sibstrider
commited on
Commit
•
0829b32
1
Parent(s):
2ca3c1d
Training in progress, epoch 1
Browse files- model.safetensors +1 -1
- run-2/checkpoint-1650/model.safetensors +1 -1
- run-2/checkpoint-1650/optimizer.pt +1 -1
- run-2/checkpoint-1650/rng_state.pth +1 -1
- run-2/checkpoint-1650/scheduler.pt +1 -1
- run-2/checkpoint-1650/training_args.bin +1 -1
- run-2/checkpoint-2200/model.safetensors +1 -1
- run-2/checkpoint-2200/optimizer.pt +1 -1
- run-2/checkpoint-2200/rng_state.pth +1 -1
- run-2/checkpoint-2200/scheduler.pt +1 -1
- run-2/checkpoint-2200/trainer_state.json +36 -36
- run-2/checkpoint-2200/training_args.bin +1 -1
- run-2/checkpoint-2750/config.json +54 -0
- run-2/checkpoint-2750/model.safetensors +3 -0
- run-2/checkpoint-2750/optimizer.pt +3 -0
- run-2/checkpoint-2750/rng_state.pth +3 -0
- run-2/checkpoint-2750/scheduler.pt +3 -0
- run-2/checkpoint-2750/special_tokens_map.json +37 -0
- run-2/checkpoint-2750/tokenizer.json +0 -0
- run-2/checkpoint-2750/tokenizer_config.json +64 -0
- run-2/checkpoint-2750/trainer_state.json +101 -0
- run-2/checkpoint-2750/training_args.bin +3 -0
- run-2/checkpoint-2750/vocab.txt +0 -0
- run-3/checkpoint-69/config.json +54 -0
- run-3/checkpoint-69/model.safetensors +3 -0
- run-3/checkpoint-69/optimizer.pt +3 -0
- run-3/checkpoint-69/rng_state.pth +3 -0
- run-3/checkpoint-69/scheduler.pt +3 -0
- run-3/checkpoint-69/special_tokens_map.json +37 -0
- run-3/checkpoint-69/tokenizer.json +0 -0
- run-3/checkpoint-69/tokenizer_config.json +64 -0
- run-3/checkpoint-69/trainer_state.json +35 -0
- run-3/checkpoint-69/training_args.bin +3 -0
- run-3/checkpoint-69/vocab.txt +0 -0
- runs/Jan15_00-51-52_DESKTOP-RFEED41/events.out.tfevents.1705269786.DESKTOP-RFEED41.20976.18 +2 -2
- runs/Jan15_00-51-52_DESKTOP-RFEED41/events.out.tfevents.1705270920.DESKTOP-RFEED41.20976.19 +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 116795404
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e07293b8550ee61957df28bd5ea64e3824bc8a30e5bba08b6a8ea37a6e9f8ac4
|
3 |
size 116795404
|
run-2/checkpoint-1650/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 116795404
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf8e53006451443602529b914ad65cc2d8141f14fe898e01621438a0858ea33c
|
3 |
size 116795404
|
run-2/checkpoint-1650/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 233621882
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9b128d5b28ae98a1f34f6ab3388ea827025ded295009af8a2572da4aa6571b30
|
3 |
size 233621882
|
run-2/checkpoint-1650/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 13990
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e117001ef5952de6414d089b2d6168619aebb9f96cdd4c1cdd3e564778e4d3b4
|
3 |
size 13990
|
run-2/checkpoint-1650/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:ec2086a234a5f0f925816dade0ec0a19c8f075175af5bac7c2840a84aec030d4
|
3 |
size 1064
|
run-2/checkpoint-1650/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4728
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6bf6249fcaffd3bf1a6e41efb7044edf4d8222cdd0729549fa8f87e1c5b20556
|
3 |
size 4728
|
run-2/checkpoint-2200/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 116795404
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4886a8ef0bfa4d8fda4bc6668e85c25f89215e12bdb7dc3cdc97a16b9ea30510
|
3 |
size 116795404
|
run-2/checkpoint-2200/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 233621882
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4eda25768d8b5ea418efd3a40cb31a8978519da75d7ea427320f134614d54a01
|
3 |
size 233621882
|
run-2/checkpoint-2200/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 13990
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b1a55bf44755c4d82fa8d2c08dc259becb4a18d612163f5b5631aaf7fdb0b065
|
3 |
size 13990
|
run-2/checkpoint-2200/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 sha256:41922631416aa123a0fab067078b29c971a18c4c71d52b12c055d632683ba82e
|
3 |
size 1064
|
run-2/checkpoint-2200/trainer_state.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "rubert-tiny2-finetuned-classification\\run-2\\checkpoint-
|
4 |
"epoch": 4.0,
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 2200,
|
@@ -10,77 +10,77 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.91,
|
13 |
-
"learning_rate":
|
14 |
-
"loss":
|
15 |
"step": 500
|
16 |
},
|
17 |
{
|
18 |
"epoch": 1.0,
|
19 |
-
"eval_accuracy": 0.
|
20 |
-
"eval_loss": 1.
|
21 |
-
"eval_runtime": 1.
|
22 |
-
"eval_samples_per_second":
|
23 |
-
"eval_steps_per_second":
|
24 |
"step": 550
|
25 |
},
|
26 |
{
|
27 |
"epoch": 1.82,
|
28 |
-
"learning_rate":
|
29 |
-
"loss": 1.
|
30 |
"step": 1000
|
31 |
},
|
32 |
{
|
33 |
"epoch": 2.0,
|
34 |
-
"eval_accuracy": 0.
|
35 |
-
"eval_loss":
|
36 |
-
"eval_runtime": 1.
|
37 |
-
"eval_samples_per_second":
|
38 |
-
"eval_steps_per_second":
|
39 |
"step": 1100
|
40 |
},
|
41 |
{
|
42 |
"epoch": 2.73,
|
43 |
-
"learning_rate":
|
44 |
-
"loss":
|
45 |
"step": 1500
|
46 |
},
|
47 |
{
|
48 |
"epoch": 3.0,
|
49 |
-
"eval_accuracy": 0.
|
50 |
-
"eval_loss":
|
51 |
-
"eval_runtime":
|
52 |
-
"eval_samples_per_second":
|
53 |
-
"eval_steps_per_second":
|
54 |
"step": 1650
|
55 |
},
|
56 |
{
|
57 |
"epoch": 3.64,
|
58 |
-
"learning_rate":
|
59 |
-
"loss":
|
60 |
"step": 2000
|
61 |
},
|
62 |
{
|
63 |
"epoch": 4.0,
|
64 |
-
"eval_accuracy": 0.
|
65 |
-
"eval_loss": 0.
|
66 |
-
"eval_runtime": 1.
|
67 |
-
"eval_samples_per_second":
|
68 |
-
"eval_steps_per_second":
|
69 |
"step": 2200
|
70 |
}
|
71 |
],
|
72 |
"logging_steps": 500,
|
73 |
-
"max_steps":
|
74 |
"num_input_tokens_seen": 0,
|
75 |
-
"num_train_epochs":
|
76 |
"save_steps": 500,
|
77 |
-
"total_flos":
|
78 |
"train_batch_size": 4,
|
79 |
"trial_name": null,
|
80 |
"trial_params": {
|
81 |
-
"learning_rate":
|
82 |
-
"num_train_epochs":
|
83 |
"per_device_train_batch_size": 4,
|
84 |
-
"seed":
|
85 |
}
|
86 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.8163265306122449,
|
3 |
+
"best_model_checkpoint": "rubert-tiny2-finetuned-classification\\run-2\\checkpoint-2200",
|
4 |
"epoch": 4.0,
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 2200,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.91,
|
13 |
+
"learning_rate": 7.123150895957912e-06,
|
14 |
+
"loss": 2.1151,
|
15 |
"step": 500
|
16 |
},
|
17 |
{
|
18 |
"epoch": 1.0,
|
19 |
+
"eval_accuracy": 0.6326530612244898,
|
20 |
+
"eval_loss": 1.7264677286148071,
|
21 |
+
"eval_runtime": 1.125,
|
22 |
+
"eval_samples_per_second": 217.778,
|
23 |
+
"eval_steps_per_second": 14.222,
|
24 |
"step": 550
|
25 |
},
|
26 |
{
|
27 |
"epoch": 1.82,
|
28 |
+
"learning_rate": 5.540228474633931e-06,
|
29 |
+
"loss": 1.5823,
|
30 |
"step": 1000
|
31 |
},
|
32 |
{
|
33 |
"epoch": 2.0,
|
34 |
+
"eval_accuracy": 0.7755102040816326,
|
35 |
+
"eval_loss": 1.2948896884918213,
|
36 |
+
"eval_runtime": 1.575,
|
37 |
+
"eval_samples_per_second": 155.555,
|
38 |
+
"eval_steps_per_second": 10.159,
|
39 |
"step": 1100
|
40 |
},
|
41 |
{
|
42 |
"epoch": 2.73,
|
43 |
+
"learning_rate": 3.9573060533099506e-06,
|
44 |
+
"loss": 1.2756,
|
45 |
"step": 1500
|
46 |
},
|
47 |
{
|
48 |
"epoch": 3.0,
|
49 |
+
"eval_accuracy": 0.8,
|
50 |
+
"eval_loss": 1.0647388696670532,
|
51 |
+
"eval_runtime": 2.6287,
|
52 |
+
"eval_samples_per_second": 93.202,
|
53 |
+
"eval_steps_per_second": 6.087,
|
54 |
"step": 1650
|
55 |
},
|
56 |
{
|
57 |
"epoch": 3.64,
|
58 |
+
"learning_rate": 2.37438363198597e-06,
|
59 |
+
"loss": 1.0916,
|
60 |
"step": 2000
|
61 |
},
|
62 |
{
|
63 |
"epoch": 4.0,
|
64 |
+
"eval_accuracy": 0.8163265306122449,
|
65 |
+
"eval_loss": 0.9502941966056824,
|
66 |
+
"eval_runtime": 1.215,
|
67 |
+
"eval_samples_per_second": 201.646,
|
68 |
+
"eval_steps_per_second": 13.169,
|
69 |
"step": 2200
|
70 |
}
|
71 |
],
|
72 |
"logging_steps": 500,
|
73 |
+
"max_steps": 2750,
|
74 |
"num_input_tokens_seen": 0,
|
75 |
+
"num_train_epochs": 5,
|
76 |
"save_steps": 500,
|
77 |
+
"total_flos": 3864466200000.0,
|
78 |
"train_batch_size": 4,
|
79 |
"trial_name": null,
|
80 |
"trial_params": {
|
81 |
+
"learning_rate": 8.706073317281892e-06,
|
82 |
+
"num_train_epochs": 5,
|
83 |
"per_device_train_batch_size": 4,
|
84 |
+
"seed": 1
|
85 |
}
|
86 |
}
|
run-2/checkpoint-2200/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4728
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6bf6249fcaffd3bf1a6e41efb7044edf4d8222cdd0729549fa8f87e1c5b20556
|
3 |
size 4728
|
run-2/checkpoint-2750/config.json
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "cointegrated/rubert-tiny2",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"emb_size": 312,
|
9 |
+
"gradient_checkpointing": false,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 312,
|
13 |
+
"id2label": {
|
14 |
+
"0": "LABEL_0",
|
15 |
+
"1": "LABEL_1",
|
16 |
+
"2": "LABEL_2",
|
17 |
+
"3": "LABEL_3",
|
18 |
+
"4": "LABEL_4",
|
19 |
+
"5": "LABEL_5",
|
20 |
+
"6": "LABEL_6",
|
21 |
+
"7": "LABEL_7",
|
22 |
+
"8": "LABEL_8",
|
23 |
+
"9": "LABEL_9",
|
24 |
+
"10": "LABEL_10"
|
25 |
+
},
|
26 |
+
"initializer_range": 0.02,
|
27 |
+
"intermediate_size": 600,
|
28 |
+
"label2id": {
|
29 |
+
"LABEL_0": 0,
|
30 |
+
"LABEL_1": 1,
|
31 |
+
"LABEL_10": 10,
|
32 |
+
"LABEL_2": 2,
|
33 |
+
"LABEL_3": 3,
|
34 |
+
"LABEL_4": 4,
|
35 |
+
"LABEL_5": 5,
|
36 |
+
"LABEL_6": 6,
|
37 |
+
"LABEL_7": 7,
|
38 |
+
"LABEL_8": 8,
|
39 |
+
"LABEL_9": 9
|
40 |
+
},
|
41 |
+
"layer_norm_eps": 1e-12,
|
42 |
+
"max_position_embeddings": 2048,
|
43 |
+
"model_type": "bert",
|
44 |
+
"num_attention_heads": 12,
|
45 |
+
"num_hidden_layers": 3,
|
46 |
+
"pad_token_id": 0,
|
47 |
+
"position_embedding_type": "absolute",
|
48 |
+
"problem_type": "single_label_classification",
|
49 |
+
"torch_dtype": "float32",
|
50 |
+
"transformers_version": "4.36.2",
|
51 |
+
"type_vocab_size": 2,
|
52 |
+
"use_cache": true,
|
53 |
+
"vocab_size": 83828
|
54 |
+
}
|
run-2/checkpoint-2750/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3d74ae96e9083228430d06262059bbc20f3914b807bb3f15ef01508e308e2dac
|
3 |
+
size 116795404
|
run-2/checkpoint-2750/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3ecab0126c9f37abcb558a3f30fce3e080cd880e35aa569056b62b2d88dac380
|
3 |
+
size 233621882
|
run-2/checkpoint-2750/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b55bbb8627c758bfbd2b90b33f7cfa0f353925e23f30d3b3a7619cbb9665c11f
|
3 |
+
size 13990
|
run-2/checkpoint-2750/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6982af2571d2be085061534f83b036a604ef20cdc463ad82de235b5b0381e206
|
3 |
+
size 1064
|
run-2/checkpoint-2750/special_tokens_map.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": {
|
3 |
+
"content": "[CLS]",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"mask_token": {
|
10 |
+
"content": "[MASK]",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "[PAD]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"sep_token": {
|
24 |
+
"content": "[SEP]",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"unk_token": {
|
31 |
+
"content": "[UNK]",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
}
|
37 |
+
}
|
run-2/checkpoint-2750/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-2/checkpoint-2750/tokenizer_config.json
ADDED
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"1": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"4": {
|
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_basic_tokenize": true,
|
47 |
+
"do_lower_case": false,
|
48 |
+
"mask_token": "[MASK]",
|
49 |
+
"max_length": 512,
|
50 |
+
"model_max_length": 2048,
|
51 |
+
"never_split": null,
|
52 |
+
"pad_to_multiple_of": null,
|
53 |
+
"pad_token": "[PAD]",
|
54 |
+
"pad_token_type_id": 0,
|
55 |
+
"padding_side": "right",
|
56 |
+
"sep_token": "[SEP]",
|
57 |
+
"stride": 0,
|
58 |
+
"strip_accents": null,
|
59 |
+
"tokenize_chinese_chars": true,
|
60 |
+
"tokenizer_class": "BertTokenizer",
|
61 |
+
"truncation_side": "right",
|
62 |
+
"truncation_strategy": "longest_first",
|
63 |
+
"unk_token": "[UNK]"
|
64 |
+
}
|
run-2/checkpoint-2750/trainer_state.json
ADDED
@@ -0,0 +1,101 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.8244897959183674,
|
3 |
+
"best_model_checkpoint": "rubert-tiny2-finetuned-classification\\run-2\\checkpoint-2750",
|
4 |
+
"epoch": 5.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 2750,
|
7 |
+
"is_hyper_param_search": true,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.91,
|
13 |
+
"learning_rate": 7.123150895957912e-06,
|
14 |
+
"loss": 2.1151,
|
15 |
+
"step": 500
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 1.0,
|
19 |
+
"eval_accuracy": 0.6326530612244898,
|
20 |
+
"eval_loss": 1.7264677286148071,
|
21 |
+
"eval_runtime": 1.125,
|
22 |
+
"eval_samples_per_second": 217.778,
|
23 |
+
"eval_steps_per_second": 14.222,
|
24 |
+
"step": 550
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 1.82,
|
28 |
+
"learning_rate": 5.540228474633931e-06,
|
29 |
+
"loss": 1.5823,
|
30 |
+
"step": 1000
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 2.0,
|
34 |
+
"eval_accuracy": 0.7755102040816326,
|
35 |
+
"eval_loss": 1.2948896884918213,
|
36 |
+
"eval_runtime": 1.575,
|
37 |
+
"eval_samples_per_second": 155.555,
|
38 |
+
"eval_steps_per_second": 10.159,
|
39 |
+
"step": 1100
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 2.73,
|
43 |
+
"learning_rate": 3.9573060533099506e-06,
|
44 |
+
"loss": 1.2756,
|
45 |
+
"step": 1500
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 3.0,
|
49 |
+
"eval_accuracy": 0.8,
|
50 |
+
"eval_loss": 1.0647388696670532,
|
51 |
+
"eval_runtime": 2.6287,
|
52 |
+
"eval_samples_per_second": 93.202,
|
53 |
+
"eval_steps_per_second": 6.087,
|
54 |
+
"step": 1650
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 3.64,
|
58 |
+
"learning_rate": 2.37438363198597e-06,
|
59 |
+
"loss": 1.0916,
|
60 |
+
"step": 2000
|
61 |
+
},
|
62 |
+
{
|
63 |
+
"epoch": 4.0,
|
64 |
+
"eval_accuracy": 0.8163265306122449,
|
65 |
+
"eval_loss": 0.9502941966056824,
|
66 |
+
"eval_runtime": 1.215,
|
67 |
+
"eval_samples_per_second": 201.646,
|
68 |
+
"eval_steps_per_second": 13.169,
|
69 |
+
"step": 2200
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 4.55,
|
73 |
+
"learning_rate": 7.914612106619902e-07,
|
74 |
+
"loss": 0.9936,
|
75 |
+
"step": 2500
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 5.0,
|
79 |
+
"eval_accuracy": 0.8244897959183674,
|
80 |
+
"eval_loss": 0.9156307578086853,
|
81 |
+
"eval_runtime": 1.564,
|
82 |
+
"eval_samples_per_second": 156.65,
|
83 |
+
"eval_steps_per_second": 10.23,
|
84 |
+
"step": 2750
|
85 |
+
}
|
86 |
+
],
|
87 |
+
"logging_steps": 500,
|
88 |
+
"max_steps": 2750,
|
89 |
+
"num_input_tokens_seen": 0,
|
90 |
+
"num_train_epochs": 5,
|
91 |
+
"save_steps": 500,
|
92 |
+
"total_flos": 4825160961600.0,
|
93 |
+
"train_batch_size": 4,
|
94 |
+
"trial_name": null,
|
95 |
+
"trial_params": {
|
96 |
+
"learning_rate": 8.706073317281892e-06,
|
97 |
+
"num_train_epochs": 5,
|
98 |
+
"per_device_train_batch_size": 4,
|
99 |
+
"seed": 1
|
100 |
+
}
|
101 |
+
}
|
run-2/checkpoint-2750/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6bf6249fcaffd3bf1a6e41efb7044edf4d8222cdd0729549fa8f87e1c5b20556
|
3 |
+
size 4728
|
run-2/checkpoint-2750/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-3/checkpoint-69/config.json
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "cointegrated/rubert-tiny2",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"emb_size": 312,
|
9 |
+
"gradient_checkpointing": false,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 312,
|
13 |
+
"id2label": {
|
14 |
+
"0": "LABEL_0",
|
15 |
+
"1": "LABEL_1",
|
16 |
+
"2": "LABEL_2",
|
17 |
+
"3": "LABEL_3",
|
18 |
+
"4": "LABEL_4",
|
19 |
+
"5": "LABEL_5",
|
20 |
+
"6": "LABEL_6",
|
21 |
+
"7": "LABEL_7",
|
22 |
+
"8": "LABEL_8",
|
23 |
+
"9": "LABEL_9",
|
24 |
+
"10": "LABEL_10"
|
25 |
+
},
|
26 |
+
"initializer_range": 0.02,
|
27 |
+
"intermediate_size": 600,
|
28 |
+
"label2id": {
|
29 |
+
"LABEL_0": 0,
|
30 |
+
"LABEL_1": 1,
|
31 |
+
"LABEL_10": 10,
|
32 |
+
"LABEL_2": 2,
|
33 |
+
"LABEL_3": 3,
|
34 |
+
"LABEL_4": 4,
|
35 |
+
"LABEL_5": 5,
|
36 |
+
"LABEL_6": 6,
|
37 |
+
"LABEL_7": 7,
|
38 |
+
"LABEL_8": 8,
|
39 |
+
"LABEL_9": 9
|
40 |
+
},
|
41 |
+
"layer_norm_eps": 1e-12,
|
42 |
+
"max_position_embeddings": 2048,
|
43 |
+
"model_type": "bert",
|
44 |
+
"num_attention_heads": 12,
|
45 |
+
"num_hidden_layers": 3,
|
46 |
+
"pad_token_id": 0,
|
47 |
+
"position_embedding_type": "absolute",
|
48 |
+
"problem_type": "single_label_classification",
|
49 |
+
"torch_dtype": "float32",
|
50 |
+
"transformers_version": "4.36.2",
|
51 |
+
"type_vocab_size": 2,
|
52 |
+
"use_cache": true,
|
53 |
+
"vocab_size": 83828
|
54 |
+
}
|
run-3/checkpoint-69/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e07293b8550ee61957df28bd5ea64e3824bc8a30e5bba08b6a8ea37a6e9f8ac4
|
3 |
+
size 116795404
|
run-3/checkpoint-69/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a47fb6745cd3b3d6006ff369a4f7e5585dcf445ddc4dfb8586f4c6429c59e2f6
|
3 |
+
size 233621882
|
run-3/checkpoint-69/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1abead86d00b70119210512fa60b1c02a81616c40d0f772d753fa9c4790cd5cf
|
3 |
+
size 13990
|
run-3/checkpoint-69/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d423447796aba602e95cfb9a6f1258c79019aea6508d73460d164c1a4e1420e0
|
3 |
+
size 1064
|
run-3/checkpoint-69/special_tokens_map.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": {
|
3 |
+
"content": "[CLS]",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"mask_token": {
|
10 |
+
"content": "[MASK]",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "[PAD]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"sep_token": {
|
24 |
+
"content": "[SEP]",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"unk_token": {
|
31 |
+
"content": "[UNK]",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
}
|
37 |
+
}
|
run-3/checkpoint-69/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-3/checkpoint-69/tokenizer_config.json
ADDED
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"1": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"4": {
|
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_basic_tokenize": true,
|
47 |
+
"do_lower_case": false,
|
48 |
+
"mask_token": "[MASK]",
|
49 |
+
"max_length": 512,
|
50 |
+
"model_max_length": 2048,
|
51 |
+
"never_split": null,
|
52 |
+
"pad_to_multiple_of": null,
|
53 |
+
"pad_token": "[PAD]",
|
54 |
+
"pad_token_type_id": 0,
|
55 |
+
"padding_side": "right",
|
56 |
+
"sep_token": "[SEP]",
|
57 |
+
"stride": 0,
|
58 |
+
"strip_accents": null,
|
59 |
+
"tokenize_chinese_chars": true,
|
60 |
+
"tokenizer_class": "BertTokenizer",
|
61 |
+
"truncation_side": "right",
|
62 |
+
"truncation_strategy": "longest_first",
|
63 |
+
"unk_token": "[UNK]"
|
64 |
+
}
|
run-3/checkpoint-69/trainer_state.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.5306122448979592,
|
3 |
+
"best_model_checkpoint": "rubert-tiny2-finetuned-classification\\run-3\\checkpoint-69",
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 69,
|
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_accuracy": 0.5306122448979592,
|
14 |
+
"eval_loss": 1.82464599609375,
|
15 |
+
"eval_runtime": 1.207,
|
16 |
+
"eval_samples_per_second": 202.983,
|
17 |
+
"eval_steps_per_second": 13.256,
|
18 |
+
"step": 69
|
19 |
+
}
|
20 |
+
],
|
21 |
+
"logging_steps": 500,
|
22 |
+
"max_steps": 138,
|
23 |
+
"num_input_tokens_seen": 0,
|
24 |
+
"num_train_epochs": 2,
|
25 |
+
"save_steps": 500,
|
26 |
+
"total_flos": 0,
|
27 |
+
"train_batch_size": 32,
|
28 |
+
"trial_name": null,
|
29 |
+
"trial_params": {
|
30 |
+
"learning_rate": 4.261436385170268e-05,
|
31 |
+
"num_train_epochs": 2,
|
32 |
+
"per_device_train_batch_size": 32,
|
33 |
+
"seed": 19
|
34 |
+
}
|
35 |
+
}
|
run-3/checkpoint-69/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:de7dfb12ae78b2a3a5a3bdb07396295b69e9f91585b8680920fa4eacf5f3c08f
|
3 |
+
size 4728
|
run-3/checkpoint-69/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
runs/Jan15_00-51-52_DESKTOP-RFEED41/events.out.tfevents.1705269786.DESKTOP-RFEED41.20976.18
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 sha256:5c0b41d4be757b109a27575788a0e87ad68f3496d586c027a3496cb801164d04
|
3 |
+
size 7704
|
runs/Jan15_00-51-52_DESKTOP-RFEED41/events.out.tfevents.1705270920.DESKTOP-RFEED41.20976.19
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7d7c2e12c97bbbe4bc463fb07d29188015d2b79836cf0f52c8d6c5410d3193a9
|
3 |
+
size 5946
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4728
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:de7dfb12ae78b2a3a5a3bdb07396295b69e9f91585b8680920fa4eacf5f3c08f
|
3 |
size 4728
|