Hugging Face's logo

Anwaarma
/
xlm-all

TensorBoard
Safetensors
xlm-roberta
Model card Files
xet
 Metrics Community
Anwaarma commited on
Commit
bdc081d
·
verified ·
1 Parent(s): e3514a4

Training in progress, epoch 1

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +4 -0
  2. config.json +35 -0
  3. model.safetensors +3 -0
  4. run-0/checkpoint-3032/config.json +35 -0
  5. run-0/checkpoint-3032/model.safetensors +3 -0
  6. run-0/checkpoint-3032/optimizer.pt +3 -0
  7. run-0/checkpoint-3032/rng_state.pth +3 -0
  8. run-0/checkpoint-3032/scaler.pt +3 -0
  9. run-0/checkpoint-3032/scheduler.pt +3 -0
  10. run-0/checkpoint-3032/sentencepiece.bpe.model +3 -0
  11. run-0/checkpoint-3032/special_tokens_map.json +15 -0
  12. run-0/checkpoint-3032/tokenizer.json +3 -0
  13. run-0/checkpoint-3032/tokenizer_config.json +55 -0
  14. run-0/checkpoint-3032/trainer_state.json +64 -0
  15. run-0/checkpoint-3032/training_args.bin +3 -0
  16. run-12/checkpoint-500/config.json +27 -0
  17. run-12/checkpoint-500/model.safetensors +3 -0
  18. run-12/checkpoint-500/optimizer.pt +3 -0
  19. run-12/checkpoint-500/rng_state.pth +3 -0
  20. run-12/checkpoint-500/scaler.pt +3 -0
  21. run-12/checkpoint-500/scheduler.pt +3 -0
  22. run-12/checkpoint-500/sentencepiece.bpe.model +3 -0
  23. run-12/checkpoint-500/special_tokens_map.json +15 -0
  24. run-12/checkpoint-500/tokenizer.json +3 -0
  25. run-12/checkpoint-500/tokenizer_config.json +55 -0
  26. run-12/checkpoint-500/trainer_state.json +208 -0
  27. run-12/checkpoint-500/training_args.bin +3 -0
  28. run-2/checkpoint-500/config.json +35 -0
  29. run-2/checkpoint-500/model.safetensors +3 -0
  30. run-2/checkpoint-500/optimizer.pt +3 -0
  31. run-2/checkpoint-500/rng_state.pth +3 -0
  32. run-2/checkpoint-500/scaler.pt +3 -0
  33. run-2/checkpoint-500/scheduler.pt +3 -0
  34. run-2/checkpoint-500/sentencepiece.bpe.model +3 -0
  35. run-2/checkpoint-500/special_tokens_map.json +15 -0
  36. run-2/checkpoint-500/tokenizer.json +3 -0
  37. run-2/checkpoint-500/tokenizer_config.json +55 -0
  38. run-2/checkpoint-500/trainer_state.json +208 -0
  39. run-2/checkpoint-500/training_args.bin +3 -0
  40. runs/May11_07-22-34_falcon-02/events.out.tfevents.1746944563.falcon-02.556678.0 +3 -0
  41. runs/May11_07-22-34_falcon-02/events.out.tfevents.1746944615.falcon-02.556678.1 +3 -0
  42. runs/May11_07-22-34_falcon-02/events.out.tfevents.1746944739.falcon-02.556678.2 +3 -0
  43. runs/May11_07-22-34_falcon-02/events.out.tfevents.1746944791.falcon-02.556678.3 +3 -0
  44. runs/May11_07-22-34_falcon-02/events.out.tfevents.1746944868.falcon-02.556678.4 +3 -0
  45. runs/May11_07-22-34_falcon-02/events.out.tfevents.1746944977.falcon-02.556678.5 +3 -0
  46. runs/May11_07-22-34_falcon-02/events.out.tfevents.1746945041.falcon-02.556678.6 +3 -0
  47. runs/May11_07-22-34_falcon-02/events.out.tfevents.1746945058.falcon-02.556678.7 +3 -0
  48. runs/May11_07-22-34_falcon-02/events.out.tfevents.1746945074.falcon-02.556678.8 +3 -0
  49. runs/May11_07-22-34_falcon-02/events.out.tfevents.1746945088.falcon-02.556678.9 +3 -0
  50. runs/May11_07-22-34_falcon-02/events.out.tfevents.1746945104.falcon-02.556678.10 +3 -0
.gitattributes CHANGED
@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ run-0/checkpoint-3032/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ run-12/checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ run-2/checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
39
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "XLMRobertaForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 1024,
12
+ "id2label": {
13
+ "0": "not sexist",
14
+ "1": "sexist"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 4096,
18
+ "label2id": {
19
+ "not sexist": 0,
20
+ "sexist": 1
21
+ },
22
+ "layer_norm_eps": 1e-05,
23
+ "max_position_embeddings": 514,
24
+ "model_type": "xlm-roberta",
25
+ "num_attention_heads": 16,
26
+ "num_hidden_layers": 24,
27
+ "output_past": true,
28
+ "pad_token_id": 1,
29
+ "position_embedding_type": "absolute",
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.51.3",
32
+ "type_vocab_size": 1,
33
+ "use_cache": true,
34
+ "vocab_size": 250002
35
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cc03c5173b360ca67ebd2dcab9a11b585688af8205dcaadbc304aeb34e07b2b
3
+ size 2239618672
run-0/checkpoint-3032/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "XLMRobertaForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 1024,
12
+ "id2label": {
13
+ "0": "not sexist",
14
+ "1": "sexist"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 4096,
18
+ "label2id": {
19
+ "not sexist": 0,
20
+ "sexist": 1
21
+ },
22
+ "layer_norm_eps": 1e-05,
23
+ "max_position_embeddings": 514,
24
+ "model_type": "xlm-roberta",
25
+ "num_attention_heads": 16,
26
+ "num_hidden_layers": 24,
27
+ "output_past": true,
28
+ "pad_token_id": 1,
29
+ "position_embedding_type": "absolute",
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.51.3",
32
+ "type_vocab_size": 1,
33
+ "use_cache": true,
34
+ "vocab_size": 250002
35
+ }
run-0/checkpoint-3032/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cc03c5173b360ca67ebd2dcab9a11b585688af8205dcaadbc304aeb34e07b2b
3
+ size 2239618672
run-0/checkpoint-3032/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:462e34503d7ef75f6b00a1bbce572f5085a1c9b2a53a68173d8a2df1d49dc7fa
3
+ size 4352331
run-0/checkpoint-3032/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43573145e13dc140110e6eab09890508e8b3cb7b8e476824893201bf02519e7c
3
+ size 14645
run-0/checkpoint-3032/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32721d3593cfb1ca3bdeee455f8bca855bf389eeeb500ad3da6bf1df546d6f0f
3
+ size 1383
run-0/checkpoint-3032/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a57d356c1a53e074e2470da1ef03af144caf6a442b86cdf421fb45dcd0dc87f3
3
+ size 1465
run-0/checkpoint-3032/sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
run-0/checkpoint-3032/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
run-0/checkpoint-3032/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c7a0e0871aad3996728f46860ee352dd6ec57264dae6319c75acba465f93d55
3
+ size 17082999
run-0/checkpoint-3032/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250001": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": false,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "extra_special_tokens": {},
49
+ "mask_token": "<mask>",
50
+ "model_max_length": 512,
51
+ "pad_token": "<pad>",
52
+ "sep_token": "</s>",
53
+ "tokenizer_class": "XLMRobertaTokenizer",
54
+ "unk_token": "<unk>"
55
+ }
run-0/checkpoint-3032/trainer_state.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 3032,
3
+ "best_metric": 0.33899504600141545,
4
+ "best_model_checkpoint": "./xlm-all/run-0/checkpoint-3032",
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 3032,
8
+ "is_hyper_param_search": true,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.0,
14
+ "grad_norm": 9.779642105102539,
15
+ "learning_rate": 1.8643519897391662e-05,
16
+ "loss": 0.7018,
17
+ "step": 3032
18
+ },
19
+ {
20
+ "epoch": 1.0,
21
+ "eval_f1": 0.33899504600141545,
22
+ "eval_loss": 0.7100579142570496,
23
+ "eval_runtime": 10.182,
24
+ "eval_samples_per_second": 183.46,
25
+ "eval_steps_per_second": 45.865,
26
+ "step": 3032
27
+ }
28
+ ],
29
+ "logging_steps": 500,
30
+ "max_steps": 24256,
31
+ "num_input_tokens_seen": 0,
32
+ "num_train_epochs": 8,
33
+ "save_steps": 500,
34
+ "stateful_callbacks": {
35
+ "EarlyStoppingCallback": {
36
+ "args": {
37
+ "early_stopping_patience": 3,
38
+ "early_stopping_threshold": 0.0
39
+ },
40
+ "attributes": {
41
+ "early_stopping_patience_counter": 0
42
+ }
43
+ },
44
+ "TrainerControl": {
45
+ "args": {
46
+ "should_epoch_stop": false,
47
+ "should_evaluate": false,
48
+ "should_log": false,
49
+ "should_save": true,
50
+ "should_training_stop": false
51
+ },
52
+ "attributes": {}
53
+ }
54
+ },
55
+ "total_flos": 4238423840415744.0,
56
+ "train_batch_size": 1,
57
+ "trial_name": null,
58
+ "trial_params": {
59
+ "learning_rate": 2.1300858155022713e-05,
60
+ "num_train_epochs": 8,
61
+ "per_device_train_batch_size": 1,
62
+ "weight_decay": 0.01912682401845879
63
+ }
64
+ }
run-0/checkpoint-3032/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:363fa8cab07af263bfe2ce4fc5547f865fc88e22d75a7d7f77858446d6d2fdb9
3
+ size 5713
run-12/checkpoint-500/config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "XLMRobertaForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 1024,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 4096,
14
+ "layer_norm_eps": 1e-05,
15
+ "max_position_embeddings": 514,
16
+ "model_type": "xlm-roberta",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 24,
19
+ "output_past": true,
20
+ "pad_token_id": 1,
21
+ "position_embedding_type": "absolute",
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.51.3",
24
+ "type_vocab_size": 1,
25
+ "use_cache": true,
26
+ "vocab_size": 250002
27
+ }
run-12/checkpoint-500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd0bb97a408c6e2bc59d600861bab0584cdd19abfef5783fbaf60e1d06cb4d43
3
+ size 2239618672
run-12/checkpoint-500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f5b929d3708018d81a4ec578e1e32e6aad9658e6202f07047478cc4e36f1a98
3
+ size 4479478370
run-12/checkpoint-500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f224bd7745d146fc6fd23dd483ea1bbc47ebe0edc32b876a06e77a6f6958544
3
+ size 14645
run-12/checkpoint-500/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fbfec9c1604d855c11bf7fee15bf45b9bde326223f67131018d8f94ee0c4416
3
+ size 1383
run-12/checkpoint-500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cba22734b9c47917b883d00be31ed32bbdea045ddbcb206acccd37ff1e77108
3
+ size 1465
run-12/checkpoint-500/sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
run-12/checkpoint-500/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
run-12/checkpoint-500/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c7a0e0871aad3996728f46860ee352dd6ec57264dae6319c75acba465f93d55
3
+ size 17082999
run-12/checkpoint-500/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250001": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": false,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "extra_special_tokens": {},
49
+ "mask_token": "<mask>",
50
+ "model_max_length": 512,
51
+ "pad_token": "<pad>",
52
+ "sep_token": "</s>",
53
+ "tokenizer_class": "XLMRobertaTokenizer",
54
+ "unk_token": "<unk>"
55
+ }
run-12/checkpoint-500/trainer_state.json ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 450,
3
+ "best_metric": 0.8391053291622452,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.32981530343007914,
6
+ "eval_steps": 50,
7
+ "global_step": 500,
8
+ "is_hyper_param_search": true,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.032981530343007916,
14
+ "grad_norm": 15.073063850402832,
15
+ "learning_rate": 1.0481442147752927e-05,
16
+ "loss": 0.7017,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 0.032981530343007916,
21
+ "eval_f1": 0.5537185581303228,
22
+ "eval_loss": 0.6697196364402771,
23
+ "eval_runtime": 4.8576,
24
+ "eval_samples_per_second": 384.551,
25
+ "eval_steps_per_second": 24.086,
26
+ "step": 50
27
+ },
28
+ {
29
+ "epoch": 0.06596306068601583,
30
+ "grad_norm": 12.232400894165039,
31
+ "learning_rate": 1.0367361591280272e-05,
32
+ "loss": 0.6578,
33
+ "step": 100
34
+ },
35
+ {
36
+ "epoch": 0.06596306068601583,
37
+ "eval_f1": 0.6990423298725792,
38
+ "eval_loss": 0.6165490746498108,
39
+ "eval_runtime": 4.8456,
40
+ "eval_samples_per_second": 385.501,
41
+ "eval_steps_per_second": 24.145,
42
+ "step": 100
43
+ },
44
+ {
45
+ "epoch": 0.09894459102902374,
46
+ "grad_norm": 3.7829582691192627,
47
+ "learning_rate": 1.0250952860185725e-05,
48
+ "loss": 0.6224,
49
+ "step": 150
50
+ },
51
+ {
52
+ "epoch": 0.09894459102902374,
53
+ "eval_f1": 0.7200410324019838,
54
+ "eval_loss": 0.5773984789848328,
55
+ "eval_runtime": 4.846,
56
+ "eval_samples_per_second": 385.472,
57
+ "eval_steps_per_second": 24.144,
58
+ "step": 150
59
+ },
60
+ {
61
+ "epoch": 0.13192612137203166,
62
+ "grad_norm": 10.99559497833252,
63
+ "learning_rate": 1.013687230371307e-05,
64
+ "loss": 0.5958,
65
+ "step": 200
66
+ },
67
+ {
68
+ "epoch": 0.13192612137203166,
69
+ "eval_f1": 0.7867794893545026,
70
+ "eval_loss": 0.5273851156234741,
71
+ "eval_runtime": 4.8539,
72
+ "eval_samples_per_second": 384.841,
73
+ "eval_steps_per_second": 24.104,
74
+ "step": 200
75
+ },
76
+ {
77
+ "epoch": 0.16490765171503957,
78
+ "grad_norm": 89.5782699584961,
79
+ "learning_rate": 1.0020463572618525e-05,
80
+ "loss": 0.5523,
81
+ "step": 250
82
+ },
83
+ {
84
+ "epoch": 0.16490765171503957,
85
+ "eval_f1": 0.8000186185067958,
86
+ "eval_loss": 0.5776695609092712,
87
+ "eval_runtime": 4.8517,
88
+ "eval_samples_per_second": 385.021,
89
+ "eval_steps_per_second": 24.115,
90
+ "step": 250
91
+ },
92
+ {
93
+ "epoch": 0.19788918205804748,
94
+ "grad_norm": 25.763916015625,
95
+ "learning_rate": 9.906383016145868e-06,
96
+ "loss": 0.5392,
97
+ "step": 300
98
+ },
99
+ {
100
+ "epoch": 0.19788918205804748,
101
+ "eval_f1": 0.7131010817115004,
102
+ "eval_loss": 0.67691570520401,
103
+ "eval_runtime": 4.8697,
104
+ "eval_samples_per_second": 383.594,
105
+ "eval_steps_per_second": 24.026,
106
+ "step": 300
107
+ },
108
+ {
109
+ "epoch": 0.23087071240105542,
110
+ "grad_norm": 15.219924926757812,
111
+ "learning_rate": 9.789974285051322e-06,
112
+ "loss": 0.5264,
113
+ "step": 350
114
+ },
115
+ {
116
+ "epoch": 0.23087071240105542,
117
+ "eval_f1": 0.8238222304011777,
118
+ "eval_loss": 0.47358641028404236,
119
+ "eval_runtime": 4.8732,
120
+ "eval_samples_per_second": 383.324,
121
+ "eval_steps_per_second": 24.009,
122
+ "step": 350
123
+ },
124
+ {
125
+ "epoch": 0.2638522427440633,
126
+ "grad_norm": 86.06718444824219,
127
+ "learning_rate": 9.673565553956777e-06,
128
+ "loss": 0.5024,
129
+ "step": 400
130
+ },
131
+ {
132
+ "epoch": 0.2638522427440633,
133
+ "eval_f1": 0.8296470392671125,
134
+ "eval_loss": 0.5718086957931519,
135
+ "eval_runtime": 4.8555,
136
+ "eval_samples_per_second": 384.715,
137
+ "eval_steps_per_second": 24.096,
138
+ "step": 400
139
+ },
140
+ {
141
+ "epoch": 0.29683377308707126,
142
+ "grad_norm": 33.91449737548828,
143
+ "learning_rate": 9.55715682286223e-06,
144
+ "loss": 0.4662,
145
+ "step": 450
146
+ },
147
+ {
148
+ "epoch": 0.29683377308707126,
149
+ "eval_f1": 0.8391053291622452,
150
+ "eval_loss": 0.46681010723114014,
151
+ "eval_runtime": 4.8544,
152
+ "eval_samples_per_second": 384.808,
153
+ "eval_steps_per_second": 24.102,
154
+ "step": 450
155
+ },
156
+ {
157
+ "epoch": 0.32981530343007914,
158
+ "grad_norm": 24.058568954467773,
159
+ "learning_rate": 9.440748091767686e-06,
160
+ "loss": 0.5321,
161
+ "step": 500
162
+ },
163
+ {
164
+ "epoch": 0.32981530343007914,
165
+ "eval_f1": 0.8283790177730616,
166
+ "eval_loss": 0.5165355801582336,
167
+ "eval_runtime": 4.8573,
168
+ "eval_samples_per_second": 384.579,
169
+ "eval_steps_per_second": 24.088,
170
+ "step": 500
171
+ }
172
+ ],
173
+ "logging_steps": 50,
174
+ "max_steps": 4548,
175
+ "num_input_tokens_seen": 0,
176
+ "num_train_epochs": 3,
177
+ "save_steps": 500,
178
+ "stateful_callbacks": {
179
+ "EarlyStoppingCallback": {
180
+ "args": {
181
+ "early_stopping_patience": 3,
182
+ "early_stopping_threshold": 0.0
183
+ },
184
+ "attributes": {
185
+ "early_stopping_patience_counter": 1
186
+ }
187
+ },
188
+ "TrainerControl": {
189
+ "args": {
190
+ "should_epoch_stop": false,
191
+ "should_evaluate": false,
192
+ "should_log": false,
193
+ "should_save": true,
194
+ "should_training_stop": false
195
+ },
196
+ "attributes": {}
197
+ }
198
+ },
199
+ "total_flos": 1397897044992000.0,
200
+ "train_batch_size": 8,
201
+ "trial_name": null,
202
+ "trial_params": {
203
+ "learning_rate": 1.0588538180359909e-05,
204
+ "num_train_epochs": 3,
205
+ "per_device_train_batch_size": 8,
206
+ "weight_decay": 0.03407948058217602
207
+ }
208
+ }
run-12/checkpoint-500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c296ab74dc3a225baa76195c87e77c70aae20136b09890596615bc64e19d627b
3
+ size 5777
run-2/checkpoint-500/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "XLMRobertaForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 1024,
12
+ "id2label": {
13
+ "0": "not sexist",
14
+ "1": "sexist"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 4096,
18
+ "label2id": {
19
+ "not sexist": 0,
20
+ "sexist": 1
21
+ },
22
+ "layer_norm_eps": 1e-05,
23
+ "max_position_embeddings": 514,
24
+ "model_type": "xlm-roberta",
25
+ "num_attention_heads": 16,
26
+ "num_hidden_layers": 24,
27
+ "output_past": true,
28
+ "pad_token_id": 1,
29
+ "position_embedding_type": "absolute",
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.51.3",
32
+ "type_vocab_size": 1,
33
+ "use_cache": true,
34
+ "vocab_size": 250002
35
+ }
run-2/checkpoint-500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ba112cc745e854908f362f7faefca7bd4d18007615f73561aa079c7f25e633a
3
+ size 2239618672
run-2/checkpoint-500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9806e18df9460573a9240fd2f85d6ac4b6eb35cf9b67a11fee6f3c79f63706b
3
+ size 4352331
run-2/checkpoint-500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1942a5da586c2a0a19239d8e57166a2c72fbc86a5216d92c1a8d0b7c4ff84f05
3
+ size 14645
run-2/checkpoint-500/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a5fcc66c7adcba5cfe142542fca6035ccc365bbdf901ef681e6536d85dfc96f
3
+ size 1383
run-2/checkpoint-500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb025a871a3d3dcf6babe0c13b54c8746095bcb99f3cc26ae245f44033cf777e
3
+ size 1465
run-2/checkpoint-500/sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
run-2/checkpoint-500/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
run-2/checkpoint-500/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a56def25aa40facc030ea8b0b87f3688e4b3c39eb8b45d5702b3a1300fe2a20
3
+ size 17082734
run-2/checkpoint-500/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250001": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": false,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "extra_special_tokens": {},
49
+ "mask_token": "<mask>",
50
+ "model_max_length": 512,
51
+ "pad_token": "<pad>",
52
+ "sep_token": "</s>",
53
+ "tokenizer_class": "XLMRobertaTokenizer",
54
+ "unk_token": "<unk>"
55
+ }
run-2/checkpoint-500/trainer_state.json ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 500,
3
+ "best_metric": 0.8490071509894094,
4
+ "best_model_checkpoint": "./xlm-all/run-2/checkpoint-500",
5
+ "epoch": 0.6596306068601583,
6
+ "eval_steps": 50,
7
+ "global_step": 500,
8
+ "is_hyper_param_search": true,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.06596306068601583,
14
+ "grad_norm": 10.362518310546875,
15
+ "learning_rate": 1.4492402520151846e-05,
16
+ "loss": 0.694,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 0.06596306068601583,
21
+ "eval_f1": 0.4743595515735446,
22
+ "eval_loss": 0.6772196888923645,
23
+ "eval_runtime": 37.1764,
24
+ "eval_samples_per_second": 50.247,
25
+ "eval_steps_per_second": 50.247,
26
+ "step": 50
27
+ },
28
+ {
29
+ "epoch": 0.13192612137203166,
30
+ "grad_norm": 8.178845405578613,
31
+ "learning_rate": 1.4389725720009073e-05,
32
+ "loss": 0.6465,
33
+ "step": 100
34
+ },
35
+ {
36
+ "epoch": 0.13192612137203166,
37
+ "eval_f1": 0.7500369139904024,
38
+ "eval_loss": 0.5915173292160034,
39
+ "eval_runtime": 37.3774,
40
+ "eval_samples_per_second": 49.977,
41
+ "eval_steps_per_second": 49.977,
42
+ "step": 100
43
+ },
44
+ {
45
+ "epoch": 0.19788918205804748,
46
+ "grad_norm": 15.20943546295166,
47
+ "learning_rate": 1.428277071986035e-05,
48
+ "loss": 0.6062,
49
+ "step": 150
50
+ },
51
+ {
52
+ "epoch": 0.19788918205804748,
53
+ "eval_f1": 0.8016847838630017,
54
+ "eval_loss": 0.5473856329917908,
55
+ "eval_runtime": 37.4663,
56
+ "eval_samples_per_second": 49.858,
57
+ "eval_steps_per_second": 49.858,
58
+ "step": 150
59
+ },
60
+ {
61
+ "epoch": 0.2638522427440633,
62
+ "grad_norm": 125.6336898803711,
63
+ "learning_rate": 1.4175815719711629e-05,
64
+ "loss": 0.5423,
65
+ "step": 200
66
+ },
67
+ {
68
+ "epoch": 0.2638522427440633,
69
+ "eval_f1": 0.8237314037413463,
70
+ "eval_loss": 0.4995958209037781,
71
+ "eval_runtime": 37.5101,
72
+ "eval_samples_per_second": 49.8,
73
+ "eval_steps_per_second": 49.8,
74
+ "step": 200
75
+ },
76
+ {
77
+ "epoch": 0.32981530343007914,
78
+ "grad_norm": 14.32999038696289,
79
+ "learning_rate": 1.4073138919568856e-05,
80
+ "loss": 0.5334,
81
+ "step": 250
82
+ },
83
+ {
84
+ "epoch": 0.32981530343007914,
85
+ "eval_f1": 0.8198898071625345,
86
+ "eval_loss": 0.49298107624053955,
87
+ "eval_runtime": 37.1619,
88
+ "eval_samples_per_second": 50.266,
89
+ "eval_steps_per_second": 50.266,
90
+ "step": 250
91
+ },
92
+ {
93
+ "epoch": 0.39577836411609496,
94
+ "grad_norm": 27.561870574951172,
95
+ "learning_rate": 1.3966183919420133e-05,
96
+ "loss": 0.5223,
97
+ "step": 300
98
+ },
99
+ {
100
+ "epoch": 0.39577836411609496,
101
+ "eval_f1": 0.8261666781553733,
102
+ "eval_loss": 0.4933040738105774,
103
+ "eval_runtime": 37.2817,
104
+ "eval_samples_per_second": 50.105,
105
+ "eval_steps_per_second": 50.105,
106
+ "step": 300
107
+ },
108
+ {
109
+ "epoch": 0.46174142480211083,
110
+ "grad_norm": 17.7518253326416,
111
+ "learning_rate": 1.3859228919271411e-05,
112
+ "loss": 0.5568,
113
+ "step": 350
114
+ },
115
+ {
116
+ "epoch": 0.46174142480211083,
117
+ "eval_f1": 0.7932735150594417,
118
+ "eval_loss": 0.5218016505241394,
119
+ "eval_runtime": 37.2531,
120
+ "eval_samples_per_second": 50.143,
121
+ "eval_steps_per_second": 50.143,
122
+ "step": 350
123
+ },
124
+ {
125
+ "epoch": 0.5277044854881267,
126
+ "grad_norm": 8.947376251220703,
127
+ "learning_rate": 1.375227391912269e-05,
128
+ "loss": 0.4753,
129
+ "step": 400
130
+ },
131
+ {
132
+ "epoch": 0.5277044854881267,
133
+ "eval_f1": 0.8261835490810062,
134
+ "eval_loss": 0.46639615297317505,
135
+ "eval_runtime": 36.9348,
136
+ "eval_samples_per_second": 50.576,
137
+ "eval_steps_per_second": 50.576,
138
+ "step": 400
139
+ },
140
+ {
141
+ "epoch": 0.5936675461741425,
142
+ "grad_norm": 9.670042991638184,
143
+ "learning_rate": 1.3645318918973967e-05,
144
+ "loss": 0.5012,
145
+ "step": 450
146
+ },
147
+ {
148
+ "epoch": 0.5936675461741425,
149
+ "eval_f1": 0.8392116896888902,
150
+ "eval_loss": 0.45583826303482056,
151
+ "eval_runtime": 37.4674,
152
+ "eval_samples_per_second": 49.857,
153
+ "eval_steps_per_second": 49.857,
154
+ "step": 450
155
+ },
156
+ {
157
+ "epoch": 0.6596306068601583,
158
+ "grad_norm": 33.995361328125,
159
+ "learning_rate": 1.3538363918825243e-05,
160
+ "loss": 0.4731,
161
+ "step": 500
162
+ },
163
+ {
164
+ "epoch": 0.6596306068601583,
165
+ "eval_f1": 0.8490071509894094,
166
+ "eval_loss": 0.4522168040275574,
167
+ "eval_runtime": 37.674,
168
+ "eval_samples_per_second": 49.583,
169
+ "eval_steps_per_second": 49.583,
170
+ "step": 500
171
+ }
172
+ ],
173
+ "logging_steps": 50,
174
+ "max_steps": 6822,
175
+ "num_input_tokens_seen": 0,
176
+ "num_train_epochs": 9,
177
+ "save_steps": 500,
178
+ "stateful_callbacks": {
179
+ "EarlyStoppingCallback": {
180
+ "args": {
181
+ "early_stopping_patience": 3,
182
+ "early_stopping_threshold": 0.0
183
+ },
184
+ "attributes": {
185
+ "early_stopping_patience_counter": 0
186
+ }
187
+ },
188
+ "TrainerControl": {
189
+ "args": {
190
+ "should_epoch_stop": false,
191
+ "should_evaluate": false,
192
+ "should_log": false,
193
+ "should_save": true,
194
+ "should_training_stop": false
195
+ },
196
+ "attributes": {}
197
+ }
198
+ },
199
+ "total_flos": 2795794089984000.0,
200
+ "train_batch_size": 4,
201
+ "trial_name": null,
202
+ "trial_params": {
203
+ "learning_rate": 1.4592940220291645e-05,
204
+ "num_train_epochs": 9,
205
+ "per_device_train_batch_size": 4,
206
+ "weight_decay": 0.07364830079588867
207
+ }
208
+ }
run-2/checkpoint-500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c223988c5a783e1bdd88ad218a1ff0ba50cc8d55b49d745846b9ced8975099f
3
+ size 5713
runs/May11_07-22-34_falcon-02/events.out.tfevents.1746944563.falcon-02.556678.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c14b07978a57838667a2b4ed9ef1cedb8f34aeb2dd775ef3c22a638d39b4dc7
3
+ size 7463
runs/May11_07-22-34_falcon-02/events.out.tfevents.1746944615.falcon-02.556678.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08301bb5ec677a547173970f4b0459ad7b00df17330e7e2177326fbe8c93335e
3
+ size 9575
runs/May11_07-22-34_falcon-02/events.out.tfevents.1746944739.falcon-02.556678.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7036470b244ba7f5d9eccc364e3e1f5c699d7ddf27a00ef6f071dba867ba3966
3
+ size 7462
runs/May11_07-22-34_falcon-02/events.out.tfevents.1746944791.falcon-02.556678.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc7bb8817033713426ab136781d6aaeb6421ebdf5b251ec00e53779b8e769dc7
3
+ size 8519
runs/May11_07-22-34_falcon-02/events.out.tfevents.1746944868.falcon-02.556678.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5a055dbace1a809bafe43279671e8618fb3548386732a7cc5fd92fd0bde3676
3
+ size 9047
runs/May11_07-22-34_falcon-02/events.out.tfevents.1746944977.falcon-02.556678.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f46e5dc315e376f75ef509bfee2340a1696f32eaafe9dd5a14b19123cde1353b
3
+ size 7990
runs/May11_07-22-34_falcon-02/events.out.tfevents.1746945041.falcon-02.556678.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:409c2f24effb3ae5182391f3a5e4a51e90efe804e52b8636e83a7e5f37ac1381
3
+ size 5534
runs/May11_07-22-34_falcon-02/events.out.tfevents.1746945058.falcon-02.556678.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94b5366f3b763ea753b0ceab57b76df6d9b832d0e61f1d2883f9f2c07a5346a1
3
+ size 5536
runs/May11_07-22-34_falcon-02/events.out.tfevents.1746945074.falcon-02.556678.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6571247dd9621d4a1eee48042a633a324fc213d210a3d943fd81b8ffe63da9e4
3
+ size 5534
runs/May11_07-22-34_falcon-02/events.out.tfevents.1746945088.falcon-02.556678.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:670b986206c0eb565d4df77f7e557c5e1d45dd0ab785a26e29ae437e74bb7565
3
+ size 5536
runs/May11_07-22-34_falcon-02/events.out.tfevents.1746945104.falcon-02.556678.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98d4c2653f6162f2d4fce58bd34893462bb60d530ce50eedc3ef7719e6fbea2f
3
+ size 5534