Training in progress, epoch 1
Browse files- model.safetensors +1 -1
- run-3/checkpoint-4276/model.safetensors +1 -1
- run-3/checkpoint-4276/optimizer.pt +1 -1
- run-3/checkpoint-4276/rng_state.pth +1 -1
- run-3/checkpoint-4276/scheduler.pt +1 -1
- run-3/checkpoint-4276/trainer_state.json +30 -30
- run-3/checkpoint-4276/training_args.bin +1 -1
- run-4/checkpoint-268/config.json +25 -0
- run-4/checkpoint-268/model.safetensors +3 -0
- run-4/checkpoint-268/optimizer.pt +3 -0
- run-4/checkpoint-268/rng_state.pth +3 -0
- run-4/checkpoint-268/scheduler.pt +3 -0
- run-4/checkpoint-268/special_tokens_map.json +7 -0
- run-4/checkpoint-268/tokenizer.json +0 -0
- run-4/checkpoint-268/tokenizer_config.json +55 -0
- run-4/checkpoint-268/trainer_state.json +35 -0
- run-4/checkpoint-268/training_args.bin +3 -0
- run-4/checkpoint-268/vocab.txt +0 -0
- runs/Dec23_01-09-39_cab176ec49ea/events.out.tfevents.1703294598.cab176ec49ea.681.5 +2 -2
- runs/Dec23_01-09-39_cab176ec49ea/events.out.tfevents.1703294819.cab176ec49ea.681.6 +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:adf4873f03711bcd1e5aac7f2cccc8c1e3507a2ce13e9346f72877865b9aa266
|
3 |
size 267832560
|
run-3/checkpoint-4276/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 sha256:9b79ac969e55af980c6ecffec584fca548259b204d7dd280677b4565c71b275f
|
3 |
size 267832560
|
run-3/checkpoint-4276/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 535727290
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:df469924aa7f005d2bd0d92593b898e648585bd1333307e56c541f1bf7e85b37
|
3 |
size 535727290
|
run-3/checkpoint-4276/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2f50295e8a0c4f0f933e09f97afc25144ae22817ebc0c489063f461ce78b8860
|
3 |
size 14244
|
run-3/checkpoint-4276/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:73c5117f48e54404543986abbdd101f260b16cc1231e96c07ee8bf4f093b84d7
|
3 |
size 1064
|
run-3/checkpoint-4276/trainer_state.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-4276",
|
4 |
"epoch": 2.0,
|
5 |
"eval_steps": 500,
|
@@ -10,68 +10,68 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.23,
|
13 |
-
"learning_rate":
|
14 |
-
"loss": 0.
|
15 |
"step": 500
|
16 |
},
|
17 |
{
|
18 |
"epoch": 0.47,
|
19 |
-
"learning_rate": 1.
|
20 |
-
"loss": 0.
|
21 |
"step": 1000
|
22 |
},
|
23 |
{
|
24 |
"epoch": 0.7,
|
25 |
-
"learning_rate":
|
26 |
-
"loss": 0.
|
27 |
"step": 1500
|
28 |
},
|
29 |
{
|
30 |
"epoch": 0.94,
|
31 |
-
"learning_rate":
|
32 |
-
"loss": 0.
|
33 |
"step": 2000
|
34 |
},
|
35 |
{
|
36 |
"epoch": 1.0,
|
37 |
-
"eval_loss": 0.
|
38 |
-
"eval_matthews_correlation": 0.
|
39 |
-
"eval_runtime": 0.
|
40 |
-
"eval_samples_per_second":
|
41 |
-
"eval_steps_per_second":
|
42 |
"step": 2138
|
43 |
},
|
44 |
{
|
45 |
"epoch": 1.17,
|
46 |
-
"learning_rate":
|
47 |
-
"loss": 0.
|
48 |
"step": 2500
|
49 |
},
|
50 |
{
|
51 |
"epoch": 1.4,
|
52 |
-
"learning_rate":
|
53 |
-
"loss": 0.
|
54 |
"step": 3000
|
55 |
},
|
56 |
{
|
57 |
"epoch": 1.64,
|
58 |
-
"learning_rate":
|
59 |
-
"loss": 0.
|
60 |
"step": 3500
|
61 |
},
|
62 |
{
|
63 |
"epoch": 1.87,
|
64 |
-
"learning_rate":
|
65 |
-
"loss": 0.
|
66 |
"step": 4000
|
67 |
},
|
68 |
{
|
69 |
"epoch": 2.0,
|
70 |
-
"eval_loss": 0.
|
71 |
-
"eval_matthews_correlation": 0.
|
72 |
-
"eval_runtime": 0.
|
73 |
-
"eval_samples_per_second":
|
74 |
-
"eval_steps_per_second":
|
75 |
"step": 4276
|
76 |
}
|
77 |
],
|
@@ -80,13 +80,13 @@
|
|
80 |
"num_input_tokens_seen": 0,
|
81 |
"num_train_epochs": 2,
|
82 |
"save_steps": 500,
|
83 |
-
"total_flos":
|
84 |
"train_batch_size": 4,
|
85 |
"trial_name": null,
|
86 |
"trial_params": {
|
87 |
-
"learning_rate":
|
88 |
"num_train_epochs": 2,
|
89 |
"per_device_train_batch_size": 4,
|
90 |
-
"seed":
|
91 |
}
|
92 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.27657164760495423,
|
3 |
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-4276",
|
4 |
"epoch": 2.0,
|
5 |
"eval_steps": 500,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.23,
|
13 |
+
"learning_rate": 1.3504098486610872e-06,
|
14 |
+
"loss": 0.6235,
|
15 |
"step": 500
|
16 |
},
|
17 |
{
|
18 |
"epoch": 0.47,
|
19 |
+
"learning_rate": 1.1715949852260916e-06,
|
20 |
+
"loss": 0.6084,
|
21 |
"step": 1000
|
22 |
},
|
23 |
{
|
24 |
"epoch": 0.7,
|
25 |
+
"learning_rate": 9.92780121791096e-07,
|
26 |
+
"loss": 0.5687,
|
27 |
"step": 1500
|
28 |
},
|
29 |
{
|
30 |
"epoch": 0.94,
|
31 |
+
"learning_rate": 8.139652583561002e-07,
|
32 |
+
"loss": 0.5599,
|
33 |
"step": 2000
|
34 |
},
|
35 |
{
|
36 |
"epoch": 1.0,
|
37 |
+
"eval_loss": 0.5971149802207947,
|
38 |
+
"eval_matthews_correlation": 0.0463559874942472,
|
39 |
+
"eval_runtime": 0.7351,
|
40 |
+
"eval_samples_per_second": 1418.884,
|
41 |
+
"eval_steps_per_second": 89.786,
|
42 |
"step": 2138
|
43 |
},
|
44 |
{
|
45 |
"epoch": 1.17,
|
46 |
+
"learning_rate": 6.351503949211046e-07,
|
47 |
+
"loss": 0.5449,
|
48 |
"step": 2500
|
49 |
},
|
50 |
{
|
51 |
"epoch": 1.4,
|
52 |
+
"learning_rate": 4.563355314861089e-07,
|
53 |
+
"loss": 0.5175,
|
54 |
"step": 3000
|
55 |
},
|
56 |
{
|
57 |
"epoch": 1.64,
|
58 |
+
"learning_rate": 2.7752066805111325e-07,
|
59 |
+
"loss": 0.535,
|
60 |
"step": 3500
|
61 |
},
|
62 |
{
|
63 |
"epoch": 1.87,
|
64 |
+
"learning_rate": 9.870580461611762e-08,
|
65 |
+
"loss": 0.5162,
|
66 |
"step": 4000
|
67 |
},
|
68 |
{
|
69 |
"epoch": 2.0,
|
70 |
+
"eval_loss": 0.571711540222168,
|
71 |
+
"eval_matthews_correlation": 0.27657164760495423,
|
72 |
+
"eval_runtime": 0.7318,
|
73 |
+
"eval_samples_per_second": 1425.327,
|
74 |
+
"eval_steps_per_second": 90.193,
|
75 |
"step": 4276
|
76 |
}
|
77 |
],
|
|
|
80 |
"num_input_tokens_seen": 0,
|
81 |
"num_train_epochs": 2,
|
82 |
"save_steps": 500,
|
83 |
+
"total_flos": 65111866045632.0,
|
84 |
"train_batch_size": 4,
|
85 |
"trial_name": null,
|
86 |
"trial_params": {
|
87 |
+
"learning_rate": 1.529224712096083e-06,
|
88 |
"num_train_epochs": 2,
|
89 |
"per_device_train_batch_size": 4,
|
90 |
+
"seed": 5
|
91 |
}
|
92 |
}
|
run-3/checkpoint-4276/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4792
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ff0b8762417b71e573ee14cf5d6c55e801af11f299848bcf4bde51f1e4499d53
|
3 |
size 4792
|
run-4/checkpoint-268/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": "4.36.2",
|
24 |
+
"vocab_size": 30522
|
25 |
+
}
|
run-4/checkpoint-268/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:adf4873f03711bcd1e5aac7f2cccc8c1e3507a2ce13e9346f72877865b9aa266
|
3 |
+
size 267832560
|
run-4/checkpoint-268/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8017e85329f480f7f722447b565c27ed2c5a8ca84e9d341886d1808a9efaafec
|
3 |
+
size 535727290
|
run-4/checkpoint-268/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3f3c6f33738840ae66d602ec44a31805c3c1244f220af1ccc8bbf30e6d301f82
|
3 |
+
size 14244
|
run-4/checkpoint-268/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:48a779c7928a522e4fd10586286eacb8a2942eb602be0c498de64a3454085c13
|
3 |
+
size 1064
|
run-4/checkpoint-268/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-268/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-4/checkpoint-268/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-268/trainer_state.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.4981947529906373,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-268",
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 268,
|
7 |
+
"is_hyper_param_search": true,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.0,
|
13 |
+
"eval_loss": 0.478412002325058,
|
14 |
+
"eval_matthews_correlation": 0.4981947529906373,
|
15 |
+
"eval_runtime": 0.7412,
|
16 |
+
"eval_samples_per_second": 1407.09,
|
17 |
+
"eval_steps_per_second": 89.039,
|
18 |
+
"step": 268
|
19 |
+
}
|
20 |
+
],
|
21 |
+
"logging_steps": 500,
|
22 |
+
"max_steps": 1072,
|
23 |
+
"num_input_tokens_seen": 0,
|
24 |
+
"num_train_epochs": 4,
|
25 |
+
"save_steps": 500,
|
26 |
+
"total_flos": 0,
|
27 |
+
"train_batch_size": 32,
|
28 |
+
"trial_name": null,
|
29 |
+
"trial_params": {
|
30 |
+
"learning_rate": 1.546889870762945e-05,
|
31 |
+
"num_train_epochs": 4,
|
32 |
+
"per_device_train_batch_size": 32,
|
33 |
+
"seed": 6
|
34 |
+
}
|
35 |
+
}
|
run-4/checkpoint-268/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e659d03ffe6756d57c4e0e598cf990e7f41d01544dda0051abdb26300ef89e7f
|
3 |
+
size 4792
|
run-4/checkpoint-268/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
runs/Dec23_01-09-39_cab176ec49ea/events.out.tfevents.1703294598.cab176ec49ea.681.5
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c3a7c1c4dcb46e84582be78fff6345d3c543e7652a5375702e10317a67d72d51
|
3 |
+
size 6619
|
runs/Dec23_01-09-39_cab176ec49ea/events.out.tfevents.1703294819.cab176ec49ea.681.6
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7916c397e5c4e447fd066debeae674f6659881eeec61b70d611840c9dd919c88
|
3 |
+
size 5167
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4792
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e659d03ffe6756d57c4e0e598cf990e7f41d01544dda0051abdb26300ef89e7f
|
3 |
size 4792
|