Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- g1_0_baseline_original_code/250M/README.md +60 -0
- g1_0_baseline_original_code/250M/added_tokens.json +28 -0
- g1_0_baseline_original_code/250M/all_results.json +8 -0
- g1_0_baseline_original_code/250M/chat_template.jinja +85 -0
- g1_0_baseline_original_code/250M/config.json +68 -0
- g1_0_baseline_original_code/250M/generation_config.json +8 -0
- g1_0_baseline_original_code/250M/merges.txt +0 -0
- g1_0_baseline_original_code/250M/model-00001-of-00004.safetensors +3 -0
- g1_0_baseline_original_code/250M/model-00002-of-00004.safetensors +3 -0
- g1_0_baseline_original_code/250M/model-00003-of-00004.safetensors +3 -0
- g1_0_baseline_original_code/250M/model-00004-of-00004.safetensors +3 -0
- g1_0_baseline_original_code/250M/model.safetensors.index.json +407 -0
- g1_0_baseline_original_code/250M/special_tokens_map.json +31 -0
- g1_0_baseline_original_code/250M/tokenizer.json +3 -0
- g1_0_baseline_original_code/250M/tokenizer_config.json +240 -0
- g1_0_baseline_original_code/250M/train_results.json +8 -0
- g1_0_baseline_original_code/250M/trainer_log.jsonl +26 -0
- g1_0_baseline_original_code/250M/trainer_state.json +1996 -0
- g1_0_baseline_original_code/250M/training_args.bin +3 -0
- g1_0_baseline_original_code/250M/training_loss.png +0 -0
- g1_0_baseline_original_code/250M/vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -34,3 +34,4 @@ saved_model/**/* 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 |
g1_blog_post/250M/tokenizer.json 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 |
g1_blog_post/250M/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
g1_0_baseline_original_code/250M/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
g1_0_baseline_original_code/250M/README.md
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: other
|
| 4 |
+
base_model: Qwen/Qwen3-8B-Base
|
| 5 |
+
tags:
|
| 6 |
+
- llama-factory
|
| 7 |
+
- full
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: 250M
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# 250M
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [/lus/flare/projects/MultiModalLLM/model-weights/Qwen/Qwen3-8B-Base](https://huggingface.co//lus/flare/projects/MultiModalLLM/model-weights/Qwen/Qwen3-8B-Base) on the rv5_g1_0_baseline_original_code and the instruct_replay datasets.
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 2e-05
|
| 39 |
+
- train_batch_size: 1
|
| 40 |
+
- eval_batch_size: 8
|
| 41 |
+
- seed: 42
|
| 42 |
+
- distributed_type: multi-GPU
|
| 43 |
+
- num_devices: 12
|
| 44 |
+
- total_train_batch_size: 12
|
| 45 |
+
- total_eval_batch_size: 96
|
| 46 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.95) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 47 |
+
- lr_scheduler_type: warmup_stable_decay
|
| 48 |
+
- lr_scheduler_warmup_steps: 178
|
| 49 |
+
- training_steps: 2797
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
|
| 54 |
+
|
| 55 |
+
### Framework versions
|
| 56 |
+
|
| 57 |
+
- Transformers 4.57.6
|
| 58 |
+
- Pytorch 2.10.0a0+git449b176
|
| 59 |
+
- Datasets 4.5.0
|
| 60 |
+
- Tokenizers 0.22.2
|
g1_0_baseline_original_code/250M/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 |
+
}
|
g1_0_baseline_original_code/250M/all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.24340788443129405,
|
| 3 |
+
"total_flos": 1.2485883762455871e+19,
|
| 4 |
+
"train_loss": 0.0675735119030993,
|
| 5 |
+
"train_runtime": 2890.5564,
|
| 6 |
+
"train_samples_per_second": 11.612,
|
| 7 |
+
"train_steps_per_second": 0.968
|
| 8 |
+
}
|
g1_0_baseline_original_code/250M/chat_template.jinja
ADDED
|
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 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.role == "user") or (message.role == "system" and not loop.first) %}
|
| 27 |
+
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
| 28 |
+
{%- elif message.role == "assistant" %}
|
| 29 |
+
{%- set content = message.content %}
|
| 30 |
+
{%- set reasoning_content = '' %}
|
| 31 |
+
{%- if message.reasoning_content is defined and message.reasoning_content is not none %}
|
| 32 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 33 |
+
{%- else %}
|
| 34 |
+
{%- if '</think>' in message.content %}
|
| 35 |
+
{%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
|
| 36 |
+
{%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 37 |
+
{%- endif %}
|
| 38 |
+
{%- endif %}
|
| 39 |
+
{%- if loop.index0 > ns.last_query_index %}
|
| 40 |
+
{%- if loop.last or (not loop.last and reasoning_content) %}
|
| 41 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
| 42 |
+
{%- else %}
|
| 43 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 44 |
+
{%- endif %}
|
| 45 |
+
{%- else %}
|
| 46 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 47 |
+
{%- endif %}
|
| 48 |
+
{%- if message.tool_calls %}
|
| 49 |
+
{%- for tool_call in message.tool_calls %}
|
| 50 |
+
{%- if (loop.first and content) or (not loop.first) %}
|
| 51 |
+
{{- '\n' }}
|
| 52 |
+
{%- endif %}
|
| 53 |
+
{%- if tool_call.function %}
|
| 54 |
+
{%- set tool_call = tool_call.function %}
|
| 55 |
+
{%- endif %}
|
| 56 |
+
{{- '<tool_call>\n{"name": "' }}
|
| 57 |
+
{{- tool_call.name }}
|
| 58 |
+
{{- '", "arguments": ' }}
|
| 59 |
+
{%- if tool_call.arguments is string %}
|
| 60 |
+
{{- tool_call.arguments }}
|
| 61 |
+
{%- else %}
|
| 62 |
+
{{- tool_call.arguments | tojson }}
|
| 63 |
+
{%- endif %}
|
| 64 |
+
{{- '}\n</tool_call>' }}
|
| 65 |
+
{%- endfor %}
|
| 66 |
+
{%- endif %}
|
| 67 |
+
{{- '<|im_end|>\n' }}
|
| 68 |
+
{%- elif message.role == "tool" %}
|
| 69 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 70 |
+
{{- '<|im_start|>user' }}
|
| 71 |
+
{%- endif %}
|
| 72 |
+
{{- '\n<tool_response>\n' }}
|
| 73 |
+
{{- message.content }}
|
| 74 |
+
{{- '\n</tool_response>' }}
|
| 75 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 76 |
+
{{- '<|im_end|>\n' }}
|
| 77 |
+
{%- endif %}
|
| 78 |
+
{%- endif %}
|
| 79 |
+
{%- endfor %}
|
| 80 |
+
{%- if add_generation_prompt %}
|
| 81 |
+
{{- '<|im_start|>assistant\n' }}
|
| 82 |
+
{%- if enable_thinking is defined and enable_thinking is false %}
|
| 83 |
+
{{- '<think>\n\n</think>\n\n' }}
|
| 84 |
+
{%- endif %}
|
| 85 |
+
{%- endif %}
|
g1_0_baseline_original_code/250M/config.json
ADDED
|
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"dtype": "bfloat16",
|
| 8 |
+
"eos_token_id": 151643,
|
| 9 |
+
"head_dim": 128,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 4096,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 12288,
|
| 14 |
+
"layer_types": [
|
| 15 |
+
"full_attention",
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"full_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"full_attention",
|
| 49 |
+
"full_attention",
|
| 50 |
+
"full_attention"
|
| 51 |
+
],
|
| 52 |
+
"max_position_embeddings": 32768,
|
| 53 |
+
"max_window_layers": 36,
|
| 54 |
+
"model_type": "qwen3",
|
| 55 |
+
"num_attention_heads": 32,
|
| 56 |
+
"num_hidden_layers": 36,
|
| 57 |
+
"num_key_value_heads": 8,
|
| 58 |
+
"pad_token_id": 151643,
|
| 59 |
+
"rms_norm_eps": 1e-06,
|
| 60 |
+
"rope_scaling": null,
|
| 61 |
+
"rope_theta": 1000000,
|
| 62 |
+
"sliding_window": null,
|
| 63 |
+
"tie_word_embeddings": false,
|
| 64 |
+
"transformers_version": "4.57.6",
|
| 65 |
+
"use_cache": false,
|
| 66 |
+
"use_sliding_window": false,
|
| 67 |
+
"vocab_size": 151936
|
| 68 |
+
}
|
g1_0_baseline_original_code/250M/generation_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"eos_token_id": [
|
| 3 |
+
151643
|
| 4 |
+
],
|
| 5 |
+
"max_new_tokens": 2048,
|
| 6 |
+
"pad_token_id": 151643,
|
| 7 |
+
"transformers_version": "4.57.6"
|
| 8 |
+
}
|
g1_0_baseline_original_code/250M/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
g1_0_baseline_original_code/250M/model-00001-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2bfcdef7e9a606e31c2c64fbd9fcbd7e628c2fd742980e9c5c3e36933e7ea84f
|
| 3 |
+
size 4902257696
|
g1_0_baseline_original_code/250M/model-00002-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d5ec02d5582143715437257cb12d34b41b83dbd7eb6dd20ca20517d531936398
|
| 3 |
+
size 4915960368
|
g1_0_baseline_original_code/250M/model-00003-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:64d86ebb5d26068718e76a52d236366de0c84474e648837c44846cb8b43ef79c
|
| 3 |
+
size 4983068496
|
g1_0_baseline_original_code/250M/model-00004-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:23c32c8e9bf122c1825523bcf05c179c68b1ef75697c9a0d6493331eb6928c9d
|
| 3 |
+
size 1580230264
|
g1_0_baseline_original_code/250M/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,407 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 8190735360,
|
| 4 |
+
"total_size": 16381470720
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"lm_head.weight": "model-00004-of-00004.safetensors",
|
| 8 |
+
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
| 9 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 10 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 11 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 12 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 13 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 19 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 20 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 21 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 22 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 23 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 24 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 29 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 30 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 31 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 32 |
+
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 33 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 34 |
+
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 35 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 36 |
+
"model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 37 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 38 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 39 |
+
"model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 40 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 41 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 42 |
+
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 43 |
+
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 44 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 45 |
+
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 46 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 47 |
+
"model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 48 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 49 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 50 |
+
"model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 51 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 52 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 53 |
+
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 54 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 55 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 56 |
+
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 57 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 58 |
+
"model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 59 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 60 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 61 |
+
"model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 62 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 63 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 64 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 65 |
+
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 66 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 67 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 68 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 69 |
+
"model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 70 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 71 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 72 |
+
"model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 73 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 74 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 75 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 76 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 77 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 78 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 79 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 80 |
+
"model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 81 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 82 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 83 |
+
"model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 84 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 85 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 86 |
+
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 87 |
+
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 88 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 89 |
+
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 90 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 91 |
+
"model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 92 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 93 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 94 |
+
"model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 95 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 96 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 97 |
+
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 98 |
+
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 99 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 100 |
+
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 101 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 102 |
+
"model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 103 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 104 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 105 |
+
"model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 106 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 107 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 108 |
+
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 109 |
+
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 110 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 111 |
+
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 112 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 113 |
+
"model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 114 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 115 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 116 |
+
"model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 117 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 118 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 119 |
+
"model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 120 |
+
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 121 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 122 |
+
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 123 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 124 |
+
"model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 125 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 126 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 127 |
+
"model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 128 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 129 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 130 |
+
"model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 131 |
+
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 132 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 133 |
+
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 134 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 135 |
+
"model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 136 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 137 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 138 |
+
"model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 139 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 140 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 141 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 142 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 143 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 144 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 145 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 146 |
+
"model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 147 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 148 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 149 |
+
"model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 150 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 151 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 152 |
+
"model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 153 |
+
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 154 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 155 |
+
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 156 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 157 |
+
"model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 158 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 159 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 160 |
+
"model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 161 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 162 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 163 |
+
"model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 164 |
+
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 165 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 166 |
+
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 167 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 168 |
+
"model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 169 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 170 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 171 |
+
"model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 172 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 173 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 174 |
+
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 175 |
+
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 176 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 177 |
+
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 178 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 179 |
+
"model.layers.22.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 180 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 181 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 182 |
+
"model.layers.22.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 183 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 184 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 185 |
+
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 186 |
+
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 187 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 188 |
+
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 189 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 190 |
+
"model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 191 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 192 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 193 |
+
"model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 194 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 195 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 196 |
+
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 197 |
+
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 198 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 199 |
+
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 200 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 201 |
+
"model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 202 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 203 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 204 |
+
"model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 205 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 206 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 207 |
+
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 208 |
+
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 209 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 210 |
+
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 211 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 212 |
+
"model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 213 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 214 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 215 |
+
"model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 216 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 217 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 218 |
+
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 219 |
+
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 220 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 221 |
+
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 222 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 223 |
+
"model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 224 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 225 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 226 |
+
"model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 227 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 228 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 229 |
+
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 230 |
+
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 231 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 232 |
+
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 233 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 234 |
+
"model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 235 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 236 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 237 |
+
"model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 238 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 239 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 240 |
+
"model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 241 |
+
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 242 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 243 |
+
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 244 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 245 |
+
"model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 246 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 247 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 248 |
+
"model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 249 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 250 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 251 |
+
"model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 252 |
+
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 253 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 254 |
+
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 255 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 256 |
+
"model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 257 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 258 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 259 |
+
"model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 260 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 261 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 262 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 263 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 264 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 265 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 266 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 267 |
+
"model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 268 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 269 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 270 |
+
"model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 271 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 272 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 273 |
+
"model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 274 |
+
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 275 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 276 |
+
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 277 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 278 |
+
"model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 279 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 280 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 281 |
+
"model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 282 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 283 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 284 |
+
"model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 285 |
+
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 286 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 287 |
+
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 288 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 289 |
+
"model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 290 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 291 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 292 |
+
"model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 293 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 294 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 295 |
+
"model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 296 |
+
"model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 297 |
+
"model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 298 |
+
"model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 299 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 300 |
+
"model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 301 |
+
"model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 302 |
+
"model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 303 |
+
"model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 304 |
+
"model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 305 |
+
"model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 306 |
+
"model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 307 |
+
"model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 308 |
+
"model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 309 |
+
"model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 310 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 311 |
+
"model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 312 |
+
"model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 313 |
+
"model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 314 |
+
"model.layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 315 |
+
"model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 316 |
+
"model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 317 |
+
"model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 318 |
+
"model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 319 |
+
"model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 320 |
+
"model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 321 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 322 |
+
"model.layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 323 |
+
"model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 324 |
+
"model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 325 |
+
"model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 326 |
+
"model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 327 |
+
"model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 328 |
+
"model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 329 |
+
"model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 330 |
+
"model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 331 |
+
"model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 332 |
+
"model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 333 |
+
"model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
| 334 |
+
"model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 335 |
+
"model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
| 336 |
+
"model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
| 337 |
+
"model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 338 |
+
"model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 339 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 340 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 341 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 342 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 343 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 344 |
+
"model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 345 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 346 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 347 |
+
"model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 348 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 349 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 350 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 351 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 352 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 353 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 354 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 355 |
+
"model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 356 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 357 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 358 |
+
"model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 359 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 360 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 361 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 362 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 363 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 364 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 365 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 366 |
+
"model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 367 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 368 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 369 |
+
"model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 370 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 371 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 372 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 373 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 374 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 375 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 376 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 377 |
+
"model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 378 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 379 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 380 |
+
"model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 381 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 382 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 383 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 384 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 385 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 386 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 387 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 388 |
+
"model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 389 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 390 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 391 |
+
"model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 392 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 393 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 394 |
+
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 395 |
+
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 396 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 397 |
+
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 398 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 399 |
+
"model.layers.9.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 400 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 401 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 402 |
+
"model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 403 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 404 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 405 |
+
"model.norm.weight": "model-00004-of-00004.safetensors"
|
| 406 |
+
}
|
| 407 |
+
}
|
g1_0_baseline_original_code/250M/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": "<|endoftext|>",
|
| 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 |
+
}
|
g1_0_baseline_original_code/250M/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
| 3 |
+
size 11422654
|
g1_0_baseline_original_code/250M/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": "<|endoftext|>",
|
| 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 |
+
}
|
g1_0_baseline_original_code/250M/train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.24340788443129405,
|
| 3 |
+
"total_flos": 1.2485883762455871e+19,
|
| 4 |
+
"train_loss": 0.0675735119030993,
|
| 5 |
+
"train_runtime": 2890.5564,
|
| 6 |
+
"train_samples_per_second": 11.612,
|
| 7 |
+
"train_steps_per_second": 0.968
|
| 8 |
+
}
|
g1_0_baseline_original_code/250M/trainer_log.jsonl
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 2550, "total_steps": 2797, "loss": 0.7929, "lr": 1.997261400182901e-05, "epoch": 0.22191280132277436, "percentage": 91.17, "elapsed_time": "0:01:25", "remaining_time": "0:00:08"}
|
| 2 |
+
{"current_steps": 2560, "total_steps": 2797, "loss": 0.7735, "lr": 1.9805800746810423e-05, "epoch": 0.2227830476024715, "percentage": 91.53, "elapsed_time": "0:03:17", "remaining_time": "0:00:18"}
|
| 3 |
+
{"current_steps": 2570, "total_steps": 2797, "loss": 0.7434, "lr": 1.9489934220110274e-05, "epoch": 0.22365329388216865, "percentage": 91.88, "elapsed_time": "0:05:10", "remaining_time": "0:00:27"}
|
| 4 |
+
{"current_steps": 2580, "total_steps": 2797, "loss": 0.6999, "lr": 1.9029840364820392e-05, "epoch": 0.22452354016186582, "percentage": 92.24, "elapsed_time": "0:07:03", "remaining_time": "0:00:35"}
|
| 5 |
+
{"current_steps": 2590, "total_steps": 2797, "loss": 0.7438, "lr": 1.8432548690479908e-05, "epoch": 0.22539378644156297, "percentage": 92.6, "elapsed_time": "0:08:56", "remaining_time": "0:00:42"}
|
| 6 |
+
{"current_steps": 2600, "total_steps": 2797, "loss": 0.7853, "lr": 1.7707184873239772e-05, "epoch": 0.2262640327212601, "percentage": 92.96, "elapsed_time": "0:10:49", "remaining_time": "0:00:49"}
|
| 7 |
+
{"current_steps": 2610, "total_steps": 2797, "loss": 0.759, "lr": 1.6864831329902565e-05, "epoch": 0.22713427900095728, "percentage": 93.31, "elapsed_time": "0:12:42", "remaining_time": "0:00:54"}
|
| 8 |
+
{"current_steps": 2620, "total_steps": 2797, "loss": 0.7196, "lr": 1.591835789604667e-05, "epoch": 0.22800452528065443, "percentage": 93.67, "elapsed_time": "0:14:35", "remaining_time": "0:00:59"}
|
| 9 |
+
{"current_steps": 2630, "total_steps": 2797, "loss": 0.7285, "lr": 1.4882225195206459e-05, "epoch": 0.22887477156035158, "percentage": 94.03, "elapsed_time": "0:16:28", "remaining_time": "0:01:02"}
|
| 10 |
+
{"current_steps": 2640, "total_steps": 2797, "loss": 0.7005, "lr": 1.3772263703317695e-05, "epoch": 0.22974501784004872, "percentage": 94.39, "elapsed_time": "0:18:21", "remaining_time": "0:01:05"}
|
| 11 |
+
{"current_steps": 2650, "total_steps": 2797, "loss": 0.7329, "lr": 1.2605431883975547e-05, "epoch": 0.2306152641197459, "percentage": 94.74, "elapsed_time": "0:20:13", "remaining_time": "0:01:07"}
|
| 12 |
+
{"current_steps": 2660, "total_steps": 2797, "loss": 0.6914, "lr": 1.1399557089817574e-05, "epoch": 0.23148551039944304, "percentage": 95.1, "elapsed_time": "0:22:06", "remaining_time": "0:01:08"}
|
| 13 |
+
{"current_steps": 2670, "total_steps": 2797, "loss": 0.7477, "lr": 1.0173063188650463e-05, "epoch": 0.23235575667914019, "percentage": 95.46, "elapsed_time": "0:23:59", "remaining_time": "0:01:08"}
|
| 14 |
+
{"current_steps": 2680, "total_steps": 2797, "loss": 0.7411, "lr": 8.944689075764396e-06, "epoch": 0.23322600295883736, "percentage": 95.82, "elapsed_time": "0:25:51", "remaining_time": "0:01:07"}
|
| 15 |
+
{"current_steps": 2690, "total_steps": 2797, "loss": 0.737, "lr": 7.73320237312362e-06, "epoch": 0.2340962492385345, "percentage": 96.17, "elapsed_time": "0:27:44", "remaining_time": "0:01:06"}
|
| 16 |
+
{"current_steps": 2700, "total_steps": 2797, "loss": 0.7999, "lr": 6.557112689658629e-06, "epoch": 0.23496649551823165, "percentage": 96.53, "elapsed_time": "0:29:37", "remaining_time": "0:01:03"}
|
| 17 |
+
{"current_steps": 2710, "total_steps": 2797, "loss": 0.7811, "lr": 5.434388823591213e-06, "epoch": 0.23583674179792882, "percentage": 96.89, "elapsed_time": "0:31:30", "remaining_time": "0:01:00"}
|
| 18 |
+
{"current_steps": 2720, "total_steps": 2797, "loss": 0.6815, "lr": 4.382184227495424e-06, "epoch": 0.23670698807762597, "percentage": 97.25, "elapsed_time": "0:33:23", "remaining_time": "0:00:56"}
|
| 19 |
+
{"current_steps": 2730, "total_steps": 2797, "loss": 0.7317, "lr": 3.4165749305560203e-06, "epoch": 0.2375772343573231, "percentage": 97.6, "elapsed_time": "0:35:15", "remaining_time": "0:00:51"}
|
| 20 |
+
{"current_steps": 2740, "total_steps": 2797, "loss": 0.7648, "lr": 2.5523139221595556e-06, "epoch": 0.2384474806370203, "percentage": 97.96, "elapsed_time": "0:37:08", "remaining_time": "0:00:46"}
|
| 21 |
+
{"current_steps": 2750, "total_steps": 2797, "loss": 0.714, "lr": 1.8026057494499821e-06, "epoch": 0.23931772691671743, "percentage": 98.32, "elapsed_time": "0:39:01", "remaining_time": "0:00:40"}
|
| 22 |
+
{"current_steps": 2760, "total_steps": 2797, "loss": 0.7488, "lr": 1.178904772643223e-06, "epoch": 0.24018797319641458, "percentage": 98.68, "elapsed_time": "0:40:54", "remaining_time": "0:00:32"}
|
| 23 |
+
{"current_steps": 2770, "total_steps": 2797, "loss": 0.723, "lr": 6.90740160441754e-07, "epoch": 0.24105821947611175, "percentage": 99.03, "elapsed_time": "0:42:47", "remaining_time": "0:00:25"}
|
| 24 |
+
{"current_steps": 2780, "total_steps": 2797, "loss": 0.7705, "lr": 3.45570299343632e-07, "epoch": 0.2419284657558089, "percentage": 99.39, "elapsed_time": "0:44:40", "remaining_time": "0:00:16"}
|
| 25 |
+
{"current_steps": 2790, "total_steps": 2797, "loss": 0.7337, "lr": 1.486688412425152e-07, "epoch": 0.24279871203550604, "percentage": 99.75, "elapsed_time": "0:46:33", "remaining_time": "0:00:07"}
|
| 26 |
+
{"current_steps": 2797, "total_steps": 2797, "epoch": 0.24340788443129405, "percentage": 100.0, "elapsed_time": "0:48:10", "remaining_time": "0:00:00"}
|
g1_0_baseline_original_code/250M/trainer_state.json
ADDED
|
@@ -0,0 +1,1996 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.24340788443129405,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 2797,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.0008702462796971543,
|
| 14 |
+
"grad_norm": 0.8158680200576782,
|
| 15 |
+
"learning_rate": 1.1061797752808989e-06,
|
| 16 |
+
"loss": 0.8064,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.0017404925593943086,
|
| 21 |
+
"grad_norm": 0.7179011106491089,
|
| 22 |
+
"learning_rate": 2.2241573033707866e-06,
|
| 23 |
+
"loss": 0.8611,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.002610738839091463,
|
| 28 |
+
"grad_norm": 0.7616086006164551,
|
| 29 |
+
"learning_rate": 3.342134831460675e-06,
|
| 30 |
+
"loss": 0.8345,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.003480985118788617,
|
| 35 |
+
"grad_norm": 0.7575607299804688,
|
| 36 |
+
"learning_rate": 4.4601123595505624e-06,
|
| 37 |
+
"loss": 0.782,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.004351231398485772,
|
| 42 |
+
"grad_norm": 0.693459689617157,
|
| 43 |
+
"learning_rate": 5.5780898876404495e-06,
|
| 44 |
+
"loss": 0.7982,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.005221477678182926,
|
| 49 |
+
"grad_norm": 0.8085905313491821,
|
| 50 |
+
"learning_rate": 6.6960674157303374e-06,
|
| 51 |
+
"loss": 0.833,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.00609172395788008,
|
| 56 |
+
"grad_norm": 0.7296540141105652,
|
| 57 |
+
"learning_rate": 7.814044943820226e-06,
|
| 58 |
+
"loss": 0.8223,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.006961970237577234,
|
| 63 |
+
"grad_norm": 0.8127589821815491,
|
| 64 |
+
"learning_rate": 8.932022471910112e-06,
|
| 65 |
+
"loss": 0.821,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.00783221651727439,
|
| 70 |
+
"grad_norm": 0.7933650612831116,
|
| 71 |
+
"learning_rate": 1.005e-05,
|
| 72 |
+
"loss": 0.8126,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.008702462796971544,
|
| 77 |
+
"grad_norm": 0.8780409097671509,
|
| 78 |
+
"learning_rate": 1.1167977528089888e-05,
|
| 79 |
+
"loss": 0.8142,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.009572709076668698,
|
| 84 |
+
"grad_norm": 0.6804197430610657,
|
| 85 |
+
"learning_rate": 1.2285955056179776e-05,
|
| 86 |
+
"loss": 0.7658,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.010442955356365852,
|
| 91 |
+
"grad_norm": 0.7107055187225342,
|
| 92 |
+
"learning_rate": 1.3403932584269664e-05,
|
| 93 |
+
"loss": 0.7991,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.011313201636063006,
|
| 98 |
+
"grad_norm": 0.8758859038352966,
|
| 99 |
+
"learning_rate": 1.4521910112359552e-05,
|
| 100 |
+
"loss": 0.7913,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.01218344791576016,
|
| 105 |
+
"grad_norm": 0.7684692740440369,
|
| 106 |
+
"learning_rate": 1.563988764044944e-05,
|
| 107 |
+
"loss": 0.7822,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.013053694195457315,
|
| 112 |
+
"grad_norm": 0.7298606634140015,
|
| 113 |
+
"learning_rate": 1.6757865168539328e-05,
|
| 114 |
+
"loss": 0.8112,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.013923940475154469,
|
| 119 |
+
"grad_norm": 0.8325710296630859,
|
| 120 |
+
"learning_rate": 1.7875842696629214e-05,
|
| 121 |
+
"loss": 0.7793,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.014794186754851623,
|
| 126 |
+
"grad_norm": 0.7262638807296753,
|
| 127 |
+
"learning_rate": 1.89938202247191e-05,
|
| 128 |
+
"loss": 0.8179,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.01566443303454878,
|
| 133 |
+
"grad_norm": 0.6672640442848206,
|
| 134 |
+
"learning_rate": 2e-05,
|
| 135 |
+
"loss": 0.785,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.01653467931424593,
|
| 140 |
+
"grad_norm": 0.6894041895866394,
|
| 141 |
+
"learning_rate": 2e-05,
|
| 142 |
+
"loss": 0.7999,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.017404925593943087,
|
| 147 |
+
"grad_norm": 0.874378502368927,
|
| 148 |
+
"learning_rate": 2e-05,
|
| 149 |
+
"loss": 0.8239,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.01827517187364024,
|
| 154 |
+
"grad_norm": 1.8603137731552124,
|
| 155 |
+
"learning_rate": 2e-05,
|
| 156 |
+
"loss": 0.8027,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.019145418153337396,
|
| 161 |
+
"grad_norm": 0.6029776930809021,
|
| 162 |
+
"learning_rate": 2e-05,
|
| 163 |
+
"loss": 0.7925,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.020015664433034548,
|
| 168 |
+
"grad_norm": 0.5086408257484436,
|
| 169 |
+
"learning_rate": 2e-05,
|
| 170 |
+
"loss": 0.7848,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.020885910712731704,
|
| 175 |
+
"grad_norm": 0.6472004652023315,
|
| 176 |
+
"learning_rate": 2e-05,
|
| 177 |
+
"loss": 0.866,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.021756156992428857,
|
| 182 |
+
"grad_norm": 0.5685424208641052,
|
| 183 |
+
"learning_rate": 2e-05,
|
| 184 |
+
"loss": 0.8428,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.022626403272126012,
|
| 189 |
+
"grad_norm": 1.3492158651351929,
|
| 190 |
+
"learning_rate": 2e-05,
|
| 191 |
+
"loss": 0.8308,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.023496649551823165,
|
| 196 |
+
"grad_norm": 0.5286843776702881,
|
| 197 |
+
"learning_rate": 2e-05,
|
| 198 |
+
"loss": 0.8261,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.02436689583152032,
|
| 203 |
+
"grad_norm": 0.6105023622512817,
|
| 204 |
+
"learning_rate": 2e-05,
|
| 205 |
+
"loss": 0.7661,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.025237142111217473,
|
| 210 |
+
"grad_norm": 0.4609563648700714,
|
| 211 |
+
"learning_rate": 2e-05,
|
| 212 |
+
"loss": 0.8126,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.02610738839091463,
|
| 217 |
+
"grad_norm": 0.6476384997367859,
|
| 218 |
+
"learning_rate": 2e-05,
|
| 219 |
+
"loss": 0.8278,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.02697763467061178,
|
| 224 |
+
"grad_norm": 0.5048861503601074,
|
| 225 |
+
"learning_rate": 2e-05,
|
| 226 |
+
"loss": 0.8506,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.027847880950308938,
|
| 231 |
+
"grad_norm": 0.5072876811027527,
|
| 232 |
+
"learning_rate": 2e-05,
|
| 233 |
+
"loss": 0.8343,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.02871812723000609,
|
| 238 |
+
"grad_norm": 0.5325110554695129,
|
| 239 |
+
"learning_rate": 2e-05,
|
| 240 |
+
"loss": 0.8436,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.029588373509703246,
|
| 245 |
+
"grad_norm": 0.7821893692016602,
|
| 246 |
+
"learning_rate": 2e-05,
|
| 247 |
+
"loss": 0.863,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.030458619789400402,
|
| 252 |
+
"grad_norm": 0.6330892443656921,
|
| 253 |
+
"learning_rate": 2e-05,
|
| 254 |
+
"loss": 0.8124,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.03132886606909756,
|
| 259 |
+
"grad_norm": 0.4850161671638489,
|
| 260 |
+
"learning_rate": 2e-05,
|
| 261 |
+
"loss": 0.7852,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.03219911234879471,
|
| 266 |
+
"grad_norm": 0.4619266092777252,
|
| 267 |
+
"learning_rate": 2e-05,
|
| 268 |
+
"loss": 0.8301,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.03306935862849186,
|
| 273 |
+
"grad_norm": 0.5263406038284302,
|
| 274 |
+
"learning_rate": 2e-05,
|
| 275 |
+
"loss": 0.7954,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.033939604908189015,
|
| 280 |
+
"grad_norm": 0.9923900365829468,
|
| 281 |
+
"learning_rate": 2e-05,
|
| 282 |
+
"loss": 0.8744,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.034809851187886175,
|
| 287 |
+
"grad_norm": 0.5081281661987305,
|
| 288 |
+
"learning_rate": 2e-05,
|
| 289 |
+
"loss": 0.8617,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.03568009746758333,
|
| 294 |
+
"grad_norm": 0.451652467250824,
|
| 295 |
+
"learning_rate": 2e-05,
|
| 296 |
+
"loss": 0.8295,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.03655034374728048,
|
| 301 |
+
"grad_norm": 0.47090429067611694,
|
| 302 |
+
"learning_rate": 2e-05,
|
| 303 |
+
"loss": 0.8121,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.03742059002697763,
|
| 308 |
+
"grad_norm": 0.7138198614120483,
|
| 309 |
+
"learning_rate": 2e-05,
|
| 310 |
+
"loss": 0.8482,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.03829083630667479,
|
| 315 |
+
"grad_norm": 0.46840688586235046,
|
| 316 |
+
"learning_rate": 2e-05,
|
| 317 |
+
"loss": 0.7972,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.039161082586371944,
|
| 322 |
+
"grad_norm": 0.4283294379711151,
|
| 323 |
+
"learning_rate": 2e-05,
|
| 324 |
+
"loss": 0.7798,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.040031328866069096,
|
| 329 |
+
"grad_norm": 0.572551429271698,
|
| 330 |
+
"learning_rate": 2e-05,
|
| 331 |
+
"loss": 0.8056,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.04090157514576625,
|
| 336 |
+
"grad_norm": 0.46540436148643494,
|
| 337 |
+
"learning_rate": 2e-05,
|
| 338 |
+
"loss": 0.8542,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.04177182142546341,
|
| 343 |
+
"grad_norm": 0.4510163962841034,
|
| 344 |
+
"learning_rate": 2e-05,
|
| 345 |
+
"loss": 0.7786,
|
| 346 |
+
"step": 480
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.04264206770516056,
|
| 350 |
+
"grad_norm": 0.42309340834617615,
|
| 351 |
+
"learning_rate": 2e-05,
|
| 352 |
+
"loss": 0.8706,
|
| 353 |
+
"step": 490
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.04351231398485771,
|
| 357 |
+
"grad_norm": 0.5350301861763,
|
| 358 |
+
"learning_rate": 2e-05,
|
| 359 |
+
"loss": 0.7619,
|
| 360 |
+
"step": 500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.044382560264554866,
|
| 364 |
+
"grad_norm": 0.4541406035423279,
|
| 365 |
+
"learning_rate": 2e-05,
|
| 366 |
+
"loss": 0.8028,
|
| 367 |
+
"step": 510
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.045252806544252025,
|
| 371 |
+
"grad_norm": 0.4715532958507538,
|
| 372 |
+
"learning_rate": 2e-05,
|
| 373 |
+
"loss": 0.8048,
|
| 374 |
+
"step": 520
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.04612305282394918,
|
| 378 |
+
"grad_norm": 0.4572128653526306,
|
| 379 |
+
"learning_rate": 2e-05,
|
| 380 |
+
"loss": 0.8758,
|
| 381 |
+
"step": 530
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.04699329910364633,
|
| 385 |
+
"grad_norm": 0.6988846063613892,
|
| 386 |
+
"learning_rate": 2e-05,
|
| 387 |
+
"loss": 0.8037,
|
| 388 |
+
"step": 540
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.04786354538334349,
|
| 392 |
+
"grad_norm": 0.4304225742816925,
|
| 393 |
+
"learning_rate": 2e-05,
|
| 394 |
+
"loss": 0.817,
|
| 395 |
+
"step": 550
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.04873379166304064,
|
| 399 |
+
"grad_norm": 2.422055959701538,
|
| 400 |
+
"learning_rate": 2e-05,
|
| 401 |
+
"loss": 0.7814,
|
| 402 |
+
"step": 560
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.049604037942737794,
|
| 406 |
+
"grad_norm": 0.5068548321723938,
|
| 407 |
+
"learning_rate": 2e-05,
|
| 408 |
+
"loss": 0.8187,
|
| 409 |
+
"step": 570
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.05047428422243495,
|
| 413 |
+
"grad_norm": 0.5027887225151062,
|
| 414 |
+
"learning_rate": 2e-05,
|
| 415 |
+
"loss": 0.8086,
|
| 416 |
+
"step": 580
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.051344530502132106,
|
| 420 |
+
"grad_norm": 0.4520089328289032,
|
| 421 |
+
"learning_rate": 2e-05,
|
| 422 |
+
"loss": 0.7763,
|
| 423 |
+
"step": 590
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.05221477678182926,
|
| 427 |
+
"grad_norm": 0.5107803344726562,
|
| 428 |
+
"learning_rate": 2e-05,
|
| 429 |
+
"loss": 0.8159,
|
| 430 |
+
"step": 600
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.05308502306152641,
|
| 434 |
+
"grad_norm": 0.45489200949668884,
|
| 435 |
+
"learning_rate": 2e-05,
|
| 436 |
+
"loss": 0.7862,
|
| 437 |
+
"step": 610
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.05395526934122356,
|
| 441 |
+
"grad_norm": 0.7768973112106323,
|
| 442 |
+
"learning_rate": 2e-05,
|
| 443 |
+
"loss": 0.8653,
|
| 444 |
+
"step": 620
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.05482551562092072,
|
| 448 |
+
"grad_norm": 0.6188347935676575,
|
| 449 |
+
"learning_rate": 2e-05,
|
| 450 |
+
"loss": 0.776,
|
| 451 |
+
"step": 630
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.055695761900617875,
|
| 455 |
+
"grad_norm": 0.48372647166252136,
|
| 456 |
+
"learning_rate": 2e-05,
|
| 457 |
+
"loss": 0.8327,
|
| 458 |
+
"step": 640
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.05656600818031503,
|
| 462 |
+
"grad_norm": 0.5156493186950684,
|
| 463 |
+
"learning_rate": 2e-05,
|
| 464 |
+
"loss": 0.8038,
|
| 465 |
+
"step": 650
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.05743625446001218,
|
| 469 |
+
"grad_norm": 0.39719289541244507,
|
| 470 |
+
"learning_rate": 2e-05,
|
| 471 |
+
"loss": 0.7371,
|
| 472 |
+
"step": 660
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.05830650073970934,
|
| 476 |
+
"grad_norm": 0.44546040892601013,
|
| 477 |
+
"learning_rate": 2e-05,
|
| 478 |
+
"loss": 0.8425,
|
| 479 |
+
"step": 670
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.05917674701940649,
|
| 483 |
+
"grad_norm": 0.41636353731155396,
|
| 484 |
+
"learning_rate": 2e-05,
|
| 485 |
+
"loss": 0.77,
|
| 486 |
+
"step": 680
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.060046993299103645,
|
| 490 |
+
"grad_norm": 0.4664352536201477,
|
| 491 |
+
"learning_rate": 2e-05,
|
| 492 |
+
"loss": 0.7957,
|
| 493 |
+
"step": 690
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.060917239578800804,
|
| 497 |
+
"grad_norm": 0.8170375823974609,
|
| 498 |
+
"learning_rate": 2e-05,
|
| 499 |
+
"loss": 0.7785,
|
| 500 |
+
"step": 700
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.061787485858497956,
|
| 504 |
+
"grad_norm": 0.4736400842666626,
|
| 505 |
+
"learning_rate": 2e-05,
|
| 506 |
+
"loss": 0.7872,
|
| 507 |
+
"step": 710
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.06265773213819512,
|
| 511 |
+
"grad_norm": 0.4570176601409912,
|
| 512 |
+
"learning_rate": 2e-05,
|
| 513 |
+
"loss": 0.8049,
|
| 514 |
+
"step": 720
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.06352797841789226,
|
| 518 |
+
"grad_norm": 0.46406471729278564,
|
| 519 |
+
"learning_rate": 2e-05,
|
| 520 |
+
"loss": 0.7429,
|
| 521 |
+
"step": 730
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.06439822469758942,
|
| 525 |
+
"grad_norm": 0.47335994243621826,
|
| 526 |
+
"learning_rate": 2e-05,
|
| 527 |
+
"loss": 0.8056,
|
| 528 |
+
"step": 740
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.06526847097728657,
|
| 532 |
+
"grad_norm": 0.42934441566467285,
|
| 533 |
+
"learning_rate": 2e-05,
|
| 534 |
+
"loss": 0.7531,
|
| 535 |
+
"step": 750
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.06613871725698373,
|
| 539 |
+
"grad_norm": 0.6495123505592346,
|
| 540 |
+
"learning_rate": 2e-05,
|
| 541 |
+
"loss": 0.7565,
|
| 542 |
+
"step": 760
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.06700896353668089,
|
| 546 |
+
"grad_norm": 0.47502997517585754,
|
| 547 |
+
"learning_rate": 2e-05,
|
| 548 |
+
"loss": 0.7943,
|
| 549 |
+
"step": 770
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.06787920981637803,
|
| 553 |
+
"grad_norm": 0.44012171030044556,
|
| 554 |
+
"learning_rate": 2e-05,
|
| 555 |
+
"loss": 0.7512,
|
| 556 |
+
"step": 780
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.06874945609607519,
|
| 560 |
+
"grad_norm": 0.4645586907863617,
|
| 561 |
+
"learning_rate": 2e-05,
|
| 562 |
+
"loss": 0.8388,
|
| 563 |
+
"step": 790
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.06961970237577235,
|
| 567 |
+
"grad_norm": 0.4409954249858856,
|
| 568 |
+
"learning_rate": 2e-05,
|
| 569 |
+
"loss": 0.7789,
|
| 570 |
+
"step": 800
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.0704899486554695,
|
| 574 |
+
"grad_norm": 0.4368588924407959,
|
| 575 |
+
"learning_rate": 2e-05,
|
| 576 |
+
"loss": 0.8082,
|
| 577 |
+
"step": 810
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.07136019493516665,
|
| 581 |
+
"grad_norm": 0.44530150294303894,
|
| 582 |
+
"learning_rate": 2e-05,
|
| 583 |
+
"loss": 0.8205,
|
| 584 |
+
"step": 820
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.0722304412148638,
|
| 588 |
+
"grad_norm": 0.4685135781764984,
|
| 589 |
+
"learning_rate": 2e-05,
|
| 590 |
+
"loss": 0.8119,
|
| 591 |
+
"step": 830
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.07310068749456096,
|
| 595 |
+
"grad_norm": 0.4285910725593567,
|
| 596 |
+
"learning_rate": 2e-05,
|
| 597 |
+
"loss": 0.7817,
|
| 598 |
+
"step": 840
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.07397093377425812,
|
| 602 |
+
"grad_norm": 0.4711061716079712,
|
| 603 |
+
"learning_rate": 2e-05,
|
| 604 |
+
"loss": 0.7861,
|
| 605 |
+
"step": 850
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.07484118005395526,
|
| 609 |
+
"grad_norm": 0.4402053654193878,
|
| 610 |
+
"learning_rate": 2e-05,
|
| 611 |
+
"loss": 0.812,
|
| 612 |
+
"step": 860
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.07571142633365242,
|
| 616 |
+
"grad_norm": 0.5239667892456055,
|
| 617 |
+
"learning_rate": 2e-05,
|
| 618 |
+
"loss": 0.799,
|
| 619 |
+
"step": 870
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.07658167261334958,
|
| 623 |
+
"grad_norm": 0.4384970963001251,
|
| 624 |
+
"learning_rate": 2e-05,
|
| 625 |
+
"loss": 0.8007,
|
| 626 |
+
"step": 880
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.07745191889304673,
|
| 630 |
+
"grad_norm": 0.4427013099193573,
|
| 631 |
+
"learning_rate": 2e-05,
|
| 632 |
+
"loss": 0.7517,
|
| 633 |
+
"step": 890
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.07832216517274389,
|
| 637 |
+
"grad_norm": 0.5057333111763,
|
| 638 |
+
"learning_rate": 2e-05,
|
| 639 |
+
"loss": 0.8007,
|
| 640 |
+
"step": 900
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.07919241145244105,
|
| 644 |
+
"grad_norm": 0.4353077709674835,
|
| 645 |
+
"learning_rate": 2e-05,
|
| 646 |
+
"loss": 0.7765,
|
| 647 |
+
"step": 910
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.08006265773213819,
|
| 651 |
+
"grad_norm": 0.4344167113304138,
|
| 652 |
+
"learning_rate": 2e-05,
|
| 653 |
+
"loss": 0.7613,
|
| 654 |
+
"step": 920
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.08093290401183535,
|
| 658 |
+
"grad_norm": 0.4684934616088867,
|
| 659 |
+
"learning_rate": 2e-05,
|
| 660 |
+
"loss": 0.8119,
|
| 661 |
+
"step": 930
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.0818031502915325,
|
| 665 |
+
"grad_norm": 0.45113563537597656,
|
| 666 |
+
"learning_rate": 2e-05,
|
| 667 |
+
"loss": 0.8423,
|
| 668 |
+
"step": 940
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.08267339657122966,
|
| 672 |
+
"grad_norm": 0.48128587007522583,
|
| 673 |
+
"learning_rate": 2e-05,
|
| 674 |
+
"loss": 0.806,
|
| 675 |
+
"step": 950
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.08354364285092682,
|
| 679 |
+
"grad_norm": 0.5116154551506042,
|
| 680 |
+
"learning_rate": 2e-05,
|
| 681 |
+
"loss": 0.8151,
|
| 682 |
+
"step": 960
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.08441388913062396,
|
| 686 |
+
"grad_norm": 0.46216142177581787,
|
| 687 |
+
"learning_rate": 2e-05,
|
| 688 |
+
"loss": 0.8347,
|
| 689 |
+
"step": 970
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.08528413541032112,
|
| 693 |
+
"grad_norm": 0.4997548758983612,
|
| 694 |
+
"learning_rate": 2e-05,
|
| 695 |
+
"loss": 0.7892,
|
| 696 |
+
"step": 980
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.08615438169001828,
|
| 700 |
+
"grad_norm": 0.45023390650749207,
|
| 701 |
+
"learning_rate": 2e-05,
|
| 702 |
+
"loss": 0.7927,
|
| 703 |
+
"step": 990
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.08702462796971543,
|
| 707 |
+
"grad_norm": 0.40059617161750793,
|
| 708 |
+
"learning_rate": 2e-05,
|
| 709 |
+
"loss": 0.8127,
|
| 710 |
+
"step": 1000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.08789487424941259,
|
| 714 |
+
"grad_norm": 0.491871178150177,
|
| 715 |
+
"learning_rate": 2e-05,
|
| 716 |
+
"loss": 0.8114,
|
| 717 |
+
"step": 1010
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.08876512052910973,
|
| 721 |
+
"grad_norm": 0.4577973484992981,
|
| 722 |
+
"learning_rate": 2e-05,
|
| 723 |
+
"loss": 0.805,
|
| 724 |
+
"step": 1020
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.08963536680880689,
|
| 728 |
+
"grad_norm": 0.45535245537757874,
|
| 729 |
+
"learning_rate": 2e-05,
|
| 730 |
+
"loss": 0.8234,
|
| 731 |
+
"step": 1030
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.09050561308850405,
|
| 735 |
+
"grad_norm": 0.5529155731201172,
|
| 736 |
+
"learning_rate": 2e-05,
|
| 737 |
+
"loss": 0.7799,
|
| 738 |
+
"step": 1040
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.0913758593682012,
|
| 742 |
+
"grad_norm": 0.4578253924846649,
|
| 743 |
+
"learning_rate": 2e-05,
|
| 744 |
+
"loss": 0.7914,
|
| 745 |
+
"step": 1050
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.09224610564789835,
|
| 749 |
+
"grad_norm": 0.4929894804954529,
|
| 750 |
+
"learning_rate": 2e-05,
|
| 751 |
+
"loss": 0.7802,
|
| 752 |
+
"step": 1060
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.09311635192759551,
|
| 756 |
+
"grad_norm": 0.6339548826217651,
|
| 757 |
+
"learning_rate": 2e-05,
|
| 758 |
+
"loss": 0.8247,
|
| 759 |
+
"step": 1070
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.09398659820729266,
|
| 763 |
+
"grad_norm": 0.4438812732696533,
|
| 764 |
+
"learning_rate": 2e-05,
|
| 765 |
+
"loss": 0.8281,
|
| 766 |
+
"step": 1080
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.09485684448698982,
|
| 770 |
+
"grad_norm": 0.4699355959892273,
|
| 771 |
+
"learning_rate": 2e-05,
|
| 772 |
+
"loss": 0.7957,
|
| 773 |
+
"step": 1090
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.09572709076668698,
|
| 777 |
+
"grad_norm": 0.5119197964668274,
|
| 778 |
+
"learning_rate": 2e-05,
|
| 779 |
+
"loss": 0.7972,
|
| 780 |
+
"step": 1100
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.09659733704638412,
|
| 784 |
+
"grad_norm": 0.49015742540359497,
|
| 785 |
+
"learning_rate": 2e-05,
|
| 786 |
+
"loss": 0.7534,
|
| 787 |
+
"step": 1110
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.09746758332608128,
|
| 791 |
+
"grad_norm": 0.4448586702346802,
|
| 792 |
+
"learning_rate": 2e-05,
|
| 793 |
+
"loss": 0.8066,
|
| 794 |
+
"step": 1120
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.09833782960577843,
|
| 798 |
+
"grad_norm": 0.4577223062515259,
|
| 799 |
+
"learning_rate": 2e-05,
|
| 800 |
+
"loss": 0.7799,
|
| 801 |
+
"step": 1130
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.09920807588547559,
|
| 805 |
+
"grad_norm": 0.40512940287590027,
|
| 806 |
+
"learning_rate": 2e-05,
|
| 807 |
+
"loss": 0.7267,
|
| 808 |
+
"step": 1140
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.10007832216517275,
|
| 812 |
+
"grad_norm": 0.6204017996788025,
|
| 813 |
+
"learning_rate": 2e-05,
|
| 814 |
+
"loss": 0.7876,
|
| 815 |
+
"step": 1150
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.1009485684448699,
|
| 819 |
+
"grad_norm": 0.4756101071834564,
|
| 820 |
+
"learning_rate": 2e-05,
|
| 821 |
+
"loss": 0.7766,
|
| 822 |
+
"step": 1160
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.10181881472456705,
|
| 826 |
+
"grad_norm": 0.413986474275589,
|
| 827 |
+
"learning_rate": 2e-05,
|
| 828 |
+
"loss": 0.8251,
|
| 829 |
+
"step": 1170
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.10268906100426421,
|
| 833 |
+
"grad_norm": 0.4388023912906647,
|
| 834 |
+
"learning_rate": 2e-05,
|
| 835 |
+
"loss": 0.8239,
|
| 836 |
+
"step": 1180
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.10355930728396136,
|
| 840 |
+
"grad_norm": 0.7469768524169922,
|
| 841 |
+
"learning_rate": 2e-05,
|
| 842 |
+
"loss": 0.816,
|
| 843 |
+
"step": 1190
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.10442955356365852,
|
| 847 |
+
"grad_norm": 0.44992774724960327,
|
| 848 |
+
"learning_rate": 2e-05,
|
| 849 |
+
"loss": 0.7602,
|
| 850 |
+
"step": 1200
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.10529979984335568,
|
| 854 |
+
"grad_norm": 0.5907509326934814,
|
| 855 |
+
"learning_rate": 2e-05,
|
| 856 |
+
"loss": 0.7828,
|
| 857 |
+
"step": 1210
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.10617004612305282,
|
| 861 |
+
"grad_norm": 0.49899953603744507,
|
| 862 |
+
"learning_rate": 2e-05,
|
| 863 |
+
"loss": 0.7979,
|
| 864 |
+
"step": 1220
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.10704029240274998,
|
| 868 |
+
"grad_norm": 0.5390329957008362,
|
| 869 |
+
"learning_rate": 2e-05,
|
| 870 |
+
"loss": 0.8337,
|
| 871 |
+
"step": 1230
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.10791053868244713,
|
| 875 |
+
"grad_norm": 0.602109968662262,
|
| 876 |
+
"learning_rate": 2e-05,
|
| 877 |
+
"loss": 0.8012,
|
| 878 |
+
"step": 1240
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.10878078496214429,
|
| 882 |
+
"grad_norm": 0.4221755862236023,
|
| 883 |
+
"learning_rate": 2e-05,
|
| 884 |
+
"loss": 0.7642,
|
| 885 |
+
"step": 1250
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.10965103124184145,
|
| 889 |
+
"grad_norm": 0.5170415043830872,
|
| 890 |
+
"learning_rate": 2e-05,
|
| 891 |
+
"loss": 0.7778,
|
| 892 |
+
"step": 1260
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.11052127752153859,
|
| 896 |
+
"grad_norm": 0.41967836022377014,
|
| 897 |
+
"learning_rate": 2e-05,
|
| 898 |
+
"loss": 0.7927,
|
| 899 |
+
"step": 1270
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.11139152380123575,
|
| 903 |
+
"grad_norm": 0.4352816343307495,
|
| 904 |
+
"learning_rate": 2e-05,
|
| 905 |
+
"loss": 0.8553,
|
| 906 |
+
"step": 1280
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.11226177008093291,
|
| 910 |
+
"grad_norm": 0.47659218311309814,
|
| 911 |
+
"learning_rate": 2e-05,
|
| 912 |
+
"loss": 0.8313,
|
| 913 |
+
"step": 1290
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.11313201636063006,
|
| 917 |
+
"grad_norm": 0.423639178276062,
|
| 918 |
+
"learning_rate": 2e-05,
|
| 919 |
+
"loss": 0.7694,
|
| 920 |
+
"step": 1300
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.11400226264032721,
|
| 924 |
+
"grad_norm": 0.5942362546920776,
|
| 925 |
+
"learning_rate": 2e-05,
|
| 926 |
+
"loss": 0.7942,
|
| 927 |
+
"step": 1310
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.11487250892002436,
|
| 931 |
+
"grad_norm": 0.734011173248291,
|
| 932 |
+
"learning_rate": 2e-05,
|
| 933 |
+
"loss": 0.8186,
|
| 934 |
+
"step": 1320
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.11574275519972152,
|
| 938 |
+
"grad_norm": 0.509438157081604,
|
| 939 |
+
"learning_rate": 2e-05,
|
| 940 |
+
"loss": 0.774,
|
| 941 |
+
"step": 1330
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.11661300147941868,
|
| 945 |
+
"grad_norm": 0.4301545023918152,
|
| 946 |
+
"learning_rate": 2e-05,
|
| 947 |
+
"loss": 0.7868,
|
| 948 |
+
"step": 1340
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.11748324775911582,
|
| 952 |
+
"grad_norm": 0.5790858864784241,
|
| 953 |
+
"learning_rate": 2e-05,
|
| 954 |
+
"loss": 0.8409,
|
| 955 |
+
"step": 1350
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.11835349403881298,
|
| 959 |
+
"grad_norm": 0.572526216506958,
|
| 960 |
+
"learning_rate": 2e-05,
|
| 961 |
+
"loss": 0.7629,
|
| 962 |
+
"step": 1360
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.11922374031851014,
|
| 966 |
+
"grad_norm": 0.41416874527931213,
|
| 967 |
+
"learning_rate": 2e-05,
|
| 968 |
+
"loss": 0.7444,
|
| 969 |
+
"step": 1370
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.12009398659820729,
|
| 973 |
+
"grad_norm": 0.42482760548591614,
|
| 974 |
+
"learning_rate": 2e-05,
|
| 975 |
+
"loss": 0.8166,
|
| 976 |
+
"step": 1380
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.12096423287790445,
|
| 980 |
+
"grad_norm": 0.5289201736450195,
|
| 981 |
+
"learning_rate": 2e-05,
|
| 982 |
+
"loss": 0.7905,
|
| 983 |
+
"step": 1390
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.12183447915760161,
|
| 987 |
+
"grad_norm": 0.6437199711799622,
|
| 988 |
+
"learning_rate": 2e-05,
|
| 989 |
+
"loss": 0.8018,
|
| 990 |
+
"step": 1400
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.12270472543729875,
|
| 994 |
+
"grad_norm": 0.4240756630897522,
|
| 995 |
+
"learning_rate": 2e-05,
|
| 996 |
+
"loss": 0.7754,
|
| 997 |
+
"step": 1410
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 0.12357497171699591,
|
| 1001 |
+
"grad_norm": 0.4162019193172455,
|
| 1002 |
+
"learning_rate": 2e-05,
|
| 1003 |
+
"loss": 0.8251,
|
| 1004 |
+
"step": 1420
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 0.12444521799669306,
|
| 1008 |
+
"grad_norm": 0.37912917137145996,
|
| 1009 |
+
"learning_rate": 2e-05,
|
| 1010 |
+
"loss": 0.7593,
|
| 1011 |
+
"step": 1430
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.12531546427639023,
|
| 1015 |
+
"grad_norm": 0.4540870487689972,
|
| 1016 |
+
"learning_rate": 2e-05,
|
| 1017 |
+
"loss": 0.7938,
|
| 1018 |
+
"step": 1440
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.12618571055608738,
|
| 1022 |
+
"grad_norm": 0.47705939412117004,
|
| 1023 |
+
"learning_rate": 2e-05,
|
| 1024 |
+
"loss": 0.7462,
|
| 1025 |
+
"step": 1450
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 0.12705595683578452,
|
| 1029 |
+
"grad_norm": 0.505840003490448,
|
| 1030 |
+
"learning_rate": 2e-05,
|
| 1031 |
+
"loss": 0.8048,
|
| 1032 |
+
"step": 1460
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 0.12792620311548167,
|
| 1036 |
+
"grad_norm": 0.4361368715763092,
|
| 1037 |
+
"learning_rate": 2e-05,
|
| 1038 |
+
"loss": 0.7541,
|
| 1039 |
+
"step": 1470
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 0.12879644939517884,
|
| 1043 |
+
"grad_norm": 0.4416942298412323,
|
| 1044 |
+
"learning_rate": 2e-05,
|
| 1045 |
+
"loss": 0.7644,
|
| 1046 |
+
"step": 1480
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 0.129666695674876,
|
| 1050 |
+
"grad_norm": 0.4668676555156708,
|
| 1051 |
+
"learning_rate": 2e-05,
|
| 1052 |
+
"loss": 0.7819,
|
| 1053 |
+
"step": 1490
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.13053694195457313,
|
| 1057 |
+
"grad_norm": 0.5167171955108643,
|
| 1058 |
+
"learning_rate": 2e-05,
|
| 1059 |
+
"loss": 0.7733,
|
| 1060 |
+
"step": 1500
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 0.1314071882342703,
|
| 1064 |
+
"grad_norm": 0.463228315114975,
|
| 1065 |
+
"learning_rate": 2e-05,
|
| 1066 |
+
"loss": 0.7875,
|
| 1067 |
+
"step": 1510
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 0.13227743451396745,
|
| 1071 |
+
"grad_norm": 0.5149139165878296,
|
| 1072 |
+
"learning_rate": 2e-05,
|
| 1073 |
+
"loss": 0.767,
|
| 1074 |
+
"step": 1520
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.1331476807936646,
|
| 1078 |
+
"grad_norm": 0.5566201210021973,
|
| 1079 |
+
"learning_rate": 2e-05,
|
| 1080 |
+
"loss": 0.7724,
|
| 1081 |
+
"step": 1530
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.13401792707336177,
|
| 1085 |
+
"grad_norm": 0.46756866574287415,
|
| 1086 |
+
"learning_rate": 2e-05,
|
| 1087 |
+
"loss": 0.7582,
|
| 1088 |
+
"step": 1540
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.13488817335305892,
|
| 1092 |
+
"grad_norm": 0.5017741322517395,
|
| 1093 |
+
"learning_rate": 2e-05,
|
| 1094 |
+
"loss": 0.7412,
|
| 1095 |
+
"step": 1550
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.13575841963275606,
|
| 1099 |
+
"grad_norm": 0.47724220156669617,
|
| 1100 |
+
"learning_rate": 2e-05,
|
| 1101 |
+
"loss": 0.7497,
|
| 1102 |
+
"step": 1560
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.13662866591245323,
|
| 1106 |
+
"grad_norm": 0.43308478593826294,
|
| 1107 |
+
"learning_rate": 2e-05,
|
| 1108 |
+
"loss": 0.7917,
|
| 1109 |
+
"step": 1570
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.13749891219215038,
|
| 1113 |
+
"grad_norm": 0.4760570526123047,
|
| 1114 |
+
"learning_rate": 2e-05,
|
| 1115 |
+
"loss": 0.772,
|
| 1116 |
+
"step": 1580
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.13836915847184753,
|
| 1120 |
+
"grad_norm": 0.5164790749549866,
|
| 1121 |
+
"learning_rate": 2e-05,
|
| 1122 |
+
"loss": 0.7828,
|
| 1123 |
+
"step": 1590
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.1392394047515447,
|
| 1127 |
+
"grad_norm": 0.42711082100868225,
|
| 1128 |
+
"learning_rate": 2e-05,
|
| 1129 |
+
"loss": 0.7824,
|
| 1130 |
+
"step": 1600
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.14010965103124184,
|
| 1134 |
+
"grad_norm": 0.4353615343570709,
|
| 1135 |
+
"learning_rate": 2e-05,
|
| 1136 |
+
"loss": 0.7785,
|
| 1137 |
+
"step": 1610
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.140979897310939,
|
| 1141 |
+
"grad_norm": 0.5650473237037659,
|
| 1142 |
+
"learning_rate": 2e-05,
|
| 1143 |
+
"loss": 0.7868,
|
| 1144 |
+
"step": 1620
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.14185014359063616,
|
| 1148 |
+
"grad_norm": 0.42322027683258057,
|
| 1149 |
+
"learning_rate": 2e-05,
|
| 1150 |
+
"loss": 0.7754,
|
| 1151 |
+
"step": 1630
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.1427203898703333,
|
| 1155 |
+
"grad_norm": 0.444169819355011,
|
| 1156 |
+
"learning_rate": 2e-05,
|
| 1157 |
+
"loss": 0.7702,
|
| 1158 |
+
"step": 1640
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 0.14359063615003045,
|
| 1162 |
+
"grad_norm": 0.4093152582645416,
|
| 1163 |
+
"learning_rate": 2e-05,
|
| 1164 |
+
"loss": 0.7351,
|
| 1165 |
+
"step": 1650
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.1444608824297276,
|
| 1169 |
+
"grad_norm": 0.5174054503440857,
|
| 1170 |
+
"learning_rate": 2e-05,
|
| 1171 |
+
"loss": 0.7561,
|
| 1172 |
+
"step": 1660
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.14533112870942477,
|
| 1176 |
+
"grad_norm": 0.505251944065094,
|
| 1177 |
+
"learning_rate": 2e-05,
|
| 1178 |
+
"loss": 0.7739,
|
| 1179 |
+
"step": 1670
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.14620137498912192,
|
| 1183 |
+
"grad_norm": 0.5114858746528625,
|
| 1184 |
+
"learning_rate": 2e-05,
|
| 1185 |
+
"loss": 0.7783,
|
| 1186 |
+
"step": 1680
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.14707162126881906,
|
| 1190 |
+
"grad_norm": 0.46383386850357056,
|
| 1191 |
+
"learning_rate": 2e-05,
|
| 1192 |
+
"loss": 0.7514,
|
| 1193 |
+
"step": 1690
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 0.14794186754851624,
|
| 1197 |
+
"grad_norm": 0.4825400114059448,
|
| 1198 |
+
"learning_rate": 2e-05,
|
| 1199 |
+
"loss": 0.7423,
|
| 1200 |
+
"step": 1700
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 0.14881211382821338,
|
| 1204 |
+
"grad_norm": 0.4293632507324219,
|
| 1205 |
+
"learning_rate": 2e-05,
|
| 1206 |
+
"loss": 0.7864,
|
| 1207 |
+
"step": 1710
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 0.14968236010791053,
|
| 1211 |
+
"grad_norm": 0.4266756474971771,
|
| 1212 |
+
"learning_rate": 2e-05,
|
| 1213 |
+
"loss": 0.7831,
|
| 1214 |
+
"step": 1720
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 0.1505526063876077,
|
| 1218 |
+
"grad_norm": 0.4431057274341583,
|
| 1219 |
+
"learning_rate": 2e-05,
|
| 1220 |
+
"loss": 0.8235,
|
| 1221 |
+
"step": 1730
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 0.15142285266730485,
|
| 1225 |
+
"grad_norm": 0.4605584442615509,
|
| 1226 |
+
"learning_rate": 2e-05,
|
| 1227 |
+
"loss": 0.7799,
|
| 1228 |
+
"step": 1740
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 0.152293098947002,
|
| 1232 |
+
"grad_norm": 0.4502711892127991,
|
| 1233 |
+
"learning_rate": 2e-05,
|
| 1234 |
+
"loss": 0.8347,
|
| 1235 |
+
"step": 1750
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 0.15316334522669917,
|
| 1239 |
+
"grad_norm": 0.4378204643726349,
|
| 1240 |
+
"learning_rate": 2e-05,
|
| 1241 |
+
"loss": 0.7418,
|
| 1242 |
+
"step": 1760
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 0.1540335915063963,
|
| 1246 |
+
"grad_norm": 0.4948919415473938,
|
| 1247 |
+
"learning_rate": 2e-05,
|
| 1248 |
+
"loss": 0.7236,
|
| 1249 |
+
"step": 1770
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 0.15490383778609346,
|
| 1253 |
+
"grad_norm": 0.554040789604187,
|
| 1254 |
+
"learning_rate": 2e-05,
|
| 1255 |
+
"loss": 0.7495,
|
| 1256 |
+
"step": 1780
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 0.15577408406579063,
|
| 1260 |
+
"grad_norm": 0.4786621034145355,
|
| 1261 |
+
"learning_rate": 2e-05,
|
| 1262 |
+
"loss": 0.7711,
|
| 1263 |
+
"step": 1790
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.15664433034548778,
|
| 1267 |
+
"grad_norm": 1.7628140449523926,
|
| 1268 |
+
"learning_rate": 2e-05,
|
| 1269 |
+
"loss": 0.8155,
|
| 1270 |
+
"step": 1800
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 0.15751457662518492,
|
| 1274 |
+
"grad_norm": 0.6795057058334351,
|
| 1275 |
+
"learning_rate": 2e-05,
|
| 1276 |
+
"loss": 0.7575,
|
| 1277 |
+
"step": 1810
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 0.1583848229048821,
|
| 1281 |
+
"grad_norm": 0.4630829989910126,
|
| 1282 |
+
"learning_rate": 2e-05,
|
| 1283 |
+
"loss": 0.7953,
|
| 1284 |
+
"step": 1820
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 0.15925506918457924,
|
| 1288 |
+
"grad_norm": 0.49706682562828064,
|
| 1289 |
+
"learning_rate": 2e-05,
|
| 1290 |
+
"loss": 0.717,
|
| 1291 |
+
"step": 1830
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.16012531546427639,
|
| 1295 |
+
"grad_norm": 1.4661074876785278,
|
| 1296 |
+
"learning_rate": 2e-05,
|
| 1297 |
+
"loss": 0.7729,
|
| 1298 |
+
"step": 1840
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.16099556174397353,
|
| 1302 |
+
"grad_norm": 0.512326180934906,
|
| 1303 |
+
"learning_rate": 2e-05,
|
| 1304 |
+
"loss": 0.7295,
|
| 1305 |
+
"step": 1850
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.1618658080236707,
|
| 1309 |
+
"grad_norm": 0.4158364534378052,
|
| 1310 |
+
"learning_rate": 2e-05,
|
| 1311 |
+
"loss": 0.8028,
|
| 1312 |
+
"step": 1860
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 0.16273605430336785,
|
| 1316 |
+
"grad_norm": 0.48909589648246765,
|
| 1317 |
+
"learning_rate": 2e-05,
|
| 1318 |
+
"loss": 0.7681,
|
| 1319 |
+
"step": 1870
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 0.163606300583065,
|
| 1323 |
+
"grad_norm": 0.46397605538368225,
|
| 1324 |
+
"learning_rate": 2e-05,
|
| 1325 |
+
"loss": 0.8951,
|
| 1326 |
+
"step": 1880
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 0.16447654686276217,
|
| 1330 |
+
"grad_norm": 0.4484255313873291,
|
| 1331 |
+
"learning_rate": 2e-05,
|
| 1332 |
+
"loss": 0.7216,
|
| 1333 |
+
"step": 1890
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 0.16534679314245931,
|
| 1337 |
+
"grad_norm": 0.40970051288604736,
|
| 1338 |
+
"learning_rate": 2e-05,
|
| 1339 |
+
"loss": 0.7683,
|
| 1340 |
+
"step": 1900
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 0.16621703942215646,
|
| 1344 |
+
"grad_norm": 0.41634735465049744,
|
| 1345 |
+
"learning_rate": 2e-05,
|
| 1346 |
+
"loss": 0.7183,
|
| 1347 |
+
"step": 1910
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 0.16708728570185363,
|
| 1351 |
+
"grad_norm": 0.4962814748287201,
|
| 1352 |
+
"learning_rate": 2e-05,
|
| 1353 |
+
"loss": 0.7327,
|
| 1354 |
+
"step": 1920
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 0.16795753198155078,
|
| 1358 |
+
"grad_norm": 0.5092255473136902,
|
| 1359 |
+
"learning_rate": 2e-05,
|
| 1360 |
+
"loss": 0.7487,
|
| 1361 |
+
"step": 1930
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 0.16882777826124792,
|
| 1365 |
+
"grad_norm": 0.4674493670463562,
|
| 1366 |
+
"learning_rate": 2e-05,
|
| 1367 |
+
"loss": 0.7486,
|
| 1368 |
+
"step": 1940
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 0.1696980245409451,
|
| 1372 |
+
"grad_norm": 0.4231005609035492,
|
| 1373 |
+
"learning_rate": 2e-05,
|
| 1374 |
+
"loss": 0.7715,
|
| 1375 |
+
"step": 1950
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 0.17056827082064224,
|
| 1379 |
+
"grad_norm": 0.44939273595809937,
|
| 1380 |
+
"learning_rate": 2e-05,
|
| 1381 |
+
"loss": 0.7612,
|
| 1382 |
+
"step": 1960
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 0.1714385171003394,
|
| 1386 |
+
"grad_norm": 0.8990416526794434,
|
| 1387 |
+
"learning_rate": 2e-05,
|
| 1388 |
+
"loss": 0.7474,
|
| 1389 |
+
"step": 1970
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.17230876338003656,
|
| 1393 |
+
"grad_norm": 0.46539953351020813,
|
| 1394 |
+
"learning_rate": 2e-05,
|
| 1395 |
+
"loss": 0.736,
|
| 1396 |
+
"step": 1980
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 0.1731790096597337,
|
| 1400 |
+
"grad_norm": 0.4826977252960205,
|
| 1401 |
+
"learning_rate": 2e-05,
|
| 1402 |
+
"loss": 0.7341,
|
| 1403 |
+
"step": 1990
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 0.17404925593943085,
|
| 1407 |
+
"grad_norm": 0.4497602880001068,
|
| 1408 |
+
"learning_rate": 2e-05,
|
| 1409 |
+
"loss": 0.7978,
|
| 1410 |
+
"step": 2000
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 0.17491950221912803,
|
| 1414 |
+
"grad_norm": 0.48287254571914673,
|
| 1415 |
+
"learning_rate": 2e-05,
|
| 1416 |
+
"loss": 0.7241,
|
| 1417 |
+
"step": 2010
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 0.17578974849882517,
|
| 1421 |
+
"grad_norm": 0.44837716221809387,
|
| 1422 |
+
"learning_rate": 2e-05,
|
| 1423 |
+
"loss": 0.807,
|
| 1424 |
+
"step": 2020
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 0.17665999477852232,
|
| 1428 |
+
"grad_norm": 0.45343154668807983,
|
| 1429 |
+
"learning_rate": 2e-05,
|
| 1430 |
+
"loss": 0.7602,
|
| 1431 |
+
"step": 2030
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 0.17753024105821946,
|
| 1435 |
+
"grad_norm": 0.5054377913475037,
|
| 1436 |
+
"learning_rate": 2e-05,
|
| 1437 |
+
"loss": 0.7711,
|
| 1438 |
+
"step": 2040
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 0.17840048733791664,
|
| 1442 |
+
"grad_norm": 0.45880326628685,
|
| 1443 |
+
"learning_rate": 2e-05,
|
| 1444 |
+
"loss": 0.8296,
|
| 1445 |
+
"step": 2050
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 0.17927073361761378,
|
| 1449 |
+
"grad_norm": 0.7572662234306335,
|
| 1450 |
+
"learning_rate": 2e-05,
|
| 1451 |
+
"loss": 0.7473,
|
| 1452 |
+
"step": 2060
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 0.18014097989731093,
|
| 1456 |
+
"grad_norm": 0.39630433917045593,
|
| 1457 |
+
"learning_rate": 2e-05,
|
| 1458 |
+
"loss": 0.734,
|
| 1459 |
+
"step": 2070
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 0.1810112261770081,
|
| 1463 |
+
"grad_norm": 0.42546096444129944,
|
| 1464 |
+
"learning_rate": 2e-05,
|
| 1465 |
+
"loss": 0.8011,
|
| 1466 |
+
"step": 2080
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 0.18188147245670525,
|
| 1470 |
+
"grad_norm": 0.4565868675708771,
|
| 1471 |
+
"learning_rate": 2e-05,
|
| 1472 |
+
"loss": 0.7203,
|
| 1473 |
+
"step": 2090
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 0.1827517187364024,
|
| 1477 |
+
"grad_norm": 0.4691726863384247,
|
| 1478 |
+
"learning_rate": 2e-05,
|
| 1479 |
+
"loss": 0.7448,
|
| 1480 |
+
"step": 2100
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 0.18362196501609956,
|
| 1484 |
+
"grad_norm": 0.5789287686347961,
|
| 1485 |
+
"learning_rate": 2e-05,
|
| 1486 |
+
"loss": 0.7678,
|
| 1487 |
+
"step": 2110
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 0.1844922112957967,
|
| 1491 |
+
"grad_norm": 0.4530183672904968,
|
| 1492 |
+
"learning_rate": 2e-05,
|
| 1493 |
+
"loss": 0.7345,
|
| 1494 |
+
"step": 2120
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 0.18536245757549386,
|
| 1498 |
+
"grad_norm": 0.45162123441696167,
|
| 1499 |
+
"learning_rate": 2e-05,
|
| 1500 |
+
"loss": 0.7477,
|
| 1501 |
+
"step": 2130
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 0.18623270385519103,
|
| 1505 |
+
"grad_norm": 0.45647943019866943,
|
| 1506 |
+
"learning_rate": 2e-05,
|
| 1507 |
+
"loss": 0.7518,
|
| 1508 |
+
"step": 2140
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 0.18710295013488817,
|
| 1512 |
+
"grad_norm": 0.5056896209716797,
|
| 1513 |
+
"learning_rate": 2e-05,
|
| 1514 |
+
"loss": 0.7622,
|
| 1515 |
+
"step": 2150
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 0.18797319641458532,
|
| 1519 |
+
"grad_norm": 0.4555186331272125,
|
| 1520 |
+
"learning_rate": 2e-05,
|
| 1521 |
+
"loss": 0.7627,
|
| 1522 |
+
"step": 2160
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 0.1888434426942825,
|
| 1526 |
+
"grad_norm": 0.4564407169818878,
|
| 1527 |
+
"learning_rate": 2e-05,
|
| 1528 |
+
"loss": 0.8085,
|
| 1529 |
+
"step": 2170
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 0.18971368897397964,
|
| 1533 |
+
"grad_norm": 0.4697491228580475,
|
| 1534 |
+
"learning_rate": 2e-05,
|
| 1535 |
+
"loss": 0.779,
|
| 1536 |
+
"step": 2180
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 0.19058393525367678,
|
| 1540 |
+
"grad_norm": 0.6114519834518433,
|
| 1541 |
+
"learning_rate": 2e-05,
|
| 1542 |
+
"loss": 0.7408,
|
| 1543 |
+
"step": 2190
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 0.19145418153337396,
|
| 1547 |
+
"grad_norm": 0.44777148962020874,
|
| 1548 |
+
"learning_rate": 2e-05,
|
| 1549 |
+
"loss": 0.7461,
|
| 1550 |
+
"step": 2200
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 0.1923244278130711,
|
| 1554 |
+
"grad_norm": 0.48813092708587646,
|
| 1555 |
+
"learning_rate": 2e-05,
|
| 1556 |
+
"loss": 0.7867,
|
| 1557 |
+
"step": 2210
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 0.19319467409276825,
|
| 1561 |
+
"grad_norm": 0.4505617916584015,
|
| 1562 |
+
"learning_rate": 2e-05,
|
| 1563 |
+
"loss": 0.7527,
|
| 1564 |
+
"step": 2220
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 0.19406492037246542,
|
| 1568 |
+
"grad_norm": 0.46313464641571045,
|
| 1569 |
+
"learning_rate": 2e-05,
|
| 1570 |
+
"loss": 0.8453,
|
| 1571 |
+
"step": 2230
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 0.19493516665216257,
|
| 1575 |
+
"grad_norm": 0.46306613087654114,
|
| 1576 |
+
"learning_rate": 2e-05,
|
| 1577 |
+
"loss": 0.7907,
|
| 1578 |
+
"step": 2240
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 0.1958054129318597,
|
| 1582 |
+
"grad_norm": 0.513311505317688,
|
| 1583 |
+
"learning_rate": 2e-05,
|
| 1584 |
+
"loss": 0.7062,
|
| 1585 |
+
"step": 2250
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 0.19667565921155686,
|
| 1589 |
+
"grad_norm": 0.4533046782016754,
|
| 1590 |
+
"learning_rate": 2e-05,
|
| 1591 |
+
"loss": 0.7926,
|
| 1592 |
+
"step": 2260
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 0.19754590549125403,
|
| 1596 |
+
"grad_norm": 0.5268926620483398,
|
| 1597 |
+
"learning_rate": 2e-05,
|
| 1598 |
+
"loss": 0.7547,
|
| 1599 |
+
"step": 2270
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 0.19841615177095118,
|
| 1603 |
+
"grad_norm": 0.7747378349304199,
|
| 1604 |
+
"learning_rate": 2e-05,
|
| 1605 |
+
"loss": 0.7199,
|
| 1606 |
+
"step": 2280
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 0.19928639805064832,
|
| 1610 |
+
"grad_norm": 0.49979445338249207,
|
| 1611 |
+
"learning_rate": 2e-05,
|
| 1612 |
+
"loss": 0.7293,
|
| 1613 |
+
"step": 2290
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 0.2001566443303455,
|
| 1617 |
+
"grad_norm": 0.46914732456207275,
|
| 1618 |
+
"learning_rate": 2e-05,
|
| 1619 |
+
"loss": 0.7152,
|
| 1620 |
+
"step": 2300
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 0.20102689061004264,
|
| 1624 |
+
"grad_norm": 0.616715133190155,
|
| 1625 |
+
"learning_rate": 2e-05,
|
| 1626 |
+
"loss": 0.7269,
|
| 1627 |
+
"step": 2310
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 0.2018971368897398,
|
| 1631 |
+
"grad_norm": 0.42736414074897766,
|
| 1632 |
+
"learning_rate": 2e-05,
|
| 1633 |
+
"loss": 0.8516,
|
| 1634 |
+
"step": 2320
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 0.20276738316943696,
|
| 1638 |
+
"grad_norm": 0.47521495819091797,
|
| 1639 |
+
"learning_rate": 2e-05,
|
| 1640 |
+
"loss": 0.7388,
|
| 1641 |
+
"step": 2330
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 0.2036376294491341,
|
| 1645 |
+
"grad_norm": 0.5417228937149048,
|
| 1646 |
+
"learning_rate": 2e-05,
|
| 1647 |
+
"loss": 0.7324,
|
| 1648 |
+
"step": 2340
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 0.20450787572883125,
|
| 1652 |
+
"grad_norm": 0.5534002780914307,
|
| 1653 |
+
"learning_rate": 2e-05,
|
| 1654 |
+
"loss": 0.7222,
|
| 1655 |
+
"step": 2350
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 0.20537812200852842,
|
| 1659 |
+
"grad_norm": 0.4372415840625763,
|
| 1660 |
+
"learning_rate": 2e-05,
|
| 1661 |
+
"loss": 0.7704,
|
| 1662 |
+
"step": 2360
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 0.20624836828822557,
|
| 1666 |
+
"grad_norm": 0.5380441546440125,
|
| 1667 |
+
"learning_rate": 2e-05,
|
| 1668 |
+
"loss": 0.7455,
|
| 1669 |
+
"step": 2370
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 0.20711861456792272,
|
| 1673 |
+
"grad_norm": 0.49372661113739014,
|
| 1674 |
+
"learning_rate": 2e-05,
|
| 1675 |
+
"loss": 0.767,
|
| 1676 |
+
"step": 2380
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 0.2079888608476199,
|
| 1680 |
+
"grad_norm": 0.5214691162109375,
|
| 1681 |
+
"learning_rate": 2e-05,
|
| 1682 |
+
"loss": 0.7388,
|
| 1683 |
+
"step": 2390
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 0.20885910712731703,
|
| 1687 |
+
"grad_norm": 0.4492393434047699,
|
| 1688 |
+
"learning_rate": 2e-05,
|
| 1689 |
+
"loss": 0.7398,
|
| 1690 |
+
"step": 2400
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 0.20972935340701418,
|
| 1694 |
+
"grad_norm": 0.49798527359962463,
|
| 1695 |
+
"learning_rate": 2e-05,
|
| 1696 |
+
"loss": 0.8195,
|
| 1697 |
+
"step": 2410
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 0.21059959968671135,
|
| 1701 |
+
"grad_norm": 0.49228090047836304,
|
| 1702 |
+
"learning_rate": 2e-05,
|
| 1703 |
+
"loss": 0.782,
|
| 1704 |
+
"step": 2420
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 0.2114698459664085,
|
| 1708 |
+
"grad_norm": 0.6478143930435181,
|
| 1709 |
+
"learning_rate": 2e-05,
|
| 1710 |
+
"loss": 0.7294,
|
| 1711 |
+
"step": 2430
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 0.21234009224610564,
|
| 1715 |
+
"grad_norm": 0.4686027765274048,
|
| 1716 |
+
"learning_rate": 2e-05,
|
| 1717 |
+
"loss": 0.7205,
|
| 1718 |
+
"step": 2440
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 0.2132103385258028,
|
| 1722 |
+
"grad_norm": 0.4516022205352783,
|
| 1723 |
+
"learning_rate": 2e-05,
|
| 1724 |
+
"loss": 0.7314,
|
| 1725 |
+
"step": 2450
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 0.21408058480549996,
|
| 1729 |
+
"grad_norm": 0.4500731825828552,
|
| 1730 |
+
"learning_rate": 2e-05,
|
| 1731 |
+
"loss": 0.7037,
|
| 1732 |
+
"step": 2460
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 0.2149508310851971,
|
| 1736 |
+
"grad_norm": 0.5103179812431335,
|
| 1737 |
+
"learning_rate": 2e-05,
|
| 1738 |
+
"loss": 0.7656,
|
| 1739 |
+
"step": 2470
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 0.21582107736489425,
|
| 1743 |
+
"grad_norm": 0.4888087809085846,
|
| 1744 |
+
"learning_rate": 2e-05,
|
| 1745 |
+
"loss": 0.7471,
|
| 1746 |
+
"step": 2480
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 0.21669132364459143,
|
| 1750 |
+
"grad_norm": 0.5165966749191284,
|
| 1751 |
+
"learning_rate": 2e-05,
|
| 1752 |
+
"loss": 0.7738,
|
| 1753 |
+
"step": 2490
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 0.21756156992428857,
|
| 1757 |
+
"grad_norm": 0.47505345940589905,
|
| 1758 |
+
"learning_rate": 2e-05,
|
| 1759 |
+
"loss": 0.7452,
|
| 1760 |
+
"step": 2500
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 0.21843181620398572,
|
| 1764 |
+
"grad_norm": 0.509752631187439,
|
| 1765 |
+
"learning_rate": 2e-05,
|
| 1766 |
+
"loss": 0.7788,
|
| 1767 |
+
"step": 2510
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 0.2193020624836829,
|
| 1771 |
+
"grad_norm": 0.39926689863204956,
|
| 1772 |
+
"learning_rate": 2e-05,
|
| 1773 |
+
"loss": 0.7611,
|
| 1774 |
+
"step": 2520
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 0.22017230876338004,
|
| 1778 |
+
"grad_norm": 0.5184482932090759,
|
| 1779 |
+
"learning_rate": 2e-05,
|
| 1780 |
+
"loss": 0.7346,
|
| 1781 |
+
"step": 2530
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 0.22104255504307718,
|
| 1785 |
+
"grad_norm": 0.45654305815696716,
|
| 1786 |
+
"learning_rate": 2e-05,
|
| 1787 |
+
"loss": 0.7424,
|
| 1788 |
+
"step": 2540
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 0.22191280132277436,
|
| 1792 |
+
"grad_norm": 0.4474726617336273,
|
| 1793 |
+
"learning_rate": 1.997261400182901e-05,
|
| 1794 |
+
"loss": 0.7929,
|
| 1795 |
+
"step": 2550
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 0.2227830476024715,
|
| 1799 |
+
"grad_norm": 0.8602055311203003,
|
| 1800 |
+
"learning_rate": 1.9805800746810423e-05,
|
| 1801 |
+
"loss": 0.7735,
|
| 1802 |
+
"step": 2560
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 0.22365329388216865,
|
| 1806 |
+
"grad_norm": 0.47405391931533813,
|
| 1807 |
+
"learning_rate": 1.9489934220110274e-05,
|
| 1808 |
+
"loss": 0.7434,
|
| 1809 |
+
"step": 2570
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 0.22452354016186582,
|
| 1813 |
+
"grad_norm": 0.4841902256011963,
|
| 1814 |
+
"learning_rate": 1.9029840364820392e-05,
|
| 1815 |
+
"loss": 0.6999,
|
| 1816 |
+
"step": 2580
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 0.22539378644156297,
|
| 1820 |
+
"grad_norm": 0.46785056591033936,
|
| 1821 |
+
"learning_rate": 1.8432548690479908e-05,
|
| 1822 |
+
"loss": 0.7438,
|
| 1823 |
+
"step": 2590
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 0.2262640327212601,
|
| 1827 |
+
"grad_norm": 0.6724407076835632,
|
| 1828 |
+
"learning_rate": 1.7707184873239772e-05,
|
| 1829 |
+
"loss": 0.7853,
|
| 1830 |
+
"step": 2600
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 0.22713427900095728,
|
| 1834 |
+
"grad_norm": 0.5495203137397766,
|
| 1835 |
+
"learning_rate": 1.6864831329902565e-05,
|
| 1836 |
+
"loss": 0.759,
|
| 1837 |
+
"step": 2610
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 0.22800452528065443,
|
| 1841 |
+
"grad_norm": 0.4913140535354614,
|
| 1842 |
+
"learning_rate": 1.591835789604667e-05,
|
| 1843 |
+
"loss": 0.7196,
|
| 1844 |
+
"step": 2620
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 0.22887477156035158,
|
| 1848 |
+
"grad_norm": 0.4577329754829407,
|
| 1849 |
+
"learning_rate": 1.4882225195206459e-05,
|
| 1850 |
+
"loss": 0.7285,
|
| 1851 |
+
"step": 2630
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 0.22974501784004872,
|
| 1855 |
+
"grad_norm": 0.4680711030960083,
|
| 1856 |
+
"learning_rate": 1.3772263703317695e-05,
|
| 1857 |
+
"loss": 0.7005,
|
| 1858 |
+
"step": 2640
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 0.2306152641197459,
|
| 1862 |
+
"grad_norm": 0.4433872401714325,
|
| 1863 |
+
"learning_rate": 1.2605431883975547e-05,
|
| 1864 |
+
"loss": 0.7329,
|
| 1865 |
+
"step": 2650
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 0.23148551039944304,
|
| 1869 |
+
"grad_norm": 0.4885198473930359,
|
| 1870 |
+
"learning_rate": 1.1399557089817574e-05,
|
| 1871 |
+
"loss": 0.6914,
|
| 1872 |
+
"step": 2660
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 0.23235575667914019,
|
| 1876 |
+
"grad_norm": 0.6006641387939453,
|
| 1877 |
+
"learning_rate": 1.0173063188650463e-05,
|
| 1878 |
+
"loss": 0.7477,
|
| 1879 |
+
"step": 2670
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 0.23322600295883736,
|
| 1883 |
+
"grad_norm": 0.4173085391521454,
|
| 1884 |
+
"learning_rate": 8.944689075764396e-06,
|
| 1885 |
+
"loss": 0.7411,
|
| 1886 |
+
"step": 2680
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 0.2340962492385345,
|
| 1890 |
+
"grad_norm": 0.494748055934906,
|
| 1891 |
+
"learning_rate": 7.73320237312362e-06,
|
| 1892 |
+
"loss": 0.737,
|
| 1893 |
+
"step": 2690
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 0.23496649551823165,
|
| 1897 |
+
"grad_norm": 0.48495543003082275,
|
| 1898 |
+
"learning_rate": 6.557112689658629e-06,
|
| 1899 |
+
"loss": 0.7999,
|
| 1900 |
+
"step": 2700
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"epoch": 0.23583674179792882,
|
| 1904 |
+
"grad_norm": 0.4789693057537079,
|
| 1905 |
+
"learning_rate": 5.434388823591213e-06,
|
| 1906 |
+
"loss": 0.7811,
|
| 1907 |
+
"step": 2710
|
| 1908 |
+
},
|
| 1909 |
+
{
|
| 1910 |
+
"epoch": 0.23670698807762597,
|
| 1911 |
+
"grad_norm": 0.42050349712371826,
|
| 1912 |
+
"learning_rate": 4.382184227495424e-06,
|
| 1913 |
+
"loss": 0.6815,
|
| 1914 |
+
"step": 2720
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 0.2375772343573231,
|
| 1918 |
+
"grad_norm": 0.5127126574516296,
|
| 1919 |
+
"learning_rate": 3.4165749305560203e-06,
|
| 1920 |
+
"loss": 0.7317,
|
| 1921 |
+
"step": 2730
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 0.2384474806370203,
|
| 1925 |
+
"grad_norm": 0.4152151644229889,
|
| 1926 |
+
"learning_rate": 2.5523139221595556e-06,
|
| 1927 |
+
"loss": 0.7648,
|
| 1928 |
+
"step": 2740
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 0.23931772691671743,
|
| 1932 |
+
"grad_norm": 0.4343687891960144,
|
| 1933 |
+
"learning_rate": 1.8026057494499821e-06,
|
| 1934 |
+
"loss": 0.714,
|
| 1935 |
+
"step": 2750
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 0.24018797319641458,
|
| 1939 |
+
"grad_norm": 0.5041891932487488,
|
| 1940 |
+
"learning_rate": 1.178904772643223e-06,
|
| 1941 |
+
"loss": 0.7488,
|
| 1942 |
+
"step": 2760
|
| 1943 |
+
},
|
| 1944 |
+
{
|
| 1945 |
+
"epoch": 0.24105821947611175,
|
| 1946 |
+
"grad_norm": 0.4714384973049164,
|
| 1947 |
+
"learning_rate": 6.90740160441754e-07,
|
| 1948 |
+
"loss": 0.723,
|
| 1949 |
+
"step": 2770
|
| 1950 |
+
},
|
| 1951 |
+
{
|
| 1952 |
+
"epoch": 0.2419284657558089,
|
| 1953 |
+
"grad_norm": 0.4543507993221283,
|
| 1954 |
+
"learning_rate": 3.45570299343632e-07,
|
| 1955 |
+
"loss": 0.7705,
|
| 1956 |
+
"step": 2780
|
| 1957 |
+
},
|
| 1958 |
+
{
|
| 1959 |
+
"epoch": 0.24279871203550604,
|
| 1960 |
+
"grad_norm": 0.4485136866569519,
|
| 1961 |
+
"learning_rate": 1.486688412425152e-07,
|
| 1962 |
+
"loss": 0.7337,
|
| 1963 |
+
"step": 2790
|
| 1964 |
+
},
|
| 1965 |
+
{
|
| 1966 |
+
"epoch": 0.24340788443129405,
|
| 1967 |
+
"step": 2797,
|
| 1968 |
+
"total_flos": 1.2485883762455871e+19,
|
| 1969 |
+
"train_loss": 0.0675735119030993,
|
| 1970 |
+
"train_runtime": 2890.5564,
|
| 1971 |
+
"train_samples_per_second": 11.612,
|
| 1972 |
+
"train_steps_per_second": 0.968
|
| 1973 |
+
}
|
| 1974 |
+
],
|
| 1975 |
+
"logging_steps": 10,
|
| 1976 |
+
"max_steps": 2797,
|
| 1977 |
+
"num_input_tokens_seen": 0,
|
| 1978 |
+
"num_train_epochs": 1,
|
| 1979 |
+
"save_steps": 2543,
|
| 1980 |
+
"stateful_callbacks": {
|
| 1981 |
+
"TrainerControl": {
|
| 1982 |
+
"args": {
|
| 1983 |
+
"should_epoch_stop": false,
|
| 1984 |
+
"should_evaluate": false,
|
| 1985 |
+
"should_log": false,
|
| 1986 |
+
"should_save": true,
|
| 1987 |
+
"should_training_stop": true
|
| 1988 |
+
},
|
| 1989 |
+
"attributes": {}
|
| 1990 |
+
}
|
| 1991 |
+
},
|
| 1992 |
+
"total_flos": 1.2485883762455871e+19,
|
| 1993 |
+
"train_batch_size": 1,
|
| 1994 |
+
"trial_name": null,
|
| 1995 |
+
"trial_params": null
|
| 1996 |
+
}
|
g1_0_baseline_original_code/250M/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c5698699b1635fbe0f2293b4bdee8f923b3be8898abf444da50990c92b9b50e
|
| 3 |
+
size 9105
|
g1_0_baseline_original_code/250M/training_loss.png
ADDED
|
g1_0_baseline_original_code/250M/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|