Hugging Face's logo

Seb0099
/
dataHub_autocomplete

Safetensors
t5
Model card Files
xet
Community
Seb0099 commited on
Commit
ca62999
·
verified ·
1 Parent(s): b714aa1

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. checkpoint-10624/config.json +61 -0
  2. checkpoint-10624/generation_config.json +7 -0
  3. checkpoint-10624/model.safetensors +3 -0
  4. checkpoint-10624/optimizer.pt +3 -0
  5. checkpoint-10624/rng_state.pth +3 -0
  6. checkpoint-10624/scheduler.pt +3 -0
  7. checkpoint-10624/trainer_state.json +180 -0
  8. checkpoint-10624/training_args.bin +3 -0
  9. checkpoint-11288/config.json +61 -0
  10. checkpoint-11288/generation_config.json +7 -0
  11. checkpoint-11288/model.safetensors +3 -0
  12. checkpoint-11288/optimizer.pt +3 -0
  13. checkpoint-11288/rng_state.pth +3 -0
  14. checkpoint-11288/scheduler.pt +3 -0
  15. checkpoint-11288/trainer_state.json +187 -0
  16. checkpoint-11288/training_args.bin +3 -0
  17. checkpoint-11952/config.json +61 -0
  18. checkpoint-11952/generation_config.json +7 -0
  19. checkpoint-11952/model.safetensors +3 -0
  20. checkpoint-11952/optimizer.pt +3 -0
  21. checkpoint-11952/rng_state.pth +3 -0
  22. checkpoint-11952/scheduler.pt +3 -0
  23. checkpoint-11952/trainer_state.json +194 -0
  24. checkpoint-11952/training_args.bin +3 -0
  25. checkpoint-12616/config.json +61 -0
  26. checkpoint-12616/generation_config.json +7 -0
  27. checkpoint-12616/model.safetensors +3 -0
  28. checkpoint-12616/optimizer.pt +3 -0
  29. checkpoint-12616/rng_state.pth +3 -0
  30. checkpoint-12616/scheduler.pt +3 -0
  31. checkpoint-12616/trainer_state.json +208 -0
  32. checkpoint-12616/training_args.bin +3 -0
  33. checkpoint-1328/config.json +61 -0
  34. checkpoint-1328/generation_config.json +7 -0
  35. checkpoint-1328/model.safetensors +3 -0
  36. checkpoint-1328/optimizer.pt +3 -0
  37. checkpoint-1328/rng_state.pth +3 -0
  38. checkpoint-1328/scheduler.pt +3 -0
  39. checkpoint-1328/trainer_state.json +47 -0
  40. checkpoint-1328/training_args.bin +3 -0
  41. checkpoint-13280/config.json +61 -0
  42. checkpoint-13280/generation_config.json +7 -0
  43. checkpoint-13280/model.safetensors +3 -0
  44. checkpoint-13280/optimizer.pt +3 -0
  45. checkpoint-13280/rng_state.pth +3 -0
  46. checkpoint-13280/scheduler.pt +3 -0
  47. checkpoint-13280/trainer_state.json +215 -0
  48. checkpoint-13280/training_args.bin +3 -0
  49. checkpoint-1992/config.json +61 -0
  50. checkpoint-1992/generation_config.json +7 -0
checkpoint-10624/config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "t5-small",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "classifier_dropout": 0.0,
7
+ "d_ff": 2048,
8
+ "d_kv": 64,
9
+ "d_model": 512,
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": 6,
22
+ "num_heads": 8,
23
+ "num_layers": 6,
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": "4.49.0",
59
+ "use_cache": true,
60
+ "vocab_size": 32128
61
+ }
checkpoint-10624/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": "4.49.0"
7
+ }
checkpoint-10624/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2a52a542fc460795d1eea30717f34069c2ac222ad447e5856a482d9f306f637
3
+ size 242041896
checkpoint-10624/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:626a689b9399ca5bc9be0ba4001343c82189ae6b5f17c2f154f5f420be8c8efd
3
+ size 484163514
checkpoint-10624/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:871dae08d4b0f588e7fb11dfff89a25046714f93a8b345b0a8564e6033959fb5
3
+ size 14244
checkpoint-10624/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff5e9fe88ecbc6317ecb28b185c99a3462fbdc58b45639f3e0d8c2dc79b5584f
3
+ size 1064
checkpoint-10624/trainer_state.json ADDED
@@ -0,0 +1,180 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 16.0,
5
+ "eval_steps": 500,
6
+ "global_step": 10624,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.7530120481927711,
13
+ "grad_norm": 0.2647170126438141,
14
+ "learning_rate": 0.0004811746987951807,
15
+ "loss": 0.3311,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 1.5060240963855422,
20
+ "grad_norm": 0.22880347073078156,
21
+ "learning_rate": 0.00046234939759036143,
22
+ "loss": 0.0907,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 2.2590361445783134,
27
+ "grad_norm": 0.1677163541316986,
28
+ "learning_rate": 0.00044352409638554217,
29
+ "loss": 0.0568,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 3.0120481927710845,
34
+ "grad_norm": 0.12338300049304962,
35
+ "learning_rate": 0.0004246987951807229,
36
+ "loss": 0.0451,
37
+ "step": 2000
38
+ },
39
+ {
40
+ "epoch": 3.765060240963855,
41
+ "grad_norm": 0.08597979694604874,
42
+ "learning_rate": 0.0004058734939759036,
43
+ "loss": 0.0386,
44
+ "step": 2500
45
+ },
46
+ {
47
+ "epoch": 4.518072289156627,
48
+ "grad_norm": 0.0988745242357254,
49
+ "learning_rate": 0.00038704819277108433,
50
+ "loss": 0.0352,
51
+ "step": 3000
52
+ },
53
+ {
54
+ "epoch": 5.271084337349397,
55
+ "grad_norm": 0.11785969883203506,
56
+ "learning_rate": 0.00036822289156626507,
57
+ "loss": 0.0331,
58
+ "step": 3500
59
+ },
60
+ {
61
+ "epoch": 6.024096385542169,
62
+ "grad_norm": 0.09906379133462906,
63
+ "learning_rate": 0.0003493975903614458,
64
+ "loss": 0.0315,
65
+ "step": 4000
66
+ },
67
+ {
68
+ "epoch": 6.77710843373494,
69
+ "grad_norm": 0.1129639744758606,
70
+ "learning_rate": 0.0003305722891566265,
71
+ "loss": 0.0301,
72
+ "step": 4500
73
+ },
74
+ {
75
+ "epoch": 7.530120481927711,
76
+ "grad_norm": 0.07321502268314362,
77
+ "learning_rate": 0.00031174698795180723,
78
+ "loss": 0.0292,
79
+ "step": 5000
80
+ },
81
+ {
82
+ "epoch": 8.283132530120483,
83
+ "grad_norm": 0.05083702132105827,
84
+ "learning_rate": 0.0002929216867469879,
85
+ "loss": 0.028,
86
+ "step": 5500
87
+ },
88
+ {
89
+ "epoch": 9.036144578313253,
90
+ "grad_norm": 0.073179692029953,
91
+ "learning_rate": 0.0002740963855421687,
92
+ "loss": 0.0275,
93
+ "step": 6000
94
+ },
95
+ {
96
+ "epoch": 9.789156626506024,
97
+ "grad_norm": 0.060432616621255875,
98
+ "learning_rate": 0.0002552710843373494,
99
+ "loss": 0.0266,
100
+ "step": 6500
101
+ },
102
+ {
103
+ "epoch": 10.542168674698795,
104
+ "grad_norm": 0.05641400068998337,
105
+ "learning_rate": 0.00023644578313253013,
106
+ "loss": 0.0265,
107
+ "step": 7000
108
+ },
109
+ {
110
+ "epoch": 11.295180722891565,
111
+ "grad_norm": 0.055228352546691895,
112
+ "learning_rate": 0.00021762048192771087,
113
+ "loss": 0.0257,
114
+ "step": 7500
115
+ },
116
+ {
117
+ "epoch": 12.048192771084338,
118
+ "grad_norm": 0.055986884981393814,
119
+ "learning_rate": 0.00019879518072289158,
120
+ "loss": 0.0254,
121
+ "step": 8000
122
+ },
123
+ {
124
+ "epoch": 12.801204819277109,
125
+ "grad_norm": 0.06879087537527084,
126
+ "learning_rate": 0.0001799698795180723,
127
+ "loss": 0.025,
128
+ "step": 8500
129
+ },
130
+ {
131
+ "epoch": 13.55421686746988,
132
+ "grad_norm": 0.08162941783666611,
133
+ "learning_rate": 0.00016114457831325303,
134
+ "loss": 0.0248,
135
+ "step": 9000
136
+ },
137
+ {
138
+ "epoch": 14.30722891566265,
139
+ "grad_norm": 0.0502689927816391,
140
+ "learning_rate": 0.00014231927710843374,
141
+ "loss": 0.0242,
142
+ "step": 9500
143
+ },
144
+ {
145
+ "epoch": 15.060240963855422,
146
+ "grad_norm": 0.052483588457107544,
147
+ "learning_rate": 0.00012349397590361445,
148
+ "loss": 0.0245,
149
+ "step": 10000
150
+ },
151
+ {
152
+ "epoch": 15.813253012048193,
153
+ "grad_norm": 0.04214683175086975,
154
+ "learning_rate": 0.00010466867469879517,
155
+ "loss": 0.0238,
156
+ "step": 10500
157
+ }
158
+ ],
159
+ "logging_steps": 500,
160
+ "max_steps": 13280,
161
+ "num_input_tokens_seen": 0,
162
+ "num_train_epochs": 20,
163
+ "save_steps": 500,
164
+ "stateful_callbacks": {
165
+ "TrainerControl": {
166
+ "args": {
167
+ "should_epoch_stop": false,
168
+ "should_evaluate": false,
169
+ "should_log": false,
170
+ "should_save": true,
171
+ "should_training_stop": false
172
+ },
173
+ "attributes": {}
174
+ }
175
+ },
176
+ "total_flos": 5744176738074624.0,
177
+ "train_batch_size": 32,
178
+ "trial_name": null,
179
+ "trial_params": null
180
+ }
checkpoint-10624/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ec2ab2506605f8b233e63780e2c7aa14dc16da409c9e0e5c14641534e5ff016
3
+ size 5304
checkpoint-11288/config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "t5-small",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "classifier_dropout": 0.0,
7
+ "d_ff": 2048,
8
+ "d_kv": 64,
9
+ "d_model": 512,
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": 6,
22
+ "num_heads": 8,
23
+ "num_layers": 6,
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": "4.49.0",
59
+ "use_cache": true,
60
+ "vocab_size": 32128
61
+ }
checkpoint-11288/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": "4.49.0"
7
+ }
checkpoint-11288/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d30b7966eb336d8ee47c0a75a7ba2a9369f2b9f5ff64ec647694b39217a6fe3
3
+ size 242041896
checkpoint-11288/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:225d5d0cebb7017617e05571854333032b6acc41d71a97baa451858b61dc93e9
3
+ size 484163514
checkpoint-11288/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea982c40bf13ee6d59e20a0c92fb57845229dff0ba14bb916750b0adb8f60d26
3
+ size 14244
checkpoint-11288/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f49e004a60a12580012411533599c9840ef90bb62ac0e44a6af9f00aa574415
3
+ size 1064
checkpoint-11288/trainer_state.json ADDED
@@ -0,0 +1,187 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 17.0,
5
+ "eval_steps": 500,
6
+ "global_step": 11288,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.7530120481927711,
13
+ "grad_norm": 0.2647170126438141,
14
+ "learning_rate": 0.0004811746987951807,
15
+ "loss": 0.3311,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 1.5060240963855422,
20
+ "grad_norm": 0.22880347073078156,
21
+ "learning_rate": 0.00046234939759036143,
22
+ "loss": 0.0907,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 2.2590361445783134,
27
+ "grad_norm": 0.1677163541316986,
28
+ "learning_rate": 0.00044352409638554217,
29
+ "loss": 0.0568,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 3.0120481927710845,
34
+ "grad_norm": 0.12338300049304962,
35
+ "learning_rate": 0.0004246987951807229,
36
+ "loss": 0.0451,
37
+ "step": 2000
38
+ },
39
+ {
40
+ "epoch": 3.765060240963855,
41
+ "grad_norm": 0.08597979694604874,
42
+ "learning_rate": 0.0004058734939759036,
43
+ "loss": 0.0386,
44
+ "step": 2500
45
+ },
46
+ {
47
+ "epoch": 4.518072289156627,
48
+ "grad_norm": 0.0988745242357254,
49
+ "learning_rate": 0.00038704819277108433,
50
+ "loss": 0.0352,
51
+ "step": 3000
52
+ },
53
+ {
54
+ "epoch": 5.271084337349397,
55
+ "grad_norm": 0.11785969883203506,
56
+ "learning_rate": 0.00036822289156626507,
57
+ "loss": 0.0331,
58
+ "step": 3500
59
+ },
60
+ {
61
+ "epoch": 6.024096385542169,
62
+ "grad_norm": 0.09906379133462906,
63
+ "learning_rate": 0.0003493975903614458,
64
+ "loss": 0.0315,
65
+ "step": 4000
66
+ },
67
+ {
68
+ "epoch": 6.77710843373494,
69
+ "grad_norm": 0.1129639744758606,
70
+ "learning_rate": 0.0003305722891566265,
71
+ "loss": 0.0301,
72
+ "step": 4500
73
+ },
74
+ {
75
+ "epoch": 7.530120481927711,
76
+ "grad_norm": 0.07321502268314362,
77
+ "learning_rate": 0.00031174698795180723,
78
+ "loss": 0.0292,
79
+ "step": 5000
80
+ },
81
+ {
82
+ "epoch": 8.283132530120483,
83
+ "grad_norm": 0.05083702132105827,
84
+ "learning_rate": 0.0002929216867469879,
85
+ "loss": 0.028,
86
+ "step": 5500
87
+ },
88
+ {
89
+ "epoch": 9.036144578313253,
90
+ "grad_norm": 0.073179692029953,
91
+ "learning_rate": 0.0002740963855421687,
92
+ "loss": 0.0275,
93
+ "step": 6000
94
+ },
95
+ {
96
+ "epoch": 9.789156626506024,
97
+ "grad_norm": 0.060432616621255875,
98
+ "learning_rate": 0.0002552710843373494,
99
+ "loss": 0.0266,
100
+ "step": 6500
101
+ },
102
+ {
103
+ "epoch": 10.542168674698795,
104
+ "grad_norm": 0.05641400068998337,
105
+ "learning_rate": 0.00023644578313253013,
106
+ "loss": 0.0265,
107
+ "step": 7000
108
+ },
109
+ {
110
+ "epoch": 11.295180722891565,
111
+ "grad_norm": 0.055228352546691895,
112
+ "learning_rate": 0.00021762048192771087,
113
+ "loss": 0.0257,
114
+ "step": 7500
115
+ },
116
+ {
117
+ "epoch": 12.048192771084338,
118
+ "grad_norm": 0.055986884981393814,
119
+ "learning_rate": 0.00019879518072289158,
120
+ "loss": 0.0254,
121
+ "step": 8000
122
+ },
123
+ {
124
+ "epoch": 12.801204819277109,
125
+ "grad_norm": 0.06879087537527084,
126
+ "learning_rate": 0.0001799698795180723,
127
+ "loss": 0.025,
128
+ "step": 8500
129
+ },
130
+ {
131
+ "epoch": 13.55421686746988,
132
+ "grad_norm": 0.08162941783666611,
133
+ "learning_rate": 0.00016114457831325303,
134
+ "loss": 0.0248,
135
+ "step": 9000
136
+ },
137
+ {
138
+ "epoch": 14.30722891566265,
139
+ "grad_norm": 0.0502689927816391,
140
+ "learning_rate": 0.00014231927710843374,
141
+ "loss": 0.0242,
142
+ "step": 9500
143
+ },
144
+ {
145
+ "epoch": 15.060240963855422,
146
+ "grad_norm": 0.052483588457107544,
147
+ "learning_rate": 0.00012349397590361445,
148
+ "loss": 0.0245,
149
+ "step": 10000
150
+ },
151
+ {
152
+ "epoch": 15.813253012048193,
153
+ "grad_norm": 0.04214683175086975,
154
+ "learning_rate": 0.00010466867469879517,
155
+ "loss": 0.0238,
156
+ "step": 10500
157
+ },
158
+ {
159
+ "epoch": 16.566265060240966,
160
+ "grad_norm": 0.03767360374331474,
161
+ "learning_rate": 8.58433734939759e-05,
162
+ "loss": 0.0239,
163
+ "step": 11000
164
+ }
165
+ ],
166
+ "logging_steps": 500,
167
+ "max_steps": 13280,
168
+ "num_input_tokens_seen": 0,
169
+ "num_train_epochs": 20,
170
+ "save_steps": 500,
171
+ "stateful_callbacks": {
172
+ "TrainerControl": {
173
+ "args": {
174
+ "should_epoch_stop": false,
175
+ "should_evaluate": false,
176
+ "should_log": false,
177
+ "should_save": true,
178
+ "should_training_stop": false
179
+ },
180
+ "attributes": {}
181
+ }
182
+ },
183
+ "total_flos": 6103187784204288.0,
184
+ "train_batch_size": 32,
185
+ "trial_name": null,
186
+ "trial_params": null
187
+ }
checkpoint-11288/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ec2ab2506605f8b233e63780e2c7aa14dc16da409c9e0e5c14641534e5ff016
3
+ size 5304
checkpoint-11952/config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "t5-small",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "classifier_dropout": 0.0,
7
+ "d_ff": 2048,
8
+ "d_kv": 64,
9
+ "d_model": 512,
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": 6,
22
+ "num_heads": 8,
23
+ "num_layers": 6,
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": "4.49.0",
59
+ "use_cache": true,
60
+ "vocab_size": 32128
61
+ }
checkpoint-11952/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": "4.49.0"
7
+ }
checkpoint-11952/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2eb96a9f08127ec7592e050ea89cd120320db5b74966dc5656609bbd208511c2
3
+ size 242041896
checkpoint-11952/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9cce771a11a0f6043f4a77c724a7499306145b423778e42ee3413da80892d3d
3
+ size 484163514
checkpoint-11952/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c503ee05f88e202769d6afdb9591580059e32575c1447b22ecf57bac3a49734
3
+ size 14244
checkpoint-11952/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22cc1df3a420b1528700cb2c2255107d6d7b4d17b007299a04e9c786c3c472a4
3
+ size 1064
checkpoint-11952/trainer_state.json ADDED
@@ -0,0 +1,194 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 18.0,
5
+ "eval_steps": 500,
6
+ "global_step": 11952,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.7530120481927711,
13
+ "grad_norm": 0.2647170126438141,
14
+ "learning_rate": 0.0004811746987951807,
15
+ "loss": 0.3311,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 1.5060240963855422,
20
+ "grad_norm": 0.22880347073078156,
21
+ "learning_rate": 0.00046234939759036143,
22
+ "loss": 0.0907,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 2.2590361445783134,
27
+ "grad_norm": 0.1677163541316986,
28
+ "learning_rate": 0.00044352409638554217,
29
+ "loss": 0.0568,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 3.0120481927710845,
34
+ "grad_norm": 0.12338300049304962,
35
+ "learning_rate": 0.0004246987951807229,
36
+ "loss": 0.0451,
37
+ "step": 2000
38
+ },
39
+ {
40
+ "epoch": 3.765060240963855,
41
+ "grad_norm": 0.08597979694604874,
42
+ "learning_rate": 0.0004058734939759036,
43
+ "loss": 0.0386,
44
+ "step": 2500
45
+ },
46
+ {
47
+ "epoch": 4.518072289156627,
48
+ "grad_norm": 0.0988745242357254,
49
+ "learning_rate": 0.00038704819277108433,
50
+ "loss": 0.0352,
51
+ "step": 3000
52
+ },
53
+ {
54
+ "epoch": 5.271084337349397,
55
+ "grad_norm": 0.11785969883203506,
56
+ "learning_rate": 0.00036822289156626507,
57
+ "loss": 0.0331,
58
+ "step": 3500
59
+ },
60
+ {
61
+ "epoch": 6.024096385542169,
62
+ "grad_norm": 0.09906379133462906,
63
+ "learning_rate": 0.0003493975903614458,
64
+ "loss": 0.0315,
65
+ "step": 4000
66
+ },
67
+ {
68
+ "epoch": 6.77710843373494,
69
+ "grad_norm": 0.1129639744758606,
70
+ "learning_rate": 0.0003305722891566265,
71
+ "loss": 0.0301,
72
+ "step": 4500
73
+ },
74
+ {
75
+ "epoch": 7.530120481927711,
76
+ "grad_norm": 0.07321502268314362,
77
+ "learning_rate": 0.00031174698795180723,
78
+ "loss": 0.0292,
79
+ "step": 5000
80
+ },
81
+ {
82
+ "epoch": 8.283132530120483,
83
+ "grad_norm": 0.05083702132105827,
84
+ "learning_rate": 0.0002929216867469879,
85
+ "loss": 0.028,
86
+ "step": 5500
87
+ },
88
+ {
89
+ "epoch": 9.036144578313253,
90
+ "grad_norm": 0.073179692029953,
91
+ "learning_rate": 0.0002740963855421687,
92
+ "loss": 0.0275,
93
+ "step": 6000
94
+ },
95
+ {
96
+ "epoch": 9.789156626506024,
97
+ "grad_norm": 0.060432616621255875,
98
+ "learning_rate": 0.0002552710843373494,
99
+ "loss": 0.0266,
100
+ "step": 6500
101
+ },
102
+ {
103
+ "epoch": 10.542168674698795,
104
+ "grad_norm": 0.05641400068998337,
105
+ "learning_rate": 0.00023644578313253013,
106
+ "loss": 0.0265,
107
+ "step": 7000
108
+ },
109
+ {
110
+ "epoch": 11.295180722891565,
111
+ "grad_norm": 0.055228352546691895,
112
+ "learning_rate": 0.00021762048192771087,
113
+ "loss": 0.0257,
114
+ "step": 7500
115
+ },
116
+ {
117
+ "epoch": 12.048192771084338,
118
+ "grad_norm": 0.055986884981393814,
119
+ "learning_rate": 0.00019879518072289158,
120
+ "loss": 0.0254,
121
+ "step": 8000
122
+ },
123
+ {
124
+ "epoch": 12.801204819277109,
125
+ "grad_norm": 0.06879087537527084,
126
+ "learning_rate": 0.0001799698795180723,
127
+ "loss": 0.025,
128
+ "step": 8500
129
+ },
130
+ {
131
+ "epoch": 13.55421686746988,
132
+ "grad_norm": 0.08162941783666611,
133
+ "learning_rate": 0.00016114457831325303,
134
+ "loss": 0.0248,
135
+ "step": 9000
136
+ },
137
+ {
138
+ "epoch": 14.30722891566265,
139
+ "grad_norm": 0.0502689927816391,
140
+ "learning_rate": 0.00014231927710843374,
141
+ "loss": 0.0242,
142
+ "step": 9500
143
+ },
144
+ {
145
+ "epoch": 15.060240963855422,
146
+ "grad_norm": 0.052483588457107544,
147
+ "learning_rate": 0.00012349397590361445,
148
+ "loss": 0.0245,
149
+ "step": 10000
150
+ },
151
+ {
152
+ "epoch": 15.813253012048193,
153
+ "grad_norm": 0.04214683175086975,
154
+ "learning_rate": 0.00010466867469879517,
155
+ "loss": 0.0238,
156
+ "step": 10500
157
+ },
158
+ {
159
+ "epoch": 16.566265060240966,
160
+ "grad_norm": 0.03767360374331474,
161
+ "learning_rate": 8.58433734939759e-05,
162
+ "loss": 0.0239,
163
+ "step": 11000
164
+ },
165
+ {
166
+ "epoch": 17.319277108433734,
167
+ "grad_norm": 0.04902500659227371,
168
+ "learning_rate": 6.701807228915662e-05,
169
+ "loss": 0.0234,
170
+ "step": 11500
171
+ }
172
+ ],
173
+ "logging_steps": 500,
174
+ "max_steps": 13280,
175
+ "num_input_tokens_seen": 0,
176
+ "num_train_epochs": 20,
177
+ "save_steps": 500,
178
+ "stateful_callbacks": {
179
+ "TrainerControl": {
180
+ "args": {
181
+ "should_epoch_stop": false,
182
+ "should_evaluate": false,
183
+ "should_log": false,
184
+ "should_save": true,
185
+ "should_training_stop": false
186
+ },
187
+ "attributes": {}
188
+ }
189
+ },
190
+ "total_flos": 6462198830333952.0,
191
+ "train_batch_size": 32,
192
+ "trial_name": null,
193
+ "trial_params": null
194
+ }
checkpoint-11952/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ec2ab2506605f8b233e63780e2c7aa14dc16da409c9e0e5c14641534e5ff016
3
+ size 5304
checkpoint-12616/config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "t5-small",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "classifier_dropout": 0.0,
7
+ "d_ff": 2048,
8
+ "d_kv": 64,
9
+ "d_model": 512,
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": 6,
22
+ "num_heads": 8,
23
+ "num_layers": 6,
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": "4.49.0",
59
+ "use_cache": true,
60
+ "vocab_size": 32128
61
+ }
checkpoint-12616/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": "4.49.0"
7
+ }
checkpoint-12616/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e6b7740a417775a39ca07bbcb3f19c41d1de00ef5d3c600eb612b81f032d12a
3
+ size 242041896
checkpoint-12616/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:298fd0e26e0e50e6407d3e5b11ce54997833eae70441b852ffc0ce668a639ccc
3
+ size 484163514
checkpoint-12616/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21b5b2d0d4ef3a10347f33189f220aa44bc97dadc5d71a227e0fb3e22c380ff6
3
+ size 14244
checkpoint-12616/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:822b1fd7a3f099d382f34877c8a7ac2274ddcadf9bb3122afba35168bc2788e6
3
+ size 1064
checkpoint-12616/trainer_state.json ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 19.0,
5
+ "eval_steps": 500,
6
+ "global_step": 12616,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.7530120481927711,
13
+ "grad_norm": 0.2647170126438141,
14
+ "learning_rate": 0.0004811746987951807,
15
+ "loss": 0.3311,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 1.5060240963855422,
20
+ "grad_norm": 0.22880347073078156,
21
+ "learning_rate": 0.00046234939759036143,
22
+ "loss": 0.0907,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 2.2590361445783134,
27
+ "grad_norm": 0.1677163541316986,
28
+ "learning_rate": 0.00044352409638554217,
29
+ "loss": 0.0568,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 3.0120481927710845,
34
+ "grad_norm": 0.12338300049304962,
35
+ "learning_rate": 0.0004246987951807229,
36
+ "loss": 0.0451,
37
+ "step": 2000
38
+ },
39
+ {
40
+ "epoch": 3.765060240963855,
41
+ "grad_norm": 0.08597979694604874,
42
+ "learning_rate": 0.0004058734939759036,
43
+ "loss": 0.0386,
44
+ "step": 2500
45
+ },
46
+ {
47
+ "epoch": 4.518072289156627,
48
+ "grad_norm": 0.0988745242357254,
49
+ "learning_rate": 0.00038704819277108433,
50
+ "loss": 0.0352,
51
+ "step": 3000
52
+ },
53
+ {
54
+ "epoch": 5.271084337349397,
55
+ "grad_norm": 0.11785969883203506,
56
+ "learning_rate": 0.00036822289156626507,
57
+ "loss": 0.0331,
58
+ "step": 3500
59
+ },
60
+ {
61
+ "epoch": 6.024096385542169,
62
+ "grad_norm": 0.09906379133462906,
63
+ "learning_rate": 0.0003493975903614458,
64
+ "loss": 0.0315,
65
+ "step": 4000
66
+ },
67
+ {
68
+ "epoch": 6.77710843373494,
69
+ "grad_norm": 0.1129639744758606,
70
+ "learning_rate": 0.0003305722891566265,
71
+ "loss": 0.0301,
72
+ "step": 4500
73
+ },
74
+ {
75
+ "epoch": 7.530120481927711,
76
+ "grad_norm": 0.07321502268314362,
77
+ "learning_rate": 0.00031174698795180723,
78
+ "loss": 0.0292,
79
+ "step": 5000
80
+ },
81
+ {
82
+ "epoch": 8.283132530120483,
83
+ "grad_norm": 0.05083702132105827,
84
+ "learning_rate": 0.0002929216867469879,
85
+ "loss": 0.028,
86
+ "step": 5500
87
+ },
88
+ {
89
+ "epoch": 9.036144578313253,
90
+ "grad_norm": 0.073179692029953,
91
+ "learning_rate": 0.0002740963855421687,
92
+ "loss": 0.0275,
93
+ "step": 6000
94
+ },
95
+ {
96
+ "epoch": 9.789156626506024,
97
+ "grad_norm": 0.060432616621255875,
98
+ "learning_rate": 0.0002552710843373494,
99
+ "loss": 0.0266,
100
+ "step": 6500
101
+ },
102
+ {
103
+ "epoch": 10.542168674698795,
104
+ "grad_norm": 0.05641400068998337,
105
+ "learning_rate": 0.00023644578313253013,
106
+ "loss": 0.0265,
107
+ "step": 7000
108
+ },
109
+ {
110
+ "epoch": 11.295180722891565,
111
+ "grad_norm": 0.055228352546691895,
112
+ "learning_rate": 0.00021762048192771087,
113
+ "loss": 0.0257,
114
+ "step": 7500
115
+ },
116
+ {
117
+ "epoch": 12.048192771084338,
118
+ "grad_norm": 0.055986884981393814,
119
+ "learning_rate": 0.00019879518072289158,
120
+ "loss": 0.0254,
121
+ "step": 8000
122
+ },
123
+ {
124
+ "epoch": 12.801204819277109,
125
+ "grad_norm": 0.06879087537527084,
126
+ "learning_rate": 0.0001799698795180723,
127
+ "loss": 0.025,
128
+ "step": 8500
129
+ },
130
+ {
131
+ "epoch": 13.55421686746988,
132
+ "grad_norm": 0.08162941783666611,
133
+ "learning_rate": 0.00016114457831325303,
134
+ "loss": 0.0248,
135
+ "step": 9000
136
+ },
137
+ {
138
+ "epoch": 14.30722891566265,
139
+ "grad_norm": 0.0502689927816391,
140
+ "learning_rate": 0.00014231927710843374,
141
+ "loss": 0.0242,
142
+ "step": 9500
143
+ },
144
+ {
145
+ "epoch": 15.060240963855422,
146
+ "grad_norm": 0.052483588457107544,
147
+ "learning_rate": 0.00012349397590361445,
148
+ "loss": 0.0245,
149
+ "step": 10000
150
+ },
151
+ {
152
+ "epoch": 15.813253012048193,
153
+ "grad_norm": 0.04214683175086975,
154
+ "learning_rate": 0.00010466867469879517,
155
+ "loss": 0.0238,
156
+ "step": 10500
157
+ },
158
+ {
159
+ "epoch": 16.566265060240966,
160
+ "grad_norm": 0.03767360374331474,
161
+ "learning_rate": 8.58433734939759e-05,
162
+ "loss": 0.0239,
163
+ "step": 11000
164
+ },
165
+ {
166
+ "epoch": 17.319277108433734,
167
+ "grad_norm": 0.04902500659227371,
168
+ "learning_rate": 6.701807228915662e-05,
169
+ "loss": 0.0234,
170
+ "step": 11500
171
+ },
172
+ {
173
+ "epoch": 18.072289156626507,
174
+ "grad_norm": 0.058824148029088974,
175
+ "learning_rate": 4.8192771084337354e-05,
176
+ "loss": 0.0232,
177
+ "step": 12000
178
+ },
179
+ {
180
+ "epoch": 18.825301204819276,
181
+ "grad_norm": 0.06361762434244156,
182
+ "learning_rate": 2.9367469879518075e-05,
183
+ "loss": 0.0231,
184
+ "step": 12500
185
+ }
186
+ ],
187
+ "logging_steps": 500,
188
+ "max_steps": 13280,
189
+ "num_input_tokens_seen": 0,
190
+ "num_train_epochs": 20,
191
+ "save_steps": 500,
192
+ "stateful_callbacks": {
193
+ "TrainerControl": {
194
+ "args": {
195
+ "should_epoch_stop": false,
196
+ "should_evaluate": false,
197
+ "should_log": false,
198
+ "should_save": true,
199
+ "should_training_stop": false
200
+ },
201
+ "attributes": {}
202
+ }
203
+ },
204
+ "total_flos": 6821209876463616.0,
205
+ "train_batch_size": 32,
206
+ "trial_name": null,
207
+ "trial_params": null
208
+ }
checkpoint-12616/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ec2ab2506605f8b233e63780e2c7aa14dc16da409c9e0e5c14641534e5ff016
3
+ size 5304
checkpoint-1328/config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "t5-small",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "classifier_dropout": 0.0,
7
+ "d_ff": 2048,
8
+ "d_kv": 64,
9
+ "d_model": 512,
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": 6,
22
+ "num_heads": 8,
23
+ "num_layers": 6,
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": "4.49.0",
59
+ "use_cache": true,
60
+ "vocab_size": 32128
61
+ }
checkpoint-1328/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": "4.49.0"
7
+ }
checkpoint-1328/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cb90960a87bb689d468344aeff8b4e9d5590b017945b0a486ddb999a6542813
3
+ size 242041896
checkpoint-1328/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5100188e6dcc93a1184d247117fb0df100240535a266ec5f78e8b8bd3943062e
3
+ size 484163514
checkpoint-1328/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8737df5603a32aae5e5e9c2da6de40078a49291ae4477cd8b2ae7c3f57890fbc
3
+ size 14244
checkpoint-1328/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b51d887a83d6c3823b34be1c27e0a48d7412ba51ea0a6f9ef63aa05d8faea20
3
+ size 1064
checkpoint-1328/trainer_state.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1328,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.7530120481927711,
13
+ "grad_norm": 0.2647170126438141,
14
+ "learning_rate": 0.0004811746987951807,
15
+ "loss": 0.3311,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 1.5060240963855422,
20
+ "grad_norm": 0.22880347073078156,
21
+ "learning_rate": 0.00046234939759036143,
22
+ "loss": 0.0907,
23
+ "step": 1000
24
+ }
25
+ ],
26
+ "logging_steps": 500,
27
+ "max_steps": 13280,
28
+ "num_input_tokens_seen": 0,
29
+ "num_train_epochs": 20,
30
+ "save_steps": 500,
31
+ "stateful_callbacks": {
32
+ "TrainerControl": {
33
+ "args": {
34
+ "should_epoch_stop": false,
35
+ "should_evaluate": false,
36
+ "should_log": false,
37
+ "should_save": true,
38
+ "should_training_stop": false
39
+ },
40
+ "attributes": {}
41
+ }
42
+ },
43
+ "total_flos": 718022092259328.0,
44
+ "train_batch_size": 32,
45
+ "trial_name": null,
46
+ "trial_params": null
47
+ }
checkpoint-1328/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ec2ab2506605f8b233e63780e2c7aa14dc16da409c9e0e5c14641534e5ff016
3
+ size 5304
checkpoint-13280/config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "t5-small",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "classifier_dropout": 0.0,
7
+ "d_ff": 2048,
8
+ "d_kv": 64,
9
+ "d_model": 512,
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": 6,
22
+ "num_heads": 8,
23
+ "num_layers": 6,
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": "4.49.0",
59
+ "use_cache": true,
60
+ "vocab_size": 32128
61
+ }
checkpoint-13280/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": "4.49.0"
7
+ }
checkpoint-13280/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8bd36f4c4292c3d390f593bc70a7f6421f9732c1adde462e862d0e1dd1f20c9
3
+ size 242041896
checkpoint-13280/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:301f1132d8ad5001f1b12cf4300d5b23653e59d8885b0c5005bf916df091417c
3
+ size 484163514
checkpoint-13280/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb1f5a9993254e34859ad003f7605d6f3577e096450d91bae1e372fe7a69711b
3
+ size 14244
checkpoint-13280/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cd06fe26347b0405fefe5ed1eea662b1479b2b2b4875e24a34f8e1b73b73ad7
3
+ size 1064
checkpoint-13280/trainer_state.json ADDED
@@ -0,0 +1,215 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 20.0,
5
+ "eval_steps": 500,
6
+ "global_step": 13280,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.7530120481927711,
13
+ "grad_norm": 0.2647170126438141,
14
+ "learning_rate": 0.0004811746987951807,
15
+ "loss": 0.3311,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 1.5060240963855422,
20
+ "grad_norm": 0.22880347073078156,
21
+ "learning_rate": 0.00046234939759036143,
22
+ "loss": 0.0907,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 2.2590361445783134,
27
+ "grad_norm": 0.1677163541316986,
28
+ "learning_rate": 0.00044352409638554217,
29
+ "loss": 0.0568,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 3.0120481927710845,
34
+ "grad_norm": 0.12338300049304962,
35
+ "learning_rate": 0.0004246987951807229,
36
+ "loss": 0.0451,
37
+ "step": 2000
38
+ },
39
+ {
40
+ "epoch": 3.765060240963855,
41
+ "grad_norm": 0.08597979694604874,
42
+ "learning_rate": 0.0004058734939759036,
43
+ "loss": 0.0386,
44
+ "step": 2500
45
+ },
46
+ {
47
+ "epoch": 4.518072289156627,
48
+ "grad_norm": 0.0988745242357254,
49
+ "learning_rate": 0.00038704819277108433,
50
+ "loss": 0.0352,
51
+ "step": 3000
52
+ },
53
+ {
54
+ "epoch": 5.271084337349397,
55
+ "grad_norm": 0.11785969883203506,
56
+ "learning_rate": 0.00036822289156626507,
57
+ "loss": 0.0331,
58
+ "step": 3500
59
+ },
60
+ {
61
+ "epoch": 6.024096385542169,
62
+ "grad_norm": 0.09906379133462906,
63
+ "learning_rate": 0.0003493975903614458,
64
+ "loss": 0.0315,
65
+ "step": 4000
66
+ },
67
+ {
68
+ "epoch": 6.77710843373494,
69
+ "grad_norm": 0.1129639744758606,
70
+ "learning_rate": 0.0003305722891566265,
71
+ "loss": 0.0301,
72
+ "step": 4500
73
+ },
74
+ {
75
+ "epoch": 7.530120481927711,
76
+ "grad_norm": 0.07321502268314362,
77
+ "learning_rate": 0.00031174698795180723,
78
+ "loss": 0.0292,
79
+ "step": 5000
80
+ },
81
+ {
82
+ "epoch": 8.283132530120483,
83
+ "grad_norm": 0.05083702132105827,
84
+ "learning_rate": 0.0002929216867469879,
85
+ "loss": 0.028,
86
+ "step": 5500
87
+ },
88
+ {
89
+ "epoch": 9.036144578313253,
90
+ "grad_norm": 0.073179692029953,
91
+ "learning_rate": 0.0002740963855421687,
92
+ "loss": 0.0275,
93
+ "step": 6000
94
+ },
95
+ {
96
+ "epoch": 9.789156626506024,
97
+ "grad_norm": 0.060432616621255875,
98
+ "learning_rate": 0.0002552710843373494,
99
+ "loss": 0.0266,
100
+ "step": 6500
101
+ },
102
+ {
103
+ "epoch": 10.542168674698795,
104
+ "grad_norm": 0.05641400068998337,
105
+ "learning_rate": 0.00023644578313253013,
106
+ "loss": 0.0265,
107
+ "step": 7000
108
+ },
109
+ {
110
+ "epoch": 11.295180722891565,
111
+ "grad_norm": 0.055228352546691895,
112
+ "learning_rate": 0.00021762048192771087,
113
+ "loss": 0.0257,
114
+ "step": 7500
115
+ },
116
+ {
117
+ "epoch": 12.048192771084338,
118
+ "grad_norm": 0.055986884981393814,
119
+ "learning_rate": 0.00019879518072289158,
120
+ "loss": 0.0254,
121
+ "step": 8000
122
+ },
123
+ {
124
+ "epoch": 12.801204819277109,
125
+ "grad_norm": 0.06879087537527084,
126
+ "learning_rate": 0.0001799698795180723,
127
+ "loss": 0.025,
128
+ "step": 8500
129
+ },
130
+ {
131
+ "epoch": 13.55421686746988,
132
+ "grad_norm": 0.08162941783666611,
133
+ "learning_rate": 0.00016114457831325303,
134
+ "loss": 0.0248,
135
+ "step": 9000
136
+ },
137
+ {
138
+ "epoch": 14.30722891566265,
139
+ "grad_norm": 0.0502689927816391,
140
+ "learning_rate": 0.00014231927710843374,
141
+ "loss": 0.0242,
142
+ "step": 9500
143
+ },
144
+ {
145
+ "epoch": 15.060240963855422,
146
+ "grad_norm": 0.052483588457107544,
147
+ "learning_rate": 0.00012349397590361445,
148
+ "loss": 0.0245,
149
+ "step": 10000
150
+ },
151
+ {
152
+ "epoch": 15.813253012048193,
153
+ "grad_norm": 0.04214683175086975,
154
+ "learning_rate": 0.00010466867469879517,
155
+ "loss": 0.0238,
156
+ "step": 10500
157
+ },
158
+ {
159
+ "epoch": 16.566265060240966,
160
+ "grad_norm": 0.03767360374331474,
161
+ "learning_rate": 8.58433734939759e-05,
162
+ "loss": 0.0239,
163
+ "step": 11000
164
+ },
165
+ {
166
+ "epoch": 17.319277108433734,
167
+ "grad_norm": 0.04902500659227371,
168
+ "learning_rate": 6.701807228915662e-05,
169
+ "loss": 0.0234,
170
+ "step": 11500
171
+ },
172
+ {
173
+ "epoch": 18.072289156626507,
174
+ "grad_norm": 0.058824148029088974,
175
+ "learning_rate": 4.8192771084337354e-05,
176
+ "loss": 0.0232,
177
+ "step": 12000
178
+ },
179
+ {
180
+ "epoch": 18.825301204819276,
181
+ "grad_norm": 0.06361762434244156,
182
+ "learning_rate": 2.9367469879518075e-05,
183
+ "loss": 0.0231,
184
+ "step": 12500
185
+ },
186
+ {
187
+ "epoch": 19.57831325301205,
188
+ "grad_norm": 0.053078796714544296,
189
+ "learning_rate": 1.0542168674698795e-05,
190
+ "loss": 0.0232,
191
+ "step": 13000
192
+ }
193
+ ],
194
+ "logging_steps": 500,
195
+ "max_steps": 13280,
196
+ "num_input_tokens_seen": 0,
197
+ "num_train_epochs": 20,
198
+ "save_steps": 500,
199
+ "stateful_callbacks": {
200
+ "TrainerControl": {
201
+ "args": {
202
+ "should_epoch_stop": false,
203
+ "should_evaluate": false,
204
+ "should_log": false,
205
+ "should_save": true,
206
+ "should_training_stop": true
207
+ },
208
+ "attributes": {}
209
+ }
210
+ },
211
+ "total_flos": 7180220922593280.0,
212
+ "train_batch_size": 32,
213
+ "trial_name": null,
214
+ "trial_params": null
215
+ }
checkpoint-13280/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ec2ab2506605f8b233e63780e2c7aa14dc16da409c9e0e5c14641534e5ff016
3
+ size 5304
checkpoint-1992/config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "t5-small",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "classifier_dropout": 0.0,
7
+ "d_ff": 2048,
8
+ "d_kv": 64,
9
+ "d_model": 512,
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": 6,
22
+ "num_heads": 8,
23
+ "num_layers": 6,
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": "4.49.0",
59
+ "use_cache": true,
60
+ "vocab_size": 32128
61
+ }
checkpoint-1992/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": "4.49.0"
7
+ }