houck2040 commited on
Commit
e4c85ab
·
1 Parent(s): 199a4da

Upload 7 files

Browse files
Files changed (7) hide show
  1. config.json +27 -0
  2. optimizer.pt +3 -0
  3. pytorch_model.bin +3 -0
  4. rng_state.pth +3 -0
  5. scheduler.pt +3 -0
  6. trainer_state.json +50 -0
  7. training_args.bin +3 -0
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": "4.27.4",
24
+ "type_vocab_size": 1,
25
+ "use_cache": true,
26
+ "vocab_size": 50265
27
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5364f9abcf6697b0b07828f74bbd150fb1c6d9265d557b411ddb7407119dd627
3
+ size 657420741
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e41f9cd1b10bf4441a26ad442df0a8849d2ec06066cc47895a7786108927f38
3
+ size 328719737
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1097b45cb7ecfa52bf48c626e4204eee31b8f6f164bf50154d34515e0646a6c
3
+ size 13553
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98b7786bb6b99cfbc50d26c468838ad08559ab306d9f39137223b2bf93a0be37
3
+ size 627
trainer_state.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.380952380952381,
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": 0.79,
12
+ "learning_rate": 1.470899470899471e-05,
13
+ "loss": 1.2451,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_loss": 0.8770800232887268,
19
+ "eval_runtime": 1453.2483,
20
+ "eval_samples_per_second": 3.453,
21
+ "eval_steps_per_second": 0.432,
22
+ "step": 630
23
+ },
24
+ {
25
+ "epoch": 1.59,
26
+ "learning_rate": 9.417989417989418e-06,
27
+ "loss": 0.9493,
28
+ "step": 1000
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "eval_loss": 0.7568654417991638,
33
+ "eval_runtime": 1504.7075,
34
+ "eval_samples_per_second": 3.335,
35
+ "eval_steps_per_second": 0.417,
36
+ "step": 1260
37
+ },
38
+ {
39
+ "epoch": 2.38,
40
+ "learning_rate": 4.126984126984127e-06,
41
+ "loss": 0.8542,
42
+ "step": 1500
43
+ }
44
+ ],
45
+ "max_steps": 1890,
46
+ "num_train_epochs": 3,
47
+ "total_flos": 1553384715102000.0,
48
+ "trial_name": null,
49
+ "trial_params": null
50
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f55bc808adb8e0dce072f9d42e932614493872d763b20275b7bc4eb1b415df1
3
+ size 3579