fpadovani commited on
Commit
57ed7e6
1 Parent(s): c2ba1e7

Training in progress, step 6000, checkpoint

Browse files
checkpoint-6000/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 5,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 4,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 128,
15
+ "n_embd": 128,
16
+ "n_head": 4,
17
+ "n_inner": null,
18
+ "n_layer": 4,
19
+ "n_positions": 128,
20
+ "reorder_and_upcast_attn": false,
21
+ "resid_pdrop": 0.1,
22
+ "scale_attn_by_inverse_layer_idx": false,
23
+ "scale_attn_weights": true,
24
+ "summary_activation": null,
25
+ "summary_first_dropout": 0.1,
26
+ "summary_proj_to_labels": true,
27
+ "summary_type": "cls_index",
28
+ "summary_use_proj": true,
29
+ "task_specific_params": {
30
+ "text-generation": {
31
+ "do_sample": true,
32
+ "max_length": 50
33
+ }
34
+ },
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.45.2",
37
+ "use_cache": true,
38
+ "vocab_size": 8192
39
+ }
checkpoint-6000/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 5,
4
+ "eos_token_id": 4,
5
+ "transformers_version": "4.45.2"
6
+ }
checkpoint-6000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8a2192f0420d342db518bf7f8d2be5b5987af8ade36fb9edfb7a7fd9294e8be
3
+ size 7438256
checkpoint-6000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b952350cb93c932b5a7341a067806de212244a034b77123208b7ffd1f5bf23b
3
+ size 14908602
checkpoint-6000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:121dcbb2d59715b0a9c59833d08182ee0f57f7fdc9fc249155235de874b27dac
3
+ size 13990
checkpoint-6000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89d74f096518ba83815dd1274e414bc1476cc60aea1f7ffaab887eca6f636c10
3
+ size 1192
checkpoint-6000/special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "[BOS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "[EOS]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "[EOS]"
17
+ }
checkpoint-6000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-6000/tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[UNK]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[CLS]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[SEP]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[PAD]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[EOS]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "5": {
44
+ "content": "[BOS]",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ }
51
+ },
52
+ "bos_token": "[BOS]",
53
+ "clean_up_tokenization_spaces": true,
54
+ "eos_token": "[EOS]",
55
+ "model_max_length": 1000000000000000019884624838656,
56
+ "pad_token": "[EOS]",
57
+ "tokenizer_class": "PreTrainedTokenizerFast"
58
+ }
checkpoint-6000/trainer_state.json ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 3.872448444366455,
3
+ "best_model_checkpoint": "/Users/frapadovani/Desktop/babyLM_controlled/models_trained/reduce_on_plateau_convergence/age_random/checkpoint-6000",
4
+ "epoch": 0.03174922346690937,
5
+ "eval_steps": 2000,
6
+ "global_step": 6000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.010583074488969791,
13
+ "grad_norm": 1.3282362222671509,
14
+ "learning_rate": 0.0001,
15
+ "loss": 4.8574,
16
+ "step": 2000
17
+ },
18
+ {
19
+ "epoch": 0.010583074488969791,
20
+ "eval_loss": 4.1984477043151855,
21
+ "eval_runtime": 2.3492,
22
+ "eval_samples_per_second": 744.941,
23
+ "eval_steps_per_second": 46.825,
24
+ "step": 2000
25
+ },
26
+ {
27
+ "epoch": 0.021166148977939583,
28
+ "grad_norm": 1.406479835510254,
29
+ "learning_rate": 0.0001,
30
+ "loss": 4.145,
31
+ "step": 4000
32
+ },
33
+ {
34
+ "epoch": 0.021166148977939583,
35
+ "eval_loss": 3.9832916259765625,
36
+ "eval_runtime": 2.1928,
37
+ "eval_samples_per_second": 798.069,
38
+ "eval_steps_per_second": 50.164,
39
+ "step": 4000
40
+ },
41
+ {
42
+ "epoch": 0.03174922346690937,
43
+ "grad_norm": 1.4979146718978882,
44
+ "learning_rate": 0.0001,
45
+ "loss": 3.9948,
46
+ "step": 6000
47
+ },
48
+ {
49
+ "epoch": 0.03174922346690937,
50
+ "eval_loss": 3.872448444366455,
51
+ "eval_runtime": 2.0908,
52
+ "eval_samples_per_second": 837.0,
53
+ "eval_steps_per_second": 52.611,
54
+ "step": 6000
55
+ }
56
+ ],
57
+ "logging_steps": 2000,
58
+ "max_steps": 188981,
59
+ "num_input_tokens_seen": 0,
60
+ "num_train_epochs": 1,
61
+ "save_steps": 2000,
62
+ "stateful_callbacks": {
63
+ "EarlyStoppingCallback": {
64
+ "args": {
65
+ "early_stopping_patience": 3,
66
+ "early_stopping_threshold": 0.001
67
+ },
68
+ "attributes": {
69
+ "early_stopping_patience_counter": 0
70
+ }
71
+ },
72
+ "TrainerControl": {
73
+ "args": {
74
+ "should_epoch_stop": false,
75
+ "should_evaluate": false,
76
+ "should_log": false,
77
+ "should_save": true,
78
+ "should_training_stop": false
79
+ },
80
+ "attributes": {}
81
+ }
82
+ },
83
+ "total_flos": 58491666432000.0,
84
+ "train_batch_size": 16,
85
+ "trial_name": null,
86
+ "trial_params": null
87
+ }
checkpoint-6000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c0a2b1811aeefb927284bf3c5c8de0a89d0ad3fd57a0b61184713eb6f012eba
3
+ size 5432