End of training
Browse files- .gitattributes +1 -0
- README.md +148 -0
- added_tokens.json +0 -0
- config.json +61 -0
- generation_config.json +7 -0
- model.safetensors +3 -0
- special_tokens_map.json +125 -0
- spiece.model +3 -0
- tokenizer_config.json +3 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer_config.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,148 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
model-index:
|
6 |
+
- name: t5-base-p-l-akk-en-20241125-151008
|
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 |
+
# t5-base-p-l-akk-en-20241125-151008
|
14 |
+
|
15 |
+
This model was trained from scratch on the None dataset.
|
16 |
+
It achieves the following results on the evaluation set:
|
17 |
+
- Loss: 0.4584
|
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: 0.0001
|
37 |
+
- train_batch_size: 200
|
38 |
+
- eval_batch_size: 200
|
39 |
+
- seed: 42
|
40 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
41 |
+
- lr_scheduler_type: linear
|
42 |
+
- lr_scheduler_warmup_steps: 2000
|
43 |
+
- num_epochs: 200
|
44 |
+
|
45 |
+
### Training results
|
46 |
+
|
47 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
48 |
+
|:-------------:|:-----:|:------:|:---------------:|
|
49 |
+
| 0.9667 | 1.0 | 10362 | 0.9112 |
|
50 |
+
| 0.8355 | 2.0 | 20724 | 0.7909 |
|
51 |
+
| 0.772 | 3.0 | 31086 | 0.7263 |
|
52 |
+
| 0.7326 | 4.0 | 41448 | 0.6910 |
|
53 |
+
| 0.7033 | 5.0 | 51810 | 0.6666 |
|
54 |
+
| 0.6787 | 6.0 | 62172 | 0.6455 |
|
55 |
+
| 0.6633 | 7.0 | 72534 | 0.6329 |
|
56 |
+
| 0.652 | 8.0 | 82896 | 0.6206 |
|
57 |
+
| 0.6408 | 9.0 | 93258 | 0.6073 |
|
58 |
+
| 0.6315 | 10.0 | 103620 | 0.6015 |
|
59 |
+
| 0.6161 | 11.0 | 113982 | 0.5914 |
|
60 |
+
| 0.6211 | 12.0 | 124344 | 0.5857 |
|
61 |
+
| 0.6053 | 13.0 | 134706 | 0.5766 |
|
62 |
+
| 0.6043 | 14.0 | 145068 | 0.5727 |
|
63 |
+
| 0.5954 | 15.0 | 155430 | 0.5681 |
|
64 |
+
| 0.59 | 16.0 | 165792 | 0.5649 |
|
65 |
+
| 0.5844 | 17.0 | 176154 | 0.5628 |
|
66 |
+
| 0.579 | 18.0 | 186516 | 0.5564 |
|
67 |
+
| 0.5792 | 19.0 | 196878 | 0.5493 |
|
68 |
+
| 0.5739 | 20.0 | 207240 | 0.5479 |
|
69 |
+
| 0.567 | 21.0 | 217602 | 0.5435 |
|
70 |
+
| 0.5626 | 22.0 | 227964 | 0.5406 |
|
71 |
+
| 0.5591 | 23.0 | 238326 | 0.5375 |
|
72 |
+
| 0.5508 | 24.0 | 248688 | 0.5356 |
|
73 |
+
| 0.5548 | 25.0 | 259050 | 0.5329 |
|
74 |
+
| 0.5512 | 26.0 | 269412 | 0.5299 |
|
75 |
+
| 0.5473 | 27.0 | 279774 | 0.5267 |
|
76 |
+
| 0.5413 | 28.0 | 290136 | 0.5243 |
|
77 |
+
| 0.5433 | 29.0 | 300498 | 0.5246 |
|
78 |
+
| 0.5378 | 30.0 | 310860 | 0.5209 |
|
79 |
+
| 0.5375 | 31.0 | 321222 | 0.5206 |
|
80 |
+
| 0.5363 | 32.0 | 331584 | 0.5178 |
|
81 |
+
| 0.528 | 33.0 | 341946 | 0.5143 |
|
82 |
+
| 0.532 | 34.0 | 352308 | 0.5121 |
|
83 |
+
| 0.5279 | 35.0 | 362670 | 0.5137 |
|
84 |
+
| 0.5265 | 36.0 | 373032 | 0.5080 |
|
85 |
+
| 0.5231 | 37.0 | 383394 | 0.5077 |
|
86 |
+
| 0.5187 | 38.0 | 393756 | 0.5082 |
|
87 |
+
| 0.5191 | 39.0 | 404118 | 0.5047 |
|
88 |
+
| 0.5159 | 40.0 | 414480 | 0.5029 |
|
89 |
+
| 0.5159 | 41.0 | 424842 | 0.5014 |
|
90 |
+
| 0.5131 | 42.0 | 435204 | 0.4998 |
|
91 |
+
| 0.5137 | 43.0 | 445566 | 0.4973 |
|
92 |
+
| 0.5128 | 44.0 | 455928 | 0.4972 |
|
93 |
+
| 0.5101 | 45.0 | 466290 | 0.4985 |
|
94 |
+
| 0.505 | 46.0 | 476652 | 0.4969 |
|
95 |
+
| 0.5014 | 47.0 | 487014 | 0.4964 |
|
96 |
+
| 0.4988 | 48.0 | 497376 | 0.4938 |
|
97 |
+
| 0.5051 | 49.0 | 507738 | 0.4898 |
|
98 |
+
| 0.4974 | 50.0 | 518100 | 0.4928 |
|
99 |
+
| 0.4999 | 51.0 | 528462 | 0.4904 |
|
100 |
+
| 0.4973 | 52.0 | 538824 | 0.4884 |
|
101 |
+
| 0.4973 | 53.0 | 549186 | 0.4877 |
|
102 |
+
| 0.4913 | 54.0 | 559548 | 0.4879 |
|
103 |
+
| 0.4968 | 55.0 | 569910 | 0.4846 |
|
104 |
+
| 0.4916 | 56.0 | 580272 | 0.4838 |
|
105 |
+
| 0.4938 | 57.0 | 590634 | 0.4833 |
|
106 |
+
| 0.4866 | 58.0 | 600996 | 0.4819 |
|
107 |
+
| 0.4871 | 59.0 | 611358 | 0.4818 |
|
108 |
+
| 0.4837 | 60.0 | 621720 | 0.4792 |
|
109 |
+
| 0.4855 | 61.0 | 632082 | 0.4783 |
|
110 |
+
| 0.4828 | 62.0 | 642444 | 0.4781 |
|
111 |
+
| 0.4789 | 63.0 | 652806 | 0.4780 |
|
112 |
+
| 0.4781 | 64.0 | 663168 | 0.4785 |
|
113 |
+
| 0.4803 | 65.0 | 673530 | 0.4767 |
|
114 |
+
| 0.4791 | 66.0 | 683892 | 0.4755 |
|
115 |
+
| 0.4783 | 67.0 | 694254 | 0.4743 |
|
116 |
+
| 0.4772 | 68.0 | 704616 | 0.4739 |
|
117 |
+
| 0.4757 | 69.0 | 714978 | 0.4730 |
|
118 |
+
| 0.4708 | 70.0 | 725340 | 0.4711 |
|
119 |
+
| 0.4698 | 71.0 | 735702 | 0.4717 |
|
120 |
+
| 0.4719 | 72.0 | 746064 | 0.4733 |
|
121 |
+
| 0.4708 | 73.0 | 756426 | 0.4703 |
|
122 |
+
| 0.4717 | 74.0 | 766788 | 0.4700 |
|
123 |
+
| 0.4714 | 75.0 | 777150 | 0.4677 |
|
124 |
+
| 0.4641 | 76.0 | 787512 | 0.4688 |
|
125 |
+
| 0.4642 | 77.0 | 797874 | 0.4678 |
|
126 |
+
| 0.4656 | 78.0 | 808236 | 0.4666 |
|
127 |
+
| 0.4625 | 79.0 | 818598 | 0.4661 |
|
128 |
+
| 0.4623 | 80.0 | 828960 | 0.4664 |
|
129 |
+
| 0.4619 | 81.0 | 839322 | 0.4657 |
|
130 |
+
| 0.4574 | 82.0 | 849684 | 0.4635 |
|
131 |
+
| 0.4562 | 83.0 | 860046 | 0.4628 |
|
132 |
+
| 0.4593 | 84.0 | 870408 | 0.4613 |
|
133 |
+
| 0.4583 | 85.0 | 880770 | 0.4600 |
|
134 |
+
| 0.4573 | 86.0 | 891132 | 0.4598 |
|
135 |
+
| 0.4518 | 87.0 | 901494 | 0.4564 |
|
136 |
+
| 0.4599 | 88.0 | 911856 | 0.4577 |
|
137 |
+
| 0.4545 | 89.0 | 922218 | 0.4594 |
|
138 |
+
| 0.4534 | 90.0 | 932580 | 0.4564 |
|
139 |
+
| 0.449 | 91.0 | 942942 | 0.4564 |
|
140 |
+
| 0.4523 | 92.0 | 953304 | 0.4584 |
|
141 |
+
|
142 |
+
|
143 |
+
### Framework versions
|
144 |
+
|
145 |
+
- Transformers 4.45.2
|
146 |
+
- Pytorch 2.6.0.dev20241022+cu124
|
147 |
+
- Datasets 3.0.1
|
148 |
+
- Tokenizers 0.20.1
|
added_tokens.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
config.json
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/home/bly/GitHub/results/t5-base-e12",
|
3 |
+
"architectures": [
|
4 |
+
"T5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"classifier_dropout": 0.0,
|
7 |
+
"d_ff": 3072,
|
8 |
+
"d_kv": 64,
|
9 |
+
"d_model": 768,
|
10 |
+
"decoder_start_token_id": 0,
|
11 |
+
"dense_act_fn": "relu",
|
12 |
+
"dropout_rate": 0.1,
|
13 |
+
"eos_token_id": 1,
|
14 |
+
"feed_forward_proj": "relu",
|
15 |
+
"initializer_factor": 1.0,
|
16 |
+
"is_encoder_decoder": true,
|
17 |
+
"is_gated_act": false,
|
18 |
+
"layer_norm_epsilon": 1e-06,
|
19 |
+
"model_type": "t5",
|
20 |
+
"n_positions": 512,
|
21 |
+
"num_decoder_layers": 12,
|
22 |
+
"num_heads": 12,
|
23 |
+
"num_layers": 12,
|
24 |
+
"output_past": true,
|
25 |
+
"pad_token_id": 0,
|
26 |
+
"relative_attention_max_distance": 128,
|
27 |
+
"relative_attention_num_buckets": 32,
|
28 |
+
"task_specific_params": {
|
29 |
+
"summarization": {
|
30 |
+
"early_stopping": true,
|
31 |
+
"length_penalty": 2.0,
|
32 |
+
"max_length": 200,
|
33 |
+
"min_length": 30,
|
34 |
+
"no_repeat_ngram_size": 3,
|
35 |
+
"num_beams": 4,
|
36 |
+
"prefix": "summarize: "
|
37 |
+
},
|
38 |
+
"translation_en_to_de": {
|
39 |
+
"early_stopping": true,
|
40 |
+
"max_length": 300,
|
41 |
+
"num_beams": 4,
|
42 |
+
"prefix": "translate English to German: "
|
43 |
+
},
|
44 |
+
"translation_en_to_fr": {
|
45 |
+
"early_stopping": true,
|
46 |
+
"max_length": 300,
|
47 |
+
"num_beams": 4,
|
48 |
+
"prefix": "translate English to French: "
|
49 |
+
},
|
50 |
+
"translation_en_to_ro": {
|
51 |
+
"early_stopping": true,
|
52 |
+
"max_length": 300,
|
53 |
+
"num_beams": 4,
|
54 |
+
"prefix": "translate English to Romanian: "
|
55 |
+
}
|
56 |
+
},
|
57 |
+
"torch_dtype": "float32",
|
58 |
+
"transformers_version": "4.45.2",
|
59 |
+
"use_cache": true,
|
60 |
+
"vocab_size": 221682
|
61 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"decoder_start_token_id": 0,
|
4 |
+
"eos_token_id": 1,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.45.2"
|
7 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:17a2b664657e585e2f2fc23bba63ff1ef506c51923401ed41995a8fdb66c064d
|
3 |
+
size 1473954600
|
special_tokens_map.json
ADDED
@@ -0,0 +1,125 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<extra_id_0>",
|
4 |
+
"<extra_id_1>",
|
5 |
+
"<extra_id_2>",
|
6 |
+
"<extra_id_3>",
|
7 |
+
"<extra_id_4>",
|
8 |
+
"<extra_id_5>",
|
9 |
+
"<extra_id_6>",
|
10 |
+
"<extra_id_7>",
|
11 |
+
"<extra_id_8>",
|
12 |
+
"<extra_id_9>",
|
13 |
+
"<extra_id_10>",
|
14 |
+
"<extra_id_11>",
|
15 |
+
"<extra_id_12>",
|
16 |
+
"<extra_id_13>",
|
17 |
+
"<extra_id_14>",
|
18 |
+
"<extra_id_15>",
|
19 |
+
"<extra_id_16>",
|
20 |
+
"<extra_id_17>",
|
21 |
+
"<extra_id_18>",
|
22 |
+
"<extra_id_19>",
|
23 |
+
"<extra_id_20>",
|
24 |
+
"<extra_id_21>",
|
25 |
+
"<extra_id_22>",
|
26 |
+
"<extra_id_23>",
|
27 |
+
"<extra_id_24>",
|
28 |
+
"<extra_id_25>",
|
29 |
+
"<extra_id_26>",
|
30 |
+
"<extra_id_27>",
|
31 |
+
"<extra_id_28>",
|
32 |
+
"<extra_id_29>",
|
33 |
+
"<extra_id_30>",
|
34 |
+
"<extra_id_31>",
|
35 |
+
"<extra_id_32>",
|
36 |
+
"<extra_id_33>",
|
37 |
+
"<extra_id_34>",
|
38 |
+
"<extra_id_35>",
|
39 |
+
"<extra_id_36>",
|
40 |
+
"<extra_id_37>",
|
41 |
+
"<extra_id_38>",
|
42 |
+
"<extra_id_39>",
|
43 |
+
"<extra_id_40>",
|
44 |
+
"<extra_id_41>",
|
45 |
+
"<extra_id_42>",
|
46 |
+
"<extra_id_43>",
|
47 |
+
"<extra_id_44>",
|
48 |
+
"<extra_id_45>",
|
49 |
+
"<extra_id_46>",
|
50 |
+
"<extra_id_47>",
|
51 |
+
"<extra_id_48>",
|
52 |
+
"<extra_id_49>",
|
53 |
+
"<extra_id_50>",
|
54 |
+
"<extra_id_51>",
|
55 |
+
"<extra_id_52>",
|
56 |
+
"<extra_id_53>",
|
57 |
+
"<extra_id_54>",
|
58 |
+
"<extra_id_55>",
|
59 |
+
"<extra_id_56>",
|
60 |
+
"<extra_id_57>",
|
61 |
+
"<extra_id_58>",
|
62 |
+
"<extra_id_59>",
|
63 |
+
"<extra_id_60>",
|
64 |
+
"<extra_id_61>",
|
65 |
+
"<extra_id_62>",
|
66 |
+
"<extra_id_63>",
|
67 |
+
"<extra_id_64>",
|
68 |
+
"<extra_id_65>",
|
69 |
+
"<extra_id_66>",
|
70 |
+
"<extra_id_67>",
|
71 |
+
"<extra_id_68>",
|
72 |
+
"<extra_id_69>",
|
73 |
+
"<extra_id_70>",
|
74 |
+
"<extra_id_71>",
|
75 |
+
"<extra_id_72>",
|
76 |
+
"<extra_id_73>",
|
77 |
+
"<extra_id_74>",
|
78 |
+
"<extra_id_75>",
|
79 |
+
"<extra_id_76>",
|
80 |
+
"<extra_id_77>",
|
81 |
+
"<extra_id_78>",
|
82 |
+
"<extra_id_79>",
|
83 |
+
"<extra_id_80>",
|
84 |
+
"<extra_id_81>",
|
85 |
+
"<extra_id_82>",
|
86 |
+
"<extra_id_83>",
|
87 |
+
"<extra_id_84>",
|
88 |
+
"<extra_id_85>",
|
89 |
+
"<extra_id_86>",
|
90 |
+
"<extra_id_87>",
|
91 |
+
"<extra_id_88>",
|
92 |
+
"<extra_id_89>",
|
93 |
+
"<extra_id_90>",
|
94 |
+
"<extra_id_91>",
|
95 |
+
"<extra_id_92>",
|
96 |
+
"<extra_id_93>",
|
97 |
+
"<extra_id_94>",
|
98 |
+
"<extra_id_95>",
|
99 |
+
"<extra_id_96>",
|
100 |
+
"<extra_id_97>",
|
101 |
+
"<extra_id_98>",
|
102 |
+
"<extra_id_99>"
|
103 |
+
],
|
104 |
+
"eos_token": {
|
105 |
+
"content": "</s>",
|
106 |
+
"lstrip": false,
|
107 |
+
"normalized": false,
|
108 |
+
"rstrip": false,
|
109 |
+
"single_word": false
|
110 |
+
},
|
111 |
+
"pad_token": {
|
112 |
+
"content": "<pad>",
|
113 |
+
"lstrip": false,
|
114 |
+
"normalized": false,
|
115 |
+
"rstrip": false,
|
116 |
+
"single_word": false
|
117 |
+
},
|
118 |
+
"unk_token": {
|
119 |
+
"content": "<unk>",
|
120 |
+
"lstrip": false,
|
121 |
+
"normalized": false,
|
122 |
+
"rstrip": false,
|
123 |
+
"single_word": false
|
124 |
+
}
|
125 |
+
}
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
|
3 |
+
size 791656
|
tokenizer_config.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:90cf171e287b67e51a7c5883be3b39bffaa0afacae1552a6a07245468f44b3d5
|
3 |
+
size 33692787
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f331445e7be1dbfbcfd278c5c355cae976c750563630bee5383d8313f61d6aa7
|
3 |
+
size 5432
|