Upload 59 files
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- checkpoint-1000/config.json +48 -0
- checkpoint-1000/optimizer.pt +3 -0
- checkpoint-1000/pytorch_model.bin +3 -0
- checkpoint-1000/rng_state.pth +3 -0
- checkpoint-1000/scheduler.pt +3 -0
- checkpoint-1000/trainer_state.json +28 -0
- checkpoint-1000/training_args.bin +3 -0
- checkpoint-1500/config.json +48 -0
- checkpoint-1500/optimizer.pt +3 -0
- checkpoint-1500/pytorch_model.bin +3 -0
- checkpoint-1500/rng_state.pth +3 -0
- checkpoint-1500/scheduler.pt +3 -0
- checkpoint-1500/trainer_state.json +34 -0
- checkpoint-1500/training_args.bin +3 -0
- checkpoint-2000/config.json +48 -0
- checkpoint-2000/optimizer.pt +3 -0
- checkpoint-2000/pytorch_model.bin +3 -0
- checkpoint-2000/rng_state.pth +3 -0
- checkpoint-2000/scheduler.pt +3 -0
- checkpoint-2000/trainer_state.json +40 -0
- checkpoint-2000/training_args.bin +3 -0
- checkpoint-2500/config.json +48 -0
- checkpoint-2500/optimizer.pt +3 -0
- checkpoint-2500/pytorch_model.bin +3 -0
- checkpoint-2500/rng_state.pth +3 -0
- checkpoint-2500/scheduler.pt +3 -0
- checkpoint-2500/trainer_state.json +46 -0
- checkpoint-2500/training_args.bin +3 -0
- checkpoint-3000/config.json +48 -0
- checkpoint-3000/optimizer.pt +3 -0
- checkpoint-3000/pytorch_model.bin +3 -0
- checkpoint-3000/rng_state.pth +3 -0
- checkpoint-3000/scheduler.pt +3 -0
- checkpoint-3000/trainer_state.json +52 -0
- checkpoint-3000/training_args.bin +3 -0
- checkpoint-3500/config.json +48 -0
- checkpoint-3500/optimizer.pt +3 -0
- checkpoint-3500/pytorch_model.bin +3 -0
- checkpoint-3500/rng_state.pth +3 -0
- checkpoint-3500/scheduler.pt +3 -0
- checkpoint-3500/trainer_state.json +58 -0
- checkpoint-3500/training_args.bin +3 -0
- checkpoint-4000/config.json +48 -0
- checkpoint-4000/optimizer.pt +3 -0
- checkpoint-4000/pytorch_model.bin +3 -0
- checkpoint-4000/rng_state.pth +3 -0
- checkpoint-4000/scheduler.pt +3 -0
- checkpoint-4000/trainer_state.json +64 -0
- checkpoint-4000/training_args.bin +3 -0
- checkpoint-500/config.json +48 -0
checkpoint-1000/config.json
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "albert-base-v2",
|
3 |
+
"architectures": [
|
4 |
+
"AlbertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0,
|
7 |
+
"bos_token_id": 2,
|
8 |
+
"classifier_dropout_prob": 0.1,
|
9 |
+
"down_scale_factor": 1,
|
10 |
+
"embedding_size": 128,
|
11 |
+
"eos_token_id": 3,
|
12 |
+
"gap_size": 0,
|
13 |
+
"hidden_act": "gelu_new",
|
14 |
+
"hidden_dropout_prob": 0,
|
15 |
+
"hidden_size": 768,
|
16 |
+
"id2label": {
|
17 |
+
"0": "LABEL_0",
|
18 |
+
"1": "LABEL_1",
|
19 |
+
"2": "LABEL_2",
|
20 |
+
"3": "LABEL_3",
|
21 |
+
"4": "LABEL_4"
|
22 |
+
},
|
23 |
+
"initializer_range": 0.02,
|
24 |
+
"inner_group_num": 1,
|
25 |
+
"intermediate_size": 3072,
|
26 |
+
"label2id": {
|
27 |
+
"LABEL_0": 0,
|
28 |
+
"LABEL_1": 1,
|
29 |
+
"LABEL_2": 2,
|
30 |
+
"LABEL_3": 3,
|
31 |
+
"LABEL_4": 4
|
32 |
+
},
|
33 |
+
"layer_norm_eps": 1e-12,
|
34 |
+
"max_position_embeddings": 512,
|
35 |
+
"model_type": "albert",
|
36 |
+
"net_structure_type": 0,
|
37 |
+
"num_attention_heads": 12,
|
38 |
+
"num_hidden_groups": 1,
|
39 |
+
"num_hidden_layers": 12,
|
40 |
+
"num_memory_blocks": 0,
|
41 |
+
"pad_token_id": 0,
|
42 |
+
"position_embedding_type": "absolute",
|
43 |
+
"problem_type": "single_label_classification",
|
44 |
+
"torch_dtype": "float32",
|
45 |
+
"transformers_version": "4.30.2",
|
46 |
+
"type_vocab_size": 2,
|
47 |
+
"vocab_size": 30000
|
48 |
+
}
|
checkpoint-1000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5162cdc7e150c38199a0bf2f6b022e86fe4e5fab0a4b1571eb3cfd1e04c3595a
|
3 |
+
size 93515251
|
checkpoint-1000/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:287a721123004c8d73c220ae75a7e6b149cf0be72e47e01c77e97b730ce43f39
|
3 |
+
size 46763397
|
checkpoint-1000/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ee7b70f7fa47ac37bcbe098e2b10c20b3b195f8c1766739e3db895348a26874
|
3 |
+
size 14575
|
checkpoint-1000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:084ebba0eb2a420ffdfb3098966cebfb8672516d6cdb7cb9bd358081a446703c
|
3 |
+
size 627
|
checkpoint-1000/trainer_state.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.4452359750667854,
|
5 |
+
"global_step": 1000,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.22,
|
12 |
+
"learning_rate": 5e-05,
|
13 |
+
"loss": 1.3082,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.45,
|
18 |
+
"learning_rate": 4.37374749498998e-05,
|
19 |
+
"loss": 1.0848,
|
20 |
+
"step": 1000
|
21 |
+
}
|
22 |
+
],
|
23 |
+
"max_steps": 4492,
|
24 |
+
"num_train_epochs": 2,
|
25 |
+
"total_flos": 382483021824000.0,
|
26 |
+
"trial_name": null,
|
27 |
+
"trial_params": null
|
28 |
+
}
|
checkpoint-1000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:69c74f0fea927ae5a6dd93c20442abe9cb0ec0c27b1feb0ae3d88288eefccf96
|
3 |
+
size 3899
|
checkpoint-1500/config.json
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "albert-base-v2",
|
3 |
+
"architectures": [
|
4 |
+
"AlbertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0,
|
7 |
+
"bos_token_id": 2,
|
8 |
+
"classifier_dropout_prob": 0.1,
|
9 |
+
"down_scale_factor": 1,
|
10 |
+
"embedding_size": 128,
|
11 |
+
"eos_token_id": 3,
|
12 |
+
"gap_size": 0,
|
13 |
+
"hidden_act": "gelu_new",
|
14 |
+
"hidden_dropout_prob": 0,
|
15 |
+
"hidden_size": 768,
|
16 |
+
"id2label": {
|
17 |
+
"0": "LABEL_0",
|
18 |
+
"1": "LABEL_1",
|
19 |
+
"2": "LABEL_2",
|
20 |
+
"3": "LABEL_3",
|
21 |
+
"4": "LABEL_4"
|
22 |
+
},
|
23 |
+
"initializer_range": 0.02,
|
24 |
+
"inner_group_num": 1,
|
25 |
+
"intermediate_size": 3072,
|
26 |
+
"label2id": {
|
27 |
+
"LABEL_0": 0,
|
28 |
+
"LABEL_1": 1,
|
29 |
+
"LABEL_2": 2,
|
30 |
+
"LABEL_3": 3,
|
31 |
+
"LABEL_4": 4
|
32 |
+
},
|
33 |
+
"layer_norm_eps": 1e-12,
|
34 |
+
"max_position_embeddings": 512,
|
35 |
+
"model_type": "albert",
|
36 |
+
"net_structure_type": 0,
|
37 |
+
"num_attention_heads": 12,
|
38 |
+
"num_hidden_groups": 1,
|
39 |
+
"num_hidden_layers": 12,
|
40 |
+
"num_memory_blocks": 0,
|
41 |
+
"pad_token_id": 0,
|
42 |
+
"position_embedding_type": "absolute",
|
43 |
+
"problem_type": "single_label_classification",
|
44 |
+
"torch_dtype": "float32",
|
45 |
+
"transformers_version": "4.30.2",
|
46 |
+
"type_vocab_size": 2,
|
47 |
+
"vocab_size": 30000
|
48 |
+
}
|
checkpoint-1500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:631adef8f48cc879fc1772f0a4ab1210dbad8d9c5355bc16922c4432659e0e07
|
3 |
+
size 93515251
|
checkpoint-1500/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e078665c7f18286737bf025cff999343ec68bc3f367c66f6e8c7a1baa40a6b3e
|
3 |
+
size 46763397
|
checkpoint-1500/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8cf83649e305fc92e7f425c75319d8d8f11a58bbf5ed6ad6d1f21875f76f9f51
|
3 |
+
size 14575
|
checkpoint-1500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e94bfc714f526b0ce075c39d8e757ea14a02823f50580140d9d9927a3c16307f
|
3 |
+
size 627
|
checkpoint-1500/trainer_state.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.667853962600178,
|
5 |
+
"global_step": 1500,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.22,
|
12 |
+
"learning_rate": 5e-05,
|
13 |
+
"loss": 1.3082,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.45,
|
18 |
+
"learning_rate": 4.37374749498998e-05,
|
19 |
+
"loss": 1.0848,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.67,
|
24 |
+
"learning_rate": 3.74749498997996e-05,
|
25 |
+
"loss": 1.0004,
|
26 |
+
"step": 1500
|
27 |
+
}
|
28 |
+
],
|
29 |
+
"max_steps": 4492,
|
30 |
+
"num_train_epochs": 2,
|
31 |
+
"total_flos": 573724532736000.0,
|
32 |
+
"trial_name": null,
|
33 |
+
"trial_params": null
|
34 |
+
}
|
checkpoint-1500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:69c74f0fea927ae5a6dd93c20442abe9cb0ec0c27b1feb0ae3d88288eefccf96
|
3 |
+
size 3899
|
checkpoint-2000/config.json
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "albert-base-v2",
|
3 |
+
"architectures": [
|
4 |
+
"AlbertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0,
|
7 |
+
"bos_token_id": 2,
|
8 |
+
"classifier_dropout_prob": 0.1,
|
9 |
+
"down_scale_factor": 1,
|
10 |
+
"embedding_size": 128,
|
11 |
+
"eos_token_id": 3,
|
12 |
+
"gap_size": 0,
|
13 |
+
"hidden_act": "gelu_new",
|
14 |
+
"hidden_dropout_prob": 0,
|
15 |
+
"hidden_size": 768,
|
16 |
+
"id2label": {
|
17 |
+
"0": "LABEL_0",
|
18 |
+
"1": "LABEL_1",
|
19 |
+
"2": "LABEL_2",
|
20 |
+
"3": "LABEL_3",
|
21 |
+
"4": "LABEL_4"
|
22 |
+
},
|
23 |
+
"initializer_range": 0.02,
|
24 |
+
"inner_group_num": 1,
|
25 |
+
"intermediate_size": 3072,
|
26 |
+
"label2id": {
|
27 |
+
"LABEL_0": 0,
|
28 |
+
"LABEL_1": 1,
|
29 |
+
"LABEL_2": 2,
|
30 |
+
"LABEL_3": 3,
|
31 |
+
"LABEL_4": 4
|
32 |
+
},
|
33 |
+
"layer_norm_eps": 1e-12,
|
34 |
+
"max_position_embeddings": 512,
|
35 |
+
"model_type": "albert",
|
36 |
+
"net_structure_type": 0,
|
37 |
+
"num_attention_heads": 12,
|
38 |
+
"num_hidden_groups": 1,
|
39 |
+
"num_hidden_layers": 12,
|
40 |
+
"num_memory_blocks": 0,
|
41 |
+
"pad_token_id": 0,
|
42 |
+
"position_embedding_type": "absolute",
|
43 |
+
"problem_type": "single_label_classification",
|
44 |
+
"torch_dtype": "float32",
|
45 |
+
"transformers_version": "4.30.2",
|
46 |
+
"type_vocab_size": 2,
|
47 |
+
"vocab_size": 30000
|
48 |
+
}
|
checkpoint-2000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d3e122441167c8b2acaae70972155a403a7af29ff8205ad3895b1ee87c23e8f1
|
3 |
+
size 93515251
|
checkpoint-2000/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a6a2747097db5358954b136384a9032ab622e51e4496c59fcc9bf6f19ad75258
|
3 |
+
size 46763397
|
checkpoint-2000/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c41916c11c52ae9eb1f8eb57fa5e92ab81b4719df8e81cf9955d611fff46c648
|
3 |
+
size 14575
|
checkpoint-2000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:514cee12839556455629fe90048db0fbd080eb8fab678afa2636814da5a87b0b
|
3 |
+
size 627
|
checkpoint-2000/trainer_state.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.8904719501335708,
|
5 |
+
"global_step": 2000,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.22,
|
12 |
+
"learning_rate": 5e-05,
|
13 |
+
"loss": 1.3082,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.45,
|
18 |
+
"learning_rate": 4.37374749498998e-05,
|
19 |
+
"loss": 1.0848,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.67,
|
24 |
+
"learning_rate": 3.74749498997996e-05,
|
25 |
+
"loss": 1.0004,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.89,
|
30 |
+
"learning_rate": 3.12124248496994e-05,
|
31 |
+
"loss": 0.9697,
|
32 |
+
"step": 2000
|
33 |
+
}
|
34 |
+
],
|
35 |
+
"max_steps": 4492,
|
36 |
+
"num_train_epochs": 2,
|
37 |
+
"total_flos": 764966043648000.0,
|
38 |
+
"trial_name": null,
|
39 |
+
"trial_params": null
|
40 |
+
}
|
checkpoint-2000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:69c74f0fea927ae5a6dd93c20442abe9cb0ec0c27b1feb0ae3d88288eefccf96
|
3 |
+
size 3899
|
checkpoint-2500/config.json
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "albert-base-v2",
|
3 |
+
"architectures": [
|
4 |
+
"AlbertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0,
|
7 |
+
"bos_token_id": 2,
|
8 |
+
"classifier_dropout_prob": 0.1,
|
9 |
+
"down_scale_factor": 1,
|
10 |
+
"embedding_size": 128,
|
11 |
+
"eos_token_id": 3,
|
12 |
+
"gap_size": 0,
|
13 |
+
"hidden_act": "gelu_new",
|
14 |
+
"hidden_dropout_prob": 0,
|
15 |
+
"hidden_size": 768,
|
16 |
+
"id2label": {
|
17 |
+
"0": "LABEL_0",
|
18 |
+
"1": "LABEL_1",
|
19 |
+
"2": "LABEL_2",
|
20 |
+
"3": "LABEL_3",
|
21 |
+
"4": "LABEL_4"
|
22 |
+
},
|
23 |
+
"initializer_range": 0.02,
|
24 |
+
"inner_group_num": 1,
|
25 |
+
"intermediate_size": 3072,
|
26 |
+
"label2id": {
|
27 |
+
"LABEL_0": 0,
|
28 |
+
"LABEL_1": 1,
|
29 |
+
"LABEL_2": 2,
|
30 |
+
"LABEL_3": 3,
|
31 |
+
"LABEL_4": 4
|
32 |
+
},
|
33 |
+
"layer_norm_eps": 1e-12,
|
34 |
+
"max_position_embeddings": 512,
|
35 |
+
"model_type": "albert",
|
36 |
+
"net_structure_type": 0,
|
37 |
+
"num_attention_heads": 12,
|
38 |
+
"num_hidden_groups": 1,
|
39 |
+
"num_hidden_layers": 12,
|
40 |
+
"num_memory_blocks": 0,
|
41 |
+
"pad_token_id": 0,
|
42 |
+
"position_embedding_type": "absolute",
|
43 |
+
"problem_type": "single_label_classification",
|
44 |
+
"torch_dtype": "float32",
|
45 |
+
"transformers_version": "4.30.2",
|
46 |
+
"type_vocab_size": 2,
|
47 |
+
"vocab_size": 30000
|
48 |
+
}
|
checkpoint-2500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1926b9f4407cddf2624857403d0a49eaed378a219e2395a47b5d58712e20b199
|
3 |
+
size 93515251
|
checkpoint-2500/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ee437a17f548e4badf2b4432a5ed01d1d00c2e411f797e1ed5c30c2328b5146
|
3 |
+
size 46763397
|
checkpoint-2500/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:50a44eb54b4705cdd4d53277365f55b77947a284fdf9040322c04e7f4228ea32
|
3 |
+
size 14575
|
checkpoint-2500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a34cf069b87bb3938fb90cccd941ef9160d044d428876ee79ec13296d8ba0514
|
3 |
+
size 627
|
checkpoint-2500/trainer_state.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.1130899376669634,
|
5 |
+
"global_step": 2500,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.22,
|
12 |
+
"learning_rate": 5e-05,
|
13 |
+
"loss": 1.3082,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.45,
|
18 |
+
"learning_rate": 4.37374749498998e-05,
|
19 |
+
"loss": 1.0848,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.67,
|
24 |
+
"learning_rate": 3.74749498997996e-05,
|
25 |
+
"loss": 1.0004,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.89,
|
30 |
+
"learning_rate": 3.12124248496994e-05,
|
31 |
+
"loss": 0.9697,
|
32 |
+
"step": 2000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 1.11,
|
36 |
+
"learning_rate": 2.49498997995992e-05,
|
37 |
+
"loss": 0.9269,
|
38 |
+
"step": 2500
|
39 |
+
}
|
40 |
+
],
|
41 |
+
"max_steps": 4492,
|
42 |
+
"num_train_epochs": 2,
|
43 |
+
"total_flos": 955872881915904.0,
|
44 |
+
"trial_name": null,
|
45 |
+
"trial_params": null
|
46 |
+
}
|
checkpoint-2500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:69c74f0fea927ae5a6dd93c20442abe9cb0ec0c27b1feb0ae3d88288eefccf96
|
3 |
+
size 3899
|
checkpoint-3000/config.json
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "albert-base-v2",
|
3 |
+
"architectures": [
|
4 |
+
"AlbertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0,
|
7 |
+
"bos_token_id": 2,
|
8 |
+
"classifier_dropout_prob": 0.1,
|
9 |
+
"down_scale_factor": 1,
|
10 |
+
"embedding_size": 128,
|
11 |
+
"eos_token_id": 3,
|
12 |
+
"gap_size": 0,
|
13 |
+
"hidden_act": "gelu_new",
|
14 |
+
"hidden_dropout_prob": 0,
|
15 |
+
"hidden_size": 768,
|
16 |
+
"id2label": {
|
17 |
+
"0": "LABEL_0",
|
18 |
+
"1": "LABEL_1",
|
19 |
+
"2": "LABEL_2",
|
20 |
+
"3": "LABEL_3",
|
21 |
+
"4": "LABEL_4"
|
22 |
+
},
|
23 |
+
"initializer_range": 0.02,
|
24 |
+
"inner_group_num": 1,
|
25 |
+
"intermediate_size": 3072,
|
26 |
+
"label2id": {
|
27 |
+
"LABEL_0": 0,
|
28 |
+
"LABEL_1": 1,
|
29 |
+
"LABEL_2": 2,
|
30 |
+
"LABEL_3": 3,
|
31 |
+
"LABEL_4": 4
|
32 |
+
},
|
33 |
+
"layer_norm_eps": 1e-12,
|
34 |
+
"max_position_embeddings": 512,
|
35 |
+
"model_type": "albert",
|
36 |
+
"net_structure_type": 0,
|
37 |
+
"num_attention_heads": 12,
|
38 |
+
"num_hidden_groups": 1,
|
39 |
+
"num_hidden_layers": 12,
|
40 |
+
"num_memory_blocks": 0,
|
41 |
+
"pad_token_id": 0,
|
42 |
+
"position_embedding_type": "absolute",
|
43 |
+
"problem_type": "single_label_classification",
|
44 |
+
"torch_dtype": "float32",
|
45 |
+
"transformers_version": "4.30.2",
|
46 |
+
"type_vocab_size": 2,
|
47 |
+
"vocab_size": 30000
|
48 |
+
}
|
checkpoint-3000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:420dd64f23e2b68d1b1b96356faa6548bd8615714a986e6ee6234b2a4491c8d8
|
3 |
+
size 93515251
|
checkpoint-3000/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:220a74606152bcd98b4a03ad30c8ff16aaf209fd0087a5b832c1412bf5970408
|
3 |
+
size 46763397
|
checkpoint-3000/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1aa4f5ffc0dcf47df51739d4080dfd7ed935455d66016e6df47a65d8446b90f4
|
3 |
+
size 14575
|
checkpoint-3000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef3a9f861b0aa1ad29b5b6d84f6cb654853bead44b67a901b2a1205cae12b3c8
|
3 |
+
size 627
|
checkpoint-3000/trainer_state.json
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.335707925200356,
|
5 |
+
"global_step": 3000,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.22,
|
12 |
+
"learning_rate": 5e-05,
|
13 |
+
"loss": 1.3082,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.45,
|
18 |
+
"learning_rate": 4.37374749498998e-05,
|
19 |
+
"loss": 1.0848,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.67,
|
24 |
+
"learning_rate": 3.74749498997996e-05,
|
25 |
+
"loss": 1.0004,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.89,
|
30 |
+
"learning_rate": 3.12124248496994e-05,
|
31 |
+
"loss": 0.9697,
|
32 |
+
"step": 2000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 1.11,
|
36 |
+
"learning_rate": 2.49498997995992e-05,
|
37 |
+
"loss": 0.9269,
|
38 |
+
"step": 2500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 1.34,
|
42 |
+
"learning_rate": 1.8687374749499e-05,
|
43 |
+
"loss": 0.8869,
|
44 |
+
"step": 3000
|
45 |
+
}
|
46 |
+
],
|
47 |
+
"max_steps": 4492,
|
48 |
+
"num_train_epochs": 2,
|
49 |
+
"total_flos": 1147114392827904.0,
|
50 |
+
"trial_name": null,
|
51 |
+
"trial_params": null
|
52 |
+
}
|
checkpoint-3000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:69c74f0fea927ae5a6dd93c20442abe9cb0ec0c27b1feb0ae3d88288eefccf96
|
3 |
+
size 3899
|
checkpoint-3500/config.json
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "albert-base-v2",
|
3 |
+
"architectures": [
|
4 |
+
"AlbertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0,
|
7 |
+
"bos_token_id": 2,
|
8 |
+
"classifier_dropout_prob": 0.1,
|
9 |
+
"down_scale_factor": 1,
|
10 |
+
"embedding_size": 128,
|
11 |
+
"eos_token_id": 3,
|
12 |
+
"gap_size": 0,
|
13 |
+
"hidden_act": "gelu_new",
|
14 |
+
"hidden_dropout_prob": 0,
|
15 |
+
"hidden_size": 768,
|
16 |
+
"id2label": {
|
17 |
+
"0": "LABEL_0",
|
18 |
+
"1": "LABEL_1",
|
19 |
+
"2": "LABEL_2",
|
20 |
+
"3": "LABEL_3",
|
21 |
+
"4": "LABEL_4"
|
22 |
+
},
|
23 |
+
"initializer_range": 0.02,
|
24 |
+
"inner_group_num": 1,
|
25 |
+
"intermediate_size": 3072,
|
26 |
+
"label2id": {
|
27 |
+
"LABEL_0": 0,
|
28 |
+
"LABEL_1": 1,
|
29 |
+
"LABEL_2": 2,
|
30 |
+
"LABEL_3": 3,
|
31 |
+
"LABEL_4": 4
|
32 |
+
},
|
33 |
+
"layer_norm_eps": 1e-12,
|
34 |
+
"max_position_embeddings": 512,
|
35 |
+
"model_type": "albert",
|
36 |
+
"net_structure_type": 0,
|
37 |
+
"num_attention_heads": 12,
|
38 |
+
"num_hidden_groups": 1,
|
39 |
+
"num_hidden_layers": 12,
|
40 |
+
"num_memory_blocks": 0,
|
41 |
+
"pad_token_id": 0,
|
42 |
+
"position_embedding_type": "absolute",
|
43 |
+
"problem_type": "single_label_classification",
|
44 |
+
"torch_dtype": "float32",
|
45 |
+
"transformers_version": "4.30.2",
|
46 |
+
"type_vocab_size": 2,
|
47 |
+
"vocab_size": 30000
|
48 |
+
}
|
checkpoint-3500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:33a27e283edff413aeedb98a353a22c1c2cce0c9961588fa8cbb016f443ff514
|
3 |
+
size 93515251
|
checkpoint-3500/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1baeda303de05e8e64bfde4afcdf46197d5dc8c11ec34f00e4c920d05e739bbc
|
3 |
+
size 46763397
|
checkpoint-3500/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4780cc04e020a8b669447bf7cac1162c22e0ba149ef578c010549619f16d0224
|
3 |
+
size 14575
|
checkpoint-3500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:85a30d94ddf9dc46a22db21308fefceeafa29b5fef8c980796e0c5fd1af84e31
|
3 |
+
size 627
|
checkpoint-3500/trainer_state.json
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.558325912733749,
|
5 |
+
"global_step": 3500,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.22,
|
12 |
+
"learning_rate": 5e-05,
|
13 |
+
"loss": 1.3082,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.45,
|
18 |
+
"learning_rate": 4.37374749498998e-05,
|
19 |
+
"loss": 1.0848,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.67,
|
24 |
+
"learning_rate": 3.74749498997996e-05,
|
25 |
+
"loss": 1.0004,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.89,
|
30 |
+
"learning_rate": 3.12124248496994e-05,
|
31 |
+
"loss": 0.9697,
|
32 |
+
"step": 2000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 1.11,
|
36 |
+
"learning_rate": 2.49498997995992e-05,
|
37 |
+
"loss": 0.9269,
|
38 |
+
"step": 2500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 1.34,
|
42 |
+
"learning_rate": 1.8687374749499e-05,
|
43 |
+
"loss": 0.8869,
|
44 |
+
"step": 3000
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 1.56,
|
48 |
+
"learning_rate": 1.2424849699398798e-05,
|
49 |
+
"loss": 0.8755,
|
50 |
+
"step": 3500
|
51 |
+
}
|
52 |
+
],
|
53 |
+
"max_steps": 4492,
|
54 |
+
"num_train_epochs": 2,
|
55 |
+
"total_flos": 1338355903739904.0,
|
56 |
+
"trial_name": null,
|
57 |
+
"trial_params": null
|
58 |
+
}
|
checkpoint-3500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:69c74f0fea927ae5a6dd93c20442abe9cb0ec0c27b1feb0ae3d88288eefccf96
|
3 |
+
size 3899
|
checkpoint-4000/config.json
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "albert-base-v2",
|
3 |
+
"architectures": [
|
4 |
+
"AlbertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0,
|
7 |
+
"bos_token_id": 2,
|
8 |
+
"classifier_dropout_prob": 0.1,
|
9 |
+
"down_scale_factor": 1,
|
10 |
+
"embedding_size": 128,
|
11 |
+
"eos_token_id": 3,
|
12 |
+
"gap_size": 0,
|
13 |
+
"hidden_act": "gelu_new",
|
14 |
+
"hidden_dropout_prob": 0,
|
15 |
+
"hidden_size": 768,
|
16 |
+
"id2label": {
|
17 |
+
"0": "LABEL_0",
|
18 |
+
"1": "LABEL_1",
|
19 |
+
"2": "LABEL_2",
|
20 |
+
"3": "LABEL_3",
|
21 |
+
"4": "LABEL_4"
|
22 |
+
},
|
23 |
+
"initializer_range": 0.02,
|
24 |
+
"inner_group_num": 1,
|
25 |
+
"intermediate_size": 3072,
|
26 |
+
"label2id": {
|
27 |
+
"LABEL_0": 0,
|
28 |
+
"LABEL_1": 1,
|
29 |
+
"LABEL_2": 2,
|
30 |
+
"LABEL_3": 3,
|
31 |
+
"LABEL_4": 4
|
32 |
+
},
|
33 |
+
"layer_norm_eps": 1e-12,
|
34 |
+
"max_position_embeddings": 512,
|
35 |
+
"model_type": "albert",
|
36 |
+
"net_structure_type": 0,
|
37 |
+
"num_attention_heads": 12,
|
38 |
+
"num_hidden_groups": 1,
|
39 |
+
"num_hidden_layers": 12,
|
40 |
+
"num_memory_blocks": 0,
|
41 |
+
"pad_token_id": 0,
|
42 |
+
"position_embedding_type": "absolute",
|
43 |
+
"problem_type": "single_label_classification",
|
44 |
+
"torch_dtype": "float32",
|
45 |
+
"transformers_version": "4.30.2",
|
46 |
+
"type_vocab_size": 2,
|
47 |
+
"vocab_size": 30000
|
48 |
+
}
|
checkpoint-4000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1ee87f7e203e5c399b85d4b01bca398f5344b1c8e7514b66e630de26d00b577a
|
3 |
+
size 93515251
|
checkpoint-4000/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3ed86d884ee503ba33952cd210b5dca3d77fd3fa3a06fcfd220a9c559bdf181b
|
3 |
+
size 46763397
|
checkpoint-4000/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f1eb381eb47fc8f7a1209158a79968f4c1e6905e6dc1f0625995fe2c4d3427e7
|
3 |
+
size 14575
|
checkpoint-4000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b126e824777601f7f9b00008258a8085739902f490ab32ff2eea0b26ad0a9428
|
3 |
+
size 627
|
checkpoint-4000/trainer_state.json
ADDED
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.7809439002671414,
|
5 |
+
"global_step": 4000,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.22,
|
12 |
+
"learning_rate": 5e-05,
|
13 |
+
"loss": 1.3082,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.45,
|
18 |
+
"learning_rate": 4.37374749498998e-05,
|
19 |
+
"loss": 1.0848,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.67,
|
24 |
+
"learning_rate": 3.74749498997996e-05,
|
25 |
+
"loss": 1.0004,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.89,
|
30 |
+
"learning_rate": 3.12124248496994e-05,
|
31 |
+
"loss": 0.9697,
|
32 |
+
"step": 2000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 1.11,
|
36 |
+
"learning_rate": 2.49498997995992e-05,
|
37 |
+
"loss": 0.9269,
|
38 |
+
"step": 2500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 1.34,
|
42 |
+
"learning_rate": 1.8687374749499e-05,
|
43 |
+
"loss": 0.8869,
|
44 |
+
"step": 3000
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 1.56,
|
48 |
+
"learning_rate": 1.2424849699398798e-05,
|
49 |
+
"loss": 0.8755,
|
50 |
+
"step": 3500
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 1.78,
|
54 |
+
"learning_rate": 6.162324649298597e-06,
|
55 |
+
"loss": 0.8698,
|
56 |
+
"step": 4000
|
57 |
+
}
|
58 |
+
],
|
59 |
+
"max_steps": 4492,
|
60 |
+
"num_train_epochs": 2,
|
61 |
+
"total_flos": 1529597414651904.0,
|
62 |
+
"trial_name": null,
|
63 |
+
"trial_params": null
|
64 |
+
}
|
checkpoint-4000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:69c74f0fea927ae5a6dd93c20442abe9cb0ec0c27b1feb0ae3d88288eefccf96
|
3 |
+
size 3899
|
checkpoint-500/config.json
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "albert-base-v2",
|
3 |
+
"architectures": [
|
4 |
+
"AlbertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0,
|
7 |
+
"bos_token_id": 2,
|
8 |
+
"classifier_dropout_prob": 0.1,
|
9 |
+
"down_scale_factor": 1,
|
10 |
+
"embedding_size": 128,
|
11 |
+
"eos_token_id": 3,
|
12 |
+
"gap_size": 0,
|
13 |
+
"hidden_act": "gelu_new",
|
14 |
+
"hidden_dropout_prob": 0,
|
15 |
+
"hidden_size": 768,
|
16 |
+
"id2label": {
|
17 |
+
"0": "LABEL_0",
|
18 |
+
"1": "LABEL_1",
|
19 |
+
"2": "LABEL_2",
|
20 |
+
"3": "LABEL_3",
|
21 |
+
"4": "LABEL_4"
|
22 |
+
},
|
23 |
+
"initializer_range": 0.02,
|
24 |
+
"inner_group_num": 1,
|
25 |
+
"intermediate_size": 3072,
|
26 |
+
"label2id": {
|
27 |
+
"LABEL_0": 0,
|
28 |
+
"LABEL_1": 1,
|
29 |
+
"LABEL_2": 2,
|
30 |
+
"LABEL_3": 3,
|
31 |
+
"LABEL_4": 4
|
32 |
+
},
|
33 |
+
"layer_norm_eps": 1e-12,
|
34 |
+
"max_position_embeddings": 512,
|
35 |
+
"model_type": "albert",
|
36 |
+
"net_structure_type": 0,
|
37 |
+
"num_attention_heads": 12,
|
38 |
+
"num_hidden_groups": 1,
|
39 |
+
"num_hidden_layers": 12,
|
40 |
+
"num_memory_blocks": 0,
|
41 |
+
"pad_token_id": 0,
|
42 |
+
"position_embedding_type": "absolute",
|
43 |
+
"problem_type": "single_label_classification",
|
44 |
+
"torch_dtype": "float32",
|
45 |
+
"transformers_version": "4.30.2",
|
46 |
+
"type_vocab_size": 2,
|
47 |
+
"vocab_size": 30000
|
48 |
+
}
|