Hugging Face's logo

tranhuyHoang
/
mini_VN_decoder

Safetensors
Model card Files
xet
 Community
tranhuyHoang commited on
Commit
20439af
·
verified ·
1 Parent(s): 760ac26

Training in progress, step 10, checkpoint

Browse files
Files changed (9) hide show
  1. last-checkpoint/model.safetensors +3 -0
  2. last-checkpoint/optimizer.pt +3 -0
  3. last-checkpoint/rng_state.pth +3 -0
  4. last-checkpoint/scheduler.pt +3 -0
  5. last-checkpoint/special_tokens_map.json +16 -0
  6. last-checkpoint/tokenizer.json +0 -0
  7. last-checkpoint/tokenizer_config.json +20 -0
  8. last-checkpoint/trainer_state.json +112 -0
  9. last-checkpoint/training_args.bin +3 -0
last-checkpoint/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:765f15b5e2400d065e8c16c1f6a97ba96003d00b0278e6a21327856d0acc93bb
3
+ size 91951912
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df09a8a9c398e5ad4037bb2fcefa35dba1d29159b7885bbae60b0d649011f021
3
+ size 183993547
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:098b29492211804ab324a36f37466821d948280bb74fce4ba895c03f13ecd878
3
+ size 14645
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2945fb27bbb3daaf7e310dd5d2effaf66a5c0ed185f3c15f7c55b829538fd755
3
+ size 1465
last-checkpoint/special_tokens_map.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "pad_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ }
16
+ }
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 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<|endoftext|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ }
11
+ },
12
+ "clean_up_tokenization_spaces": false,
13
+ "eos_token": "<|endoftext|>",
14
+ "extra_special_tokens": {},
15
+ "model_max_length": 2048,
16
+ "pad_token": "<|endoftext|>",
17
+ "padding_side": "right",
18
+ "tokenizer_class": "PreTrainedTokenizerFast",
19
+ "truncation_side": "right"
20
+ }
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.001,
6
+ "eval_steps": 10,
7
+ "global_step": 10,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0001,
14
+ "grad_norm": 13.644583702087402,
15
+ "learning_rate": 0.0,
16
+ "loss": 73.3569,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.0002,
21
+ "grad_norm": 13.757925987243652,
22
+ "learning_rate": 1e-05,
23
+ "loss": 73.384,
24
+ "step": 2
25
+ },
26
+ {
27
+ "epoch": 0.0003,
28
+ "grad_norm": 13.819925308227539,
29
+ "learning_rate": 2e-05,
30
+ "loss": 73.4764,
31
+ "step": 3
32
+ },
33
+ {
34
+ "epoch": 0.0004,
35
+ "grad_norm": 13.885299682617188,
36
+ "learning_rate": 3e-05,
37
+ "loss": 73.2476,
38
+ "step": 4
39
+ },
40
+ {
41
+ "epoch": 0.0005,
42
+ "grad_norm": 13.726334571838379,
43
+ "learning_rate": 4e-05,
44
+ "loss": 72.8724,
45
+ "step": 5
46
+ },
47
+ {
48
+ "epoch": 0.0006,
49
+ "grad_norm": 13.66053581237793,
50
+ "learning_rate": 5e-05,
51
+ "loss": 72.2172,
52
+ "step": 6
53
+ },
54
+ {
55
+ "epoch": 0.0007,
56
+ "grad_norm": 13.866334915161133,
57
+ "learning_rate": 6e-05,
58
+ "loss": 71.1639,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.0008,
63
+ "grad_norm": 13.102575302124023,
64
+ "learning_rate": 7.000000000000001e-05,
65
+ "loss": 70.3215,
66
+ "step": 8
67
+ },
68
+ {
69
+ "epoch": 0.0009,
70
+ "grad_norm": 13.716519355773926,
71
+ "learning_rate": 8e-05,
72
+ "loss": 67.5932,
73
+ "step": 9
74
+ },
75
+ {
76
+ "epoch": 0.001,
77
+ "grad_norm": 12.51129150390625,
78
+ "learning_rate": 8.999999999999999e-05,
79
+ "loss": 65.3889,
80
+ "step": 10
81
+ },
82
+ {
83
+ "epoch": 0.001,
84
+ "eval_loss": 7.900570869445801,
85
+ "eval_runtime": 680.8566,
86
+ "eval_samples_per_second": 14.687,
87
+ "eval_steps_per_second": 1.836,
88
+ "step": 10
89
+ }
90
+ ],
91
+ "logging_steps": 1,
92
+ "max_steps": 10000,
93
+ "num_input_tokens_seen": 0,
94
+ "num_train_epochs": 9223372036854775807,
95
+ "save_steps": 10,
96
+ "stateful_callbacks": {
97
+ "TrainerControl": {
98
+ "args": {
99
+ "should_epoch_stop": false,
100
+ "should_evaluate": false,
101
+ "should_log": false,
102
+ "should_save": true,
103
+ "should_training_stop": false
104
+ },
105
+ "attributes": {}
106
+ }
107
+ },
108
+ "total_flos": 0.0,
109
+ "train_batch_size": 8,
110
+ "trial_name": null,
111
+ "trial_params": null
112
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af02e602b37732e5013cd321602a51e5ba92ee6a737c53590897eaa51eee7722
3
+ size 5841