Training in progress, epoch 2
Browse files- pytorch_model.bin +1 -1
- run-9/checkpoint-27/config.json +1 -1
- run-9/checkpoint-27/optimizer.pt +2 -2
- run-9/checkpoint-27/rng_state.pth +2 -2
- run-9/checkpoint-27/scheduler.pt +2 -2
- run-9/checkpoint-27/tokenizer_config.json +1 -43
- run-9/checkpoint-27/trainer_state.json +11 -16
- run-9/checkpoint-27/training_args.bin +2 -2
- runs/Mar10_12-23-35_f87fe01c66be/1710075111.191353/events.out.tfevents.1710075111.f87fe01c66be.29486.22 +3 -0
- runs/Mar10_12-23-35_f87fe01c66be/events.out.tfevents.1710075060.f87fe01c66be.29486.19 +2 -2
- runs/Mar10_12-23-35_f87fe01c66be/events.out.tfevents.1710075111.f87fe01c66be.29486.21 +3 -0
- training_args.bin +1 -1
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 98725415
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8f94374c7da018adf6c949bd6694d106d4d7424b87123fcdcc76a1b763ff3a30
|
3 |
size 98725415
|
run-9/checkpoint-27/config.json
CHANGED
@@ -24,7 +24,7 @@
|
|
24 |
"pad_token_id": 0,
|
25 |
"problem_type": "single_label_classification",
|
26 |
"torch_dtype": "float32",
|
27 |
-
"transformers_version": "4.
|
28 |
"trigram_input": true,
|
29 |
"true_hidden_size": 128,
|
30 |
"type_vocab_size": 2,
|
|
|
24 |
"pad_token_id": 0,
|
25 |
"problem_type": "single_label_classification",
|
26 |
"torch_dtype": "float32",
|
27 |
+
"transformers_version": "4.27.2",
|
28 |
"trigram_input": true,
|
29 |
"true_hidden_size": 128,
|
30 |
"type_vocab_size": 2,
|
run-9/checkpoint-27/optimizer.pt
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:ccbcf4d8ea067276d6af988f57f5bb06b11116f6a5e416677b125fe988e52635
|
3 |
+
size 197314895
|
run-9/checkpoint-27/rng_state.pth
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 sha256:450605505cac9071c0b64dcb511a49a77c75d41521a4114d87bbc19fd6728c17
|
3 |
+
size 14639
|
run-9/checkpoint-27/scheduler.pt
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 sha256:75eb50fe6125e4308b7b8438357a984407a4d10e55b87584ddb159ce15a1a8f9
|
3 |
+
size 627
|
run-9/checkpoint-27/tokenizer_config.json
CHANGED
@@ -1,53 +1,11 @@
|
|
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": 1000000000000000019884624838656,
|
49 |
"pad_token": "[PAD]",
|
50 |
"sep_token": "[SEP]",
|
|
|
51 |
"strip_accents": null,
|
52 |
"tokenize_chinese_chars": true,
|
53 |
"tokenizer_class": "MobileBertTokenizer",
|
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"cls_token": "[CLS]",
|
3 |
"do_lower_case": true,
|
4 |
"mask_token": "[MASK]",
|
5 |
"model_max_length": 1000000000000000019884624838656,
|
6 |
"pad_token": "[PAD]",
|
7 |
"sep_token": "[SEP]",
|
8 |
+
"special_tokens_map_file": null,
|
9 |
"strip_accents": null,
|
10 |
"tokenize_chinese_chars": true,
|
11 |
"tokenizer_class": "MobileBertTokenizer",
|
run-9/checkpoint-27/trainer_state.json
CHANGED
@@ -1,8 +1,7 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
"best_model_checkpoint": "mobilebert-uncased-finetuned-cola/run-9/checkpoint-27",
|
4 |
"epoch": 1.0,
|
5 |
-
"eval_steps": 500,
|
6 |
"global_step": 27,
|
7 |
"is_hyper_param_search": true,
|
8 |
"is_local_process_zero": true,
|
@@ -10,26 +9,22 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
-
"eval_loss":
|
14 |
-
"eval_matthews_correlation": 0.
|
15 |
-
"eval_runtime": 2.
|
16 |
-
"eval_samples_per_second":
|
17 |
-
"eval_steps_per_second":
|
18 |
"step": 27
|
19 |
}
|
20 |
],
|
21 |
-
"
|
22 |
-
"
|
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.
|
31 |
-
"num_train_epochs":
|
32 |
"per_device_train_batch_size": 32,
|
33 |
-
"seed":
|
34 |
}
|
35 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.05010380784748445,
|
3 |
"best_model_checkpoint": "mobilebert-uncased-finetuned-cola/run-9/checkpoint-27",
|
4 |
"epoch": 1.0,
|
|
|
5 |
"global_step": 27,
|
6 |
"is_hyper_param_search": true,
|
7 |
"is_local_process_zero": true,
|
|
|
9 |
"log_history": [
|
10 |
{
|
11 |
"epoch": 1.0,
|
12 |
+
"eval_loss": 71244.34375,
|
13 |
+
"eval_matthews_correlation": 0.05010380784748445,
|
14 |
+
"eval_runtime": 2.4286,
|
15 |
+
"eval_samples_per_second": 429.471,
|
16 |
+
"eval_steps_per_second": 27.176,
|
17 |
"step": 27
|
18 |
}
|
19 |
],
|
20 |
+
"max_steps": 54,
|
21 |
+
"num_train_epochs": 2,
|
|
|
|
|
|
|
22 |
"total_flos": 0,
|
|
|
23 |
"trial_name": null,
|
24 |
"trial_params": {
|
25 |
+
"learning_rate": 1.2812201115831856e-05,
|
26 |
+
"num_train_epochs": 2,
|
27 |
"per_device_train_batch_size": 32,
|
28 |
+
"seed": 26
|
29 |
}
|
30 |
}
|
run-9/checkpoint-27/training_args.bin
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 sha256:8e5ce87fdbc29daf107e10172cee27f44a5b81cac03983ffc39492bf8e2ce4d7
|
3 |
+
size 3643
|
runs/Mar10_12-23-35_f87fe01c66be/1710075111.191353/events.out.tfevents.1710075111.f87fe01c66be.29486.22
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:94c064a9e1d3bc56ba73c4737df9ac96e5c7b84bd9308e3b4a7af47947edd32f
|
3 |
+
size 5884
|
runs/Mar10_12-23-35_f87fe01c66be/events.out.tfevents.1710075060.f87fe01c66be.29486.19
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:d39a4e3ba4505d98dcf34c90faeb7100856d9d67a68f651a2c470855a025afae
|
3 |
+
size 5282
|
runs/Mar10_12-23-35_f87fe01c66be/events.out.tfevents.1710075111.f87fe01c66be.29486.21
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f3bca086b1ee7d84c2596f7f46662e49ebb188705b6c7e68ea6a841d6e488021
|
3 |
+
size 4934
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3643
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8e5ce87fdbc29daf107e10172cee27f44a5b81cac03983ffc39492bf8e2ce4d7
|
3 |
size 3643
|