272 |
+
{"current_steps": 272, "total_steps": 444, "loss": 0.212, "lr": 3.964292671403303e-06, "epoch": 1.2258610954263127, "percentage": 61.26, "elapsed_time": "0:15:10", "remaining_time": "0:09:35"}
|
| 273 |
+
{"current_steps": 273, "total_steps": 444, "loss": 0.2146, "lr": 3.92581070400798e-06, "epoch": 1.230378317334839, "percentage": 61.49, "elapsed_time": "0:15:14", "remaining_time": "0:09:32"}
|
| 274 |
+
{"current_steps": 274, "total_steps": 444, "loss": 0.2202, "lr": 3.887395330218429e-06, "epoch": 1.2348955392433654, "percentage": 61.71, "elapsed_time": "0:15:17", "remaining_time": "0:09:29"}
|
| 275 |
+
{"current_steps": 275, "total_steps": 444, "loss": 0.2165, "lr": 3.8490489315685764e-06, "epoch": 1.2394127611518915, "percentage": 61.94, "elapsed_time": "0:15:20", "remaining_time": "0:09:25"}
|
| 276 |
+
{"current_steps": 276, "total_steps": 444, "loss": 0.2217, "lr": 3.8107738853162953e-06, "epoch": 1.2439299830604178, "percentage": 62.16, "elapsed_time": "0:15:24", "remaining_time": "0:09:22"}
|
| 277 |
+
{"current_steps": 277, "total_steps": 444, "loss": 0.2156, "lr": 3.7725725642960047e-06, "epoch": 1.2484472049689441, "percentage": 62.39, "elapsed_time": "0:15:27", "remaining_time": "0:09:19"}
|
| 278 |
+
{"current_steps": 278, "total_steps": 444, "loss": 0.2169, "lr": 3.734447336771591e-06, "epoch": 1.2529644268774702, "percentage": 62.61, "elapsed_time": "0:15:30", "remaining_time": "0:09:15"}
|
| 279 |
+
{"current_steps": 279, "total_steps": 444, "loss": 0.2265, "lr": 3.696400566289571e-06, "epoch": 1.2574816487859966, "percentage": 62.84, "elapsed_time": "0:15:34", "remaining_time": "0:09:12"}
|
| 280 |
+
{"current_steps": 280, "total_steps": 444, "loss": 0.2223, "lr": 3.658434611532578e-06, "epoch": 1.2619988706945229, "percentage": 63.06, "elapsed_time": "0:15:37", "remaining_time": "0:09:08"}
|
| 281 |
+
{"current_steps": 281, "total_steps": 444, "loss": 0.2141, "lr": 3.6205518261731247e-06, "epoch": 1.2665160926030492, "percentage": 63.29, "elapsed_time": "0:15:40", "remaining_time": "0:09:05"}
|
| 282 |
+
{"current_steps": 282, "total_steps": 444, "loss": 0.2175, "lr": 3.5827545587277033e-06, "epoch": 1.2710333145115753, "percentage": 63.51, "elapsed_time": "0:15:43", "remaining_time": "0:09:02"}
|
| 283 |
+
{"current_steps": 283, "total_steps": 444, "loss": 0.2163, "lr": 3.545045152411178e-06, "epoch": 1.2755505364201016, "percentage": 63.74, "elapsed_time": "0:15:47", "remaining_time": "0:08:58"}
|
| 284 |
+
{"current_steps": 284, "total_steps": 444, "loss": 0.215, "lr": 3.507425944991529e-06, "epoch": 1.280067758328628, "percentage": 63.96, "elapsed_time": "0:15:50", "remaining_time": "0:08:55"}
|
| 285 |
+
{"current_steps": 285, "total_steps": 444, "loss": 0.219, "lr": 3.469899268644913e-06, "epoch": 1.2845849802371543, "percentage": 64.19, "elapsed_time": "0:15:54", "remaining_time": "0:08:52"}
|
| 286 |
+
{"current_steps": 286, "total_steps": 444, "loss": 0.2185, "lr": 3.4324674498110956e-06, "epoch": 1.2891022021456804, "percentage": 64.41, "elapsed_time": "0:15:57", "remaining_time": "0:08:49"}
|
| 287 |
+
{"current_steps": 287, "total_steps": 444, "loss": 0.2244, "lr": 3.395132809049212e-06, "epoch": 1.2936194240542067, "percentage": 64.64, "elapsed_time": "0:16:00", "remaining_time": "0:08:45"}
|
| 288 |
+
{"current_steps": 288, "total_steps": 444, "loss": 0.2228, "lr": 3.3578976608939184e-06, "epoch": 1.298136645962733, "percentage": 64.86, "elapsed_time": "0:16:04", "remaining_time": "0:08:42"}
|
| 289 |
+
{"current_steps": 289, "total_steps": 444, "loss": 0.2181, "lr": 3.3207643137118872e-06, "epoch": 1.3026538678712591, "percentage": 65.09, "elapsed_time": "0:16:07", "remaining_time": "0:08:38"}
|
| 290 |
+
{"current_steps": 290, "total_steps": 444, "loss": 0.2192, "lr": 3.2837350695587237e-06, "epoch": 1.3071710897797855, "percentage": 65.32, "elapsed_time": "0:16:10", "remaining_time": "0:08:35"}
|
| 291 |
+
{"current_steps": 291, "total_steps": 444, "loss": 0.233, "lr": 3.2468122240362287e-06, "epoch": 1.3116883116883118, "percentage": 65.54, "elapsed_time": "0:16:13", "remaining_time": "0:08:32"}
|
| 292 |
+
{"current_steps": 292, "total_steps": 444, "loss": 0.2135, "lr": 3.2099980661501016e-06, "epoch": 1.316205533596838, "percentage": 65.77, "elapsed_time": "0:16:17", "remaining_time": "0:08:28"}
|
| 293 |
+
{"current_steps": 293, "total_steps": 444, "loss": 0.2035, "lr": 3.173294878168025e-06, "epoch": 1.3207227555053642, "percentage": 65.99, "elapsed_time": "0:16:20", "remaining_time": "0:08:25"}
|
| 294 |
+
{"current_steps": 294, "total_steps": 444, "loss": 0.2086, "lr": 3.1367049354781854e-06, "epoch": 1.3252399774138905, "percentage": 66.22, "elapsed_time": "0:16:23", "remaining_time": "0:08:21"}
|
| 295 |
+
{"current_steps": 295, "total_steps": 444, "loss": 0.2161, "lr": 3.1002305064482006e-06, "epoch": 1.3297571993224166, "percentage": 66.44, "elapsed_time": "0:16:26", "remaining_time": "0:08:18"}
|
| 296 |
+
{"current_steps": 296, "total_steps": 444, "loss": 0.2221, "lr": 3.063873852284508e-06, "epoch": 1.334274421230943, "percentage": 66.67, "elapsed_time": "0:16:30", "remaining_time": "0:08:15"}
|
| 297 |
+
{"current_steps": 297, "total_steps": 444, "loss": 0.215, "lr": 3.0276372268921694e-06, "epoch": 1.3387916431394693, "percentage": 66.89, "elapsed_time": "0:16:33", "remaining_time": "0:08:11"}
|
| 298 |
+
{"current_steps": 298, "total_steps": 444, "loss": 0.2115, "lr": 2.991522876735154e-06, "epoch": 1.3433088650479954, "percentage": 67.12, "elapsed_time": "0:16:36", "remaining_time": "0:08:08"}
|
| 299 |
+
{"current_steps": 299, "total_steps": 444, "loss": 0.2172, "lr": 2.9555330406970568e-06, "epoch": 1.3478260869565217, "percentage": 67.34, "elapsed_time": "0:16:39", "remaining_time": "0:08:04"}
|
| 300 |
+
{"current_steps": 300, "total_steps": 444, "loss": 0.1957, "lr": 2.9196699499423143e-06, "epoch": 1.352343308865048, "percentage": 67.57, "elapsed_time": "0:16:42", "remaining_time": "0:08:01"}
|
| 301 |
+
{"current_steps": 301, "total_steps": 444, "loss": 0.2181, "lr": 2.8839358277778758e-06, "epoch": 1.3568605307735742, "percentage": 67.79, "elapsed_time": "0:16:46", "remaining_time": "0:07:58"}
|
| 302 |
+
{"current_steps": 302, "total_steps": 444, "loss": 0.2078, "lr": 2.848332889515375e-06, "epoch": 1.3613777526821005, "percentage": 68.02, "elapsed_time": "0:16:49", "remaining_time": "0:07:54"}
|
| 303 |
+
{"current_steps": 303, "total_steps": 444, "loss": 0.215, "lr": 2.8128633423337932e-06, "epoch": 1.3658949745906268, "percentage": 68.24, "elapsed_time": "0:16:53", "remaining_time": "0:07:51"}
|
| 304 |
+
{"current_steps": 304, "total_steps": 444, "loss": 0.2151, "lr": 2.7775293851426233e-06, "epoch": 1.370412196499153, "percentage": 68.47, "elapsed_time": "0:16:56", "remaining_time": "0:07:48"}
|
| 305 |
+
{"current_steps": 305, "total_steps": 444, "loss": 0.2166, "lr": 2.7423332084455543e-06, "epoch": 1.3749294184076792, "percentage": 68.69, "elapsed_time": "0:16:59", "remaining_time": "0:07:44"}
|
| 306 |
+
{"current_steps": 306, "total_steps": 444, "loss": 0.1981, "lr": 2.7072769942046716e-06, "epoch": 1.3794466403162056, "percentage": 68.92, "elapsed_time": "0:17:03", "remaining_time": "0:07:41"}
|
| 307 |
+
{"current_steps": 307, "total_steps": 444, "loss": 0.2069, "lr": 2.6723629157051844e-06, "epoch": 1.3839638622247317, "percentage": 69.14, "elapsed_time": "0:17:06", "remaining_time": "0:07:38"}
|
| 308 |
+
{"current_steps": 308, "total_steps": 444, "loss": 0.2136, "lr": 2.637593137420702e-06, "epoch": 1.388481084133258, "percentage": 69.37, "elapsed_time": "0:17:09", "remaining_time": "0:07:34"}
|
| 309 |
+
{"current_steps": 309, "total_steps": 444, "loss": 0.2172, "lr": 2.6029698148790392e-06, "epoch": 1.3929983060417843, "percentage": 69.59, "elapsed_time": "0:17:14", "remaining_time": "0:07:31"}
|
| 310 |
+
{"current_steps": 310, "total_steps": 444, "loss": 0.2193, "lr": 2.5684950945285937e-06, "epoch": 1.3975155279503104, "percentage": 69.82, "elapsed_time": "0:17:17", "remaining_time": "0:07:28"}
|
| 311 |
+
{"current_steps": 311, "total_steps": 444, "loss": 0.2126, "lr": 2.5341711136052728e-06, "epoch": 1.4020327498588367, "percentage": 70.05, "elapsed_time": "0:17:20", "remaining_time": "0:07:25"}
|
| 312 |
+
{"current_steps": 312, "total_steps": 444, "loss": 0.2255, "lr": 2.5000000000000015e-06, "epoch": 1.406549971767363, "percentage": 70.27, "elapsed_time": "0:17:23", "remaining_time": "0:07:21"}
|
| 313 |
+
{"current_steps": 313, "total_steps": 444, "loss": 0.2025, "lr": 2.4659838721268005e-06, "epoch": 1.4110671936758894, "percentage": 70.5, "elapsed_time": "0:17:27", "remaining_time": "0:07:18"}
|
| 314 |
+
{"current_steps": 314, "total_steps": 444, "loss": 0.2118, "lr": 2.4321248387914677e-06, "epoch": 1.4155844155844157, "percentage": 70.72, "elapsed_time": "0:17:31", "remaining_time": "0:07:15"}
|
| 315 |
+
{"current_steps": 315, "total_steps": 444, "loss": 0.2075, "lr": 2.3984249990608237e-06, "epoch": 1.4201016374929418, "percentage": 70.95, "elapsed_time": "0:17:35", "remaining_time": "0:07:12"}
|
| 316 |
+
{"current_steps": 316, "total_steps": 444, "loss": 0.2201, "lr": 2.364886442132606e-06, "epoch": 1.4246188594014682, "percentage": 71.17, "elapsed_time": "0:17:38", "remaining_time": "0:07:08"}
|
| 317 |
+
{"current_steps": 317, "total_steps": 444, "loss": 0.2113, "lr": 2.331511247205933e-06, "epoch": 1.4291360813099945, "percentage": 71.4, "elapsed_time": "0:17:42", "remaining_time": "0:07:05"}
|
| 318 |
+
{"current_steps": 318, "total_steps": 444, "loss": 0.2126, "lr": 2.2983014833524115e-06, "epoch": 1.4336533032185206, "percentage": 71.62, "elapsed_time": "0:17:45", "remaining_time": "0:07:02"}
|
| 319 |
+
{"current_steps": 319, "total_steps": 444, "loss": 0.2106, "lr": 2.265259209387867e-06, "epoch": 1.438170525127047, "percentage": 71.85, "elapsed_time": "0:17:48", "remaining_time": "0:06:58"}
|
| 320 |
+
{"current_steps": 320, "total_steps": 444, "loss": 0.2055, "lr": 2.2323864737447067e-06, "epoch": 1.4426877470355732, "percentage": 72.07, "elapsed_time": "0:17:51", "remaining_time": "0:06:55"}
|
| 321 |
+
{"current_steps": 321, "total_steps": 444, "loss": 0.2094, "lr": 2.1996853143449285e-06, "epoch": 1.4472049689440993, "percentage": 72.3, "elapsed_time": "0:17:55", "remaining_time": "0:06:51"}
|
| 322 |
+
{"current_steps": 322, "total_steps": 444, "loss": 0.215, "lr": 2.16715775847379e-06, "epoch": 1.4517221908526257, "percentage": 72.52, "elapsed_time": "0:17:58", "remaining_time": "0:06:48"}
|
| 323 |
+
{"current_steps": 323, "total_steps": 444, "loss": 0.219, "lr": 2.1348058226541072e-06, "epoch": 1.456239412761152, "percentage": 72.75, "elapsed_time": "0:18:01", "remaining_time": "0:06:45"}
|
| 324 |
+
{"current_steps": 324, "total_steps": 444, "loss": 0.2034, "lr": 2.102631512521269e-06, "epoch": 1.460756634669678, "percentage": 72.97, "elapsed_time": "0:18:05", "remaining_time": "0:06:41"}
|
| 325 |
+
{"current_steps": 325, "total_steps": 444, "loss": 0.2083, "lr": 2.0706368226988772e-06, "epoch": 1.4652738565782044, "percentage": 73.2, "elapsed_time": "0:18:08", "remaining_time": "0:06:38"}
|
| 326 |
+
{"current_steps": 326, "total_steps": 444, "loss": 0.2083, "lr": 2.0388237366751005e-06, "epoch": 1.4697910784867307, "percentage": 73.42, "elapsed_time": "0:18:11", "remaining_time": "0:06:35"}
|
| 327 |
+
{"current_steps": 327, "total_steps": 444, "loss": 0.2184, "lr": 2.00719422667971e-06, "epoch": 1.4743083003952568, "percentage": 73.65, "elapsed_time": "0:18:15", "remaining_time": "0:06:31"}
|
| 328 |
+
{"current_steps": 328, "total_steps": 444, "loss": 0.1991, "lr": 1.9757502535618137e-06, "epoch": 1.4788255223037832, "percentage": 73.87, "elapsed_time": "0:18:18", "remaining_time": "0:06:28"}
|
| 329 |
+
{"current_steps": 329, "total_steps": 444, "loss": 0.2082, "lr": 1.9444937666682834e-06, "epoch": 1.4833427442123095, "percentage": 74.1, "elapsed_time": "0:18:21", "remaining_time": "0:06:25"}
|
| 330 |
+
{"current_steps": 330, "total_steps": 444, "loss": 0.2217, "lr": 1.913426703722924e-06, "epoch": 1.4878599661208356, "percentage": 74.32, "elapsed_time": "0:18:24", "remaining_time": "0:06:21"}
|
| 331 |
+
{"current_steps": 331, "total_steps": 444, "loss": 0.2107, "lr": 1.8825509907063328e-06, "epoch": 1.492377188029362, "percentage": 74.55, "elapsed_time": "0:18:28", "remaining_time": "0:06:18"}
|
| 332 |
+
{"current_steps": 332, "total_steps": 444, "loss": 0.2039, "lr": 1.851868541736503e-06, "epoch": 1.4968944099378882, "percentage": 74.77, "elapsed_time": "0:18:31", "remaining_time": "0:06:15"}
|
| 333 |
+
{"current_steps": 333, "total_steps": 444, "loss": 0.2142, "lr": 1.8213812589501611e-06, "epoch": 1.5014116318464144, "percentage": 75.0, "elapsed_time": "0:18:34", "remaining_time": "0:06:11"}
|
| 334 |
+
{"current_steps": 334, "total_steps": 444, "loss": 0.1976, "lr": 1.7910910323848435e-06, "epoch": 1.5059288537549407, "percentage": 75.23, "elapsed_time": "0:18:38", "remaining_time": "0:06:08"}
|
| 335 |
+
{"current_steps": 335, "total_steps": 444, "loss": 0.2126, "lr": 1.760999739861724e-06, "epoch": 1.510446075663467, "percentage": 75.45, "elapsed_time": "0:18:41", "remaining_time": "0:06:04"}
|
| 336 |
+
{"current_steps": 336, "total_steps": 444, "loss": 0.2178, "lr": 1.7311092468692082e-06, "epoch": 1.514963297571993, "percentage": 75.68, "elapsed_time": "0:18:44", "remaining_time": "0:06:01"}
|
| 337 |
+
{"current_steps": 337, "total_steps": 444, "loss": 0.205, "lr": 1.7014214064472646e-06, "epoch": 1.5194805194805194, "percentage": 75.9, "elapsed_time": "0:18:48", "remaining_time": "0:05:58"}
|
| 338 |
+
{"current_steps": 338, "total_steps": 444, "loss": 0.1996, "lr": 1.671938059072571e-06, "epoch": 1.5239977413890458, "percentage": 76.13, "elapsed_time": "0:18:51", "remaining_time": "0:05:54"}
|
| 339 |
+
{"current_steps": 339, "total_steps": 444, "loss": 0.2024, "lr": 1.642661032544396e-06, "epoch": 1.5285149632975719, "percentage": 76.35, "elapsed_time": "0:18:55", "remaining_time": "0:05:51"}
|
| 340 |
+
{"current_steps": 340, "total_steps": 444, "loss": 0.2095, "lr": 1.6135921418712959e-06, "epoch": 1.5330321852060984, "percentage": 76.58, "elapsed_time": "0:18:58", "remaining_time": "0:05:48"}
|
| 341 |
+
{"current_steps": 341, "total_steps": 444, "loss": 0.1995, "lr": 1.5847331891585888e-06, "epoch": 1.5375494071146245, "percentage": 76.8, "elapsed_time": "0:19:02", "remaining_time": "0:05:44"}
|
| 342 |
+
{"current_steps": 342, "total_steps": 444, "loss": 0.2064, "lr": 1.5560859634966457e-06, "epoch": 1.5420666290231506, "percentage": 77.03, "elapsed_time": "0:19:05", "remaining_time": "0:05:41"}
|
| 343 |
+
{"current_steps": 343, "total_steps": 444, "loss": 0.2164, "lr": 1.5276522408499567e-06, "epoch": 1.5465838509316772, "percentage": 77.25, "elapsed_time": "0:19:08", "remaining_time": "0:05:38"}
|
| 344 |
+
{"current_steps": 344, "total_steps": 444, "loss": 0.1971, "lr": 1.499433783947054e-06, "epoch": 1.5511010728402033, "percentage": 77.48, "elapsed_time": "0:19:11", "remaining_time": "0:05:34"}
|
| 345 |
+
{"current_steps": 345, "total_steps": 444, "loss": 0.2082, "lr": 1.4714323421712163e-06, "epoch": 1.5556182947487294, "percentage": 77.7, "elapsed_time": "0:19:15", "remaining_time": "0:05:31"}
|
| 346 |
+
{"current_steps": 346, "total_steps": 444, "loss": 0.2107, "lr": 1.4436496514520253e-06, "epoch": 1.560135516657256, "percentage": 77.93, "elapsed_time": "0:19:18", "remaining_time": "0:05:28"}
|
| 347 |
+
{"current_steps": 347, "total_steps": 444, "loss": 0.214, "lr": 1.4160874341577447e-06, "epoch": 1.564652738565782, "percentage": 78.15, "elapsed_time": "0:19:21", "remaining_time": "0:05:24"}
|
| 348 |
+
{"current_steps": 348, "total_steps": 444, "loss": 0.2149, "lr": 1.3887473989885441e-06, "epoch": 1.5691699604743083, "percentage": 78.38, "elapsed_time": "0:19:27", "remaining_time": "0:05:21"}
|
| 349 |
+
{"current_steps": 349, "total_steps": 444, "loss": 0.2027, "lr": 1.361631240870569e-06, "epoch": 1.5736871823828347, "percentage": 78.6, "elapsed_time": "0:19:30", "remaining_time": "0:05:18"}
|
| 350 |
+
{"current_steps": 350, "total_steps": 444, "loss": 0.2111, "lr": 1.3347406408508695e-06, "epoch": 1.5782044042913608, "percentage": 78.83, "elapsed_time": "0:19:33", "remaining_time": "0:05:15"}
|
| 351 |
+
{"current_steps": 351, "total_steps": 444, "loss": 0.2047, "lr": 1.3080772659931728e-06, "epoch": 1.582721626199887, "percentage": 79.05, "elapsed_time": "0:19:37", "remaining_time": "0:05:11"}
|
| 352 |
+
{"current_steps": 352, "total_steps": 444, "loss": 0.2085, "lr": 1.281642769274552e-06, "epoch": 1.5872388481084134, "percentage": 79.28, "elapsed_time": "0:19:40", "remaining_time": "0:05:08"}
|
| 353 |
+
{"current_steps": 353, "total_steps": 444, "loss": 0.2072, "lr": 1.255438789482935e-06, "epoch": 1.5917560700169395, "percentage": 79.5, "elapsed_time": "0:19:44", "remaining_time": "0:05:05"}
|
| 354 |
+
{"current_steps": 354, "total_steps": 444, "loss": 0.2148, "lr": 1.2294669511155193e-06, "epoch": 1.5962732919254659, "percentage": 79.73, "elapsed_time": "0:19:47", "remaining_time": "0:05:01"}
|
| 355 |
+
{"current_steps": 355, "total_steps": 444, "loss": 0.2049, "lr": 1.2037288642780575e-06, "epoch": 1.6007905138339922, "percentage": 79.95, "elapsed_time": "0:19:51", "remaining_time": "0:04:58"}
|
| 356 |
+
{"current_steps": 356, "total_steps": 444, "loss": 0.2153, "lr": 1.1782261245850417e-06, "epoch": 1.6053077357425183, "percentage": 80.18, "elapsed_time": "0:19:54", "remaining_time": "0:04:55"}
|
| 357 |
+
{"current_steps": 357, "total_steps": 444, "loss": 0.2179, "lr": 1.1529603130607837e-06, "epoch": 1.6098249576510446, "percentage": 80.41, "elapsed_time": "0:19:58", "remaining_time": "0:04:52"}
|
| 358 |
+
{"current_steps": 358, "total_steps": 444, "loss": 0.2087, "lr": 1.1279329960414047e-06, "epoch": 1.614342179559571, "percentage": 80.63, "elapsed_time": "0:20:01", "remaining_time": "0:04:48"}
|
| 359 |
+
{"current_steps": 359, "total_steps": 444, "loss": 0.2153, "lr": 1.1031457250777206e-06, "epoch": 1.618859401468097, "percentage": 80.86, "elapsed_time": "0:20:04", "remaining_time": "0:04:45"}
|
| 360 |
+
{"current_steps": 360, "total_steps": 444, "loss": 0.2122, "lr": 1.0786000368390686e-06, "epoch": 1.6233766233766234, "percentage": 81.08, "elapsed_time": "0:20:08", "remaining_time": "0:04:41"}
|
| 361 |
+
{"current_steps": 361, "total_steps": 444, "loss": 0.2116, "lr": 1.0542974530180327e-06, "epoch": 1.6278938452851497, "percentage": 81.31, "elapsed_time": "0:20:11", "remaining_time": "0:04:38"}
|
| 362 |
+
{"current_steps": 362, "total_steps": 444, "loss": 0.2245, "lr": 1.0302394802361104e-06, "epoch": 1.6324110671936758, "percentage": 81.53, "elapsed_time": "0:20:15", "remaining_time": "0:04:35"}
|
| 363 |
+
{"current_steps": 363, "total_steps": 444, "loss": 0.2034, "lr": 1.00642760995031e-06, "epoch": 1.6369282891022021, "percentage": 81.76, "elapsed_time": "0:20:18", "remaining_time": "0:04:31"}
|
| 364 |
+
{"current_steps": 364, "total_steps": 444, "loss": 0.2122, "lr": 9.82863318360695e-07, "epoch": 1.6414455110107284, "percentage": 81.98, "elapsed_time": "0:20:21", "remaining_time": "0:04:28"}
|
| 365 |
+
{"current_steps": 365, "total_steps": 444, "loss": 0.2034, "lr": 9.595480663188528e-07, "epoch": 1.6459627329192545, "percentage": 82.21, "elapsed_time": "0:20:24", "remaining_time": "0:04:25"}
|
| 366 |
+
{"current_steps": 366, "total_steps": 444, "loss": 0.213, "lr": 9.364832992373501e-07, "epoch": 1.6504799548277809, "percentage": 82.43, "elapsed_time": "0:20:28", "remaining_time": "0:04:21"}
|
| 367 |
+
{"current_steps": 367, "total_steps": 444, "loss": 0.2147, "lr": 9.136704470001101e-07, "epoch": 1.6549971767363072, "percentage": 82.66, "elapsed_time": "0:20:31", "remaining_time": "0:04:18"}
|
| 368 |
+
{"current_steps": 368, "total_steps": 444, "loss": 0.2186, "lr": 8.911109238737748e-07, "epoch": 1.6595143986448333, "percentage": 82.88, "elapsed_time": "0:20:35", "remaining_time": "0:04:15"}
|
| 369 |
+
{"current_steps": 369, "total_steps": 444, "loss": 0.1923, "lr": 8.688061284200266e-07, "epoch": 1.6640316205533598, "percentage": 83.11, "elapsed_time": "0:20:38", "remaining_time": "0:04:11"}
|
| 370 |
+
{"current_steps": 370, "total_steps": 444, "loss": 0.2056, "lr": 8.46757443408886e-07, "epoch": 1.668548842461886, "percentage": 83.33, "elapsed_time": "0:20:41", "remaining_time": "0:04:08"}
|
| 371 |
+
{"current_steps": 371, "total_steps": 444, "loss": 0.215, "lr": 8.24966235732988e-07, "epoch": 1.673066064370412, "percentage": 83.56, "elapsed_time": "0:20:45", "remaining_time": "0:04:04"}
|
| 372 |
+
{"current_steps": 372, "total_steps": 444, "loss": 0.2176, "lr": 8.03433856322845e-07, "epoch": 1.6775832862789386, "percentage": 83.78, "elapsed_time": "0:20:49", "remaining_time": "0:04:01"}
|
| 373 |
+
{"current_steps": 373, "total_steps": 444, "loss": 0.2097, "lr": 7.821616400630866e-07, "epoch": 1.6821005081874647, "percentage": 84.01, "elapsed_time": "0:20:52", "remaining_time": "0:03:58"}
|
| 374 |
+
{"current_steps": 374, "total_steps": 444, "loss": 0.2156, "lr": 7.611509057097211e-07, "epoch": 1.6866177300959908, "percentage": 84.23, "elapsed_time": "0:20:55", "remaining_time": "0:03:55"}
|
| 375 |
+
{"current_steps": 375, "total_steps": 444, "loss": 0.2139, "lr": 7.404029558083653e-07, "epoch": 1.6911349520045174, "percentage": 84.46, "elapsed_time": "0:20:59", "remaining_time": "0:03:51"}
|
| 376 |
+
{"current_steps": 376, "total_steps": 444, "loss": 0.2086, "lr": 7.199190766135001e-07, "epoch": 1.6956521739130435, "percentage": 84.68, "elapsed_time": "0:21:02", "remaining_time": "0:03:48"}
|
| 377 |
+
{"current_steps": 377, "total_steps": 444, "loss": 0.2235, "lr": 6.997005380087301e-07, "epoch": 1.7001693958215698, "percentage": 84.91, "elapsed_time": "0:21:05", "remaining_time": "0:03:44"}
|
| 378 |
+
{"current_steps": 378, "total_steps": 444, "loss": 0.204, "lr": 6.797485934280618e-07, "epoch": 1.704686617730096, "percentage": 85.14, "elapsed_time": "0:21:08", "remaining_time": "0:03:41"}
|
| 379 |
+
{"current_steps": 379, "total_steps": 444, "loss": 0.2172, "lr": 6.600644797781847e-07, "epoch": 1.7092038396386222, "percentage": 85.36, "elapsed_time": "0:21:12", "remaining_time": "0:03:38"}
|
| 380 |
+
{"current_steps": 380, "total_steps": 444, "loss": 0.2014, "lr": 6.406494173618083e-07, "epoch": 1.7137210615471485, "percentage": 85.59, "elapsed_time": "0:21:15", "remaining_time": "0:03:34"}
|
| 381 |
+
{"current_steps": 381, "total_steps": 444, "loss": 0.2057, "lr": 6.215046098019967e-07, "epoch": 1.7182382834556749, "percentage": 85.81, "elapsed_time": "0:21:19", "remaining_time": "0:03:31"}
|
| 382 |
+
{"current_steps": 382, "total_steps": 444, "loss": 0.2144, "lr": 6.026312439675553e-07, "epoch": 1.722755505364201, "percentage": 86.04, "elapsed_time": "0:21:22", "remaining_time": "0:03:28"}
|
| 383 |
+
{"current_steps": 383, "total_steps": 444, "loss": 0.205, "lr": 5.84030489899452e-07, "epoch": 1.7272727272727273, "percentage": 86.26, "elapsed_time": "0:21:25", "remaining_time": "0:03:24"}
|
| 384 |
+
{"current_steps": 384, "total_steps": 444, "loss": 0.2107, "lr": 5.657035007382822e-07, "epoch": 1.7317899491812536, "percentage": 86.49, "elapsed_time": "0:21:29", "remaining_time": "0:03:21"}
|
| 385 |
+
{"current_steps": 385, "total_steps": 444, "loss": 0.2147, "lr": 5.476514126527771e-07, "epoch": 1.7363071710897797, "percentage": 86.71, "elapsed_time": "0:21:32", "remaining_time": "0:03:18"}
|
| 386 |
+
{"current_steps": 386, "total_steps": 444, "loss": 0.2195, "lr": 5.29875344769375e-07, "epoch": 1.740824392998306, "percentage": 86.94, "elapsed_time": "0:21:35", "remaining_time": "0:03:14"}
|
| 387 |
+
{"current_steps": 387, "total_steps": 444, "loss": 0.2047, "lr": 5.123763991028291e-07, "epoch": 1.7453416149068324, "percentage": 87.16, "elapsed_time": "0:21:39", "remaining_time": "0:03:11"}
|
| 388 |
+
{"current_steps": 388, "total_steps": 444, "loss": 0.2087, "lr": 4.951556604879049e-07, "epoch": 1.7498588368153585, "percentage": 87.39, "elapsed_time": "0:21:42", "remaining_time": "0:03:07"}
|
| 389 |
+
{"current_steps": 389, "total_steps": 444, "loss": 0.2142, "lr": 4.782141965121129e-07, "epoch": 1.7543760587238848, "percentage": 87.61, "elapsed_time": "0:21:45", "remaining_time": "0:03:04"}
|
| 390 |
+
{"current_steps": 390, "total_steps": 444, "loss": 0.2109, "lr": 4.615530574495325e-07, "epoch": 1.7588932806324111, "percentage": 87.84, "elapsed_time": "0:21:49", "remaining_time": "0:03:01"}
|
| 391 |
+
{"current_steps": 391, "total_steps": 444, "loss": 0.2098, "lr": 4.4517327619569784e-07, "epoch": 1.7634105025409372, "percentage": 88.06, "elapsed_time": "0:21:52", "remaining_time": "0:02:57"}
|
| 392 |
+
{"current_steps": 392, "total_steps": 444, "loss": 0.2014, "lr": 4.2907586820356337e-07, "epoch": 1.7679277244494636, "percentage": 88.29, "elapsed_time": "0:21:55", "remaining_time": "0:02:54"}
|
| 393 |
+
{"current_steps": 393, "total_steps": 444, "loss": 0.2126, "lr": 4.132618314205544e-07, "epoch": 1.7724449463579899, "percentage": 88.51, "elapsed_time": "0:21:58", "remaining_time": "0:02:51"}
|
| 394 |
+
{"current_steps": 394, "total_steps": 444, "loss": 0.2033, "lr": 3.9773214622669974e-07, "epoch": 1.776962168266516, "percentage": 88.74, "elapsed_time": "0:22:02", "remaining_time": "0:02:47"}
|
| 395 |
+
{"current_steps": 395, "total_steps": 444, "loss": 0.2057, "lr": 3.8248777537384763e-07, "epoch": 1.7814793901750423, "percentage": 88.96, "elapsed_time": "0:22:05", "remaining_time": "0:02:44"}
|
| 396 |
+
{"current_steps": 396, "total_steps": 444, "loss": 0.2103, "lr": 3.675296639259912e-07, "epoch": 1.7859966120835686, "percentage": 89.19, "elapsed_time": "0:22:09", "remaining_time": "0:02:41"}
|
| 397 |
+
{"current_steps": 397, "total_steps": 444, "loss": 0.214, "lr": 3.528587392006716e-07, "epoch": 1.7905138339920947, "percentage": 89.41, "elapsed_time": "0:22:12", "remaining_time": "0:02:37"}
|
| 398 |
+
{"current_steps": 398, "total_steps": 444, "loss": 0.207, "lr": 3.38475910711491e-07, "epoch": 1.795031055900621, "percentage": 89.64, "elapsed_time": "0:22:15", "remaining_time": "0:02:34"}
|
| 399 |
+
{"current_steps": 399, "total_steps": 444, "loss": 0.2026, "lr": 3.243820701117306e-07, "epoch": 1.7995482778091474, "percentage": 89.86, "elapsed_time": "0:22:19", "remaining_time": "0:02:31"}
|
| 400 |
+
{"current_steps": 400, "total_steps": 444, "loss": 0.2106, "lr": 3.105780911390738e-07, "epoch": 1.8040654997176735, "percentage": 90.09, "elapsed_time": "0:22:22", "remaining_time": "0:02:27"}
|
| 401 |
+
{"current_steps": 401, "total_steps": 444, "loss": 0.2014, "lr": 2.97064829561432e-07, "epoch": 1.8085827216262, "percentage": 90.32, "elapsed_time": "0:22:26", "remaining_time": "0:02:24"}
|
| 402 |
+
{"current_steps": 402, "total_steps": 444, "loss": 0.212, "lr": 2.8384312312390306e-07, "epoch": 1.8130999435347261, "percentage": 90.54, "elapsed_time": "0:22:29", "remaining_time": "0:02:21"}
|
| 403 |
+
{"current_steps": 403, "total_steps": 444, "loss": 0.2198, "lr": 2.7091379149682683e-07, "epoch": 1.8176171654432522, "percentage": 90.77, "elapsed_time": "0:22:32", "remaining_time": "0:02:17"}
|
| 404 |
+
{"current_steps": 404, "total_steps": 444, "loss": 0.2048, "lr": 2.582776362249739e-07, "epoch": 1.8221343873517788, "percentage": 90.99, "elapsed_time": "0:22:36", "remaining_time": "0:02:14"}
|
| 405 |
+
{"current_steps": 405, "total_steps": 444, "loss": 0.2075, "lr": 2.459354406778547e-07, "epoch": 1.826651609260305, "percentage": 91.22, "elapsed_time": "0:22:39", "remaining_time": "0:02:10"}
|
| 406 |
+
{"current_steps": 406, "total_steps": 444, "loss": 0.2068, "lr": 2.3388797000115427e-07, "epoch": 1.8311688311688312, "percentage": 91.44, "elapsed_time": "0:22:43", "remaining_time": "0:02:07"}
|
| 407 |
+
{"current_steps": 407, "total_steps": 444, "loss": 0.2077, "lr": 2.2213597106929608e-07, "epoch": 1.8356860530773575, "percentage": 91.67, "elapsed_time": "0:22:46", "remaining_time": "0:02:04"}
|
| 408 |
+
{"current_steps": 408, "total_steps": 444, "loss": 0.1998, "lr": 2.1068017243914663e-07, "epoch": 1.8402032749858837, "percentage": 91.89, "elapsed_time": "0:22:49", "remaining_time": "0:02:00"}
|
| 409 |
+
{"current_steps": 409, "total_steps": 444, "loss": 0.2118, "lr": 1.9952128430483718e-07, "epoch": 1.84472049689441, "percentage": 92.12, "elapsed_time": "0:22:53", "remaining_time": "0:01:57"}
|
| 410 |
+
{"current_steps": 410, "total_steps": 444, "loss": 0.2041, "lr": 1.8865999845374794e-07, "epoch": 1.8492377188029363, "percentage": 92.34, "elapsed_time": "0:22:56", "remaining_time": "0:01:54"}
|
| 411 |
+
{"current_steps": 411, "total_steps": 444, "loss": 0.2107, "lr": 1.78096988223615e-07, "epoch": 1.8537549407114624, "percentage": 92.57, "elapsed_time": "0:22:59", "remaining_time": "0:01:50"}
|
| 412 |
+
{"current_steps": 412, "total_steps": 444, "loss": 0.2029, "lr": 1.6783290846078714e-07, "epoch": 1.8582721626199887, "percentage": 92.79, "elapsed_time": "0:23:03", "remaining_time": "0:01:47"}
|
| 413 |
+
{"current_steps": 413, "total_steps": 444, "loss": 0.208, "lr": 1.5786839547963008e-07, "epoch": 1.862789384528515, "percentage": 93.02, "elapsed_time": "0:23:06", "remaining_time": "0:01:44"}
|
| 414 |
+
{"current_steps": 414, "total_steps": 444, "loss": 0.2075, "lr": 1.4820406702308165e-07, "epoch": 1.8673066064370412, "percentage": 93.24, "elapsed_time": "0:23:10", "remaining_time": "0:01:40"}
|
| 415 |
+
{"current_steps": 415, "total_steps": 444, "loss": 0.2034, "lr": 1.388405222243472e-07, "epoch": 1.8718238283455675, "percentage": 93.47, "elapsed_time": "0:23:13", "remaining_time": "0:01:37"}
|
| 416 |
+
{"current_steps": 416, "total_steps": 444, "loss": 0.2159, "lr": 1.2977834156976733e-07, "epoch": 1.8763410502540938, "percentage": 93.69, "elapsed_time": "0:23:16", "remaining_time": "0:01:34"}
|
| 417 |
+
{"current_steps": 417, "total_steps": 444, "loss": 0.2078, "lr": 1.210180868628219e-07, "epoch": 1.88085827216262, "percentage": 93.92, "elapsed_time": "0:23:20", "remaining_time": "0:01:30"}
|
| 418 |
+
{"current_steps": 418, "total_steps": 444, "loss": 0.2048, "lr": 1.1256030118930727e-07, "epoch": 1.8853754940711462, "percentage": 94.14, "elapsed_time": "0:23:23", "remaining_time": "0:01:27"}
|
| 419 |
+
{"current_steps": 419, "total_steps": 444, "loss": 0.2027, "lr": 1.0440550888366485e-07, "epoch": 1.8898927159796726, "percentage": 94.37, "elapsed_time": "0:23:26", "remaining_time": "0:01:23"}
|
| 420 |
+
{"current_steps": 420, "total_steps": 444, "loss": 0.2073, "lr": 9.655421549647603e-08, "epoch": 1.8944099378881987, "percentage": 94.59, "elapsed_time": "0:23:30", "remaining_time": "0:01:20"}
|
| 421 |
+
{"current_steps": 421, "total_steps": 444, "loss": 0.2054, "lr": 8.900690776312282e-08, "epoch": 1.898927159796725, "percentage": 94.82, "elapsed_time": "0:23:33", "remaining_time": "0:01:17"}
|
| 422 |
+
{"current_steps": 422, "total_steps": 444, "loss": 0.2162, "lr": 8.176405357361194e-08, "epoch": 1.9034443817052513, "percentage": 95.05, "elapsed_time": "0:23:36", "remaining_time": "0:01:13"}
|
| 423 |
+
{"current_steps": 423, "total_steps": 444, "loss": 0.208, "lr": 7.482610194356477e-08, "epoch": 1.9079616036137774, "percentage": 95.27, "elapsed_time": "0:23:40", "remaining_time": "0:01:10"}
|
| 424 |
+
{"current_steps": 424, "total_steps": 444, "loss": 0.1984, "lr": 6.819348298638839e-08, "epoch": 1.9124788255223037, "percentage": 95.5, "elapsed_time": "0:23:43", "remaining_time": "0:01:07"}
|
| 425 |
+
{"current_steps": 425, "total_steps": 444, "loss": 0.2058, "lr": 6.186660788660315e-08, "epoch": 1.91699604743083, "percentage": 95.72, "elapsed_time": "0:23:47", "remaining_time": "0:01:03"}
|
| 426 |
+
{"current_steps": 426, "total_steps": 444, "loss": 0.2108, "lr": 5.584586887435739e-08, "epoch": 1.9215132693393562, "percentage": 95.95, "elapsed_time": "0:23:50", "remaining_time": "0:01:00"}
|
| 427 |
+
{"current_steps": 427, "total_steps": 444, "loss": 0.2254, "lr": 5.013163920110864e-08, "epoch": 1.9260304912478825, "percentage": 96.17, "elapsed_time": "0:23:53", "remaining_time": "0:00:57"}
|
| 428 |
+
{"current_steps": 428, "total_steps": 444, "loss": 0.2061, "lr": 4.4724273116483754e-08, "epoch": 1.9305477131564088, "percentage": 96.4, "elapsed_time": "0:23:57", "remaining_time": "0:00:53"}
|
| 429 |
+
{"current_steps": 429, "total_steps": 444, "loss": 0.2148, "lr": 3.9624105846319813e-08, "epoch": 1.935064935064935, "percentage": 96.62, "elapsed_time": "0:24:00", "remaining_time": "0:00:50"}
|
| 430 |
+
{"current_steps": 430, "total_steps": 444, "loss": 0.2014, "lr": 3.483145357187967e-08, "epoch": 1.9395821569734615, "percentage": 96.85, "elapsed_time": "0:24:03", "remaining_time": "0:00:47"}
|
| 431 |
+
{"current_steps": 431, "total_steps": 444, "loss": 0.2104, "lr": 3.034661341025258e-08, "epoch": 1.9440993788819876, "percentage": 97.07, "elapsed_time": "0:24:07", "remaining_time": "0:00:43"}
|
| 432 |
+
{"current_steps": 432, "total_steps": 444, "loss": 0.2003, "lr": 2.6169863395932304e-08, "epoch": 1.9486166007905137, "percentage": 97.3, "elapsed_time": "0:24:10", "remaining_time": "0:00:40"}
|
| 433 |
+
{"current_steps": 433, "total_steps": 444, "loss": 0.2174, "lr": 2.230146246358256e-08, "epoch": 1.9531338226990402, "percentage": 97.52, "elapsed_time": "0:24:14", "remaining_time": "0:00:36"}
|
| 434 |
+
{"current_steps": 434, "total_steps": 444, "loss": 0.2025, "lr": 1.8741650431982615e-08, "epoch": 1.9576510446075663, "percentage": 97.75, "elapsed_time": "0:24:17", "remaining_time": "0:00:33"}
|
| 435 |
+
{"current_steps": 435, "total_steps": 444, "loss": 0.2117, "lr": 1.549064798916311e-08, "epoch": 1.9621682665160924, "percentage": 97.97, "elapsed_time": "0:24:20", "remaining_time": "0:00:30"}
|
| 436 |
+
{"current_steps": 436, "total_steps": 444, "loss": 0.2104, "lr": 1.2548656678721404e-08, "epoch": 1.966685488424619, "percentage": 98.2, "elapsed_time": "0:24:24", "remaining_time": "0:00:26"}
|
| 437 |
+
{"current_steps": 437, "total_steps": 444, "loss": 0.2189, "lr": 9.915858887327157e-09, "epoch": 1.971202710333145, "percentage": 98.42, "elapsed_time": "0:24:27", "remaining_time": "0:00:23"}
|
| 438 |
+
{"current_steps": 438, "total_steps": 444, "loss": 0.2026, "lr": 7.59241783341913e-09, "epoch": 1.9757199322416714, "percentage": 98.65, "elapsed_time": "0:24:30", "remaining_time": "0:00:20"}
|
| 439 |
+
{"current_steps": 439, "total_steps": 444, "loss": 0.2134, "lr": 5.578477557081074e-09, "epoch": 1.9802371541501977, "percentage": 98.87, "elapsed_time": "0:24:34", "remaining_time": "0:00:16"}
|
| 440 |
+
{"current_steps": 440, "total_steps": 444, "loss": 0.2081, "lr": 3.874162911117196e-09, "epoch": 1.9847543760587238, "percentage": 99.1, "elapsed_time": "0:24:37", "remaining_time": "0:00:13"}
|
| 441 |
+
{"current_steps": 441, "total_steps": 444, "loss": 0.2027, "lr": 2.479579553307798e-09, "epoch": 1.9892715979672502, "percentage": 99.32, "elapsed_time": "0:24:40", "remaining_time": "0:00:10"}
|
| 442 |
+
{"current_steps": 442, "total_steps": 444, "loss": 0.1985, "lr": 1.3948139398628492e-09, "epoch": 1.9937888198757765, "percentage": 99.55, "elapsed_time": "0:24:44", "remaining_time": "0:00:06"}
|
| 443 |
+
{"current_steps": 443, "total_steps": 444, "loss": 0.1963, "lr": 6.199333200590519e-10, "epoch": 1.9983060417843026, "percentage": 99.77, "elapsed_time": "0:24:47", "remaining_time": "0:00:03"}
|
| 444 |
+
{"current_steps": 444, "total_steps": 444, "loss": 0.2171, "lr": 1.5498573207262112e-10, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "0:24:48", "remaining_time": "0:00:00"}
|
| 445 |
+
{"current_steps": 444, "total_steps": 444, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "0:25:19", "remaining_time": "0:00:00"}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4ed9d1b4df68ffa7ba098f359abef0aec4d28cb3d45670ea7f091bdc384a7d21
|
| 3 |
+
size 6417
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|