Hugging Face's logo

CodeIsAbstract
/
HybridTimeScaleModel

Transformers
Safetensors
hybrid_fourier_lm
Generated from Trainer
Model card Files
xet
 Community
CodeIsAbstract commited on
Commit
76153aa
·
verified ·
1 Parent(s): 3e4e4c3

Training in progress, step 400, checkpoint

Browse files
Files changed (10) hide show
  1. last-checkpoint/config.json +33 -0
  2. last-checkpoint/generation_config.json +9 -0
  3. last-checkpoint/model.safetensors +3 -0
  4. last-checkpoint/optimizer.pt +3 -0
  5. last-checkpoint/rng_state.pth +3 -0
  6. last-checkpoint/scheduler.pt +3 -0
  7. last-checkpoint/tokenizer.json +0 -0
  8. last-checkpoint/tokenizer_config.json +17 -0
  9. last-checkpoint/trainer_state.json +94 -0
  10. last-checkpoint/training_args.bin +3 -0
last-checkpoint/config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "HybridFourierLM"
4
+ ],
5
+ "bos_token_id": 1,
6
+ "dropout": 0.05,
7
+ "dtype": "float32",
8
+ "eos_token_id": 2,
9
+ "latent_dim": 768,
10
+ "layer_types": [
11
+ "linear",
12
+ "linear",
13
+ "linear",
14
+ "softmax",
15
+ "linear",
16
+ "linear",
17
+ "linear",
18
+ "softmax",
19
+ "linear",
20
+ "linear",
21
+ "linear",
22
+ "softmax"
23
+ ],
24
+ "model_type": "hybrid_fourier_lm",
25
+ "num_layers": 12,
26
+ "num_modes": 64,
27
+ "pad_token_id": 2,
28
+ "tie_word_embeddings": true,
29
+ "time_scale": 128.0,
30
+ "transformers_version": "5.13.1",
31
+ "use_cache": false,
32
+ "vocab_size": 32768
33
+ }
last-checkpoint/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "output_attentions": false,
6
+ "output_hidden_states": false,
7
+ "pad_token_id": 2,
8
+ "transformers_version": "5.13.1"
9
+ }
last-checkpoint/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4570a7676418e7c1dbde619776b27e38071294b6d1f599604c28b8750b0802b3
3
+ size 469337272
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd703a45f50dc2abb2a4f115433253cdb847e4eda86120375a82fd5c964707f3
3
+ size 938825803
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:891bb229e9f5406f30ec3d01b02fe5fa385184e516d5ba6cefbcc26ed8f82302
3
+ size 14645
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1df8bb9e7a99af13686c1e59df1dfb5127b155b3d22f582bbd03a82455d5ded8
3
+ size 1465
last-checkpoint/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/tokenizer_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<s>",
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "</s>",
7
+ "is_local": false,
8
+ "legacy": false,
9
+ "local_files_only": false,
10
+ "model_max_length": 1000000000,
11
+ "pad_token": "</s>",
12
+ "sp_model_kwargs": {},
13
+ "spaces_between_special_tokens": false,
14
+ "tokenizer_class": "TokenizersBackend",
15
+ "unk_token": "<unk>",
16
+ "use_default_system_prompt": false
17
+ }
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,94 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.003125,
6
+ "eval_steps": 100,
7
+ "global_step": 400,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.00078125,
14
+ "grad_norm": 0.548005223274231,
15
+ "learning_rate": 0.00066,
16
+ "loss": 7.392943725585938,
17
+ "step": 100
18
+ },
19
+ {
20
+ "epoch": 0.00078125,
21
+ "eval_loss": 6.319089889526367,
22
+ "eval_runtime": 7.0241,
23
+ "eval_samples_per_second": 82.003,
24
+ "eval_steps_per_second": 20.501,
25
+ "step": 100
26
+ },
27
+ {
28
+ "epoch": 0.0015625,
29
+ "grad_norm": 0.6282612085342407,
30
+ "learning_rate": 0.0009999996375647776,
31
+ "loss": 5.802936401367187,
32
+ "step": 200
33
+ },
34
+ {
35
+ "epoch": 0.0015625,
36
+ "eval_loss": 5.66627836227417,
37
+ "eval_runtime": 6.87,
38
+ "eval_samples_per_second": 83.843,
39
+ "eval_steps_per_second": 20.961,
40
+ "step": 200
41
+ },
42
+ {
43
+ "epoch": 0.00234375,
44
+ "grad_norm": 0.39866289496421814,
45
+ "learning_rate": 0.0009999966487228837,
46
+ "loss": 5.2531396484375,
47
+ "step": 300
48
+ },
49
+ {
50
+ "epoch": 0.00234375,
51
+ "eval_loss": 5.31585693359375,
52
+ "eval_runtime": 6.8076,
53
+ "eval_samples_per_second": 84.612,
54
+ "eval_steps_per_second": 21.153,
55
+ "step": 300
56
+ },
57
+ {
58
+ "epoch": 0.003125,
59
+ "grad_norm": 0.4630204141139984,
60
+ "learning_rate": 0.0009999906408667911,
61
+ "loss": 4.958253784179687,
62
+ "step": 400
63
+ },
64
+ {
65
+ "epoch": 0.003125,
66
+ "eval_loss": 5.078152179718018,
67
+ "eval_runtime": 6.8409,
68
+ "eval_samples_per_second": 84.2,
69
+ "eval_steps_per_second": 21.05,
70
+ "step": 400
71
+ }
72
+ ],
73
+ "logging_steps": 100,
74
+ "max_steps": 128000,
75
+ "num_input_tokens_seen": 0,
76
+ "num_train_epochs": 9223372036854775807,
77
+ "save_steps": 400,
78
+ "stateful_callbacks": {
79
+ "TrainerControl": {
80
+ "args": {
81
+ "should_epoch_stop": false,
82
+ "should_evaluate": false,
83
+ "should_log": false,
84
+ "should_save": true,
85
+ "should_training_stop": false
86
+ },
87
+ "attributes": {}
88
+ }
89
+ },
90
+ "total_flos": 9965832398438400.0,
91
+ "train_batch_size": 22,
92
+ "trial_name": null,
93
+ "trial_params": null
94
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3b71add29216572affacbd140d488514e006cd0cdd1bd77cb7bc84501d9c04c
3
+ size 5201