Ethan Sim
commited on
Commit
•
a7706cb
1
Parent(s):
05c098b
stage best base simple tfidf wce model
Browse files- checkpoint-60000/config.json +62 -0
- checkpoint-60000/generation_config.json +16 -0
- checkpoint-60000/optimizer.pt +3 -0
- checkpoint-60000/pytorch_model.bin +3 -0
- checkpoint-60000/rng_state.pth +3 -0
- checkpoint-60000/scaler.pt +3 -0
- checkpoint-60000/scheduler.pt +3 -0
- checkpoint-60000/source.spm +0 -0
- checkpoint-60000/special_tokens_map.json +5 -0
- checkpoint-60000/target.spm +0 -0
- checkpoint-60000/tokenizer_config.json +12 -0
- checkpoint-60000/trainer_state.json +256 -0
- checkpoint-60000/training_args.bin +3 -0
- checkpoint-60000/vocab.json +0 -0
- config.json +62 -0
- generation_config.json +16 -0
- pytorch_model.bin +3 -0
- source.spm +0 -0
- special_tokens_map.json +5 -0
- target.spm +0 -0
- tokenizer_config.json +12 -0
- training_args.bin +3 -0
- vocab.json +0 -0
checkpoint-60000/config.json
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Helsinki-NLP/opus-mt-en-fr",
|
3 |
+
"_num_labels": 3,
|
4 |
+
"activation_dropout": 0.0,
|
5 |
+
"activation_function": "swish",
|
6 |
+
"add_bias_logits": false,
|
7 |
+
"add_final_layer_norm": false,
|
8 |
+
"architectures": [
|
9 |
+
"MarianMTModel"
|
10 |
+
],
|
11 |
+
"attention_dropout": 0.0,
|
12 |
+
"bad_words_ids": [
|
13 |
+
[
|
14 |
+
59513
|
15 |
+
]
|
16 |
+
],
|
17 |
+
"bos_token_id": 0,
|
18 |
+
"classif_dropout": 0.0,
|
19 |
+
"classifier_dropout": 0.0,
|
20 |
+
"d_model": 512,
|
21 |
+
"decoder_attention_heads": 8,
|
22 |
+
"decoder_ffn_dim": 2048,
|
23 |
+
"decoder_layerdrop": 0.0,
|
24 |
+
"decoder_layers": 6,
|
25 |
+
"decoder_start_token_id": 59513,
|
26 |
+
"decoder_vocab_size": 59514,
|
27 |
+
"dropout": 0.1,
|
28 |
+
"encoder_attention_heads": 8,
|
29 |
+
"encoder_ffn_dim": 2048,
|
30 |
+
"encoder_layerdrop": 0.0,
|
31 |
+
"encoder_layers": 6,
|
32 |
+
"eos_token_id": 0,
|
33 |
+
"forced_eos_token_id": 0,
|
34 |
+
"gradient_checkpointing": false,
|
35 |
+
"id2label": {
|
36 |
+
"0": "LABEL_0",
|
37 |
+
"1": "LABEL_1",
|
38 |
+
"2": "LABEL_2"
|
39 |
+
},
|
40 |
+
"init_std": 0.02,
|
41 |
+
"is_encoder_decoder": true,
|
42 |
+
"label2id": {
|
43 |
+
"LABEL_0": 0,
|
44 |
+
"LABEL_1": 1,
|
45 |
+
"LABEL_2": 2
|
46 |
+
},
|
47 |
+
"max_length": 512,
|
48 |
+
"max_position_embeddings": 512,
|
49 |
+
"model_type": "marian",
|
50 |
+
"normalize_before": false,
|
51 |
+
"normalize_embedding": false,
|
52 |
+
"num_beams": 4,
|
53 |
+
"num_hidden_layers": 6,
|
54 |
+
"pad_token_id": 59513,
|
55 |
+
"scale_embedding": true,
|
56 |
+
"share_encoder_decoder_embeddings": true,
|
57 |
+
"static_position_embeddings": true,
|
58 |
+
"torch_dtype": "float32",
|
59 |
+
"transformers_version": "4.28.0",
|
60 |
+
"use_cache": true,
|
61 |
+
"vocab_size": 59514
|
62 |
+
}
|
checkpoint-60000/generation_config.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bad_words_ids": [
|
3 |
+
[
|
4 |
+
59513
|
5 |
+
]
|
6 |
+
],
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"decoder_start_token_id": 59513,
|
9 |
+
"eos_token_id": 0,
|
10 |
+
"forced_eos_token_id": 0,
|
11 |
+
"max_length": 512,
|
12 |
+
"num_beams": 4,
|
13 |
+
"pad_token_id": 59513,
|
14 |
+
"renormalize_logits": true,
|
15 |
+
"transformers_version": "4.28.0"
|
16 |
+
}
|
checkpoint-60000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2e59520691c117ea1bd877e1bfe01882afb6344ca21e55b98715bd485704a575
|
3 |
+
size 597025797
|
checkpoint-60000/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8fc98e1224f3c436077f903fb1738893ae0cc176dff85bbd440b582504cf6967
|
3 |
+
size 298763205
|
checkpoint-60000/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:425f4664411f9ce455fd3bd3524c36aefb9f3d55834e6f423d5ea5f4789b68ac
|
3 |
+
size 14511
|
checkpoint-60000/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6387ad04f732286d3be24c378e3195aff7d77378a7b0a5ad2c05e2d6bd20582e
|
3 |
+
size 557
|
checkpoint-60000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:16591d2163f8bc85d56572a600f474f5f9444cf73f0e3bfd3e50b0fda488247e
|
3 |
+
size 627
|
checkpoint-60000/source.spm
ADDED
Binary file (778 kB). View file
|
|
checkpoint-60000/special_tokens_map.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eos_token": "</s>",
|
3 |
+
"pad_token": "<pad>",
|
4 |
+
"unk_token": "<unk>"
|
5 |
+
}
|
checkpoint-60000/target.spm
ADDED
Binary file (802 kB). View file
|
|
checkpoint-60000/tokenizer_config.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"clean_up_tokenization_spaces": true,
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"model_max_length": 512,
|
5 |
+
"pad_token": "<pad>",
|
6 |
+
"separate_vocabs": false,
|
7 |
+
"source_lang": "en",
|
8 |
+
"sp_model_kwargs": {},
|
9 |
+
"target_lang": "fr",
|
10 |
+
"tokenizer_class": "MarianTokenizer",
|
11 |
+
"unk_token": "<unk>"
|
12 |
+
}
|
checkpoint-60000/trainer_state.json
ADDED
@@ -0,0 +1,256 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 42.5736,
|
3 |
+
"best_model_checkpoint": "opus_base_simple_tfidf_wce/checkpoint-60000",
|
4 |
+
"epoch": 2.9574132492113563,
|
5 |
+
"global_step": 60000,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.2,
|
12 |
+
"learning_rate": 1.9753918572555207e-05,
|
13 |
+
"loss": 0.2098,
|
14 |
+
"step": 4000
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.2,
|
18 |
+
"eval_bleu": 35.7996,
|
19 |
+
"eval_gen_len": 39.4171,
|
20 |
+
"eval_loss": 0.10897957533597946,
|
21 |
+
"eval_runtime": 150.8888,
|
22 |
+
"eval_samples_per_second": 6.912,
|
23 |
+
"eval_steps_per_second": 0.219,
|
24 |
+
"step": 4000
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.39,
|
28 |
+
"learning_rate": 1.950746746845426e-05,
|
29 |
+
"loss": 0.1762,
|
30 |
+
"step": 8000
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.39,
|
34 |
+
"eval_bleu": 36.8077,
|
35 |
+
"eval_gen_len": 39.0182,
|
36 |
+
"eval_loss": 0.10654434561729431,
|
37 |
+
"eval_runtime": 116.4461,
|
38 |
+
"eval_samples_per_second": 8.957,
|
39 |
+
"eval_steps_per_second": 0.283,
|
40 |
+
"step": 8000
|
41 |
+
},
|
42 |
+
{
|
43 |
+
"epoch": 0.59,
|
44 |
+
"learning_rate": 1.9261016364353314e-05,
|
45 |
+
"loss": 0.1691,
|
46 |
+
"step": 12000
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"epoch": 0.59,
|
50 |
+
"eval_bleu": 41.2732,
|
51 |
+
"eval_gen_len": 34.2013,
|
52 |
+
"eval_loss": 0.10531464219093323,
|
53 |
+
"eval_runtime": 133.3831,
|
54 |
+
"eval_samples_per_second": 7.82,
|
55 |
+
"eval_steps_per_second": 0.247,
|
56 |
+
"step": 12000
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.79,
|
60 |
+
"learning_rate": 1.9014565260252367e-05,
|
61 |
+
"loss": 0.1635,
|
62 |
+
"step": 16000
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.79,
|
66 |
+
"eval_bleu": 41.6402,
|
67 |
+
"eval_gen_len": 34.6366,
|
68 |
+
"eval_loss": 0.10416054725646973,
|
69 |
+
"eval_runtime": 104.9246,
|
70 |
+
"eval_samples_per_second": 9.94,
|
71 |
+
"eval_steps_per_second": 0.315,
|
72 |
+
"step": 16000
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.99,
|
76 |
+
"learning_rate": 1.876811415615142e-05,
|
77 |
+
"loss": 0.1611,
|
78 |
+
"step": 20000
|
79 |
+
},
|
80 |
+
{
|
81 |
+
"epoch": 0.99,
|
82 |
+
"eval_bleu": 41.7834,
|
83 |
+
"eval_gen_len": 35.3193,
|
84 |
+
"eval_loss": 0.10361454635858536,
|
85 |
+
"eval_runtime": 153.2125,
|
86 |
+
"eval_samples_per_second": 6.808,
|
87 |
+
"eval_steps_per_second": 0.215,
|
88 |
+
"step": 20000
|
89 |
+
},
|
90 |
+
{
|
91 |
+
"epoch": 1.18,
|
92 |
+
"learning_rate": 1.8521786277602524e-05,
|
93 |
+
"loss": 0.1493,
|
94 |
+
"step": 24000
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 1.18,
|
98 |
+
"eval_bleu": 41.5067,
|
99 |
+
"eval_gen_len": 35.8773,
|
100 |
+
"eval_loss": 0.10355237871408463,
|
101 |
+
"eval_runtime": 92.4584,
|
102 |
+
"eval_samples_per_second": 11.281,
|
103 |
+
"eval_steps_per_second": 0.357,
|
104 |
+
"step": 24000
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 1.38,
|
108 |
+
"learning_rate": 1.827545839905363e-05,
|
109 |
+
"loss": 0.1491,
|
110 |
+
"step": 28000
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 1.38,
|
114 |
+
"eval_bleu": 41.1362,
|
115 |
+
"eval_gen_len": 36.0518,
|
116 |
+
"eval_loss": 0.10270049422979355,
|
117 |
+
"eval_runtime": 90.7046,
|
118 |
+
"eval_samples_per_second": 11.499,
|
119 |
+
"eval_steps_per_second": 0.364,
|
120 |
+
"step": 28000
|
121 |
+
},
|
122 |
+
{
|
123 |
+
"epoch": 1.58,
|
124 |
+
"learning_rate": 1.8029130520504733e-05,
|
125 |
+
"loss": 0.1486,
|
126 |
+
"step": 32000
|
127 |
+
},
|
128 |
+
{
|
129 |
+
"epoch": 1.58,
|
130 |
+
"eval_bleu": 42.0407,
|
131 |
+
"eval_gen_len": 34.8581,
|
132 |
+
"eval_loss": 0.10218680649995804,
|
133 |
+
"eval_runtime": 93.8654,
|
134 |
+
"eval_samples_per_second": 11.112,
|
135 |
+
"eval_steps_per_second": 0.352,
|
136 |
+
"step": 32000
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 1.77,
|
140 |
+
"learning_rate": 1.778286425473186e-05,
|
141 |
+
"loss": 0.1472,
|
142 |
+
"step": 36000
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 1.77,
|
146 |
+
"eval_bleu": 40.0238,
|
147 |
+
"eval_gen_len": 37.8265,
|
148 |
+
"eval_loss": 0.10189016908407211,
|
149 |
+
"eval_runtime": 108.5416,
|
150 |
+
"eval_samples_per_second": 9.609,
|
151 |
+
"eval_steps_per_second": 0.304,
|
152 |
+
"step": 36000
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 1.97,
|
156 |
+
"learning_rate": 1.7536474763406942e-05,
|
157 |
+
"loss": 0.1463,
|
158 |
+
"step": 40000
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 1.97,
|
162 |
+
"eval_bleu": 42.5557,
|
163 |
+
"eval_gen_len": 34.1285,
|
164 |
+
"eval_loss": 0.10188464820384979,
|
165 |
+
"eval_runtime": 71.1911,
|
166 |
+
"eval_samples_per_second": 14.651,
|
167 |
+
"eval_steps_per_second": 0.464,
|
168 |
+
"step": 40000
|
169 |
+
},
|
170 |
+
{
|
171 |
+
"epoch": 2.17,
|
172 |
+
"learning_rate": 1.7290146884858045e-05,
|
173 |
+
"loss": 0.1388,
|
174 |
+
"step": 44000
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 2.17,
|
178 |
+
"eval_bleu": 42.1819,
|
179 |
+
"eval_gen_len": 35.1783,
|
180 |
+
"eval_loss": 0.10227210074663162,
|
181 |
+
"eval_runtime": 93.0555,
|
182 |
+
"eval_samples_per_second": 11.208,
|
183 |
+
"eval_steps_per_second": 0.355,
|
184 |
+
"step": 44000
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 2.37,
|
188 |
+
"learning_rate": 1.704381900630915e-05,
|
189 |
+
"loss": 0.1378,
|
190 |
+
"step": 48000
|
191 |
+
},
|
192 |
+
{
|
193 |
+
"epoch": 2.37,
|
194 |
+
"eval_bleu": 42.5524,
|
195 |
+
"eval_gen_len": 35.2148,
|
196 |
+
"eval_loss": 0.10202094167470932,
|
197 |
+
"eval_runtime": 104.8789,
|
198 |
+
"eval_samples_per_second": 9.945,
|
199 |
+
"eval_steps_per_second": 0.315,
|
200 |
+
"step": 48000
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 2.56,
|
204 |
+
"learning_rate": 1.679755274053628e-05,
|
205 |
+
"loss": 0.1367,
|
206 |
+
"step": 52000
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 2.56,
|
210 |
+
"eval_bleu": 42.2979,
|
211 |
+
"eval_gen_len": 34.6817,
|
212 |
+
"eval_loss": 0.10162690281867981,
|
213 |
+
"eval_runtime": 90.8884,
|
214 |
+
"eval_samples_per_second": 11.476,
|
215 |
+
"eval_steps_per_second": 0.363,
|
216 |
+
"step": 52000
|
217 |
+
},
|
218 |
+
{
|
219 |
+
"epoch": 2.76,
|
220 |
+
"learning_rate": 1.6551163249211358e-05,
|
221 |
+
"loss": 0.137,
|
222 |
+
"step": 56000
|
223 |
+
},
|
224 |
+
{
|
225 |
+
"epoch": 2.76,
|
226 |
+
"eval_bleu": 42.4162,
|
227 |
+
"eval_gen_len": 35.652,
|
228 |
+
"eval_loss": 0.10157214105129242,
|
229 |
+
"eval_runtime": 132.7314,
|
230 |
+
"eval_samples_per_second": 7.858,
|
231 |
+
"eval_steps_per_second": 0.249,
|
232 |
+
"step": 56000
|
233 |
+
},
|
234 |
+
{
|
235 |
+
"epoch": 2.96,
|
236 |
+
"learning_rate": 1.6304773757886436e-05,
|
237 |
+
"loss": 0.1373,
|
238 |
+
"step": 60000
|
239 |
+
},
|
240 |
+
{
|
241 |
+
"epoch": 2.96,
|
242 |
+
"eval_bleu": 42.5736,
|
243 |
+
"eval_gen_len": 34.418,
|
244 |
+
"eval_loss": 0.10088738054037094,
|
245 |
+
"eval_runtime": 113.8031,
|
246 |
+
"eval_samples_per_second": 9.165,
|
247 |
+
"eval_steps_per_second": 0.29,
|
248 |
+
"step": 60000
|
249 |
+
}
|
250 |
+
],
|
251 |
+
"max_steps": 324608,
|
252 |
+
"num_train_epochs": 16,
|
253 |
+
"total_flos": 1.0348852591617638e+17,
|
254 |
+
"trial_name": null,
|
255 |
+
"trial_params": null
|
256 |
+
}
|
checkpoint-60000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a905ba110b0d9116123e168c70df7fb6514427860ac3c19aa00cc6bd4069f0c4
|
3 |
+
size 3771
|
checkpoint-60000/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
config.json
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Helsinki-NLP/opus-mt-en-fr",
|
3 |
+
"_num_labels": 3,
|
4 |
+
"activation_dropout": 0.0,
|
5 |
+
"activation_function": "swish",
|
6 |
+
"add_bias_logits": false,
|
7 |
+
"add_final_layer_norm": false,
|
8 |
+
"architectures": [
|
9 |
+
"MarianMTModel"
|
10 |
+
],
|
11 |
+
"attention_dropout": 0.0,
|
12 |
+
"bad_words_ids": [
|
13 |
+
[
|
14 |
+
59513
|
15 |
+
]
|
16 |
+
],
|
17 |
+
"bos_token_id": 0,
|
18 |
+
"classif_dropout": 0.0,
|
19 |
+
"classifier_dropout": 0.0,
|
20 |
+
"d_model": 512,
|
21 |
+
"decoder_attention_heads": 8,
|
22 |
+
"decoder_ffn_dim": 2048,
|
23 |
+
"decoder_layerdrop": 0.0,
|
24 |
+
"decoder_layers": 6,
|
25 |
+
"decoder_start_token_id": 59513,
|
26 |
+
"decoder_vocab_size": 59514,
|
27 |
+
"dropout": 0.1,
|
28 |
+
"encoder_attention_heads": 8,
|
29 |
+
"encoder_ffn_dim": 2048,
|
30 |
+
"encoder_layerdrop": 0.0,
|
31 |
+
"encoder_layers": 6,
|
32 |
+
"eos_token_id": 0,
|
33 |
+
"forced_eos_token_id": 0,
|
34 |
+
"gradient_checkpointing": false,
|
35 |
+
"id2label": {
|
36 |
+
"0": "LABEL_0",
|
37 |
+
"1": "LABEL_1",
|
38 |
+
"2": "LABEL_2"
|
39 |
+
},
|
40 |
+
"init_std": 0.02,
|
41 |
+
"is_encoder_decoder": true,
|
42 |
+
"label2id": {
|
43 |
+
"LABEL_0": 0,
|
44 |
+
"LABEL_1": 1,
|
45 |
+
"LABEL_2": 2
|
46 |
+
},
|
47 |
+
"max_length": 512,
|
48 |
+
"max_position_embeddings": 512,
|
49 |
+
"model_type": "marian",
|
50 |
+
"normalize_before": false,
|
51 |
+
"normalize_embedding": false,
|
52 |
+
"num_beams": 4,
|
53 |
+
"num_hidden_layers": 6,
|
54 |
+
"pad_token_id": 59513,
|
55 |
+
"scale_embedding": true,
|
56 |
+
"share_encoder_decoder_embeddings": true,
|
57 |
+
"static_position_embeddings": true,
|
58 |
+
"torch_dtype": "float32",
|
59 |
+
"transformers_version": "4.28.0",
|
60 |
+
"use_cache": true,
|
61 |
+
"vocab_size": 59514
|
62 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bad_words_ids": [
|
3 |
+
[
|
4 |
+
59513
|
5 |
+
]
|
6 |
+
],
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"decoder_start_token_id": 59513,
|
9 |
+
"eos_token_id": 0,
|
10 |
+
"forced_eos_token_id": 0,
|
11 |
+
"max_length": 512,
|
12 |
+
"num_beams": 4,
|
13 |
+
"pad_token_id": 59513,
|
14 |
+
"renormalize_logits": true,
|
15 |
+
"transformers_version": "4.28.0"
|
16 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8fc98e1224f3c436077f903fb1738893ae0cc176dff85bbd440b582504cf6967
|
3 |
+
size 298763205
|
source.spm
ADDED
Binary file (778 kB). View file
|
|
special_tokens_map.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eos_token": "</s>",
|
3 |
+
"pad_token": "<pad>",
|
4 |
+
"unk_token": "<unk>"
|
5 |
+
}
|
target.spm
ADDED
Binary file (802 kB). View file
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"clean_up_tokenization_spaces": true,
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"model_max_length": 512,
|
5 |
+
"pad_token": "<pad>",
|
6 |
+
"separate_vocabs": false,
|
7 |
+
"source_lang": "en",
|
8 |
+
"sp_model_kwargs": {},
|
9 |
+
"target_lang": "fr",
|
10 |
+
"tokenizer_class": "MarianTokenizer",
|
11 |
+
"unk_token": "<unk>"
|
12 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a905ba110b0d9116123e168c70df7fb6514427860ac3c19aa00cc6bd4069f0c4
|
3 |
+
size 3771
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|