Hugging Face's logo

mootez
/
mean_codet5-base_L11_codetrans_42_src_java_tgt_c_sharp

TensorBoard
Safetensors
t5
Model card Files
xet
Metrics Community
mootez commited on
Commit
f781408
·
verified ·
1 Parent(s): 994879e

Upload folder using huggingface_hub

Browse files
Files changed (14) hide show
  1. checkpoint-5148/config.json +71 -0
  2. checkpoint-5148/generation_config.json +7 -0
  3. checkpoint-5148/model.safetensors +3 -0
  4. checkpoint-5148/optimizer.pt +3 -0
  5. checkpoint-5148/rng_state.pth +3 -0
  6. checkpoint-5148/scheduler.pt +3 -0
  7. checkpoint-5148/trainer_state.json +114 -0
  8. checkpoint-5148/training_args.bin +3 -0
  9. config.json +71 -0
  10. events.out.tfevents.1751324739.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-5148/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": 11,
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-5148/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-5148/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87471021ce6416557b649e94653dffc5cbbf21944bf45abfe1c06e305e2117ac
3
+ size 891558696
checkpoint-5148/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a538e1d273eaaf0c2ad02ee258719b6b2bbf311cbb9b0c94ac8023cdb0b11014
3
+ size 1783272762
checkpoint-5148/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9822060092967fdb7fa79aea5a2b17f4467e4c16300dfb52b107bdc0cb47a536
3
+ size 14308
checkpoint-5148/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74c38027dae9aff34b613557d259d8e3c873f7fd5b38678905a4c638a689330f
3
+ size 1064
checkpoint-5148/trainer_state.json ADDED
@@ -0,0 +1,114 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.18575827524928773,
3
+ "best_model_checkpoint": "./logs/mean_codet5-base_L11_codetrans_42_src_java_tgt_c_sharp/checkpoint-5148",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 5148,
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": 4.101528644561768,
14
+ "learning_rate": 7.77302759424796e-06,
15
+ "loss": 2.6003,
16
+ "step": 1000
17
+ },
18
+ {
19
+ "epoch": 0.777000777000777,
20
+ "grad_norm": 2.1514732837677,
21
+ "learning_rate": 1.554605518849592e-05,
22
+ "loss": 0.5467,
23
+ "step": 2000
24
+ },
25
+ {
26
+ "epoch": 1.0,
27
+ "eval_bleu": 0.18102765933374182,
28
+ "eval_brevity_penalty": 0.2011912461308713,
29
+ "eval_length_ratio": 0.38409842506794145,
30
+ "eval_loss": 0.29566365480422974,
31
+ "eval_precision": [
32
+ 0.9451228608571489,
33
+ 0.9066431156298467,
34
+ 0.883440391943386,
35
+ 0.8658477523885
36
+ ],
37
+ "eval_reference_length": 122164,
38
+ "eval_rouge1": 0.5684296785400118,
39
+ "eval_rouge2": 0.4877804308232041,
40
+ "eval_rougeL": 0.5671099971235423,
41
+ "eval_rougeLsum": 0.567095198129186,
42
+ "eval_runtime": 18.8278,
43
+ "eval_samples_per_second": 26.503,
44
+ "eval_steps_per_second": 1.7,
45
+ "eval_translation_length": 46923,
46
+ "step": 2574
47
+ },
48
+ {
49
+ "epoch": 1.1655011655011656,
50
+ "grad_norm": 1.4453285932540894,
51
+ "learning_rate": 1.9631372210471794e-05,
52
+ "loss": 0.3833,
53
+ "step": 3000
54
+ },
55
+ {
56
+ "epoch": 1.554001554001554,
57
+ "grad_norm": 3.5946884155273438,
58
+ "learning_rate": 1.8768075279492384e-05,
59
+ "loss": 0.3124,
60
+ "step": 4000
61
+ },
62
+ {
63
+ "epoch": 1.9425019425019425,
64
+ "grad_norm": 0.901043713092804,
65
+ "learning_rate": 1.790477834851297e-05,
66
+ "loss": 0.2582,
67
+ "step": 5000
68
+ },
69
+ {
70
+ "epoch": 2.0,
71
+ "eval_bleu": 0.18575827524928773,
72
+ "eval_brevity_penalty": 0.20221884752764246,
73
+ "eval_length_ratio": 0.38485151108346155,
74
+ "eval_loss": 0.21092140674591064,
75
+ "eval_precision": [
76
+ 0.9476550037222163,
77
+ 0.9229297446040072,
78
+ 0.9078818697437904,
79
+ 0.8967221758425238
80
+ ],
81
+ "eval_reference_length": 122164,
82
+ "eval_rouge1": 0.5911003200848799,
83
+ "eval_rouge2": 0.5270202608599297,
84
+ "eval_rougeL": 0.5887967110217545,
85
+ "eval_rougeLsum": 0.5895862279185209,
86
+ "eval_runtime": 18.8067,
87
+ "eval_samples_per_second": 26.533,
88
+ "eval_steps_per_second": 1.702,
89
+ "eval_translation_length": 47015,
90
+ "step": 5148
91
+ }
92
+ ],
93
+ "logging_steps": 1000,
94
+ "max_steps": 25740,
95
+ "num_input_tokens_seen": 0,
96
+ "num_train_epochs": 10,
97
+ "save_steps": 500,
98
+ "stateful_callbacks": {
99
+ "TrainerControl": {
100
+ "args": {
101
+ "should_epoch_stop": false,
102
+ "should_evaluate": false,
103
+ "should_log": false,
104
+ "should_save": true,
105
+ "should_training_stop": false
106
+ },
107
+ "attributes": {}
108
+ }
109
+ },
110
+ "total_flos": 6244732336896000.0,
111
+ "train_batch_size": 4,
112
+ "trial_name": null,
113
+ "trial_params": null
114
+ }
checkpoint-5148/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad27600469bef45de1771dcda74375b5f7cb99868dc7cbc546a1d2b75e63f260
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": 11,
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.1751324739.gra5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36d7601ff10663834b5e3791597d07a1063e947612225db294659186440683c3
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 sha256:87471021ce6416557b649e94653dffc5cbbf21944bf45abfe1c06e305e2117ac
3
+ size 891558696
results.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "rouge1": 0.5465833629194188,
3
+ "rouge2": 0.49807214862706517,
4
+ "rougeL": 0.545218530050968,
5
+ "rougeLsum": 0.5455025887330834,
6
+ "bleu": 0.40365073070508345,
7
+ "precision": [
8
+ 0.42279922663283187,
9
+ 0.40593834652461447,
10
+ 0.39662871091973195,
11
+ 0.38998199881511186
12
+ ],
13
+ "brevity_penalty": 1.0,
14
+ "length_ratio": 2.326058982410681,
15
+ "translation_length": 529632,
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:ad27600469bef45de1771dcda74375b5f7cb99868dc7cbc546a1d2b75e63f260
3
+ size 5496