Add files using upload-large-folder tool
Browse files- .gitattributes +1 -0
- README.md +61 -0
- added_tokens.json +24 -0
- all_results.json +8 -0
- chat_template.jinja +54 -0
- config.json +78 -0
- generation_config.json +13 -0
- merges.txt +0 -0
- model-00001-of-00006.safetensors +3 -0
- model-00002-of-00006.safetensors +3 -0
- model-00003-of-00006.safetensors +3 -0
- model-00004-of-00006.safetensors +3 -0
- model-00005-of-00006.safetensors +3 -0
- model-00006-of-00006.safetensors +3 -0
- model.safetensors.index.json +587 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +208 -0
- train_results.json +8 -0
- trainer_log.jsonl +81 -0
- trainer_state.json +603 -0
- training_args.bin +3 -0
- training_loss.png +0 -0
- vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: other
|
| 4 |
+
base_model: Qwen/Qwen2.5-Coder-14B-Instruct
|
| 5 |
+
tags:
|
| 6 |
+
- llama-factory
|
| 7 |
+
- full
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: R2EGym-14B-Agent-Coder-Instruct
|
| 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 |
+
# R2EGym-14B-Agent-Coder-Instruct
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-14B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-14B-Instruct) on the r2egym_sft_trajectories dataset.
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 1e-05
|
| 39 |
+
- train_batch_size: 1
|
| 40 |
+
- eval_batch_size: 8
|
| 41 |
+
- seed: 42
|
| 42 |
+
- distributed_type: multi-GPU
|
| 43 |
+
- num_devices: 4
|
| 44 |
+
- gradient_accumulation_steps: 2
|
| 45 |
+
- total_train_batch_size: 8
|
| 46 |
+
- total_eval_batch_size: 32
|
| 47 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 48 |
+
- lr_scheduler_type: cosine
|
| 49 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 50 |
+
- num_epochs: 2.0
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
|
| 55 |
+
|
| 56 |
+
### Framework versions
|
| 57 |
+
|
| 58 |
+
- Transformers 4.57.1
|
| 59 |
+
- Pytorch 2.10.0+cu128
|
| 60 |
+
- Datasets 4.0.0
|
| 61 |
+
- Tokenizers 0.22.2
|
added_tokens.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</tool_call>": 151658,
|
| 3 |
+
"<tool_call>": 151657,
|
| 4 |
+
"<|box_end|>": 151649,
|
| 5 |
+
"<|box_start|>": 151648,
|
| 6 |
+
"<|endoftext|>": 151643,
|
| 7 |
+
"<|file_sep|>": 151664,
|
| 8 |
+
"<|fim_middle|>": 151660,
|
| 9 |
+
"<|fim_pad|>": 151662,
|
| 10 |
+
"<|fim_prefix|>": 151659,
|
| 11 |
+
"<|fim_suffix|>": 151661,
|
| 12 |
+
"<|im_end|>": 151645,
|
| 13 |
+
"<|im_start|>": 151644,
|
| 14 |
+
"<|image_pad|>": 151655,
|
| 15 |
+
"<|object_ref_end|>": 151647,
|
| 16 |
+
"<|object_ref_start|>": 151646,
|
| 17 |
+
"<|quad_end|>": 151651,
|
| 18 |
+
"<|quad_start|>": 151650,
|
| 19 |
+
"<|repo_name|>": 151663,
|
| 20 |
+
"<|video_pad|>": 151656,
|
| 21 |
+
"<|vision_end|>": 151653,
|
| 22 |
+
"<|vision_pad|>": 151654,
|
| 23 |
+
"<|vision_start|>": 151652
|
| 24 |
+
}
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"total_flos": 1.995296975397847e+17,
|
| 4 |
+
"train_loss": 0.15181401895709556,
|
| 5 |
+
"train_runtime": 29257.7471,
|
| 6 |
+
"train_samples_per_second": 0.221,
|
| 7 |
+
"train_steps_per_second": 0.028
|
| 8 |
+
}
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 4 |
+
{{- messages[0]['content'] }}
|
| 5 |
+
{%- else %}
|
| 6 |
+
{{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
|
| 7 |
+
{%- endif %}
|
| 8 |
+
{{- "\n\n# 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>" }}
|
| 9 |
+
{%- for tool in tools %}
|
| 10 |
+
{{- "\n" }}
|
| 11 |
+
{{- tool | tojson }}
|
| 12 |
+
{%- endfor %}
|
| 13 |
+
{{- "\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" }}
|
| 14 |
+
{%- else %}
|
| 15 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 16 |
+
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
|
| 17 |
+
{%- else %}
|
| 18 |
+
{{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
|
| 19 |
+
{%- endif %}
|
| 20 |
+
{%- endif %}
|
| 21 |
+
{%- for message in messages %}
|
| 22 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
|
| 23 |
+
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
| 24 |
+
{%- elif message.role == "assistant" %}
|
| 25 |
+
{{- '<|im_start|>' + message.role }}
|
| 26 |
+
{%- if message.content %}
|
| 27 |
+
{{- '\n' + message.content }}
|
| 28 |
+
{%- endif %}
|
| 29 |
+
{%- for tool_call in message.tool_calls %}
|
| 30 |
+
{%- if tool_call.function is defined %}
|
| 31 |
+
{%- set tool_call = tool_call.function %}
|
| 32 |
+
{%- endif %}
|
| 33 |
+
{{- '\n<tool_call>\n{"name": "' }}
|
| 34 |
+
{{- tool_call.name }}
|
| 35 |
+
{{- '", "arguments": ' }}
|
| 36 |
+
{{- tool_call.arguments | tojson }}
|
| 37 |
+
{{- '}\n</tool_call>' }}
|
| 38 |
+
{%- endfor %}
|
| 39 |
+
{{- '<|im_end|>\n' }}
|
| 40 |
+
{%- elif message.role == "tool" %}
|
| 41 |
+
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
|
| 42 |
+
{{- '<|im_start|>user' }}
|
| 43 |
+
{%- endif %}
|
| 44 |
+
{{- '\n<tool_response>\n' }}
|
| 45 |
+
{{- message.content }}
|
| 46 |
+
{{- '\n</tool_response>' }}
|
| 47 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 48 |
+
{{- '<|im_end|>\n' }}
|
| 49 |
+
{%- endif %}
|
| 50 |
+
{%- endif %}
|
| 51 |
+
{%- endfor %}
|
| 52 |
+
{%- if add_generation_prompt %}
|
| 53 |
+
{{- '<|im_start|>assistant\n' }}
|
| 54 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"dtype": "bfloat16",
|
| 7 |
+
"eos_token_id": 151645,
|
| 8 |
+
"hidden_act": "silu",
|
| 9 |
+
"hidden_size": 5120,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 13824,
|
| 12 |
+
"layer_types": [
|
| 13 |
+
"full_attention",
|
| 14 |
+
"full_attention",
|
| 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 |
+
"full_attention",
|
| 52 |
+
"full_attention",
|
| 53 |
+
"full_attention",
|
| 54 |
+
"full_attention",
|
| 55 |
+
"full_attention",
|
| 56 |
+
"full_attention",
|
| 57 |
+
"full_attention",
|
| 58 |
+
"full_attention",
|
| 59 |
+
"full_attention",
|
| 60 |
+
"full_attention"
|
| 61 |
+
],
|
| 62 |
+
"max_position_embeddings": 32768,
|
| 63 |
+
"max_window_layers": 48,
|
| 64 |
+
"model_type": "qwen2",
|
| 65 |
+
"num_attention_heads": 40,
|
| 66 |
+
"num_hidden_layers": 48,
|
| 67 |
+
"num_key_value_heads": 8,
|
| 68 |
+
"pad_token_id": 151643,
|
| 69 |
+
"rms_norm_eps": 1e-06,
|
| 70 |
+
"rope_scaling": null,
|
| 71 |
+
"rope_theta": 1000000.0,
|
| 72 |
+
"sliding_window": null,
|
| 73 |
+
"tie_word_embeddings": false,
|
| 74 |
+
"transformers_version": "4.57.1",
|
| 75 |
+
"use_cache": false,
|
| 76 |
+
"use_sliding_window": false,
|
| 77 |
+
"vocab_size": 152064
|
| 78 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_sample": true,
|
| 3 |
+
"eos_token_id": [
|
| 4 |
+
151645,
|
| 5 |
+
151643
|
| 6 |
+
],
|
| 7 |
+
"pad_token_id": 151643,
|
| 8 |
+
"repetition_penalty": 1.05,
|
| 9 |
+
"temperature": 0.7,
|
| 10 |
+
"top_k": 20,
|
| 11 |
+
"top_p": 0.8,
|
| 12 |
+
"transformers_version": "4.57.1"
|
| 13 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00006.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:905a33f6f15f23da076b5ef29c36ce134c763e36ff339a831ba289a59629100f
|
| 3 |
+
size 4986211280
|
model-00002-of-00006.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:181bcd9823d7bbec23fad8cb7c6aaa313e0a66e01717ff5993d83a63ac921897
|
| 3 |
+
size 4954847344
|
model-00003-of-00006.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3f594e6cabc4bda2f816ac0fb0808dfeff31c43d2da200514826fcea192cabce
|
| 3 |
+
size 4954847392
|
model-00004-of-00006.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4e849ec037e251fc2c7400f974b1b9d3053f8af1203602d69c9caadf8850d517
|
| 3 |
+
size 4954847392
|
model-00005-of-00006.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:191e5eac2f793be5619df04b1c7fdc250491799fc068a2b929d90b01fb23e92d
|
| 3 |
+
size 4954847392
|
model-00006-of-00006.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:988b966f0b70efd8251b372783d9f4a7bf9f4d9343ba191ebb6c77edb9a0c683
|
| 3 |
+
size 4734533160
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,587 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 840704,
|
| 4 |
+
"total_size": 29540067328
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"lm_head.weight": "model-00006-of-00006.safetensors",
|
| 8 |
+
"model.embed_tokens.weight": "model-00001-of-00006.safetensors",
|
| 9 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
| 10 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
| 11 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
| 12 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
| 13 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
| 19 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
|
| 20 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
| 21 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
| 22 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
| 23 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
| 24 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
| 25 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
| 29 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
|
| 30 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
| 31 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
|
| 32 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
| 33 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 34 |
+
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
| 35 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
| 36 |
+
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
| 37 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 38 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
|
| 39 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
| 40 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
| 41 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
|
| 42 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
| 43 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
|
| 44 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
| 45 |
+
"model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 46 |
+
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
| 47 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
| 48 |
+
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
| 49 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 50 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
|
| 51 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
| 52 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
| 53 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
|
| 54 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
| 55 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
|
| 56 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
| 57 |
+
"model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 58 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
| 59 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
| 60 |
+
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
| 61 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 62 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
|
| 63 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
| 64 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
| 65 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
|
| 66 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
| 67 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
|
| 68 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
| 69 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 70 |
+
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
| 71 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
| 72 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
| 73 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 74 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
|
| 75 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
| 76 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
| 77 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
|
| 78 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
| 79 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
|
| 80 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
| 81 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 82 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
| 83 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
| 84 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
| 85 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 86 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
|
| 87 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
| 88 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
| 89 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
|
| 90 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
| 91 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
|
| 92 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
| 93 |
+
"model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 94 |
+
"model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
| 95 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
| 96 |
+
"model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
| 97 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 98 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
|
| 99 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
| 100 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
| 101 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
|
| 102 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
| 103 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
|
| 104 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
| 105 |
+
"model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 106 |
+
"model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
| 107 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
| 108 |
+
"model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
| 109 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 110 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
|
| 111 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
| 112 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
| 113 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
|
| 114 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
| 115 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
|
| 116 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
| 117 |
+
"model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 118 |
+
"model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
| 119 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
| 120 |
+
"model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
| 121 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 122 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
|
| 123 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
| 124 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
| 125 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
|
| 126 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
| 127 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
|
| 128 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
| 129 |
+
"model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 130 |
+
"model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
| 131 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
| 132 |
+
"model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
| 133 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 134 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
|
| 135 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
| 136 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
| 137 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
|
| 138 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
| 139 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
|
| 140 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
| 141 |
+
"model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 142 |
+
"model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
| 143 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
| 144 |
+
"model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
| 145 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 146 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
|
| 147 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
| 148 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
| 149 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
|
| 150 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
| 151 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
|
| 152 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
| 153 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
| 154 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
| 155 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
| 156 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
| 157 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
| 158 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
|
| 159 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
| 160 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
| 161 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
|
| 162 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
| 163 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
|
| 164 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
| 165 |
+
"model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 166 |
+
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
| 167 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
| 168 |
+
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
| 169 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 170 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
|
| 171 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
| 172 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
| 173 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
|
| 174 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
| 175 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
|
| 176 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
| 177 |
+
"model.layers.21.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 178 |
+
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
| 179 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
| 180 |
+
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
| 181 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 182 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
|
| 183 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
| 184 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
| 185 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
|
| 186 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
| 187 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
|
| 188 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
| 189 |
+
"model.layers.22.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 190 |
+
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
| 191 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
| 192 |
+
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
| 193 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 194 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
|
| 195 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
| 196 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
| 197 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
|
| 198 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
| 199 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
|
| 200 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
| 201 |
+
"model.layers.23.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 202 |
+
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
| 203 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
| 204 |
+
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
| 205 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 206 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
|
| 207 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
| 208 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
| 209 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
|
| 210 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
| 211 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
|
| 212 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
| 213 |
+
"model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 214 |
+
"model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
| 215 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
| 216 |
+
"model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
| 217 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 218 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
|
| 219 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
| 220 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
| 221 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
|
| 222 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
| 223 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
|
| 224 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
| 225 |
+
"model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 226 |
+
"model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
| 227 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
| 228 |
+
"model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
| 229 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 230 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
|
| 231 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
| 232 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
| 233 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
|
| 234 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
| 235 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
|
| 236 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
| 237 |
+
"model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 238 |
+
"model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
| 239 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
| 240 |
+
"model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
| 241 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 242 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
|
| 243 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
| 244 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
| 245 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
|
| 246 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
| 247 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
|
| 248 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
| 249 |
+
"model.layers.27.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 250 |
+
"model.layers.27.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
| 251 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
| 252 |
+
"model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
| 253 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 254 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
|
| 255 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
| 256 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
| 257 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
|
| 258 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
| 259 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
|
| 260 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
| 261 |
+
"model.layers.28.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 262 |
+
"model.layers.28.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
| 263 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
| 264 |
+
"model.layers.28.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
| 265 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 266 |
+
"model.layers.28.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
|
| 267 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
| 268 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
| 269 |
+
"model.layers.28.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
|
| 270 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
| 271 |
+
"model.layers.28.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
|
| 272 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
| 273 |
+
"model.layers.29.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 274 |
+
"model.layers.29.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
| 275 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
| 276 |
+
"model.layers.29.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
| 277 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 278 |
+
"model.layers.29.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
|
| 279 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
| 280 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
| 281 |
+
"model.layers.29.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
|
| 282 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
| 283 |
+
"model.layers.29.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
|
| 284 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
| 285 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
| 286 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
| 287 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
| 288 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
| 289 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
| 290 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
|
| 291 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
| 292 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
| 293 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
|
| 294 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
| 295 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
|
| 296 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
| 297 |
+
"model.layers.30.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 298 |
+
"model.layers.30.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
| 299 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
| 300 |
+
"model.layers.30.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
| 301 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 302 |
+
"model.layers.30.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
|
| 303 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
| 304 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
| 305 |
+
"model.layers.30.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
|
| 306 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
| 307 |
+
"model.layers.30.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
|
| 308 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
| 309 |
+
"model.layers.31.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 310 |
+
"model.layers.31.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
| 311 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
| 312 |
+
"model.layers.31.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
| 313 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 314 |
+
"model.layers.31.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
|
| 315 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
| 316 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
| 317 |
+
"model.layers.31.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
|
| 318 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
| 319 |
+
"model.layers.31.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
|
| 320 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
| 321 |
+
"model.layers.32.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 322 |
+
"model.layers.32.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
| 323 |
+
"model.layers.32.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
| 324 |
+
"model.layers.32.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
| 325 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 326 |
+
"model.layers.32.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
|
| 327 |
+
"model.layers.32.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
| 328 |
+
"model.layers.32.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
| 329 |
+
"model.layers.32.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
|
| 330 |
+
"model.layers.32.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
| 331 |
+
"model.layers.32.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
|
| 332 |
+
"model.layers.32.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
| 333 |
+
"model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 334 |
+
"model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
| 335 |
+
"model.layers.33.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
| 336 |
+
"model.layers.33.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
| 337 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 338 |
+
"model.layers.33.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
|
| 339 |
+
"model.layers.33.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
| 340 |
+
"model.layers.33.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
| 341 |
+
"model.layers.33.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
|
| 342 |
+
"model.layers.33.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
| 343 |
+
"model.layers.33.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
|
| 344 |
+
"model.layers.33.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
| 345 |
+
"model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 346 |
+
"model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
| 347 |
+
"model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
| 348 |
+
"model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
| 349 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 350 |
+
"model.layers.34.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
|
| 351 |
+
"model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
| 352 |
+
"model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
| 353 |
+
"model.layers.34.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
|
| 354 |
+
"model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
| 355 |
+
"model.layers.34.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
|
| 356 |
+
"model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
| 357 |
+
"model.layers.35.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 358 |
+
"model.layers.35.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
| 359 |
+
"model.layers.35.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
| 360 |
+
"model.layers.35.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
| 361 |
+
"model.layers.35.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 362 |
+
"model.layers.35.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
|
| 363 |
+
"model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
| 364 |
+
"model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
| 365 |
+
"model.layers.35.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
|
| 366 |
+
"model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
| 367 |
+
"model.layers.35.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
|
| 368 |
+
"model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
| 369 |
+
"model.layers.36.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 370 |
+
"model.layers.36.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
| 371 |
+
"model.layers.36.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
| 372 |
+
"model.layers.36.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
| 373 |
+
"model.layers.36.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 374 |
+
"model.layers.36.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
|
| 375 |
+
"model.layers.36.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
| 376 |
+
"model.layers.36.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
| 377 |
+
"model.layers.36.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
|
| 378 |
+
"model.layers.36.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
| 379 |
+
"model.layers.36.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
|
| 380 |
+
"model.layers.36.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
| 381 |
+
"model.layers.37.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 382 |
+
"model.layers.37.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
| 383 |
+
"model.layers.37.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
| 384 |
+
"model.layers.37.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
| 385 |
+
"model.layers.37.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 386 |
+
"model.layers.37.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
|
| 387 |
+
"model.layers.37.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
| 388 |
+
"model.layers.37.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
| 389 |
+
"model.layers.37.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
|
| 390 |
+
"model.layers.37.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
| 391 |
+
"model.layers.37.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
|
| 392 |
+
"model.layers.37.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
| 393 |
+
"model.layers.38.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 394 |
+
"model.layers.38.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
| 395 |
+
"model.layers.38.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
| 396 |
+
"model.layers.38.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
| 397 |
+
"model.layers.38.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 398 |
+
"model.layers.38.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
|
| 399 |
+
"model.layers.38.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
| 400 |
+
"model.layers.38.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
| 401 |
+
"model.layers.38.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
|
| 402 |
+
"model.layers.38.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
| 403 |
+
"model.layers.38.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
|
| 404 |
+
"model.layers.38.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
| 405 |
+
"model.layers.39.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 406 |
+
"model.layers.39.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
| 407 |
+
"model.layers.39.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
| 408 |
+
"model.layers.39.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
| 409 |
+
"model.layers.39.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 410 |
+
"model.layers.39.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
|
| 411 |
+
"model.layers.39.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
| 412 |
+
"model.layers.39.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
| 413 |
+
"model.layers.39.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
|
| 414 |
+
"model.layers.39.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
| 415 |
+
"model.layers.39.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
|
| 416 |
+
"model.layers.39.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
| 417 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
| 418 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
| 419 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
| 420 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
| 421 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
| 422 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
|
| 423 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
| 424 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
| 425 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
|
| 426 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
| 427 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
|
| 428 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
| 429 |
+
"model.layers.40.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 430 |
+
"model.layers.40.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
| 431 |
+
"model.layers.40.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
| 432 |
+
"model.layers.40.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
| 433 |
+
"model.layers.40.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 434 |
+
"model.layers.40.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
|
| 435 |
+
"model.layers.40.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
| 436 |
+
"model.layers.40.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
| 437 |
+
"model.layers.40.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
|
| 438 |
+
"model.layers.40.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
| 439 |
+
"model.layers.40.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
|
| 440 |
+
"model.layers.40.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
| 441 |
+
"model.layers.41.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 442 |
+
"model.layers.41.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
| 443 |
+
"model.layers.41.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
| 444 |
+
"model.layers.41.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
| 445 |
+
"model.layers.41.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 446 |
+
"model.layers.41.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
|
| 447 |
+
"model.layers.41.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
| 448 |
+
"model.layers.41.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
| 449 |
+
"model.layers.41.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
|
| 450 |
+
"model.layers.41.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
| 451 |
+
"model.layers.41.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
|
| 452 |
+
"model.layers.41.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
| 453 |
+
"model.layers.42.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
| 454 |
+
"model.layers.42.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
| 455 |
+
"model.layers.42.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
| 456 |
+
"model.layers.42.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
| 457 |
+
"model.layers.42.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
| 458 |
+
"model.layers.42.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
|
| 459 |
+
"model.layers.42.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
| 460 |
+
"model.layers.42.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
| 461 |
+
"model.layers.42.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
|
| 462 |
+
"model.layers.42.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
| 463 |
+
"model.layers.42.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
|
| 464 |
+
"model.layers.42.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
| 465 |
+
"model.layers.43.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
| 466 |
+
"model.layers.43.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
| 467 |
+
"model.layers.43.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
| 468 |
+
"model.layers.43.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
| 469 |
+
"model.layers.43.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
| 470 |
+
"model.layers.43.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
|
| 471 |
+
"model.layers.43.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
|
| 472 |
+
"model.layers.43.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
| 473 |
+
"model.layers.43.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
|
| 474 |
+
"model.layers.43.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
|
| 475 |
+
"model.layers.43.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
|
| 476 |
+
"model.layers.43.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
|
| 477 |
+
"model.layers.44.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
| 478 |
+
"model.layers.44.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
| 479 |
+
"model.layers.44.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
| 480 |
+
"model.layers.44.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
| 481 |
+
"model.layers.44.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
| 482 |
+
"model.layers.44.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
|
| 483 |
+
"model.layers.44.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
|
| 484 |
+
"model.layers.44.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
| 485 |
+
"model.layers.44.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
|
| 486 |
+
"model.layers.44.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
|
| 487 |
+
"model.layers.44.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
|
| 488 |
+
"model.layers.44.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
|
| 489 |
+
"model.layers.45.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
| 490 |
+
"model.layers.45.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
| 491 |
+
"model.layers.45.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
| 492 |
+
"model.layers.45.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
| 493 |
+
"model.layers.45.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
| 494 |
+
"model.layers.45.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
|
| 495 |
+
"model.layers.45.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
|
| 496 |
+
"model.layers.45.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
| 497 |
+
"model.layers.45.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
|
| 498 |
+
"model.layers.45.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
|
| 499 |
+
"model.layers.45.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
|
| 500 |
+
"model.layers.45.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
|
| 501 |
+
"model.layers.46.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
| 502 |
+
"model.layers.46.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
| 503 |
+
"model.layers.46.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
| 504 |
+
"model.layers.46.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
| 505 |
+
"model.layers.46.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
| 506 |
+
"model.layers.46.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
|
| 507 |
+
"model.layers.46.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
|
| 508 |
+
"model.layers.46.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
| 509 |
+
"model.layers.46.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
|
| 510 |
+
"model.layers.46.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
|
| 511 |
+
"model.layers.46.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
|
| 512 |
+
"model.layers.46.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
|
| 513 |
+
"model.layers.47.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
| 514 |
+
"model.layers.47.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
| 515 |
+
"model.layers.47.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
| 516 |
+
"model.layers.47.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
| 517 |
+
"model.layers.47.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
| 518 |
+
"model.layers.47.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
|
| 519 |
+
"model.layers.47.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
|
| 520 |
+
"model.layers.47.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
| 521 |
+
"model.layers.47.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
|
| 522 |
+
"model.layers.47.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
|
| 523 |
+
"model.layers.47.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
|
| 524 |
+
"model.layers.47.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
|
| 525 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
| 526 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
| 527 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
| 528 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
| 529 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
| 530 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
|
| 531 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
| 532 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
| 533 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
|
| 534 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
| 535 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
|
| 536 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
| 537 |
+
"model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 538 |
+
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
| 539 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
| 540 |
+
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
| 541 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 542 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
|
| 543 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
| 544 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
| 545 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
|
| 546 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
| 547 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
|
| 548 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
| 549 |
+
"model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 550 |
+
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
| 551 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
| 552 |
+
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
| 553 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 554 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
|
| 555 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
| 556 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
| 557 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
|
| 558 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
| 559 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
|
| 560 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
| 561 |
+
"model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 562 |
+
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
| 563 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
| 564 |
+
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
| 565 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 566 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
|
| 567 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
| 568 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
| 569 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
|
| 570 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
| 571 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
|
| 572 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
| 573 |
+
"model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 574 |
+
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
| 575 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
| 576 |
+
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
| 577 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 578 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
|
| 579 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
| 580 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
| 581 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
|
| 582 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
| 583 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
|
| 584 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
| 585 |
+
"model.norm.weight": "model-00006-of-00006.safetensors"
|
| 586 |
+
}
|
| 587 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
| 3 |
+
size 11421896
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,208 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
},
|
| 182 |
+
"additional_special_tokens": [
|
| 183 |
+
"<|im_start|>",
|
| 184 |
+
"<|im_end|>",
|
| 185 |
+
"<|object_ref_start|>",
|
| 186 |
+
"<|object_ref_end|>",
|
| 187 |
+
"<|box_start|>",
|
| 188 |
+
"<|box_end|>",
|
| 189 |
+
"<|quad_start|>",
|
| 190 |
+
"<|quad_end|>",
|
| 191 |
+
"<|vision_start|>",
|
| 192 |
+
"<|vision_end|>",
|
| 193 |
+
"<|vision_pad|>",
|
| 194 |
+
"<|image_pad|>",
|
| 195 |
+
"<|video_pad|>"
|
| 196 |
+
],
|
| 197 |
+
"bos_token": null,
|
| 198 |
+
"clean_up_tokenization_spaces": false,
|
| 199 |
+
"eos_token": "<|im_end|>",
|
| 200 |
+
"errors": "replace",
|
| 201 |
+
"extra_special_tokens": {},
|
| 202 |
+
"model_max_length": 32768,
|
| 203 |
+
"pad_token": "<|endoftext|>",
|
| 204 |
+
"padding_side": "right",
|
| 205 |
+
"split_special_tokens": false,
|
| 206 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 207 |
+
"unk_token": null
|
| 208 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"total_flos": 1.995296975397847e+17,
|
| 4 |
+
"train_loss": 0.15181401895709556,
|
| 5 |
+
"train_runtime": 29257.7471,
|
| 6 |
+
"train_samples_per_second": 0.221,
|
| 7 |
+
"train_steps_per_second": 0.028
|
| 8 |
+
}
|
trainer_log.jsonl
ADDED
|
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 10, "total_steps": 808, "loss": 0.4428, "lr": 1.111111111111111e-06, "epoch": 0.024752475247524754, "percentage": 1.24, "elapsed_time": "0:06:05", "remaining_time": "8:05:58"}
|
| 2 |
+
{"current_steps": 20, "total_steps": 808, "loss": 0.4068, "lr": 2.345679012345679e-06, "epoch": 0.04950495049504951, "percentage": 2.48, "elapsed_time": "0:11:58", "remaining_time": "7:51:40"}
|
| 3 |
+
{"current_steps": 30, "total_steps": 808, "loss": 0.3273, "lr": 3.580246913580247e-06, "epoch": 0.07425742574257425, "percentage": 3.71, "elapsed_time": "0:17:54", "remaining_time": "7:44:17"}
|
| 4 |
+
{"current_steps": 40, "total_steps": 808, "loss": 0.2622, "lr": 4.814814814814815e-06, "epoch": 0.09900990099009901, "percentage": 4.95, "elapsed_time": "0:23:56", "remaining_time": "7:39:34"}
|
| 5 |
+
{"current_steps": 50, "total_steps": 808, "loss": 0.2315, "lr": 6.049382716049383e-06, "epoch": 0.12376237623762376, "percentage": 6.19, "elapsed_time": "0:29:56", "remaining_time": "7:33:50"}
|
| 6 |
+
{"current_steps": 60, "total_steps": 808, "loss": 0.225, "lr": 7.283950617283952e-06, "epoch": 0.1485148514851485, "percentage": 7.43, "elapsed_time": "0:35:43", "remaining_time": "7:25:27"}
|
| 7 |
+
{"current_steps": 70, "total_steps": 808, "loss": 0.2078, "lr": 8.518518518518519e-06, "epoch": 0.17326732673267325, "percentage": 8.66, "elapsed_time": "0:41:30", "remaining_time": "7:17:35"}
|
| 8 |
+
{"current_steps": 80, "total_steps": 808, "loss": 0.2007, "lr": 9.753086419753087e-06, "epoch": 0.19801980198019803, "percentage": 9.9, "elapsed_time": "0:47:24", "remaining_time": "7:11:21"}
|
| 9 |
+
{"current_steps": 90, "total_steps": 808, "loss": 0.2115, "lr": 9.997012501794273e-06, "epoch": 0.22277227722772278, "percentage": 11.14, "elapsed_time": "0:53:12", "remaining_time": "7:04:28"}
|
| 10 |
+
{"current_steps": 100, "total_steps": 808, "loss": 0.1977, "lr": 9.984881908680157e-06, "epoch": 0.24752475247524752, "percentage": 12.38, "elapsed_time": "0:59:10", "remaining_time": "6:58:58"}
|
| 11 |
+
{"current_steps": 110, "total_steps": 808, "loss": 0.2044, "lr": 9.963444133394478e-06, "epoch": 0.2722772277227723, "percentage": 13.61, "elapsed_time": "1:05:05", "remaining_time": "6:53:02"}
|
| 12 |
+
{"current_steps": 120, "total_steps": 808, "loss": 0.1859, "lr": 9.93273920201681e-06, "epoch": 0.297029702970297, "percentage": 14.85, "elapsed_time": "1:11:07", "remaining_time": "6:47:44"}
|
| 13 |
+
{"current_steps": 130, "total_steps": 808, "loss": 0.1986, "lr": 9.892824443164987e-06, "epoch": 0.3217821782178218, "percentage": 16.09, "elapsed_time": "1:17:00", "remaining_time": "6:41:36"}
|
| 14 |
+
{"current_steps": 140, "total_steps": 808, "loss": 0.1972, "lr": 9.84377438095789e-06, "epoch": 0.3465346534653465, "percentage": 17.33, "elapsed_time": "1:22:49", "remaining_time": "6:35:09"}
|
| 15 |
+
{"current_steps": 150, "total_steps": 808, "loss": 0.1973, "lr": 9.785680595872824e-06, "epoch": 0.3712871287128713, "percentage": 18.56, "elapsed_time": "1:28:35", "remaining_time": "6:28:35"}
|
| 16 |
+
{"current_steps": 160, "total_steps": 808, "loss": 0.1848, "lr": 9.718651553757266e-06, "epoch": 0.39603960396039606, "percentage": 19.8, "elapsed_time": "1:34:32", "remaining_time": "6:22:55"}
|
| 17 |
+
{"current_steps": 170, "total_steps": 808, "loss": 0.1911, "lr": 9.642812403314272e-06, "epoch": 0.4207920792079208, "percentage": 21.04, "elapsed_time": "1:40:29", "remaining_time": "6:17:06"}
|
| 18 |
+
{"current_steps": 180, "total_steps": 808, "loss": 0.1925, "lr": 9.55830474243961e-06, "epoch": 0.44554455445544555, "percentage": 22.28, "elapsed_time": "1:46:24", "remaining_time": "6:11:16"}
|
| 19 |
+
{"current_steps": 190, "total_steps": 808, "loss": 0.1866, "lr": 9.465286353846905e-06, "epoch": 0.47029702970297027, "percentage": 23.51, "elapsed_time": "1:52:21", "remaining_time": "6:05:27"}
|
| 20 |
+
{"current_steps": 200, "total_steps": 808, "loss": 0.185, "lr": 9.36393091047441e-06, "epoch": 0.49504950495049505, "percentage": 24.75, "elapsed_time": "1:58:14", "remaining_time": "5:59:27"}
|
| 21 |
+
{"current_steps": 210, "total_steps": 808, "loss": 0.1848, "lr": 9.254427651223434e-06, "epoch": 0.5198019801980198, "percentage": 25.99, "elapsed_time": "2:06:22", "remaining_time": "5:59:52"}
|
| 22 |
+
{"current_steps": 220, "total_steps": 808, "loss": 0.1851, "lr": 9.136981027633834e-06, "epoch": 0.5445544554455446, "percentage": 27.23, "elapsed_time": "2:12:21", "remaining_time": "5:53:46"}
|
| 23 |
+
{"current_steps": 230, "total_steps": 808, "loss": 0.1948, "lr": 9.011810322156269e-06, "epoch": 0.5693069306930693, "percentage": 28.47, "elapsed_time": "2:17:57", "remaining_time": "5:46:41"}
|
| 24 |
+
{"current_steps": 240, "total_steps": 808, "loss": 0.1861, "lr": 8.879149238733932e-06, "epoch": 0.594059405940594, "percentage": 29.7, "elapsed_time": "2:23:56", "remaining_time": "5:40:40"}
|
| 25 |
+
{"current_steps": 250, "total_steps": 808, "loss": 0.1757, "lr": 8.739245466458187e-06, "epoch": 0.6188118811881188, "percentage": 30.94, "elapsed_time": "2:29:39", "remaining_time": "5:34:02"}
|
| 26 |
+
{"current_steps": 260, "total_steps": 808, "loss": 0.1794, "lr": 8.592360217112759e-06, "epoch": 0.6435643564356436, "percentage": 32.18, "elapsed_time": "2:35:37", "remaining_time": "5:28:01"}
|
| 27 |
+
{"current_steps": 270, "total_steps": 808, "loss": 0.1735, "lr": 8.438767737469995e-06, "epoch": 0.6683168316831684, "percentage": 33.42, "elapsed_time": "2:41:25", "remaining_time": "5:21:39"}
|
| 28 |
+
{"current_steps": 280, "total_steps": 808, "loss": 0.1713, "lr": 8.278754797249702e-06, "epoch": 0.693069306930693, "percentage": 34.65, "elapsed_time": "2:47:14", "remaining_time": "5:15:22"}
|
| 29 |
+
{"current_steps": 290, "total_steps": 808, "loss": 0.1761, "lr": 8.11262015369663e-06, "epoch": 0.7178217821782178, "percentage": 35.89, "elapsed_time": "2:53:06", "remaining_time": "5:09:13"}
|
| 30 |
+
{"current_steps": 300, "total_steps": 808, "loss": 0.1874, "lr": 7.940673993776258e-06, "epoch": 0.7425742574257426, "percentage": 37.13, "elapsed_time": "2:59:00", "remaining_time": "5:03:07"}
|
| 31 |
+
{"current_steps": 310, "total_steps": 808, "loss": 0.1683, "lr": 7.763237355030384e-06, "epoch": 0.7673267326732673, "percentage": 38.37, "elapsed_time": "3:04:50", "remaining_time": "4:56:55"}
|
| 32 |
+
{"current_steps": 320, "total_steps": 808, "loss": 0.1776, "lr": 7.580641526173758e-06, "epoch": 0.7920792079207921, "percentage": 39.6, "elapsed_time": "3:10:46", "remaining_time": "4:50:55"}
|
| 33 |
+
{"current_steps": 330, "total_steps": 808, "loss": 0.1861, "lr": 7.39322742855097e-06, "epoch": 0.8168316831683168, "percentage": 40.84, "elapsed_time": "3:16:36", "remaining_time": "4:44:47"}
|
| 34 |
+
{"current_steps": 340, "total_steps": 808, "loss": 0.1832, "lr": 7.201344979608423e-06, "epoch": 0.8415841584158416, "percentage": 42.08, "elapsed_time": "3:22:31", "remaining_time": "4:38:46"}
|
| 35 |
+
{"current_steps": 350, "total_steps": 808, "loss": 0.1778, "lr": 7.0053524395698345e-06, "epoch": 0.8663366336633663, "percentage": 43.32, "elapsed_time": "3:28:17", "remaining_time": "4:32:33"}
|
| 36 |
+
{"current_steps": 360, "total_steps": 808, "loss": 0.1712, "lr": 6.805615742535117e-06, "epoch": 0.8910891089108911, "percentage": 44.55, "elapsed_time": "3:34:14", "remaining_time": "4:26:36"}
|
| 37 |
+
{"current_steps": 370, "total_steps": 808, "loss": 0.1752, "lr": 6.602507813251478e-06, "epoch": 0.9158415841584159, "percentage": 45.79, "elapsed_time": "3:40:14", "remaining_time": "4:20:43"}
|
| 38 |
+
{"current_steps": 380, "total_steps": 808, "loss": 0.1691, "lr": 6.396407870832419e-06, "epoch": 0.9405940594059405, "percentage": 47.03, "elapsed_time": "3:46:12", "remaining_time": "4:14:46"}
|
| 39 |
+
{"current_steps": 390, "total_steps": 808, "loss": 0.1638, "lr": 6.187700720724648e-06, "epoch": 0.9653465346534653, "percentage": 48.27, "elapsed_time": "3:52:04", "remaining_time": "4:08:44"}
|
| 40 |
+
{"current_steps": 400, "total_steps": 808, "loss": 0.1715, "lr": 5.976776036244833e-06, "epoch": 0.9900990099009901, "percentage": 49.5, "elapsed_time": "3:57:50", "remaining_time": "4:02:35"}
|
| 41 |
+
{"current_steps": 410, "total_steps": 808, "loss": 0.1338, "lr": 5.764027631027659e-06, "epoch": 1.0148514851485149, "percentage": 50.74, "elapsed_time": "4:06:08", "remaining_time": "3:58:56"}
|
| 42 |
+
{"current_steps": 420, "total_steps": 808, "loss": 0.1068, "lr": 5.549852723743564e-06, "epoch": 1.0396039603960396, "percentage": 51.98, "elapsed_time": "4:12:07", "remaining_time": "3:52:55"}
|
| 43 |
+
{"current_steps": 430, "total_steps": 808, "loss": 0.1083, "lr": 5.334651196459003e-06, "epoch": 1.0643564356435644, "percentage": 53.22, "elapsed_time": "4:18:01", "remaining_time": "3:46:49"}
|
| 44 |
+
{"current_steps": 440, "total_steps": 808, "loss": 0.0991, "lr": 5.118824848023926e-06, "epoch": 1.0891089108910892, "percentage": 54.46, "elapsed_time": "4:23:56", "remaining_time": "3:40:45"}
|
| 45 |
+
{"current_steps": 450, "total_steps": 808, "loss": 0.1082, "lr": 4.902776643880461e-06, "epoch": 1.113861386138614, "percentage": 55.69, "elapsed_time": "4:29:56", "remaining_time": "3:34:45"}
|
| 46 |
+
{"current_steps": 460, "total_steps": 808, "loss": 0.0998, "lr": 4.686909963693498e-06, "epoch": 1.1386138613861387, "percentage": 56.93, "elapsed_time": "4:35:49", "remaining_time": "3:28:40"}
|
| 47 |
+
{"current_steps": 470, "total_steps": 808, "loss": 0.1, "lr": 4.47162784820784e-06, "epoch": 1.1633663366336633, "percentage": 58.17, "elapsed_time": "4:41:38", "remaining_time": "3:22:32"}
|
| 48 |
+
{"current_steps": 480, "total_steps": 808, "loss": 0.1019, "lr": 4.257332246738201e-06, "epoch": 1.188118811881188, "percentage": 59.41, "elapsed_time": "4:47:33", "remaining_time": "3:16:29"}
|
| 49 |
+
{"current_steps": 490, "total_steps": 808, "loss": 0.1051, "lr": 4.04442326669695e-06, "epoch": 1.2128712871287128, "percentage": 60.64, "elapsed_time": "4:53:23", "remaining_time": "3:10:24"}
|
| 50 |
+
{"current_steps": 500, "total_steps": 808, "loss": 0.1004, "lr": 3.833298426560851e-06, "epoch": 1.2376237623762376, "percentage": 61.88, "elapsed_time": "4:59:23", "remaining_time": "3:04:25"}
|
| 51 |
+
{"current_steps": 510, "total_steps": 808, "loss": 0.1014, "lr": 3.624351913671571e-06, "epoch": 1.2623762376237624, "percentage": 63.12, "elapsed_time": "5:05:16", "remaining_time": "2:58:22"}
|
| 52 |
+
{"current_steps": 520, "total_steps": 808, "loss": 0.1049, "lr": 3.4179738482556648e-06, "epoch": 1.2871287128712872, "percentage": 64.36, "elapsed_time": "5:11:12", "remaining_time": "2:52:21"}
|
| 53 |
+
{"current_steps": 530, "total_steps": 808, "loss": 0.1009, "lr": 3.214549555038218e-06, "epoch": 1.311881188118812, "percentage": 65.59, "elapsed_time": "5:17:05", "remaining_time": "2:46:19"}
|
| 54 |
+
{"current_steps": 540, "total_steps": 808, "loss": 0.0999, "lr": 3.0144588438100693e-06, "epoch": 1.3366336633663367, "percentage": 66.83, "elapsed_time": "5:23:02", "remaining_time": "2:40:19"}
|
| 55 |
+
{"current_steps": 550, "total_steps": 808, "loss": 0.0991, "lr": 2.8180753002918735e-06, "epoch": 1.3613861386138613, "percentage": 68.07, "elapsed_time": "5:28:50", "remaining_time": "2:34:15"}
|
| 56 |
+
{"current_steps": 560, "total_steps": 808, "loss": 0.0933, "lr": 2.6257655886190147e-06, "epoch": 1.386138613861386, "percentage": 69.31, "elapsed_time": "5:34:42", "remaining_time": "2:28:13"}
|
| 57 |
+
{"current_steps": 570, "total_steps": 808, "loss": 0.0989, "lr": 2.4378887667496696e-06, "epoch": 1.4108910891089108, "percentage": 70.54, "elapsed_time": "5:40:38", "remaining_time": "2:22:13"}
|
| 58 |
+
{"current_steps": 580, "total_steps": 808, "loss": 0.0994, "lr": 2.2547956160742473e-06, "epoch": 1.4356435643564356, "percentage": 71.78, "elapsed_time": "5:46:30", "remaining_time": "2:16:12"}
|
| 59 |
+
{"current_steps": 590, "total_steps": 808, "loss": 0.1083, "lr": 2.0768279864778475e-06, "epoch": 1.4603960396039604, "percentage": 73.02, "elapsed_time": "5:52:24", "remaining_time": "2:10:12"}
|
| 60 |
+
{"current_steps": 600, "total_steps": 808, "loss": 0.0955, "lr": 1.9043181580785597e-06, "epoch": 1.4851485148514851, "percentage": 74.26, "elapsed_time": "5:58:06", "remaining_time": "2:04:08"}
|
| 61 |
+
{"current_steps": 610, "total_steps": 808, "loss": 0.1021, "lr": 1.73758822083332e-06, "epoch": 1.50990099009901, "percentage": 75.5, "elapsed_time": "6:06:29", "remaining_time": "1:58:57"}
|
| 62 |
+
{"current_steps": 620, "total_steps": 808, "loss": 0.0944, "lr": 1.5769494731696206e-06, "epoch": 1.5346534653465347, "percentage": 76.73, "elapsed_time": "6:12:28", "remaining_time": "1:52:56"}
|
| 63 |
+
{"current_steps": 630, "total_steps": 808, "loss": 0.103, "lr": 1.4227018407658822e-06, "epoch": 1.5594059405940595, "percentage": 77.97, "elapsed_time": "6:18:18", "remaining_time": "1:46:53"}
|
| 64 |
+
{"current_steps": 640, "total_steps": 808, "loss": 0.1015, "lr": 1.275133316565691e-06, "epoch": 1.5841584158415842, "percentage": 79.21, "elapsed_time": "6:24:10", "remaining_time": "1:40:50"}
|
| 65 |
+
{"current_steps": 650, "total_steps": 808, "loss": 0.0916, "lr": 1.1345194230714235e-06, "epoch": 1.608910891089109, "percentage": 80.45, "elapsed_time": "6:30:07", "remaining_time": "1:34:49"}
|
| 66 |
+
{"current_steps": 660, "total_steps": 808, "loss": 0.1006, "lr": 1.001122697921197e-06, "epoch": 1.6336633663366338, "percentage": 81.68, "elapsed_time": "6:35:48", "remaining_time": "1:28:45"}
|
| 67 |
+
{"current_steps": 670, "total_steps": 808, "loss": 0.0973, "lr": 8.751922037096328e-07, "epoch": 1.6584158415841586, "percentage": 82.92, "elapsed_time": "6:41:43", "remaining_time": "1:22:44"}
|
| 68 |
+
{"current_steps": 680, "total_steps": 808, "loss": 0.0988, "lr": 7.569630629676294e-07, "epoch": 1.6831683168316833, "percentage": 84.16, "elapsed_time": "6:47:37", "remaining_time": "1:16:43"}
|
| 69 |
+
{"current_steps": 690, "total_steps": 808, "loss": 0.0948, "lr": 6.466560191693566e-07, "epoch": 1.7079207920792079, "percentage": 85.4, "elapsed_time": "6:53:35", "remaining_time": "1:10:43"}
|
| 70 |
+
{"current_steps": 700, "total_steps": 808, "loss": 0.0913, "lr": 5.444770245861553e-07, "epoch": 1.7326732673267327, "percentage": 86.63, "elapsed_time": "6:59:30", "remaining_time": "1:04:43"}
|
| 71 |
+
{"current_steps": 710, "total_steps": 808, "loss": 0.0944, "lr": 4.506168557567886e-07, "epoch": 1.7574257425742574, "percentage": 87.87, "elapsed_time": "7:05:28", "remaining_time": "0:58:43"}
|
| 72 |
+
{"current_steps": 720, "total_steps": 808, "loss": 0.0922, "lr": 3.6525075729205274e-07, "epoch": 1.7821782178217822, "percentage": 89.11, "elapsed_time": "7:11:22", "remaining_time": "0:52:43"}
|
| 73 |
+
{"current_steps": 730, "total_steps": 808, "loss": 0.098, "lr": 2.8853811467875413e-07, "epoch": 1.806930693069307, "percentage": 90.35, "elapsed_time": "7:17:12", "remaining_time": "0:46:42"}
|
| 74 |
+
{"current_steps": 740, "total_steps": 808, "loss": 0.1025, "lr": 2.2062215669397201e-07, "epoch": 1.8316831683168315, "percentage": 91.58, "elapsed_time": "7:23:11", "remaining_time": "0:40:43"}
|
| 75 |
+
{"current_steps": 750, "total_steps": 808, "loss": 0.0906, "lr": 1.616296879852175e-07, "epoch": 1.8564356435643563, "percentage": 92.82, "elapsed_time": "7:29:11", "remaining_time": "0:34:44"}
|
| 76 |
+
{"current_steps": 760, "total_steps": 808, "loss": 0.1015, "lr": 1.1167085231579111e-07, "epoch": 1.881188118811881, "percentage": 94.06, "elapsed_time": "7:34:48", "remaining_time": "0:28:43"}
|
| 77 |
+
{"current_steps": 770, "total_steps": 808, "loss": 0.1024, "lr": 7.083892691736428e-08, "epoch": 1.9059405940594059, "percentage": 95.3, "elapsed_time": "7:40:39", "remaining_time": "0:22:44"}
|
| 78 |
+
{"current_steps": 780, "total_steps": 808, "loss": 0.0925, "lr": 3.9210148333763135e-08, "epoch": 1.9306930693069306, "percentage": 96.53, "elapsed_time": "7:46:29", "remaining_time": "0:16:44"}
|
| 79 |
+
{"current_steps": 790, "total_steps": 808, "loss": 0.0973, "lr": 1.684357008110593e-08, "epoch": 1.9554455445544554, "percentage": 97.77, "elapsed_time": "7:52:17", "remaining_time": "0:10:45"}
|
| 80 |
+
{"current_steps": 800, "total_steps": 808, "loss": 0.0901, "lr": 3.780952390058379e-09, "epoch": 1.9801980198019802, "percentage": 99.01, "elapsed_time": "7:58:10", "remaining_time": "0:04:46"}
|
| 81 |
+
{"current_steps": 808, "total_steps": 808, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "8:07:37", "remaining_time": "0:00:00"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,603 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 2.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 808,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.024752475247524754,
|
| 14 |
+
"grad_norm": 1.4873312819674722,
|
| 15 |
+
"learning_rate": 1.111111111111111e-06,
|
| 16 |
+
"loss": 0.4428,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.04950495049504951,
|
| 21 |
+
"grad_norm": 0.860149696440848,
|
| 22 |
+
"learning_rate": 2.345679012345679e-06,
|
| 23 |
+
"loss": 0.4068,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.07425742574257425,
|
| 28 |
+
"grad_norm": 0.7730974534228278,
|
| 29 |
+
"learning_rate": 3.580246913580247e-06,
|
| 30 |
+
"loss": 0.3273,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.09900990099009901,
|
| 35 |
+
"grad_norm": 0.5689200686287729,
|
| 36 |
+
"learning_rate": 4.814814814814815e-06,
|
| 37 |
+
"loss": 0.2622,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.12376237623762376,
|
| 42 |
+
"grad_norm": 0.717240303466821,
|
| 43 |
+
"learning_rate": 6.049382716049383e-06,
|
| 44 |
+
"loss": 0.2315,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.1485148514851485,
|
| 49 |
+
"grad_norm": 0.5479796314240546,
|
| 50 |
+
"learning_rate": 7.283950617283952e-06,
|
| 51 |
+
"loss": 0.225,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.17326732673267325,
|
| 56 |
+
"grad_norm": 0.5367981858324066,
|
| 57 |
+
"learning_rate": 8.518518518518519e-06,
|
| 58 |
+
"loss": 0.2078,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.19801980198019803,
|
| 63 |
+
"grad_norm": 0.5128703711055814,
|
| 64 |
+
"learning_rate": 9.753086419753087e-06,
|
| 65 |
+
"loss": 0.2007,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.22277227722772278,
|
| 70 |
+
"grad_norm": 0.5500134916740962,
|
| 71 |
+
"learning_rate": 9.997012501794273e-06,
|
| 72 |
+
"loss": 0.2115,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.24752475247524752,
|
| 77 |
+
"grad_norm": 0.5442543564775922,
|
| 78 |
+
"learning_rate": 9.984881908680157e-06,
|
| 79 |
+
"loss": 0.1977,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.2722772277227723,
|
| 84 |
+
"grad_norm": 0.4987905277999744,
|
| 85 |
+
"learning_rate": 9.963444133394478e-06,
|
| 86 |
+
"loss": 0.2044,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.297029702970297,
|
| 91 |
+
"grad_norm": 0.5792621848377878,
|
| 92 |
+
"learning_rate": 9.93273920201681e-06,
|
| 93 |
+
"loss": 0.1859,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.3217821782178218,
|
| 98 |
+
"grad_norm": 0.4991425649649758,
|
| 99 |
+
"learning_rate": 9.892824443164987e-06,
|
| 100 |
+
"loss": 0.1986,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.3465346534653465,
|
| 105 |
+
"grad_norm": 0.5558327647976072,
|
| 106 |
+
"learning_rate": 9.84377438095789e-06,
|
| 107 |
+
"loss": 0.1972,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.3712871287128713,
|
| 112 |
+
"grad_norm": 0.5522405055451383,
|
| 113 |
+
"learning_rate": 9.785680595872824e-06,
|
| 114 |
+
"loss": 0.1973,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.39603960396039606,
|
| 119 |
+
"grad_norm": 0.4641525226246223,
|
| 120 |
+
"learning_rate": 9.718651553757266e-06,
|
| 121 |
+
"loss": 0.1848,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.4207920792079208,
|
| 126 |
+
"grad_norm": 0.4712224353128171,
|
| 127 |
+
"learning_rate": 9.642812403314272e-06,
|
| 128 |
+
"loss": 0.1911,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.44554455445544555,
|
| 133 |
+
"grad_norm": 0.5142622413114706,
|
| 134 |
+
"learning_rate": 9.55830474243961e-06,
|
| 135 |
+
"loss": 0.1925,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.47029702970297027,
|
| 140 |
+
"grad_norm": 0.4006105519636306,
|
| 141 |
+
"learning_rate": 9.465286353846905e-06,
|
| 142 |
+
"loss": 0.1866,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.49504950495049505,
|
| 147 |
+
"grad_norm": 0.5073171400534645,
|
| 148 |
+
"learning_rate": 9.36393091047441e-06,
|
| 149 |
+
"loss": 0.185,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.5198019801980198,
|
| 154 |
+
"grad_norm": 0.5880177221650992,
|
| 155 |
+
"learning_rate": 9.254427651223434e-06,
|
| 156 |
+
"loss": 0.1848,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.5445544554455446,
|
| 161 |
+
"grad_norm": 0.4554484357702942,
|
| 162 |
+
"learning_rate": 9.136981027633834e-06,
|
| 163 |
+
"loss": 0.1851,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.5693069306930693,
|
| 168 |
+
"grad_norm": 0.5031293487926348,
|
| 169 |
+
"learning_rate": 9.011810322156269e-06,
|
| 170 |
+
"loss": 0.1948,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.594059405940594,
|
| 175 |
+
"grad_norm": 0.4577032226856764,
|
| 176 |
+
"learning_rate": 8.879149238733932e-06,
|
| 177 |
+
"loss": 0.1861,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.6188118811881188,
|
| 182 |
+
"grad_norm": 0.44733995052099396,
|
| 183 |
+
"learning_rate": 8.739245466458187e-06,
|
| 184 |
+
"loss": 0.1757,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.6435643564356436,
|
| 189 |
+
"grad_norm": 0.5406277161031414,
|
| 190 |
+
"learning_rate": 8.592360217112759e-06,
|
| 191 |
+
"loss": 0.1794,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.6683168316831684,
|
| 196 |
+
"grad_norm": 0.4515622758216762,
|
| 197 |
+
"learning_rate": 8.438767737469995e-06,
|
| 198 |
+
"loss": 0.1735,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.693069306930693,
|
| 203 |
+
"grad_norm": 0.4635294881039678,
|
| 204 |
+
"learning_rate": 8.278754797249702e-06,
|
| 205 |
+
"loss": 0.1713,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.7178217821782178,
|
| 210 |
+
"grad_norm": 0.5013665282058885,
|
| 211 |
+
"learning_rate": 8.11262015369663e-06,
|
| 212 |
+
"loss": 0.1761,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.7425742574257426,
|
| 217 |
+
"grad_norm": 0.4829501917570715,
|
| 218 |
+
"learning_rate": 7.940673993776258e-06,
|
| 219 |
+
"loss": 0.1874,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.7673267326732673,
|
| 224 |
+
"grad_norm": 0.443719131169877,
|
| 225 |
+
"learning_rate": 7.763237355030384e-06,
|
| 226 |
+
"loss": 0.1683,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.7920792079207921,
|
| 231 |
+
"grad_norm": 0.4280811144981197,
|
| 232 |
+
"learning_rate": 7.580641526173758e-06,
|
| 233 |
+
"loss": 0.1776,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.8168316831683168,
|
| 238 |
+
"grad_norm": 0.6434688708393701,
|
| 239 |
+
"learning_rate": 7.39322742855097e-06,
|
| 240 |
+
"loss": 0.1861,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.8415841584158416,
|
| 245 |
+
"grad_norm": 0.4538744032232575,
|
| 246 |
+
"learning_rate": 7.201344979608423e-06,
|
| 247 |
+
"loss": 0.1832,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.8663366336633663,
|
| 252 |
+
"grad_norm": 0.4590505681626231,
|
| 253 |
+
"learning_rate": 7.0053524395698345e-06,
|
| 254 |
+
"loss": 0.1778,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.8910891089108911,
|
| 259 |
+
"grad_norm": 0.39529209206101645,
|
| 260 |
+
"learning_rate": 6.805615742535117e-06,
|
| 261 |
+
"loss": 0.1712,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.9158415841584159,
|
| 266 |
+
"grad_norm": 0.5257661202592374,
|
| 267 |
+
"learning_rate": 6.602507813251478e-06,
|
| 268 |
+
"loss": 0.1752,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.9405940594059405,
|
| 273 |
+
"grad_norm": 0.49075057672303185,
|
| 274 |
+
"learning_rate": 6.396407870832419e-06,
|
| 275 |
+
"loss": 0.1691,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.9653465346534653,
|
| 280 |
+
"grad_norm": 0.4063721529471352,
|
| 281 |
+
"learning_rate": 6.187700720724648e-06,
|
| 282 |
+
"loss": 0.1638,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.9900990099009901,
|
| 287 |
+
"grad_norm": 0.49409556281854755,
|
| 288 |
+
"learning_rate": 5.976776036244833e-06,
|
| 289 |
+
"loss": 0.1715,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.0148514851485149,
|
| 294 |
+
"grad_norm": 0.4704764465424178,
|
| 295 |
+
"learning_rate": 5.764027631027659e-06,
|
| 296 |
+
"loss": 0.1338,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.0396039603960396,
|
| 301 |
+
"grad_norm": 0.514030762089054,
|
| 302 |
+
"learning_rate": 5.549852723743564e-06,
|
| 303 |
+
"loss": 0.1068,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 1.0643564356435644,
|
| 308 |
+
"grad_norm": 0.46024391907618734,
|
| 309 |
+
"learning_rate": 5.334651196459003e-06,
|
| 310 |
+
"loss": 0.1083,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.0891089108910892,
|
| 315 |
+
"grad_norm": 0.5084928690964229,
|
| 316 |
+
"learning_rate": 5.118824848023926e-06,
|
| 317 |
+
"loss": 0.0991,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.113861386138614,
|
| 322 |
+
"grad_norm": 0.5721555377829844,
|
| 323 |
+
"learning_rate": 4.902776643880461e-06,
|
| 324 |
+
"loss": 0.1082,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.1386138613861387,
|
| 329 |
+
"grad_norm": 0.44271050446405025,
|
| 330 |
+
"learning_rate": 4.686909963693498e-06,
|
| 331 |
+
"loss": 0.0998,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.1633663366336633,
|
| 336 |
+
"grad_norm": 0.4765511931794564,
|
| 337 |
+
"learning_rate": 4.47162784820784e-06,
|
| 338 |
+
"loss": 0.1,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.188118811881188,
|
| 343 |
+
"grad_norm": 0.4946911218893508,
|
| 344 |
+
"learning_rate": 4.257332246738201e-06,
|
| 345 |
+
"loss": 0.1019,
|
| 346 |
+
"step": 480
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.2128712871287128,
|
| 350 |
+
"grad_norm": 0.4965201004334917,
|
| 351 |
+
"learning_rate": 4.04442326669695e-06,
|
| 352 |
+
"loss": 0.1051,
|
| 353 |
+
"step": 490
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.2376237623762376,
|
| 357 |
+
"grad_norm": 0.5408097804856393,
|
| 358 |
+
"learning_rate": 3.833298426560851e-06,
|
| 359 |
+
"loss": 0.1004,
|
| 360 |
+
"step": 500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.2623762376237624,
|
| 364 |
+
"grad_norm": 0.5252320189983105,
|
| 365 |
+
"learning_rate": 3.624351913671571e-06,
|
| 366 |
+
"loss": 0.1014,
|
| 367 |
+
"step": 510
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.2871287128712872,
|
| 371 |
+
"grad_norm": 0.556206677324514,
|
| 372 |
+
"learning_rate": 3.4179738482556648e-06,
|
| 373 |
+
"loss": 0.1049,
|
| 374 |
+
"step": 520
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.311881188118812,
|
| 378 |
+
"grad_norm": 0.5360529256375285,
|
| 379 |
+
"learning_rate": 3.214549555038218e-06,
|
| 380 |
+
"loss": 0.1009,
|
| 381 |
+
"step": 530
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.3366336633663367,
|
| 385 |
+
"grad_norm": 0.48742930116454386,
|
| 386 |
+
"learning_rate": 3.0144588438100693e-06,
|
| 387 |
+
"loss": 0.0999,
|
| 388 |
+
"step": 540
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.3613861386138613,
|
| 392 |
+
"grad_norm": 0.7874631044020063,
|
| 393 |
+
"learning_rate": 2.8180753002918735e-06,
|
| 394 |
+
"loss": 0.0991,
|
| 395 |
+
"step": 550
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.386138613861386,
|
| 399 |
+
"grad_norm": 0.4606133875814067,
|
| 400 |
+
"learning_rate": 2.6257655886190147e-06,
|
| 401 |
+
"loss": 0.0933,
|
| 402 |
+
"step": 560
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.4108910891089108,
|
| 406 |
+
"grad_norm": 0.47731270631998807,
|
| 407 |
+
"learning_rate": 2.4378887667496696e-06,
|
| 408 |
+
"loss": 0.0989,
|
| 409 |
+
"step": 570
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 1.4356435643564356,
|
| 413 |
+
"grad_norm": 0.5003301127513975,
|
| 414 |
+
"learning_rate": 2.2547956160742473e-06,
|
| 415 |
+
"loss": 0.0994,
|
| 416 |
+
"step": 580
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.4603960396039604,
|
| 420 |
+
"grad_norm": 0.5212714732655578,
|
| 421 |
+
"learning_rate": 2.0768279864778475e-06,
|
| 422 |
+
"loss": 0.1083,
|
| 423 |
+
"step": 590
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.4851485148514851,
|
| 427 |
+
"grad_norm": 0.4573167459369404,
|
| 428 |
+
"learning_rate": 1.9043181580785597e-06,
|
| 429 |
+
"loss": 0.0955,
|
| 430 |
+
"step": 600
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 1.50990099009901,
|
| 434 |
+
"grad_norm": 0.5828901902132052,
|
| 435 |
+
"learning_rate": 1.73758822083332e-06,
|
| 436 |
+
"loss": 0.1021,
|
| 437 |
+
"step": 610
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 1.5346534653465347,
|
| 441 |
+
"grad_norm": 0.44258879326834666,
|
| 442 |
+
"learning_rate": 1.5769494731696206e-06,
|
| 443 |
+
"loss": 0.0944,
|
| 444 |
+
"step": 620
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.5594059405940595,
|
| 448 |
+
"grad_norm": 0.5612729118082875,
|
| 449 |
+
"learning_rate": 1.4227018407658822e-06,
|
| 450 |
+
"loss": 0.103,
|
| 451 |
+
"step": 630
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.5841584158415842,
|
| 455 |
+
"grad_norm": 0.5111939858784064,
|
| 456 |
+
"learning_rate": 1.275133316565691e-06,
|
| 457 |
+
"loss": 0.1015,
|
| 458 |
+
"step": 640
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.608910891089109,
|
| 462 |
+
"grad_norm": 0.43301100280236354,
|
| 463 |
+
"learning_rate": 1.1345194230714235e-06,
|
| 464 |
+
"loss": 0.0916,
|
| 465 |
+
"step": 650
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.6336633663366338,
|
| 469 |
+
"grad_norm": 0.5685808742921838,
|
| 470 |
+
"learning_rate": 1.001122697921197e-06,
|
| 471 |
+
"loss": 0.1006,
|
| 472 |
+
"step": 660
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 1.6584158415841586,
|
| 476 |
+
"grad_norm": 0.4732021093665504,
|
| 477 |
+
"learning_rate": 8.751922037096328e-07,
|
| 478 |
+
"loss": 0.0973,
|
| 479 |
+
"step": 670
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.6831683168316833,
|
| 483 |
+
"grad_norm": 0.5002688727866472,
|
| 484 |
+
"learning_rate": 7.569630629676294e-07,
|
| 485 |
+
"loss": 0.0988,
|
| 486 |
+
"step": 680
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 1.7079207920792079,
|
| 490 |
+
"grad_norm": 0.6448602699924979,
|
| 491 |
+
"learning_rate": 6.466560191693566e-07,
|
| 492 |
+
"loss": 0.0948,
|
| 493 |
+
"step": 690
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 1.7326732673267327,
|
| 497 |
+
"grad_norm": 0.49223407652600815,
|
| 498 |
+
"learning_rate": 5.444770245861553e-07,
|
| 499 |
+
"loss": 0.0913,
|
| 500 |
+
"step": 700
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.7574257425742574,
|
| 504 |
+
"grad_norm": 0.4356390296013288,
|
| 505 |
+
"learning_rate": 4.506168557567886e-07,
|
| 506 |
+
"loss": 0.0944,
|
| 507 |
+
"step": 710
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 1.7821782178217822,
|
| 511 |
+
"grad_norm": 0.4524339230442861,
|
| 512 |
+
"learning_rate": 3.6525075729205274e-07,
|
| 513 |
+
"loss": 0.0922,
|
| 514 |
+
"step": 720
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 1.806930693069307,
|
| 518 |
+
"grad_norm": 0.6615290546421568,
|
| 519 |
+
"learning_rate": 2.8853811467875413e-07,
|
| 520 |
+
"loss": 0.098,
|
| 521 |
+
"step": 730
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.8316831683168315,
|
| 525 |
+
"grad_norm": 0.49847536579909224,
|
| 526 |
+
"learning_rate": 2.2062215669397201e-07,
|
| 527 |
+
"loss": 0.1025,
|
| 528 |
+
"step": 740
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 1.8564356435643563,
|
| 532 |
+
"grad_norm": 0.4027083627268508,
|
| 533 |
+
"learning_rate": 1.616296879852175e-07,
|
| 534 |
+
"loss": 0.0906,
|
| 535 |
+
"step": 750
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 1.881188118811881,
|
| 539 |
+
"grad_norm": 0.5545161003969088,
|
| 540 |
+
"learning_rate": 1.1167085231579111e-07,
|
| 541 |
+
"loss": 0.1015,
|
| 542 |
+
"step": 760
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 1.9059405940594059,
|
| 546 |
+
"grad_norm": 0.6170175679054791,
|
| 547 |
+
"learning_rate": 7.083892691736428e-08,
|
| 548 |
+
"loss": 0.1024,
|
| 549 |
+
"step": 770
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.9306930693069306,
|
| 553 |
+
"grad_norm": 0.643468057667551,
|
| 554 |
+
"learning_rate": 3.9210148333763135e-08,
|
| 555 |
+
"loss": 0.0925,
|
| 556 |
+
"step": 780
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.9554455445544554,
|
| 560 |
+
"grad_norm": 0.4524005775955007,
|
| 561 |
+
"learning_rate": 1.684357008110593e-08,
|
| 562 |
+
"loss": 0.0973,
|
| 563 |
+
"step": 790
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.9801980198019802,
|
| 567 |
+
"grad_norm": 0.4828849570873087,
|
| 568 |
+
"learning_rate": 3.780952390058379e-09,
|
| 569 |
+
"loss": 0.0901,
|
| 570 |
+
"step": 800
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 2.0,
|
| 574 |
+
"step": 808,
|
| 575 |
+
"total_flos": 1.995296975397847e+17,
|
| 576 |
+
"train_loss": 0.15181401895709556,
|
| 577 |
+
"train_runtime": 29257.7471,
|
| 578 |
+
"train_samples_per_second": 0.221,
|
| 579 |
+
"train_steps_per_second": 0.028
|
| 580 |
+
}
|
| 581 |
+
],
|
| 582 |
+
"logging_steps": 10,
|
| 583 |
+
"max_steps": 808,
|
| 584 |
+
"num_input_tokens_seen": 0,
|
| 585 |
+
"num_train_epochs": 2,
|
| 586 |
+
"save_steps": 200,
|
| 587 |
+
"stateful_callbacks": {
|
| 588 |
+
"TrainerControl": {
|
| 589 |
+
"args": {
|
| 590 |
+
"should_epoch_stop": false,
|
| 591 |
+
"should_evaluate": false,
|
| 592 |
+
"should_log": false,
|
| 593 |
+
"should_save": true,
|
| 594 |
+
"should_training_stop": true
|
| 595 |
+
},
|
| 596 |
+
"attributes": {}
|
| 597 |
+
}
|
| 598 |
+
},
|
| 599 |
+
"total_flos": 1.995296975397847e+17,
|
| 600 |
+
"train_batch_size": 1,
|
| 601 |
+
"trial_name": null,
|
| 602 |
+
"trial_params": null
|
| 603 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:32068f93dc6f578d4398096b69773f0c43c71045e13a3d8361bdbb741ebdc0ea
|
| 3 |
+
size 8337
|
training_loss.png
ADDED
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|