Hugging Face's logo

eamar
/
mt5-small-finetuned-amazon-ja

Transformers
PyTorch
mt5
text2text-generation
Model card Files
xet
 Community
1
eamar commited on
Commit
6b413dc
·
1 Parent(s): f2e0aca

Initial commit

Browse files
Files changed (12) hide show
  1. .gitattributes +1 -0
  2. config.json +31 -0
  3. optimizer.pt +3 -0
  4. pytorch_model.bin +3 -0
  5. rng_state.pth +3 -0
  6. scheduler.pt +3 -0
  7. special_tokens_map.json +5 -0
  8. spiece.model +3 -0
  9. tokenizer.json +3 -0
  10. tokenizer_config.json +11 -0
  11. trainer_state.json +142 -0
  12. training_args.bin +3 -0
.gitattributes CHANGED
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
35
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/mt5-small",
3
+ "architectures": [
4
+ "MT5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 1024,
7
+ "d_kv": 64,
8
+ "d_model": 512,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "gelu_new",
11
+ "dropout_rate": 0.1,
12
+ "eos_token_id": 1,
13
+ "feed_forward_proj": "gated-gelu",
14
+ "initializer_factor": 1.0,
15
+ "is_encoder_decoder": true,
16
+ "is_gated_act": true,
17
+ "layer_norm_epsilon": 1e-06,
18
+ "model_type": "mt5",
19
+ "num_decoder_layers": 8,
20
+ "num_heads": 6,
21
+ "num_layers": 8,
22
+ "pad_token_id": 0,
23
+ "relative_attention_max_distance": 128,
24
+ "relative_attention_num_buckets": 32,
25
+ "tie_word_embeddings": false,
26
+ "tokenizer_class": "T5Tokenizer",
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.21.3",
29
+ "use_cache": true,
30
+ "vocab_size": 250112
31
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b636e5464c320be15ef1e29d03e3f7a4216cd11ebb8b550b0d80f0592b4aae0
3
+ size 2401521477
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccd98611fe94534d06be3f866c1654779d190bcda006d8742e1233f6c30ee85c
3
+ size 1200769797
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdc87252ec02f63a193b8977bec971f56659c7425f67ac0f985de709eb646ac5
3
+ size 13553
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1dfe10daf7e2e40c4fae87c2289c1318782a287d6bf167ab9580c6a95c482f9d
3
+ size 627
special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "eos_token": "</s>",
3
+ "pad_token": "<pad>",
4
+ "unk_token": "<unk>"
5
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
3
+ size 4309802
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93c3578052e1605d8332eb961bc08d72e246071974e4cc54aa6991826b802aa5
3
+ size 16330369
tokenizer_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": null,
3
+ "eos_token": "</s>",
4
+ "extra_ids": 0,
5
+ "name_or_path": "google/mt5-small",
6
+ "pad_token": "<pad>",
7
+ "sp_model_kwargs": {},
8
+ "special_tokens_map_file": "/Users/e.amar/.cache/huggingface/transformers/685ac0ca8568ec593a48b61b0a3c272beee9bc194a3c7241d15dcadb5f875e53.f76030f3ec1b96a8199b2593390c610e76ca8028ef3d24680000619ffb646276",
9
+ "tokenizer_class": "T5Tokenizer",
10
+ "unk_token": "<unk>"
11
+ }
trainer_state.json ADDED
@@ -0,0 +1,142 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 7.936507936507937,
5
+ "global_step": 7500,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "learning_rate": 4.9007407407407405e-05,
13
+ "loss": 6.9695,
14
+ "step": 944
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_loss": 4.147339344024658,
19
+ "eval_rouge1": 0.0,
20
+ "eval_rouge2": 0.0,
21
+ "eval_rougeL": 0.0,
22
+ "eval_rougeLsum": 0.0,
23
+ "eval_runtime": 20.6593,
24
+ "eval_samples_per_second": 7.745,
25
+ "eval_steps_per_second": 0.968,
26
+ "step": 945
27
+ },
28
+ {
29
+ "epoch": 2.0,
30
+ "learning_rate": 4.201481481481482e-05,
31
+ "loss": 4.5567,
32
+ "step": 1888
33
+ },
34
+ {
35
+ "epoch": 2.0,
36
+ "eval_loss": 3.9342198371887207,
37
+ "eval_rouge1": 0.625,
38
+ "eval_rouge2": 0.0,
39
+ "eval_rougeL": 0.625,
40
+ "eval_rougeLsum": 0.625,
41
+ "eval_runtime": 20.7037,
42
+ "eval_samples_per_second": 7.728,
43
+ "eval_steps_per_second": 0.966,
44
+ "step": 1890
45
+ },
46
+ {
47
+ "epoch": 3.0,
48
+ "learning_rate": 3.502222222222222e-05,
49
+ "loss": 4.2704,
50
+ "step": 2832
51
+ },
52
+ {
53
+ "epoch": 3.0,
54
+ "eval_loss": 3.8318352699279785,
55
+ "eval_rouge1": 0.0,
56
+ "eval_rouge2": 0.0,
57
+ "eval_rougeL": 0.0,
58
+ "eval_rougeLsum": 0.0,
59
+ "eval_runtime": 18.8952,
60
+ "eval_samples_per_second": 8.468,
61
+ "eval_steps_per_second": 1.058,
62
+ "step": 2835
63
+ },
64
+ {
65
+ "epoch": 4.0,
66
+ "learning_rate": 2.8029629629629628e-05,
67
+ "loss": 4.1165,
68
+ "step": 3776
69
+ },
70
+ {
71
+ "epoch": 4.0,
72
+ "eval_loss": 3.836942195892334,
73
+ "eval_rouge1": 0.0,
74
+ "eval_rouge2": 0.0,
75
+ "eval_rougeL": 0.0,
76
+ "eval_rougeLsum": 0.0,
77
+ "eval_runtime": 19.8612,
78
+ "eval_samples_per_second": 8.056,
79
+ "eval_steps_per_second": 1.007,
80
+ "step": 3780
81
+ },
82
+ {
83
+ "epoch": 4.99,
84
+ "learning_rate": 2.1037037037037034e-05,
85
+ "loss": 4.015,
86
+ "step": 4720
87
+ },
88
+ {
89
+ "epoch": 5.0,
90
+ "eval_loss": 3.792680025100708,
91
+ "eval_rouge1": 0.0,
92
+ "eval_rouge2": 0.0,
93
+ "eval_rougeL": 0.0,
94
+ "eval_rougeLsum": 0.0,
95
+ "eval_runtime": 20.3459,
96
+ "eval_samples_per_second": 7.864,
97
+ "eval_steps_per_second": 0.983,
98
+ "step": 4725
99
+ },
100
+ {
101
+ "epoch": 5.99,
102
+ "learning_rate": 1.4044444444444445e-05,
103
+ "loss": 3.9414,
104
+ "step": 5664
105
+ },
106
+ {
107
+ "epoch": 6.0,
108
+ "eval_loss": 3.7542567253112793,
109
+ "eval_rouge1": 0.0,
110
+ "eval_rouge2": 0.0,
111
+ "eval_rougeL": 0.0,
112
+ "eval_rougeLsum": 0.0,
113
+ "eval_runtime": 19.4583,
114
+ "eval_samples_per_second": 8.223,
115
+ "eval_steps_per_second": 1.028,
116
+ "step": 5670
117
+ },
118
+ {
119
+ "epoch": 6.99,
120
+ "learning_rate": 7.051851851851851e-06,
121
+ "loss": 3.893,
122
+ "step": 6608
123
+ },
124
+ {
125
+ "epoch": 7.0,
126
+ "eval_loss": 3.7550926208496094,
127
+ "eval_rouge1": 0.0,
128
+ "eval_rouge2": 0.0,
129
+ "eval_rougeL": 0.0,
130
+ "eval_rougeLsum": 0.0,
131
+ "eval_runtime": 19.588,
132
+ "eval_samples_per_second": 8.168,
133
+ "eval_steps_per_second": 1.021,
134
+ "step": 6615
135
+ }
136
+ ],
137
+ "max_steps": 7560,
138
+ "num_train_epochs": 8,
139
+ "total_flos": 1.032980990088192e+16,
140
+ "trial_name": null,
141
+ "trial_params": null
142
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09457756900e5cdfae9447b75ead0bb28b48246afa83d54f52b92dd66eeb0a4a
3
+ size 3451