varun-v-rao commited on
Commit
18b59ba
1 Parent(s): 25924aa

End of training

Browse files
README.md ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ base_model: facebook/opt-1.3b
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ model-index:
9
+ - name: opt-1.3b-lora-3.15M-snli-model3
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # opt-1.3b-lora-3.15M-snli-model3
17
+
18
+ This model is a fine-tuned version of [facebook/opt-1.3b](https://huggingface.co/facebook/opt-1.3b) on the None dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.6832
21
+ - Accuracy: 0.761
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 2e-05
41
+ - train_batch_size: 128
42
+ - eval_batch_size: 128
43
+ - seed: 49
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - num_epochs: 3
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|
52
+ | 0.3553 | 1.0 | 4292 | 0.2816 | 0.8942 |
53
+ | 0.3227 | 2.0 | 8584 | 0.2643 | 0.9043 |
54
+ | 0.3151 | 3.0 | 12876 | 0.2574 | 0.9076 |
55
+
56
+
57
+ ### Framework versions
58
+
59
+ - Transformers 4.35.2
60
+ - Pytorch 2.1.1+cu121
61
+ - Datasets 2.15.0
62
+ - Tokenizers 0.15.0
config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/opt-1.3b",
3
+ "_remove_final_layer_norm": false,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "relu",
6
+ "architectures": [
7
+ "OPTForSequenceClassification"
8
+ ],
9
+ "attention_dropout": 0.0,
10
+ "bos_token_id": 2,
11
+ "do_layer_norm_before": true,
12
+ "dropout": 0.1,
13
+ "enable_bias": true,
14
+ "eos_token_id": 2,
15
+ "ffn_dim": 8192,
16
+ "hidden_size": 2048,
17
+ "id2label": {
18
+ "0": "LABEL_0",
19
+ "1": "LABEL_1",
20
+ "2": "LABEL_2"
21
+ },
22
+ "init_std": 0.02,
23
+ "label2id": {
24
+ "LABEL_0": 0,
25
+ "LABEL_1": 1,
26
+ "LABEL_2": 2
27
+ },
28
+ "layer_norm_elementwise_affine": true,
29
+ "layerdrop": 0.0,
30
+ "max_position_embeddings": 2048,
31
+ "model_type": "opt",
32
+ "num_attention_heads": 32,
33
+ "num_hidden_layers": 24,
34
+ "pad_token_id": 1,
35
+ "prefix": "</s>",
36
+ "problem_type": "single_label_classification",
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.35.2",
39
+ "use_cache": true,
40
+ "vocab_size": 50272,
41
+ "word_embed_proj_dim": 2048
42
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a2f7290876292aecaa2bf96957350a019f59b25905f3b0ea72f4bce53b97fa1
3
+ size 4994509120
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:852e82c9c1babc8d971c00f28e78b905eedd9edfd71067913cba4054f1f48009
3
+ size 268593512
model.safetensors.index.json ADDED
@@ -0,0 +1,396 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 5263056896
4
+ },
5
+ "weight_map": {
6
+ "model.decoder.embed_positions.weight": "model-00001-of-00002.safetensors",
7
+ "model.decoder.embed_tokens.weight": "model-00001-of-00002.safetensors",
8
+ "model.decoder.final_layer_norm.bias": "model-00001-of-00002.safetensors",
9
+ "model.decoder.final_layer_norm.weight": "model-00001-of-00002.safetensors",
10
+ "model.decoder.layers.0.fc1.bias": "model-00001-of-00002.safetensors",
11
+ "model.decoder.layers.0.fc1.weight": "model-00001-of-00002.safetensors",
12
+ "model.decoder.layers.0.fc2.bias": "model-00001-of-00002.safetensors",
13
+ "model.decoder.layers.0.fc2.weight": "model-00001-of-00002.safetensors",
14
+ "model.decoder.layers.0.final_layer_norm.bias": "model-00001-of-00002.safetensors",
15
+ "model.decoder.layers.0.final_layer_norm.weight": "model-00001-of-00002.safetensors",
16
+ "model.decoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
17
+ "model.decoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
18
+ "model.decoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
19
+ "model.decoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
20
+ "model.decoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
21
+ "model.decoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
22
+ "model.decoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
23
+ "model.decoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
24
+ "model.decoder.layers.0.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
25
+ "model.decoder.layers.0.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
26
+ "model.decoder.layers.1.fc1.bias": "model-00001-of-00002.safetensors",
27
+ "model.decoder.layers.1.fc1.weight": "model-00001-of-00002.safetensors",
28
+ "model.decoder.layers.1.fc2.bias": "model-00001-of-00002.safetensors",
29
+ "model.decoder.layers.1.fc2.weight": "model-00001-of-00002.safetensors",
30
+ "model.decoder.layers.1.final_layer_norm.bias": "model-00001-of-00002.safetensors",
31
+ "model.decoder.layers.1.final_layer_norm.weight": "model-00001-of-00002.safetensors",
32
+ "model.decoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
33
+ "model.decoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
34
+ "model.decoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
35
+ "model.decoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
36
+ "model.decoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
37
+ "model.decoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
38
+ "model.decoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
39
+ "model.decoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
40
+ "model.decoder.layers.1.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
41
+ "model.decoder.layers.1.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
42
+ "model.decoder.layers.10.fc1.bias": "model-00001-of-00002.safetensors",
43
+ "model.decoder.layers.10.fc1.weight": "model-00001-of-00002.safetensors",
44
+ "model.decoder.layers.10.fc2.bias": "model-00001-of-00002.safetensors",
45
+ "model.decoder.layers.10.fc2.weight": "model-00001-of-00002.safetensors",
46
+ "model.decoder.layers.10.final_layer_norm.bias": "model-00001-of-00002.safetensors",
47
+ "model.decoder.layers.10.final_layer_norm.weight": "model-00001-of-00002.safetensors",
48
+ "model.decoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
49
+ "model.decoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
50
+ "model.decoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
51
+ "model.decoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
52
+ "model.decoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
53
+ "model.decoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
54
+ "model.decoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
55
+ "model.decoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
56
+ "model.decoder.layers.10.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
57
+ "model.decoder.layers.10.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
58
+ "model.decoder.layers.11.fc1.bias": "model-00001-of-00002.safetensors",
59
+ "model.decoder.layers.11.fc1.weight": "model-00001-of-00002.safetensors",
60
+ "model.decoder.layers.11.fc2.bias": "model-00001-of-00002.safetensors",
61
+ "model.decoder.layers.11.fc2.weight": "model-00001-of-00002.safetensors",
62
+ "model.decoder.layers.11.final_layer_norm.bias": "model-00001-of-00002.safetensors",
63
+ "model.decoder.layers.11.final_layer_norm.weight": "model-00001-of-00002.safetensors",
64
+ "model.decoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
65
+ "model.decoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
66
+ "model.decoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
67
+ "model.decoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
68
+ "model.decoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
69
+ "model.decoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
70
+ "model.decoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
71
+ "model.decoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
72
+ "model.decoder.layers.11.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
73
+ "model.decoder.layers.11.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
74
+ "model.decoder.layers.12.fc1.bias": "model-00001-of-00002.safetensors",
75
+ "model.decoder.layers.12.fc1.weight": "model-00001-of-00002.safetensors",
76
+ "model.decoder.layers.12.fc2.bias": "model-00001-of-00002.safetensors",
77
+ "model.decoder.layers.12.fc2.weight": "model-00001-of-00002.safetensors",
78
+ "model.decoder.layers.12.final_layer_norm.bias": "model-00001-of-00002.safetensors",
79
+ "model.decoder.layers.12.final_layer_norm.weight": "model-00001-of-00002.safetensors",
80
+ "model.decoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
81
+ "model.decoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
82
+ "model.decoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
83
+ "model.decoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
84
+ "model.decoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
85
+ "model.decoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
86
+ "model.decoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
87
+ "model.decoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
88
+ "model.decoder.layers.12.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
89
+ "model.decoder.layers.12.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
90
+ "model.decoder.layers.13.fc1.bias": "model-00001-of-00002.safetensors",
91
+ "model.decoder.layers.13.fc1.weight": "model-00001-of-00002.safetensors",
92
+ "model.decoder.layers.13.fc2.bias": "model-00001-of-00002.safetensors",
93
+ "model.decoder.layers.13.fc2.weight": "model-00001-of-00002.safetensors",
94
+ "model.decoder.layers.13.final_layer_norm.bias": "model-00001-of-00002.safetensors",
95
+ "model.decoder.layers.13.final_layer_norm.weight": "model-00001-of-00002.safetensors",
96
+ "model.decoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
97
+ "model.decoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
98
+ "model.decoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
99
+ "model.decoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
100
+ "model.decoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
101
+ "model.decoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
102
+ "model.decoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
103
+ "model.decoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
104
+ "model.decoder.layers.13.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
105
+ "model.decoder.layers.13.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
106
+ "model.decoder.layers.14.fc1.bias": "model-00001-of-00002.safetensors",
107
+ "model.decoder.layers.14.fc1.weight": "model-00001-of-00002.safetensors",
108
+ "model.decoder.layers.14.fc2.bias": "model-00001-of-00002.safetensors",
109
+ "model.decoder.layers.14.fc2.weight": "model-00001-of-00002.safetensors",
110
+ "model.decoder.layers.14.final_layer_norm.bias": "model-00001-of-00002.safetensors",
111
+ "model.decoder.layers.14.final_layer_norm.weight": "model-00001-of-00002.safetensors",
112
+ "model.decoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
113
+ "model.decoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
114
+ "model.decoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
115
+ "model.decoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
116
+ "model.decoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
117
+ "model.decoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
118
+ "model.decoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
119
+ "model.decoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
120
+ "model.decoder.layers.14.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
121
+ "model.decoder.layers.14.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
122
+ "model.decoder.layers.15.fc1.bias": "model-00001-of-00002.safetensors",
123
+ "model.decoder.layers.15.fc1.weight": "model-00001-of-00002.safetensors",
124
+ "model.decoder.layers.15.fc2.bias": "model-00001-of-00002.safetensors",
125
+ "model.decoder.layers.15.fc2.weight": "model-00001-of-00002.safetensors",
126
+ "model.decoder.layers.15.final_layer_norm.bias": "model-00001-of-00002.safetensors",
127
+ "model.decoder.layers.15.final_layer_norm.weight": "model-00001-of-00002.safetensors",
128
+ "model.decoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
129
+ "model.decoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
130
+ "model.decoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
131
+ "model.decoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
132
+ "model.decoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
133
+ "model.decoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
134
+ "model.decoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
135
+ "model.decoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
136
+ "model.decoder.layers.15.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
137
+ "model.decoder.layers.15.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
138
+ "model.decoder.layers.16.fc1.bias": "model-00001-of-00002.safetensors",
139
+ "model.decoder.layers.16.fc1.weight": "model-00001-of-00002.safetensors",
140
+ "model.decoder.layers.16.fc2.bias": "model-00001-of-00002.safetensors",
141
+ "model.decoder.layers.16.fc2.weight": "model-00001-of-00002.safetensors",
142
+ "model.decoder.layers.16.final_layer_norm.bias": "model-00001-of-00002.safetensors",
143
+ "model.decoder.layers.16.final_layer_norm.weight": "model-00001-of-00002.safetensors",
144
+ "model.decoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
145
+ "model.decoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
146
+ "model.decoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
147
+ "model.decoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
148
+ "model.decoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
149
+ "model.decoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
150
+ "model.decoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
151
+ "model.decoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
152
+ "model.decoder.layers.16.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
153
+ "model.decoder.layers.16.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
154
+ "model.decoder.layers.17.fc1.bias": "model-00001-of-00002.safetensors",
155
+ "model.decoder.layers.17.fc1.weight": "model-00001-of-00002.safetensors",
156
+ "model.decoder.layers.17.fc2.bias": "model-00001-of-00002.safetensors",
157
+ "model.decoder.layers.17.fc2.weight": "model-00001-of-00002.safetensors",
158
+ "model.decoder.layers.17.final_layer_norm.bias": "model-00001-of-00002.safetensors",
159
+ "model.decoder.layers.17.final_layer_norm.weight": "model-00001-of-00002.safetensors",
160
+ "model.decoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
161
+ "model.decoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
162
+ "model.decoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
163
+ "model.decoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
164
+ "model.decoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
165
+ "model.decoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
166
+ "model.decoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
167
+ "model.decoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
168
+ "model.decoder.layers.17.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
169
+ "model.decoder.layers.17.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
170
+ "model.decoder.layers.18.fc1.bias": "model-00001-of-00002.safetensors",
171
+ "model.decoder.layers.18.fc1.weight": "model-00001-of-00002.safetensors",
172
+ "model.decoder.layers.18.fc2.bias": "model-00001-of-00002.safetensors",
173
+ "model.decoder.layers.18.fc2.weight": "model-00001-of-00002.safetensors",
174
+ "model.decoder.layers.18.final_layer_norm.bias": "model-00001-of-00002.safetensors",
175
+ "model.decoder.layers.18.final_layer_norm.weight": "model-00001-of-00002.safetensors",
176
+ "model.decoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
177
+ "model.decoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
178
+ "model.decoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
179
+ "model.decoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
180
+ "model.decoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
181
+ "model.decoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
182
+ "model.decoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
183
+ "model.decoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
184
+ "model.decoder.layers.18.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
185
+ "model.decoder.layers.18.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
186
+ "model.decoder.layers.19.fc1.bias": "model-00001-of-00002.safetensors",
187
+ "model.decoder.layers.19.fc1.weight": "model-00001-of-00002.safetensors",
188
+ "model.decoder.layers.19.fc2.bias": "model-00001-of-00002.safetensors",
189
+ "model.decoder.layers.19.fc2.weight": "model-00001-of-00002.safetensors",
190
+ "model.decoder.layers.19.final_layer_norm.bias": "model-00001-of-00002.safetensors",
191
+ "model.decoder.layers.19.final_layer_norm.weight": "model-00001-of-00002.safetensors",
192
+ "model.decoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
193
+ "model.decoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
194
+ "model.decoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
195
+ "model.decoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
196
+ "model.decoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
197
+ "model.decoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
198
+ "model.decoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
199
+ "model.decoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
200
+ "model.decoder.layers.19.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
201
+ "model.decoder.layers.19.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
202
+ "model.decoder.layers.2.fc1.bias": "model-00001-of-00002.safetensors",
203
+ "model.decoder.layers.2.fc1.weight": "model-00001-of-00002.safetensors",
204
+ "model.decoder.layers.2.fc2.bias": "model-00001-of-00002.safetensors",
205
+ "model.decoder.layers.2.fc2.weight": "model-00001-of-00002.safetensors",
206
+ "model.decoder.layers.2.final_layer_norm.bias": "model-00001-of-00002.safetensors",
207
+ "model.decoder.layers.2.final_layer_norm.weight": "model-00001-of-00002.safetensors",
208
+ "model.decoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
209
+ "model.decoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
210
+ "model.decoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
211
+ "model.decoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
212
+ "model.decoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
213
+ "model.decoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
214
+ "model.decoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
215
+ "model.decoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
216
+ "model.decoder.layers.2.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
217
+ "model.decoder.layers.2.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
218
+ "model.decoder.layers.20.fc1.bias": "model-00001-of-00002.safetensors",
219
+ "model.decoder.layers.20.fc1.weight": "model-00001-of-00002.safetensors",
220
+ "model.decoder.layers.20.fc2.bias": "model-00001-of-00002.safetensors",
221
+ "model.decoder.layers.20.fc2.weight": "model-00001-of-00002.safetensors",
222
+ "model.decoder.layers.20.final_layer_norm.bias": "model-00001-of-00002.safetensors",
223
+ "model.decoder.layers.20.final_layer_norm.weight": "model-00001-of-00002.safetensors",
224
+ "model.decoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
225
+ "model.decoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
226
+ "model.decoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
227
+ "model.decoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
228
+ "model.decoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
229
+ "model.decoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
230
+ "model.decoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
231
+ "model.decoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
232
+ "model.decoder.layers.20.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
233
+ "model.decoder.layers.20.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
234
+ "model.decoder.layers.21.fc1.bias": "model-00001-of-00002.safetensors",
235
+ "model.decoder.layers.21.fc1.weight": "model-00001-of-00002.safetensors",
236
+ "model.decoder.layers.21.fc2.bias": "model-00001-of-00002.safetensors",
237
+ "model.decoder.layers.21.fc2.weight": "model-00001-of-00002.safetensors",
238
+ "model.decoder.layers.21.final_layer_norm.bias": "model-00001-of-00002.safetensors",
239
+ "model.decoder.layers.21.final_layer_norm.weight": "model-00001-of-00002.safetensors",
240
+ "model.decoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
241
+ "model.decoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
242
+ "model.decoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
243
+ "model.decoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
244
+ "model.decoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
245
+ "model.decoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
246
+ "model.decoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
247
+ "model.decoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
248
+ "model.decoder.layers.21.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
249
+ "model.decoder.layers.21.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
250
+ "model.decoder.layers.22.fc1.bias": "model-00001-of-00002.safetensors",
251
+ "model.decoder.layers.22.fc1.weight": "model-00001-of-00002.safetensors",
252
+ "model.decoder.layers.22.fc2.bias": "model-00002-of-00002.safetensors",
253
+ "model.decoder.layers.22.fc2.weight": "model-00002-of-00002.safetensors",
254
+ "model.decoder.layers.22.final_layer_norm.bias": "model-00002-of-00002.safetensors",
255
+ "model.decoder.layers.22.final_layer_norm.weight": "model-00002-of-00002.safetensors",
256
+ "model.decoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
257
+ "model.decoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
258
+ "model.decoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
259
+ "model.decoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
260
+ "model.decoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
261
+ "model.decoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
262
+ "model.decoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
263
+ "model.decoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
264
+ "model.decoder.layers.22.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
265
+ "model.decoder.layers.22.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
266
+ "model.decoder.layers.23.fc1.bias": "model-00002-of-00002.safetensors",
267
+ "model.decoder.layers.23.fc1.weight": "model-00002-of-00002.safetensors",
268
+ "model.decoder.layers.23.fc2.bias": "model-00002-of-00002.safetensors",
269
+ "model.decoder.layers.23.fc2.weight": "model-00002-of-00002.safetensors",
270
+ "model.decoder.layers.23.final_layer_norm.bias": "model-00002-of-00002.safetensors",
271
+ "model.decoder.layers.23.final_layer_norm.weight": "model-00002-of-00002.safetensors",
272
+ "model.decoder.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
273
+ "model.decoder.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
274
+ "model.decoder.layers.23.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
275
+ "model.decoder.layers.23.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
276
+ "model.decoder.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
277
+ "model.decoder.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
278
+ "model.decoder.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
279
+ "model.decoder.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
280
+ "model.decoder.layers.23.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
281
+ "model.decoder.layers.23.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
282
+ "model.decoder.layers.3.fc1.bias": "model-00001-of-00002.safetensors",
283
+ "model.decoder.layers.3.fc1.weight": "model-00001-of-00002.safetensors",
284
+ "model.decoder.layers.3.fc2.bias": "model-00001-of-00002.safetensors",
285
+ "model.decoder.layers.3.fc2.weight": "model-00001-of-00002.safetensors",
286
+ "model.decoder.layers.3.final_layer_norm.bias": "model-00001-of-00002.safetensors",
287
+ "model.decoder.layers.3.final_layer_norm.weight": "model-00001-of-00002.safetensors",
288
+ "model.decoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
289
+ "model.decoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
290
+ "model.decoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
291
+ "model.decoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
292
+ "model.decoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
293
+ "model.decoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
294
+ "model.decoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
295
+ "model.decoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
296
+ "model.decoder.layers.3.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
297
+ "model.decoder.layers.3.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
298
+ "model.decoder.layers.4.fc1.bias": "model-00001-of-00002.safetensors",
299
+ "model.decoder.layers.4.fc1.weight": "model-00001-of-00002.safetensors",
300
+ "model.decoder.layers.4.fc2.bias": "model-00001-of-00002.safetensors",
301
+ "model.decoder.layers.4.fc2.weight": "model-00001-of-00002.safetensors",
302
+ "model.decoder.layers.4.final_layer_norm.bias": "model-00001-of-00002.safetensors",
303
+ "model.decoder.layers.4.final_layer_norm.weight": "model-00001-of-00002.safetensors",
304
+ "model.decoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
305
+ "model.decoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
306
+ "model.decoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
307
+ "model.decoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
308
+ "model.decoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
309
+ "model.decoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
310
+ "model.decoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
311
+ "model.decoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
312
+ "model.decoder.layers.4.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
313
+ "model.decoder.layers.4.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
314
+ "model.decoder.layers.5.fc1.bias": "model-00001-of-00002.safetensors",
315
+ "model.decoder.layers.5.fc1.weight": "model-00001-of-00002.safetensors",
316
+ "model.decoder.layers.5.fc2.bias": "model-00001-of-00002.safetensors",
317
+ "model.decoder.layers.5.fc2.weight": "model-00001-of-00002.safetensors",
318
+ "model.decoder.layers.5.final_layer_norm.bias": "model-00001-of-00002.safetensors",
319
+ "model.decoder.layers.5.final_layer_norm.weight": "model-00001-of-00002.safetensors",
320
+ "model.decoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
321
+ "model.decoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
322
+ "model.decoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
323
+ "model.decoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
324
+ "model.decoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
325
+ "model.decoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
326
+ "model.decoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
327
+ "model.decoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
328
+ "model.decoder.layers.5.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
329
+ "model.decoder.layers.5.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
330
+ "model.decoder.layers.6.fc1.bias": "model-00001-of-00002.safetensors",
331
+ "model.decoder.layers.6.fc1.weight": "model-00001-of-00002.safetensors",
332
+ "model.decoder.layers.6.fc2.bias": "model-00001-of-00002.safetensors",
333
+ "model.decoder.layers.6.fc2.weight": "model-00001-of-00002.safetensors",
334
+ "model.decoder.layers.6.final_layer_norm.bias": "model-00001-of-00002.safetensors",
335
+ "model.decoder.layers.6.final_layer_norm.weight": "model-00001-of-00002.safetensors",
336
+ "model.decoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
337
+ "model.decoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
338
+ "model.decoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
339
+ "model.decoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
340
+ "model.decoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
341
+ "model.decoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
342
+ "model.decoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
343
+ "model.decoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
344
+ "model.decoder.layers.6.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
345
+ "model.decoder.layers.6.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
346
+ "model.decoder.layers.7.fc1.bias": "model-00001-of-00002.safetensors",
347
+ "model.decoder.layers.7.fc1.weight": "model-00001-of-00002.safetensors",
348
+ "model.decoder.layers.7.fc2.bias": "model-00001-of-00002.safetensors",
349
+ "model.decoder.layers.7.fc2.weight": "model-00001-of-00002.safetensors",
350
+ "model.decoder.layers.7.final_layer_norm.bias": "model-00001-of-00002.safetensors",
351
+ "model.decoder.layers.7.final_layer_norm.weight": "model-00001-of-00002.safetensors",
352
+ "model.decoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
353
+ "model.decoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
354
+ "model.decoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
355
+ "model.decoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
356
+ "model.decoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
357
+ "model.decoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
358
+ "model.decoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
359
+ "model.decoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
360
+ "model.decoder.layers.7.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
361
+ "model.decoder.layers.7.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
362
+ "model.decoder.layers.8.fc1.bias": "model-00001-of-00002.safetensors",
363
+ "model.decoder.layers.8.fc1.weight": "model-00001-of-00002.safetensors",
364
+ "model.decoder.layers.8.fc2.bias": "model-00001-of-00002.safetensors",
365
+ "model.decoder.layers.8.fc2.weight": "model-00001-of-00002.safetensors",
366
+ "model.decoder.layers.8.final_layer_norm.bias": "model-00001-of-00002.safetensors",
367
+ "model.decoder.layers.8.final_layer_norm.weight": "model-00001-of-00002.safetensors",
368
+ "model.decoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
369
+ "model.decoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
370
+ "model.decoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
371
+ "model.decoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
372
+ "model.decoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
373
+ "model.decoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
374
+ "model.decoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
375
+ "model.decoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
376
+ "model.decoder.layers.8.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
377
+ "model.decoder.layers.8.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
378
+ "model.decoder.layers.9.fc1.bias": "model-00001-of-00002.safetensors",
379
+ "model.decoder.layers.9.fc1.weight": "model-00001-of-00002.safetensors",
380
+ "model.decoder.layers.9.fc2.bias": "model-00001-of-00002.safetensors",
381
+ "model.decoder.layers.9.fc2.weight": "model-00001-of-00002.safetensors",
382
+ "model.decoder.layers.9.final_layer_norm.bias": "model-00001-of-00002.safetensors",
383
+ "model.decoder.layers.9.final_layer_norm.weight": "model-00001-of-00002.safetensors",
384
+ "model.decoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
385
+ "model.decoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
386
+ "model.decoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
387
+ "model.decoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
388
+ "model.decoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
389
+ "model.decoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
390
+ "model.decoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
391
+ "model.decoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
392
+ "model.decoder.layers.9.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
393
+ "model.decoder.layers.9.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
394
+ "score.weight": "model-00002-of-00002.safetensors"
395
+ }
396
+ }
runs/Feb06_21-16-21_gl1516.arc-ts.umich.edu/events.out.tfevents.1707295203.gl1516.arc-ts.umich.edu.3421130.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b47e6525e4faf19fba2605cf5415e913de05b450284ab7d011992a141427ff13
3
+ size 1380