Hugging Face's logo

romilshah16
/
VILA-2.7b

Text Generation
Transformers
Safetensors
llava_llama
VILA
VLM
Inference Endpoints
Model card Files Community
romilshah16 commited on
Commit
5d64586
•
1 Parent(s): 6819c8c

Initial Commit

Browse files
Files changed (10) hide show
  1. README.md +56 -0
  2. config.json +43 -0
  3. generation_config.json +7 -0
  4. gitattributes.txt +35 -0
  5. model.safetensors.index.json +693 -0
  6. special_tokens_map.json +24 -0
  7. tokenizer.model +3 -0
  8. tokenizer_config.json +43 -0
  9. trainer_state.json +3719 -0
  10. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-4.0
3
+ library_name: transformers
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - VILA
7
+ - VLM
8
+ ---
9
+
10
+ # VILA Model Card
11
+
12
+ ## Model details
13
+
14
+ **Model type:**
15
+ VILA is a visual language model (VLM) pretrained with interleaved image-text data at scale, enabling multi-image VLM. VILA is deployable on the edge, including Jetson Orin and laptop by AWQ 4bit quantization through TinyChat framework. We find: (1) image-text pairs are not enough, interleaved image-text is essential; (2) unfreezing LLM during interleaved image-text pre-training enables in-context learning; (3)re-blending text-only instruction data is crucial to boost both VLM and text-only performance. VILA unveils appealing capabilities, including: multi-image reasoning, in-context learning, visual chain-of-thought, and better world knowledge.
16
+
17
+ **Model date:**
18
+ VILA-2.7b was trained in Feb 2024.
19
+
20
+ **Paper or resources for more information:**
21
+ https://github.com/Efficient-Large-Model/VILA
22
+
23
+ ```
24
+ @misc{lin2023vila,
25
+ title={VILA: On Pre-training for Visual Language Models},
26
+ author={Ji Lin and Hongxu Yin and Wei Ping and Yao Lu and Pavlo Molchanov and Andrew Tao and Huizi Mao and Jan Kautz and Mohammad Shoeybi and Song Han},
27
+ year={2023},
28
+ eprint={2312.07533},
29
+ archivePrefix={arXiv},
30
+ primaryClass={cs.CV}
31
+ }
32
+ ```
33
+
34
+ ## License
35
+ - The code is released under the Apache 2.0 license as found in the [LICENSE](./LICENSE) file.
36
+ - The pretrained weights are released under the [CC-BY-NC-SA-4.0 license](https://creativecommons.org/licenses/by-nc-sa/4.0/deed.en).
37
+ - The service is a research preview intended for non-commercial use only, and is subject to the following licenses and terms:
38
+ - [Model License](https://github.com/facebookresearch/llama/blob/main/MODEL_CARD.md) of LLaMA
39
+ - [Terms of Use](https://openai.com/policies/terms-of-use) of the data generated by OpenAI
40
+ - [Dataset Licenses](https://github.com/Efficient-Large-Model/VILA/blob/main/data_prepare/LICENSE) for each one used during training.
41
+
42
+ **Where to send questions or comments about the model:**
43
+ https://github.com/Efficient-Large-Model/VILA/issues
44
+
45
+ ## Intended use
46
+ **Primary intended uses:**
47
+ The primary use of VILA is research on large multimodal models and chatbots.
48
+
49
+ **Primary intended users:**
50
+ The primary intended users of the model are researchers and hobbyists in computer vision, natural language processing, machine learning, and artificial intelligence.
51
+
52
+ ## Training dataset
53
+ See [Dataset Preparation](https://github.com/Efficient-Large-Model/VILA/blob/main/data_prepare/README.md) for more details.
54
+
55
+ ## Evaluation dataset
56
+ A collection of 12 benchmarks, including 5 academic VQA benchmarks and 7 recent benchmarks specifically proposed for instruction-following LMMs.
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./checkpoints/vila-sheared-llama-2.7b-256gpus-mmc4-coyo",
3
+ "architectures": [
4
+ "LlavaLlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "freeze_mm_mlp_adapter": false,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 2560,
13
+ "image_aspect_ratio": "pad",
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 6912,
16
+ "max_position_embeddings": 4096,
17
+ "mm_hidden_size": 1024,
18
+ "mm_projector_lr": null,
19
+ "mm_projector_type": "mlp2x_gelu",
20
+ "mm_use_im_patch_token": false,
21
+ "mm_use_im_start_end": false,
22
+ "mm_vision_select_feature": "patch",
23
+ "mm_vision_select_layer": -2,
24
+ "mm_vision_tower": "openai/clip-vit-large-patch14-336",
25
+ "model_type": "llava_llama",
26
+ "num_attention_heads": 20,
27
+ "num_hidden_layers": 32,
28
+ "num_key_value_heads": 20,
29
+ "pad_token_id": 0,
30
+ "pretraining_tp": 1,
31
+ "rms_norm_eps": 1e-05,
32
+ "rope_scaling": null,
33
+ "rope_theta": 10000.0,
34
+ "tie_word_embeddings": false,
35
+ "tokenizer_model_max_length": 4096,
36
+ "tokenizer_padding_side": "right",
37
+ "torch_dtype": "bfloat16",
38
+ "transformers_version": "4.38.1",
39
+ "tune_mm_mlp_adapter": false,
40
+ "use_cache": true,
41
+ "use_mm_proj": true,
42
+ "vocab_size": 32000
43
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.38.1"
7
+ }
gitattributes.txt ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
model.safetensors.index.json ADDED
@@ -0,0 +1,693 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 6028495872
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00002-of-00002.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
296
+ "model.mm_projector.0.bias": "model-00002-of-00002.safetensors",
297
+ "model.mm_projector.0.weight": "model-00002-of-00002.safetensors",
298
+ "model.mm_projector.2.bias": "model-00002-of-00002.safetensors",
299
+ "model.mm_projector.2.weight": "model-00002-of-00002.safetensors",
300
+ "model.norm.weight": "model-00002-of-00002.safetensors",
301
+ "model.vision_tower.vision_tower.vision_model.embeddings.class_embedding": "model-00002-of-00002.safetensors",
302
+ "model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00002-of-00002.safetensors",
303
+ "model.vision_tower.vision_tower.vision_model.embeddings.position_embedding.weight": "model-00002-of-00002.safetensors",
304
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00002-of-00002.safetensors",
305
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00002-of-00002.safetensors",
306
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00002-of-00002.safetensors",
307
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00002-of-00002.safetensors",
308
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00002-of-00002.safetensors",
309
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00002-of-00002.safetensors",
310
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00002-of-00002.safetensors",
311
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00002-of-00002.safetensors",
312
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
313
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
314
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
315
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
316
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
317
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
318
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
319
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
320
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00002-of-00002.safetensors",
321
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00002-of-00002.safetensors",
322
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00002-of-00002.safetensors",
323
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00002-of-00002.safetensors",
324
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00002-of-00002.safetensors",
325
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00002-of-00002.safetensors",
326
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00002-of-00002.safetensors",
327
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00002-of-00002.safetensors",
328
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
329
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
330
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
331
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
332
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
333
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
334
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
335
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
336
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00002-of-00002.safetensors",
337
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00002-of-00002.safetensors",
338
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00002-of-00002.safetensors",
339
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00002-of-00002.safetensors",
340
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00002-of-00002.safetensors",
341
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00002-of-00002.safetensors",
342
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00002-of-00002.safetensors",
343
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00002-of-00002.safetensors",
344
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
345
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
346
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
347
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
348
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
349
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
350
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
351
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
352
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00002-of-00002.safetensors",
353
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00002-of-00002.safetensors",
354
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00002-of-00002.safetensors",
355
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00002-of-00002.safetensors",
356
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00002-of-00002.safetensors",
357
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00002-of-00002.safetensors",
358
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00002-of-00002.safetensors",
359
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00002-of-00002.safetensors",
360
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
361
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
362
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
363
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
364
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
365
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
366
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
367
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
368
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00002-of-00002.safetensors",
369
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00002-of-00002.safetensors",
370
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00002-of-00002.safetensors",
371
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00002-of-00002.safetensors",
372
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00002-of-00002.safetensors",
373
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00002-of-00002.safetensors",
374
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00002-of-00002.safetensors",
375
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00002-of-00002.safetensors",
376
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
377
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
378
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
379
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
380
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
381
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
382
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
383
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
384
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00002-of-00002.safetensors",
385
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00002-of-00002.safetensors",
386
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00002-of-00002.safetensors",
387
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00002-of-00002.safetensors",
388
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00002-of-00002.safetensors",
389
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00002-of-00002.safetensors",
390
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00002-of-00002.safetensors",
391
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00002-of-00002.safetensors",
392
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
393
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
394
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
395
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
396
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
397
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
398
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
399
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
400
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00002-of-00002.safetensors",
401
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00002-of-00002.safetensors",
402
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00002-of-00002.safetensors",
403
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00002-of-00002.safetensors",
404
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00002-of-00002.safetensors",
405
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00002-of-00002.safetensors",
406
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00002-of-00002.safetensors",
407
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00002-of-00002.safetensors",
408
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
409
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
410
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
411
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
412
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
413
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
414
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
415
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
416
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00002-of-00002.safetensors",
417
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00002-of-00002.safetensors",
418
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00002-of-00002.safetensors",
419
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00002-of-00002.safetensors",
420
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00002-of-00002.safetensors",
421
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00002-of-00002.safetensors",
422
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00002-of-00002.safetensors",
423
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00002-of-00002.safetensors",
424
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
425
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
426
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
427
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
428
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
429
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
430
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
431
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
432
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00002-of-00002.safetensors",
433
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00002-of-00002.safetensors",
434
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00002-of-00002.safetensors",
435
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00002-of-00002.safetensors",
436
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00002-of-00002.safetensors",
437
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00002-of-00002.safetensors",
438
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00002-of-00002.safetensors",
439
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00002-of-00002.safetensors",
440
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
441
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
442
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
443
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
444
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
445
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
446
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
447
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
448
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00002-of-00002.safetensors",
449
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00002-of-00002.safetensors",
450
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00002-of-00002.safetensors",
451
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00002-of-00002.safetensors",
452
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00002-of-00002.safetensors",
453
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00002-of-00002.safetensors",
454
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00002-of-00002.safetensors",
455
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00002-of-00002.safetensors",
456
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
457
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
458
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
459
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
460
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
461
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
462
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
463
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
464
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00002-of-00002.safetensors",
465
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00002-of-00002.safetensors",
466
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00002-of-00002.safetensors",
467
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00002-of-00002.safetensors",
468
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00002-of-00002.safetensors",
469
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00002-of-00002.safetensors",
470
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00002-of-00002.safetensors",
471
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00002-of-00002.safetensors",
472
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
473
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
474
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
475
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
476
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
477
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
478
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
479
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
480
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00002-of-00002.safetensors",
481
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00002-of-00002.safetensors",
482
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00002-of-00002.safetensors",
483
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00002-of-00002.safetensors",
484
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00002-of-00002.safetensors",
485
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00002-of-00002.safetensors",
486
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00002-of-00002.safetensors",
487
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00002-of-00002.safetensors",
488
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
489
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
490
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
491
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
492
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
493
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
494
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
495
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
496
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00002-of-00002.safetensors",
497
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00002-of-00002.safetensors",
498
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00002-of-00002.safetensors",
499
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00002-of-00002.safetensors",
500
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00002-of-00002.safetensors",
501
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00002-of-00002.safetensors",
502
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00002-of-00002.safetensors",
503
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00002-of-00002.safetensors",
504
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
505
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
506
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
507
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
508
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
509
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
510
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
511
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
512
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00002-of-00002.safetensors",
513
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00002-of-00002.safetensors",
514
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00002-of-00002.safetensors",
515
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00002-of-00002.safetensors",
516
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00002-of-00002.safetensors",
517
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00002-of-00002.safetensors",
518
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00002-of-00002.safetensors",
519
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00002-of-00002.safetensors",
520
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
521
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
522
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
523
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
524
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
525
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
526
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
527
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
528
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00002-of-00002.safetensors",
529
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00002-of-00002.safetensors",
530
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00002-of-00002.safetensors",
531
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00002-of-00002.safetensors",
532
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00002-of-00002.safetensors",
533
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00002-of-00002.safetensors",
534
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00002-of-00002.safetensors",
535
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00002-of-00002.safetensors",
536
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
537
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
538
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
539
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
540
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
541
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
542
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
543
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
544
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00002-of-00002.safetensors",
545
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00002-of-00002.safetensors",
546
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00002-of-00002.safetensors",
547
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00002-of-00002.safetensors",
548
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00002-of-00002.safetensors",
549
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00002-of-00002.safetensors",
550
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00002-of-00002.safetensors",
551
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00002-of-00002.safetensors",
552
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
553
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
554
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
555
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
556
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
557
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
558
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
559
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
560
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00002-of-00002.safetensors",
561
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00002-of-00002.safetensors",
562
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00002-of-00002.safetensors",
563
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00002-of-00002.safetensors",
564
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00002-of-00002.safetensors",
565
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00002-of-00002.safetensors",
566
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00002-of-00002.safetensors",
567
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00002-of-00002.safetensors",
568
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
569
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
570
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
571
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
572
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
573
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
574
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
575
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
576
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00002-of-00002.safetensors",
577
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00002-of-00002.safetensors",
578
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00002-of-00002.safetensors",
579
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00002-of-00002.safetensors",
580
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00002-of-00002.safetensors",
581
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00002-of-00002.safetensors",
582
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00002-of-00002.safetensors",
583
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00002-of-00002.safetensors",
584
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
585
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
586
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
587
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
588
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
589
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
590
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
591
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
592
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00002-of-00002.safetensors",
593
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00002-of-00002.safetensors",
594
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00002-of-00002.safetensors",
595
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00002-of-00002.safetensors",
596
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00002-of-00002.safetensors",
597
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00002-of-00002.safetensors",
598
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00002-of-00002.safetensors",
599
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00002-of-00002.safetensors",
600
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
601
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
602
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
603
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
604
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
605
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
606
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
607
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
608
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00002-of-00002.safetensors",
609
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00002-of-00002.safetensors",
610
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00002-of-00002.safetensors",
611
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00002-of-00002.safetensors",
612
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00002-of-00002.safetensors",
613
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00002-of-00002.safetensors",
614
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00002-of-00002.safetensors",
615
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00002-of-00002.safetensors",
616
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
617
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
618
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
619
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
620
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
621
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
622
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
623
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
624
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00002-of-00002.safetensors",
625
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00002-of-00002.safetensors",
626
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00002-of-00002.safetensors",
627
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00002-of-00002.safetensors",
628
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00002-of-00002.safetensors",
629
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00002-of-00002.safetensors",
630
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00002-of-00002.safetensors",
631
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00002-of-00002.safetensors",
632
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
633
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
634
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
635
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
636
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
637
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
638
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
639
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
640
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00002-of-00002.safetensors",
641
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00002-of-00002.safetensors",
642
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00002-of-00002.safetensors",
643
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00002-of-00002.safetensors",
644
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00002-of-00002.safetensors",
645
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00002-of-00002.safetensors",
646
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00002-of-00002.safetensors",
647
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00002-of-00002.safetensors",
648
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
649
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
650
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
651
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
652
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
653
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
654
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
655
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
656
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00002-of-00002.safetensors",
657
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00002-of-00002.safetensors",
658
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00002-of-00002.safetensors",
659
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00002-of-00002.safetensors",
660
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00002-of-00002.safetensors",
661
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00002-of-00002.safetensors",
662
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00002-of-00002.safetensors",
663
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00002-of-00002.safetensors",
664
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
665
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
666
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
667
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
668
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
669
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
670
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
671
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
672
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00002-of-00002.safetensors",
673
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00002-of-00002.safetensors",
674
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00002-of-00002.safetensors",
675
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00002-of-00002.safetensors",
676
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00002-of-00002.safetensors",
677
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00002-of-00002.safetensors",
678
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00002-of-00002.safetensors",
679
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00002-of-00002.safetensors",
680
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
681
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
682
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
683
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
684
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
685
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
686
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
687
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
688
+ "model.vision_tower.vision_tower.vision_model.post_layernorm.bias": "model-00002-of-00002.safetensors",
689
+ "model.vision_tower.vision_tower.vision_model.post_layernorm.weight": "model-00002-of-00002.safetensors",
690
+ "model.vision_tower.vision_tower.vision_model.pre_layrnorm.bias": "model-00002-of-00002.safetensors",
691
+ "model.vision_tower.vision_tower.vision_model.pre_layrnorm.weight": "model-00002-of-00002.safetensors"
692
+ }
693
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<unk>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "bos_token": "<s>",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": false,
35
+ "model_max_length": 4096,
36
+ "pad_token": "<unk>",
37
+ "padding_side": "right",
38
+ "sp_model_kwargs": {},
39
+ "spaces_between_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false
43
+ }
trainer_state.json ADDED
@@ -0,0 +1,3719 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 527,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "grad_norm": 18.569529999247134,
14
+ "learning_rate": 6.25e-06,
15
+ "loss": 2.2344,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.0,
20
+ "grad_norm": 17.774880014109563,
21
+ "learning_rate": 1.25e-05,
22
+ "loss": 2.2188,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.01,
27
+ "grad_norm": 16.126910180369833,
28
+ "learning_rate": 1.8750000000000002e-05,
29
+ "loss": 2.0938,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.01,
34
+ "grad_norm": 4.004205399706303,
35
+ "learning_rate": 2.5e-05,
36
+ "loss": 1.5625,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.01,
41
+ "grad_norm": 4.475863116578534,
42
+ "learning_rate": 3.125e-05,
43
+ "loss": 1.5547,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.01,
48
+ "grad_norm": 3.9418457877357183,
49
+ "learning_rate": 3.7500000000000003e-05,
50
+ "loss": 1.5312,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.01,
55
+ "grad_norm": 3.35497476295258,
56
+ "learning_rate": 4.375e-05,
57
+ "loss": 1.5312,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.02,
62
+ "grad_norm": 2.0238486012287824,
63
+ "learning_rate": 5e-05,
64
+ "loss": 1.4453,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.02,
69
+ "grad_norm": 1.3025920158121342,
70
+ "learning_rate": 5.6250000000000005e-05,
71
+ "loss": 1.4062,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.02,
76
+ "grad_norm": 2.1578221590331648,
77
+ "learning_rate": 6.25e-05,
78
+ "loss": 1.4141,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.02,
83
+ "grad_norm": 1.639048247445056,
84
+ "learning_rate": 6.875e-05,
85
+ "loss": 1.3906,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.02,
90
+ "grad_norm": 1.0758955455274364,
91
+ "learning_rate": 7.500000000000001e-05,
92
+ "loss": 1.3672,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.02,
97
+ "grad_norm": 0.9988841624058318,
98
+ "learning_rate": 8.125000000000001e-05,
99
+ "loss": 1.3516,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.03,
104
+ "grad_norm": 1.036582323851064,
105
+ "learning_rate": 8.75e-05,
106
+ "loss": 1.3438,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.03,
111
+ "grad_norm": 1.0040586950026587,
112
+ "learning_rate": 9.375e-05,
113
+ "loss": 1.3438,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.03,
118
+ "grad_norm": 0.8112402128458829,
119
+ "learning_rate": 0.0001,
120
+ "loss": 1.3047,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.03,
125
+ "grad_norm": 0.806608090114202,
126
+ "learning_rate": 9.999905507663936e-05,
127
+ "loss": 1.3203,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.03,
132
+ "grad_norm": 0.8164159045230494,
133
+ "learning_rate": 9.99962203422726e-05,
134
+ "loss": 1.2812,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.04,
139
+ "grad_norm": 0.7335139492736167,
140
+ "learning_rate": 9.9991495904044e-05,
141
+ "loss": 1.2969,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.04,
146
+ "grad_norm": 0.799772371827826,
147
+ "learning_rate": 9.998488194052287e-05,
148
+ "loss": 1.2734,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.04,
153
+ "grad_norm": 0.6718755777667486,
154
+ "learning_rate": 9.997637870169672e-05,
155
+ "loss": 1.2734,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.04,
160
+ "grad_norm": 0.7599864750693303,
161
+ "learning_rate": 9.996598650896192e-05,
162
+ "loss": 1.2578,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.04,
167
+ "grad_norm": 0.6886726902695142,
168
+ "learning_rate": 9.995370575511151e-05,
169
+ "loss": 1.2656,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.05,
174
+ "grad_norm": 0.6823417918062775,
175
+ "learning_rate": 9.993953690432031e-05,
176
+ "loss": 1.2734,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.05,
181
+ "grad_norm": 0.6382222948594751,
182
+ "learning_rate": 9.99234804921275e-05,
183
+ "loss": 1.2422,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.05,
188
+ "grad_norm": 0.6452753693126838,
189
+ "learning_rate": 9.990553712541617e-05,
190
+ "loss": 1.2422,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.05,
195
+ "grad_norm": 0.5904936283655213,
196
+ "learning_rate": 9.988570748239062e-05,
197
+ "loss": 1.2266,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.05,
202
+ "grad_norm": 0.5640365175871925,
203
+ "learning_rate": 9.986399231255056e-05,
204
+ "loss": 1.2031,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.06,
209
+ "grad_norm": 0.514358456822939,
210
+ "learning_rate": 9.984039243666283e-05,
211
+ "loss": 1.2344,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.06,
216
+ "grad_norm": 0.636209974460906,
217
+ "learning_rate": 9.981490874673039e-05,
218
+ "loss": 1.1953,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.06,
223
+ "grad_norm": 0.5479990507502773,
224
+ "learning_rate": 9.978754220595861e-05,
225
+ "loss": 1.2031,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.06,
230
+ "grad_norm": 0.5561261900343224,
231
+ "learning_rate": 9.975829384871884e-05,
232
+ "loss": 1.2344,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.06,
237
+ "grad_norm": 0.4948569883144301,
238
+ "learning_rate": 9.97271647805093e-05,
239
+ "loss": 1.2109,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.06,
244
+ "grad_norm": 0.5167119119909488,
245
+ "learning_rate": 9.969415617791336e-05,
246
+ "loss": 1.2266,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.07,
251
+ "grad_norm": 0.508354119180698,
252
+ "learning_rate": 9.965926928855499e-05,
253
+ "loss": 1.2109,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.07,
258
+ "grad_norm": 0.5326133584880987,
259
+ "learning_rate": 9.962250543105167e-05,
260
+ "loss": 1.1797,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.07,
265
+ "grad_norm": 0.47996354720772333,
266
+ "learning_rate": 9.95838659949645e-05,
267
+ "loss": 1.1719,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.07,
272
+ "grad_norm": 0.4584403899961059,
273
+ "learning_rate": 9.954335244074574e-05,
274
+ "loss": 1.1797,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.07,
279
+ "grad_norm": 0.478024134726985,
280
+ "learning_rate": 9.950096629968352e-05,
281
+ "loss": 1.1953,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.08,
286
+ "grad_norm": 0.4831225145909792,
287
+ "learning_rate": 9.945670917384403e-05,
288
+ "loss": 1.1797,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.08,
293
+ "grad_norm": 0.47054504799219404,
294
+ "learning_rate": 9.941058273601096e-05,
295
+ "loss": 1.1719,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.08,
300
+ "grad_norm": 0.4940788339187542,
301
+ "learning_rate": 9.936258872962228e-05,
302
+ "loss": 1.1719,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.08,
307
+ "grad_norm": 0.44655071198353546,
308
+ "learning_rate": 9.931272896870426e-05,
309
+ "loss": 1.1953,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.08,
314
+ "grad_norm": 0.4620978351861828,
315
+ "learning_rate": 9.926100533780303e-05,
316
+ "loss": 1.1797,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.09,
321
+ "grad_norm": 0.4777738095085538,
322
+ "learning_rate": 9.920741979191331e-05,
323
+ "loss": 1.1641,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.09,
328
+ "grad_norm": 0.46687195896903444,
329
+ "learning_rate": 9.91519743564044e-05,
330
+ "loss": 1.1562,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.09,
335
+ "grad_norm": 0.4572029233269296,
336
+ "learning_rate": 9.909467112694384e-05,
337
+ "loss": 1.1719,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.09,
342
+ "grad_norm": 0.4379619610466461,
343
+ "learning_rate": 9.903551226941801e-05,
344
+ "loss": 1.1562,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.09,
349
+ "grad_norm": 0.4625672515990539,
350
+ "learning_rate": 9.897450001985039e-05,
351
+ "loss": 1.1406,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.09,
356
+ "grad_norm": 0.45763509639124433,
357
+ "learning_rate": 9.891163668431695e-05,
358
+ "loss": 1.1719,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.1,
363
+ "grad_norm": 0.4759593297993926,
364
+ "learning_rate": 9.88469246388591e-05,
365
+ "loss": 1.1484,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.1,
370
+ "grad_norm": 0.47690674058291993,
371
+ "learning_rate": 9.878036632939374e-05,
372
+ "loss": 1.2031,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.1,
377
+ "grad_norm": 0.44532349751989236,
378
+ "learning_rate": 9.871196427162092e-05,
379
+ "loss": 1.1172,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.1,
384
+ "grad_norm": 0.452106382176349,
385
+ "learning_rate": 9.86417210509288e-05,
386
+ "loss": 1.1094,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.1,
391
+ "grad_norm": 0.452753191760464,
392
+ "learning_rate": 9.85696393222957e-05,
393
+ "loss": 1.1953,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.11,
398
+ "grad_norm": 0.45441530517528445,
399
+ "learning_rate": 9.849572181019007e-05,
400
+ "loss": 1.1406,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 0.11,
405
+ "grad_norm": 0.5007896403646297,
406
+ "learning_rate": 9.84199713084672e-05,
407
+ "loss": 1.1406,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 0.11,
412
+ "grad_norm": 0.4608644722591853,
413
+ "learning_rate": 9.834239068026387e-05,
414
+ "loss": 1.1328,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 0.11,
419
+ "grad_norm": 0.4968111745587068,
420
+ "learning_rate": 9.826298285789002e-05,
421
+ "loss": 1.1328,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 0.11,
426
+ "grad_norm": 0.44573050581792,
427
+ "learning_rate": 9.818175084271786e-05,
428
+ "loss": 1.125,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 0.12,
433
+ "grad_norm": 0.46589557608902915,
434
+ "learning_rate": 9.809869770506856e-05,
435
+ "loss": 1.1328,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 0.12,
440
+ "grad_norm": 0.45678602237538535,
441
+ "learning_rate": 9.80138265840961e-05,
442
+ "loss": 1.1328,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 0.12,
447
+ "grad_norm": 0.43959375518292026,
448
+ "learning_rate": 9.792714068766872e-05,
449
+ "loss": 1.125,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 0.12,
454
+ "grad_norm": 0.41984631355693813,
455
+ "learning_rate": 9.783864329224752e-05,
456
+ "loss": 1.1406,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 0.12,
461
+ "grad_norm": 0.43389373514903795,
462
+ "learning_rate": 9.774833774276278e-05,
463
+ "loss": 1.1172,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 0.13,
468
+ "grad_norm": 0.4336892341975021,
469
+ "learning_rate": 9.765622745248739e-05,
470
+ "loss": 1.1406,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 0.13,
475
+ "grad_norm": 0.4410380396458464,
476
+ "learning_rate": 9.7562315902908e-05,
477
+ "loss": 1.1172,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 0.13,
482
+ "grad_norm": 0.5141753129119535,
483
+ "learning_rate": 9.746660664359326e-05,
484
+ "loss": 1.1172,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 0.13,
489
+ "grad_norm": 0.46159702650365997,
490
+ "learning_rate": 9.736910329205978e-05,
491
+ "loss": 1.1328,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 0.13,
496
+ "grad_norm": 0.45575998013176866,
497
+ "learning_rate": 9.726980953363536e-05,
498
+ "loss": 1.1328,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 0.13,
503
+ "grad_norm": 0.4458400134106401,
504
+ "learning_rate": 9.716872912131964e-05,
505
+ "loss": 1.1172,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 0.14,
510
+ "grad_norm": 0.4403442516042718,
511
+ "learning_rate": 9.706586587564237e-05,
512
+ "loss": 1.1406,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 0.14,
517
+ "grad_norm": 0.4513799624319814,
518
+ "learning_rate": 9.696122368451886e-05,
519
+ "loss": 1.1406,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 0.14,
524
+ "grad_norm": 0.4348698465314392,
525
+ "learning_rate": 9.685480650310318e-05,
526
+ "loss": 1.1641,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 0.14,
531
+ "grad_norm": 0.4498345537005005,
532
+ "learning_rate": 9.674661835363858e-05,
533
+ "loss": 1.125,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 0.14,
538
+ "grad_norm": 0.43144309981302603,
539
+ "learning_rate": 9.663666332530541e-05,
540
+ "loss": 1.1172,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 0.15,
545
+ "grad_norm": 0.4399921408069473,
546
+ "learning_rate": 9.652494557406666e-05,
547
+ "loss": 1.125,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 0.15,
552
+ "grad_norm": 0.47704120684842194,
553
+ "learning_rate": 9.641146932251089e-05,
554
+ "loss": 1.1328,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 0.15,
559
+ "grad_norm": 0.44749472258572454,
560
+ "learning_rate": 9.62962388596925e-05,
561
+ "loss": 1.1406,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 0.15,
566
+ "grad_norm": 0.4413794417064817,
567
+ "learning_rate": 9.617925854096975e-05,
568
+ "loss": 1.1406,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 0.15,
573
+ "grad_norm": 0.42859705779561913,
574
+ "learning_rate": 9.606053278784009e-05,
575
+ "loss": 1.1172,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 0.16,
580
+ "grad_norm": 0.45418306254807467,
581
+ "learning_rate": 9.5940066087773e-05,
582
+ "loss": 1.1016,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 0.16,
587
+ "grad_norm": 0.43688517954319694,
588
+ "learning_rate": 9.581786299404045e-05,
589
+ "loss": 1.1172,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 0.16,
594
+ "grad_norm": 0.4397567687148274,
595
+ "learning_rate": 9.569392812554478e-05,
596
+ "loss": 1.1172,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 0.16,
601
+ "grad_norm": 0.46690101219263686,
602
+ "learning_rate": 9.556826616664407e-05,
603
+ "loss": 1.1328,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 0.16,
608
+ "grad_norm": 0.4756162905348212,
609
+ "learning_rate": 9.544088186697515e-05,
610
+ "loss": 1.1172,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 0.17,
615
+ "grad_norm": 0.4366895335330985,
616
+ "learning_rate": 9.531178004127403e-05,
617
+ "loss": 1.1172,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 0.17,
622
+ "grad_norm": 0.46048461137548086,
623
+ "learning_rate": 9.518096556919396e-05,
624
+ "loss": 1.125,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 0.17,
629
+ "grad_norm": 0.45095033069608803,
630
+ "learning_rate": 9.504844339512095e-05,
631
+ "loss": 1.1016,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 0.17,
636
+ "grad_norm": 0.440538034417393,
637
+ "learning_rate": 9.491421852798696e-05,
638
+ "loss": 1.1016,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 0.17,
643
+ "grad_norm": 0.4472029761648666,
644
+ "learning_rate": 9.477829604108044e-05,
645
+ "loss": 1.0938,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 0.17,
650
+ "grad_norm": 0.4369667303362839,
651
+ "learning_rate": 9.464068107185476e-05,
652
+ "loss": 1.0781,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 0.18,
657
+ "grad_norm": 0.5249913549114,
658
+ "learning_rate": 9.450137882173384e-05,
659
+ "loss": 1.0703,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 0.18,
664
+ "grad_norm": 0.4465738523446084,
665
+ "learning_rate": 9.436039455591573e-05,
666
+ "loss": 1.0859,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 0.18,
671
+ "grad_norm": 0.43766479595594365,
672
+ "learning_rate": 9.421773360317347e-05,
673
+ "loss": 1.1016,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 0.18,
678
+ "grad_norm": 0.4240043286719592,
679
+ "learning_rate": 9.407340135565374e-05,
680
+ "loss": 1.0938,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 0.18,
685
+ "grad_norm": 0.42744921800889424,
686
+ "learning_rate": 9.392740326867304e-05,
687
+ "loss": 1.1172,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 0.19,
692
+ "grad_norm": 0.458478203908347,
693
+ "learning_rate": 9.377974486051147e-05,
694
+ "loss": 1.1172,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 0.19,
699
+ "grad_norm": 0.4320194692065847,
700
+ "learning_rate": 9.363043171220423e-05,
701
+ "loss": 1.0859,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 0.19,
706
+ "grad_norm": 0.42941401875819113,
707
+ "learning_rate": 9.347946946733055e-05,
708
+ "loss": 1.0938,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 0.19,
713
+ "grad_norm": 0.4345817070644086,
714
+ "learning_rate": 9.332686383180055e-05,
715
+ "loss": 1.0781,
716
+ "step": 101
717
+ },
718
+ {
719
+ "epoch": 0.19,
720
+ "grad_norm": 0.42729040555243186,
721
+ "learning_rate": 9.31726205736394e-05,
722
+ "loss": 1.1094,
723
+ "step": 102
724
+ },
725
+ {
726
+ "epoch": 0.2,
727
+ "grad_norm": 0.4676759430208925,
728
+ "learning_rate": 9.301674552276942e-05,
729
+ "loss": 1.0859,
730
+ "step": 103
731
+ },
732
+ {
733
+ "epoch": 0.2,
734
+ "grad_norm": 0.437120596292176,
735
+ "learning_rate": 9.28592445707897e-05,
736
+ "loss": 1.1094,
737
+ "step": 104
738
+ },
739
+ {
740
+ "epoch": 0.2,
741
+ "grad_norm": 0.44408267981562327,
742
+ "learning_rate": 9.270012367075336e-05,
743
+ "loss": 1.1094,
744
+ "step": 105
745
+ },
746
+ {
747
+ "epoch": 0.2,
748
+ "grad_norm": 0.4408320908096716,
749
+ "learning_rate": 9.253938883694267e-05,
750
+ "loss": 1.0859,
751
+ "step": 106
752
+ },
753
+ {
754
+ "epoch": 0.2,
755
+ "grad_norm": 0.4153884549704849,
756
+ "learning_rate": 9.237704614464156e-05,
757
+ "loss": 1.0781,
758
+ "step": 107
759
+ },
760
+ {
761
+ "epoch": 0.2,
762
+ "grad_norm": 0.44536034771337696,
763
+ "learning_rate": 9.221310172990616e-05,
764
+ "loss": 1.0781,
765
+ "step": 108
766
+ },
767
+ {
768
+ "epoch": 0.21,
769
+ "grad_norm": 0.42677756463500066,
770
+ "learning_rate": 9.204756178933274e-05,
771
+ "loss": 1.0703,
772
+ "step": 109
773
+ },
774
+ {
775
+ "epoch": 0.21,
776
+ "grad_norm": 0.4378028436016707,
777
+ "learning_rate": 9.18804325798236e-05,
778
+ "loss": 1.0938,
779
+ "step": 110
780
+ },
781
+ {
782
+ "epoch": 0.21,
783
+ "grad_norm": 0.42237143257723425,
784
+ "learning_rate": 9.17117204183505e-05,
785
+ "loss": 1.1094,
786
+ "step": 111
787
+ },
788
+ {
789
+ "epoch": 0.21,
790
+ "grad_norm": 0.43243228227443636,
791
+ "learning_rate": 9.154143168171592e-05,
792
+ "loss": 1.0859,
793
+ "step": 112
794
+ },
795
+ {
796
+ "epoch": 0.21,
797
+ "grad_norm": 0.41404933017475487,
798
+ "learning_rate": 9.136957280631212e-05,
799
+ "loss": 1.0938,
800
+ "step": 113
801
+ },
802
+ {
803
+ "epoch": 0.22,
804
+ "grad_norm": 0.4409966487573737,
805
+ "learning_rate": 9.119615028787771e-05,
806
+ "loss": 1.0625,
807
+ "step": 114
808
+ },
809
+ {
810
+ "epoch": 0.22,
811
+ "grad_norm": 0.40666941809648666,
812
+ "learning_rate": 9.102117068125226e-05,
813
+ "loss": 1.0703,
814
+ "step": 115
815
+ },
816
+ {
817
+ "epoch": 0.22,
818
+ "grad_norm": 0.4436737155967258,
819
+ "learning_rate": 9.08446406001285e-05,
820
+ "loss": 1.0859,
821
+ "step": 116
822
+ },
823
+ {
824
+ "epoch": 0.22,
825
+ "grad_norm": 0.4274067363700415,
826
+ "learning_rate": 9.06665667168023e-05,
827
+ "loss": 1.0547,
828
+ "step": 117
829
+ },
830
+ {
831
+ "epoch": 0.22,
832
+ "grad_norm": 0.40913040466042055,
833
+ "learning_rate": 9.048695576192058e-05,
834
+ "loss": 1.0625,
835
+ "step": 118
836
+ },
837
+ {
838
+ "epoch": 0.23,
839
+ "grad_norm": 0.4937917107991283,
840
+ "learning_rate": 9.030581452422679e-05,
841
+ "loss": 1.1172,
842
+ "step": 119
843
+ },
844
+ {
845
+ "epoch": 0.23,
846
+ "grad_norm": 0.4404941593953187,
847
+ "learning_rate": 9.012314985030445e-05,
848
+ "loss": 1.0781,
849
+ "step": 120
850
+ },
851
+ {
852
+ "epoch": 0.23,
853
+ "grad_norm": 0.39523077054498146,
854
+ "learning_rate": 8.993896864431826e-05,
855
+ "loss": 1.0625,
856
+ "step": 121
857
+ },
858
+ {
859
+ "epoch": 0.23,
860
+ "grad_norm": 0.4373478392227282,
861
+ "learning_rate": 8.975327786775315e-05,
862
+ "loss": 1.0703,
863
+ "step": 122
864
+ },
865
+ {
866
+ "epoch": 0.23,
867
+ "grad_norm": 0.4577216496829238,
868
+ "learning_rate": 8.956608453915125e-05,
869
+ "loss": 1.1016,
870
+ "step": 123
871
+ },
872
+ {
873
+ "epoch": 0.24,
874
+ "grad_norm": 0.4276538666446135,
875
+ "learning_rate": 8.937739573384653e-05,
876
+ "loss": 1.0781,
877
+ "step": 124
878
+ },
879
+ {
880
+ "epoch": 0.24,
881
+ "grad_norm": 0.4362035096548072,
882
+ "learning_rate": 8.918721858369738e-05,
883
+ "loss": 1.0703,
884
+ "step": 125
885
+ },
886
+ {
887
+ "epoch": 0.24,
888
+ "grad_norm": 0.4493303937073408,
889
+ "learning_rate": 8.899556027681709e-05,
890
+ "loss": 1.0703,
891
+ "step": 126
892
+ },
893
+ {
894
+ "epoch": 0.24,
895
+ "grad_norm": 0.4434149185545328,
896
+ "learning_rate": 8.880242805730208e-05,
897
+ "loss": 1.0938,
898
+ "step": 127
899
+ },
900
+ {
901
+ "epoch": 0.24,
902
+ "grad_norm": 0.43950175470648284,
903
+ "learning_rate": 8.860782922495822e-05,
904
+ "loss": 1.0703,
905
+ "step": 128
906
+ },
907
+ {
908
+ "epoch": 0.24,
909
+ "grad_norm": 0.426071957636363,
910
+ "learning_rate": 8.841177113502482e-05,
911
+ "loss": 1.0703,
912
+ "step": 129
913
+ },
914
+ {
915
+ "epoch": 0.25,
916
+ "grad_norm": 0.450291923405564,
917
+ "learning_rate": 8.821426119789662e-05,
918
+ "loss": 1.0781,
919
+ "step": 130
920
+ },
921
+ {
922
+ "epoch": 0.25,
923
+ "grad_norm": 0.40557626842779504,
924
+ "learning_rate": 8.801530687884378e-05,
925
+ "loss": 1.0781,
926
+ "step": 131
927
+ },
928
+ {
929
+ "epoch": 0.25,
930
+ "grad_norm": 0.4702580576149972,
931
+ "learning_rate": 8.781491569772966e-05,
932
+ "loss": 1.0547,
933
+ "step": 132
934
+ },
935
+ {
936
+ "epoch": 0.25,
937
+ "grad_norm": 0.44111964762493167,
938
+ "learning_rate": 8.761309522872657e-05,
939
+ "loss": 1.0469,
940
+ "step": 133
941
+ },
942
+ {
943
+ "epoch": 0.25,
944
+ "grad_norm": 0.41670105323821127,
945
+ "learning_rate": 8.740985310002956e-05,
946
+ "loss": 1.0859,
947
+ "step": 134
948
+ },
949
+ {
950
+ "epoch": 0.26,
951
+ "grad_norm": 0.4475226900837088,
952
+ "learning_rate": 8.720519699356804e-05,
953
+ "loss": 1.0859,
954
+ "step": 135
955
+ },
956
+ {
957
+ "epoch": 0.26,
958
+ "grad_norm": 0.43566177490537383,
959
+ "learning_rate": 8.699913464471543e-05,
960
+ "loss": 1.0859,
961
+ "step": 136
962
+ },
963
+ {
964
+ "epoch": 0.26,
965
+ "grad_norm": 0.45325103614908197,
966
+ "learning_rate": 8.679167384199684e-05,
967
+ "loss": 1.0625,
968
+ "step": 137
969
+ },
970
+ {
971
+ "epoch": 0.26,
972
+ "grad_norm": 0.42259820068503184,
973
+ "learning_rate": 8.658282242679461e-05,
974
+ "loss": 1.0859,
975
+ "step": 138
976
+ },
977
+ {
978
+ "epoch": 0.26,
979
+ "grad_norm": 0.42782456224560983,
980
+ "learning_rate": 8.637258829305199e-05,
981
+ "loss": 1.0938,
982
+ "step": 139
983
+ },
984
+ {
985
+ "epoch": 0.27,
986
+ "grad_norm": 0.42070148732795626,
987
+ "learning_rate": 8.616097938697475e-05,
988
+ "loss": 1.0859,
989
+ "step": 140
990
+ },
991
+ {
992
+ "epoch": 0.27,
993
+ "grad_norm": 0.4103382323854611,
994
+ "learning_rate": 8.594800370673083e-05,
995
+ "loss": 1.1016,
996
+ "step": 141
997
+ },
998
+ {
999
+ "epoch": 0.27,
1000
+ "grad_norm": 0.4273680868793077,
1001
+ "learning_rate": 8.573366930214806e-05,
1002
+ "loss": 1.0859,
1003
+ "step": 142
1004
+ },
1005
+ {
1006
+ "epoch": 0.27,
1007
+ "grad_norm": 0.41570068283778067,
1008
+ "learning_rate": 8.551798427440986e-05,
1009
+ "loss": 1.0469,
1010
+ "step": 143
1011
+ },
1012
+ {
1013
+ "epoch": 0.27,
1014
+ "grad_norm": 0.4189560948484794,
1015
+ "learning_rate": 8.53009567757491e-05,
1016
+ "loss": 1.0938,
1017
+ "step": 144
1018
+ },
1019
+ {
1020
+ "epoch": 0.28,
1021
+ "grad_norm": 0.40232705129491403,
1022
+ "learning_rate": 8.50825950091399e-05,
1023
+ "loss": 1.0469,
1024
+ "step": 145
1025
+ },
1026
+ {
1027
+ "epoch": 0.28,
1028
+ "grad_norm": 0.45728641315276936,
1029
+ "learning_rate": 8.486290722798764e-05,
1030
+ "loss": 1.0625,
1031
+ "step": 146
1032
+ },
1033
+ {
1034
+ "epoch": 0.28,
1035
+ "grad_norm": 0.43979948317554834,
1036
+ "learning_rate": 8.464190173581699e-05,
1037
+ "loss": 1.0938,
1038
+ "step": 147
1039
+ },
1040
+ {
1041
+ "epoch": 0.28,
1042
+ "grad_norm": 0.4374598465086451,
1043
+ "learning_rate": 8.441958688595801e-05,
1044
+ "loss": 1.0625,
1045
+ "step": 148
1046
+ },
1047
+ {
1048
+ "epoch": 0.28,
1049
+ "grad_norm": 0.4352920608233416,
1050
+ "learning_rate": 8.419597108123054e-05,
1051
+ "loss": 1.0547,
1052
+ "step": 149
1053
+ },
1054
+ {
1055
+ "epoch": 0.28,
1056
+ "grad_norm": 0.42744190205787813,
1057
+ "learning_rate": 8.397106277362647e-05,
1058
+ "loss": 1.0703,
1059
+ "step": 150
1060
+ },
1061
+ {
1062
+ "epoch": 0.29,
1063
+ "grad_norm": 0.6185631612514999,
1064
+ "learning_rate": 8.374487046399036e-05,
1065
+ "loss": 1.0781,
1066
+ "step": 151
1067
+ },
1068
+ {
1069
+ "epoch": 0.29,
1070
+ "grad_norm": 0.4214859539037842,
1071
+ "learning_rate": 8.35174027016981e-05,
1072
+ "loss": 1.0703,
1073
+ "step": 152
1074
+ },
1075
+ {
1076
+ "epoch": 0.29,
1077
+ "grad_norm": 0.4300234685508506,
1078
+ "learning_rate": 8.328866808433378e-05,
1079
+ "loss": 1.0312,
1080
+ "step": 153
1081
+ },
1082
+ {
1083
+ "epoch": 0.29,
1084
+ "grad_norm": 0.4516779428626118,
1085
+ "learning_rate": 8.305867525736474e-05,
1086
+ "loss": 1.0547,
1087
+ "step": 154
1088
+ },
1089
+ {
1090
+ "epoch": 0.29,
1091
+ "grad_norm": 0.4444842072606281,
1092
+ "learning_rate": 8.282743291381481e-05,
1093
+ "loss": 1.0703,
1094
+ "step": 155
1095
+ },
1096
+ {
1097
+ "epoch": 0.3,
1098
+ "grad_norm": 0.44891341810235713,
1099
+ "learning_rate": 8.259494979393563e-05,
1100
+ "loss": 1.0469,
1101
+ "step": 156
1102
+ },
1103
+ {
1104
+ "epoch": 0.3,
1105
+ "grad_norm": 0.4403106392279916,
1106
+ "learning_rate": 8.236123468487648e-05,
1107
+ "loss": 1.0703,
1108
+ "step": 157
1109
+ },
1110
+ {
1111
+ "epoch": 0.3,
1112
+ "grad_norm": 0.4558686783543436,
1113
+ "learning_rate": 8.212629642035199e-05,
1114
+ "loss": 1.0547,
1115
+ "step": 158
1116
+ },
1117
+ {
1118
+ "epoch": 0.3,
1119
+ "grad_norm": 0.47853095524964395,
1120
+ "learning_rate": 8.189014388030833e-05,
1121
+ "loss": 1.0859,
1122
+ "step": 159
1123
+ },
1124
+ {
1125
+ "epoch": 0.3,
1126
+ "grad_norm": 0.454113313074197,
1127
+ "learning_rate": 8.165278599058761e-05,
1128
+ "loss": 1.0547,
1129
+ "step": 160
1130
+ },
1131
+ {
1132
+ "epoch": 0.31,
1133
+ "grad_norm": 0.4406670018539545,
1134
+ "learning_rate": 8.141423172259038e-05,
1135
+ "loss": 1.0859,
1136
+ "step": 161
1137
+ },
1138
+ {
1139
+ "epoch": 0.31,
1140
+ "grad_norm": 0.434252392773616,
1141
+ "learning_rate": 8.117449009293668e-05,
1142
+ "loss": 1.0547,
1143
+ "step": 162
1144
+ },
1145
+ {
1146
+ "epoch": 0.31,
1147
+ "grad_norm": 0.44488081257640494,
1148
+ "learning_rate": 8.093357016312517e-05,
1149
+ "loss": 1.0703,
1150
+ "step": 163
1151
+ },
1152
+ {
1153
+ "epoch": 0.31,
1154
+ "grad_norm": 0.4291046723882578,
1155
+ "learning_rate": 8.069148103919064e-05,
1156
+ "loss": 1.0703,
1157
+ "step": 164
1158
+ },
1159
+ {
1160
+ "epoch": 0.31,
1161
+ "grad_norm": 0.4701461632642551,
1162
+ "learning_rate": 8.044823187135984e-05,
1163
+ "loss": 1.0703,
1164
+ "step": 165
1165
+ },
1166
+ {
1167
+ "epoch": 0.31,
1168
+ "grad_norm": 0.41504338561910276,
1169
+ "learning_rate": 8.020383185370559e-05,
1170
+ "loss": 1.0469,
1171
+ "step": 166
1172
+ },
1173
+ {
1174
+ "epoch": 0.32,
1175
+ "grad_norm": 0.43178723119245843,
1176
+ "learning_rate": 7.995829022379936e-05,
1177
+ "loss": 1.0703,
1178
+ "step": 167
1179
+ },
1180
+ {
1181
+ "epoch": 0.32,
1182
+ "grad_norm": 0.4204377336860703,
1183
+ "learning_rate": 7.9711616262362e-05,
1184
+ "loss": 1.0547,
1185
+ "step": 168
1186
+ },
1187
+ {
1188
+ "epoch": 0.32,
1189
+ "grad_norm": 0.4407346163963636,
1190
+ "learning_rate": 7.94638192929131e-05,
1191
+ "loss": 1.0703,
1192
+ "step": 169
1193
+ },
1194
+ {
1195
+ "epoch": 0.32,
1196
+ "grad_norm": 0.4264303388977427,
1197
+ "learning_rate": 7.921490868141843e-05,
1198
+ "loss": 1.0391,
1199
+ "step": 170
1200
+ },
1201
+ {
1202
+ "epoch": 0.32,
1203
+ "grad_norm": 0.40640791387915454,
1204
+ "learning_rate": 7.896489383593606e-05,
1205
+ "loss": 1.0,
1206
+ "step": 171
1207
+ },
1208
+ {
1209
+ "epoch": 0.33,
1210
+ "grad_norm": 0.43144011890160755,
1211
+ "learning_rate": 7.871378420626072e-05,
1212
+ "loss": 1.0547,
1213
+ "step": 172
1214
+ },
1215
+ {
1216
+ "epoch": 0.33,
1217
+ "grad_norm": 0.4744375892527014,
1218
+ "learning_rate": 7.84615892835666e-05,
1219
+ "loss": 1.0391,
1220
+ "step": 173
1221
+ },
1222
+ {
1223
+ "epoch": 0.33,
1224
+ "grad_norm": 0.4414917687031027,
1225
+ "learning_rate": 7.820831860004867e-05,
1226
+ "loss": 1.0391,
1227
+ "step": 174
1228
+ },
1229
+ {
1230
+ "epoch": 0.33,
1231
+ "grad_norm": 0.43753081136596556,
1232
+ "learning_rate": 7.795398172856233e-05,
1233
+ "loss": 1.0391,
1234
+ "step": 175
1235
+ },
1236
+ {
1237
+ "epoch": 0.33,
1238
+ "grad_norm": 0.44688090549658416,
1239
+ "learning_rate": 7.769858828226164e-05,
1240
+ "loss": 1.0859,
1241
+ "step": 176
1242
+ },
1243
+ {
1244
+ "epoch": 0.34,
1245
+ "grad_norm": 0.4324472242080182,
1246
+ "learning_rate": 7.744214791423596e-05,
1247
+ "loss": 1.0781,
1248
+ "step": 177
1249
+ },
1250
+ {
1251
+ "epoch": 0.34,
1252
+ "grad_norm": 0.39471909710720243,
1253
+ "learning_rate": 7.718467031714506e-05,
1254
+ "loss": 1.0938,
1255
+ "step": 178
1256
+ },
1257
+ {
1258
+ "epoch": 0.34,
1259
+ "grad_norm": 0.42273379977293096,
1260
+ "learning_rate": 7.692616522285278e-05,
1261
+ "loss": 1.0703,
1262
+ "step": 179
1263
+ },
1264
+ {
1265
+ "epoch": 0.34,
1266
+ "grad_norm": 0.41049110470779143,
1267
+ "learning_rate": 7.666664240205922e-05,
1268
+ "loss": 1.0469,
1269
+ "step": 180
1270
+ },
1271
+ {
1272
+ "epoch": 0.34,
1273
+ "grad_norm": 0.4309053261577172,
1274
+ "learning_rate": 7.640611166393141e-05,
1275
+ "loss": 1.0547,
1276
+ "step": 181
1277
+ },
1278
+ {
1279
+ "epoch": 0.35,
1280
+ "grad_norm": 0.4297343270635459,
1281
+ "learning_rate": 7.614458285573261e-05,
1282
+ "loss": 1.0547,
1283
+ "step": 182
1284
+ },
1285
+ {
1286
+ "epoch": 0.35,
1287
+ "grad_norm": 0.42742054343292596,
1288
+ "learning_rate": 7.588206586245002e-05,
1289
+ "loss": 1.0469,
1290
+ "step": 183
1291
+ },
1292
+ {
1293
+ "epoch": 0.35,
1294
+ "grad_norm": 0.4332643732697325,
1295
+ "learning_rate": 7.56185706064212e-05,
1296
+ "loss": 1.0391,
1297
+ "step": 184
1298
+ },
1299
+ {
1300
+ "epoch": 0.35,
1301
+ "grad_norm": 0.42811233809608473,
1302
+ "learning_rate": 7.535410704695906e-05,
1303
+ "loss": 1.0469,
1304
+ "step": 185
1305
+ },
1306
+ {
1307
+ "epoch": 0.35,
1308
+ "grad_norm": 0.4489861675889494,
1309
+ "learning_rate": 7.508868517997544e-05,
1310
+ "loss": 1.0312,
1311
+ "step": 186
1312
+ },
1313
+ {
1314
+ "epoch": 0.35,
1315
+ "grad_norm": 0.4205028088463761,
1316
+ "learning_rate": 7.482231503760325e-05,
1317
+ "loss": 1.0469,
1318
+ "step": 187
1319
+ },
1320
+ {
1321
+ "epoch": 0.36,
1322
+ "grad_norm": 0.41000506415552723,
1323
+ "learning_rate": 7.455500668781726e-05,
1324
+ "loss": 1.0547,
1325
+ "step": 188
1326
+ },
1327
+ {
1328
+ "epoch": 0.36,
1329
+ "grad_norm": 0.41183736439865304,
1330
+ "learning_rate": 7.428677023405366e-05,
1331
+ "loss": 1.0547,
1332
+ "step": 189
1333
+ },
1334
+ {
1335
+ "epoch": 0.36,
1336
+ "grad_norm": 0.4246427305638071,
1337
+ "learning_rate": 7.40176158148281e-05,
1338
+ "loss": 1.0625,
1339
+ "step": 190
1340
+ },
1341
+ {
1342
+ "epoch": 0.36,
1343
+ "grad_norm": 0.43275232447123674,
1344
+ "learning_rate": 7.374755360335253e-05,
1345
+ "loss": 1.0469,
1346
+ "step": 191
1347
+ },
1348
+ {
1349
+ "epoch": 0.36,
1350
+ "grad_norm": 0.42692084681273973,
1351
+ "learning_rate": 7.347659380715061e-05,
1352
+ "loss": 1.0234,
1353
+ "step": 192
1354
+ },
1355
+ {
1356
+ "epoch": 0.37,
1357
+ "grad_norm": 0.4311244552583607,
1358
+ "learning_rate": 7.320474666767201e-05,
1359
+ "loss": 1.0234,
1360
+ "step": 193
1361
+ },
1362
+ {
1363
+ "epoch": 0.37,
1364
+ "grad_norm": 0.42719595530993326,
1365
+ "learning_rate": 7.293202245990526e-05,
1366
+ "loss": 1.0469,
1367
+ "step": 194
1368
+ },
1369
+ {
1370
+ "epoch": 0.37,
1371
+ "grad_norm": 0.4174615425446307,
1372
+ "learning_rate": 7.265843149198931e-05,
1373
+ "loss": 1.0547,
1374
+ "step": 195
1375
+ },
1376
+ {
1377
+ "epoch": 0.37,
1378
+ "grad_norm": 0.42222785480422026,
1379
+ "learning_rate": 7.238398410482408e-05,
1380
+ "loss": 1.0547,
1381
+ "step": 196
1382
+ },
1383
+ {
1384
+ "epoch": 0.37,
1385
+ "grad_norm": 0.4157306068460529,
1386
+ "learning_rate": 7.210869067167942e-05,
1387
+ "loss": 1.0234,
1388
+ "step": 197
1389
+ },
1390
+ {
1391
+ "epoch": 0.38,
1392
+ "grad_norm": 0.4241319467586246,
1393
+ "learning_rate": 7.18325615978032e-05,
1394
+ "loss": 1.0625,
1395
+ "step": 198
1396
+ },
1397
+ {
1398
+ "epoch": 0.38,
1399
+ "grad_norm": 0.4087921332041852,
1400
+ "learning_rate": 7.155560732002791e-05,
1401
+ "loss": 1.0391,
1402
+ "step": 199
1403
+ },
1404
+ {
1405
+ "epoch": 0.38,
1406
+ "grad_norm": 0.426858061802629,
1407
+ "learning_rate": 7.127783830637625e-05,
1408
+ "loss": 1.0469,
1409
+ "step": 200
1410
+ },
1411
+ {
1412
+ "epoch": 0.38,
1413
+ "grad_norm": 0.41722790561085193,
1414
+ "learning_rate": 7.099926505566537e-05,
1415
+ "loss": 1.0469,
1416
+ "step": 201
1417
+ },
1418
+ {
1419
+ "epoch": 0.38,
1420
+ "grad_norm": 0.4199601470491497,
1421
+ "learning_rate": 7.071989809711019e-05,
1422
+ "loss": 1.0547,
1423
+ "step": 202
1424
+ },
1425
+ {
1426
+ "epoch": 0.39,
1427
+ "grad_norm": 0.44231292212761336,
1428
+ "learning_rate": 7.043974798992532e-05,
1429
+ "loss": 1.0547,
1430
+ "step": 203
1431
+ },
1432
+ {
1433
+ "epoch": 0.39,
1434
+ "grad_norm": 0.40964479400554343,
1435
+ "learning_rate": 7.015882532292598e-05,
1436
+ "loss": 1.0547,
1437
+ "step": 204
1438
+ },
1439
+ {
1440
+ "epoch": 0.39,
1441
+ "grad_norm": 0.41103344664490243,
1442
+ "learning_rate": 6.98771407141278e-05,
1443
+ "loss": 1.0391,
1444
+ "step": 205
1445
+ },
1446
+ {
1447
+ "epoch": 0.39,
1448
+ "grad_norm": 0.418536368662017,
1449
+ "learning_rate": 6.959470481034547e-05,
1450
+ "loss": 1.0391,
1451
+ "step": 206
1452
+ },
1453
+ {
1454
+ "epoch": 0.39,
1455
+ "grad_norm": 0.43983351138714233,
1456
+ "learning_rate": 6.931152828679033e-05,
1457
+ "loss": 1.0312,
1458
+ "step": 207
1459
+ },
1460
+ {
1461
+ "epoch": 0.39,
1462
+ "grad_norm": 0.4167726489287608,
1463
+ "learning_rate": 6.902762184666687e-05,
1464
+ "loss": 1.0234,
1465
+ "step": 208
1466
+ },
1467
+ {
1468
+ "epoch": 0.4,
1469
+ "grad_norm": 0.42759288997893236,
1470
+ "learning_rate": 6.874299622076816e-05,
1471
+ "loss": 1.0625,
1472
+ "step": 209
1473
+ },
1474
+ {
1475
+ "epoch": 0.4,
1476
+ "grad_norm": 0.4163882383830232,
1477
+ "learning_rate": 6.845766216707037e-05,
1478
+ "loss": 1.0469,
1479
+ "step": 210
1480
+ },
1481
+ {
1482
+ "epoch": 0.4,
1483
+ "grad_norm": 0.40983190994051244,
1484
+ "learning_rate": 6.817163047032598e-05,
1485
+ "loss": 1.0234,
1486
+ "step": 211
1487
+ },
1488
+ {
1489
+ "epoch": 0.4,
1490
+ "grad_norm": 0.40059171202862986,
1491
+ "learning_rate": 6.78849119416563e-05,
1492
+ "loss": 1.0156,
1493
+ "step": 212
1494
+ },
1495
+ {
1496
+ "epoch": 0.4,
1497
+ "grad_norm": 0.4187064398891471,
1498
+ "learning_rate": 6.759751741814271e-05,
1499
+ "loss": 1.0469,
1500
+ "step": 213
1501
+ },
1502
+ {
1503
+ "epoch": 0.41,
1504
+ "grad_norm": 0.42319499896716717,
1505
+ "learning_rate": 6.730945776241722e-05,
1506
+ "loss": 1.0234,
1507
+ "step": 214
1508
+ },
1509
+ {
1510
+ "epoch": 0.41,
1511
+ "grad_norm": 0.43680930005688956,
1512
+ "learning_rate": 6.702074386225175e-05,
1513
+ "loss": 1.0469,
1514
+ "step": 215
1515
+ },
1516
+ {
1517
+ "epoch": 0.41,
1518
+ "grad_norm": 0.4108033837354488,
1519
+ "learning_rate": 6.67313866301466e-05,
1520
+ "loss": 1.0469,
1521
+ "step": 216
1522
+ },
1523
+ {
1524
+ "epoch": 0.41,
1525
+ "grad_norm": 0.40903728151823127,
1526
+ "learning_rate": 6.644139700291817e-05,
1527
+ "loss": 1.0469,
1528
+ "step": 217
1529
+ },
1530
+ {
1531
+ "epoch": 0.41,
1532
+ "grad_norm": 0.40715077992299514,
1533
+ "learning_rate": 6.615078594128531e-05,
1534
+ "loss": 1.0703,
1535
+ "step": 218
1536
+ },
1537
+ {
1538
+ "epoch": 0.42,
1539
+ "grad_norm": 0.41322957469383936,
1540
+ "learning_rate": 6.585956442945532e-05,
1541
+ "loss": 1.0234,
1542
+ "step": 219
1543
+ },
1544
+ {
1545
+ "epoch": 0.42,
1546
+ "grad_norm": 0.421602554588443,
1547
+ "learning_rate": 6.556774347470855e-05,
1548
+ "loss": 1.0625,
1549
+ "step": 220
1550
+ },
1551
+ {
1552
+ "epoch": 0.42,
1553
+ "grad_norm": 0.4246703826676253,
1554
+ "learning_rate": 6.52753341069825e-05,
1555
+ "loss": 1.0391,
1556
+ "step": 221
1557
+ },
1558
+ {
1559
+ "epoch": 0.42,
1560
+ "grad_norm": 0.4277032038662427,
1561
+ "learning_rate": 6.498234737845488e-05,
1562
+ "loss": 1.0234,
1563
+ "step": 222
1564
+ },
1565
+ {
1566
+ "epoch": 0.42,
1567
+ "grad_norm": 0.40733604211970925,
1568
+ "learning_rate": 6.468879436312584e-05,
1569
+ "loss": 1.0547,
1570
+ "step": 223
1571
+ },
1572
+ {
1573
+ "epoch": 0.43,
1574
+ "grad_norm": 0.41272813606786746,
1575
+ "learning_rate": 6.439468615639946e-05,
1576
+ "loss": 1.0625,
1577
+ "step": 224
1578
+ },
1579
+ {
1580
+ "epoch": 0.43,
1581
+ "grad_norm": 0.40178981821143017,
1582
+ "learning_rate": 6.410003387466433e-05,
1583
+ "loss": 1.0234,
1584
+ "step": 225
1585
+ },
1586
+ {
1587
+ "epoch": 0.43,
1588
+ "grad_norm": 0.4153854554817549,
1589
+ "learning_rate": 6.380484865487347e-05,
1590
+ "loss": 1.0391,
1591
+ "step": 226
1592
+ },
1593
+ {
1594
+ "epoch": 0.43,
1595
+ "grad_norm": 0.40755934293498974,
1596
+ "learning_rate": 6.35091416541232e-05,
1597
+ "loss": 1.0391,
1598
+ "step": 227
1599
+ },
1600
+ {
1601
+ "epoch": 0.43,
1602
+ "grad_norm": 0.41967206872870166,
1603
+ "learning_rate": 6.321292404923167e-05,
1604
+ "loss": 1.0703,
1605
+ "step": 228
1606
+ },
1607
+ {
1608
+ "epoch": 0.43,
1609
+ "grad_norm": 0.4017640092647761,
1610
+ "learning_rate": 6.29162070363163e-05,
1611
+ "loss": 1.0625,
1612
+ "step": 229
1613
+ },
1614
+ {
1615
+ "epoch": 0.44,
1616
+ "grad_norm": 0.39890051372690344,
1617
+ "learning_rate": 6.261900183037052e-05,
1618
+ "loss": 1.0312,
1619
+ "step": 230
1620
+ },
1621
+ {
1622
+ "epoch": 0.44,
1623
+ "grad_norm": 0.4036725539891162,
1624
+ "learning_rate": 6.232131966484006e-05,
1625
+ "loss": 1.0312,
1626
+ "step": 231
1627
+ },
1628
+ {
1629
+ "epoch": 0.44,
1630
+ "grad_norm": 0.4122985901559554,
1631
+ "learning_rate": 6.202317179119817e-05,
1632
+ "loss": 1.0156,
1633
+ "step": 232
1634
+ },
1635
+ {
1636
+ "epoch": 0.44,
1637
+ "grad_norm": 0.4113133842869648,
1638
+ "learning_rate": 6.172456947852049e-05,
1639
+ "loss": 1.0469,
1640
+ "step": 233
1641
+ },
1642
+ {
1643
+ "epoch": 0.44,
1644
+ "grad_norm": 0.4028322239410973,
1645
+ "learning_rate": 6.142552401305906e-05,
1646
+ "loss": 1.0469,
1647
+ "step": 234
1648
+ },
1649
+ {
1650
+ "epoch": 0.45,
1651
+ "grad_norm": 0.4077613734483574,
1652
+ "learning_rate": 6.112604669781572e-05,
1653
+ "loss": 1.0391,
1654
+ "step": 235
1655
+ },
1656
+ {
1657
+ "epoch": 0.45,
1658
+ "grad_norm": 0.40208253242419867,
1659
+ "learning_rate": 6.0826148852114936e-05,
1660
+ "loss": 1.0469,
1661
+ "step": 236
1662
+ },
1663
+ {
1664
+ "epoch": 0.45,
1665
+ "grad_norm": 0.39795754759528085,
1666
+ "learning_rate": 6.052584181117589e-05,
1667
+ "loss": 1.0469,
1668
+ "step": 237
1669
+ },
1670
+ {
1671
+ "epoch": 0.45,
1672
+ "grad_norm": 0.40763706027293223,
1673
+ "learning_rate": 6.022513692568412e-05,
1674
+ "loss": 1.0625,
1675
+ "step": 238
1676
+ },
1677
+ {
1678
+ "epoch": 0.45,
1679
+ "grad_norm": 0.4296039465981587,
1680
+ "learning_rate": 5.9924045561362474e-05,
1681
+ "loss": 1.0391,
1682
+ "step": 239
1683
+ },
1684
+ {
1685
+ "epoch": 0.46,
1686
+ "grad_norm": 0.4070047169709585,
1687
+ "learning_rate": 5.96225790985415e-05,
1688
+ "loss": 1.0547,
1689
+ "step": 240
1690
+ },
1691
+ {
1692
+ "epoch": 0.46,
1693
+ "grad_norm": 0.41013474576772757,
1694
+ "learning_rate": 5.9320748931729344e-05,
1695
+ "loss": 1.0156,
1696
+ "step": 241
1697
+ },
1698
+ {
1699
+ "epoch": 0.46,
1700
+ "grad_norm": 0.40322499716017,
1701
+ "learning_rate": 5.9018566469180994e-05,
1702
+ "loss": 1.0391,
1703
+ "step": 242
1704
+ },
1705
+ {
1706
+ "epoch": 0.46,
1707
+ "grad_norm": 0.3898763992841581,
1708
+ "learning_rate": 5.87160431324672e-05,
1709
+ "loss": 1.0156,
1710
+ "step": 243
1711
+ },
1712
+ {
1713
+ "epoch": 0.46,
1714
+ "grad_norm": 0.42982455700255084,
1715
+ "learning_rate": 5.841319035604267e-05,
1716
+ "loss": 1.0625,
1717
+ "step": 244
1718
+ },
1719
+ {
1720
+ "epoch": 0.46,
1721
+ "grad_norm": 0.4040478163311833,
1722
+ "learning_rate": 5.8110019586813946e-05,
1723
+ "loss": 0.9961,
1724
+ "step": 245
1725
+ },
1726
+ {
1727
+ "epoch": 0.47,
1728
+ "grad_norm": 0.40273222517295776,
1729
+ "learning_rate": 5.780654228370669e-05,
1730
+ "loss": 1.0234,
1731
+ "step": 246
1732
+ },
1733
+ {
1734
+ "epoch": 0.47,
1735
+ "grad_norm": 0.40974932826857524,
1736
+ "learning_rate": 5.7502769917232635e-05,
1737
+ "loss": 1.0156,
1738
+ "step": 247
1739
+ },
1740
+ {
1741
+ "epoch": 0.47,
1742
+ "grad_norm": 0.39928761514091116,
1743
+ "learning_rate": 5.7198713969056026e-05,
1744
+ "loss": 1.0234,
1745
+ "step": 248
1746
+ },
1747
+ {
1748
+ "epoch": 0.47,
1749
+ "grad_norm": 0.41874763062357806,
1750
+ "learning_rate": 5.689438593155956e-05,
1751
+ "loss": 1.0312,
1752
+ "step": 249
1753
+ },
1754
+ {
1755
+ "epoch": 0.47,
1756
+ "grad_norm": 0.4493892592268143,
1757
+ "learning_rate": 5.658979730741014e-05,
1758
+ "loss": 1.0547,
1759
+ "step": 250
1760
+ },
1761
+ {
1762
+ "epoch": 0.48,
1763
+ "grad_norm": 0.40018316116952474,
1764
+ "learning_rate": 5.6284959609124e-05,
1765
+ "loss": 1.0469,
1766
+ "step": 251
1767
+ },
1768
+ {
1769
+ "epoch": 0.48,
1770
+ "grad_norm": 0.43858332707717207,
1771
+ "learning_rate": 5.597988435863166e-05,
1772
+ "loss": 1.0312,
1773
+ "step": 252
1774
+ },
1775
+ {
1776
+ "epoch": 0.48,
1777
+ "grad_norm": 0.40836711063525477,
1778
+ "learning_rate": 5.567458308684232e-05,
1779
+ "loss": 1.0547,
1780
+ "step": 253
1781
+ },
1782
+ {
1783
+ "epoch": 0.48,
1784
+ "grad_norm": 0.42292844222040155,
1785
+ "learning_rate": 5.536906733320816e-05,
1786
+ "loss": 1.0156,
1787
+ "step": 254
1788
+ },
1789
+ {
1790
+ "epoch": 0.48,
1791
+ "grad_norm": 0.41490508684177924,
1792
+ "learning_rate": 5.506334864528808e-05,
1793
+ "loss": 1.0234,
1794
+ "step": 255
1795
+ },
1796
+ {
1797
+ "epoch": 0.49,
1798
+ "grad_norm": 0.4058447957006835,
1799
+ "learning_rate": 5.475743857831127e-05,
1800
+ "loss": 1.0156,
1801
+ "step": 256
1802
+ },
1803
+ {
1804
+ "epoch": 0.49,
1805
+ "grad_norm": 0.4254621460881678,
1806
+ "learning_rate": 5.445134869474049e-05,
1807
+ "loss": 1.0391,
1808
+ "step": 257
1809
+ },
1810
+ {
1811
+ "epoch": 0.49,
1812
+ "grad_norm": 0.4075861687227603,
1813
+ "learning_rate": 5.414509056383498e-05,
1814
+ "loss": 1.0078,
1815
+ "step": 258
1816
+ },
1817
+ {
1818
+ "epoch": 0.49,
1819
+ "grad_norm": 0.40610391261853535,
1820
+ "learning_rate": 5.3838675761213244e-05,
1821
+ "loss": 1.0547,
1822
+ "step": 259
1823
+ },
1824
+ {
1825
+ "epoch": 0.49,
1826
+ "grad_norm": 0.38922815015134116,
1827
+ "learning_rate": 5.3532115868415464e-05,
1828
+ "loss": 1.0078,
1829
+ "step": 260
1830
+ },
1831
+ {
1832
+ "epoch": 0.5,
1833
+ "grad_norm": 0.4046852521792458,
1834
+ "learning_rate": 5.3225422472465824e-05,
1835
+ "loss": 1.0078,
1836
+ "step": 261
1837
+ },
1838
+ {
1839
+ "epoch": 0.5,
1840
+ "grad_norm": 0.40728479784786964,
1841
+ "learning_rate": 5.29186071654345e-05,
1842
+ "loss": 0.9648,
1843
+ "step": 262
1844
+ },
1845
+ {
1846
+ "epoch": 0.5,
1847
+ "grad_norm": 0.41255158343952975,
1848
+ "learning_rate": 5.261168154399952e-05,
1849
+ "loss": 1.0234,
1850
+ "step": 263
1851
+ },
1852
+ {
1853
+ "epoch": 0.5,
1854
+ "grad_norm": 0.4028183441362248,
1855
+ "learning_rate": 5.23046572090085e-05,
1856
+ "loss": 1.0078,
1857
+ "step": 264
1858
+ },
1859
+ {
1860
+ "epoch": 0.5,
1861
+ "grad_norm": 0.40792031816309837,
1862
+ "learning_rate": 5.199754576504006e-05,
1863
+ "loss": 1.0078,
1864
+ "step": 265
1865
+ },
1866
+ {
1867
+ "epoch": 0.5,
1868
+ "grad_norm": 0.4089443562798811,
1869
+ "learning_rate": 5.169035881996533e-05,
1870
+ "loss": 1.0312,
1871
+ "step": 266
1872
+ },
1873
+ {
1874
+ "epoch": 0.51,
1875
+ "grad_norm": 0.40684122314346166,
1876
+ "learning_rate": 5.138310798450912e-05,
1877
+ "loss": 1.0312,
1878
+ "step": 267
1879
+ },
1880
+ {
1881
+ "epoch": 0.51,
1882
+ "grad_norm": 0.40867014012821695,
1883
+ "learning_rate": 5.1075804871811115e-05,
1884
+ "loss": 1.0312,
1885
+ "step": 268
1886
+ },
1887
+ {
1888
+ "epoch": 0.51,
1889
+ "grad_norm": 0.40061062002695064,
1890
+ "learning_rate": 5.076846109698693e-05,
1891
+ "loss": 1.0547,
1892
+ "step": 269
1893
+ },
1894
+ {
1895
+ "epoch": 0.51,
1896
+ "grad_norm": 0.423175226061232,
1897
+ "learning_rate": 5.046108827668903e-05,
1898
+ "loss": 1.0469,
1899
+ "step": 270
1900
+ },
1901
+ {
1902
+ "epoch": 0.51,
1903
+ "grad_norm": 0.3898202650786047,
1904
+ "learning_rate": 5.01536980286678e-05,
1905
+ "loss": 1.0156,
1906
+ "step": 271
1907
+ },
1908
+ {
1909
+ "epoch": 0.52,
1910
+ "grad_norm": 0.411610879755615,
1911
+ "learning_rate": 4.9846301971332234e-05,
1912
+ "loss": 0.9883,
1913
+ "step": 272
1914
+ },
1915
+ {
1916
+ "epoch": 0.52,
1917
+ "grad_norm": 0.39055415860483883,
1918
+ "learning_rate": 4.9538911723310976e-05,
1919
+ "loss": 1.0156,
1920
+ "step": 273
1921
+ },
1922
+ {
1923
+ "epoch": 0.52,
1924
+ "grad_norm": 0.4259500716874186,
1925
+ "learning_rate": 4.92315389030131e-05,
1926
+ "loss": 1.0391,
1927
+ "step": 274
1928
+ },
1929
+ {
1930
+ "epoch": 0.52,
1931
+ "grad_norm": 0.39261415846035824,
1932
+ "learning_rate": 4.892419512818889e-05,
1933
+ "loss": 1.0312,
1934
+ "step": 275
1935
+ },
1936
+ {
1937
+ "epoch": 0.52,
1938
+ "grad_norm": 0.4217477527558212,
1939
+ "learning_rate": 4.86168920154909e-05,
1940
+ "loss": 0.9922,
1941
+ "step": 276
1942
+ },
1943
+ {
1944
+ "epoch": 0.53,
1945
+ "grad_norm": 0.38700415086180145,
1946
+ "learning_rate": 4.830964118003468e-05,
1947
+ "loss": 1.0,
1948
+ "step": 277
1949
+ },
1950
+ {
1951
+ "epoch": 0.53,
1952
+ "grad_norm": 0.40332274074495494,
1953
+ "learning_rate": 4.800245423495997e-05,
1954
+ "loss": 1.0,
1955
+ "step": 278
1956
+ },
1957
+ {
1958
+ "epoch": 0.53,
1959
+ "grad_norm": 0.41396865993704085,
1960
+ "learning_rate": 4.769534279099152e-05,
1961
+ "loss": 1.0078,
1962
+ "step": 279
1963
+ },
1964
+ {
1965
+ "epoch": 0.53,
1966
+ "grad_norm": 0.4041936351639291,
1967
+ "learning_rate": 4.7388318456000496e-05,
1968
+ "loss": 1.0078,
1969
+ "step": 280
1970
+ },
1971
+ {
1972
+ "epoch": 0.53,
1973
+ "grad_norm": 0.4270421784351172,
1974
+ "learning_rate": 4.708139283456551e-05,
1975
+ "loss": 1.0625,
1976
+ "step": 281
1977
+ },
1978
+ {
1979
+ "epoch": 0.54,
1980
+ "grad_norm": 0.4028939120443396,
1981
+ "learning_rate": 4.6774577527534195e-05,
1982
+ "loss": 1.0234,
1983
+ "step": 282
1984
+ },
1985
+ {
1986
+ "epoch": 0.54,
1987
+ "grad_norm": 0.40455125854222046,
1988
+ "learning_rate": 4.646788413158455e-05,
1989
+ "loss": 1.0469,
1990
+ "step": 283
1991
+ },
1992
+ {
1993
+ "epoch": 0.54,
1994
+ "grad_norm": 0.4058895633541385,
1995
+ "learning_rate": 4.616132423878679e-05,
1996
+ "loss": 1.0391,
1997
+ "step": 284
1998
+ },
1999
+ {
2000
+ "epoch": 0.54,
2001
+ "grad_norm": 0.3942526283657809,
2002
+ "learning_rate": 4.585490943616504e-05,
2003
+ "loss": 1.0156,
2004
+ "step": 285
2005
+ },
2006
+ {
2007
+ "epoch": 0.54,
2008
+ "grad_norm": 0.40351277549494935,
2009
+ "learning_rate": 4.554865130525953e-05,
2010
+ "loss": 1.0156,
2011
+ "step": 286
2012
+ },
2013
+ {
2014
+ "epoch": 0.54,
2015
+ "grad_norm": 0.39184809982008023,
2016
+ "learning_rate": 4.524256142168874e-05,
2017
+ "loss": 1.0156,
2018
+ "step": 287
2019
+ },
2020
+ {
2021
+ "epoch": 0.55,
2022
+ "grad_norm": 0.4006543568884177,
2023
+ "learning_rate": 4.4936651354711946e-05,
2024
+ "loss": 0.9727,
2025
+ "step": 288
2026
+ },
2027
+ {
2028
+ "epoch": 0.55,
2029
+ "grad_norm": 0.4256220682218964,
2030
+ "learning_rate": 4.463093266679185e-05,
2031
+ "loss": 1.0156,
2032
+ "step": 289
2033
+ },
2034
+ {
2035
+ "epoch": 0.55,
2036
+ "grad_norm": 0.3959597237885138,
2037
+ "learning_rate": 4.4325416913157704e-05,
2038
+ "loss": 1.0078,
2039
+ "step": 290
2040
+ },
2041
+ {
2042
+ "epoch": 0.55,
2043
+ "grad_norm": 0.4191614983510994,
2044
+ "learning_rate": 4.402011564136836e-05,
2045
+ "loss": 1.0,
2046
+ "step": 291
2047
+ },
2048
+ {
2049
+ "epoch": 0.55,
2050
+ "grad_norm": 0.41102487050201564,
2051
+ "learning_rate": 4.371504039087602e-05,
2052
+ "loss": 1.0156,
2053
+ "step": 292
2054
+ },
2055
+ {
2056
+ "epoch": 0.56,
2057
+ "grad_norm": 0.43350039494098586,
2058
+ "learning_rate": 4.341020269258987e-05,
2059
+ "loss": 1.0078,
2060
+ "step": 293
2061
+ },
2062
+ {
2063
+ "epoch": 0.56,
2064
+ "grad_norm": 0.3956163702456906,
2065
+ "learning_rate": 4.310561406844045e-05,
2066
+ "loss": 1.0078,
2067
+ "step": 294
2068
+ },
2069
+ {
2070
+ "epoch": 0.56,
2071
+ "grad_norm": 0.40529243964979217,
2072
+ "learning_rate": 4.2801286030943985e-05,
2073
+ "loss": 1.0,
2074
+ "step": 295
2075
+ },
2076
+ {
2077
+ "epoch": 0.56,
2078
+ "grad_norm": 0.4184379424977412,
2079
+ "learning_rate": 4.249723008276737e-05,
2080
+ "loss": 1.0078,
2081
+ "step": 296
2082
+ },
2083
+ {
2084
+ "epoch": 0.56,
2085
+ "grad_norm": 0.3971028781090587,
2086
+ "learning_rate": 4.219345771629333e-05,
2087
+ "loss": 1.0156,
2088
+ "step": 297
2089
+ },
2090
+ {
2091
+ "epoch": 0.57,
2092
+ "grad_norm": 0.4124935318732211,
2093
+ "learning_rate": 4.188998041318608e-05,
2094
+ "loss": 1.0078,
2095
+ "step": 298
2096
+ },
2097
+ {
2098
+ "epoch": 0.57,
2099
+ "grad_norm": 0.38790648111231085,
2100
+ "learning_rate": 4.1586809643957345e-05,
2101
+ "loss": 1.0,
2102
+ "step": 299
2103
+ },
2104
+ {
2105
+ "epoch": 0.57,
2106
+ "grad_norm": 0.40687278861829684,
2107
+ "learning_rate": 4.128395686753282e-05,
2108
+ "loss": 1.0312,
2109
+ "step": 300
2110
+ },
2111
+ {
2112
+ "epoch": 0.57,
2113
+ "grad_norm": 0.3842187210077263,
2114
+ "learning_rate": 4.098143353081902e-05,
2115
+ "loss": 1.0078,
2116
+ "step": 301
2117
+ },
2118
+ {
2119
+ "epoch": 0.57,
2120
+ "grad_norm": 0.4023673478113215,
2121
+ "learning_rate": 4.067925106827068e-05,
2122
+ "loss": 1.0156,
2123
+ "step": 302
2124
+ },
2125
+ {
2126
+ "epoch": 0.57,
2127
+ "grad_norm": 0.40540929917797186,
2128
+ "learning_rate": 4.0377420901458506e-05,
2129
+ "loss": 1.0469,
2130
+ "step": 303
2131
+ },
2132
+ {
2133
+ "epoch": 0.58,
2134
+ "grad_norm": 0.3923349737804049,
2135
+ "learning_rate": 4.0075954438637545e-05,
2136
+ "loss": 1.0,
2137
+ "step": 304
2138
+ },
2139
+ {
2140
+ "epoch": 0.58,
2141
+ "grad_norm": 0.41558812455430966,
2142
+ "learning_rate": 3.977486307431589e-05,
2143
+ "loss": 1.0078,
2144
+ "step": 305
2145
+ },
2146
+ {
2147
+ "epoch": 0.58,
2148
+ "grad_norm": 0.40891549560712703,
2149
+ "learning_rate": 3.947415818882414e-05,
2150
+ "loss": 1.0391,
2151
+ "step": 306
2152
+ },
2153
+ {
2154
+ "epoch": 0.58,
2155
+ "grad_norm": 0.38609997258343076,
2156
+ "learning_rate": 3.9173851147885075e-05,
2157
+ "loss": 1.0312,
2158
+ "step": 307
2159
+ },
2160
+ {
2161
+ "epoch": 0.58,
2162
+ "grad_norm": 0.3906811392128105,
2163
+ "learning_rate": 3.887395330218429e-05,
2164
+ "loss": 1.0156,
2165
+ "step": 308
2166
+ },
2167
+ {
2168
+ "epoch": 0.59,
2169
+ "grad_norm": 0.4108545484386376,
2170
+ "learning_rate": 3.857447598694094e-05,
2171
+ "loss": 0.9922,
2172
+ "step": 309
2173
+ },
2174
+ {
2175
+ "epoch": 0.59,
2176
+ "grad_norm": 0.40531422168101394,
2177
+ "learning_rate": 3.827543052147952e-05,
2178
+ "loss": 1.0078,
2179
+ "step": 310
2180
+ },
2181
+ {
2182
+ "epoch": 0.59,
2183
+ "grad_norm": 0.3991587404518294,
2184
+ "learning_rate": 3.797682820880184e-05,
2185
+ "loss": 0.9961,
2186
+ "step": 311
2187
+ },
2188
+ {
2189
+ "epoch": 0.59,
2190
+ "grad_norm": 0.41113645678509786,
2191
+ "learning_rate": 3.7678680335159954e-05,
2192
+ "loss": 1.0156,
2193
+ "step": 312
2194
+ },
2195
+ {
2196
+ "epoch": 0.59,
2197
+ "grad_norm": 0.4038074947234651,
2198
+ "learning_rate": 3.7380998169629476e-05,
2199
+ "loss": 1.0312,
2200
+ "step": 313
2201
+ },
2202
+ {
2203
+ "epoch": 0.6,
2204
+ "grad_norm": 0.3853125109344581,
2205
+ "learning_rate": 3.708379296368372e-05,
2206
+ "loss": 1.0234,
2207
+ "step": 314
2208
+ },
2209
+ {
2210
+ "epoch": 0.6,
2211
+ "grad_norm": 0.4104650046809597,
2212
+ "learning_rate": 3.678707595076834e-05,
2213
+ "loss": 0.9922,
2214
+ "step": 315
2215
+ },
2216
+ {
2217
+ "epoch": 0.6,
2218
+ "grad_norm": 0.39375524771920445,
2219
+ "learning_rate": 3.649085834587683e-05,
2220
+ "loss": 1.0156,
2221
+ "step": 316
2222
+ },
2223
+ {
2224
+ "epoch": 0.6,
2225
+ "grad_norm": 0.40077662746048126,
2226
+ "learning_rate": 3.619515134512656e-05,
2227
+ "loss": 1.0156,
2228
+ "step": 317
2229
+ },
2230
+ {
2231
+ "epoch": 0.6,
2232
+ "grad_norm": 0.38214253590604597,
2233
+ "learning_rate": 3.589996612533568e-05,
2234
+ "loss": 1.0156,
2235
+ "step": 318
2236
+ },
2237
+ {
2238
+ "epoch": 0.61,
2239
+ "grad_norm": 0.4009148055080218,
2240
+ "learning_rate": 3.560531384360055e-05,
2241
+ "loss": 1.0078,
2242
+ "step": 319
2243
+ },
2244
+ {
2245
+ "epoch": 0.61,
2246
+ "grad_norm": 0.41232895347465953,
2247
+ "learning_rate": 3.531120563687419e-05,
2248
+ "loss": 1.0469,
2249
+ "step": 320
2250
+ },
2251
+ {
2252
+ "epoch": 0.61,
2253
+ "grad_norm": 0.38911553214208094,
2254
+ "learning_rate": 3.501765262154513e-05,
2255
+ "loss": 1.0078,
2256
+ "step": 321
2257
+ },
2258
+ {
2259
+ "epoch": 0.61,
2260
+ "grad_norm": 0.4093791732496366,
2261
+ "learning_rate": 3.472466589301751e-05,
2262
+ "loss": 0.9766,
2263
+ "step": 322
2264
+ },
2265
+ {
2266
+ "epoch": 0.61,
2267
+ "grad_norm": 0.3850449300702058,
2268
+ "learning_rate": 3.4432256525291465e-05,
2269
+ "loss": 0.9883,
2270
+ "step": 323
2271
+ },
2272
+ {
2273
+ "epoch": 0.61,
2274
+ "grad_norm": 0.3889336160040775,
2275
+ "learning_rate": 3.41404355705447e-05,
2276
+ "loss": 0.9766,
2277
+ "step": 324
2278
+ },
2279
+ {
2280
+ "epoch": 0.62,
2281
+ "grad_norm": 0.4084726866306118,
2282
+ "learning_rate": 3.3849214058714704e-05,
2283
+ "loss": 1.0156,
2284
+ "step": 325
2285
+ },
2286
+ {
2287
+ "epoch": 0.62,
2288
+ "grad_norm": 0.4014871038120363,
2289
+ "learning_rate": 3.3558602997081866e-05,
2290
+ "loss": 1.0156,
2291
+ "step": 326
2292
+ },
2293
+ {
2294
+ "epoch": 0.62,
2295
+ "grad_norm": 0.4266625922630768,
2296
+ "learning_rate": 3.326861336985341e-05,
2297
+ "loss": 1.0391,
2298
+ "step": 327
2299
+ },
2300
+ {
2301
+ "epoch": 0.62,
2302
+ "grad_norm": 0.396771175025528,
2303
+ "learning_rate": 3.297925613774828e-05,
2304
+ "loss": 1.0078,
2305
+ "step": 328
2306
+ },
2307
+ {
2308
+ "epoch": 0.62,
2309
+ "grad_norm": 0.4417896085826512,
2310
+ "learning_rate": 3.269054223758279e-05,
2311
+ "loss": 0.9922,
2312
+ "step": 329
2313
+ },
2314
+ {
2315
+ "epoch": 0.63,
2316
+ "grad_norm": 0.3809941597462593,
2317
+ "learning_rate": 3.240248258185731e-05,
2318
+ "loss": 0.9961,
2319
+ "step": 330
2320
+ },
2321
+ {
2322
+ "epoch": 0.63,
2323
+ "grad_norm": 0.4074336906480307,
2324
+ "learning_rate": 3.2115088058343725e-05,
2325
+ "loss": 0.9922,
2326
+ "step": 331
2327
+ },
2328
+ {
2329
+ "epoch": 0.63,
2330
+ "grad_norm": 0.39553570295641505,
2331
+ "learning_rate": 3.1828369529674046e-05,
2332
+ "loss": 1.0,
2333
+ "step": 332
2334
+ },
2335
+ {
2336
+ "epoch": 0.63,
2337
+ "grad_norm": 0.397983999068491,
2338
+ "learning_rate": 3.1542337832929644e-05,
2339
+ "loss": 1.0078,
2340
+ "step": 333
2341
+ },
2342
+ {
2343
+ "epoch": 0.63,
2344
+ "grad_norm": 0.41099820792481956,
2345
+ "learning_rate": 3.125700377923186e-05,
2346
+ "loss": 1.0469,
2347
+ "step": 334
2348
+ },
2349
+ {
2350
+ "epoch": 0.64,
2351
+ "grad_norm": 0.40386749243880216,
2352
+ "learning_rate": 3.0972378153333145e-05,
2353
+ "loss": 0.9961,
2354
+ "step": 335
2355
+ },
2356
+ {
2357
+ "epoch": 0.64,
2358
+ "grad_norm": 0.41080474099987024,
2359
+ "learning_rate": 3.068847171320969e-05,
2360
+ "loss": 1.0156,
2361
+ "step": 336
2362
+ },
2363
+ {
2364
+ "epoch": 0.64,
2365
+ "grad_norm": 0.403700576708479,
2366
+ "learning_rate": 3.0405295189654537e-05,
2367
+ "loss": 1.0234,
2368
+ "step": 337
2369
+ },
2370
+ {
2371
+ "epoch": 0.64,
2372
+ "grad_norm": 0.40482152116129083,
2373
+ "learning_rate": 3.0122859285872214e-05,
2374
+ "loss": 1.0156,
2375
+ "step": 338
2376
+ },
2377
+ {
2378
+ "epoch": 0.64,
2379
+ "grad_norm": 0.40683717747057807,
2380
+ "learning_rate": 2.9841174677074035e-05,
2381
+ "loss": 0.9805,
2382
+ "step": 339
2383
+ },
2384
+ {
2385
+ "epoch": 0.65,
2386
+ "grad_norm": 0.4153367260281328,
2387
+ "learning_rate": 2.9560252010074706e-05,
2388
+ "loss": 1.0078,
2389
+ "step": 340
2390
+ },
2391
+ {
2392
+ "epoch": 0.65,
2393
+ "grad_norm": 0.3911854931588867,
2394
+ "learning_rate": 2.9280101902889824e-05,
2395
+ "loss": 1.0312,
2396
+ "step": 341
2397
+ },
2398
+ {
2399
+ "epoch": 0.65,
2400
+ "grad_norm": 0.4042030431024755,
2401
+ "learning_rate": 2.900073494433464e-05,
2402
+ "loss": 1.0156,
2403
+ "step": 342
2404
+ },
2405
+ {
2406
+ "epoch": 0.65,
2407
+ "grad_norm": 0.40059455864229415,
2408
+ "learning_rate": 2.8722161693623772e-05,
2409
+ "loss": 0.9922,
2410
+ "step": 343
2411
+ },
2412
+ {
2413
+ "epoch": 0.65,
2414
+ "grad_norm": 0.4074896896435664,
2415
+ "learning_rate": 2.8444392679972103e-05,
2416
+ "loss": 0.9883,
2417
+ "step": 344
2418
+ },
2419
+ {
2420
+ "epoch": 0.65,
2421
+ "grad_norm": 0.4095882276226098,
2422
+ "learning_rate": 2.8167438402196805e-05,
2423
+ "loss": 1.0312,
2424
+ "step": 345
2425
+ },
2426
+ {
2427
+ "epoch": 0.66,
2428
+ "grad_norm": 0.4055972430711286,
2429
+ "learning_rate": 2.7891309328320592e-05,
2430
+ "loss": 1.0078,
2431
+ "step": 346
2432
+ },
2433
+ {
2434
+ "epoch": 0.66,
2435
+ "grad_norm": 0.4147093983828081,
2436
+ "learning_rate": 2.761601589517595e-05,
2437
+ "loss": 0.9727,
2438
+ "step": 347
2439
+ },
2440
+ {
2441
+ "epoch": 0.66,
2442
+ "grad_norm": 0.3824364918889605,
2443
+ "learning_rate": 2.7341568508010705e-05,
2444
+ "loss": 1.0234,
2445
+ "step": 348
2446
+ },
2447
+ {
2448
+ "epoch": 0.66,
2449
+ "grad_norm": 0.4173989668789549,
2450
+ "learning_rate": 2.706797754009476e-05,
2451
+ "loss": 0.9961,
2452
+ "step": 349
2453
+ },
2454
+ {
2455
+ "epoch": 0.66,
2456
+ "grad_norm": 0.41599241388744446,
2457
+ "learning_rate": 2.6795253332327995e-05,
2458
+ "loss": 0.9844,
2459
+ "step": 350
2460
+ },
2461
+ {
2462
+ "epoch": 0.67,
2463
+ "grad_norm": 0.40510951524103034,
2464
+ "learning_rate": 2.6523406192849386e-05,
2465
+ "loss": 0.9688,
2466
+ "step": 351
2467
+ },
2468
+ {
2469
+ "epoch": 0.67,
2470
+ "grad_norm": 0.38849419233186266,
2471
+ "learning_rate": 2.62524463966475e-05,
2472
+ "loss": 1.0312,
2473
+ "step": 352
2474
+ },
2475
+ {
2476
+ "epoch": 0.67,
2477
+ "grad_norm": 0.38718946711482044,
2478
+ "learning_rate": 2.5982384185171906e-05,
2479
+ "loss": 1.0078,
2480
+ "step": 353
2481
+ },
2482
+ {
2483
+ "epoch": 0.67,
2484
+ "grad_norm": 0.3842929434765999,
2485
+ "learning_rate": 2.5713229765946357e-05,
2486
+ "loss": 1.0156,
2487
+ "step": 354
2488
+ },
2489
+ {
2490
+ "epoch": 0.67,
2491
+ "grad_norm": 0.39359245264071546,
2492
+ "learning_rate": 2.544499331218274e-05,
2493
+ "loss": 0.9883,
2494
+ "step": 355
2495
+ },
2496
+ {
2497
+ "epoch": 0.68,
2498
+ "grad_norm": 0.4033582052703098,
2499
+ "learning_rate": 2.5177684962396765e-05,
2500
+ "loss": 1.0,
2501
+ "step": 356
2502
+ },
2503
+ {
2504
+ "epoch": 0.68,
2505
+ "grad_norm": 0.38879954929363575,
2506
+ "learning_rate": 2.4911314820024568e-05,
2507
+ "loss": 1.0078,
2508
+ "step": 357
2509
+ },
2510
+ {
2511
+ "epoch": 0.68,
2512
+ "grad_norm": 0.40327329986367616,
2513
+ "learning_rate": 2.4645892953040962e-05,
2514
+ "loss": 1.0078,
2515
+ "step": 358
2516
+ },
2517
+ {
2518
+ "epoch": 0.68,
2519
+ "grad_norm": 0.3920586735187762,
2520
+ "learning_rate": 2.438142939357882e-05,
2521
+ "loss": 1.0,
2522
+ "step": 359
2523
+ },
2524
+ {
2525
+ "epoch": 0.68,
2526
+ "grad_norm": 0.4143087212185901,
2527
+ "learning_rate": 2.4117934137550003e-05,
2528
+ "loss": 0.9961,
2529
+ "step": 360
2530
+ },
2531
+ {
2532
+ "epoch": 0.69,
2533
+ "grad_norm": 0.3935944385117418,
2534
+ "learning_rate": 2.38554171442674e-05,
2535
+ "loss": 1.0156,
2536
+ "step": 361
2537
+ },
2538
+ {
2539
+ "epoch": 0.69,
2540
+ "grad_norm": 0.4077637452431266,
2541
+ "learning_rate": 2.3593888336068597e-05,
2542
+ "loss": 0.9883,
2543
+ "step": 362
2544
+ },
2545
+ {
2546
+ "epoch": 0.69,
2547
+ "grad_norm": 0.4025782626367008,
2548
+ "learning_rate": 2.3333357597940793e-05,
2549
+ "loss": 1.0078,
2550
+ "step": 363
2551
+ },
2552
+ {
2553
+ "epoch": 0.69,
2554
+ "grad_norm": 0.4036874759716257,
2555
+ "learning_rate": 2.3073834777147236e-05,
2556
+ "loss": 0.9922,
2557
+ "step": 364
2558
+ },
2559
+ {
2560
+ "epoch": 0.69,
2561
+ "grad_norm": 0.4001732077591455,
2562
+ "learning_rate": 2.281532968285494e-05,
2563
+ "loss": 1.0156,
2564
+ "step": 365
2565
+ },
2566
+ {
2567
+ "epoch": 0.69,
2568
+ "grad_norm": 0.38090979037495276,
2569
+ "learning_rate": 2.2557852085764053e-05,
2570
+ "loss": 0.9766,
2571
+ "step": 366
2572
+ },
2573
+ {
2574
+ "epoch": 0.7,
2575
+ "grad_norm": 0.40328341409897206,
2576
+ "learning_rate": 2.230141171773836e-05,
2577
+ "loss": 0.9922,
2578
+ "step": 367
2579
+ },
2580
+ {
2581
+ "epoch": 0.7,
2582
+ "grad_norm": 0.3838644049185376,
2583
+ "learning_rate": 2.204601827143769e-05,
2584
+ "loss": 0.9844,
2585
+ "step": 368
2586
+ },
2587
+ {
2588
+ "epoch": 0.7,
2589
+ "grad_norm": 0.38931148821481226,
2590
+ "learning_rate": 2.179168139995134e-05,
2591
+ "loss": 1.0156,
2592
+ "step": 369
2593
+ },
2594
+ {
2595
+ "epoch": 0.7,
2596
+ "grad_norm": 0.4024461082037364,
2597
+ "learning_rate": 2.1538410716433417e-05,
2598
+ "loss": 0.9805,
2599
+ "step": 370
2600
+ },
2601
+ {
2602
+ "epoch": 0.7,
2603
+ "grad_norm": 0.3736565961055131,
2604
+ "learning_rate": 2.1286215793739302e-05,
2605
+ "loss": 1.0078,
2606
+ "step": 371
2607
+ },
2608
+ {
2609
+ "epoch": 0.71,
2610
+ "grad_norm": 0.3833954847678005,
2611
+ "learning_rate": 2.103510616406396e-05,
2612
+ "loss": 1.0156,
2613
+ "step": 372
2614
+ },
2615
+ {
2616
+ "epoch": 0.71,
2617
+ "grad_norm": 0.38010761506947877,
2618
+ "learning_rate": 2.0785091318581577e-05,
2619
+ "loss": 0.9883,
2620
+ "step": 373
2621
+ },
2622
+ {
2623
+ "epoch": 0.71,
2624
+ "grad_norm": 0.3883359267276046,
2625
+ "learning_rate": 2.053618070708691e-05,
2626
+ "loss": 1.0234,
2627
+ "step": 374
2628
+ },
2629
+ {
2630
+ "epoch": 0.71,
2631
+ "grad_norm": 0.38727784403682314,
2632
+ "learning_rate": 2.0288383737638006e-05,
2633
+ "loss": 1.0,
2634
+ "step": 375
2635
+ },
2636
+ {
2637
+ "epoch": 0.71,
2638
+ "grad_norm": 0.37785442157781823,
2639
+ "learning_rate": 2.0041709776200664e-05,
2640
+ "loss": 0.9766,
2641
+ "step": 376
2642
+ },
2643
+ {
2644
+ "epoch": 0.72,
2645
+ "grad_norm": 0.374719617466221,
2646
+ "learning_rate": 1.9796168146294412e-05,
2647
+ "loss": 0.9727,
2648
+ "step": 377
2649
+ },
2650
+ {
2651
+ "epoch": 0.72,
2652
+ "grad_norm": 0.3978681831649405,
2653
+ "learning_rate": 1.9551768128640175e-05,
2654
+ "loss": 1.0156,
2655
+ "step": 378
2656
+ },
2657
+ {
2658
+ "epoch": 0.72,
2659
+ "grad_norm": 0.40863119356002636,
2660
+ "learning_rate": 1.9308518960809353e-05,
2661
+ "loss": 0.9805,
2662
+ "step": 379
2663
+ },
2664
+ {
2665
+ "epoch": 0.72,
2666
+ "grad_norm": 0.37974978552322725,
2667
+ "learning_rate": 1.9066429836874844e-05,
2668
+ "loss": 1.0078,
2669
+ "step": 380
2670
+ },
2671
+ {
2672
+ "epoch": 0.72,
2673
+ "grad_norm": 0.38613047300957787,
2674
+ "learning_rate": 1.8825509907063327e-05,
2675
+ "loss": 0.9688,
2676
+ "step": 381
2677
+ },
2678
+ {
2679
+ "epoch": 0.72,
2680
+ "grad_norm": 0.39858125559813595,
2681
+ "learning_rate": 1.8585768277409636e-05,
2682
+ "loss": 1.0078,
2683
+ "step": 382
2684
+ },
2685
+ {
2686
+ "epoch": 0.73,
2687
+ "grad_norm": 0.39902011519219927,
2688
+ "learning_rate": 1.83472140094124e-05,
2689
+ "loss": 0.9609,
2690
+ "step": 383
2691
+ },
2692
+ {
2693
+ "epoch": 0.73,
2694
+ "grad_norm": 0.39852324308132375,
2695
+ "learning_rate": 1.810985611969167e-05,
2696
+ "loss": 0.9766,
2697
+ "step": 384
2698
+ },
2699
+ {
2700
+ "epoch": 0.73,
2701
+ "grad_norm": 0.39740793737557956,
2702
+ "learning_rate": 1.7873703579648034e-05,
2703
+ "loss": 0.9961,
2704
+ "step": 385
2705
+ },
2706
+ {
2707
+ "epoch": 0.73,
2708
+ "grad_norm": 0.38900589785267126,
2709
+ "learning_rate": 1.763876531512354e-05,
2710
+ "loss": 0.9688,
2711
+ "step": 386
2712
+ },
2713
+ {
2714
+ "epoch": 0.73,
2715
+ "grad_norm": 0.386397499552252,
2716
+ "learning_rate": 1.7405050206064373e-05,
2717
+ "loss": 1.0078,
2718
+ "step": 387
2719
+ },
2720
+ {
2721
+ "epoch": 0.74,
2722
+ "grad_norm": 0.39337570995784904,
2723
+ "learning_rate": 1.7172567086185205e-05,
2724
+ "loss": 0.9727,
2725
+ "step": 388
2726
+ },
2727
+ {
2728
+ "epoch": 0.74,
2729
+ "grad_norm": 0.39083779363840615,
2730
+ "learning_rate": 1.694132474263526e-05,
2731
+ "loss": 0.9961,
2732
+ "step": 389
2733
+ },
2734
+ {
2735
+ "epoch": 0.74,
2736
+ "grad_norm": 0.38939147028830934,
2737
+ "learning_rate": 1.671133191566624e-05,
2738
+ "loss": 0.9844,
2739
+ "step": 390
2740
+ },
2741
+ {
2742
+ "epoch": 0.74,
2743
+ "grad_norm": 0.44238601157646656,
2744
+ "learning_rate": 1.6482597298301916e-05,
2745
+ "loss": 0.9805,
2746
+ "step": 391
2747
+ },
2748
+ {
2749
+ "epoch": 0.74,
2750
+ "grad_norm": 0.39265218999260465,
2751
+ "learning_rate": 1.625512953600966e-05,
2752
+ "loss": 1.0,
2753
+ "step": 392
2754
+ },
2755
+ {
2756
+ "epoch": 0.75,
2757
+ "grad_norm": 0.3835027930578862,
2758
+ "learning_rate": 1.6028937226373536e-05,
2759
+ "loss": 0.9766,
2760
+ "step": 393
2761
+ },
2762
+ {
2763
+ "epoch": 0.75,
2764
+ "grad_norm": 0.4052201995250459,
2765
+ "learning_rate": 1.5804028918769485e-05,
2766
+ "loss": 1.0,
2767
+ "step": 394
2768
+ },
2769
+ {
2770
+ "epoch": 0.75,
2771
+ "grad_norm": 0.3929827776726385,
2772
+ "learning_rate": 1.5580413114042e-05,
2773
+ "loss": 0.9766,
2774
+ "step": 395
2775
+ },
2776
+ {
2777
+ "epoch": 0.75,
2778
+ "grad_norm": 0.37984173524249143,
2779
+ "learning_rate": 1.535809826418304e-05,
2780
+ "loss": 0.9922,
2781
+ "step": 396
2782
+ },
2783
+ {
2784
+ "epoch": 0.75,
2785
+ "grad_norm": 0.39211944754121586,
2786
+ "learning_rate": 1.5137092772012368e-05,
2787
+ "loss": 0.9844,
2788
+ "step": 397
2789
+ },
2790
+ {
2791
+ "epoch": 0.76,
2792
+ "grad_norm": 0.39835572557937476,
2793
+ "learning_rate": 1.4917404990860112e-05,
2794
+ "loss": 1.0156,
2795
+ "step": 398
2796
+ },
2797
+ {
2798
+ "epoch": 0.76,
2799
+ "grad_norm": 0.3685838055250128,
2800
+ "learning_rate": 1.469904322425092e-05,
2801
+ "loss": 1.0078,
2802
+ "step": 399
2803
+ },
2804
+ {
2805
+ "epoch": 0.76,
2806
+ "grad_norm": 0.3708790521540525,
2807
+ "learning_rate": 1.4482015725590158e-05,
2808
+ "loss": 0.9727,
2809
+ "step": 400
2810
+ },
2811
+ {
2812
+ "epoch": 0.76,
2813
+ "grad_norm": 0.3796896559412745,
2814
+ "learning_rate": 1.4266330697851954e-05,
2815
+ "loss": 0.9961,
2816
+ "step": 401
2817
+ },
2818
+ {
2819
+ "epoch": 0.76,
2820
+ "grad_norm": 0.374826650593594,
2821
+ "learning_rate": 1.4051996293269182e-05,
2822
+ "loss": 0.9766,
2823
+ "step": 402
2824
+ },
2825
+ {
2826
+ "epoch": 0.76,
2827
+ "grad_norm": 0.38661887803441924,
2828
+ "learning_rate": 1.3839020613025266e-05,
2829
+ "loss": 1.0,
2830
+ "step": 403
2831
+ },
2832
+ {
2833
+ "epoch": 0.77,
2834
+ "grad_norm": 0.3745066620120658,
2835
+ "learning_rate": 1.3627411706948029e-05,
2836
+ "loss": 0.9688,
2837
+ "step": 404
2838
+ },
2839
+ {
2840
+ "epoch": 0.77,
2841
+ "grad_norm": 0.3772263032436855,
2842
+ "learning_rate": 1.3417177573205398e-05,
2843
+ "loss": 0.9922,
2844
+ "step": 405
2845
+ },
2846
+ {
2847
+ "epoch": 0.77,
2848
+ "grad_norm": 0.37135625308638415,
2849
+ "learning_rate": 1.3208326158003171e-05,
2850
+ "loss": 0.9844,
2851
+ "step": 406
2852
+ },
2853
+ {
2854
+ "epoch": 0.77,
2855
+ "grad_norm": 0.39016768277198083,
2856
+ "learning_rate": 1.3000865355284563e-05,
2857
+ "loss": 0.9922,
2858
+ "step": 407
2859
+ },
2860
+ {
2861
+ "epoch": 0.77,
2862
+ "grad_norm": 0.3927111734870179,
2863
+ "learning_rate": 1.2794803006431982e-05,
2864
+ "loss": 0.9688,
2865
+ "step": 408
2866
+ },
2867
+ {
2868
+ "epoch": 0.78,
2869
+ "grad_norm": 0.37854433770919677,
2870
+ "learning_rate": 1.2590146899970446e-05,
2871
+ "loss": 0.9805,
2872
+ "step": 409
2873
+ },
2874
+ {
2875
+ "epoch": 0.78,
2876
+ "grad_norm": 0.39232004793616226,
2877
+ "learning_rate": 1.2386904771273444e-05,
2878
+ "loss": 0.9961,
2879
+ "step": 410
2880
+ },
2881
+ {
2882
+ "epoch": 0.78,
2883
+ "grad_norm": 0.38535521167421993,
2884
+ "learning_rate": 1.218508430227035e-05,
2885
+ "loss": 0.9844,
2886
+ "step": 411
2887
+ },
2888
+ {
2889
+ "epoch": 0.78,
2890
+ "grad_norm": 0.3686602860581547,
2891
+ "learning_rate": 1.1984693121156226e-05,
2892
+ "loss": 0.9922,
2893
+ "step": 412
2894
+ },
2895
+ {
2896
+ "epoch": 0.78,
2897
+ "grad_norm": 0.3859440212089631,
2898
+ "learning_rate": 1.1785738802103396e-05,
2899
+ "loss": 1.0156,
2900
+ "step": 413
2901
+ },
2902
+ {
2903
+ "epoch": 0.79,
2904
+ "grad_norm": 0.3921328346507493,
2905
+ "learning_rate": 1.158822886497521e-05,
2906
+ "loss": 0.9688,
2907
+ "step": 414
2908
+ },
2909
+ {
2910
+ "epoch": 0.79,
2911
+ "grad_norm": 0.39742562204123394,
2912
+ "learning_rate": 1.1392170775041788e-05,
2913
+ "loss": 1.0078,
2914
+ "step": 415
2915
+ },
2916
+ {
2917
+ "epoch": 0.79,
2918
+ "grad_norm": 0.3713395354970734,
2919
+ "learning_rate": 1.1197571942697938e-05,
2920
+ "loss": 0.9805,
2921
+ "step": 416
2922
+ },
2923
+ {
2924
+ "epoch": 0.79,
2925
+ "grad_norm": 0.37345209868445495,
2926
+ "learning_rate": 1.1004439723182942e-05,
2927
+ "loss": 1.0,
2928
+ "step": 417
2929
+ },
2930
+ {
2931
+ "epoch": 0.79,
2932
+ "grad_norm": 0.3856263873198924,
2933
+ "learning_rate": 1.0812781416302642e-05,
2934
+ "loss": 0.9648,
2935
+ "step": 418
2936
+ },
2937
+ {
2938
+ "epoch": 0.8,
2939
+ "grad_norm": 0.37612362914326103,
2940
+ "learning_rate": 1.0622604266153485e-05,
2941
+ "loss": 1.0156,
2942
+ "step": 419
2943
+ },
2944
+ {
2945
+ "epoch": 0.8,
2946
+ "grad_norm": 0.3735721290488117,
2947
+ "learning_rate": 1.0433915460848764e-05,
2948
+ "loss": 0.9531,
2949
+ "step": 420
2950
+ },
2951
+ {
2952
+ "epoch": 0.8,
2953
+ "grad_norm": 0.3831137038951988,
2954
+ "learning_rate": 1.0246722132246856e-05,
2955
+ "loss": 0.9727,
2956
+ "step": 421
2957
+ },
2958
+ {
2959
+ "epoch": 0.8,
2960
+ "grad_norm": 0.38425446590883783,
2961
+ "learning_rate": 1.0061031355681766e-05,
2962
+ "loss": 0.9805,
2963
+ "step": 422
2964
+ },
2965
+ {
2966
+ "epoch": 0.8,
2967
+ "grad_norm": 0.37733541326906417,
2968
+ "learning_rate": 9.876850149695555e-06,
2969
+ "loss": 0.9727,
2970
+ "step": 423
2971
+ },
2972
+ {
2973
+ "epoch": 0.8,
2974
+ "grad_norm": 0.3919247049760062,
2975
+ "learning_rate": 9.694185475773216e-06,
2976
+ "loss": 0.9844,
2977
+ "step": 424
2978
+ },
2979
+ {
2980
+ "epoch": 0.81,
2981
+ "grad_norm": 0.37412167877987657,
2982
+ "learning_rate": 9.513044238079427e-06,
2983
+ "loss": 0.9844,
2984
+ "step": 425
2985
+ },
2986
+ {
2987
+ "epoch": 0.81,
2988
+ "grad_norm": 0.3960239887267585,
2989
+ "learning_rate": 9.333433283197702e-06,
2990
+ "loss": 1.0078,
2991
+ "step": 426
2992
+ },
2993
+ {
2994
+ "epoch": 0.81,
2995
+ "grad_norm": 0.36022823771296714,
2996
+ "learning_rate": 9.15535939987151e-06,
2997
+ "loss": 0.9648,
2998
+ "step": 427
2999
+ },
3000
+ {
3001
+ "epoch": 0.81,
3002
+ "grad_norm": 0.3789422853471504,
3003
+ "learning_rate": 8.978829318747745e-06,
3004
+ "loss": 0.9844,
3005
+ "step": 428
3006
+ },
3007
+ {
3008
+ "epoch": 0.81,
3009
+ "grad_norm": 0.39075327374116037,
3010
+ "learning_rate": 8.803849712122292e-06,
3011
+ "loss": 1.0156,
3012
+ "step": 429
3013
+ },
3014
+ {
3015
+ "epoch": 0.82,
3016
+ "grad_norm": 0.389242893802255,
3017
+ "learning_rate": 8.63042719368789e-06,
3018
+ "loss": 0.9766,
3019
+ "step": 430
3020
+ },
3021
+ {
3022
+ "epoch": 0.82,
3023
+ "grad_norm": 0.3779626313074645,
3024
+ "learning_rate": 8.458568318284088e-06,
3025
+ "loss": 0.9883,
3026
+ "step": 431
3027
+ },
3028
+ {
3029
+ "epoch": 0.82,
3030
+ "grad_norm": 0.39319540149781285,
3031
+ "learning_rate": 8.288279581649528e-06,
3032
+ "loss": 1.0,
3033
+ "step": 432
3034
+ },
3035
+ {
3036
+ "epoch": 0.82,
3037
+ "grad_norm": 0.3759206398973123,
3038
+ "learning_rate": 8.11956742017641e-06,
3039
+ "loss": 0.9766,
3040
+ "step": 433
3041
+ },
3042
+ {
3043
+ "epoch": 0.82,
3044
+ "grad_norm": 0.3938599895612702,
3045
+ "learning_rate": 7.952438210667268e-06,
3046
+ "loss": 1.0156,
3047
+ "step": 434
3048
+ },
3049
+ {
3050
+ "epoch": 0.83,
3051
+ "grad_norm": 0.3821358600474751,
3052
+ "learning_rate": 7.786898270093846e-06,
3053
+ "loss": 0.9766,
3054
+ "step": 435
3055
+ },
3056
+ {
3057
+ "epoch": 0.83,
3058
+ "grad_norm": 0.3811416337365797,
3059
+ "learning_rate": 7.6229538553584556e-06,
3060
+ "loss": 0.9844,
3061
+ "step": 436
3062
+ },
3063
+ {
3064
+ "epoch": 0.83,
3065
+ "grad_norm": 0.384284050269022,
3066
+ "learning_rate": 7.460611163057346e-06,
3067
+ "loss": 0.9727,
3068
+ "step": 437
3069
+ },
3070
+ {
3071
+ "epoch": 0.83,
3072
+ "grad_norm": 0.3868115258369787,
3073
+ "learning_rate": 7.299876329246652e-06,
3074
+ "loss": 0.9805,
3075
+ "step": 438
3076
+ },
3077
+ {
3078
+ "epoch": 0.83,
3079
+ "grad_norm": 0.37631545582941645,
3080
+ "learning_rate": 7.140755429210316e-06,
3081
+ "loss": 0.9766,
3082
+ "step": 439
3083
+ },
3084
+ {
3085
+ "epoch": 0.83,
3086
+ "grad_norm": 0.3763933121794425,
3087
+ "learning_rate": 6.983254477230588e-06,
3088
+ "loss": 0.9805,
3089
+ "step": 440
3090
+ },
3091
+ {
3092
+ "epoch": 0.84,
3093
+ "grad_norm": 0.38966862555598764,
3094
+ "learning_rate": 6.827379426360614e-06,
3095
+ "loss": 0.9414,
3096
+ "step": 441
3097
+ },
3098
+ {
3099
+ "epoch": 0.84,
3100
+ "grad_norm": 0.38924826237998583,
3101
+ "learning_rate": 6.673136168199467e-06,
3102
+ "loss": 0.9766,
3103
+ "step": 442
3104
+ },
3105
+ {
3106
+ "epoch": 0.84,
3107
+ "grad_norm": 0.3716162541474658,
3108
+ "learning_rate": 6.52053053266945e-06,
3109
+ "loss": 1.0078,
3110
+ "step": 443
3111
+ },
3112
+ {
3113
+ "epoch": 0.84,
3114
+ "grad_norm": 0.40192334917868294,
3115
+ "learning_rate": 6.369568287795791e-06,
3116
+ "loss": 1.0,
3117
+ "step": 444
3118
+ },
3119
+ {
3120
+ "epoch": 0.84,
3121
+ "grad_norm": 0.3827921806873429,
3122
+ "learning_rate": 6.22025513948854e-06,
3123
+ "loss": 0.9609,
3124
+ "step": 445
3125
+ },
3126
+ {
3127
+ "epoch": 0.85,
3128
+ "grad_norm": 0.3651988094584562,
3129
+ "learning_rate": 6.0725967313269736e-06,
3130
+ "loss": 1.0234,
3131
+ "step": 446
3132
+ },
3133
+ {
3134
+ "epoch": 0.85,
3135
+ "grad_norm": 0.3854817154179708,
3136
+ "learning_rate": 5.926598644346259e-06,
3137
+ "loss": 0.9883,
3138
+ "step": 447
3139
+ },
3140
+ {
3141
+ "epoch": 0.85,
3142
+ "grad_norm": 0.4041053789118015,
3143
+ "learning_rate": 5.782266396826536e-06,
3144
+ "loss": 0.9922,
3145
+ "step": 448
3146
+ },
3147
+ {
3148
+ "epoch": 0.85,
3149
+ "grad_norm": 0.3840835793609324,
3150
+ "learning_rate": 5.639605444084273e-06,
3151
+ "loss": 0.9922,
3152
+ "step": 449
3153
+ },
3154
+ {
3155
+ "epoch": 0.85,
3156
+ "grad_norm": 0.3827506231880665,
3157
+ "learning_rate": 5.498621178266167e-06,
3158
+ "loss": 0.9844,
3159
+ "step": 450
3160
+ },
3161
+ {
3162
+ "epoch": 0.86,
3163
+ "grad_norm": 0.37488009002085854,
3164
+ "learning_rate": 5.3593189281452625e-06,
3165
+ "loss": 0.9883,
3166
+ "step": 451
3167
+ },
3168
+ {
3169
+ "epoch": 0.86,
3170
+ "grad_norm": 0.3644346732423304,
3171
+ "learning_rate": 5.221703958919572e-06,
3172
+ "loss": 1.0,
3173
+ "step": 452
3174
+ },
3175
+ {
3176
+ "epoch": 0.86,
3177
+ "grad_norm": 0.3648839469610167,
3178
+ "learning_rate": 5.085781472013051e-06,
3179
+ "loss": 0.9844,
3180
+ "step": 453
3181
+ },
3182
+ {
3183
+ "epoch": 0.86,
3184
+ "grad_norm": 0.3888452684975849,
3185
+ "learning_rate": 4.951556604879048e-06,
3186
+ "loss": 0.9961,
3187
+ "step": 454
3188
+ },
3189
+ {
3190
+ "epoch": 0.86,
3191
+ "grad_norm": 0.38081986253747263,
3192
+ "learning_rate": 4.819034430806046e-06,
3193
+ "loss": 1.0234,
3194
+ "step": 455
3195
+ },
3196
+ {
3197
+ "epoch": 0.87,
3198
+ "grad_norm": 0.37504903165101505,
3199
+ "learning_rate": 4.688219958725981e-06,
3200
+ "loss": 0.9922,
3201
+ "step": 456
3202
+ },
3203
+ {
3204
+ "epoch": 0.87,
3205
+ "grad_norm": 0.3896425547477861,
3206
+ "learning_rate": 4.559118133024853e-06,
3207
+ "loss": 0.9688,
3208
+ "step": 457
3209
+ },
3210
+ {
3211
+ "epoch": 0.87,
3212
+ "grad_norm": 0.3794758055441137,
3213
+ "learning_rate": 4.431733833355933e-06,
3214
+ "loss": 0.9766,
3215
+ "step": 458
3216
+ },
3217
+ {
3218
+ "epoch": 0.87,
3219
+ "grad_norm": 0.39706131136751927,
3220
+ "learning_rate": 4.3060718744552256e-06,
3221
+ "loss": 1.0,
3222
+ "step": 459
3223
+ },
3224
+ {
3225
+ "epoch": 0.87,
3226
+ "grad_norm": 0.3697319148486722,
3227
+ "learning_rate": 4.1821370059595575e-06,
3228
+ "loss": 0.9961,
3229
+ "step": 460
3230
+ },
3231
+ {
3232
+ "epoch": 0.87,
3233
+ "grad_norm": 0.3732079712646108,
3234
+ "learning_rate": 4.05993391222701e-06,
3235
+ "loss": 0.9922,
3236
+ "step": 461
3237
+ },
3238
+ {
3239
+ "epoch": 0.88,
3240
+ "grad_norm": 0.38872894699778315,
3241
+ "learning_rate": 3.939467212159925e-06,
3242
+ "loss": 0.957,
3243
+ "step": 462
3244
+ },
3245
+ {
3246
+ "epoch": 0.88,
3247
+ "grad_norm": 0.39026050723200223,
3248
+ "learning_rate": 3.820741459030253e-06,
3249
+ "loss": 1.0,
3250
+ "step": 463
3251
+ },
3252
+ {
3253
+ "epoch": 0.88,
3254
+ "grad_norm": 0.3816637074881011,
3255
+ "learning_rate": 3.70376114030751e-06,
3256
+ "loss": 0.9727,
3257
+ "step": 464
3258
+ },
3259
+ {
3260
+ "epoch": 0.88,
3261
+ "grad_norm": 0.381226241519682,
3262
+ "learning_rate": 3.5885306774891215e-06,
3263
+ "loss": 0.957,
3264
+ "step": 465
3265
+ },
3266
+ {
3267
+ "epoch": 0.88,
3268
+ "grad_norm": 0.3815235626105606,
3269
+ "learning_rate": 3.475054425933344e-06,
3270
+ "loss": 1.0078,
3271
+ "step": 466
3272
+ },
3273
+ {
3274
+ "epoch": 0.89,
3275
+ "grad_norm": 0.37253784076771357,
3276
+ "learning_rate": 3.3633366746946004e-06,
3277
+ "loss": 0.9844,
3278
+ "step": 467
3279
+ },
3280
+ {
3281
+ "epoch": 0.89,
3282
+ "grad_norm": 0.3919508192472245,
3283
+ "learning_rate": 3.2533816463614253e-06,
3284
+ "loss": 0.9805,
3285
+ "step": 468
3286
+ },
3287
+ {
3288
+ "epoch": 0.89,
3289
+ "grad_norm": 0.3589524968140092,
3290
+ "learning_rate": 3.145193496896809e-06,
3291
+ "loss": 0.9805,
3292
+ "step": 469
3293
+ },
3294
+ {
3295
+ "epoch": 0.89,
3296
+ "grad_norm": 0.37438948854975374,
3297
+ "learning_rate": 3.0387763154811454e-06,
3298
+ "loss": 0.9766,
3299
+ "step": 470
3300
+ },
3301
+ {
3302
+ "epoch": 0.89,
3303
+ "grad_norm": 0.37638045292642797,
3304
+ "learning_rate": 2.934134124357646e-06,
3305
+ "loss": 0.9766,
3306
+ "step": 471
3307
+ },
3308
+ {
3309
+ "epoch": 0.9,
3310
+ "grad_norm": 0.37548669011906294,
3311
+ "learning_rate": 2.83127087868037e-06,
3312
+ "loss": 0.9961,
3313
+ "step": 472
3314
+ },
3315
+ {
3316
+ "epoch": 0.9,
3317
+ "grad_norm": 0.37099994562581057,
3318
+ "learning_rate": 2.7301904663646516e-06,
3319
+ "loss": 0.9805,
3320
+ "step": 473
3321
+ },
3322
+ {
3323
+ "epoch": 0.9,
3324
+ "grad_norm": 0.3955783574675612,
3325
+ "learning_rate": 2.630896707940228e-06,
3326
+ "loss": 1.0,
3327
+ "step": 474
3328
+ },
3329
+ {
3330
+ "epoch": 0.9,
3331
+ "grad_norm": 0.3781205817722125,
3332
+ "learning_rate": 2.5333933564067492e-06,
3333
+ "loss": 0.9648,
3334
+ "step": 475
3335
+ },
3336
+ {
3337
+ "epoch": 0.9,
3338
+ "grad_norm": 0.3753919414015063,
3339
+ "learning_rate": 2.4376840970920134e-06,
3340
+ "loss": 0.9766,
3341
+ "step": 476
3342
+ },
3343
+ {
3344
+ "epoch": 0.91,
3345
+ "grad_norm": 0.37073539113386406,
3346
+ "learning_rate": 2.343772547512613e-06,
3347
+ "loss": 0.9727,
3348
+ "step": 477
3349
+ },
3350
+ {
3351
+ "epoch": 0.91,
3352
+ "grad_norm": 0.38467962659041166,
3353
+ "learning_rate": 2.2516622572372414e-06,
3354
+ "loss": 0.9961,
3355
+ "step": 478
3356
+ },
3357
+ {
3358
+ "epoch": 0.91,
3359
+ "grad_norm": 0.37351142314581637,
3360
+ "learning_rate": 2.1613567077524875e-06,
3361
+ "loss": 0.9648,
3362
+ "step": 479
3363
+ },
3364
+ {
3365
+ "epoch": 0.91,
3366
+ "grad_norm": 0.3827518716422808,
3367
+ "learning_rate": 2.0728593123312935e-06,
3368
+ "loss": 0.957,
3369
+ "step": 480
3370
+ },
3371
+ {
3372
+ "epoch": 0.91,
3373
+ "grad_norm": 0.38424950524851154,
3374
+ "learning_rate": 1.9861734159038968e-06,
3375
+ "loss": 0.9805,
3376
+ "step": 481
3377
+ },
3378
+ {
3379
+ "epoch": 0.91,
3380
+ "grad_norm": 0.3738580907918172,
3381
+ "learning_rate": 1.9013022949314563e-06,
3382
+ "loss": 1.0,
3383
+ "step": 482
3384
+ },
3385
+ {
3386
+ "epoch": 0.92,
3387
+ "grad_norm": 0.35985698703033747,
3388
+ "learning_rate": 1.8182491572821536e-06,
3389
+ "loss": 0.9688,
3390
+ "step": 483
3391
+ },
3392
+ {
3393
+ "epoch": 0.92,
3394
+ "grad_norm": 0.37376402159660854,
3395
+ "learning_rate": 1.7370171421099978e-06,
3396
+ "loss": 0.9805,
3397
+ "step": 484
3398
+ },
3399
+ {
3400
+ "epoch": 0.92,
3401
+ "grad_norm": 0.3652435400198038,
3402
+ "learning_rate": 1.6576093197361253e-06,
3403
+ "loss": 1.0,
3404
+ "step": 485
3405
+ },
3406
+ {
3407
+ "epoch": 0.92,
3408
+ "grad_norm": 0.3740292147578786,
3409
+ "learning_rate": 1.5800286915328033e-06,
3410
+ "loss": 0.9922,
3411
+ "step": 486
3412
+ },
3413
+ {
3414
+ "epoch": 0.92,
3415
+ "grad_norm": 0.38020345497873537,
3416
+ "learning_rate": 1.5042781898099434e-06,
3417
+ "loss": 0.9883,
3418
+ "step": 487
3419
+ },
3420
+ {
3421
+ "epoch": 0.93,
3422
+ "grad_norm": 0.38405525205639585,
3423
+ "learning_rate": 1.430360677704301e-06,
3424
+ "loss": 0.9844,
3425
+ "step": 488
3426
+ },
3427
+ {
3428
+ "epoch": 0.93,
3429
+ "grad_norm": 0.37116971953078254,
3430
+ "learning_rate": 1.3582789490712179e-06,
3431
+ "loss": 0.9727,
3432
+ "step": 489
3433
+ },
3434
+ {
3435
+ "epoch": 0.93,
3436
+ "grad_norm": 0.3675736740984735,
3437
+ "learning_rate": 1.2880357283790777e-06,
3438
+ "loss": 0.9961,
3439
+ "step": 490
3440
+ },
3441
+ {
3442
+ "epoch": 0.93,
3443
+ "grad_norm": 0.3615376408573602,
3444
+ "learning_rate": 1.2196336706062739e-06,
3445
+ "loss": 0.9805,
3446
+ "step": 491
3447
+ },
3448
+ {
3449
+ "epoch": 0.93,
3450
+ "grad_norm": 0.3749327617084023,
3451
+ "learning_rate": 1.153075361140915e-06,
3452
+ "loss": 1.0156,
3453
+ "step": 492
3454
+ },
3455
+ {
3456
+ "epoch": 0.94,
3457
+ "grad_norm": 0.36973528586380827,
3458
+ "learning_rate": 1.0883633156830553e-06,
3459
+ "loss": 1.0234,
3460
+ "step": 493
3461
+ },
3462
+ {
3463
+ "epoch": 0.94,
3464
+ "grad_norm": 0.36950719264405446,
3465
+ "learning_rate": 1.0254999801496247e-06,
3466
+ "loss": 0.9883,
3467
+ "step": 494
3468
+ },
3469
+ {
3470
+ "epoch": 0.94,
3471
+ "grad_norm": 0.3811515872434199,
3472
+ "learning_rate": 9.644877305819976e-07,
3473
+ "loss": 0.9844,
3474
+ "step": 495
3475
+ },
3476
+ {
3477
+ "epoch": 0.94,
3478
+ "grad_norm": 0.37251325878792274,
3479
+ "learning_rate": 9.053288730561716e-07,
3480
+ "loss": 1.0,
3481
+ "step": 496
3482
+ },
3483
+ {
3484
+ "epoch": 0.94,
3485
+ "grad_norm": 0.3784945023163416,
3486
+ "learning_rate": 8.480256435956124e-07,
3487
+ "loss": 0.9883,
3488
+ "step": 497
3489
+ },
3490
+ {
3491
+ "epoch": 0.94,
3492
+ "grad_norm": 0.3823913771851788,
3493
+ "learning_rate": 7.925802080867128e-07,
3494
+ "loss": 0.9922,
3495
+ "step": 498
3496
+ },
3497
+ {
3498
+ "epoch": 0.95,
3499
+ "grad_norm": 0.3723209207003651,
3500
+ "learning_rate": 7.389946621969679e-07,
3501
+ "loss": 0.9766,
3502
+ "step": 499
3503
+ },
3504
+ {
3505
+ "epoch": 0.95,
3506
+ "grad_norm": 0.3734561531299352,
3507
+ "learning_rate": 6.872710312957497e-07,
3508
+ "loss": 0.9883,
3509
+ "step": 500
3510
+ },
3511
+ {
3512
+ "epoch": 0.95,
3513
+ "grad_norm": 0.3718975890363552,
3514
+ "learning_rate": 6.374112703777301e-07,
3515
+ "loss": 0.9727,
3516
+ "step": 501
3517
+ },
3518
+ {
3519
+ "epoch": 0.95,
3520
+ "grad_norm": 0.3853867112825849,
3521
+ "learning_rate": 5.894172639890394e-07,
3522
+ "loss": 0.9727,
3523
+ "step": 502
3524
+ },
3525
+ {
3526
+ "epoch": 0.95,
3527
+ "grad_norm": 0.3666171985176669,
3528
+ "learning_rate": 5.432908261559733e-07,
3529
+ "loss": 0.9727,
3530
+ "step": 503
3531
+ },
3532
+ {
3533
+ "epoch": 0.96,
3534
+ "grad_norm": 0.37512968709593764,
3535
+ "learning_rate": 4.990337003164924e-07,
3536
+ "loss": 0.9688,
3537
+ "step": 504
3538
+ },
3539
+ {
3540
+ "epoch": 0.96,
3541
+ "grad_norm": 0.38232480313500466,
3542
+ "learning_rate": 4.5664755925426403e-07,
3543
+ "loss": 0.9844,
3544
+ "step": 505
3545
+ },
3546
+ {
3547
+ "epoch": 0.96,
3548
+ "grad_norm": 0.3700171570622694,
3549
+ "learning_rate": 4.1613400503550114e-07,
3550
+ "loss": 0.9766,
3551
+ "step": 506
3552
+ },
3553
+ {
3554
+ "epoch": 0.96,
3555
+ "grad_norm": 0.3900755929317903,
3556
+ "learning_rate": 3.7749456894834447e-07,
3557
+ "loss": 0.9609,
3558
+ "step": 507
3559
+ },
3560
+ {
3561
+ "epoch": 0.96,
3562
+ "grad_norm": 0.36995686804328504,
3563
+ "learning_rate": 3.4073071144502533e-07,
3564
+ "loss": 0.9688,
3565
+ "step": 508
3566
+ },
3567
+ {
3568
+ "epoch": 0.97,
3569
+ "grad_norm": 0.36023064413895745,
3570
+ "learning_rate": 3.058438220866544e-07,
3571
+ "loss": 0.9883,
3572
+ "step": 509
3573
+ },
3574
+ {
3575
+ "epoch": 0.97,
3576
+ "grad_norm": 0.37996338814367037,
3577
+ "learning_rate": 2.72835219490708e-07,
3578
+ "loss": 0.9805,
3579
+ "step": 510
3580
+ },
3581
+ {
3582
+ "epoch": 0.97,
3583
+ "grad_norm": 0.36362699174525226,
3584
+ "learning_rate": 2.4170615128117357e-07,
3585
+ "loss": 0.9453,
3586
+ "step": 511
3587
+ },
3588
+ {
3589
+ "epoch": 0.97,
3590
+ "grad_norm": 0.37920383685543685,
3591
+ "learning_rate": 2.12457794041393e-07,
3592
+ "loss": 1.0156,
3593
+ "step": 512
3594
+ },
3595
+ {
3596
+ "epoch": 0.97,
3597
+ "grad_norm": 0.3802256086316899,
3598
+ "learning_rate": 1.850912532696092e-07,
3599
+ "loss": 0.9883,
3600
+ "step": 513
3601
+ },
3602
+ {
3603
+ "epoch": 0.98,
3604
+ "grad_norm": 0.3840079426171848,
3605
+ "learning_rate": 1.596075633371774e-07,
3606
+ "loss": 1.0,
3607
+ "step": 514
3608
+ },
3609
+ {
3610
+ "epoch": 0.98,
3611
+ "grad_norm": 0.372033357737712,
3612
+ "learning_rate": 1.3600768744944647e-07,
3613
+ "loss": 0.9727,
3614
+ "step": 515
3615
+ },
3616
+ {
3617
+ "epoch": 0.98,
3618
+ "grad_norm": 0.3700966978882948,
3619
+ "learning_rate": 1.1429251760938231e-07,
3620
+ "loss": 0.9453,
3621
+ "step": 516
3622
+ },
3623
+ {
3624
+ "epoch": 0.98,
3625
+ "grad_norm": 0.37138234312324336,
3626
+ "learning_rate": 9.446287458383385e-08,
3627
+ "loss": 0.9531,
3628
+ "step": 517
3629
+ },
3630
+ {
3631
+ "epoch": 0.98,
3632
+ "grad_norm": 0.38319867619202025,
3633
+ "learning_rate": 7.651950787251339e-08,
3634
+ "loss": 0.9883,
3635
+ "step": 518
3636
+ },
3637
+ {
3638
+ "epoch": 0.98,
3639
+ "grad_norm": 0.36834536474781127,
3640
+ "learning_rate": 6.046309567968588e-08,
3641
+ "loss": 0.9805,
3642
+ "step": 519
3643
+ },
3644
+ {
3645
+ "epoch": 0.99,
3646
+ "grad_norm": 0.3838857136930694,
3647
+ "learning_rate": 4.6294244888500645e-08,
3648
+ "loss": 1.0,
3649
+ "step": 520
3650
+ },
3651
+ {
3652
+ "epoch": 0.99,
3653
+ "grad_norm": 0.37142652746946664,
3654
+ "learning_rate": 3.4013491038087375e-08,
3655
+ "loss": 1.0,
3656
+ "step": 521
3657
+ },
3658
+ {
3659
+ "epoch": 0.99,
3660
+ "grad_norm": 0.3764293979963409,
3661
+ "learning_rate": 2.3621298303294625e-08,
3662
+ "loss": 0.9688,
3663
+ "step": 522
3664
+ },
3665
+ {
3666
+ "epoch": 0.99,
3667
+ "grad_norm": 0.3612657340251834,
3668
+ "learning_rate": 1.511805947714273e-08,
3669
+ "loss": 0.9961,
3670
+ "step": 523
3671
+ },
3672
+ {
3673
+ "epoch": 0.99,
3674
+ "grad_norm": 0.3846047566682503,
3675
+ "learning_rate": 8.504095956002323e-09,
3676
+ "loss": 0.9922,
3677
+ "step": 524
3678
+ },
3679
+ {
3680
+ "epoch": 1.0,
3681
+ "grad_norm": 0.37603252090597145,
3682
+ "learning_rate": 3.7796577274096245e-09,
3683
+ "loss": 0.9727,
3684
+ "step": 525
3685
+ },
3686
+ {
3687
+ "epoch": 1.0,
3688
+ "grad_norm": 0.3918810108171524,
3689
+ "learning_rate": 9.449233606573238e-10,
3690
+ "loss": 0.9805,
3691
+ "step": 526
3692
+ },
3693
+ {
3694
+ "epoch": 1.0,
3695
+ "grad_norm": 0.37221487121132474,
3696
+ "learning_rate": 0.0,
3697
+ "loss": 1.0078,
3698
+ "step": 527
3699
+ },
3700
+ {
3701
+ "epoch": 1.0,
3702
+ "step": 527,
3703
+ "total_flos": 2.9568341572059136e+16,
3704
+ "train_loss": 1.0576598078747628,
3705
+ "train_runtime": 6355.9639,
3706
+ "train_samples_per_second": 340.075,
3707
+ "train_steps_per_second": 0.083
3708
+ }
3709
+ ],
3710
+ "logging_steps": 1.0,
3711
+ "max_steps": 527,
3712
+ "num_input_tokens_seen": 0,
3713
+ "num_train_epochs": 1,
3714
+ "save_steps": 210,
3715
+ "total_flos": 2.9568341572059136e+16,
3716
+ "train_batch_size": 16,
3717
+ "trial_name": null,
3718
+ "trial_params": null
3719
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e832039ee7206cc26424f54e091cb93c28d03dd4e03ebcf5bec918cf7ede8a7
3
+ size 6779