Training in progress, epoch 5
Browse files- model.safetensors +1 -1
- run-1/checkpoint-2140/config.json +25 -0
- run-1/checkpoint-2140/model.safetensors +3 -0
- run-1/checkpoint-2140/optimizer.pt +3 -0
- run-1/checkpoint-2140/rng_state.pth +3 -0
- run-1/checkpoint-2140/scheduler.pt +3 -0
- run-1/checkpoint-2140/special_tokens_map.json +7 -0
- run-1/checkpoint-2140/tokenizer.json +0 -0
- run-1/checkpoint-2140/tokenizer_config.json +55 -0
- run-1/checkpoint-2140/trainer_state.json +86 -0
- run-1/checkpoint-2140/training_args.bin +3 -0
- run-1/checkpoint-2140/vocab.txt +0 -0
- run-1/checkpoint-2675/config.json +25 -0
- run-1/checkpoint-2675/model.safetensors +3 -0
- run-1/checkpoint-2675/optimizer.pt +3 -0
- run-1/checkpoint-2675/rng_state.pth +3 -0
- run-1/checkpoint-2675/scheduler.pt +3 -0
- run-1/checkpoint-2675/special_tokens_map.json +7 -0
- run-1/checkpoint-2675/tokenizer.json +0 -0
- run-1/checkpoint-2675/tokenizer_config.json +55 -0
- run-1/checkpoint-2675/trainer_state.json +101 -0
- run-1/checkpoint-2675/training_args.bin +3 -0
- run-1/checkpoint-2675/vocab.txt +0 -0
- runs/Dec23_01-55-51_48296f50e732/events.out.tfevents.1703298290.48296f50e732.508.2 +2 -2
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:a2341e07b9fab710ae7e7e9662580ae074bab25dcdb9fc67635b765231dc88c0
|
3 |
size 267832560
|
run-1/checkpoint-2140/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-1/checkpoint-2140/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:70d9a68b8c2564e077d1ebf2e3458219bc8a833e224ecef0f0b7bb288dd5a0a1
|
3 |
+
size 267832560
|
run-1/checkpoint-2140/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fe472f2a38a6ef49fd19c048c86c824e6b9fe6288fbe0e3f93ff9804ef3d491d
|
3 |
+
size 535727290
|
run-1/checkpoint-2140/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:76ca1ea9b12a550880ec2e54310831ca5ed79a62271d1d0c0a801486c6a46fa1
|
3 |
+
size 14308
|
run-1/checkpoint-2140/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2892273e243ba126f3eeaed5d2a811f3f64a0ba5da314c3f1466273302a82a6b
|
3 |
+
size 1064
|
run-1/checkpoint-2140/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-1/checkpoint-2140/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-1/checkpoint-2140/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-1/checkpoint-2140/trainer_state.json
ADDED
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.514713087977408,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-2140",
|
4 |
+
"epoch": 4.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 2140,
|
7 |
+
"is_hyper_param_search": true,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.93,
|
13 |
+
"learning_rate": 4.894237945372658e-05,
|
14 |
+
"loss": 0.5408,
|
15 |
+
"step": 500
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 1.0,
|
19 |
+
"eval_loss": 0.48756271600723267,
|
20 |
+
"eval_matthews_correlation": 0.4371151083758757,
|
21 |
+
"eval_runtime": 0.7652,
|
22 |
+
"eval_samples_per_second": 1363.003,
|
23 |
+
"eval_steps_per_second": 86.249,
|
24 |
+
"step": 535
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 1.87,
|
28 |
+
"learning_rate": 3.769125774022621e-05,
|
29 |
+
"loss": 0.3186,
|
30 |
+
"step": 1000
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 2.0,
|
34 |
+
"eval_loss": 0.4699440896511078,
|
35 |
+
"eval_matthews_correlation": 0.48170038113970914,
|
36 |
+
"eval_runtime": 0.7508,
|
37 |
+
"eval_samples_per_second": 1389.228,
|
38 |
+
"eval_steps_per_second": 87.909,
|
39 |
+
"step": 1070
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 2.8,
|
43 |
+
"learning_rate": 2.644013602672585e-05,
|
44 |
+
"loss": 0.2026,
|
45 |
+
"step": 1500
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 3.0,
|
49 |
+
"eval_loss": 0.7681801319122314,
|
50 |
+
"eval_matthews_correlation": 0.47428224772244454,
|
51 |
+
"eval_runtime": 0.7372,
|
52 |
+
"eval_samples_per_second": 1414.877,
|
53 |
+
"eval_steps_per_second": 89.532,
|
54 |
+
"step": 1605
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 3.74,
|
58 |
+
"learning_rate": 1.5189014313225487e-05,
|
59 |
+
"loss": 0.1282,
|
60 |
+
"step": 2000
|
61 |
+
},
|
62 |
+
{
|
63 |
+
"epoch": 4.0,
|
64 |
+
"eval_loss": 0.8975861072540283,
|
65 |
+
"eval_matthews_correlation": 0.514713087977408,
|
66 |
+
"eval_runtime": 1.2396,
|
67 |
+
"eval_samples_per_second": 841.372,
|
68 |
+
"eval_steps_per_second": 53.241,
|
69 |
+
"step": 2140
|
70 |
+
}
|
71 |
+
],
|
72 |
+
"logging_steps": 500,
|
73 |
+
"max_steps": 2675,
|
74 |
+
"num_input_tokens_seen": 0,
|
75 |
+
"num_train_epochs": 5,
|
76 |
+
"save_steps": 500,
|
77 |
+
"total_flos": 171168835819980.0,
|
78 |
+
"train_batch_size": 16,
|
79 |
+
"trial_name": null,
|
80 |
+
"trial_params": {
|
81 |
+
"learning_rate": 6.019350116722694e-05,
|
82 |
+
"num_train_epochs": 5,
|
83 |
+
"per_device_train_batch_size": 16,
|
84 |
+
"seed": 13
|
85 |
+
}
|
86 |
+
}
|
run-1/checkpoint-2140/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf249ce55272fbde68001c7053fc83d7d8152ef8c83e36c8c055bcdcbd21b4af
|
3 |
+
size 4792
|
run-1/checkpoint-2140/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-1/checkpoint-2675/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-1/checkpoint-2675/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a2341e07b9fab710ae7e7e9662580ae074bab25dcdb9fc67635b765231dc88c0
|
3 |
+
size 267832560
|
run-1/checkpoint-2675/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f286f41b5bea4ca752a36052357921977b60f4360cddbd650b8f829d0c8fd012
|
3 |
+
size 535727290
|
run-1/checkpoint-2675/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:040a9dcbf8d317ee5aa05aed7ed085e899a3f3c5f28239d65e65948fd79c1e68
|
3 |
+
size 14308
|
run-1/checkpoint-2675/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:64161085f029cd8bcf6d16677ab586032126adb9a9c681fe7e2a25d24515b839
|
3 |
+
size 1064
|
run-1/checkpoint-2675/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-1/checkpoint-2675/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-1/checkpoint-2675/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-1/checkpoint-2675/trainer_state.json
ADDED
@@ -0,0 +1,101 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.514713087977408,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-2140",
|
4 |
+
"epoch": 5.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 2675,
|
7 |
+
"is_hyper_param_search": true,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.93,
|
13 |
+
"learning_rate": 4.894237945372658e-05,
|
14 |
+
"loss": 0.5408,
|
15 |
+
"step": 500
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 1.0,
|
19 |
+
"eval_loss": 0.48756271600723267,
|
20 |
+
"eval_matthews_correlation": 0.4371151083758757,
|
21 |
+
"eval_runtime": 0.7652,
|
22 |
+
"eval_samples_per_second": 1363.003,
|
23 |
+
"eval_steps_per_second": 86.249,
|
24 |
+
"step": 535
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 1.87,
|
28 |
+
"learning_rate": 3.769125774022621e-05,
|
29 |
+
"loss": 0.3186,
|
30 |
+
"step": 1000
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 2.0,
|
34 |
+
"eval_loss": 0.4699440896511078,
|
35 |
+
"eval_matthews_correlation": 0.48170038113970914,
|
36 |
+
"eval_runtime": 0.7508,
|
37 |
+
"eval_samples_per_second": 1389.228,
|
38 |
+
"eval_steps_per_second": 87.909,
|
39 |
+
"step": 1070
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 2.8,
|
43 |
+
"learning_rate": 2.644013602672585e-05,
|
44 |
+
"loss": 0.2026,
|
45 |
+
"step": 1500
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 3.0,
|
49 |
+
"eval_loss": 0.7681801319122314,
|
50 |
+
"eval_matthews_correlation": 0.47428224772244454,
|
51 |
+
"eval_runtime": 0.7372,
|
52 |
+
"eval_samples_per_second": 1414.877,
|
53 |
+
"eval_steps_per_second": 89.532,
|
54 |
+
"step": 1605
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 3.74,
|
58 |
+
"learning_rate": 1.5189014313225487e-05,
|
59 |
+
"loss": 0.1282,
|
60 |
+
"step": 2000
|
61 |
+
},
|
62 |
+
{
|
63 |
+
"epoch": 4.0,
|
64 |
+
"eval_loss": 0.8975861072540283,
|
65 |
+
"eval_matthews_correlation": 0.514713087977408,
|
66 |
+
"eval_runtime": 1.2396,
|
67 |
+
"eval_samples_per_second": 841.372,
|
68 |
+
"eval_steps_per_second": 53.241,
|
69 |
+
"step": 2140
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 4.67,
|
73 |
+
"learning_rate": 3.937892599725126e-06,
|
74 |
+
"loss": 0.0762,
|
75 |
+
"step": 2500
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 5.0,
|
79 |
+
"eval_loss": 1.1111303567886353,
|
80 |
+
"eval_matthews_correlation": 0.5002057401338981,
|
81 |
+
"eval_runtime": 0.8031,
|
82 |
+
"eval_samples_per_second": 1298.779,
|
83 |
+
"eval_steps_per_second": 82.185,
|
84 |
+
"step": 2675
|
85 |
+
}
|
86 |
+
],
|
87 |
+
"logging_steps": 500,
|
88 |
+
"max_steps": 2675,
|
89 |
+
"num_input_tokens_seen": 0,
|
90 |
+
"num_train_epochs": 5,
|
91 |
+
"save_steps": 500,
|
92 |
+
"total_flos": 214298616724968.0,
|
93 |
+
"train_batch_size": 16,
|
94 |
+
"trial_name": null,
|
95 |
+
"trial_params": {
|
96 |
+
"learning_rate": 6.019350116722694e-05,
|
97 |
+
"num_train_epochs": 5,
|
98 |
+
"per_device_train_batch_size": 16,
|
99 |
+
"seed": 13
|
100 |
+
}
|
101 |
+
}
|
run-1/checkpoint-2675/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf249ce55272fbde68001c7053fc83d7d8152ef8c83e36c8c055bcdcbd21b4af
|
3 |
+
size 4792
|
run-1/checkpoint-2675/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
runs/Dec23_01-55-51_48296f50e732/events.out.tfevents.1703298290.48296f50e732.508.2
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 sha256:219c7047fdbfadec292399132ee6a1c3aa1775e326ef25858509cc204a82f867
|
3 |
+
size 7160
|