Commit
•
3161cb8
1
Parent(s):
7a259d0
Training in progress, epoch 1
Browse files- model.safetensors +1 -1
- run-2/checkpoint-8419/config.json +25 -0
- run-2/checkpoint-8419/model.safetensors +3 -0
- run-2/checkpoint-8419/optimizer.pt +3 -0
- run-2/checkpoint-8419/rng_state.pth +3 -0
- run-2/checkpoint-8419/scheduler.pt +3 -0
- run-2/checkpoint-8419/special_tokens_map.json +7 -0
- run-2/checkpoint-8419/tokenizer.json +0 -0
- run-2/checkpoint-8419/tokenizer_config.json +55 -0
- run-2/checkpoint-8419/trainer_state.json +147 -0
- run-2/checkpoint-8419/training_args.bin +3 -0
- run-2/checkpoint-8419/vocab.txt +0 -0
- runs/May14_13-42-22_d0b6fd4b0e89/events.out.tfevents.1715698909.d0b6fd4b0e89.396.4 +3 -0
- training_args.bin +1 -1
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 267832560
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf18a7465401fcc61cb71532b6caa2080bc8041bf5a7ab3bfff157decd0062ec
|
3 |
size 267832560
|
run-2/checkpoint-8419/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-uncased",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"DistilBertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"dim": 768,
|
9 |
+
"dropout": 0.1,
|
10 |
+
"hidden_dim": 3072,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"max_position_embeddings": 512,
|
13 |
+
"model_type": "distilbert",
|
14 |
+
"n_heads": 12,
|
15 |
+
"n_layers": 6,
|
16 |
+
"pad_token_id": 0,
|
17 |
+
"problem_type": "single_label_classification",
|
18 |
+
"qa_dropout": 0.1,
|
19 |
+
"seq_classif_dropout": 0.2,
|
20 |
+
"sinusoidal_pos_embds": false,
|
21 |
+
"tie_weights_": true,
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.40.2",
|
24 |
+
"vocab_size": 30522
|
25 |
+
}
|
run-2/checkpoint-8419/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf18a7465401fcc61cb71532b6caa2080bc8041bf5a7ab3bfff157decd0062ec
|
3 |
+
size 267832560
|
run-2/checkpoint-8419/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8951761772483cb1795f2c52dfd044499145a406e5d450adcc0089d3ed031041
|
3 |
+
size 535727290
|
run-2/checkpoint-8419/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:807b380840933ef50ee402581d24c86e698aaff9c3d4ad8fa8ae434ea153ff1a
|
3 |
+
size 14244
|
run-2/checkpoint-8419/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ae6d515b6233ed373310234fd585ffcefcfe34d802cc02c573ba24598f6de520
|
3 |
+
size 1064
|
run-2/checkpoint-8419/special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
run-2/checkpoint-8419/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-2/checkpoint-8419/tokenizer_config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_lower_case": true,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 512,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "DistilBertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
run-2/checkpoint-8419/trainer_state.json
ADDED
@@ -0,0 +1,147 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.8979357798165137,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-sst2/run-2/checkpoint-8419",
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 8419,
|
7 |
+
"is_hyper_param_search": true,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.05938947618482005,
|
13 |
+
"grad_norm": 6.959882736206055,
|
14 |
+
"learning_rate": 2.20446303880587e-06,
|
15 |
+
"loss": 0.5244,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.1187789523696401,
|
20 |
+
"grad_norm": 27.900440216064453,
|
21 |
+
"learning_rate": 2.1599410240462895e-06,
|
22 |
+
"loss": 0.3407,
|
23 |
+
"step": 1000
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.17816842855446016,
|
27 |
+
"grad_norm": 16.400848388671875,
|
28 |
+
"learning_rate": 2.115419009286709e-06,
|
29 |
+
"loss": 0.3444,
|
30 |
+
"step": 1500
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.2375579047392802,
|
34 |
+
"grad_norm": 16.666898727416992,
|
35 |
+
"learning_rate": 2.0708969945271283e-06,
|
36 |
+
"loss": 0.3153,
|
37 |
+
"step": 2000
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.2969473809241002,
|
41 |
+
"grad_norm": 22.084596633911133,
|
42 |
+
"learning_rate": 2.026374979767548e-06,
|
43 |
+
"loss": 0.3076,
|
44 |
+
"step": 2500
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.3563368571089203,
|
48 |
+
"grad_norm": 42.26548385620117,
|
49 |
+
"learning_rate": 1.9818529650079676e-06,
|
50 |
+
"loss": 0.3228,
|
51 |
+
"step": 3000
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.41572633329374037,
|
55 |
+
"grad_norm": 48.90976333618164,
|
56 |
+
"learning_rate": 1.937330950248387e-06,
|
57 |
+
"loss": 0.3099,
|
58 |
+
"step": 3500
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.4751158094785604,
|
62 |
+
"grad_norm": 23.298206329345703,
|
63 |
+
"learning_rate": 1.8928089354888066e-06,
|
64 |
+
"loss": 0.2982,
|
65 |
+
"step": 4000
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.5345052856633804,
|
69 |
+
"grad_norm": 31.678531646728516,
|
70 |
+
"learning_rate": 1.848286920729226e-06,
|
71 |
+
"loss": 0.3012,
|
72 |
+
"step": 4500
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.5938947618482004,
|
76 |
+
"grad_norm": 14.523043632507324,
|
77 |
+
"learning_rate": 1.8037649059696455e-06,
|
78 |
+
"loss": 0.3075,
|
79 |
+
"step": 5000
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.6532842380330206,
|
83 |
+
"grad_norm": 2.0264182090759277,
|
84 |
+
"learning_rate": 1.7592428912100647e-06,
|
85 |
+
"loss": 0.2902,
|
86 |
+
"step": 5500
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.7126737142178406,
|
90 |
+
"grad_norm": 1.4845110177993774,
|
91 |
+
"learning_rate": 1.7147208764504845e-06,
|
92 |
+
"loss": 0.2929,
|
93 |
+
"step": 6000
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.7720631904026607,
|
97 |
+
"grad_norm": 21.62343406677246,
|
98 |
+
"learning_rate": 1.6701988616909037e-06,
|
99 |
+
"loss": 0.3003,
|
100 |
+
"step": 6500
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.8314526665874807,
|
104 |
+
"grad_norm": 6.294283866882324,
|
105 |
+
"learning_rate": 1.6256768469313231e-06,
|
106 |
+
"loss": 0.2949,
|
107 |
+
"step": 7000
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.8908421427723008,
|
111 |
+
"grad_norm": 52.94987106323242,
|
112 |
+
"learning_rate": 1.5811548321717428e-06,
|
113 |
+
"loss": 0.2685,
|
114 |
+
"step": 7500
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.9502316189571208,
|
118 |
+
"grad_norm": 10.51728343963623,
|
119 |
+
"learning_rate": 1.5366328174121622e-06,
|
120 |
+
"loss": 0.299,
|
121 |
+
"step": 8000
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 1.0,
|
125 |
+
"eval_accuracy": 0.8979357798165137,
|
126 |
+
"eval_loss": 0.33407795429229736,
|
127 |
+
"eval_runtime": 1.2282,
|
128 |
+
"eval_samples_per_second": 709.994,
|
129 |
+
"eval_steps_per_second": 44.782,
|
130 |
+
"step": 8419
|
131 |
+
}
|
132 |
+
],
|
133 |
+
"logging_steps": 500,
|
134 |
+
"max_steps": 25257,
|
135 |
+
"num_input_tokens_seen": 0,
|
136 |
+
"num_train_epochs": 3,
|
137 |
+
"save_steps": 500,
|
138 |
+
"total_flos": 490274261244480.0,
|
139 |
+
"train_batch_size": 8,
|
140 |
+
"trial_name": null,
|
141 |
+
"trial_params": {
|
142 |
+
"learning_rate": 2.2489850535654507e-06,
|
143 |
+
"num_train_epochs": 3,
|
144 |
+
"per_device_train_batch_size": 8,
|
145 |
+
"seed": 11
|
146 |
+
}
|
147 |
+
}
|
run-2/checkpoint-8419/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6f28c54c631beb4aad19ce06fef9fbf9a411e80177ae39964fa9c31526a231b3
|
3 |
+
size 5048
|
run-2/checkpoint-8419/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
runs/May14_13-42-22_d0b6fd4b0e89/events.out.tfevents.1715698909.d0b6fd4b0e89.396.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b79ef833c1dbffa42afcd3532e667a85874d91099cb0c9cc1d7dfc82baf10add
|
3 |
+
size 8759
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5048
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6f28c54c631beb4aad19ce06fef9fbf9a411e80177ae39964fa9c31526a231b3
|
3 |
size 5048
|