Hugging Face's logo

mootez
/
mean_codet5-base_L9_codetrans_442_src_java_tgt_c_sharp

TensorBoard
Safetensors
t5
Model card Files
xet
Metrics Community
mootez commited on
Commit
399a72b
·
verified ·
1 Parent(s): b4ce83b

Upload folder using huggingface_hub

Browse files
Files changed (14) hide show
  1. checkpoint-7722/config.json +71 -0
  2. checkpoint-7722/generation_config.json +7 -0
  3. checkpoint-7722/model.safetensors +3 -0
  4. checkpoint-7722/optimizer.pt +3 -0
  5. checkpoint-7722/rng_state.pth +3 -0
  6. checkpoint-7722/scheduler.pt +3 -0
  7. checkpoint-7722/trainer_state.json +151 -0
  8. checkpoint-7722/training_args.bin +3 -0
  9. config.json +71 -0
  10. events.out.tfevents.1751443199.gra5 +3 -0
  11. generation_config.json +7 -0
  12. model.safetensors +3 -0
  13. results.json +17 -0
  14. training_args.bin +3 -0
checkpoint-7722/config.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/mootez/projects/def-tusharma/mootez/local_models/codet5-base",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "classifier_dropout": 0.0,
8
+ "d_ff": 3072,
9
+ "d_kv": 64,
10
+ "d_model": 768,
11
+ "decoder_start_token_id": 0,
12
+ "dense_act_fn": "relu",
13
+ "dropout_rate": 0.1,
14
+ "eos_token_id": 2,
15
+ "feed_forward_proj": "relu",
16
+ "gradient_checkpointing": false,
17
+ "id2label": {
18
+ "0": "LABEL_0"
19
+ },
20
+ "initializer_factor": 1.0,
21
+ "is_encoder_decoder": true,
22
+ "is_gated_act": false,
23
+ "label2id": {
24
+ "LABEL_0": 0
25
+ },
26
+ "layer_norm_epsilon": 1e-06,
27
+ "merge_layer_index": 9,
28
+ "merger_type": "mean",
29
+ "model_type": "t5",
30
+ "n_positions": 512,
31
+ "num_decoder_layers": 12,
32
+ "num_heads": 12,
33
+ "num_layers": 12,
34
+ "output_past": true,
35
+ "pad_token_id": 0,
36
+ "relative_attention_max_distance": 128,
37
+ "relative_attention_num_buckets": 32,
38
+ "task_specific_params": {
39
+ "summarization": {
40
+ "early_stopping": true,
41
+ "length_penalty": 2.0,
42
+ "max_length": 200,
43
+ "min_length": 30,
44
+ "no_repeat_ngram_size": 3,
45
+ "num_beams": 4,
46
+ "prefix": "summarize: "
47
+ },
48
+ "translation_en_to_de": {
49
+ "early_stopping": true,
50
+ "max_length": 300,
51
+ "num_beams": 4,
52
+ "prefix": "translate English to German: "
53
+ },
54
+ "translation_en_to_fr": {
55
+ "early_stopping": true,
56
+ "max_length": 300,
57
+ "num_beams": 4,
58
+ "prefix": "translate English to French: "
59
+ },
60
+ "translation_en_to_ro": {
61
+ "early_stopping": true,
62
+ "max_length": 300,
63
+ "num_beams": 4,
64
+ "prefix": "translate English to Romanian: "
65
+ }
66
+ },
67
+ "torch_dtype": "float32",
68
+ "transformers_version": "4.48.2",
69
+ "use_cache": true,
70
+ "vocab_size": 32100
71
+ }
checkpoint-7722/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "decoder_start_token_id": 0,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.48.2"
7
+ }
checkpoint-7722/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89859d51e260e2979a62892c7686223c907a674f23ccc17325eafc6f6b9acfdf
3
+ size 891558696
checkpoint-7722/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37a9c0537d30bacb8f8bfcb9c750c5ddbc2d627c23af4046abf7d9863010d819
3
+ size 1783272762
checkpoint-7722/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c22c371a198feaa01f310ab42a67b084047d50bf7bac9bfcddb8d53d956f4ba
3
+ size 14308
checkpoint-7722/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5d46859dfbb0c62564f5c237261364ad22f90a9a0188c2fafa539eca73caba2
3
+ size 1064
checkpoint-7722/trainer_state.json ADDED
@@ -0,0 +1,151 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.18441354635826024,
3
+ "best_model_checkpoint": "./logs/mean_codet5-base_L9_codetrans_442_src_java_tgt_c_sharp/checkpoint-7722",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 7722,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.3885003885003885,
13
+ "grad_norm": 6.798919677734375,
14
+ "learning_rate": 7.77302759424796e-06,
15
+ "loss": 2.6856,
16
+ "step": 1000
17
+ },
18
+ {
19
+ "epoch": 0.777000777000777,
20
+ "grad_norm": 2.100330114364624,
21
+ "learning_rate": 1.554605518849592e-05,
22
+ "loss": 0.5453,
23
+ "step": 2000
24
+ },
25
+ {
26
+ "epoch": 1.0,
27
+ "eval_bleu": 0.17829203659223233,
28
+ "eval_brevity_penalty": 0.19826038730459755,
29
+ "eval_length_ratio": 0.3819455813496611,
30
+ "eval_loss": 0.2992079555988312,
31
+ "eval_precision": [
32
+ 0.9443849121303043,
33
+ 0.9069560884729534,
34
+ 0.8829880425736937,
35
+ 0.8647565485020924
36
+ ],
37
+ "eval_reference_length": 122164,
38
+ "eval_rouge1": 0.5651597591004975,
39
+ "eval_rouge2": 0.48038318963443805,
40
+ "eval_rougeL": 0.5642194755662775,
41
+ "eval_rougeLsum": 0.5632665531422743,
42
+ "eval_runtime": 19.5129,
43
+ "eval_samples_per_second": 25.573,
44
+ "eval_steps_per_second": 1.64,
45
+ "eval_translation_length": 46660,
46
+ "step": 2574
47
+ },
48
+ {
49
+ "epoch": 1.1655011655011656,
50
+ "grad_norm": 1.5482529401779175,
51
+ "learning_rate": 1.9631372210471794e-05,
52
+ "loss": 0.3899,
53
+ "step": 3000
54
+ },
55
+ {
56
+ "epoch": 1.554001554001554,
57
+ "grad_norm": 1.733742117881775,
58
+ "learning_rate": 1.8768075279492384e-05,
59
+ "loss": 0.309,
60
+ "step": 4000
61
+ },
62
+ {
63
+ "epoch": 1.9425019425019425,
64
+ "grad_norm": 2.044071674346924,
65
+ "learning_rate": 1.790477834851297e-05,
66
+ "loss": 0.2731,
67
+ "step": 5000
68
+ },
69
+ {
70
+ "epoch": 2.0,
71
+ "eval_bleu": 0.18411633601962932,
72
+ "eval_brevity_penalty": 0.20166021843150442,
73
+ "eval_length_ratio": 0.3844422252054615,
74
+ "eval_loss": 0.2134634256362915,
75
+ "eval_precision": [
76
+ 0.9458107101032683,
77
+ 0.9183919424955882,
78
+ 0.9007766441142558,
79
+ 0.8880531362716636
80
+ ],
81
+ "eval_reference_length": 122164,
82
+ "eval_rouge1": 0.584479835605842,
83
+ "eval_rouge2": 0.5177035533096785,
84
+ "eval_rougeL": 0.5824047115731658,
85
+ "eval_rougeLsum": 0.5824514188220322,
86
+ "eval_runtime": 19.4462,
87
+ "eval_samples_per_second": 25.661,
88
+ "eval_steps_per_second": 1.646,
89
+ "eval_translation_length": 46965,
90
+ "step": 5148
91
+ },
92
+ {
93
+ "epoch": 2.331002331002331,
94
+ "grad_norm": 0.6968048214912415,
95
+ "learning_rate": 1.7041481417533562e-05,
96
+ "loss": 0.2192,
97
+ "step": 6000
98
+ },
99
+ {
100
+ "epoch": 2.7195027195027195,
101
+ "grad_norm": 1.0236526727676392,
102
+ "learning_rate": 1.6178184486554153e-05,
103
+ "loss": 0.2017,
104
+ "step": 7000
105
+ },
106
+ {
107
+ "epoch": 3.0,
108
+ "eval_bleu": 0.18441354635826024,
109
+ "eval_brevity_penalty": 0.19989730826376506,
110
+ "eval_length_ratio": 0.3831488818309813,
111
+ "eval_loss": 0.18781286478042603,
112
+ "eval_precision": [
113
+ 0.9517166235819429,
114
+ 0.9270320462986957,
115
+ 0.9114802768015019,
116
+ 0.9007283160450231
117
+ ],
118
+ "eval_reference_length": 122164,
119
+ "eval_rouge1": 0.5920430908644092,
120
+ "eval_rouge2": 0.5307220922363098,
121
+ "eval_rougeL": 0.5904379566748066,
122
+ "eval_rougeLsum": 0.590627093739196,
123
+ "eval_runtime": 19.4419,
124
+ "eval_samples_per_second": 25.666,
125
+ "eval_steps_per_second": 1.646,
126
+ "eval_translation_length": 46807,
127
+ "step": 7722
128
+ }
129
+ ],
130
+ "logging_steps": 1000,
131
+ "max_steps": 25740,
132
+ "num_input_tokens_seen": 0,
133
+ "num_train_epochs": 10,
134
+ "save_steps": 500,
135
+ "stateful_callbacks": {
136
+ "TrainerControl": {
137
+ "args": {
138
+ "should_epoch_stop": false,
139
+ "should_evaluate": false,
140
+ "should_log": false,
141
+ "should_save": true,
142
+ "should_training_stop": false
143
+ },
144
+ "attributes": {}
145
+ }
146
+ },
147
+ "total_flos": 9367098505344000.0,
148
+ "train_batch_size": 4,
149
+ "trial_name": null,
150
+ "trial_params": null
151
+ }
checkpoint-7722/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e78e607d8228443c867ad75c31e3a7d0861f88a0d5aa4358225f9eea2153815
3
+ size 5496
config.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/mootez/projects/def-tusharma/mootez/local_models/codet5-base",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "classifier_dropout": 0.0,
8
+ "d_ff": 3072,
9
+ "d_kv": 64,
10
+ "d_model": 768,
11
+ "decoder_start_token_id": 0,
12
+ "dense_act_fn": "relu",
13
+ "dropout_rate": 0.1,
14
+ "eos_token_id": 2,
15
+ "feed_forward_proj": "relu",
16
+ "gradient_checkpointing": false,
17
+ "id2label": {
18
+ "0": "LABEL_0"
19
+ },
20
+ "initializer_factor": 1.0,
21
+ "is_encoder_decoder": true,
22
+ "is_gated_act": false,
23
+ "label2id": {
24
+ "LABEL_0": 0
25
+ },
26
+ "layer_norm_epsilon": 1e-06,
27
+ "merge_layer_index": 9,
28
+ "merger_type": "mean",
29
+ "model_type": "t5",
30
+ "n_positions": 512,
31
+ "num_decoder_layers": 12,
32
+ "num_heads": 12,
33
+ "num_layers": 12,
34
+ "output_past": true,
35
+ "pad_token_id": 0,
36
+ "relative_attention_max_distance": 128,
37
+ "relative_attention_num_buckets": 32,
38
+ "task_specific_params": {
39
+ "summarization": {
40
+ "early_stopping": true,
41
+ "length_penalty": 2.0,
42
+ "max_length": 200,
43
+ "min_length": 30,
44
+ "no_repeat_ngram_size": 3,
45
+ "num_beams": 4,
46
+ "prefix": "summarize: "
47
+ },
48
+ "translation_en_to_de": {
49
+ "early_stopping": true,
50
+ "max_length": 300,
51
+ "num_beams": 4,
52
+ "prefix": "translate English to German: "
53
+ },
54
+ "translation_en_to_fr": {
55
+ "early_stopping": true,
56
+ "max_length": 300,
57
+ "num_beams": 4,
58
+ "prefix": "translate English to French: "
59
+ },
60
+ "translation_en_to_ro": {
61
+ "early_stopping": true,
62
+ "max_length": 300,
63
+ "num_beams": 4,
64
+ "prefix": "translate English to Romanian: "
65
+ }
66
+ },
67
+ "torch_dtype": "float32",
68
+ "transformers_version": "4.48.2",
69
+ "use_cache": true,
70
+ "vocab_size": 32100
71
+ }
events.out.tfevents.1751443199.gra5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b66af0dda2e38ac85cae26dc4536b9182b9e7b8b3a7a1237c890e9852a5be4ea
3
+ size 19660
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "decoder_start_token_id": 0,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.48.2"
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89859d51e260e2979a62892c7686223c907a674f23ccc17325eafc6f6b9acfdf
3
+ size 891558696
results.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "rouge1": 0.5769267303165843,
3
+ "rouge2": 0.5298746050039503,
4
+ "rougeL": 0.5749463752901323,
5
+ "rougeLsum": 0.5745935503166687,
6
+ "bleu": 0.4257360608521651,
7
+ "precision": [
8
+ 0.44335984979495036,
9
+ 0.4279360364374474,
10
+ 0.41927079716255766,
11
+ 0.4129827526218997
12
+ ],
13
+ "brevity_penalty": 1.0,
14
+ "length_ratio": 2.222161224444981,
15
+ "translation_length": 505975,
16
+ "reference_length": 227695
17
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e78e607d8228443c867ad75c31e3a7d0861f88a0d5aa4358225f9eea2153815
3
+ size 5496