Training in progress, epoch 4
Browse files- model.safetensors +1 -1
- run-4/checkpoint-8552/config.json +25 -0
- run-4/checkpoint-8552/model.safetensors +3 -0
- run-4/checkpoint-8552/optimizer.pt +3 -0
- run-4/checkpoint-8552/rng_state.pth +3 -0
- run-4/checkpoint-8552/scheduler.pt +3 -0
- run-4/checkpoint-8552/special_tokens_map.json +7 -0
- run-4/checkpoint-8552/tokenizer.json +0 -0
- run-4/checkpoint-8552/tokenizer_config.json +55 -0
- run-4/checkpoint-8552/trainer_state.json +181 -0
- run-4/checkpoint-8552/training_args.bin +3 -0
- run-4/checkpoint-8552/vocab.txt +0 -0
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:b9e13fe829399366b0a60237a76a6fa47f869f0a95e1bb37f876e7347a101714
|
3 |
size 267832560
|
run-4/checkpoint-8552/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": "4.38.2",
|
24 |
+
"vocab_size": 30522
|
25 |
+
}
|
run-4/checkpoint-8552/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b9e13fe829399366b0a60237a76a6fa47f869f0a95e1bb37f876e7347a101714
|
3 |
+
size 267832560
|
run-4/checkpoint-8552/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b192d2057bd5035eaf232aa7a1d2bec6e0c55e6d760b21c6a335170cd692897
|
3 |
+
size 535727290
|
run-4/checkpoint-8552/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b4f990838f8212b3aeb4fdec6f127ab912879aa5e4eddc343c62c6efda2318d0
|
3 |
+
size 14244
|
run-4/checkpoint-8552/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:417959ace7a96594aafc9ecc39cde9418e47efca00b10a012fea336e46c0da00
|
3 |
+
size 1064
|
run-4/checkpoint-8552/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-4/checkpoint-8552/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-4/checkpoint-8552/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-4/checkpoint-8552/trainer_state.json
ADDED
@@ -0,0 +1,181 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.4286063983911785,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-8552",
|
4 |
+
"epoch": 4.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 8552,
|
7 |
+
"is_hyper_param_search": true,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.23,
|
13 |
+
"grad_norm": 4.632926940917969,
|
14 |
+
"learning_rate": 1.2946011611760917e-06,
|
15 |
+
"loss": 0.6259,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.47,
|
20 |
+
"grad_norm": 5.080592155456543,
|
21 |
+
"learning_rate": 1.2310780423745168e-06,
|
22 |
+
"loss": 0.6096,
|
23 |
+
"step": 1000
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.7,
|
27 |
+
"grad_norm": 7.2639031410217285,
|
28 |
+
"learning_rate": 1.1675549235729423e-06,
|
29 |
+
"loss": 0.5698,
|
30 |
+
"step": 1500
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.94,
|
34 |
+
"grad_norm": 12.567307472229004,
|
35 |
+
"learning_rate": 1.1040318047713676e-06,
|
36 |
+
"loss": 0.5589,
|
37 |
+
"step": 2000
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 1.0,
|
41 |
+
"eval_loss": 0.5995281934738159,
|
42 |
+
"eval_matthews_correlation": 0.08036809130702588,
|
43 |
+
"eval_runtime": 0.3414,
|
44 |
+
"eval_samples_per_second": 3055.256,
|
45 |
+
"eval_steps_per_second": 193.334,
|
46 |
+
"step": 2138
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"epoch": 1.17,
|
50 |
+
"grad_norm": 15.908562660217285,
|
51 |
+
"learning_rate": 1.0405086859697929e-06,
|
52 |
+
"loss": 0.5387,
|
53 |
+
"step": 2500
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 1.4,
|
57 |
+
"grad_norm": 11.577272415161133,
|
58 |
+
"learning_rate": 9.769855671682182e-07,
|
59 |
+
"loss": 0.5105,
|
60 |
+
"step": 3000
|
61 |
+
},
|
62 |
+
{
|
63 |
+
"epoch": 1.64,
|
64 |
+
"grad_norm": 36.38253402709961,
|
65 |
+
"learning_rate": 9.134624483666437e-07,
|
66 |
+
"loss": 0.5256,
|
67 |
+
"step": 3500
|
68 |
+
},
|
69 |
+
{
|
70 |
+
"epoch": 1.87,
|
71 |
+
"grad_norm": 11.872018814086914,
|
72 |
+
"learning_rate": 8.499393295650689e-07,
|
73 |
+
"loss": 0.511,
|
74 |
+
"step": 4000
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 2.0,
|
78 |
+
"eval_loss": 0.5569708347320557,
|
79 |
+
"eval_matthews_correlation": 0.39137710349170013,
|
80 |
+
"eval_runtime": 0.5165,
|
81 |
+
"eval_samples_per_second": 2019.532,
|
82 |
+
"eval_steps_per_second": 127.794,
|
83 |
+
"step": 4276
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 2.1,
|
87 |
+
"grad_norm": 20.970304489135742,
|
88 |
+
"learning_rate": 7.864162107634943e-07,
|
89 |
+
"loss": 0.475,
|
90 |
+
"step": 4500
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"epoch": 2.34,
|
94 |
+
"grad_norm": 9.216538429260254,
|
95 |
+
"learning_rate": 7.228930919619195e-07,
|
96 |
+
"loss": 0.4814,
|
97 |
+
"step": 5000
|
98 |
+
},
|
99 |
+
{
|
100 |
+
"epoch": 2.57,
|
101 |
+
"grad_norm": 19.621673583984375,
|
102 |
+
"learning_rate": 6.593699731603449e-07,
|
103 |
+
"loss": 0.4871,
|
104 |
+
"step": 5500
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 2.81,
|
108 |
+
"grad_norm": 19.49756622314453,
|
109 |
+
"learning_rate": 5.958468543587703e-07,
|
110 |
+
"loss": 0.4675,
|
111 |
+
"step": 6000
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 3.0,
|
115 |
+
"eval_loss": 0.5788199305534363,
|
116 |
+
"eval_matthews_correlation": 0.39891405791978285,
|
117 |
+
"eval_runtime": 0.3422,
|
118 |
+
"eval_samples_per_second": 3047.878,
|
119 |
+
"eval_steps_per_second": 192.867,
|
120 |
+
"step": 6414
|
121 |
+
},
|
122 |
+
{
|
123 |
+
"epoch": 3.04,
|
124 |
+
"grad_norm": 49.59273910522461,
|
125 |
+
"learning_rate": 5.323237355571956e-07,
|
126 |
+
"loss": 0.5038,
|
127 |
+
"step": 6500
|
128 |
+
},
|
129 |
+
{
|
130 |
+
"epoch": 3.27,
|
131 |
+
"grad_norm": 34.72640609741211,
|
132 |
+
"learning_rate": 4.6880061675562097e-07,
|
133 |
+
"loss": 0.4434,
|
134 |
+
"step": 7000
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 3.51,
|
138 |
+
"grad_norm": 55.005916595458984,
|
139 |
+
"learning_rate": 4.052774979540463e-07,
|
140 |
+
"loss": 0.4816,
|
141 |
+
"step": 7500
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 3.74,
|
145 |
+
"grad_norm": 79.78916931152344,
|
146 |
+
"learning_rate": 3.417543791524717e-07,
|
147 |
+
"loss": 0.4923,
|
148 |
+
"step": 8000
|
149 |
+
},
|
150 |
+
{
|
151 |
+
"epoch": 3.98,
|
152 |
+
"grad_norm": 49.529483795166016,
|
153 |
+
"learning_rate": 2.78231260350897e-07,
|
154 |
+
"loss": 0.4698,
|
155 |
+
"step": 8500
|
156 |
+
},
|
157 |
+
{
|
158 |
+
"epoch": 4.0,
|
159 |
+
"eval_loss": 0.6026819944381714,
|
160 |
+
"eval_matthews_correlation": 0.4286063983911785,
|
161 |
+
"eval_runtime": 0.3402,
|
162 |
+
"eval_samples_per_second": 3065.812,
|
163 |
+
"eval_steps_per_second": 194.002,
|
164 |
+
"step": 8552
|
165 |
+
}
|
166 |
+
],
|
167 |
+
"logging_steps": 500,
|
168 |
+
"max_steps": 10690,
|
169 |
+
"num_input_tokens_seen": 0,
|
170 |
+
"num_train_epochs": 5,
|
171 |
+
"save_steps": 500,
|
172 |
+
"total_flos": 138507342838860.0,
|
173 |
+
"train_batch_size": 4,
|
174 |
+
"trial_name": null,
|
175 |
+
"trial_params": {
|
176 |
+
"learning_rate": 1.3581242799776662e-06,
|
177 |
+
"num_train_epochs": 5,
|
178 |
+
"per_device_train_batch_size": 4,
|
179 |
+
"seed": 5
|
180 |
+
}
|
181 |
+
}
|
run-4/checkpoint-8552/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e09d686d744a0008ff792f3863883364cd703287c8e9332ee8d8209d508c0a5d
|
3 |
+
size 4984
|
run-4/checkpoint-8552/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|