Hugging Face's logo

BramVanroy
/
falcon-7b-ft-alpaca-cleaned-dutch

Text Generation
Transformers
Safetensors
Dutch
falcon
custom_code
text-generation-inference
Model card Files Community
2
BramVanroy commited on
Commit
227a3af
·
1 Parent(s): cdfd160

init model

Browse files
Files changed (13) hide show
  1. README.md +172 -0
  2. all_results.json +14 -0
  3. config.json +33 -0
  4. eval_results.json +9 -0
  5. generation_config.json +6 -0
  6. model-00001-of-00002.safetensors +3 -0
  7. model-00002-of-00002.safetensors +3 -0
  8. model.safetensors.index.json +202 -0
  9. special_tokens_map.json +16 -0
  10. tokenizer.json +0 -0
  11. tokenizer_config.json +7 -0
  12. train_results.json +8 -0
  13. trainer_state.json +0 -0
README.md CHANGED
@@ -1,3 +1,175 @@
1
  ---
2
  license: cc-by-nc-4.0
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: cc-by-nc-4.0
3
+ datasets:
4
+ - BramVanroy/alpaca-cleaned-dutch
5
+ model-index:
6
+ - name: falcon-7b-ft-alpaca-cleaned-dutch
7
+ results: []
8
  ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # falcon-7b-ft-alpaca-cleaned-dutch
14
+
15
+ This model is a fine-tuned version of [ybelkada/falcon-7b-sharded-bf16](https://huggingface.co/ybelkada/falcon-7b-sharded-bf16) on the BramVanroy/alpaca-cleaned-dutch dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 1.5448
18
+
19
+ ## Model description
20
+
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
+
31
+ ## Training procedure
32
+
33
+ ### Training hyperparameters
34
+
35
+ The following hyperparameters were used during training:
36
+ - learning_rate: 1e-05
37
+ - train_batch_size: 4
38
+ - eval_batch_size: 4
39
+ - seed: 42
40
+ - distributed_type: multi-GPU
41
+ - num_devices: 4
42
+ - gradient_accumulation_steps: 8
43
+ - total_train_batch_size: 128
44
+ - total_eval_batch_size: 16
45
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
+ - lr_scheduler_type: cosine
47
+ - lr_scheduler_warmup_ratio: 0.03
48
+ - num_epochs: 3
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss |
53
+ |:-------------:|:-----:|:----:|:---------------:|
54
+ | 1.9832 | 0.03 | 10 | 1.8889 |
55
+ | 1.9355 | 0.05 | 20 | 1.8834 |
56
+ | 1.9694 | 0.08 | 30 | 1.8671 |
57
+ | 1.9048 | 0.1 | 40 | 1.8328 |
58
+ | 1.8443 | 0.13 | 50 | 1.7970 |
59
+ | 1.7448 | 0.16 | 60 | 1.7711 |
60
+ | 1.8004 | 0.18 | 70 | 1.7522 |
61
+ | 1.7767 | 0.21 | 80 | 1.7370 |
62
+ | 1.7733 | 0.23 | 90 | 1.7248 |
63
+ | 1.7926 | 0.26 | 100 | 1.7149 |
64
+ | 1.8258 | 0.29 | 110 | 1.7066 |
65
+ | 1.6709 | 0.31 | 120 | 1.6993 |
66
+ | 1.6612 | 0.34 | 130 | 1.6926 |
67
+ | 1.8463 | 0.36 | 140 | 1.6867 |
68
+ | 1.8413 | 0.39 | 150 | 1.6814 |
69
+ | 1.7659 | 0.42 | 160 | 1.6765 |
70
+ | 1.69 | 0.44 | 170 | 1.6715 |
71
+ | 1.7219 | 0.47 | 180 | 1.6673 |
72
+ | 1.6755 | 0.49 | 190 | 1.6627 |
73
+ | 1.7823 | 0.52 | 200 | 1.6584 |
74
+ | 1.7635 | 0.55 | 210 | 1.6545 |
75
+ | 1.7335 | 0.57 | 220 | 1.6506 |
76
+ | 1.7272 | 0.6 | 230 | 1.6471 |
77
+ | 1.718 | 0.63 | 240 | 1.6436 |
78
+ | 1.6899 | 0.65 | 250 | 1.6403 |
79
+ | 1.622 | 0.68 | 260 | 1.6370 |
80
+ | 1.6556 | 0.7 | 270 | 1.6337 |
81
+ | 1.7912 | 0.73 | 280 | 1.6304 |
82
+ | 1.6025 | 0.76 | 290 | 1.6274 |
83
+ | 1.7181 | 0.78 | 300 | 1.6246 |
84
+ | 1.7452 | 0.81 | 310 | 1.6217 |
85
+ | 1.5975 | 0.83 | 320 | 1.6189 |
86
+ | 1.5754 | 0.86 | 330 | 1.6162 |
87
+ | 1.7077 | 0.89 | 340 | 1.6136 |
88
+ | 1.5848 | 0.91 | 350 | 1.6112 |
89
+ | 1.7011 | 0.94 | 360 | 1.6087 |
90
+ | 1.6697 | 0.96 | 370 | 1.6065 |
91
+ | 1.6633 | 0.99 | 380 | 1.6042 |
92
+ | 1.6722 | 1.02 | 390 | 1.6015 |
93
+ | 1.7181 | 1.04 | 400 | 1.5993 |
94
+ | 1.6414 | 1.07 | 410 | 1.5972 |
95
+ | 1.6856 | 1.09 | 420 | 1.5952 |
96
+ | 1.6491 | 1.12 | 430 | 1.5930 |
97
+ | 1.6736 | 1.15 | 440 | 1.5912 |
98
+ | 1.619 | 1.17 | 450 | 1.5893 |
99
+ | 1.6452 | 1.2 | 460 | 1.5870 |
100
+ | 1.6498 | 1.22 | 470 | 1.5854 |
101
+ | 1.675 | 1.25 | 480 | 1.5839 |
102
+ | 1.684 | 1.28 | 490 | 1.5823 |
103
+ | 1.6379 | 1.3 | 500 | 1.5802 |
104
+ | 1.5173 | 1.33 | 510 | 1.5786 |
105
+ | 1.6443 | 1.35 | 520 | 1.5773 |
106
+ | 1.5628 | 1.38 | 530 | 1.5755 |
107
+ | 1.7287 | 1.41 | 540 | 1.5738 |
108
+ | 1.5615 | 1.43 | 550 | 1.5725 |
109
+ | 1.6129 | 1.46 | 560 | 1.5712 |
110
+ | 1.6709 | 1.48 | 570 | 1.5700 |
111
+ | 1.5818 | 1.51 | 580 | 1.5683 |
112
+ | 1.6358 | 1.54 | 590 | 1.5672 |
113
+ | 1.6513 | 1.56 | 600 | 1.5662 |
114
+ | 1.5637 | 1.59 | 610 | 1.5654 |
115
+ | 1.612 | 1.62 | 620 | 1.5643 |
116
+ | 1.6396 | 1.64 | 630 | 1.5630 |
117
+ | 1.6414 | 1.67 | 640 | 1.5620 |
118
+ | 1.6096 | 1.69 | 650 | 1.5611 |
119
+ | 1.6149 | 1.72 | 660 | 1.5603 |
120
+ | 1.5886 | 1.75 | 670 | 1.5593 |
121
+ | 1.537 | 1.77 | 680 | 1.5582 |
122
+ | 1.5883 | 1.8 | 690 | 1.5574 |
123
+ | 1.6512 | 1.82 | 700 | 1.5566 |
124
+ | 1.683 | 1.85 | 710 | 1.5559 |
125
+ | 1.7059 | 1.88 | 720 | 1.5549 |
126
+ | 1.5453 | 1.9 | 730 | 1.5542 |
127
+ | 1.5738 | 1.93 | 740 | 1.5536 |
128
+ | 1.6004 | 1.95 | 750 | 1.5530 |
129
+ | 1.6753 | 1.98 | 760 | 1.5523 |
130
+ | 1.6362 | 2.01 | 770 | 1.5517 |
131
+ | 1.5805 | 2.03 | 780 | 1.5511 |
132
+ | 1.6416 | 2.06 | 790 | 1.5508 |
133
+ | 1.5755 | 2.08 | 800 | 1.5506 |
134
+ | 1.5763 | 2.11 | 810 | 1.5501 |
135
+ | 1.7112 | 2.14 | 820 | 1.5497 |
136
+ | 1.6533 | 2.16 | 830 | 1.5493 |
137
+ | 1.6008 | 2.19 | 840 | 1.5489 |
138
+ | 1.5731 | 2.21 | 850 | 1.5485 |
139
+ | 1.4975 | 2.24 | 860 | 1.5480 |
140
+ | 1.6158 | 2.27 | 870 | 1.5478 |
141
+ | 1.6063 | 2.29 | 880 | 1.5474 |
142
+ | 1.628 | 2.32 | 890 | 1.5470 |
143
+ | 1.6177 | 2.34 | 900 | 1.5468 |
144
+ | 1.5646 | 2.37 | 910 | 1.5467 |
145
+ | 1.5272 | 2.4 | 920 | 1.5466 |
146
+ | 1.5402 | 2.42 | 930 | 1.5464 |
147
+ | 1.5815 | 2.45 | 940 | 1.5461 |
148
+ | 1.4857 | 2.47 | 950 | 1.5459 |
149
+ | 1.5923 | 2.5 | 960 | 1.5458 |
150
+ | 1.6167 | 2.53 | 970 | 1.5456 |
151
+ | 1.7214 | 2.55 | 980 | 1.5456 |
152
+ | 1.5467 | 2.58 | 990 | 1.5455 |
153
+ | 1.6455 | 2.61 | 1000 | 1.5453 |
154
+ | 1.6137 | 2.63 | 1010 | 1.5453 |
155
+ | 1.6104 | 2.66 | 1020 | 1.5453 |
156
+ | 1.6756 | 2.68 | 1030 | 1.5451 |
157
+ | 1.5818 | 2.71 | 1040 | 1.5450 |
158
+ | 1.5829 | 2.74 | 1050 | 1.5450 |
159
+ | 1.5753 | 2.76 | 1060 | 1.5450 |
160
+ | 1.6484 | 2.79 | 1070 | 1.5450 |
161
+ | 1.6765 | 2.81 | 1080 | 1.5450 |
162
+ | 1.623 | 2.84 | 1090 | 1.5449 |
163
+ | 1.6901 | 2.87 | 1100 | 1.5449 |
164
+ | 1.6601 | 2.89 | 1110 | 1.5449 |
165
+ | 1.6763 | 2.92 | 1120 | 1.5449 |
166
+ | 1.6203 | 2.94 | 1130 | 1.5449 |
167
+ | 1.5113 | 2.97 | 1140 | 1.5448 |
168
+
169
+
170
+ ### Framework versions
171
+
172
+ - Transformers 4.30.2
173
+ - Pytorch 2.0.1+cu117
174
+ - Datasets 2.13.1
175
+ - Tokenizers 0.13.3
all_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.99,
3
+ "eval_loss": 1.5448263883590698,
4
+ "eval_runtime": 221.5449,
5
+ "eval_samples": 2586,
6
+ "eval_samples_per_second": 11.673,
7
+ "eval_steps_per_second": 0.731,
8
+ "perplexity": 4.687157811221204,
9
+ "train_loss": 1.6580357963464072,
10
+ "train_runtime": 61956.043,
11
+ "train_samples": 49125,
12
+ "train_samples_per_second": 2.379,
13
+ "train_steps_per_second": 0.019
14
+ }
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/local/vanroy/llm-finetuning/instruct-tuning/merged/falcon-7b-ft-alpaca-cleaned-dutch",
3
+ "alibi": false,
4
+ "apply_residual_connection_post_layernorm": false,
5
+ "architectures": [
6
+ "RWForCausalLM"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "auto_map": {
10
+ "AutoConfig": "tiiuae/falcon-7b--configuration_RW.RWConfig",
11
+ "AutoModel": "tiiuae/falcon-7b--modelling_RW.RWModel",
12
+ "AutoModelForCausalLM": "tiiuae/falcon-7b--modelling_RW.RWForCausalLM",
13
+ "AutoModelForQuestionAnswering": "tiiuae/falcon-7b--modelling_RW.RWForQuestionAnswering",
14
+ "AutoModelForSequenceClassification": "tiiuae/falcon-7b--modelling_RW.RWForSequenceClassification",
15
+ "AutoModelForTokenClassification": "tiiuae/falcon-7b--modelling_RW.RWForTokenClassification"
16
+ },
17
+ "bias": false,
18
+ "bos_token_id": 11,
19
+ "eos_token_id": 11,
20
+ "hidden_dropout": 0.0,
21
+ "hidden_size": 4544,
22
+ "initializer_range": 0.02,
23
+ "layer_norm_epsilon": 1e-05,
24
+ "model_type": "RefinedWebModel",
25
+ "multi_query": true,
26
+ "n_head": 71,
27
+ "n_layer": 32,
28
+ "parallel_attn": true,
29
+ "torch_dtype": "bfloat16",
30
+ "transformers_version": "4.30.2",
31
+ "use_cache": true,
32
+ "vocab_size": 65024
33
+ }
eval_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.99,
3
+ "eval_loss": 1.5448263883590698,
4
+ "eval_runtime": 221.5449,
5
+ "eval_samples": 2586,
6
+ "eval_samples_per_second": 11.673,
7
+ "eval_steps_per_second": 0.731,
8
+ "perplexity": 4.687157811221204
9
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.30.2"
6
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:343a8f4a33ef0c0f57053da7b2662b3f44ba620985029cf718f3f8cce7ebdf4b
3
+ size 9950994832
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e214536f52f17f46c418e1136fde56c08c97f3940747df789e1ee25281b7ef3d
3
+ size 3892469920
model.safetensors.index.json ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 13843441408
4
+ },
5
+ "weight_map": {
6
+ "transformer.h.0.input_layernorm.bias": "model-00001-of-00002.safetensors",
7
+ "transformer.h.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
8
+ "transformer.h.0.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
9
+ "transformer.h.0.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
10
+ "transformer.h.0.self_attention.dense.weight": "model-00001-of-00002.safetensors",
11
+ "transformer.h.0.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
12
+ "transformer.h.1.input_layernorm.bias": "model-00001-of-00002.safetensors",
13
+ "transformer.h.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
14
+ "transformer.h.1.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
15
+ "transformer.h.1.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
16
+ "transformer.h.1.self_attention.dense.weight": "model-00001-of-00002.safetensors",
17
+ "transformer.h.1.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
18
+ "transformer.h.10.input_layernorm.bias": "model-00001-of-00002.safetensors",
19
+ "transformer.h.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
20
+ "transformer.h.10.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
21
+ "transformer.h.10.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
22
+ "transformer.h.10.self_attention.dense.weight": "model-00001-of-00002.safetensors",
23
+ "transformer.h.10.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
24
+ "transformer.h.11.input_layernorm.bias": "model-00001-of-00002.safetensors",
25
+ "transformer.h.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
26
+ "transformer.h.11.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
27
+ "transformer.h.11.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
28
+ "transformer.h.11.self_attention.dense.weight": "model-00001-of-00002.safetensors",
29
+ "transformer.h.11.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
30
+ "transformer.h.12.input_layernorm.bias": "model-00001-of-00002.safetensors",
31
+ "transformer.h.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
32
+ "transformer.h.12.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
33
+ "transformer.h.12.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
34
+ "transformer.h.12.self_attention.dense.weight": "model-00001-of-00002.safetensors",
35
+ "transformer.h.12.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
36
+ "transformer.h.13.input_layernorm.bias": "model-00001-of-00002.safetensors",
37
+ "transformer.h.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
38
+ "transformer.h.13.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
39
+ "transformer.h.13.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
40
+ "transformer.h.13.self_attention.dense.weight": "model-00001-of-00002.safetensors",
41
+ "transformer.h.13.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
42
+ "transformer.h.14.input_layernorm.bias": "model-00001-of-00002.safetensors",
43
+ "transformer.h.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
44
+ "transformer.h.14.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
45
+ "transformer.h.14.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
46
+ "transformer.h.14.self_attention.dense.weight": "model-00001-of-00002.safetensors",
47
+ "transformer.h.14.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
48
+ "transformer.h.15.input_layernorm.bias": "model-00001-of-00002.safetensors",
49
+ "transformer.h.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
50
+ "transformer.h.15.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
51
+ "transformer.h.15.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
52
+ "transformer.h.15.self_attention.dense.weight": "model-00001-of-00002.safetensors",
53
+ "transformer.h.15.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
54
+ "transformer.h.16.input_layernorm.bias": "model-00001-of-00002.safetensors",
55
+ "transformer.h.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
56
+ "transformer.h.16.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
57
+ "transformer.h.16.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
58
+ "transformer.h.16.self_attention.dense.weight": "model-00001-of-00002.safetensors",
59
+ "transformer.h.16.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
60
+ "transformer.h.17.input_layernorm.bias": "model-00001-of-00002.safetensors",
61
+ "transformer.h.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
62
+ "transformer.h.17.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
63
+ "transformer.h.17.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
64
+ "transformer.h.17.self_attention.dense.weight": "model-00001-of-00002.safetensors",
65
+ "transformer.h.17.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
66
+ "transformer.h.18.input_layernorm.bias": "model-00001-of-00002.safetensors",
67
+ "transformer.h.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
68
+ "transformer.h.18.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
69
+ "transformer.h.18.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
70
+ "transformer.h.18.self_attention.dense.weight": "model-00001-of-00002.safetensors",
71
+ "transformer.h.18.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
72
+ "transformer.h.19.input_layernorm.bias": "model-00001-of-00002.safetensors",
73
+ "transformer.h.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
74
+ "transformer.h.19.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
75
+ "transformer.h.19.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
76
+ "transformer.h.19.self_attention.dense.weight": "model-00001-of-00002.safetensors",
77
+ "transformer.h.19.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
78
+ "transformer.h.2.input_layernorm.bias": "model-00001-of-00002.safetensors",
79
+ "transformer.h.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
80
+ "transformer.h.2.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
81
+ "transformer.h.2.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
82
+ "transformer.h.2.self_attention.dense.weight": "model-00001-of-00002.safetensors",
83
+ "transformer.h.2.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
84
+ "transformer.h.20.input_layernorm.bias": "model-00001-of-00002.safetensors",
85
+ "transformer.h.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
86
+ "transformer.h.20.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
87
+ "transformer.h.20.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
88
+ "transformer.h.20.self_attention.dense.weight": "model-00001-of-00002.safetensors",
89
+ "transformer.h.20.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
90
+ "transformer.h.21.input_layernorm.bias": "model-00001-of-00002.safetensors",
91
+ "transformer.h.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
92
+ "transformer.h.21.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
93
+ "transformer.h.21.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
94
+ "transformer.h.21.self_attention.dense.weight": "model-00001-of-00002.safetensors",
95
+ "transformer.h.21.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
96
+ "transformer.h.22.input_layernorm.bias": "model-00001-of-00002.safetensors",
97
+ "transformer.h.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
98
+ "transformer.h.22.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
99
+ "transformer.h.22.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
100
+ "transformer.h.22.self_attention.dense.weight": "model-00001-of-00002.safetensors",
101
+ "transformer.h.22.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
102
+ "transformer.h.23.input_layernorm.bias": "model-00002-of-00002.safetensors",
103
+ "transformer.h.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
104
+ "transformer.h.23.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
105
+ "transformer.h.23.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
106
+ "transformer.h.23.self_attention.dense.weight": "model-00002-of-00002.safetensors",
107
+ "transformer.h.23.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
108
+ "transformer.h.24.input_layernorm.bias": "model-00002-of-00002.safetensors",
109
+ "transformer.h.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
110
+ "transformer.h.24.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
111
+ "transformer.h.24.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
112
+ "transformer.h.24.self_attention.dense.weight": "model-00002-of-00002.safetensors",
113
+ "transformer.h.24.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
114
+ "transformer.h.25.input_layernorm.bias": "model-00002-of-00002.safetensors",
115
+ "transformer.h.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
116
+ "transformer.h.25.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
117
+ "transformer.h.25.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
118
+ "transformer.h.25.self_attention.dense.weight": "model-00002-of-00002.safetensors",
119
+ "transformer.h.25.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
120
+ "transformer.h.26.input_layernorm.bias": "model-00002-of-00002.safetensors",
121
+ "transformer.h.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
122
+ "transformer.h.26.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
123
+ "transformer.h.26.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
124
+ "transformer.h.26.self_attention.dense.weight": "model-00002-of-00002.safetensors",
125
+ "transformer.h.26.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
126
+ "transformer.h.27.input_layernorm.bias": "model-00002-of-00002.safetensors",
127
+ "transformer.h.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
128
+ "transformer.h.27.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
129
+ "transformer.h.27.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
130
+ "transformer.h.27.self_attention.dense.weight": "model-00002-of-00002.safetensors",
131
+ "transformer.h.27.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
132
+ "transformer.h.28.input_layernorm.bias": "model-00002-of-00002.safetensors",
133
+ "transformer.h.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
134
+ "transformer.h.28.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
135
+ "transformer.h.28.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
136
+ "transformer.h.28.self_attention.dense.weight": "model-00002-of-00002.safetensors",
137
+ "transformer.h.28.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
138
+ "transformer.h.29.input_layernorm.bias": "model-00002-of-00002.safetensors",
139
+ "transformer.h.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
140
+ "transformer.h.29.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
141
+ "transformer.h.29.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
142
+ "transformer.h.29.self_attention.dense.weight": "model-00002-of-00002.safetensors",
143
+ "transformer.h.29.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
144
+ "transformer.h.3.input_layernorm.bias": "model-00001-of-00002.safetensors",
145
+ "transformer.h.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
146
+ "transformer.h.3.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
147
+ "transformer.h.3.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
148
+ "transformer.h.3.self_attention.dense.weight": "model-00001-of-00002.safetensors",
149
+ "transformer.h.3.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
150
+ "transformer.h.30.input_layernorm.bias": "model-00002-of-00002.safetensors",
151
+ "transformer.h.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
152
+ "transformer.h.30.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
153
+ "transformer.h.30.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
154
+ "transformer.h.30.self_attention.dense.weight": "model-00002-of-00002.safetensors",
155
+ "transformer.h.30.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
156
+ "transformer.h.31.input_layernorm.bias": "model-00002-of-00002.safetensors",
157
+ "transformer.h.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
158
+ "transformer.h.31.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
159
+ "transformer.h.31.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
160
+ "transformer.h.31.self_attention.dense.weight": "model-00002-of-00002.safetensors",
161
+ "transformer.h.31.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
162
+ "transformer.h.4.input_layernorm.bias": "model-00001-of-00002.safetensors",
163
+ "transformer.h.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
164
+ "transformer.h.4.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
165
+ "transformer.h.4.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
166
+ "transformer.h.4.self_attention.dense.weight": "model-00001-of-00002.safetensors",
167
+ "transformer.h.4.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
168
+ "transformer.h.5.input_layernorm.bias": "model-00001-of-00002.safetensors",
169
+ "transformer.h.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
170
+ "transformer.h.5.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
171
+ "transformer.h.5.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
172
+ "transformer.h.5.self_attention.dense.weight": "model-00001-of-00002.safetensors",
173
+ "transformer.h.5.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
174
+ "transformer.h.6.input_layernorm.bias": "model-00001-of-00002.safetensors",
175
+ "transformer.h.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
176
+ "transformer.h.6.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
177
+ "transformer.h.6.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
178
+ "transformer.h.6.self_attention.dense.weight": "model-00001-of-00002.safetensors",
179
+ "transformer.h.6.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
180
+ "transformer.h.7.input_layernorm.bias": "model-00001-of-00002.safetensors",
181
+ "transformer.h.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
182
+ "transformer.h.7.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
183
+ "transformer.h.7.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
184
+ "transformer.h.7.self_attention.dense.weight": "model-00001-of-00002.safetensors",
185
+ "transformer.h.7.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
186
+ "transformer.h.8.input_layernorm.bias": "model-00001-of-00002.safetensors",
187
+ "transformer.h.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
188
+ "transformer.h.8.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
189
+ "transformer.h.8.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
190
+ "transformer.h.8.self_attention.dense.weight": "model-00001-of-00002.safetensors",
191
+ "transformer.h.8.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
192
+ "transformer.h.9.input_layernorm.bias": "model-00001-of-00002.safetensors",
193
+ "transformer.h.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
194
+ "transformer.h.9.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
195
+ "transformer.h.9.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
196
+ "transformer.h.9.self_attention.dense.weight": "model-00001-of-00002.safetensors",
197
+ "transformer.h.9.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
198
+ "transformer.ln_f.bias": "model-00002-of-00002.safetensors",
199
+ "transformer.ln_f.weight": "model-00002-of-00002.safetensors",
200
+ "transformer.word_embeddings.weight": "model-00001-of-00002.safetensors"
201
+ }
202
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ ">>TITLE<<",
4
+ ">>ABSTRACT<<",
5
+ ">>INTRODUCTION<<",
6
+ ">>SUMMARY<<",
7
+ ">>COMMENT<<",
8
+ ">>ANSWER<<",
9
+ ">>QUESTION<<",
10
+ ">>DOMAIN<<",
11
+ ">>PREFIX<<",
12
+ ">>SUFFIX<<",
13
+ ">>MIDDLE<<"
14
+ ],
15
+ "eos_token": "<|endoftext|>"
16
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "clean_up_tokenization_spaces": true,
4
+ "eos_token": "<|endoftext|>",
5
+ "model_max_length": 2048,
6
+ "tokenizer_class": "PreTrainedTokenizerFast"
7
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.99,
3
+ "train_loss": 1.6580357963464072,
4
+ "train_runtime": 61956.043,
5
+ "train_samples": 49125,
6
+ "train_samples_per_second": 2.379,
7
+ "train_steps_per_second": 0.019
8
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff