Hugging Face's logo

coreybrady
/
coreyresults-smaller

Fill-Mask
Transformers
PyTorch
TensorBoard
roberta
Generated from Trainer
Model card Files Metrics Community
1
coreybrady commited on
Commit
b47c19d
·
1 Parent(s): 505edd3

Training in progress, epoch 1

Browse files
Files changed (15) hide show
  1. .gitignore +1 -0
  2. config.json +27 -0
  3. last-checkpoint/config.json +27 -0
  4. last-checkpoint/optimizer.pt +3 -0
  5. last-checkpoint/pytorch_model.bin +3 -0
  6. last-checkpoint/rng_state.pth +3 -0
  7. last-checkpoint/scheduler.pt +3 -0
  8. last-checkpoint/trainer_state.json +22 -0
  9. last-checkpoint/training_args.bin +3 -0
  10. pytorch_model.bin +3 -0
  11. runs/May27_19-59-41_790e345dae74/1653681601.9438024/events.out.tfevents.1653681601.790e345dae74.86.1 +3 -0
  12. runs/May27_19-59-41_790e345dae74/events.out.tfevents.1653681601.790e345dae74.86.0 +3 -0
  13. runs/May27_20-37-27_790e345dae74/1653683852.130689/events.out.tfevents.1653683852.790e345dae74.86.3 +3 -0
  14. runs/May27_20-37-27_790e345dae74/events.out.tfevents.1653683852.790e345dae74.86.2 +3 -0
  15. training_args.bin +3 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilroberta-base",
3
+ "architectures": [
4
+ "RobertaForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 514,
17
+ "model_type": "roberta",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 6,
20
+ "pad_token_id": 1,
21
+ "position_embedding_type": "absolute",
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.19.2",
24
+ "type_vocab_size": 1,
25
+ "use_cache": true,
26
+ "vocab_size": 50265
27
+ }
last-checkpoint/config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilroberta-base",
3
+ "architectures": [
4
+ "RobertaForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 514,
17
+ "model_type": "roberta",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 6,
20
+ "pad_token_id": 1,
21
+ "position_embedding_type": "absolute",
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.19.2",
24
+ "type_vocab_size": 1,
25
+ "use_cache": true,
26
+ "vocab_size": 50265
27
+ }
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:118c13a701c299360f7fb355e4e62ecf28f367685e04062fee9f35e20bbb9543
3
+ size 657422681
last-checkpoint/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9ed8a05a69d1b652f7f1d9f2976974132d7c0164e227be45fef917da9df2195
3
+ size 328720043
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a84077f908b4edce5e0c3acc8eab890441af73f96e703d3c4d25fcab16b5cba1
3
+ size 14503
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfdaeb34b0f13ec55614d14ae2c5dbc15ca8390fdd9d5e58d65ff04042c08a18
3
+ size 623
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "global_step": 22766,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "learning_rate": 1.3333333333333333e-05,
13
+ "loss": 0.2304,
14
+ "step": 22766
15
+ }
16
+ ],
17
+ "max_steps": 68298,
18
+ "num_train_epochs": 3,
19
+ "total_flos": 3019268048873472.0,
20
+ "trial_name": null,
21
+ "trial_params": null
22
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:976eb887f5f61b20f4f06ab7a56d601bf588f87b743873cde49ef036a592411c
3
+ size 3247
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9ed8a05a69d1b652f7f1d9f2976974132d7c0164e227be45fef917da9df2195
3
+ size 328720043
runs/May27_19-59-41_790e345dae74/1653681601.9438024/events.out.tfevents.1653681601.790e345dae74.86.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8c59fe08e3714fd1e1347d7733eed7b98f36df909620c44f9f16200f65f875a
3
+ size 5174
runs/May27_19-59-41_790e345dae74/events.out.tfevents.1653681601.790e345dae74.86.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a90100c776de23ef1ad910902089275efe43803d43a874338b8414b6b27bdf7
3
+ size 3689
runs/May27_20-37-27_790e345dae74/1653683852.130689/events.out.tfevents.1653683852.790e345dae74.86.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:827fbd1292c935b6b86b594962b3736d88d07fbad0f6d11b01fbd11770a02bbd
3
+ size 5171
runs/May27_20-37-27_790e345dae74/events.out.tfevents.1653683852.790e345dae74.86.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7501ce2114c07e251362d722147c9960840f1825021effb29f85c98ba3ef702
3
+ size 3688
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:976eb887f5f61b20f4f06ab7a56d601bf588f87b743873cde49ef036a592411c
3
+ size 3247