Hugging Face's logo

Samuael
/
amhmt5-base-finetuned-amt5

Text2Text Generation
Transformers
TensorBoard
Safetensors
mt5
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Samuael commited on
Commit
87e4ae1
·
verified ·
1 Parent(s): bb04c09

Training in progress, step 500

Browse files
Files changed (17) hide show
  1. model.safetensors +1 -1
  2. runs/Feb24_13-50-38_6932ad46bf92/events.out.tfevents.1708782698.6932ad46bf92.1403.3 +2 -2
  3. runs/Feb24_14-24-42_6932ad46bf92/events.out.tfevents.1708784709.6932ad46bf92.1403.4 +3 -0
  4. runs/Feb24_14-32-59_6932ad46bf92/events.out.tfevents.1708785198.6932ad46bf92.1403.5 +3 -0
  5. tmp-checkpoint-6000/config.json +33 -0
  6. tmp-checkpoint-6000/generation_config.json +6 -0
  7. tmp-checkpoint-6000/model.safetensors +3 -0
  8. tmp-checkpoint-6000/optimizer.pt +3 -0
  9. tmp-checkpoint-6000/rng_state.pth +3 -0
  10. tmp-checkpoint-6000/scheduler.pt +3 -0
  11. tmp-checkpoint-6000/special_tokens_map.json +23 -0
  12. tmp-checkpoint-6000/spiece.model +3 -0
  13. tmp-checkpoint-6000/tokenizer.json +0 -0
  14. tmp-checkpoint-6000/tokenizer_config.json +38 -0
  15. tmp-checkpoint-6000/trainer_state.json +153 -0
  16. tmp-checkpoint-6000/training_args.bin +3 -0
  17. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1709857e89fd698403c31888dbd0938675c0924fe7fcd2851aba6c79de99025b
3
  size 805078888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30b3ba0e51e81f59241e69744461ecf361f3977f2b370fa572c7ecd30ee458b3
3
  size 805078888
runs/Feb24_13-50-38_6932ad46bf92/events.out.tfevents.1708782698.6932ad46bf92.1403.3 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b85c7c668cd0c398cc5d721c1233c50c79801e8496822b735d51ed52b98277e
3
- size 8302
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba951038914f0bae356ce9c2c6226a722ff5c1a6c3223f8eb7bcf39c73eb9bd1
3
+ size 9078
runs/Feb24_14-24-42_6932ad46bf92/events.out.tfevents.1708784709.6932ad46bf92.1403.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66ce66b2821203f210f02f36749b15d4fc5873d1fb7b01c9c9eb48c8323ec3b4
3
+ size 23390
runs/Feb24_14-32-59_6932ad46bf92/events.out.tfevents.1708785198.6932ad46bf92.1403.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7dabf2df5f176673b03b4cb2811fac7a7d0dd75f170f97514a002f7cd46449bb
3
+ size 4875
tmp-checkpoint-6000/config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Samuael/amt5-base",
3
+ "architectures": [
4
+ "MT5ForConditionalGeneration"
5
+ ],
6
+ "classifier_dropout": 0.0,
7
+ "d_ff": 2048,
8
+ "d_kv": 64,
9
+ "d_model": 768,
10
+ "decoder_start_token_id": 0,
11
+ "dense_act_fn": "gelu_new",
12
+ "dropout_rate": 0.1,
13
+ "eos_token_id": 1,
14
+ "feed_forward_proj": "gated-gelu",
15
+ "initializer_factor": 1.0,
16
+ "is_encoder_decoder": true,
17
+ "is_gated_act": true,
18
+ "layer_norm_epsilon": 1e-06,
19
+ "model_type": "mt5",
20
+ "num_decoder_layers": 12,
21
+ "num_heads": 12,
22
+ "num_layers": 12,
23
+ "output_past": true,
24
+ "pad_token_id": 0,
25
+ "relative_attention_max_distance": 128,
26
+ "relative_attention_num_buckets": 32,
27
+ "tie_word_embeddings": false,
28
+ "tokenizer_class": "T5Tokenizer",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.37.2",
31
+ "use_cache": true,
32
+ "vocab_size": 1974
33
+ }
tmp-checkpoint-6000/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "decoder_start_token_id": 0,
3
+ "eos_token_id": 1,
4
+ "pad_token_id": 0,
5
+ "transformers_version": "4.37.2"
6
+ }
tmp-checkpoint-6000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:664c871ff449461ccece21a4b598401fff822c04386a1b111448907c67fc0d10
3
+ size 805078888
tmp-checkpoint-6000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41db2b4fb8eb61863f83046a36eb54c238aea2d8d9dc12f9424d20a04ed429ce
3
+ size 1610328058
tmp-checkpoint-6000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8986cab551eaf3c20458bc999e0c66ce731826fd453fdd75ba98d2beafd34312
3
+ size 14244
tmp-checkpoint-6000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8f1e0a01c3ec955fd91c34b57bb8bc93c43879c16552a33dcf8c46898c406a5
3
+ size 1064
tmp-checkpoint-6000/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token": {
3
+ "content": "</s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "pad_token": {
10
+ "content": "<pad>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tmp-checkpoint-6000/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4569f9a1b0905de28f7172fa2d0dd1ad95bf39dc41f2b28fe273ab834fd9dd11
3
+ size 275619
tmp-checkpoint-6000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tmp-checkpoint-6000/tokenizer_config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<pad>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "</s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<unk>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "additional_special_tokens": [],
29
+ "clean_up_tokenization_spaces": true,
30
+ "eos_token": "</s>",
31
+ "extra_ids": 0,
32
+ "legacy": true,
33
+ "model_max_length": 1000000000000000019884624838656,
34
+ "pad_token": "<pad>",
35
+ "sp_model_kwargs": {},
36
+ "tokenizer_class": "T5Tokenizer",
37
+ "unk_token": "<unk>"
38
+ }
tmp-checkpoint-6000/trainer_state.json ADDED
@@ -0,0 +1,153 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.231311706629055,
5
+ "eval_steps": 500,
6
+ "global_step": 6000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.35,
13
+ "learning_rate": 0.00019764927127409498,
14
+ "loss": 0.0562,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.71,
19
+ "learning_rate": 0.00019529854254818997,
20
+ "loss": 0.0547,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 1.0,
25
+ "eval_cer": 0.5411753427284057,
26
+ "eval_gen_len": 18.5961,
27
+ "eval_loss": 0.712102472782135,
28
+ "eval_rouge1": 0.0,
29
+ "eval_rouge2": 0.0,
30
+ "eval_rougeL": 0.0,
31
+ "eval_rougeLsum": 0.0,
32
+ "eval_runtime": 4.0762,
33
+ "eval_samples_per_second": 88.073,
34
+ "eval_steps_per_second": 1.472,
35
+ "eval_wer": 0.6228557622614158,
36
+ "step": 1418
37
+ },
38
+ {
39
+ "epoch": 1.06,
40
+ "learning_rate": 0.00019294781382228493,
41
+ "loss": 0.0501,
42
+ "step": 1500
43
+ },
44
+ {
45
+ "epoch": 1.41,
46
+ "learning_rate": 0.00019059708509637987,
47
+ "loss": 0.0414,
48
+ "step": 2000
49
+ },
50
+ {
51
+ "epoch": 1.76,
52
+ "learning_rate": 0.00018824635637047486,
53
+ "loss": 0.0404,
54
+ "step": 2500
55
+ },
56
+ {
57
+ "epoch": 2.0,
58
+ "eval_cer": 0.5413191448566772,
59
+ "eval_gen_len": 18.5961,
60
+ "eval_loss": 0.7446629405021667,
61
+ "eval_rouge1": 0.0,
62
+ "eval_rouge2": 0.0,
63
+ "eval_rougeL": 0.0,
64
+ "eval_rougeLsum": 0.0,
65
+ "eval_runtime": 4.0502,
66
+ "eval_samples_per_second": 88.638,
67
+ "eval_steps_per_second": 1.481,
68
+ "eval_wer": 0.6221309495047113,
69
+ "step": 2836
70
+ },
71
+ {
72
+ "epoch": 2.12,
73
+ "learning_rate": 0.00018589562764456983,
74
+ "loss": 0.0381,
75
+ "step": 3000
76
+ },
77
+ {
78
+ "epoch": 2.47,
79
+ "learning_rate": 0.0001835448989186648,
80
+ "loss": 0.0324,
81
+ "step": 3500
82
+ },
83
+ {
84
+ "epoch": 2.82,
85
+ "learning_rate": 0.00018119417019275976,
86
+ "loss": 0.0313,
87
+ "step": 4000
88
+ },
89
+ {
90
+ "epoch": 3.0,
91
+ "eval_cer": 0.5414629469849487,
92
+ "eval_gen_len": 18.5933,
93
+ "eval_loss": 0.81730717420578,
94
+ "eval_rouge1": 0.0,
95
+ "eval_rouge2": 0.0,
96
+ "eval_rougeL": 0.0,
97
+ "eval_rougeLsum": 0.0,
98
+ "eval_runtime": 4.0016,
99
+ "eval_samples_per_second": 89.714,
100
+ "eval_steps_per_second": 1.499,
101
+ "eval_wer": 0.6218893452524764,
102
+ "step": 4254
103
+ },
104
+ {
105
+ "epoch": 3.17,
106
+ "learning_rate": 0.00017884344146685475,
107
+ "loss": 0.0382,
108
+ "step": 4500
109
+ },
110
+ {
111
+ "epoch": 3.53,
112
+ "learning_rate": 0.0001764927127409497,
113
+ "loss": 0.0504,
114
+ "step": 5000
115
+ },
116
+ {
117
+ "epoch": 3.88,
118
+ "learning_rate": 0.00017414198401504466,
119
+ "loss": 0.0501,
120
+ "step": 5500
121
+ },
122
+ {
123
+ "epoch": 4.0,
124
+ "eval_cer": 0.5411753427284057,
125
+ "eval_gen_len": 18.5961,
126
+ "eval_loss": 0.6638574004173279,
127
+ "eval_rouge1": 0.0,
128
+ "eval_rouge2": 0.0,
129
+ "eval_rougeL": 0.0,
130
+ "eval_rougeLsum": 0.0,
131
+ "eval_runtime": 4.0421,
132
+ "eval_samples_per_second": 88.815,
133
+ "eval_steps_per_second": 1.484,
134
+ "eval_wer": 0.6216477410002416,
135
+ "step": 5672
136
+ },
137
+ {
138
+ "epoch": 4.23,
139
+ "learning_rate": 0.00017179125528913965,
140
+ "loss": 0.0434,
141
+ "step": 6000
142
+ }
143
+ ],
144
+ "logging_steps": 500,
145
+ "max_steps": 42540,
146
+ "num_input_tokens_seen": 0,
147
+ "num_train_epochs": 30,
148
+ "save_steps": 500,
149
+ "total_flos": 6.348767856482304e+16,
150
+ "train_batch_size": 64,
151
+ "trial_name": null,
152
+ "trial_params": null
153
+ }
tmp-checkpoint-6000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb8451d4f705f97819275987e1b9e0af869f4373ac82cd1f996cd005be4c7f40
3
+ size 4856
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fb8451d4f705f97819275987e1b9e0af869f4373ac82cd1f996cd005be4c7f40
3
  size 4856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d68c4fa0a8fcfe63eb26a5631e3de60f73e7c17ceff7dfa6400ad477c031590e
3
  size 4856