Training in progress, step 10
Browse files- added_tokens.json +17 -0
- checkpoint-10/added_tokens.json +17 -0
- checkpoint-10/config.json +45 -0
- checkpoint-10/optimizer.pt +3 -0
- checkpoint-10/pytorch_model.bin +3 -0
- checkpoint-10/rng_state.pth +3 -0
- checkpoint-10/scaler.pt +3 -0
- checkpoint-10/scheduler.pt +3 -0
- checkpoint-10/special_tokens_map.json +25 -0
- checkpoint-10/spm.model +3 -0
- checkpoint-10/tokenizer.json +0 -0
- checkpoint-10/tokenizer_config.json +32 -0
- checkpoint-10/trainer_state.json +30 -0
- checkpoint-10/training_args.bin +3 -0
- config.json +45 -0
- pytorch_model.bin +3 -0
- runs/Nov26_03-30-10_f19dc631087e/1669433434.984191/events.out.tfevents.1669433434.f19dc631087e.2463.1 +3 -0
- runs/Nov26_03-30-10_f19dc631087e/events.out.tfevents.1669433434.f19dc631087e.2463.0 +3 -0
- special_tokens_map.json +25 -0
- spm.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +32 -0
- training_args.bin +3 -0
added_tokens.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[CLAIM_END]": 128006,
|
3 |
+
"[CLAIM_START]": 128005,
|
4 |
+
"[CONCLUDING STATEMENT_END]": 128014,
|
5 |
+
"[CONCLUDING STATEMENT_START]": 128013,
|
6 |
+
"[COUNTERCLAIM_END]": 128008,
|
7 |
+
"[COUNTERCLAIM_START]": 128007,
|
8 |
+
"[EVIDENCE_END]": 128012,
|
9 |
+
"[EVIDENCE_START]": 128011,
|
10 |
+
"[LEAD_END]": 128002,
|
11 |
+
"[LEAD_START]": 128001,
|
12 |
+
"[MASK]": 128000,
|
13 |
+
"[POSITION_END]": 128004,
|
14 |
+
"[POSITION_START]": 128003,
|
15 |
+
"[REBUTTAL_END]": 128010,
|
16 |
+
"[REBUTTAL_START]": 128009
|
17 |
+
}
|
checkpoint-10/added_tokens.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[CLAIM_END]": 128006,
|
3 |
+
"[CLAIM_START]": 128005,
|
4 |
+
"[CONCLUDING STATEMENT_END]": 128014,
|
5 |
+
"[CONCLUDING STATEMENT_START]": 128013,
|
6 |
+
"[COUNTERCLAIM_END]": 128008,
|
7 |
+
"[COUNTERCLAIM_START]": 128007,
|
8 |
+
"[EVIDENCE_END]": 128012,
|
9 |
+
"[EVIDENCE_START]": 128011,
|
10 |
+
"[LEAD_END]": 128002,
|
11 |
+
"[LEAD_START]": 128001,
|
12 |
+
"[MASK]": 128000,
|
13 |
+
"[POSITION_END]": 128004,
|
14 |
+
"[POSITION_START]": 128003,
|
15 |
+
"[REBUTTAL_END]": 128010,
|
16 |
+
"[REBUTTAL_START]": 128009
|
17 |
+
}
|
checkpoint-10/config.json
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "TTian/deberta-classifier-feedback-1024-pseudo",
|
3 |
+
"architectures": [
|
4 |
+
"DebertaV2ForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"hidden_act": "gelu",
|
8 |
+
"hidden_dropout_prob": 0.1,
|
9 |
+
"hidden_size": 1024,
|
10 |
+
"id2label": {
|
11 |
+
"0": "LABEL_0",
|
12 |
+
"1": "LABEL_1",
|
13 |
+
"2": "LABEL_2"
|
14 |
+
},
|
15 |
+
"initializer_range": 0.02,
|
16 |
+
"intermediate_size": 4096,
|
17 |
+
"label2id": {
|
18 |
+
"LABEL_0": 0,
|
19 |
+
"LABEL_1": 1,
|
20 |
+
"LABEL_2": 2
|
21 |
+
},
|
22 |
+
"layer_norm_eps": 1e-07,
|
23 |
+
"max_position_embeddings": 1024,
|
24 |
+
"max_relative_positions": 128,
|
25 |
+
"model_type": "deberta-v2",
|
26 |
+
"norm_rel_ebd": "layer_norm",
|
27 |
+
"num_attention_heads": 16,
|
28 |
+
"num_hidden_layers": 24,
|
29 |
+
"pad_token_id": 0,
|
30 |
+
"pooler_dropout": 0,
|
31 |
+
"pooler_hidden_act": "gelu",
|
32 |
+
"pooler_hidden_size": 1024,
|
33 |
+
"pos_att_type": [
|
34 |
+
"p2c",
|
35 |
+
"c2p"
|
36 |
+
],
|
37 |
+
"position_biased_input": false,
|
38 |
+
"position_buckets": 256,
|
39 |
+
"relative_attention": true,
|
40 |
+
"share_att_key": true,
|
41 |
+
"torch_dtype": "float32",
|
42 |
+
"transformers_version": "4.24.0",
|
43 |
+
"type_vocab_size": 0,
|
44 |
+
"vocab_size": 128100
|
45 |
+
}
|
checkpoint-10/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c9058d120f116c9f075760a3cecfadde6c48be5f6c723f4bbe6e465cb2d3b617
|
3 |
+
size 3472349601
|
checkpoint-10/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c67ed9579fbf92ad582171655d9a63cf47be3ee9a1a837842b2683db66360847
|
3 |
+
size 1736202543
|
checkpoint-10/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:32a20052bcd699bfa424ab9ab607dae575a69b96010be796c6e0d6996bd6ea4a
|
3 |
+
size 14503
|
checkpoint-10/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:20e4b012b4b9ab1daa876390beea4afff370d4f83e20e939f16cdf1855daf52f
|
3 |
+
size 559
|
checkpoint-10/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:156d8d59fa6abdae5154be64292e80cfd2e7110c86b2201d4b65c651360c1fa9
|
3 |
+
size 623
|
checkpoint-10/special_tokens_map.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"[LEAD_START]",
|
4 |
+
"[LEAD_END]",
|
5 |
+
"[POSITION_START]",
|
6 |
+
"[POSITION_END]",
|
7 |
+
"[CLAIM_START]",
|
8 |
+
"[CLAIM_END]",
|
9 |
+
"[COUNTERCLAIM_START]",
|
10 |
+
"[COUNTERCLAIM_END]",
|
11 |
+
"[REBUTTAL_START]",
|
12 |
+
"[REBUTTAL_END]",
|
13 |
+
"[EVIDENCE_START]",
|
14 |
+
"[EVIDENCE_END]",
|
15 |
+
"[CONCLUDING STATEMENT_START]",
|
16 |
+
"[CONCLUDING STATEMENT_END]"
|
17 |
+
],
|
18 |
+
"bos_token": "[CLS]",
|
19 |
+
"cls_token": "[CLS]",
|
20 |
+
"eos_token": "[SEP]",
|
21 |
+
"mask_token": "[MASK]",
|
22 |
+
"pad_token": "[PAD]",
|
23 |
+
"sep_token": "[SEP]",
|
24 |
+
"unk_token": "[UNK]"
|
25 |
+
}
|
checkpoint-10/spm.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
|
3 |
+
size 2464616
|
checkpoint-10/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-10/tokenizer_config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"[LEAD_START]",
|
4 |
+
"[LEAD_END]",
|
5 |
+
"[POSITION_START]",
|
6 |
+
"[POSITION_END]",
|
7 |
+
"[CLAIM_START]",
|
8 |
+
"[CLAIM_END]",
|
9 |
+
"[COUNTERCLAIM_START]",
|
10 |
+
"[COUNTERCLAIM_END]",
|
11 |
+
"[REBUTTAL_START]",
|
12 |
+
"[REBUTTAL_END]",
|
13 |
+
"[EVIDENCE_START]",
|
14 |
+
"[EVIDENCE_END]",
|
15 |
+
"[CONCLUDING STATEMENT_START]",
|
16 |
+
"[CONCLUDING STATEMENT_END]"
|
17 |
+
],
|
18 |
+
"bos_token": "[CLS]",
|
19 |
+
"cls_token": "[CLS]",
|
20 |
+
"do_lower_case": false,
|
21 |
+
"eos_token": "[SEP]",
|
22 |
+
"mask_token": "[MASK]",
|
23 |
+
"name_or_path": "TTian/deberta-classifier-feedback-1024-pseudo",
|
24 |
+
"pad_token": "[PAD]",
|
25 |
+
"sep_token": "[SEP]",
|
26 |
+
"sp_model_kwargs": {},
|
27 |
+
"special_tokens_map_file": null,
|
28 |
+
"split_by_punct": false,
|
29 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
30 |
+
"unk_token": "[UNK]",
|
31 |
+
"vocab_type": "spm"
|
32 |
+
}
|
checkpoint-10/trainer_state.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.5888153910636902,
|
3 |
+
"best_model_checkpoint": "deberta-classifier-feedback-1024-pseudo-final/checkpoint-10",
|
4 |
+
"epoch": 0.0423728813559322,
|
5 |
+
"global_step": 10,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.04,
|
12 |
+
"learning_rate": 1.9576271186440678e-05,
|
13 |
+
"loss": 0.5814,
|
14 |
+
"step": 10
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.04,
|
18 |
+
"eval_loss": 0.5888153910636902,
|
19 |
+
"eval_runtime": 18.2433,
|
20 |
+
"eval_samples_per_second": 23.022,
|
21 |
+
"eval_steps_per_second": 2.905,
|
22 |
+
"step": 10
|
23 |
+
}
|
24 |
+
],
|
25 |
+
"max_steps": 472,
|
26 |
+
"num_train_epochs": 2,
|
27 |
+
"total_flos": 295709116548768.0,
|
28 |
+
"trial_name": null,
|
29 |
+
"trial_params": null
|
30 |
+
}
|
checkpoint-10/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:48b5fec3efb2c118a302d92fce79c45311f12529781bf0db59fab4b9060a4ffc
|
3 |
+
size 3439
|
config.json
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "TTian/deberta-classifier-feedback-1024-pseudo",
|
3 |
+
"architectures": [
|
4 |
+
"DebertaV2ForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"hidden_act": "gelu",
|
8 |
+
"hidden_dropout_prob": 0.1,
|
9 |
+
"hidden_size": 1024,
|
10 |
+
"id2label": {
|
11 |
+
"0": "LABEL_0",
|
12 |
+
"1": "LABEL_1",
|
13 |
+
"2": "LABEL_2"
|
14 |
+
},
|
15 |
+
"initializer_range": 0.02,
|
16 |
+
"intermediate_size": 4096,
|
17 |
+
"label2id": {
|
18 |
+
"LABEL_0": 0,
|
19 |
+
"LABEL_1": 1,
|
20 |
+
"LABEL_2": 2
|
21 |
+
},
|
22 |
+
"layer_norm_eps": 1e-07,
|
23 |
+
"max_position_embeddings": 1024,
|
24 |
+
"max_relative_positions": 128,
|
25 |
+
"model_type": "deberta-v2",
|
26 |
+
"norm_rel_ebd": "layer_norm",
|
27 |
+
"num_attention_heads": 16,
|
28 |
+
"num_hidden_layers": 24,
|
29 |
+
"pad_token_id": 0,
|
30 |
+
"pooler_dropout": 0,
|
31 |
+
"pooler_hidden_act": "gelu",
|
32 |
+
"pooler_hidden_size": 1024,
|
33 |
+
"pos_att_type": [
|
34 |
+
"p2c",
|
35 |
+
"c2p"
|
36 |
+
],
|
37 |
+
"position_biased_input": false,
|
38 |
+
"position_buckets": 256,
|
39 |
+
"relative_attention": true,
|
40 |
+
"share_att_key": true,
|
41 |
+
"torch_dtype": "float32",
|
42 |
+
"transformers_version": "4.24.0",
|
43 |
+
"type_vocab_size": 0,
|
44 |
+
"vocab_size": 128100
|
45 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c67ed9579fbf92ad582171655d9a63cf47be3ee9a1a837842b2683db66360847
|
3 |
+
size 1736202543
|
runs/Nov26_03-30-10_f19dc631087e/1669433434.984191/events.out.tfevents.1669433434.f19dc631087e.2463.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:761496240271872752cf7afd3ccd39f3767bd18c4600622e083ed86593ac0e99
|
3 |
+
size 5567
|
runs/Nov26_03-30-10_f19dc631087e/events.out.tfevents.1669433434.f19dc631087e.2463.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c1407a8b3196f5e133af9fa532c7bd1a2d308e1954075e2b209034e57c624a5
|
3 |
+
size 4616
|
special_tokens_map.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"[LEAD_START]",
|
4 |
+
"[LEAD_END]",
|
5 |
+
"[POSITION_START]",
|
6 |
+
"[POSITION_END]",
|
7 |
+
"[CLAIM_START]",
|
8 |
+
"[CLAIM_END]",
|
9 |
+
"[COUNTERCLAIM_START]",
|
10 |
+
"[COUNTERCLAIM_END]",
|
11 |
+
"[REBUTTAL_START]",
|
12 |
+
"[REBUTTAL_END]",
|
13 |
+
"[EVIDENCE_START]",
|
14 |
+
"[EVIDENCE_END]",
|
15 |
+
"[CONCLUDING STATEMENT_START]",
|
16 |
+
"[CONCLUDING STATEMENT_END]"
|
17 |
+
],
|
18 |
+
"bos_token": "[CLS]",
|
19 |
+
"cls_token": "[CLS]",
|
20 |
+
"eos_token": "[SEP]",
|
21 |
+
"mask_token": "[MASK]",
|
22 |
+
"pad_token": "[PAD]",
|
23 |
+
"sep_token": "[SEP]",
|
24 |
+
"unk_token": "[UNK]"
|
25 |
+
}
|
spm.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
|
3 |
+
size 2464616
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"[LEAD_START]",
|
4 |
+
"[LEAD_END]",
|
5 |
+
"[POSITION_START]",
|
6 |
+
"[POSITION_END]",
|
7 |
+
"[CLAIM_START]",
|
8 |
+
"[CLAIM_END]",
|
9 |
+
"[COUNTERCLAIM_START]",
|
10 |
+
"[COUNTERCLAIM_END]",
|
11 |
+
"[REBUTTAL_START]",
|
12 |
+
"[REBUTTAL_END]",
|
13 |
+
"[EVIDENCE_START]",
|
14 |
+
"[EVIDENCE_END]",
|
15 |
+
"[CONCLUDING STATEMENT_START]",
|
16 |
+
"[CONCLUDING STATEMENT_END]"
|
17 |
+
],
|
18 |
+
"bos_token": "[CLS]",
|
19 |
+
"cls_token": "[CLS]",
|
20 |
+
"do_lower_case": false,
|
21 |
+
"eos_token": "[SEP]",
|
22 |
+
"mask_token": "[MASK]",
|
23 |
+
"name_or_path": "TTian/deberta-classifier-feedback-1024-pseudo",
|
24 |
+
"pad_token": "[PAD]",
|
25 |
+
"sep_token": "[SEP]",
|
26 |
+
"sp_model_kwargs": {},
|
27 |
+
"special_tokens_map_file": null,
|
28 |
+
"split_by_punct": false,
|
29 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
30 |
+
"unk_token": "[UNK]",
|
31 |
+
"vocab_type": "spm"
|
32 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:48b5fec3efb2c118a302d92fce79c45311f12529781bf0db59fab4b9060a4ffc
|
3 |
+
size 3439
|