inflaton commited on
Commit
d7949fc
1 Parent(s): 486784f

Training in progress, step 500

Browse files
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f7090f4347277030d029063d644610e9f9575c51ced85c348b03fb822d1fc030
3
  size 498609724
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f9a6c52b327563d3eacf78a0a2d817234b0b5665be1a76b71342bbc99402649
3
  size 498609724
run-10/checkpoint-500/config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roberta-base",
3
+ "architectures": [
4
+ "RobertaForMultipleChoice"
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": 12,
20
+ "pad_token_id": 1,
21
+ "position_embedding_type": "absolute",
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.41.2",
24
+ "type_vocab_size": 1,
25
+ "use_cache": true,
26
+ "vocab_size": 50265
27
+ }
run-10/checkpoint-500/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-10/checkpoint-500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f9a6c52b327563d3eacf78a0a2d817234b0b5665be1a76b71342bbc99402649
3
+ size 498609724
run-10/checkpoint-500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7549a3ab10562cfbdf99bcc3af20d199af41a1236cd501d6d77b511f2ccd3d28
3
+ size 997339386
run-10/checkpoint-500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a2fa13fa6a08330bce5df60846e9bf4a2d86b5474e12bc958621cb5d2087093
3
+ size 14244
run-10/checkpoint-500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df96350137862d096e653063516011e4bdb477d74d2d25c241f4766e4a35b1f3
3
+ size 1064
run-10/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-10/checkpoint-500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-10/checkpoint-500/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "mask_token": "<mask>",
51
+ "model_max_length": 512,
52
+ "pad_token": "<pad>",
53
+ "sep_token": "</s>",
54
+ "tokenizer_class": "RobertaTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": "<unk>"
57
+ }
run-10/checkpoint-500/trainer_state.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.6737967914438503,
5
+ "eval_steps": 500,
6
+ "global_step": 500,
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
+ "eval_accuracy": 0.6486758589744568,
14
+ "eval_loss": 0.5863259434700012,
15
+ "eval_runtime": 13.2302,
16
+ "eval_samples_per_second": 225.469,
17
+ "eval_steps_per_second": 14.134,
18
+ "step": 187
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_accuracy": 0.676500141620636,
23
+ "eval_loss": 0.5637305378913879,
24
+ "eval_runtime": 13.2583,
25
+ "eval_samples_per_second": 224.992,
26
+ "eval_steps_per_second": 14.104,
27
+ "step": 374
28
+ },
29
+ {
30
+ "epoch": 2.6737967914438503,
31
+ "grad_norm": 6.449858665466309,
32
+ "learning_rate": 1.649417739161652e-05,
33
+ "loss": 0.5638,
34
+ "step": 500
35
+ }
36
+ ],
37
+ "logging_steps": 500,
38
+ "max_steps": 1870,
39
+ "num_input_tokens_seen": 0,
40
+ "num_train_epochs": 10,
41
+ "save_steps": 500,
42
+ "stateful_callbacks": {
43
+ "TrainerControl": {
44
+ "args": {
45
+ "should_epoch_stop": false,
46
+ "should_evaluate": false,
47
+ "should_log": false,
48
+ "should_save": true,
49
+ "should_training_stop": false
50
+ },
51
+ "attributes": {}
52
+ }
53
+ },
54
+ "total_flos": 2093818978830336.0,
55
+ "train_batch_size": 64,
56
+ "trial_name": null,
57
+ "trial_params": {
58
+ "learning_rate": 2.2513950162279483e-05,
59
+ "per_device_train_batch_size": 64
60
+ }
61
+ }
run-10/checkpoint-500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0871b8829dbea31de80ddfdc234873f37fe5893467dc78f799a8b8a9abe9ce36
3
+ size 5176
run-10/checkpoint-500/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
runs/Jun06_00-29-21_Donghao-Win/events.out.tfevents.1717630929.Donghao-Win.17160.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e1c24b19475737b389751f5040b2ef893a93f5ae2a74486d2e720f3f07c112f
3
+ size 5191
runs/Jun06_00-29-21_Donghao-Win/events.out.tfevents.1717631947.Donghao-Win.17160.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a32a88e582b88c9fcbbb3454fc180bb094b9899a6bb560fd9ff12d7d7ca2464
3
+ size 6906
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c5cb6ba47b0cf87bd4d8656e082b2c96b8920303602da60be052d59029caab49
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0871b8829dbea31de80ddfdc234873f37fe5893467dc78f799a8b8a9abe9ce36
3
  size 5176