Mix Trained marian model over 9 languages of ALT dataset + 18K senetences from en-zh opus dataset.
Browse files- last-checkpoint/added_tokens.json +0 -0
- last-checkpoint/config.json +0 -62
- last-checkpoint/optimizer.pt +0 -3
- last-checkpoint/pytorch_model.bin +0 -3
- last-checkpoint/rng_state.pth +0 -3
- last-checkpoint/scaler.pt +0 -3
- last-checkpoint/scheduler.pt +0 -3
- last-checkpoint/source.spm +0 -0
- last-checkpoint/special_tokens_map.json +0 -1
- last-checkpoint/target.spm +0 -0
- last-checkpoint/tokenizer_config.json +0 -1
- last-checkpoint/trainer_state.json +0 -136
- last-checkpoint/training_args.bin +0 -3
- last-checkpoint/vocab.json +0 -0
- pytorch_model.bin +1 -1
- runs/Jan13_15-44-20_ba04f2c84f0c/events.out.tfevents.1642088673.ba04f2c84f0c.73.0 +2 -2
last-checkpoint/added_tokens.json
DELETED
The diff for this file is too large to render.
See raw diff
|
|
last-checkpoint/config.json
DELETED
@@ -1,62 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"_name_or_path": "Helsinki-NLP/opus-mt-en-zh",
|
3 |
-
"activation_dropout": 0.0,
|
4 |
-
"activation_function": "swish",
|
5 |
-
"add_bias_logits": false,
|
6 |
-
"add_final_layer_norm": false,
|
7 |
-
"architectures": [
|
8 |
-
"MarianMTModel"
|
9 |
-
],
|
10 |
-
"attention_dropout": 0.0,
|
11 |
-
"bad_words_ids": [
|
12 |
-
[
|
13 |
-
65000
|
14 |
-
]
|
15 |
-
],
|
16 |
-
"bos_token_id": 0,
|
17 |
-
"classif_dropout": 0.0,
|
18 |
-
"classifier_dropout": 0.0,
|
19 |
-
"d_model": 512,
|
20 |
-
"decoder_attention_heads": 8,
|
21 |
-
"decoder_ffn_dim": 2048,
|
22 |
-
"decoder_layerdrop": 0.0,
|
23 |
-
"decoder_layers": 6,
|
24 |
-
"decoder_start_token_id": 65000,
|
25 |
-
"do_blenderbot_90_layernorm": false,
|
26 |
-
"dropout": 0.1,
|
27 |
-
"encoder_attention_heads": 8,
|
28 |
-
"encoder_ffn_dim": 2048,
|
29 |
-
"encoder_layerdrop": 0.0,
|
30 |
-
"encoder_layers": 6,
|
31 |
-
"eos_token_id": 0,
|
32 |
-
"extra_pos_embeddings": 0,
|
33 |
-
"force_bos_token_to_be_generated": false,
|
34 |
-
"forced_eos_token_id": 0,
|
35 |
-
"gradient_checkpointing": false,
|
36 |
-
"id2label": {
|
37 |
-
"0": "LABEL_0",
|
38 |
-
"1": "LABEL_1",
|
39 |
-
"2": "LABEL_2"
|
40 |
-
},
|
41 |
-
"init_std": 0.02,
|
42 |
-
"is_encoder_decoder": true,
|
43 |
-
"label2id": {
|
44 |
-
"LABEL_0": 0,
|
45 |
-
"LABEL_1": 1,
|
46 |
-
"LABEL_2": 2
|
47 |
-
},
|
48 |
-
"max_length": 512,
|
49 |
-
"max_position_embeddings": 512,
|
50 |
-
"model_type": "marian",
|
51 |
-
"normalize_before": false,
|
52 |
-
"normalize_embedding": false,
|
53 |
-
"num_beams": 4,
|
54 |
-
"num_hidden_layers": 6,
|
55 |
-
"pad_token_id": 65000,
|
56 |
-
"scale_embedding": true,
|
57 |
-
"static_position_embeddings": true,
|
58 |
-
"torch_dtype": "float32",
|
59 |
-
"transformers_version": "4.15.0",
|
60 |
-
"use_cache": true,
|
61 |
-
"vocab_size": 101452
|
62 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/optimizer.pt
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:7dd035e4b7f154ca67a5e827f94dde0c3943eda1b1eebec5f05e33e3d56ced39
|
3 |
-
size 768802253
|
|
|
|
|
|
|
|
last-checkpoint/pytorch_model.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:28f25c68a0cf29ea50176781ab7073cc5001efefecdff92973e4dbf5cb6efd80
|
3 |
-
size 384827845
|
|
|
|
|
|
|
|
last-checkpoint/rng_state.pth
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:7611315dfec0b436e47fb6dd6b2e81144c20633935e13fada627fe3665210c35
|
3 |
-
size 14503
|
|
|
|
|
|
|
|
last-checkpoint/scaler.pt
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:5368f7f534ec825f60c19bab138293e63db2d680360440af385721e34463a6e8
|
3 |
-
size 559
|
|
|
|
|
|
|
|
last-checkpoint/scheduler.pt
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:aa541328a304ec574eb6085b477bec95c4e258191041c83a037f6e027f4fea37
|
3 |
-
size 623
|
|
|
|
|
|
|
|
last-checkpoint/source.spm
DELETED
Binary file (806 kB)
|
|
last-checkpoint/special_tokens_map.json
DELETED
@@ -1 +0,0 @@
|
|
1 |
-
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
|
|
|
|
last-checkpoint/target.spm
DELETED
Binary file (805 kB)
|
|
last-checkpoint/tokenizer_config.json
DELETED
@@ -1 +0,0 @@
|
|
1 |
-
{"source_lang": "eng", "target_lang": "zho", "unk_token": "<unk>", "eos_token": "</s>", "pad_token": "<pad>", "model_max_length": 512, "sp_model_kwargs": {}, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "Helsinki-NLP/opus-mt-en-zh", "tokenizer_class": "MarianTokenizer"}
|
|
|
|
last-checkpoint/trainer_state.json
DELETED
@@ -1,136 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"best_metric": null,
|
3 |
-
"best_model_checkpoint": null,
|
4 |
-
"epoch": 1.7863522686673812,
|
5 |
-
"global_step": 10000,
|
6 |
-
"is_hyper_param_search": false,
|
7 |
-
"is_local_process_zero": true,
|
8 |
-
"is_world_process_zero": true,
|
9 |
-
"log_history": [
|
10 |
-
{
|
11 |
-
"epoch": 0.09,
|
12 |
-
"learning_rate": 9.826661901358113e-05,
|
13 |
-
"loss": 2.8742,
|
14 |
-
"step": 500
|
15 |
-
},
|
16 |
-
{
|
17 |
-
"epoch": 0.18,
|
18 |
-
"learning_rate": 9.647962830593282e-05,
|
19 |
-
"loss": 1.8355,
|
20 |
-
"step": 1000
|
21 |
-
},
|
22 |
-
{
|
23 |
-
"epoch": 0.27,
|
24 |
-
"learning_rate": 9.46926375982845e-05,
|
25 |
-
"loss": 1.6456,
|
26 |
-
"step": 1500
|
27 |
-
},
|
28 |
-
{
|
29 |
-
"epoch": 0.36,
|
30 |
-
"learning_rate": 9.290564689063618e-05,
|
31 |
-
"loss": 1.5151,
|
32 |
-
"step": 2000
|
33 |
-
},
|
34 |
-
{
|
35 |
-
"epoch": 0.45,
|
36 |
-
"learning_rate": 9.111865618298785e-05,
|
37 |
-
"loss": 1.3961,
|
38 |
-
"step": 2500
|
39 |
-
},
|
40 |
-
{
|
41 |
-
"epoch": 0.54,
|
42 |
-
"learning_rate": 8.933166547533954e-05,
|
43 |
-
"loss": 1.3182,
|
44 |
-
"step": 3000
|
45 |
-
},
|
46 |
-
{
|
47 |
-
"epoch": 0.63,
|
48 |
-
"learning_rate": 8.754467476769121e-05,
|
49 |
-
"loss": 1.2625,
|
50 |
-
"step": 3500
|
51 |
-
},
|
52 |
-
{
|
53 |
-
"epoch": 0.71,
|
54 |
-
"learning_rate": 8.575768406004289e-05,
|
55 |
-
"loss": 1.2033,
|
56 |
-
"step": 4000
|
57 |
-
},
|
58 |
-
{
|
59 |
-
"epoch": 0.8,
|
60 |
-
"learning_rate": 8.397069335239457e-05,
|
61 |
-
"loss": 1.1532,
|
62 |
-
"step": 4500
|
63 |
-
},
|
64 |
-
{
|
65 |
-
"epoch": 0.89,
|
66 |
-
"learning_rate": 8.218370264474626e-05,
|
67 |
-
"loss": 1.1099,
|
68 |
-
"step": 5000
|
69 |
-
},
|
70 |
-
{
|
71 |
-
"epoch": 0.98,
|
72 |
-
"learning_rate": 8.039671193709793e-05,
|
73 |
-
"loss": 1.0695,
|
74 |
-
"step": 5500
|
75 |
-
},
|
76 |
-
{
|
77 |
-
"epoch": 1.07,
|
78 |
-
"learning_rate": 7.860972122944961e-05,
|
79 |
-
"loss": 1.0133,
|
80 |
-
"step": 6000
|
81 |
-
},
|
82 |
-
{
|
83 |
-
"epoch": 1.16,
|
84 |
-
"learning_rate": 7.682273052180129e-05,
|
85 |
-
"loss": 0.964,
|
86 |
-
"step": 6500
|
87 |
-
},
|
88 |
-
{
|
89 |
-
"epoch": 1.25,
|
90 |
-
"learning_rate": 7.503573981415298e-05,
|
91 |
-
"loss": 0.9535,
|
92 |
-
"step": 7000
|
93 |
-
},
|
94 |
-
{
|
95 |
-
"epoch": 1.34,
|
96 |
-
"learning_rate": 7.324874910650465e-05,
|
97 |
-
"loss": 0.9368,
|
98 |
-
"step": 7500
|
99 |
-
},
|
100 |
-
{
|
101 |
-
"epoch": 1.43,
|
102 |
-
"learning_rate": 7.146175839885633e-05,
|
103 |
-
"loss": 0.91,
|
104 |
-
"step": 8000
|
105 |
-
},
|
106 |
-
{
|
107 |
-
"epoch": 1.52,
|
108 |
-
"learning_rate": 6.9674767691208e-05,
|
109 |
-
"loss": 0.8902,
|
110 |
-
"step": 8500
|
111 |
-
},
|
112 |
-
{
|
113 |
-
"epoch": 1.61,
|
114 |
-
"learning_rate": 6.78877769835597e-05,
|
115 |
-
"loss": 0.8761,
|
116 |
-
"step": 9000
|
117 |
-
},
|
118 |
-
{
|
119 |
-
"epoch": 1.7,
|
120 |
-
"learning_rate": 6.610078627591136e-05,
|
121 |
-
"loss": 0.8699,
|
122 |
-
"step": 9500
|
123 |
-
},
|
124 |
-
{
|
125 |
-
"epoch": 1.79,
|
126 |
-
"learning_rate": 6.431379556826305e-05,
|
127 |
-
"loss": 0.8455,
|
128 |
-
"step": 10000
|
129 |
-
}
|
130 |
-
],
|
131 |
-
"max_steps": 27990,
|
132 |
-
"num_train_epochs": 5,
|
133 |
-
"total_flos": 1.08466293178368e+16,
|
134 |
-
"trial_name": null,
|
135 |
-
"trial_params": null
|
136 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/training_args.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:782a61f9b4b81744b4a6cea3c7764006510c094d62fb54b163ccda9c79bc115f
|
3 |
-
size 3119
|
|
|
|
|
|
|
|
last-checkpoint/vocab.json
DELETED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 384827845
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:416b4cf7935412622b6d7807238c1e1ad1095c667e1f009a54f178f46a2322f5
|
3 |
size 384827845
|
runs/Jan13_15-44-20_ba04f2c84f0c/events.out.tfevents.1642088673.ba04f2c84f0c.73.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:55645d79e2f12a144ecf5b939a3e695a01760b33d311fa4ad60e2e2d8fddc85d
|
3 |
+
size 13646
|