Hugging Face's logo

Nike-Hanmatheekuna
/
nllb-200-3.3B-full

Text2Text Generation
Transformers
Safetensors
m2m_100
Generated from Trainer
Inference Endpoints
Model card Files Community
Nike-Hanmatheekuna commited on
Commit
09afa56
•
1 Parent(s): 3fc910f

Model save

Browse files
Files changed (9) hide show
  1. README.md +55 -0
  2. all_results.json +9 -0
  3. generation_config.json +9 -0
  4. model-00001-of-00003.safetensors +3 -0
  5. model-00002-of-00003.safetensors +3 -0
  6. model-00003-of-00003.safetensors +3 -0
  7. model.safetensors.index.json +1020 -0
  8. train_results.json +9 -0
  9. trainer_state.json +443 -0
README.md ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-4.0
3
+ base_model: facebook/nllb-200-3.3B
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: nllb-200-3.3B-full
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # nllb-200-3.3B-full
15
+
16
+ This model is a fine-tuned version of [facebook/nllb-200-3.3B](https://huggingface.co/facebook/nllb-200-3.3B) on an unknown dataset.
17
+
18
+ ## Model description
19
+
20
+ More information needed
21
+
22
+ ## Intended uses & limitations
23
+
24
+ More information needed
25
+
26
+ ## Training and evaluation data
27
+
28
+ More information needed
29
+
30
+ ## Training procedure
31
+
32
+ ### Training hyperparameters
33
+
34
+ The following hyperparameters were used during training:
35
+ - learning_rate: 2e-05
36
+ - train_batch_size: 2
37
+ - eval_batch_size: 2
38
+ - seed: 42
39
+ - gradient_accumulation_steps: 32
40
+ - total_train_batch_size: 64
41
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
+ - lr_scheduler_type: cosine
43
+ - lr_scheduler_warmup_ratio: 0.1
44
+ - num_epochs: 3
45
+
46
+ ### Training results
47
+
48
+
49
+
50
+ ### Framework versions
51
+
52
+ - Transformers 4.40.2
53
+ - Pytorch 2.2.1+cu121
54
+ - Datasets 2.19.1
55
+ - Tokenizers 0.19.1
all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9978431433840766,
3
+ "total_flos": 2.5671411434264986e+17,
4
+ "train_loss": 0.35637976608556393,
5
+ "train_runtime": 44055.9239,
6
+ "train_samples": 63982,
7
+ "train_samples_per_second": 4.357,
8
+ "train_steps_per_second": 0.068
9
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "decoder_start_token_id": 2,
5
+ "eos_token_id": 2,
6
+ "max_length": 200,
7
+ "pad_token_id": 1,
8
+ "transformers_version": "4.40.2"
9
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:854aad1436b17db9dda9a3bbfb34c8593c3fc5256160810ee11b76c9f8c378e9
3
+ size 4986088344
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdac02ba51ca9accc1c112fbfc007ed5d7e1125d039a3349512e98570c5c19e0
3
+ size 4985688360
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27aa0c57680f4ef6f513018cde1b956c93fe11d9ce8eddfd41c55847c5cfeb10
3
+ size 3407796744
model.safetensors.index.json ADDED
@@ -0,0 +1,1020 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 13379452928
4
+ },
5
+ "weight_map": {
6
+ "model.decoder.layer_norm.bias": "model-00003-of-00003.safetensors",
7
+ "model.decoder.layer_norm.weight": "model-00003-of-00003.safetensors",
8
+ "model.decoder.layers.0.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
9
+ "model.decoder.layers.0.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
10
+ "model.decoder.layers.0.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
11
+ "model.decoder.layers.0.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
12
+ "model.decoder.layers.0.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
13
+ "model.decoder.layers.0.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
14
+ "model.decoder.layers.0.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
15
+ "model.decoder.layers.0.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
16
+ "model.decoder.layers.0.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
17
+ "model.decoder.layers.0.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
18
+ "model.decoder.layers.0.fc1.bias": "model-00002-of-00003.safetensors",
19
+ "model.decoder.layers.0.fc1.weight": "model-00002-of-00003.safetensors",
20
+ "model.decoder.layers.0.fc2.bias": "model-00002-of-00003.safetensors",
21
+ "model.decoder.layers.0.fc2.weight": "model-00002-of-00003.safetensors",
22
+ "model.decoder.layers.0.final_layer_norm.bias": "model-00002-of-00003.safetensors",
23
+ "model.decoder.layers.0.final_layer_norm.weight": "model-00002-of-00003.safetensors",
24
+ "model.decoder.layers.0.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
25
+ "model.decoder.layers.0.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
26
+ "model.decoder.layers.0.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
27
+ "model.decoder.layers.0.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
28
+ "model.decoder.layers.0.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
29
+ "model.decoder.layers.0.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
30
+ "model.decoder.layers.0.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
31
+ "model.decoder.layers.0.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
32
+ "model.decoder.layers.0.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
33
+ "model.decoder.layers.0.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
34
+ "model.decoder.layers.1.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
35
+ "model.decoder.layers.1.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
36
+ "model.decoder.layers.1.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
37
+ "model.decoder.layers.1.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
38
+ "model.decoder.layers.1.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
39
+ "model.decoder.layers.1.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
40
+ "model.decoder.layers.1.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
41
+ "model.decoder.layers.1.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
42
+ "model.decoder.layers.1.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
43
+ "model.decoder.layers.1.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
44
+ "model.decoder.layers.1.fc1.bias": "model-00002-of-00003.safetensors",
45
+ "model.decoder.layers.1.fc1.weight": "model-00002-of-00003.safetensors",
46
+ "model.decoder.layers.1.fc2.bias": "model-00002-of-00003.safetensors",
47
+ "model.decoder.layers.1.fc2.weight": "model-00002-of-00003.safetensors",
48
+ "model.decoder.layers.1.final_layer_norm.bias": "model-00002-of-00003.safetensors",
49
+ "model.decoder.layers.1.final_layer_norm.weight": "model-00002-of-00003.safetensors",
50
+ "model.decoder.layers.1.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
51
+ "model.decoder.layers.1.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
52
+ "model.decoder.layers.1.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
53
+ "model.decoder.layers.1.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
54
+ "model.decoder.layers.1.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
55
+ "model.decoder.layers.1.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
56
+ "model.decoder.layers.1.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
57
+ "model.decoder.layers.1.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
58
+ "model.decoder.layers.1.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
59
+ "model.decoder.layers.1.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
60
+ "model.decoder.layers.10.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
61
+ "model.decoder.layers.10.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
62
+ "model.decoder.layers.10.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
63
+ "model.decoder.layers.10.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
64
+ "model.decoder.layers.10.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
65
+ "model.decoder.layers.10.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
66
+ "model.decoder.layers.10.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
67
+ "model.decoder.layers.10.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
68
+ "model.decoder.layers.10.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
69
+ "model.decoder.layers.10.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
70
+ "model.decoder.layers.10.fc1.bias": "model-00002-of-00003.safetensors",
71
+ "model.decoder.layers.10.fc1.weight": "model-00002-of-00003.safetensors",
72
+ "model.decoder.layers.10.fc2.bias": "model-00002-of-00003.safetensors",
73
+ "model.decoder.layers.10.fc2.weight": "model-00002-of-00003.safetensors",
74
+ "model.decoder.layers.10.final_layer_norm.bias": "model-00002-of-00003.safetensors",
75
+ "model.decoder.layers.10.final_layer_norm.weight": "model-00002-of-00003.safetensors",
76
+ "model.decoder.layers.10.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
77
+ "model.decoder.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
78
+ "model.decoder.layers.10.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
79
+ "model.decoder.layers.10.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
80
+ "model.decoder.layers.10.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
81
+ "model.decoder.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
82
+ "model.decoder.layers.10.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
83
+ "model.decoder.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
84
+ "model.decoder.layers.10.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
85
+ "model.decoder.layers.10.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
86
+ "model.decoder.layers.11.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
87
+ "model.decoder.layers.11.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
88
+ "model.decoder.layers.11.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
89
+ "model.decoder.layers.11.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
90
+ "model.decoder.layers.11.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
91
+ "model.decoder.layers.11.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
92
+ "model.decoder.layers.11.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
93
+ "model.decoder.layers.11.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
94
+ "model.decoder.layers.11.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
95
+ "model.decoder.layers.11.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
96
+ "model.decoder.layers.11.fc1.bias": "model-00003-of-00003.safetensors",
97
+ "model.decoder.layers.11.fc1.weight": "model-00003-of-00003.safetensors",
98
+ "model.decoder.layers.11.fc2.bias": "model-00003-of-00003.safetensors",
99
+ "model.decoder.layers.11.fc2.weight": "model-00003-of-00003.safetensors",
100
+ "model.decoder.layers.11.final_layer_norm.bias": "model-00003-of-00003.safetensors",
101
+ "model.decoder.layers.11.final_layer_norm.weight": "model-00003-of-00003.safetensors",
102
+ "model.decoder.layers.11.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
103
+ "model.decoder.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
104
+ "model.decoder.layers.11.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
105
+ "model.decoder.layers.11.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
106
+ "model.decoder.layers.11.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
107
+ "model.decoder.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
108
+ "model.decoder.layers.11.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
109
+ "model.decoder.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
110
+ "model.decoder.layers.11.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
111
+ "model.decoder.layers.11.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
112
+ "model.decoder.layers.12.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
113
+ "model.decoder.layers.12.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
114
+ "model.decoder.layers.12.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
115
+ "model.decoder.layers.12.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
116
+ "model.decoder.layers.12.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
117
+ "model.decoder.layers.12.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
118
+ "model.decoder.layers.12.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
119
+ "model.decoder.layers.12.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
120
+ "model.decoder.layers.12.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
121
+ "model.decoder.layers.12.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
122
+ "model.decoder.layers.12.fc1.bias": "model-00003-of-00003.safetensors",
123
+ "model.decoder.layers.12.fc1.weight": "model-00003-of-00003.safetensors",
124
+ "model.decoder.layers.12.fc2.bias": "model-00003-of-00003.safetensors",
125
+ "model.decoder.layers.12.fc2.weight": "model-00003-of-00003.safetensors",
126
+ "model.decoder.layers.12.final_layer_norm.bias": "model-00003-of-00003.safetensors",
127
+ "model.decoder.layers.12.final_layer_norm.weight": "model-00003-of-00003.safetensors",
128
+ "model.decoder.layers.12.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
129
+ "model.decoder.layers.12.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
130
+ "model.decoder.layers.12.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
131
+ "model.decoder.layers.12.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
132
+ "model.decoder.layers.12.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
133
+ "model.decoder.layers.12.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
134
+ "model.decoder.layers.12.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
135
+ "model.decoder.layers.12.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
136
+ "model.decoder.layers.12.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
137
+ "model.decoder.layers.12.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
138
+ "model.decoder.layers.13.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
139
+ "model.decoder.layers.13.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
140
+ "model.decoder.layers.13.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
141
+ "model.decoder.layers.13.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
142
+ "model.decoder.layers.13.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
143
+ "model.decoder.layers.13.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
144
+ "model.decoder.layers.13.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
145
+ "model.decoder.layers.13.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
146
+ "model.decoder.layers.13.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
147
+ "model.decoder.layers.13.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
148
+ "model.decoder.layers.13.fc1.bias": "model-00003-of-00003.safetensors",
149
+ "model.decoder.layers.13.fc1.weight": "model-00003-of-00003.safetensors",
150
+ "model.decoder.layers.13.fc2.bias": "model-00003-of-00003.safetensors",
151
+ "model.decoder.layers.13.fc2.weight": "model-00003-of-00003.safetensors",
152
+ "model.decoder.layers.13.final_layer_norm.bias": "model-00003-of-00003.safetensors",
153
+ "model.decoder.layers.13.final_layer_norm.weight": "model-00003-of-00003.safetensors",
154
+ "model.decoder.layers.13.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
155
+ "model.decoder.layers.13.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
156
+ "model.decoder.layers.13.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
157
+ "model.decoder.layers.13.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
158
+ "model.decoder.layers.13.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
159
+ "model.decoder.layers.13.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
160
+ "model.decoder.layers.13.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
161
+ "model.decoder.layers.13.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
162
+ "model.decoder.layers.13.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
163
+ "model.decoder.layers.13.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
164
+ "model.decoder.layers.14.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
165
+ "model.decoder.layers.14.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
166
+ "model.decoder.layers.14.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
167
+ "model.decoder.layers.14.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
168
+ "model.decoder.layers.14.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
169
+ "model.decoder.layers.14.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
170
+ "model.decoder.layers.14.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
171
+ "model.decoder.layers.14.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
172
+ "model.decoder.layers.14.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
173
+ "model.decoder.layers.14.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
174
+ "model.decoder.layers.14.fc1.bias": "model-00003-of-00003.safetensors",
175
+ "model.decoder.layers.14.fc1.weight": "model-00003-of-00003.safetensors",
176
+ "model.decoder.layers.14.fc2.bias": "model-00003-of-00003.safetensors",
177
+ "model.decoder.layers.14.fc2.weight": "model-00003-of-00003.safetensors",
178
+ "model.decoder.layers.14.final_layer_norm.bias": "model-00003-of-00003.safetensors",
179
+ "model.decoder.layers.14.final_layer_norm.weight": "model-00003-of-00003.safetensors",
180
+ "model.decoder.layers.14.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
181
+ "model.decoder.layers.14.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
182
+ "model.decoder.layers.14.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
183
+ "model.decoder.layers.14.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
184
+ "model.decoder.layers.14.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
185
+ "model.decoder.layers.14.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
186
+ "model.decoder.layers.14.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
187
+ "model.decoder.layers.14.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
188
+ "model.decoder.layers.14.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
189
+ "model.decoder.layers.14.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
190
+ "model.decoder.layers.15.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
191
+ "model.decoder.layers.15.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
192
+ "model.decoder.layers.15.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
193
+ "model.decoder.layers.15.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
194
+ "model.decoder.layers.15.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
195
+ "model.decoder.layers.15.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
196
+ "model.decoder.layers.15.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
197
+ "model.decoder.layers.15.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
198
+ "model.decoder.layers.15.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
199
+ "model.decoder.layers.15.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
200
+ "model.decoder.layers.15.fc1.bias": "model-00003-of-00003.safetensors",
201
+ "model.decoder.layers.15.fc1.weight": "model-00003-of-00003.safetensors",
202
+ "model.decoder.layers.15.fc2.bias": "model-00003-of-00003.safetensors",
203
+ "model.decoder.layers.15.fc2.weight": "model-00003-of-00003.safetensors",
204
+ "model.decoder.layers.15.final_layer_norm.bias": "model-00003-of-00003.safetensors",
205
+ "model.decoder.layers.15.final_layer_norm.weight": "model-00003-of-00003.safetensors",
206
+ "model.decoder.layers.15.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
207
+ "model.decoder.layers.15.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
208
+ "model.decoder.layers.15.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
209
+ "model.decoder.layers.15.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
210
+ "model.decoder.layers.15.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
211
+ "model.decoder.layers.15.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
212
+ "model.decoder.layers.15.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
213
+ "model.decoder.layers.15.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
214
+ "model.decoder.layers.15.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
215
+ "model.decoder.layers.15.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
216
+ "model.decoder.layers.16.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
217
+ "model.decoder.layers.16.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
218
+ "model.decoder.layers.16.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
219
+ "model.decoder.layers.16.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
220
+ "model.decoder.layers.16.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
221
+ "model.decoder.layers.16.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
222
+ "model.decoder.layers.16.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
223
+ "model.decoder.layers.16.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
224
+ "model.decoder.layers.16.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
225
+ "model.decoder.layers.16.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
226
+ "model.decoder.layers.16.fc1.bias": "model-00003-of-00003.safetensors",
227
+ "model.decoder.layers.16.fc1.weight": "model-00003-of-00003.safetensors",
228
+ "model.decoder.layers.16.fc2.bias": "model-00003-of-00003.safetensors",
229
+ "model.decoder.layers.16.fc2.weight": "model-00003-of-00003.safetensors",
230
+ "model.decoder.layers.16.final_layer_norm.bias": "model-00003-of-00003.safetensors",
231
+ "model.decoder.layers.16.final_layer_norm.weight": "model-00003-of-00003.safetensors",
232
+ "model.decoder.layers.16.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
233
+ "model.decoder.layers.16.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
234
+ "model.decoder.layers.16.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
235
+ "model.decoder.layers.16.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
236
+ "model.decoder.layers.16.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
237
+ "model.decoder.layers.16.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
238
+ "model.decoder.layers.16.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
239
+ "model.decoder.layers.16.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
240
+ "model.decoder.layers.16.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
241
+ "model.decoder.layers.16.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
242
+ "model.decoder.layers.17.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
243
+ "model.decoder.layers.17.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
244
+ "model.decoder.layers.17.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
245
+ "model.decoder.layers.17.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
246
+ "model.decoder.layers.17.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
247
+ "model.decoder.layers.17.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
248
+ "model.decoder.layers.17.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
249
+ "model.decoder.layers.17.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
250
+ "model.decoder.layers.17.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
251
+ "model.decoder.layers.17.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
252
+ "model.decoder.layers.17.fc1.bias": "model-00003-of-00003.safetensors",
253
+ "model.decoder.layers.17.fc1.weight": "model-00003-of-00003.safetensors",
254
+ "model.decoder.layers.17.fc2.bias": "model-00003-of-00003.safetensors",
255
+ "model.decoder.layers.17.fc2.weight": "model-00003-of-00003.safetensors",
256
+ "model.decoder.layers.17.final_layer_norm.bias": "model-00003-of-00003.safetensors",
257
+ "model.decoder.layers.17.final_layer_norm.weight": "model-00003-of-00003.safetensors",
258
+ "model.decoder.layers.17.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
259
+ "model.decoder.layers.17.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
260
+ "model.decoder.layers.17.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
261
+ "model.decoder.layers.17.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
262
+ "model.decoder.layers.17.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
263
+ "model.decoder.layers.17.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
264
+ "model.decoder.layers.17.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
265
+ "model.decoder.layers.17.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
266
+ "model.decoder.layers.17.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
267
+ "model.decoder.layers.17.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
268
+ "model.decoder.layers.18.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
269
+ "model.decoder.layers.18.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
270
+ "model.decoder.layers.18.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
271
+ "model.decoder.layers.18.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
272
+ "model.decoder.layers.18.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
273
+ "model.decoder.layers.18.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
274
+ "model.decoder.layers.18.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
275
+ "model.decoder.layers.18.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
276
+ "model.decoder.layers.18.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
277
+ "model.decoder.layers.18.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
278
+ "model.decoder.layers.18.fc1.bias": "model-00003-of-00003.safetensors",
279
+ "model.decoder.layers.18.fc1.weight": "model-00003-of-00003.safetensors",
280
+ "model.decoder.layers.18.fc2.bias": "model-00003-of-00003.safetensors",
281
+ "model.decoder.layers.18.fc2.weight": "model-00003-of-00003.safetensors",
282
+ "model.decoder.layers.18.final_layer_norm.bias": "model-00003-of-00003.safetensors",
283
+ "model.decoder.layers.18.final_layer_norm.weight": "model-00003-of-00003.safetensors",
284
+ "model.decoder.layers.18.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
285
+ "model.decoder.layers.18.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
286
+ "model.decoder.layers.18.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
287
+ "model.decoder.layers.18.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
288
+ "model.decoder.layers.18.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
289
+ "model.decoder.layers.18.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
290
+ "model.decoder.layers.18.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
291
+ "model.decoder.layers.18.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
292
+ "model.decoder.layers.18.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
293
+ "model.decoder.layers.18.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
294
+ "model.decoder.layers.19.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
295
+ "model.decoder.layers.19.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
296
+ "model.decoder.layers.19.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
297
+ "model.decoder.layers.19.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
298
+ "model.decoder.layers.19.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
299
+ "model.decoder.layers.19.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
300
+ "model.decoder.layers.19.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
301
+ "model.decoder.layers.19.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
302
+ "model.decoder.layers.19.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
303
+ "model.decoder.layers.19.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
304
+ "model.decoder.layers.19.fc1.bias": "model-00003-of-00003.safetensors",
305
+ "model.decoder.layers.19.fc1.weight": "model-00003-of-00003.safetensors",
306
+ "model.decoder.layers.19.fc2.bias": "model-00003-of-00003.safetensors",
307
+ "model.decoder.layers.19.fc2.weight": "model-00003-of-00003.safetensors",
308
+ "model.decoder.layers.19.final_layer_norm.bias": "model-00003-of-00003.safetensors",
309
+ "model.decoder.layers.19.final_layer_norm.weight": "model-00003-of-00003.safetensors",
310
+ "model.decoder.layers.19.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
311
+ "model.decoder.layers.19.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
312
+ "model.decoder.layers.19.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
313
+ "model.decoder.layers.19.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
314
+ "model.decoder.layers.19.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
315
+ "model.decoder.layers.19.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
316
+ "model.decoder.layers.19.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
317
+ "model.decoder.layers.19.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
318
+ "model.decoder.layers.19.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
319
+ "model.decoder.layers.19.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
320
+ "model.decoder.layers.2.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
321
+ "model.decoder.layers.2.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
322
+ "model.decoder.layers.2.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
323
+ "model.decoder.layers.2.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
324
+ "model.decoder.layers.2.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
325
+ "model.decoder.layers.2.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
326
+ "model.decoder.layers.2.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
327
+ "model.decoder.layers.2.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
328
+ "model.decoder.layers.2.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
329
+ "model.decoder.layers.2.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
330
+ "model.decoder.layers.2.fc1.bias": "model-00002-of-00003.safetensors",
331
+ "model.decoder.layers.2.fc1.weight": "model-00002-of-00003.safetensors",
332
+ "model.decoder.layers.2.fc2.bias": "model-00002-of-00003.safetensors",
333
+ "model.decoder.layers.2.fc2.weight": "model-00002-of-00003.safetensors",
334
+ "model.decoder.layers.2.final_layer_norm.bias": "model-00002-of-00003.safetensors",
335
+ "model.decoder.layers.2.final_layer_norm.weight": "model-00002-of-00003.safetensors",
336
+ "model.decoder.layers.2.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
337
+ "model.decoder.layers.2.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
338
+ "model.decoder.layers.2.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
339
+ "model.decoder.layers.2.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
340
+ "model.decoder.layers.2.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
341
+ "model.decoder.layers.2.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
342
+ "model.decoder.layers.2.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
343
+ "model.decoder.layers.2.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
344
+ "model.decoder.layers.2.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
345
+ "model.decoder.layers.2.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
346
+ "model.decoder.layers.20.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
347
+ "model.decoder.layers.20.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
348
+ "model.decoder.layers.20.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
349
+ "model.decoder.layers.20.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
350
+ "model.decoder.layers.20.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
351
+ "model.decoder.layers.20.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
352
+ "model.decoder.layers.20.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
353
+ "model.decoder.layers.20.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
354
+ "model.decoder.layers.20.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
355
+ "model.decoder.layers.20.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
356
+ "model.decoder.layers.20.fc1.bias": "model-00003-of-00003.safetensors",
357
+ "model.decoder.layers.20.fc1.weight": "model-00003-of-00003.safetensors",
358
+ "model.decoder.layers.20.fc2.bias": "model-00003-of-00003.safetensors",
359
+ "model.decoder.layers.20.fc2.weight": "model-00003-of-00003.safetensors",
360
+ "model.decoder.layers.20.final_layer_norm.bias": "model-00003-of-00003.safetensors",
361
+ "model.decoder.layers.20.final_layer_norm.weight": "model-00003-of-00003.safetensors",
362
+ "model.decoder.layers.20.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
363
+ "model.decoder.layers.20.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
364
+ "model.decoder.layers.20.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
365
+ "model.decoder.layers.20.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
366
+ "model.decoder.layers.20.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
367
+ "model.decoder.layers.20.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
368
+ "model.decoder.layers.20.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
369
+ "model.decoder.layers.20.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
370
+ "model.decoder.layers.20.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
371
+ "model.decoder.layers.20.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
372
+ "model.decoder.layers.21.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
373
+ "model.decoder.layers.21.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
374
+ "model.decoder.layers.21.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
375
+ "model.decoder.layers.21.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
376
+ "model.decoder.layers.21.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
377
+ "model.decoder.layers.21.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
378
+ "model.decoder.layers.21.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
379
+ "model.decoder.layers.21.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
380
+ "model.decoder.layers.21.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
381
+ "model.decoder.layers.21.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
382
+ "model.decoder.layers.21.fc1.bias": "model-00003-of-00003.safetensors",
383
+ "model.decoder.layers.21.fc1.weight": "model-00003-of-00003.safetensors",
384
+ "model.decoder.layers.21.fc2.bias": "model-00003-of-00003.safetensors",
385
+ "model.decoder.layers.21.fc2.weight": "model-00003-of-00003.safetensors",
386
+ "model.decoder.layers.21.final_layer_norm.bias": "model-00003-of-00003.safetensors",
387
+ "model.decoder.layers.21.final_layer_norm.weight": "model-00003-of-00003.safetensors",
388
+ "model.decoder.layers.21.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
389
+ "model.decoder.layers.21.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
390
+ "model.decoder.layers.21.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
391
+ "model.decoder.layers.21.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
392
+ "model.decoder.layers.21.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
393
+ "model.decoder.layers.21.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
394
+ "model.decoder.layers.21.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
395
+ "model.decoder.layers.21.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
396
+ "model.decoder.layers.21.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
397
+ "model.decoder.layers.21.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
398
+ "model.decoder.layers.22.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
399
+ "model.decoder.layers.22.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
400
+ "model.decoder.layers.22.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
401
+ "model.decoder.layers.22.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
402
+ "model.decoder.layers.22.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
403
+ "model.decoder.layers.22.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
404
+ "model.decoder.layers.22.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
405
+ "model.decoder.layers.22.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
406
+ "model.decoder.layers.22.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
407
+ "model.decoder.layers.22.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
408
+ "model.decoder.layers.22.fc1.bias": "model-00003-of-00003.safetensors",
409
+ "model.decoder.layers.22.fc1.weight": "model-00003-of-00003.safetensors",
410
+ "model.decoder.layers.22.fc2.bias": "model-00003-of-00003.safetensors",
411
+ "model.decoder.layers.22.fc2.weight": "model-00003-of-00003.safetensors",
412
+ "model.decoder.layers.22.final_layer_norm.bias": "model-00003-of-00003.safetensors",
413
+ "model.decoder.layers.22.final_layer_norm.weight": "model-00003-of-00003.safetensors",
414
+ "model.decoder.layers.22.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
415
+ "model.decoder.layers.22.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
416
+ "model.decoder.layers.22.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
417
+ "model.decoder.layers.22.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
418
+ "model.decoder.layers.22.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
419
+ "model.decoder.layers.22.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
420
+ "model.decoder.layers.22.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
421
+ "model.decoder.layers.22.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
422
+ "model.decoder.layers.22.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
423
+ "model.decoder.layers.22.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
424
+ "model.decoder.layers.23.encoder_attn.k_proj.bias": "model-00003-of-00003.safetensors",
425
+ "model.decoder.layers.23.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
426
+ "model.decoder.layers.23.encoder_attn.out_proj.bias": "model-00003-of-00003.safetensors",
427
+ "model.decoder.layers.23.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
428
+ "model.decoder.layers.23.encoder_attn.q_proj.bias": "model-00003-of-00003.safetensors",
429
+ "model.decoder.layers.23.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
430
+ "model.decoder.layers.23.encoder_attn.v_proj.bias": "model-00003-of-00003.safetensors",
431
+ "model.decoder.layers.23.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
432
+ "model.decoder.layers.23.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
433
+ "model.decoder.layers.23.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
434
+ "model.decoder.layers.23.fc1.bias": "model-00003-of-00003.safetensors",
435
+ "model.decoder.layers.23.fc1.weight": "model-00003-of-00003.safetensors",
436
+ "model.decoder.layers.23.fc2.bias": "model-00003-of-00003.safetensors",
437
+ "model.decoder.layers.23.fc2.weight": "model-00003-of-00003.safetensors",
438
+ "model.decoder.layers.23.final_layer_norm.bias": "model-00003-of-00003.safetensors",
439
+ "model.decoder.layers.23.final_layer_norm.weight": "model-00003-of-00003.safetensors",
440
+ "model.decoder.layers.23.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
441
+ "model.decoder.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
442
+ "model.decoder.layers.23.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
443
+ "model.decoder.layers.23.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
444
+ "model.decoder.layers.23.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
445
+ "model.decoder.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
446
+ "model.decoder.layers.23.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
447
+ "model.decoder.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
448
+ "model.decoder.layers.23.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
449
+ "model.decoder.layers.23.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
450
+ "model.decoder.layers.3.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
451
+ "model.decoder.layers.3.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
452
+ "model.decoder.layers.3.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
453
+ "model.decoder.layers.3.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
454
+ "model.decoder.layers.3.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
455
+ "model.decoder.layers.3.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
456
+ "model.decoder.layers.3.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
457
+ "model.decoder.layers.3.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
458
+ "model.decoder.layers.3.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
459
+ "model.decoder.layers.3.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
460
+ "model.decoder.layers.3.fc1.bias": "model-00002-of-00003.safetensors",
461
+ "model.decoder.layers.3.fc1.weight": "model-00002-of-00003.safetensors",
462
+ "model.decoder.layers.3.fc2.bias": "model-00002-of-00003.safetensors",
463
+ "model.decoder.layers.3.fc2.weight": "model-00002-of-00003.safetensors",
464
+ "model.decoder.layers.3.final_layer_norm.bias": "model-00002-of-00003.safetensors",
465
+ "model.decoder.layers.3.final_layer_norm.weight": "model-00002-of-00003.safetensors",
466
+ "model.decoder.layers.3.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
467
+ "model.decoder.layers.3.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
468
+ "model.decoder.layers.3.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
469
+ "model.decoder.layers.3.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
470
+ "model.decoder.layers.3.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
471
+ "model.decoder.layers.3.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
472
+ "model.decoder.layers.3.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
473
+ "model.decoder.layers.3.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
474
+ "model.decoder.layers.3.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
475
+ "model.decoder.layers.3.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
476
+ "model.decoder.layers.4.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
477
+ "model.decoder.layers.4.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
478
+ "model.decoder.layers.4.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
479
+ "model.decoder.layers.4.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
480
+ "model.decoder.layers.4.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
481
+ "model.decoder.layers.4.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
482
+ "model.decoder.layers.4.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
483
+ "model.decoder.layers.4.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
484
+ "model.decoder.layers.4.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
485
+ "model.decoder.layers.4.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
486
+ "model.decoder.layers.4.fc1.bias": "model-00002-of-00003.safetensors",
487
+ "model.decoder.layers.4.fc1.weight": "model-00002-of-00003.safetensors",
488
+ "model.decoder.layers.4.fc2.bias": "model-00002-of-00003.safetensors",
489
+ "model.decoder.layers.4.fc2.weight": "model-00002-of-00003.safetensors",
490
+ "model.decoder.layers.4.final_layer_norm.bias": "model-00002-of-00003.safetensors",
491
+ "model.decoder.layers.4.final_layer_norm.weight": "model-00002-of-00003.safetensors",
492
+ "model.decoder.layers.4.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
493
+ "model.decoder.layers.4.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
494
+ "model.decoder.layers.4.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
495
+ "model.decoder.layers.4.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
496
+ "model.decoder.layers.4.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
497
+ "model.decoder.layers.4.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
498
+ "model.decoder.layers.4.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
499
+ "model.decoder.layers.4.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
500
+ "model.decoder.layers.4.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
501
+ "model.decoder.layers.4.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
502
+ "model.decoder.layers.5.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
503
+ "model.decoder.layers.5.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
504
+ "model.decoder.layers.5.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
505
+ "model.decoder.layers.5.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
506
+ "model.decoder.layers.5.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
507
+ "model.decoder.layers.5.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
508
+ "model.decoder.layers.5.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
509
+ "model.decoder.layers.5.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
510
+ "model.decoder.layers.5.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
511
+ "model.decoder.layers.5.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
512
+ "model.decoder.layers.5.fc1.bias": "model-00002-of-00003.safetensors",
513
+ "model.decoder.layers.5.fc1.weight": "model-00002-of-00003.safetensors",
514
+ "model.decoder.layers.5.fc2.bias": "model-00002-of-00003.safetensors",
515
+ "model.decoder.layers.5.fc2.weight": "model-00002-of-00003.safetensors",
516
+ "model.decoder.layers.5.final_layer_norm.bias": "model-00002-of-00003.safetensors",
517
+ "model.decoder.layers.5.final_layer_norm.weight": "model-00002-of-00003.safetensors",
518
+ "model.decoder.layers.5.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
519
+ "model.decoder.layers.5.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
520
+ "model.decoder.layers.5.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
521
+ "model.decoder.layers.5.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
522
+ "model.decoder.layers.5.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
523
+ "model.decoder.layers.5.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
524
+ "model.decoder.layers.5.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
525
+ "model.decoder.layers.5.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
526
+ "model.decoder.layers.5.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
527
+ "model.decoder.layers.5.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
528
+ "model.decoder.layers.6.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
529
+ "model.decoder.layers.6.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
530
+ "model.decoder.layers.6.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
531
+ "model.decoder.layers.6.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
532
+ "model.decoder.layers.6.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
533
+ "model.decoder.layers.6.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
534
+ "model.decoder.layers.6.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
535
+ "model.decoder.layers.6.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
536
+ "model.decoder.layers.6.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
537
+ "model.decoder.layers.6.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
538
+ "model.decoder.layers.6.fc1.bias": "model-00002-of-00003.safetensors",
539
+ "model.decoder.layers.6.fc1.weight": "model-00002-of-00003.safetensors",
540
+ "model.decoder.layers.6.fc2.bias": "model-00002-of-00003.safetensors",
541
+ "model.decoder.layers.6.fc2.weight": "model-00002-of-00003.safetensors",
542
+ "model.decoder.layers.6.final_layer_norm.bias": "model-00002-of-00003.safetensors",
543
+ "model.decoder.layers.6.final_layer_norm.weight": "model-00002-of-00003.safetensors",
544
+ "model.decoder.layers.6.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
545
+ "model.decoder.layers.6.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
546
+ "model.decoder.layers.6.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
547
+ "model.decoder.layers.6.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
548
+ "model.decoder.layers.6.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
549
+ "model.decoder.layers.6.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
550
+ "model.decoder.layers.6.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
551
+ "model.decoder.layers.6.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
552
+ "model.decoder.layers.6.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
553
+ "model.decoder.layers.6.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
554
+ "model.decoder.layers.7.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
555
+ "model.decoder.layers.7.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
556
+ "model.decoder.layers.7.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
557
+ "model.decoder.layers.7.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
558
+ "model.decoder.layers.7.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
559
+ "model.decoder.layers.7.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
560
+ "model.decoder.layers.7.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
561
+ "model.decoder.layers.7.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
562
+ "model.decoder.layers.7.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
563
+ "model.decoder.layers.7.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
564
+ "model.decoder.layers.7.fc1.bias": "model-00002-of-00003.safetensors",
565
+ "model.decoder.layers.7.fc1.weight": "model-00002-of-00003.safetensors",
566
+ "model.decoder.layers.7.fc2.bias": "model-00002-of-00003.safetensors",
567
+ "model.decoder.layers.7.fc2.weight": "model-00002-of-00003.safetensors",
568
+ "model.decoder.layers.7.final_layer_norm.bias": "model-00002-of-00003.safetensors",
569
+ "model.decoder.layers.7.final_layer_norm.weight": "model-00002-of-00003.safetensors",
570
+ "model.decoder.layers.7.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
571
+ "model.decoder.layers.7.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
572
+ "model.decoder.layers.7.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
573
+ "model.decoder.layers.7.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
574
+ "model.decoder.layers.7.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
575
+ "model.decoder.layers.7.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
576
+ "model.decoder.layers.7.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
577
+ "model.decoder.layers.7.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
578
+ "model.decoder.layers.7.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
579
+ "model.decoder.layers.7.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
580
+ "model.decoder.layers.8.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
581
+ "model.decoder.layers.8.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
582
+ "model.decoder.layers.8.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
583
+ "model.decoder.layers.8.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
584
+ "model.decoder.layers.8.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
585
+ "model.decoder.layers.8.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
586
+ "model.decoder.layers.8.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
587
+ "model.decoder.layers.8.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
588
+ "model.decoder.layers.8.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
589
+ "model.decoder.layers.8.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
590
+ "model.decoder.layers.8.fc1.bias": "model-00002-of-00003.safetensors",
591
+ "model.decoder.layers.8.fc1.weight": "model-00002-of-00003.safetensors",
592
+ "model.decoder.layers.8.fc2.bias": "model-00002-of-00003.safetensors",
593
+ "model.decoder.layers.8.fc2.weight": "model-00002-of-00003.safetensors",
594
+ "model.decoder.layers.8.final_layer_norm.bias": "model-00002-of-00003.safetensors",
595
+ "model.decoder.layers.8.final_layer_norm.weight": "model-00002-of-00003.safetensors",
596
+ "model.decoder.layers.8.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
597
+ "model.decoder.layers.8.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
598
+ "model.decoder.layers.8.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
599
+ "model.decoder.layers.8.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
600
+ "model.decoder.layers.8.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
601
+ "model.decoder.layers.8.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
602
+ "model.decoder.layers.8.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
603
+ "model.decoder.layers.8.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
604
+ "model.decoder.layers.8.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
605
+ "model.decoder.layers.8.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
606
+ "model.decoder.layers.9.encoder_attn.k_proj.bias": "model-00002-of-00003.safetensors",
607
+ "model.decoder.layers.9.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
608
+ "model.decoder.layers.9.encoder_attn.out_proj.bias": "model-00002-of-00003.safetensors",
609
+ "model.decoder.layers.9.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
610
+ "model.decoder.layers.9.encoder_attn.q_proj.bias": "model-00002-of-00003.safetensors",
611
+ "model.decoder.layers.9.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
612
+ "model.decoder.layers.9.encoder_attn.v_proj.bias": "model-00002-of-00003.safetensors",
613
+ "model.decoder.layers.9.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
614
+ "model.decoder.layers.9.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
615
+ "model.decoder.layers.9.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
616
+ "model.decoder.layers.9.fc1.bias": "model-00002-of-00003.safetensors",
617
+ "model.decoder.layers.9.fc1.weight": "model-00002-of-00003.safetensors",
618
+ "model.decoder.layers.9.fc2.bias": "model-00002-of-00003.safetensors",
619
+ "model.decoder.layers.9.fc2.weight": "model-00002-of-00003.safetensors",
620
+ "model.decoder.layers.9.final_layer_norm.bias": "model-00002-of-00003.safetensors",
621
+ "model.decoder.layers.9.final_layer_norm.weight": "model-00002-of-00003.safetensors",
622
+ "model.decoder.layers.9.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
623
+ "model.decoder.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
624
+ "model.decoder.layers.9.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
625
+ "model.decoder.layers.9.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
626
+ "model.decoder.layers.9.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
627
+ "model.decoder.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
628
+ "model.decoder.layers.9.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
629
+ "model.decoder.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
630
+ "model.decoder.layers.9.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
631
+ "model.decoder.layers.9.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
632
+ "model.encoder.layer_norm.bias": "model-00002-of-00003.safetensors",
633
+ "model.encoder.layer_norm.weight": "model-00002-of-00003.safetensors",
634
+ "model.encoder.layers.0.fc1.bias": "model-00001-of-00003.safetensors",
635
+ "model.encoder.layers.0.fc1.weight": "model-00001-of-00003.safetensors",
636
+ "model.encoder.layers.0.fc2.bias": "model-00001-of-00003.safetensors",
637
+ "model.encoder.layers.0.fc2.weight": "model-00001-of-00003.safetensors",
638
+ "model.encoder.layers.0.final_layer_norm.bias": "model-00001-of-00003.safetensors",
639
+ "model.encoder.layers.0.final_layer_norm.weight": "model-00001-of-00003.safetensors",
640
+ "model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
641
+ "model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
642
+ "model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
643
+ "model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
644
+ "model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
645
+ "model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
646
+ "model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
647
+ "model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
648
+ "model.encoder.layers.0.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
649
+ "model.encoder.layers.0.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
650
+ "model.encoder.layers.1.fc1.bias": "model-00001-of-00003.safetensors",
651
+ "model.encoder.layers.1.fc1.weight": "model-00001-of-00003.safetensors",
652
+ "model.encoder.layers.1.fc2.bias": "model-00001-of-00003.safetensors",
653
+ "model.encoder.layers.1.fc2.weight": "model-00001-of-00003.safetensors",
654
+ "model.encoder.layers.1.final_layer_norm.bias": "model-00001-of-00003.safetensors",
655
+ "model.encoder.layers.1.final_layer_norm.weight": "model-00001-of-00003.safetensors",
656
+ "model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
657
+ "model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
658
+ "model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
659
+ "model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
660
+ "model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
661
+ "model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
662
+ "model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
663
+ "model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
664
+ "model.encoder.layers.1.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
665
+ "model.encoder.layers.1.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
666
+ "model.encoder.layers.10.fc1.bias": "model-00001-of-00003.safetensors",
667
+ "model.encoder.layers.10.fc1.weight": "model-00001-of-00003.safetensors",
668
+ "model.encoder.layers.10.fc2.bias": "model-00001-of-00003.safetensors",
669
+ "model.encoder.layers.10.fc2.weight": "model-00001-of-00003.safetensors",
670
+ "model.encoder.layers.10.final_layer_norm.bias": "model-00001-of-00003.safetensors",
671
+ "model.encoder.layers.10.final_layer_norm.weight": "model-00001-of-00003.safetensors",
672
+ "model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
673
+ "model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
674
+ "model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
675
+ "model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
676
+ "model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
677
+ "model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
678
+ "model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
679
+ "model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
680
+ "model.encoder.layers.10.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
681
+ "model.encoder.layers.10.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
682
+ "model.encoder.layers.11.fc1.bias": "model-00001-of-00003.safetensors",
683
+ "model.encoder.layers.11.fc1.weight": "model-00001-of-00003.safetensors",
684
+ "model.encoder.layers.11.fc2.bias": "model-00001-of-00003.safetensors",
685
+ "model.encoder.layers.11.fc2.weight": "model-00001-of-00003.safetensors",
686
+ "model.encoder.layers.11.final_layer_norm.bias": "model-00001-of-00003.safetensors",
687
+ "model.encoder.layers.11.final_layer_norm.weight": "model-00001-of-00003.safetensors",
688
+ "model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
689
+ "model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
690
+ "model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
691
+ "model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
692
+ "model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
693
+ "model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
694
+ "model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
695
+ "model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
696
+ "model.encoder.layers.11.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
697
+ "model.encoder.layers.11.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
698
+ "model.encoder.layers.12.fc1.bias": "model-00001-of-00003.safetensors",
699
+ "model.encoder.layers.12.fc1.weight": "model-00001-of-00003.safetensors",
700
+ "model.encoder.layers.12.fc2.bias": "model-00001-of-00003.safetensors",
701
+ "model.encoder.layers.12.fc2.weight": "model-00001-of-00003.safetensors",
702
+ "model.encoder.layers.12.final_layer_norm.bias": "model-00001-of-00003.safetensors",
703
+ "model.encoder.layers.12.final_layer_norm.weight": "model-00001-of-00003.safetensors",
704
+ "model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
705
+ "model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
706
+ "model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
707
+ "model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
708
+ "model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
709
+ "model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
710
+ "model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
711
+ "model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
712
+ "model.encoder.layers.12.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
713
+ "model.encoder.layers.12.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
714
+ "model.encoder.layers.13.fc1.bias": "model-00001-of-00003.safetensors",
715
+ "model.encoder.layers.13.fc1.weight": "model-00001-of-00003.safetensors",
716
+ "model.encoder.layers.13.fc2.bias": "model-00001-of-00003.safetensors",
717
+ "model.encoder.layers.13.fc2.weight": "model-00001-of-00003.safetensors",
718
+ "model.encoder.layers.13.final_layer_norm.bias": "model-00001-of-00003.safetensors",
719
+ "model.encoder.layers.13.final_layer_norm.weight": "model-00001-of-00003.safetensors",
720
+ "model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
721
+ "model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
722
+ "model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
723
+ "model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
724
+ "model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
725
+ "model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
726
+ "model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
727
+ "model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
728
+ "model.encoder.layers.13.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
729
+ "model.encoder.layers.13.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
730
+ "model.encoder.layers.14.fc1.bias": "model-00002-of-00003.safetensors",
731
+ "model.encoder.layers.14.fc1.weight": "model-00002-of-00003.safetensors",
732
+ "model.encoder.layers.14.fc2.bias": "model-00002-of-00003.safetensors",
733
+ "model.encoder.layers.14.fc2.weight": "model-00002-of-00003.safetensors",
734
+ "model.encoder.layers.14.final_layer_norm.bias": "model-00002-of-00003.safetensors",
735
+ "model.encoder.layers.14.final_layer_norm.weight": "model-00002-of-00003.safetensors",
736
+ "model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
737
+ "model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
738
+ "model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
739
+ "model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
740
+ "model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
741
+ "model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
742
+ "model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
743
+ "model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
744
+ "model.encoder.layers.14.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
745
+ "model.encoder.layers.14.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
746
+ "model.encoder.layers.15.fc1.bias": "model-00002-of-00003.safetensors",
747
+ "model.encoder.layers.15.fc1.weight": "model-00002-of-00003.safetensors",
748
+ "model.encoder.layers.15.fc2.bias": "model-00002-of-00003.safetensors",
749
+ "model.encoder.layers.15.fc2.weight": "model-00002-of-00003.safetensors",
750
+ "model.encoder.layers.15.final_layer_norm.bias": "model-00002-of-00003.safetensors",
751
+ "model.encoder.layers.15.final_layer_norm.weight": "model-00002-of-00003.safetensors",
752
+ "model.encoder.layers.15.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
753
+ "model.encoder.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
754
+ "model.encoder.layers.15.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
755
+ "model.encoder.layers.15.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
756
+ "model.encoder.layers.15.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
757
+ "model.encoder.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
758
+ "model.encoder.layers.15.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
759
+ "model.encoder.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
760
+ "model.encoder.layers.15.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
761
+ "model.encoder.layers.15.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
762
+ "model.encoder.layers.16.fc1.bias": "model-00002-of-00003.safetensors",
763
+ "model.encoder.layers.16.fc1.weight": "model-00002-of-00003.safetensors",
764
+ "model.encoder.layers.16.fc2.bias": "model-00002-of-00003.safetensors",
765
+ "model.encoder.layers.16.fc2.weight": "model-00002-of-00003.safetensors",
766
+ "model.encoder.layers.16.final_layer_norm.bias": "model-00002-of-00003.safetensors",
767
+ "model.encoder.layers.16.final_layer_norm.weight": "model-00002-of-00003.safetensors",
768
+ "model.encoder.layers.16.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
769
+ "model.encoder.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
770
+ "model.encoder.layers.16.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
771
+ "model.encoder.layers.16.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
772
+ "model.encoder.layers.16.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
773
+ "model.encoder.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
774
+ "model.encoder.layers.16.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
775
+ "model.encoder.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
776
+ "model.encoder.layers.16.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
777
+ "model.encoder.layers.16.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
778
+ "model.encoder.layers.17.fc1.bias": "model-00002-of-00003.safetensors",
779
+ "model.encoder.layers.17.fc1.weight": "model-00002-of-00003.safetensors",
780
+ "model.encoder.layers.17.fc2.bias": "model-00002-of-00003.safetensors",
781
+ "model.encoder.layers.17.fc2.weight": "model-00002-of-00003.safetensors",
782
+ "model.encoder.layers.17.final_layer_norm.bias": "model-00002-of-00003.safetensors",
783
+ "model.encoder.layers.17.final_layer_norm.weight": "model-00002-of-00003.safetensors",
784
+ "model.encoder.layers.17.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
785
+ "model.encoder.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
786
+ "model.encoder.layers.17.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
787
+ "model.encoder.layers.17.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
788
+ "model.encoder.layers.17.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
789
+ "model.encoder.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
790
+ "model.encoder.layers.17.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
791
+ "model.encoder.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
792
+ "model.encoder.layers.17.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
793
+ "model.encoder.layers.17.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
794
+ "model.encoder.layers.18.fc1.bias": "model-00002-of-00003.safetensors",
795
+ "model.encoder.layers.18.fc1.weight": "model-00002-of-00003.safetensors",
796
+ "model.encoder.layers.18.fc2.bias": "model-00002-of-00003.safetensors",
797
+ "model.encoder.layers.18.fc2.weight": "model-00002-of-00003.safetensors",
798
+ "model.encoder.layers.18.final_layer_norm.bias": "model-00002-of-00003.safetensors",
799
+ "model.encoder.layers.18.final_layer_norm.weight": "model-00002-of-00003.safetensors",
800
+ "model.encoder.layers.18.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
801
+ "model.encoder.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
802
+ "model.encoder.layers.18.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
803
+ "model.encoder.layers.18.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
804
+ "model.encoder.layers.18.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
805
+ "model.encoder.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
806
+ "model.encoder.layers.18.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
807
+ "model.encoder.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
808
+ "model.encoder.layers.18.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
809
+ "model.encoder.layers.18.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
810
+ "model.encoder.layers.19.fc1.bias": "model-00002-of-00003.safetensors",
811
+ "model.encoder.layers.19.fc1.weight": "model-00002-of-00003.safetensors",
812
+ "model.encoder.layers.19.fc2.bias": "model-00002-of-00003.safetensors",
813
+ "model.encoder.layers.19.fc2.weight": "model-00002-of-00003.safetensors",
814
+ "model.encoder.layers.19.final_layer_norm.bias": "model-00002-of-00003.safetensors",
815
+ "model.encoder.layers.19.final_layer_norm.weight": "model-00002-of-00003.safetensors",
816
+ "model.encoder.layers.19.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
817
+ "model.encoder.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
818
+ "model.encoder.layers.19.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
819
+ "model.encoder.layers.19.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
820
+ "model.encoder.layers.19.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
821
+ "model.encoder.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
822
+ "model.encoder.layers.19.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
823
+ "model.encoder.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
824
+ "model.encoder.layers.19.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
825
+ "model.encoder.layers.19.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
826
+ "model.encoder.layers.2.fc1.bias": "model-00001-of-00003.safetensors",
827
+ "model.encoder.layers.2.fc1.weight": "model-00001-of-00003.safetensors",
828
+ "model.encoder.layers.2.fc2.bias": "model-00001-of-00003.safetensors",
829
+ "model.encoder.layers.2.fc2.weight": "model-00001-of-00003.safetensors",
830
+ "model.encoder.layers.2.final_layer_norm.bias": "model-00001-of-00003.safetensors",
831
+ "model.encoder.layers.2.final_layer_norm.weight": "model-00001-of-00003.safetensors",
832
+ "model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
833
+ "model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
834
+ "model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
835
+ "model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
836
+ "model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
837
+ "model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
838
+ "model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
839
+ "model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
840
+ "model.encoder.layers.2.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
841
+ "model.encoder.layers.2.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
842
+ "model.encoder.layers.20.fc1.bias": "model-00002-of-00003.safetensors",
843
+ "model.encoder.layers.20.fc1.weight": "model-00002-of-00003.safetensors",
844
+ "model.encoder.layers.20.fc2.bias": "model-00002-of-00003.safetensors",
845
+ "model.encoder.layers.20.fc2.weight": "model-00002-of-00003.safetensors",
846
+ "model.encoder.layers.20.final_layer_norm.bias": "model-00002-of-00003.safetensors",
847
+ "model.encoder.layers.20.final_layer_norm.weight": "model-00002-of-00003.safetensors",
848
+ "model.encoder.layers.20.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
849
+ "model.encoder.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
850
+ "model.encoder.layers.20.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
851
+ "model.encoder.layers.20.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
852
+ "model.encoder.layers.20.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
853
+ "model.encoder.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
854
+ "model.encoder.layers.20.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
855
+ "model.encoder.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
856
+ "model.encoder.layers.20.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
857
+ "model.encoder.layers.20.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
858
+ "model.encoder.layers.21.fc1.bias": "model-00002-of-00003.safetensors",
859
+ "model.encoder.layers.21.fc1.weight": "model-00002-of-00003.safetensors",
860
+ "model.encoder.layers.21.fc2.bias": "model-00002-of-00003.safetensors",
861
+ "model.encoder.layers.21.fc2.weight": "model-00002-of-00003.safetensors",
862
+ "model.encoder.layers.21.final_layer_norm.bias": "model-00002-of-00003.safetensors",
863
+ "model.encoder.layers.21.final_layer_norm.weight": "model-00002-of-00003.safetensors",
864
+ "model.encoder.layers.21.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
865
+ "model.encoder.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
866
+ "model.encoder.layers.21.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
867
+ "model.encoder.layers.21.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
868
+ "model.encoder.layers.21.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
869
+ "model.encoder.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
870
+ "model.encoder.layers.21.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
871
+ "model.encoder.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
872
+ "model.encoder.layers.21.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
873
+ "model.encoder.layers.21.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
874
+ "model.encoder.layers.22.fc1.bias": "model-00002-of-00003.safetensors",
875
+ "model.encoder.layers.22.fc1.weight": "model-00002-of-00003.safetensors",
876
+ "model.encoder.layers.22.fc2.bias": "model-00002-of-00003.safetensors",
877
+ "model.encoder.layers.22.fc2.weight": "model-00002-of-00003.safetensors",
878
+ "model.encoder.layers.22.final_layer_norm.bias": "model-00002-of-00003.safetensors",
879
+ "model.encoder.layers.22.final_layer_norm.weight": "model-00002-of-00003.safetensors",
880
+ "model.encoder.layers.22.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
881
+ "model.encoder.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
882
+ "model.encoder.layers.22.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
883
+ "model.encoder.layers.22.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
884
+ "model.encoder.layers.22.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
885
+ "model.encoder.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
886
+ "model.encoder.layers.22.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
887
+ "model.encoder.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
888
+ "model.encoder.layers.22.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
889
+ "model.encoder.layers.22.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
890
+ "model.encoder.layers.23.fc1.bias": "model-00002-of-00003.safetensors",
891
+ "model.encoder.layers.23.fc1.weight": "model-00002-of-00003.safetensors",
892
+ "model.encoder.layers.23.fc2.bias": "model-00002-of-00003.safetensors",
893
+ "model.encoder.layers.23.fc2.weight": "model-00002-of-00003.safetensors",
894
+ "model.encoder.layers.23.final_layer_norm.bias": "model-00002-of-00003.safetensors",
895
+ "model.encoder.layers.23.final_layer_norm.weight": "model-00002-of-00003.safetensors",
896
+ "model.encoder.layers.23.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
897
+ "model.encoder.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
898
+ "model.encoder.layers.23.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
899
+ "model.encoder.layers.23.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
900
+ "model.encoder.layers.23.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
901
+ "model.encoder.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
902
+ "model.encoder.layers.23.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
903
+ "model.encoder.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
904
+ "model.encoder.layers.23.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
905
+ "model.encoder.layers.23.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
906
+ "model.encoder.layers.3.fc1.bias": "model-00001-of-00003.safetensors",
907
+ "model.encoder.layers.3.fc1.weight": "model-00001-of-00003.safetensors",
908
+ "model.encoder.layers.3.fc2.bias": "model-00001-of-00003.safetensors",
909
+ "model.encoder.layers.3.fc2.weight": "model-00001-of-00003.safetensors",
910
+ "model.encoder.layers.3.final_layer_norm.bias": "model-00001-of-00003.safetensors",
911
+ "model.encoder.layers.3.final_layer_norm.weight": "model-00001-of-00003.safetensors",
912
+ "model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
913
+ "model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
914
+ "model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
915
+ "model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
916
+ "model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
917
+ "model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
918
+ "model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
919
+ "model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
920
+ "model.encoder.layers.3.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
921
+ "model.encoder.layers.3.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
922
+ "model.encoder.layers.4.fc1.bias": "model-00001-of-00003.safetensors",
923
+ "model.encoder.layers.4.fc1.weight": "model-00001-of-00003.safetensors",
924
+ "model.encoder.layers.4.fc2.bias": "model-00001-of-00003.safetensors",
925
+ "model.encoder.layers.4.fc2.weight": "model-00001-of-00003.safetensors",
926
+ "model.encoder.layers.4.final_layer_norm.bias": "model-00001-of-00003.safetensors",
927
+ "model.encoder.layers.4.final_layer_norm.weight": "model-00001-of-00003.safetensors",
928
+ "model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
929
+ "model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
930
+ "model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
931
+ "model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
932
+ "model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
933
+ "model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
934
+ "model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
935
+ "model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
936
+ "model.encoder.layers.4.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
937
+ "model.encoder.layers.4.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
938
+ "model.encoder.layers.5.fc1.bias": "model-00001-of-00003.safetensors",
939
+ "model.encoder.layers.5.fc1.weight": "model-00001-of-00003.safetensors",
940
+ "model.encoder.layers.5.fc2.bias": "model-00001-of-00003.safetensors",
941
+ "model.encoder.layers.5.fc2.weight": "model-00001-of-00003.safetensors",
942
+ "model.encoder.layers.5.final_layer_norm.bias": "model-00001-of-00003.safetensors",
943
+ "model.encoder.layers.5.final_layer_norm.weight": "model-00001-of-00003.safetensors",
944
+ "model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
945
+ "model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
946
+ "model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
947
+ "model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
948
+ "model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
949
+ "model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
950
+ "model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
951
+ "model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
952
+ "model.encoder.layers.5.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
953
+ "model.encoder.layers.5.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
954
+ "model.encoder.layers.6.fc1.bias": "model-00001-of-00003.safetensors",
955
+ "model.encoder.layers.6.fc1.weight": "model-00001-of-00003.safetensors",
956
+ "model.encoder.layers.6.fc2.bias": "model-00001-of-00003.safetensors",
957
+ "model.encoder.layers.6.fc2.weight": "model-00001-of-00003.safetensors",
958
+ "model.encoder.layers.6.final_layer_norm.bias": "model-00001-of-00003.safetensors",
959
+ "model.encoder.layers.6.final_layer_norm.weight": "model-00001-of-00003.safetensors",
960
+ "model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
961
+ "model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
962
+ "model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
963
+ "model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
964
+ "model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
965
+ "model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
966
+ "model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
967
+ "model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
968
+ "model.encoder.layers.6.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
969
+ "model.encoder.layers.6.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
970
+ "model.encoder.layers.7.fc1.bias": "model-00001-of-00003.safetensors",
971
+ "model.encoder.layers.7.fc1.weight": "model-00001-of-00003.safetensors",
972
+ "model.encoder.layers.7.fc2.bias": "model-00001-of-00003.safetensors",
973
+ "model.encoder.layers.7.fc2.weight": "model-00001-of-00003.safetensors",
974
+ "model.encoder.layers.7.final_layer_norm.bias": "model-00001-of-00003.safetensors",
975
+ "model.encoder.layers.7.final_layer_norm.weight": "model-00001-of-00003.safetensors",
976
+ "model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
977
+ "model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
978
+ "model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
979
+ "model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
980
+ "model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
981
+ "model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
982
+ "model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
983
+ "model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
984
+ "model.encoder.layers.7.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
985
+ "model.encoder.layers.7.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
986
+ "model.encoder.layers.8.fc1.bias": "model-00001-of-00003.safetensors",
987
+ "model.encoder.layers.8.fc1.weight": "model-00001-of-00003.safetensors",
988
+ "model.encoder.layers.8.fc2.bias": "model-00001-of-00003.safetensors",
989
+ "model.encoder.layers.8.fc2.weight": "model-00001-of-00003.safetensors",
990
+ "model.encoder.layers.8.final_layer_norm.bias": "model-00001-of-00003.safetensors",
991
+ "model.encoder.layers.8.final_layer_norm.weight": "model-00001-of-00003.safetensors",
992
+ "model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
993
+ "model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
994
+ "model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
995
+ "model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
996
+ "model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
997
+ "model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
998
+ "model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
999
+ "model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
1000
+ "model.encoder.layers.8.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
1001
+ "model.encoder.layers.8.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
1002
+ "model.encoder.layers.9.fc1.bias": "model-00001-of-00003.safetensors",
1003
+ "model.encoder.layers.9.fc1.weight": "model-00001-of-00003.safetensors",
1004
+ "model.encoder.layers.9.fc2.bias": "model-00001-of-00003.safetensors",
1005
+ "model.encoder.layers.9.fc2.weight": "model-00001-of-00003.safetensors",
1006
+ "model.encoder.layers.9.final_layer_norm.bias": "model-00001-of-00003.safetensors",
1007
+ "model.encoder.layers.9.final_layer_norm.weight": "model-00001-of-00003.safetensors",
1008
+ "model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
1009
+ "model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
1010
+ "model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
1011
+ "model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
1012
+ "model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
1013
+ "model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
1014
+ "model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
1015
+ "model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
1016
+ "model.encoder.layers.9.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
1017
+ "model.encoder.layers.9.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
1018
+ "model.shared.weight": "model-00001-of-00003.safetensors"
1019
+ }
1020
+ }
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9978431433840766,
3
+ "total_flos": 2.5671411434264986e+17,
4
+ "train_loss": 0.35637976608556393,
5
+ "train_runtime": 44055.9239,
6
+ "train_samples": 63982,
7
+ "train_samples_per_second": 4.357,
8
+ "train_steps_per_second": 0.068
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,443 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.9978431433840766,
5
+ "eval_steps": 500,
6
+ "global_step": 2997,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0500140664561908,
13
+ "grad_norm": 0.9210330247879028,
14
+ "learning_rate": 3.3333333333333333e-06,
15
+ "loss": 1.561,
16
+ "step": 50
17
+ },
18
+ {
19
+ "epoch": 0.1000281329123816,
20
+ "grad_norm": 0.6426990032196045,
21
+ "learning_rate": 6.666666666666667e-06,
22
+ "loss": 0.9595,
23
+ "step": 100
24
+ },
25
+ {
26
+ "epoch": 0.1500421993685724,
27
+ "grad_norm": 0.5717326998710632,
28
+ "learning_rate": 1e-05,
29
+ "loss": 0.6943,
30
+ "step": 150
31
+ },
32
+ {
33
+ "epoch": 0.2000562658247632,
34
+ "grad_norm": 0.4604141414165497,
35
+ "learning_rate": 1.3333333333333333e-05,
36
+ "loss": 0.6171,
37
+ "step": 200
38
+ },
39
+ {
40
+ "epoch": 0.25007033228095404,
41
+ "grad_norm": 0.45251232385635376,
42
+ "learning_rate": 1.6666666666666667e-05,
43
+ "loss": 0.5517,
44
+ "step": 250
45
+ },
46
+ {
47
+ "epoch": 0.3000843987371448,
48
+ "grad_norm": 0.5194812417030334,
49
+ "learning_rate": 2e-05,
50
+ "loss": 0.523,
51
+ "step": 300
52
+ },
53
+ {
54
+ "epoch": 0.35009846519333565,
55
+ "grad_norm": 0.4478510618209839,
56
+ "learning_rate": 1.9983043934122208e-05,
57
+ "loss": 0.4911,
58
+ "step": 350
59
+ },
60
+ {
61
+ "epoch": 0.4001125316495264,
62
+ "grad_norm": 0.3697112500667572,
63
+ "learning_rate": 1.9932233238122834e-05,
64
+ "loss": 0.4631,
65
+ "step": 400
66
+ },
67
+ {
68
+ "epoch": 0.45012659810571726,
69
+ "grad_norm": 0.4671821892261505,
70
+ "learning_rate": 1.984774022190361e-05,
71
+ "loss": 0.4416,
72
+ "step": 450
73
+ },
74
+ {
75
+ "epoch": 0.5001406645619081,
76
+ "grad_norm": 0.3720390498638153,
77
+ "learning_rate": 1.972985141929439e-05,
78
+ "loss": 0.4219,
79
+ "step": 500
80
+ },
81
+ {
82
+ "epoch": 0.5501547310180989,
83
+ "grad_norm": 0.3556453287601471,
84
+ "learning_rate": 1.9578966616355823e-05,
85
+ "loss": 0.4144,
86
+ "step": 550
87
+ },
88
+ {
89
+ "epoch": 0.6001687974742896,
90
+ "grad_norm": 0.34724870324134827,
91
+ "learning_rate": 1.9395597495619634e-05,
92
+ "loss": 0.4129,
93
+ "step": 600
94
+ },
95
+ {
96
+ "epoch": 0.6501828639304804,
97
+ "grad_norm": 0.35355138778686523,
98
+ "learning_rate": 1.918036590086405e-05,
99
+ "loss": 0.3979,
100
+ "step": 650
101
+ },
102
+ {
103
+ "epoch": 0.7001969303866713,
104
+ "grad_norm": 0.44766274094581604,
105
+ "learning_rate": 1.8934001728309003e-05,
106
+ "loss": 0.3843,
107
+ "step": 700
108
+ },
109
+ {
110
+ "epoch": 0.7502109968428621,
111
+ "grad_norm": 0.3572178781032562,
112
+ "learning_rate": 1.865734045138245e-05,
113
+ "loss": 0.3854,
114
+ "step": 750
115
+ },
116
+ {
117
+ "epoch": 0.8002250632990529,
118
+ "grad_norm": 0.37280118465423584,
119
+ "learning_rate": 1.8351320287451865e-05,
120
+ "loss": 0.3699,
121
+ "step": 800
122
+ },
123
+ {
124
+ "epoch": 0.8502391297552436,
125
+ "grad_norm": 0.3944127559661865,
126
+ "learning_rate": 1.8016979016129164e-05,
127
+ "loss": 0.3646,
128
+ "step": 850
129
+ },
130
+ {
131
+ "epoch": 0.9002531962114345,
132
+ "grad_norm": 0.32988861203193665,
133
+ "learning_rate": 1.7655450459938786e-05,
134
+ "loss": 0.3537,
135
+ "step": 900
136
+ },
137
+ {
138
+ "epoch": 0.9502672626676253,
139
+ "grad_norm": 0.31536394357681274,
140
+ "learning_rate": 1.726796063928382e-05,
141
+ "loss": 0.3514,
142
+ "step": 950
143
+ },
144
+ {
145
+ "epoch": 1.0002813291238162,
146
+ "grad_norm": 0.3472963869571686,
147
+ "learning_rate": 1.6855823614749474e-05,
148
+ "loss": 0.3489,
149
+ "step": 1000
150
+ },
151
+ {
152
+ "epoch": 1.050295395580007,
153
+ "grad_norm": 0.357003778219223,
154
+ "learning_rate": 1.6420437030843482e-05,
155
+ "loss": 0.3187,
156
+ "step": 1050
157
+ },
158
+ {
159
+ "epoch": 1.1003094620361977,
160
+ "grad_norm": 0.31990480422973633,
161
+ "learning_rate": 1.5963277376285646e-05,
162
+ "loss": 0.3117,
163
+ "step": 1100
164
+ },
165
+ {
166
+ "epoch": 1.1503235284923885,
167
+ "grad_norm": 0.3657567501068115,
168
+ "learning_rate": 1.5485894976919836e-05,
169
+ "loss": 0.3089,
170
+ "step": 1150
171
+ },
172
+ {
173
+ "epoch": 1.2003375949485793,
174
+ "grad_norm": 0.3026184141635895,
175
+ "learning_rate": 1.4989908738228567e-05,
176
+ "loss": 0.3005,
177
+ "step": 1200
178
+ },
179
+ {
180
+ "epoch": 1.25035166140477,
181
+ "grad_norm": 0.3388034999370575,
182
+ "learning_rate": 1.4477000655279376e-05,
183
+ "loss": 0.3042,
184
+ "step": 1250
185
+ },
186
+ {
187
+ "epoch": 1.3003657278609608,
188
+ "grad_norm": 0.3384702205657959,
189
+ "learning_rate": 1.394891010872102e-05,
190
+ "loss": 0.3057,
191
+ "step": 1300
192
+ },
193
+ {
194
+ "epoch": 1.3503797943171518,
195
+ "grad_norm": 0.3673734664916992,
196
+ "learning_rate": 1.3407427966172866e-05,
197
+ "loss": 0.2958,
198
+ "step": 1350
199
+ },
200
+ {
201
+ "epoch": 1.4003938607733426,
202
+ "grad_norm": 0.35079866647720337,
203
+ "learning_rate": 1.2854390509011061e-05,
204
+ "loss": 0.298,
205
+ "step": 1400
206
+ },
207
+ {
208
+ "epoch": 1.4504079272295334,
209
+ "grad_norm": 0.3334648013114929,
210
+ "learning_rate": 1.2291673205146908e-05,
211
+ "loss": 0.3008,
212
+ "step": 1450
213
+ },
214
+ {
215
+ "epoch": 1.5004219936857242,
216
+ "grad_norm": 0.3893981873989105,
217
+ "learning_rate": 1.1721184348915384e-05,
218
+ "loss": 0.2917,
219
+ "step": 1500
220
+ },
221
+ {
222
+ "epoch": 1.550436060141915,
223
+ "grad_norm": 0.31972965598106384,
224
+ "learning_rate": 1.1144858589642251e-05,
225
+ "loss": 0.2926,
226
+ "step": 1550
227
+ },
228
+ {
229
+ "epoch": 1.6004501265981057,
230
+ "grad_norm": 0.31529781222343445,
231
+ "learning_rate": 1.0564650370835772e-05,
232
+ "loss": 0.2876,
233
+ "step": 1600
234
+ },
235
+ {
236
+ "epoch": 1.6504641930542965,
237
+ "grad_norm": 0.3786483705043793,
238
+ "learning_rate": 9.982527302252135e-06,
239
+ "loss": 0.2904,
240
+ "step": 1650
241
+ },
242
+ {
243
+ "epoch": 1.7004782595104873,
244
+ "grad_norm": 0.33780983090400696,
245
+ "learning_rate": 9.40046348731131e-06,
246
+ "loss": 0.2906,
247
+ "step": 1700
248
+ },
249
+ {
250
+ "epoch": 1.750492325966678,
251
+ "grad_norm": 0.3387848734855652,
252
+ "learning_rate": 8.820432828491542e-06,
253
+ "loss": 0.2833,
254
+ "step": 1750
255
+ },
256
+ {
257
+ "epoch": 1.8005063924228688,
258
+ "grad_norm": 0.280521422624588,
259
+ "learning_rate": 8.244402333405252e-06,
260
+ "loss": 0.2779,
261
+ "step": 1800
262
+ },
263
+ {
264
+ "epoch": 1.8505204588790596,
265
+ "grad_norm": 0.3127559721469879,
266
+ "learning_rate": 7.674325444256899e-06,
267
+ "loss": 0.2898,
268
+ "step": 1850
269
+ },
270
+ {
271
+ "epoch": 1.9005345253352506,
272
+ "grad_norm": 0.30676454305648804,
273
+ "learning_rate": 7.112135413304042e-06,
274
+ "loss": 0.2813,
275
+ "step": 1900
276
+ },
277
+ {
278
+ "epoch": 1.9505485917914414,
279
+ "grad_norm": 0.31918200850486755,
280
+ "learning_rate": 6.55973874678682e-06,
281
+ "loss": 0.2777,
282
+ "step": 1950
283
+ },
284
+ {
285
+ "epoch": 2.0005626582476324,
286
+ "grad_norm": 0.32422205805778503,
287
+ "learning_rate": 6.0190087395588596e-06,
288
+ "loss": 0.2767,
289
+ "step": 2000
290
+ },
291
+ {
292
+ "epoch": 2.050576724703823,
293
+ "grad_norm": 0.31339433789253235,
294
+ "learning_rate": 5.491779122345093e-06,
295
+ "loss": 0.2571,
296
+ "step": 2050
297
+ },
298
+ {
299
+ "epoch": 2.100590791160014,
300
+ "grad_norm": 0.342579185962677,
301
+ "learning_rate": 4.979837843169959e-06,
302
+ "loss": 0.2516,
303
+ "step": 2100
304
+ },
305
+ {
306
+ "epoch": 2.1506048576162047,
307
+ "grad_norm": 0.38084590435028076,
308
+ "learning_rate": 4.484921004044509e-06,
309
+ "loss": 0.2536,
310
+ "step": 2150
311
+ },
312
+ {
313
+ "epoch": 2.2006189240723955,
314
+ "grad_norm": 0.3659977316856384,
315
+ "learning_rate": 4.008706973474391e-06,
316
+ "loss": 0.2508,
317
+ "step": 2200
318
+ },
319
+ {
320
+ "epoch": 2.2506329905285862,
321
+ "grad_norm": 0.3062564730644226,
322
+ "learning_rate": 3.5528106947544626e-06,
323
+ "loss": 0.2501,
324
+ "step": 2250
325
+ },
326
+ {
327
+ "epoch": 2.300647056984777,
328
+ "grad_norm": 0.31410741806030273,
329
+ "learning_rate": 3.118778209351808e-06,
330
+ "loss": 0.2555,
331
+ "step": 2300
332
+ },
333
+ {
334
+ "epoch": 2.350661123440968,
335
+ "grad_norm": 0.3308572769165039,
336
+ "learning_rate": 2.7080814139495402e-06,
337
+ "loss": 0.2519,
338
+ "step": 2350
339
+ },
340
+ {
341
+ "epoch": 2.4006751898971586,
342
+ "grad_norm": 0.32767045497894287,
343
+ "learning_rate": 2.322113068931391e-06,
344
+ "loss": 0.2496,
345
+ "step": 2400
346
+ },
347
+ {
348
+ "epoch": 2.4506892563533493,
349
+ "grad_norm": 0.302573025226593,
350
+ "learning_rate": 1.9621820752343324e-06,
351
+ "loss": 0.245,
352
+ "step": 2450
353
+ },
354
+ {
355
+ "epoch": 2.50070332280954,
356
+ "grad_norm": 0.29837408661842346,
357
+ "learning_rate": 1.629509035586484e-06,
358
+ "loss": 0.2532,
359
+ "step": 2500
360
+ },
361
+ {
362
+ "epoch": 2.550717389265731,
363
+ "grad_norm": 0.3348439931869507,
364
+ "learning_rate": 1.3252221151830513e-06,
365
+ "loss": 0.2457,
366
+ "step": 2550
367
+ },
368
+ {
369
+ "epoch": 2.6007314557219217,
370
+ "grad_norm": 0.37546366453170776,
371
+ "learning_rate": 1.0503532158376584e-06,
372
+ "loss": 0.2475,
373
+ "step": 2600
374
+ },
375
+ {
376
+ "epoch": 2.6507455221781124,
377
+ "grad_norm": 0.2989293038845062,
378
+ "learning_rate": 8.058344765833171e-07,
379
+ "loss": 0.246,
380
+ "step": 2650
381
+ },
382
+ {
383
+ "epoch": 2.7007595886343037,
384
+ "grad_norm": 0.32395079731941223,
385
+ "learning_rate": 5.924951125902545e-07,
386
+ "loss": 0.2495,
387
+ "step": 2700
388
+ },
389
+ {
390
+ "epoch": 2.7507736550904944,
391
+ "grad_norm": 0.31438368558883667,
392
+ "learning_rate": 4.11058603120511e-07,
393
+ "loss": 0.2476,
394
+ "step": 2750
395
+ },
396
+ {
397
+ "epoch": 2.800787721546685,
398
+ "grad_norm": 0.30735209584236145,
399
+ "learning_rate": 2.6214023805552826e-07,
400
+ "loss": 0.2481,
401
+ "step": 2800
402
+ },
403
+ {
404
+ "epoch": 2.850801788002876,
405
+ "grad_norm": 0.3182600736618042,
406
+ "learning_rate": 1.462450313169983e-07,
407
+ "loss": 0.245,
408
+ "step": 2850
409
+ },
410
+ {
411
+ "epoch": 2.9008158544590668,
412
+ "grad_norm": 0.3001386523246765,
413
+ "learning_rate": 6.376600825699463e-08,
414
+ "loss": 0.2459,
415
+ "step": 2900
416
+ },
417
+ {
418
+ "epoch": 2.9508299209152575,
419
+ "grad_norm": 0.3104873299598694,
420
+ "learning_rate": 1.49828728252277e-08,
421
+ "loss": 0.2419,
422
+ "step": 2950
423
+ },
424
+ {
425
+ "epoch": 2.9978431433840766,
426
+ "step": 2997,
427
+ "total_flos": 2.5671411434264986e+17,
428
+ "train_loss": 0.35637976608556393,
429
+ "train_runtime": 44055.9239,
430
+ "train_samples_per_second": 4.357,
431
+ "train_steps_per_second": 0.068
432
+ }
433
+ ],
434
+ "logging_steps": 50,
435
+ "max_steps": 2997,
436
+ "num_input_tokens_seen": 0,
437
+ "num_train_epochs": 3,
438
+ "save_steps": 100,
439
+ "total_flos": 2.5671411434264986e+17,
440
+ "train_batch_size": 2,
441
+ "trial_name": null,
442
+ "trial_params": null
443
+ }