Hugging Face's logo

ninagroot
/
thesis

Text Classification
Transformers
TensorBoard
Safetensors
phi
Generated from Trainer
custom_code
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
ninagroot commited on
Commit
ef198a0
·
verified ·
1 Parent(s): 30036ca

Training in progress, epoch 1

Browse files
Files changed (47) hide show
  1. added_tokens.json +40 -0
  2. config.json +27 -17
  3. logs/events.out.tfevents.1704888842.gcn3.local.snellius.surf.nl.4159408.0 +3 -0
  4. logs/events.out.tfevents.1704889030.gcn3.local.snellius.surf.nl.4159408.1 +3 -0
  5. logs/events.out.tfevents.1704889166.gcn3.local.snellius.surf.nl.4159408.2 +3 -0
  6. logs/events.out.tfevents.1704897066.gcn64.local.snellius.surf.nl.1239098.0 +3 -0
  7. logs/events.out.tfevents.1704897705.gcn64.local.snellius.surf.nl.1386079.0 +3 -0
  8. logs/events.out.tfevents.1704897745.gcn64.local.snellius.surf.nl.1386079.1 +3 -0
  9. logs/events.out.tfevents.1704899062.gcn47.local.snellius.surf.nl.1950528.0 +3 -0
  10. logs/events.out.tfevents.1704899089.gcn47.local.snellius.surf.nl.1950528.1 +3 -0
  11. logs/events.out.tfevents.1704899177.gcn47.local.snellius.surf.nl.1950528.2 +3 -0
  12. logs/events.out.tfevents.1704899200.gcn47.local.snellius.surf.nl.1950528.3 +3 -0
  13. logs/events.out.tfevents.1704899288.gcn47.local.snellius.surf.nl.1950528.4 +3 -0
  14. logs/events.out.tfevents.1704899391.gcn47.local.snellius.surf.nl.1950528.5 +3 -0
  15. logs/events.out.tfevents.1704899467.gcn47.local.snellius.surf.nl.1950528.6 +3 -0
  16. logs/events.out.tfevents.1704899483.gcn47.local.snellius.surf.nl.1950528.7 +3 -0
  17. logs/events.out.tfevents.1704901120.gcn47.local.snellius.surf.nl.2087264.0 +3 -0
  18. logs/events.out.tfevents.1704901460.gcn47.local.snellius.surf.nl.2087264.1 +3 -0
  19. logs/events.out.tfevents.1704901522.gcn47.local.snellius.surf.nl.2087264.2 +3 -0
  20. logs/events.out.tfevents.1704901915.gcn47.local.snellius.surf.nl.2092771.0 +3 -0
  21. logs/events.out.tfevents.1705229438.gcn19.local.snellius.surf.nl.3508561.0 +3 -0
  22. logs/events.out.tfevents.1705233800.gcn66.local.snellius.surf.nl.130229.0 +3 -0
  23. logs/events.out.tfevents.1705234251.gcn66.local.snellius.surf.nl.165798.0 +3 -0
  24. logs/events.out.tfevents.1705234390.gcn66.local.snellius.surf.nl.165798.1 +3 -0
  25. logs/events.out.tfevents.1705234786.gcn66.local.snellius.surf.nl.202021.0 +3 -0
  26. logs/events.out.tfevents.1705234945.gcn66.local.snellius.surf.nl.202021.1 +3 -0
  27. logs/events.out.tfevents.1705235049.gcn66.local.snellius.surf.nl.202021.2 +3 -0
  28. logs/events.out.tfevents.1705235281.gcn66.local.snellius.surf.nl.204421.0 +3 -0
  29. logs/events.out.tfevents.1705236407.gcn7.local.snellius.surf.nl.3399315.0 +3 -0
  30. logs/events.out.tfevents.1705236621.gcn7.local.snellius.surf.nl.3401342.0 +3 -0
  31. merges.txt +0 -0
  32. run-0/checkpoint-527/config.json +34 -0
  33. run-0/checkpoint-527/model.safetensors +3 -0
  34. run-0/checkpoint-527/optimizer.pt +3 -0
  35. run-0/checkpoint-527/rng_state.pth +3 -0
  36. run-0/checkpoint-527/scheduler.pt +3 -0
  37. run-0/checkpoint-527/special_tokens_map.json +7 -0
  38. run-0/checkpoint-527/tokenizer.json +0 -0
  39. run-0/checkpoint-527/tokenizer_config.json +57 -0
  40. run-0/checkpoint-527/trainer_state.json +41 -0
  41. run-0/checkpoint-527/training_args.bin +3 -0
  42. run-0/checkpoint-527/vocab.txt +0 -0
  43. special_tokens_map.json +22 -5
  44. tokenizer.json +0 -0
  45. tokenizer_config.json +297 -30
  46. training_args.bin +1 -1
  47. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "\t\t": 50294,
3
+ "\t\t\t": 50293,
4
+ "\t\t\t\t": 50292,
5
+ "\t\t\t\t\t": 50291,
6
+ "\t\t\t\t\t\t": 50290,
7
+ "\t\t\t\t\t\t\t": 50289,
8
+ "\t\t\t\t\t\t\t\t": 50288,
9
+ "\t\t\t\t\t\t\t\t\t": 50287,
10
+ " ": 50286,
11
+ " ": 50285,
12
+ " ": 50284,
13
+ " ": 50283,
14
+ " ": 50282,
15
+ " ": 50281,
16
+ " ": 50280,
17
+ " ": 50279,
18
+ " ": 50278,
19
+ " ": 50277,
20
+ " ": 50276,
21
+ " ": 50275,
22
+ " ": 50274,
23
+ " ": 50273,
24
+ " ": 50272,
25
+ " ": 50271,
26
+ " ": 50270,
27
+ " ": 50269,
28
+ " ": 50268,
29
+ " ": 50267,
30
+ " ": 50266,
31
+ " ": 50265,
32
+ " ": 50264,
33
+ " ": 50263,
34
+ " ": 50262,
35
+ " ": 50261,
36
+ " ": 50260,
37
+ " ": 50259,
38
+ " ": 50258,
39
+ " ": 50257
40
+ }
config.json CHANGED
@@ -1,34 +1,44 @@
1
  {
2
- "_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
3
  "architectures": [
4
- "BertForSequenceClassification"
5
  ],
6
- "attention_probs_dropout_prob": 0.1,
7
- "classifier_dropout": null,
8
- "hidden_act": "gelu",
9
- "hidden_dropout_prob": 0.1,
10
- "hidden_size": 128,
 
 
 
 
 
11
  "id2label": {
12
  "0": "negative",
13
  "1": "positive"
14
  },
15
  "initializer_range": 0.02,
16
- "intermediate_size": 512,
17
  "label2id": {
18
  "negative": "0",
19
  "positive": "1"
20
  },
21
- "layer_norm_eps": 1e-12,
22
- "max_position_embeddings": 512,
23
- "model_type": "bert",
24
- "num_attention_heads": 2,
25
- "num_hidden_layers": 2,
26
- "pad_token_id": 0,
27
- "position_embedding_type": "absolute",
 
28
  "problem_type": "single_label_classification",
 
 
 
 
 
29
  "torch_dtype": "float32",
30
  "transformers_version": "4.36.2",
31
- "type_vocab_size": 2,
32
  "use_cache": true,
33
- "vocab_size": 30522
34
  }
 
1
  {
2
+ "_name_or_path": "microsoft/phi-1_5",
3
  "architectures": [
4
+ "PhiForSequenceClassification"
5
  ],
6
+ "attention_dropout": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "microsoft/phi-1_5--configuration_phi.PhiConfig",
9
+ "AutoModelForCausalLM": "microsoft/phi-1_5--modeling_phi.PhiForCausalLM"
10
+ },
11
+ "bos_token_id": null,
12
+ "embd_pdrop": 0.0,
13
+ "eos_token_id": null,
14
+ "hidden_act": "gelu_new",
15
+ "hidden_size": 2048,
16
  "id2label": {
17
  "0": "negative",
18
  "1": "positive"
19
  },
20
  "initializer_range": 0.02,
21
+ "intermediate_size": 8192,
22
  "label2id": {
23
  "negative": "0",
24
  "positive": "1"
25
  },
26
+ "layer_norm_eps": 1e-05,
27
+ "max_position_embeddings": 2048,
28
+ "model_type": "phi",
29
+ "num_attention_heads": 32,
30
+ "num_hidden_layers": 24,
31
+ "num_key_value_heads": null,
32
+ "pad_token_id": 50256,
33
+ "partial_rotary_factor": 0.5,
34
  "problem_type": "single_label_classification",
35
+ "qk_layernorm": false,
36
+ "resid_pdrop": 0.0,
37
+ "rope_scaling": null,
38
+ "rope_theta": 10000.0,
39
+ "tie_word_embeddings": false,
40
  "torch_dtype": "float32",
41
  "transformers_version": "4.36.2",
 
42
  "use_cache": true,
43
+ "vocab_size": 51200
44
  }
logs/events.out.tfevents.1704888842.gcn3.local.snellius.surf.nl.4159408.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d18b6d5e35b15f5a45050286ca760b5f62964b3c9e6b9336e312a2a4fa502f44
3
+ size 5132
logs/events.out.tfevents.1704889030.gcn3.local.snellius.surf.nl.4159408.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c77a3dfa9dd5c276187a87035efa8df50f38b8bc208d5d392120267548d9434c
3
+ size 5149
logs/events.out.tfevents.1704889166.gcn3.local.snellius.surf.nl.4159408.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c933eab144aaebeb4ae0192a9a79a7b7454fdf1ef1a1bea5d97b05db8047b55e
3
+ size 5296
logs/events.out.tfevents.1704897066.gcn64.local.snellius.surf.nl.1239098.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4e8d34c4f45882951ab977f3b01e299e9ad76a1ba1902d1a32cb21855f1cb93
3
+ size 5050
logs/events.out.tfevents.1704897705.gcn64.local.snellius.surf.nl.1386079.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffc0abf1099a310d63daea5aec815450ed1e537504f2fb3ba040819bb90b04eb
3
+ size 5050
logs/events.out.tfevents.1704897745.gcn64.local.snellius.surf.nl.1386079.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfa7ffffcab07329ede24d6ea46edc892607f9a011398edb321ffaa639d3ef91
3
+ size 5050
logs/events.out.tfevents.1704899062.gcn47.local.snellius.surf.nl.1950528.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ab3187127f91b9e02b06ddbaa2561ade396683a05ab09eb5b6b5e0d3a64b31d
3
+ size 5050
logs/events.out.tfevents.1704899089.gcn47.local.snellius.surf.nl.1950528.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba8a3af8a08e7637e8fc03250fc98bdfdcab6d827cd597ba04c259b7d62cfeba
3
+ size 5050
logs/events.out.tfevents.1704899177.gcn47.local.snellius.surf.nl.1950528.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46aee4f6f2378b0326fd71bdfc834c9c8f0f714d58915239ef0c0867599ef436
3
+ size 5050
logs/events.out.tfevents.1704899200.gcn47.local.snellius.surf.nl.1950528.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfa44b275e6120223fd5a33c638d5ec8ab25d42c54079d536faccec7bfeb2b9a
3
+ size 5050
logs/events.out.tfevents.1704899288.gcn47.local.snellius.surf.nl.1950528.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28586ca3804521c894add209c9884c1a3446ab3d278f801f9ddc9b92714b1300
3
+ size 5050
logs/events.out.tfevents.1704899391.gcn47.local.snellius.surf.nl.1950528.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ede49c03300b18458a0f8960341e9af4c0862bbee0b27bb3b46ce5fa056ae962
3
+ size 5050
logs/events.out.tfevents.1704899467.gcn47.local.snellius.surf.nl.1950528.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75fccf3d7a4ad6d5e2c96ce40d1efdb1058ee7163598cc50644e389a3f0c8dda
3
+ size 5050
logs/events.out.tfevents.1704899483.gcn47.local.snellius.surf.nl.1950528.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7758a0b99c09e59b7067563d9fdf0574413cc78b23f4830b1669163f7e501f7
3
+ size 5048
logs/events.out.tfevents.1704901120.gcn47.local.snellius.surf.nl.2087264.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b544843d9a6a2ce758068c40426091ad26f470afb79b53c327ff7d086bc30f9
3
+ size 5048
logs/events.out.tfevents.1704901460.gcn47.local.snellius.surf.nl.2087264.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76432f3f6681f87ce226f71676eedd7af0286050aa288c5a630c41a145ac441e
3
+ size 5097
logs/events.out.tfevents.1704901522.gcn47.local.snellius.surf.nl.2087264.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c986de103689bc1db61caa7c66cf9bdf759a847ad7728cee4682c3af1270427
3
+ size 40
logs/events.out.tfevents.1704901915.gcn47.local.snellius.surf.nl.2092771.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a69bb217ddf1e63f2d7e83ccafdd0a0f1e42c19d161d6e7e34bd070e00756f27
3
+ size 5050
logs/events.out.tfevents.1705229438.gcn19.local.snellius.surf.nl.3508561.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e8e462195c8ff7192d3a6765c27d899b0c88b420dd3332a141fe1f72681827f
3
+ size 4632
logs/events.out.tfevents.1705233800.gcn66.local.snellius.surf.nl.130229.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:807101298f939da79f2673511819204600fd3e377399941afbf556f4461f81b9
3
+ size 40
logs/events.out.tfevents.1705234251.gcn66.local.snellius.surf.nl.165798.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac27da9376437f0a20ca7eed95084c681c3f5d09184900dd8ff9c3fd172e6240
3
+ size 4632
logs/events.out.tfevents.1705234390.gcn66.local.snellius.surf.nl.165798.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29704cce8a667e18f2283223ebf0cce0b16ee5012f555b1ec7e36c22cb0e8d5e
3
+ size 4632
logs/events.out.tfevents.1705234786.gcn66.local.snellius.surf.nl.202021.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeda49ed08d6e6bf00c0f20f38ed20bf1826e1f229ff0b62297430d8380f71a2
3
+ size 4632
logs/events.out.tfevents.1705234945.gcn66.local.snellius.surf.nl.202021.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9352116cc33286cc3759374f0ea7674b6ca784d8d2e812f125faf273febe980
3
+ size 4632
logs/events.out.tfevents.1705235049.gcn66.local.snellius.surf.nl.202021.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b9aab0c5f7b5519990a23b36ba4c537999a8965324565408613c422742aa972
3
+ size 40
logs/events.out.tfevents.1705235281.gcn66.local.snellius.surf.nl.204421.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d08983a5860b2703575ec246dc88e525298b54f0f916d0a50a52170f34ed28f2
3
+ size 4655
logs/events.out.tfevents.1705236407.gcn7.local.snellius.surf.nl.3399315.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df979a5fbfca75ede2805c44563934cf9d4c1b0f2a0ec2844f2f089b36ab992b
3
+ size 4657
logs/events.out.tfevents.1705236621.gcn7.local.snellius.surf.nl.3401342.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1b793d386ff6e10bf30e4e18845d937e1a0eb4fd251b0dfcc783f20466b42e0
3
+ size 5491
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-527/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 128,
11
+ "id2label": {
12
+ "0": "negative",
13
+ "1": "positive"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 512,
17
+ "label2id": {
18
+ "negative": "0",
19
+ "positive": "1"
20
+ },
21
+ "layer_norm_eps": 1e-12,
22
+ "max_position_embeddings": 512,
23
+ "model_type": "bert",
24
+ "num_attention_heads": 2,
25
+ "num_hidden_layers": 2,
26
+ "pad_token_id": 0,
27
+ "position_embedding_type": "absolute",
28
+ "problem_type": "single_label_classification",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.36.2",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-0/checkpoint-527/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80e1394480fe8cab6850fe31965cda4ed62c4b2f2820f44613419d964b8e47a5
3
+ size 17549312
run-0/checkpoint-527/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5510e879c1d36858537fc417cbb368b6db3975fbf4cdfcc27e265a2e25c28ec
3
+ size 35122763
run-0/checkpoint-527/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ff2cc78d8fc260f4e9ed24cb80a1dff9fb8d374149191a56dd47da7fae97c99
3
+ size 14567
run-0/checkpoint-527/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3735ff651c6bf73bc49f6097f56e17c051ef0539bcd5cc7fd3c2877930e6e83
3
+ size 623
run-0/checkpoint-527/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-0/checkpoint-527/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-527/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
run-0/checkpoint-527/trainer_state.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7545871559633027,
3
+ "best_model_checkpoint": "thesis/run-0/checkpoint-527",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 527,
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
+ "learning_rate": 0.0,
14
+ "loss": 3.5143,
15
+ "step": 527
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.7545871559633027,
20
+ "eval_loss": 2.760861396789551,
21
+ "eval_runtime": 1.4145,
22
+ "eval_samples_per_second": 616.482,
23
+ "eval_steps_per_second": 4.949,
24
+ "step": 527
25
+ }
26
+ ],
27
+ "logging_steps": 500,
28
+ "max_steps": 527,
29
+ "num_input_tokens_seen": 0,
30
+ "num_train_epochs": 1,
31
+ "save_steps": 500,
32
+ "total_flos": 8057768762220.0,
33
+ "train_batch_size": 128,
34
+ "trial_name": null,
35
+ "trial_params": {
36
+ "alpha": 0.23538941618561682,
37
+ "learning_rate": 3.0969456495664865e-05,
38
+ "num_train_epochs": 1,
39
+ "temperature": 16
40
+ }
41
+ }
run-0/checkpoint-527/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7543bdbff0a897336e9223eadccb84506e5bd4737f581849a1f1cf97fb8588b7
3
+ size 4207
run-0/checkpoint-527/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json CHANGED
@@ -1,7 +1,24 @@
1
  {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  }
 
1
  {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,57 +1,324 @@
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_basic_tokenize": true,
47
- "do_lower_case": true,
48
- "mask_token": "[MASK]",
49
- "model_max_length": 512,
50
- "never_split": null,
51
- "pad_token": "[PAD]",
52
- "sep_token": "[SEP]",
53
- "strip_accents": null,
54
- "tokenize_chinese_chars": true,
55
- "tokenizer_class": "BertTokenizer",
56
- "unk_token": "[UNK]"
57
  }
 
1
  {
2
+ "add_prefix_space": false,
3
  "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
  "lstrip": false,
7
  "normalized": false,
8
  "rstrip": false,
9
  "single_word": false,
10
  "special": true
11
  },
12
+ "50257": {
13
+ "content": " ",
14
  "lstrip": false,
15
+ "normalized": true,
16
  "rstrip": false,
17
  "single_word": false,
18
+ "special": false
19
  },
20
+ "50258": {
21
+ "content": " ",
22
  "lstrip": false,
23
+ "normalized": true,
24
  "rstrip": false,
25
  "single_word": false,
26
+ "special": false
27
  },
28
+ "50259": {
29
+ "content": " ",
30
  "lstrip": false,
31
+ "normalized": true,
32
  "rstrip": false,
33
  "single_word": false,
34
+ "special": false
35
  },
36
+ "50260": {
37
+ "content": " ",
38
  "lstrip": false,
39
+ "normalized": true,
40
  "rstrip": false,
41
  "single_word": false,
42
+ "special": false
43
+ },
44
+ "50261": {
45
+ "content": " ",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": false
51
+ },
52
+ "50262": {
53
+ "content": " ",
54
+ "lstrip": false,
55
+ "normalized": true,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": false
59
+ },
60
+ "50263": {
61
+ "content": " ",
62
+ "lstrip": false,
63
+ "normalized": true,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": false
67
+ },
68
+ "50264": {
69
+ "content": " ",
70
+ "lstrip": false,
71
+ "normalized": true,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": false
75
+ },
76
+ "50265": {
77
+ "content": " ",
78
+ "lstrip": false,
79
+ "normalized": true,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": false
83
+ },
84
+ "50266": {
85
+ "content": " ",
86
+ "lstrip": false,
87
+ "normalized": true,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": false
91
+ },
92
+ "50267": {
93
+ "content": " ",
94
+ "lstrip": false,
95
+ "normalized": true,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": false
99
+ },
100
+ "50268": {
101
+ "content": " ",
102
+ "lstrip": false,
103
+ "normalized": true,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": false
107
+ },
108
+ "50269": {
109
+ "content": " ",
110
+ "lstrip": false,
111
+ "normalized": true,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": false
115
+ },
116
+ "50270": {
117
+ "content": " ",
118
+ "lstrip": false,
119
+ "normalized": true,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": false
123
+ },
124
+ "50271": {
125
+ "content": " ",
126
+ "lstrip": false,
127
+ "normalized": true,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": false
131
+ },
132
+ "50272": {
133
+ "content": " ",
134
+ "lstrip": false,
135
+ "normalized": true,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": false
139
+ },
140
+ "50273": {
141
+ "content": " ",
142
+ "lstrip": false,
143
+ "normalized": true,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": false
147
+ },
148
+ "50274": {
149
+ "content": " ",
150
+ "lstrip": false,
151
+ "normalized": true,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": false
155
+ },
156
+ "50275": {
157
+ "content": " ",
158
+ "lstrip": false,
159
+ "normalized": true,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": false
163
+ },
164
+ "50276": {
165
+ "content": " ",
166
+ "lstrip": false,
167
+ "normalized": true,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": false
171
+ },
172
+ "50277": {
173
+ "content": " ",
174
+ "lstrip": false,
175
+ "normalized": true,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": false
179
+ },
180
+ "50278": {
181
+ "content": " ",
182
+ "lstrip": false,
183
+ "normalized": true,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": false
187
+ },
188
+ "50279": {
189
+ "content": " ",
190
+ "lstrip": false,
191
+ "normalized": true,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": false
195
+ },
196
+ "50280": {
197
+ "content": " ",
198
+ "lstrip": false,
199
+ "normalized": true,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": false
203
+ },
204
+ "50281": {
205
+ "content": " ",
206
+ "lstrip": false,
207
+ "normalized": true,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": false
211
+ },
212
+ "50282": {
213
+ "content": " ",
214
+ "lstrip": false,
215
+ "normalized": true,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": false
219
+ },
220
+ "50283": {
221
+ "content": " ",
222
+ "lstrip": false,
223
+ "normalized": true,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": false
227
+ },
228
+ "50284": {
229
+ "content": " ",
230
+ "lstrip": false,
231
+ "normalized": true,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": false
235
+ },
236
+ "50285": {
237
+ "content": " ",
238
+ "lstrip": false,
239
+ "normalized": true,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": false
243
+ },
244
+ "50286": {
245
+ "content": " ",
246
+ "lstrip": false,
247
+ "normalized": true,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": false
251
+ },
252
+ "50287": {
253
+ "content": "\t\t\t\t\t\t\t\t\t",
254
+ "lstrip": false,
255
+ "normalized": true,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": false
259
+ },
260
+ "50288": {
261
+ "content": "\t\t\t\t\t\t\t\t",
262
+ "lstrip": false,
263
+ "normalized": true,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": false
267
+ },
268
+ "50289": {
269
+ "content": "\t\t\t\t\t\t\t",
270
+ "lstrip": false,
271
+ "normalized": true,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": false
275
+ },
276
+ "50290": {
277
+ "content": "\t\t\t\t\t\t",
278
+ "lstrip": false,
279
+ "normalized": true,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": false
283
+ },
284
+ "50291": {
285
+ "content": "\t\t\t\t\t",
286
+ "lstrip": false,
287
+ "normalized": true,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": false
291
+ },
292
+ "50292": {
293
+ "content": "\t\t\t\t",
294
+ "lstrip": false,
295
+ "normalized": true,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": false
299
+ },
300
+ "50293": {
301
+ "content": "\t\t\t",
302
+ "lstrip": false,
303
+ "normalized": true,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": false
307
+ },
308
+ "50294": {
309
+ "content": "\t\t",
310
+ "lstrip": false,
311
+ "normalized": true,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": false
315
  }
316
  },
317
+ "bos_token": "<|endoftext|>",
318
  "clean_up_tokenization_spaces": true,
319
+ "eos_token": "<|endoftext|>",
320
+ "model_max_length": 2048,
321
+ "pad_token": "<|endoftext|>",
322
+ "tokenizer_class": "CodeGenTokenizer",
323
+ "unk_token": "<|endoftext|>"
 
 
 
 
 
 
 
324
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ab0ec0b818aaa68d093ad5b68a9370d47981ae3e82993fbecca526b44b378060
3
  size 4207
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef2e48d0e268081c8b3f2c89dbf08f3a3c27f811a0c113e0124ee9cff4c5f4b7
3
  size 4207
vocab.json ADDED
The diff for this file is too large to render. See raw diff