Hugging Face's logo

mootez
/
mean_codet5-base_L8_codetrans_123456_src_java_tgt_c_sharp

TensorBoard
Safetensors
t5
Model card Files
xet
Metrics Community
mootez commited on
Commit
29a69e3
·
verified ·
1 Parent(s): 024ff8a

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.1751361566.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": 8,
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 sha256:468264c93990212407372a1b5305f29e874beb0c940b3cc09c12bf20381ba29e
3
+ size 891558696
checkpoint-5148/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:951bc6f56a27b7421ac1da34f8df51a54b2344a8312bf04a26e7c77650fa68a2
3
+ size 1783272762
checkpoint-5148/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:443832ab8fc2947fb6e971ed71b7d65f66a64abe502cd5edabd1bb7eca823ce9
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": 0.18564115439705584,
3
+ "best_model_checkpoint": "./logs/mean_codet5-base_L8_codetrans_123456_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": 4.164821624755859,
14
+ "learning_rate": 7.77302759424796e-06,
15
+ "loss": 2.6251,
16
+ "step": 1000
17
+ },
18
+ {
19
+ "epoch": 0.777000777000777,
20
+ "grad_norm": 3.9001471996307373,
21
+ "learning_rate": 1.554605518849592e-05,
22
+ "loss": 0.5633,
23
+ "step": 2000
24
+ },
25
+ {
26
+ "epoch": 1.0,
27
+ "eval_bleu": 0.17981807429155244,
28
+ "eval_brevity_penalty": 0.2020400474390871,
29
+ "eval_length_ratio": 0.3847205396025016,
30
+ "eval_loss": 0.31051528453826904,
31
+ "eval_precision": [
32
+ 0.9388497627609098,
33
+ 0.8978709677419355,
34
+ 0.8722636464424687,
35
+ 0.8533471056217309
36
+ ],
37
+ "eval_reference_length": 122164,
38
+ "eval_rouge1": 0.5612033446415986,
39
+ "eval_rouge2": 0.4793728912955346,
40
+ "eval_rougeL": 0.5591190424714767,
41
+ "eval_rougeLsum": 0.5593696755167152,
42
+ "eval_runtime": 18.7638,
43
+ "eval_samples_per_second": 26.594,
44
+ "eval_steps_per_second": 1.705,
45
+ "eval_translation_length": 46999,
46
+ "step": 2574
47
+ },
48
+ {
49
+ "epoch": 1.1655011655011656,
50
+ "grad_norm": 4.018387317657471,
51
+ "learning_rate": 1.9631372210471794e-05,
52
+ "loss": 0.3854,
53
+ "step": 3000
54
+ },
55
+ {
56
+ "epoch": 1.554001554001554,
57
+ "grad_norm": 2.257948160171509,
58
+ "learning_rate": 1.8768075279492384e-05,
59
+ "loss": 0.3017,
60
+ "step": 4000
61
+ },
62
+ {
63
+ "epoch": 1.9425019425019425,
64
+ "grad_norm": 2.4279184341430664,
65
+ "learning_rate": 1.790477834851297e-05,
66
+ "loss": 0.2793,
67
+ "step": 5000
68
+ },
69
+ {
70
+ "epoch": 2.0,
71
+ "eval_bleu": 0.18564115439705584,
72
+ "eval_brevity_penalty": 0.20337074232564123,
73
+ "eval_length_ratio": 0.3856946399921417,
74
+ "eval_loss": 0.2206611931324005,
75
+ "eval_precision": [
76
+ 0.9460503416953181,
77
+ 0.9182307642806581,
78
+ 0.9004770164787511,
79
+ 0.8875737050919532
80
+ ],
81
+ "eval_reference_length": 122164,
82
+ "eval_rouge1": 0.581275173227071,
83
+ "eval_rouge2": 0.5152391835980499,
84
+ "eval_rougeL": 0.5800367813408477,
85
+ "eval_rougeLsum": 0.5798537106840013,
86
+ "eval_runtime": 18.6486,
87
+ "eval_samples_per_second": 26.758,
88
+ "eval_steps_per_second": 1.716,
89
+ "eval_translation_length": 47118,
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 sha256:4a908c353557ca43c8b5547815e9d01dc2fd24528b8388ecae1631d80ce4120c
3
+ size 5560
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": 8,
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.1751361566.gra5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5263b11ba99ec55d26be601464941e3dabb0734a5e060235fbaa6b67370c172
3
+ size 19672
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 sha256:468264c93990212407372a1b5305f29e874beb0c940b3cc09c12bf20381ba29e
3
+ size 891558696
results.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "rouge1": 0.5306965012391254,
3
+ "rouge2": 0.4822745197368338,
4
+ "rougeL": 0.5288135067297335,
5
+ "rougeLsum": 0.5289390187593817,
6
+ "bleu": 0.3910593719691461,
7
+ "precision": [
8
+ 0.4097480032014711,
9
+ 0.39331631801159267,
10
+ 0.38422497100178493,
11
+ 0.37768209517881246
12
+ ],
13
+ "brevity_penalty": 1.0,
14
+ "length_ratio": 2.397940227058126,
15
+ "translation_length": 545999,
16
+ "reference_length": 227695
17
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a908c353557ca43c8b5547815e9d01dc2fd24528b8388ecae1631d80ce4120c
3
+ size 5560