Hugging Face's logo

fpadovani
/
cds_w_13

Text Generation
Transformers
Safetensors
gpt2
Generated from Trainer
text-generation-inference
Model card Files
xet
 Community
fpadovani commited on
Commit
1dd3741
·
verified ·
1 Parent(s): b691ca2

Training in progress, epoch 5, checkpoint

Browse files
Files changed (12) hide show
  1. checkpoint-2480/config.json +33 -0
  2. checkpoint-2480/generation_config.json +9 -0
  3. checkpoint-2480/model.safetensors +3 -0
  4. checkpoint-2480/optimizer.pt +3 -0
  5. checkpoint-2480/rng_state.pth +3 -0
  6. checkpoint-2480/scaler.pt +3 -0
  7. checkpoint-2480/scheduler.pt +3 -0
  8. checkpoint-2480/special_tokens_map.json +8 -0
  9. checkpoint-2480/tokenizer.json +0 -0
  10. checkpoint-2480/tokenizer_config.json +62 -0
  11. checkpoint-2480/trainer_state.json +116 -0
  12. checkpoint-2480/training_args.bin +3 -0
checkpoint-2480/config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPT2LMHeadModel"
5
+ ],
6
+ "attn_pdrop": 0.1,
7
+ "bos_token_id": 1,
8
+ "dtype": "float32",
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 2,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 768,
16
+ "n_head": 12,
17
+ "n_inner": null,
18
+ "n_layer": 12,
19
+ "n_positions": 1024,
20
+ "pad_token_id": 2,
21
+ "reorder_and_upcast_attn": false,
22
+ "resid_pdrop": 0.1,
23
+ "scale_attn_by_inverse_layer_idx": false,
24
+ "scale_attn_weights": true,
25
+ "summary_activation": null,
26
+ "summary_first_dropout": 0.1,
27
+ "summary_proj_to_labels": true,
28
+ "summary_type": "cls_index",
29
+ "summary_use_proj": true,
30
+ "transformers_version": "4.56.1",
31
+ "use_cache": true,
32
+ "vocab_size": 30000
33
+ }
checkpoint-2480/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": [
5
+ 2
6
+ ],
7
+ "pad_token_id": 2,
8
+ "transformers_version": "4.56.1"
9
+ }
checkpoint-2480/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:944d3edee08b1d697d30754de7f0bf8039d030fd77ed2f73a56ebf39dfa43e23
3
+ size 435544704
checkpoint-2480/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a21d395f44349e1e67362eb146f47ad8e89d88a1440cacecb3a49253767224c
3
+ size 871183627
checkpoint-2480/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d77e6928bbfeeca774532a5a408658caf1eacdbb54a136a14486a7b9ae7f3412
3
+ size 14709
checkpoint-2480/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f913ea45494c9e456c1e6176db6261a293d54cf8f5b66747ecf71e9e8f6ad3f9
3
+ size 1383
checkpoint-2480/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8487c445e8de19b7b204c85bd762f47f9954df396c8e94e7891a44fcdc56fa21
3
+ size 1465
checkpoint-2480/special_tokens_map.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "mask_token": "<mask>",
5
+ "pad_token": "</s>",
6
+ "sep_token": "<sep>",
7
+ "unk_token": "<unk>"
8
+ }
checkpoint-2480/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-2480/tokenizer_config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "<mask>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "5": {
44
+ "content": "<sep>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ }
51
+ },
52
+ "bos_token": "<s>",
53
+ "clean_up_tokenization_spaces": false,
54
+ "eos_token": "</s>",
55
+ "extra_special_tokens": {},
56
+ "mask_token": "<mask>",
57
+ "model_max_length": 1000000000000000019884624838656,
58
+ "pad_token": "</s>",
59
+ "sep_token": "<sep>",
60
+ "tokenizer_class": "PreTrainedTokenizerFast",
61
+ "unk_token": "<unk>"
62
+ }
checkpoint-2480/trainer_state.json ADDED
@@ -0,0 +1,116 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 2480,
3
+ "best_metric": 3.143359661102295,
4
+ "best_model_checkpoint": "/home/p318482/syntactic-bootstrapping/model_trained/cds_w_13/checkpoint-2480",
5
+ "epoch": 5.0,
6
+ "eval_steps": 500,
7
+ "global_step": 2480,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0020161290322580645,
14
+ "grad_norm": 30.076793670654297,
15
+ "learning_rate": 0.0,
16
+ "loss": 10.3404,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 1.0,
21
+ "grad_norm": 4.318020343780518,
22
+ "learning_rate": 9.900000000000001e-05,
23
+ "loss": 4.5857,
24
+ "step": 496
25
+ },
26
+ {
27
+ "epoch": 1.0,
28
+ "eval_loss": 3.524101972579956,
29
+ "eval_runtime": 43.6446,
30
+ "eval_samples_per_second": 729.46,
31
+ "eval_steps_per_second": 2.864,
32
+ "step": 496
33
+ },
34
+ {
35
+ "epoch": 2.0,
36
+ "grad_norm": 4.235888481140137,
37
+ "learning_rate": 9.477659574468086e-05,
38
+ "loss": 3.3228,
39
+ "step": 992
40
+ },
41
+ {
42
+ "epoch": 2.0,
43
+ "eval_loss": 3.3001248836517334,
44
+ "eval_runtime": 44.2288,
45
+ "eval_samples_per_second": 719.826,
46
+ "eval_steps_per_second": 2.826,
47
+ "step": 992
48
+ },
49
+ {
50
+ "epoch": 3.0,
51
+ "grad_norm": 4.020275115966797,
52
+ "learning_rate": 8.950000000000001e-05,
53
+ "loss": 3.1656,
54
+ "step": 1488
55
+ },
56
+ {
57
+ "epoch": 3.0,
58
+ "eval_loss": 3.2202703952789307,
59
+ "eval_runtime": 44.1563,
60
+ "eval_samples_per_second": 721.006,
61
+ "eval_steps_per_second": 2.831,
62
+ "step": 1488
63
+ },
64
+ {
65
+ "epoch": 4.0,
66
+ "grad_norm": 4.647115707397461,
67
+ "learning_rate": 8.422340425531914e-05,
68
+ "loss": 3.078,
69
+ "step": 1984
70
+ },
71
+ {
72
+ "epoch": 4.0,
73
+ "eval_loss": 3.1739180088043213,
74
+ "eval_runtime": 44.5914,
75
+ "eval_samples_per_second": 713.972,
76
+ "eval_steps_per_second": 2.803,
77
+ "step": 1984
78
+ },
79
+ {
80
+ "epoch": 5.0,
81
+ "grad_norm": 3.8257627487182617,
82
+ "learning_rate": 7.894680851063831e-05,
83
+ "loss": 3.0125,
84
+ "step": 2480
85
+ },
86
+ {
87
+ "epoch": 5.0,
88
+ "eval_loss": 3.143359661102295,
89
+ "eval_runtime": 43.8817,
90
+ "eval_samples_per_second": 725.518,
91
+ "eval_steps_per_second": 2.849,
92
+ "step": 2480
93
+ }
94
+ ],
95
+ "logging_steps": 500,
96
+ "max_steps": 9920,
97
+ "num_input_tokens_seen": 0,
98
+ "num_train_epochs": 20,
99
+ "save_steps": 500,
100
+ "stateful_callbacks": {
101
+ "TrainerControl": {
102
+ "args": {
103
+ "should_epoch_stop": false,
104
+ "should_evaluate": false,
105
+ "should_log": false,
106
+ "should_save": true,
107
+ "should_training_stop": false
108
+ },
109
+ "attributes": {}
110
+ }
111
+ },
112
+ "total_flos": 4.138996432896e+16,
113
+ "train_batch_size": 256,
114
+ "trial_name": null,
115
+ "trial_params": null
116
+ }
checkpoint-2480/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9ce9c5ddd61da8e500a622d9923d4f34a9d7d2dd637de93ee966a57021e3430
3
+ size 5905