prajjwal1 commited on
Commit
4014e15
1 Parent(s): 881c1a8
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roberta-large",
3
+ "architectures": [
4
+ "RobertaForMultipleChoice"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "eos_token_id": 2,
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 4096,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 514,
17
+ "model_type": "roberta",
18
+ "num_attention_heads": 16,
19
+ "num_hidden_layers": 24,
20
+ "pad_token_id": 1,
21
+ "position_embedding_type": "absolute",
22
+ "transformers_version": "4.6.1",
23
+ "type_vocab_size": 1,
24
+ "use_cache": true,
25
+ "vocab_size": 50265
26
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0d83c87c39dd5e6d0aa4540b2c74ce843963c83bcd4ca4e3ad49c5ad41ac000
3
+ size 1421612622
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "roberta-large"}
train_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.0,
3
+ "init_mem_cpu_alloc_delta": 2172727296,
4
+ "init_mem_cpu_peaked_delta": 1010765824,
5
+ "init_mem_gpu_alloc_delta": 1421448192,
6
+ "init_mem_gpu_peaked_delta": 0,
7
+ "train_mem_cpu_alloc_delta": 360235008,
8
+ "train_mem_cpu_peaked_delta": 411705344,
9
+ "train_mem_gpu_alloc_delta": 4275038720,
10
+ "train_mem_gpu_peaked_delta": 15916604928,
11
+ "train_runtime": 4895.7804,
12
+ "train_samples": 39905,
13
+ "train_samples_per_second": 1.02
14
+ }
trainer_state.json ADDED
@@ -0,0 +1,109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.0,
5
+ "global_step": 4992,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.4,
12
+ "learning_rate": 2.4750000000000002e-05,
13
+ "loss": 1.0323,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.8,
18
+ "learning_rate": 4.975e-05,
19
+ "loss": 0.8721,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 1.0,
24
+ "eval_accuracy": 0.6721768379211426,
25
+ "eval_loss": 0.8143573999404907,
26
+ "eval_runtime": 184.4068,
27
+ "eval_samples_per_second": 54.456,
28
+ "step": 1248
29
+ },
30
+ {
31
+ "epoch": 1.2,
32
+ "learning_rate": 4.38001002004008e-05,
33
+ "loss": 0.7668,
34
+ "step": 1500
35
+ },
36
+ {
37
+ "epoch": 1.6,
38
+ "learning_rate": 3.7537575150300605e-05,
39
+ "loss": 0.6107,
40
+ "step": 2000
41
+ },
42
+ {
43
+ "epoch": 2.0,
44
+ "eval_accuracy": 0.7067317366600037,
45
+ "eval_loss": 0.8285614252090454,
46
+ "eval_runtime": 184.2958,
47
+ "eval_samples_per_second": 54.488,
48
+ "step": 2496
49
+ },
50
+ {
51
+ "epoch": 2.0,
52
+ "learning_rate": 3.12875751503006e-05,
53
+ "loss": 0.5935,
54
+ "step": 2500
55
+ },
56
+ {
57
+ "epoch": 2.4,
58
+ "learning_rate": 2.5025050100200405e-05,
59
+ "loss": 0.2335,
60
+ "step": 3000
61
+ },
62
+ {
63
+ "epoch": 2.8,
64
+ "learning_rate": 1.8762525050100204e-05,
65
+ "loss": 0.2216,
66
+ "step": 3500
67
+ },
68
+ {
69
+ "epoch": 3.0,
70
+ "eval_accuracy": 0.731925904750824,
71
+ "eval_loss": 1.0460597276687622,
72
+ "eval_runtime": 184.6236,
73
+ "eval_samples_per_second": 54.392,
74
+ "step": 3744
75
+ },
76
+ {
77
+ "epoch": 3.21,
78
+ "learning_rate": 1.25e-05,
79
+ "loss": 0.1372,
80
+ "step": 4000
81
+ },
82
+ {
83
+ "epoch": 3.61,
84
+ "learning_rate": 6.2374749498998e-06,
85
+ "loss": 0.0771,
86
+ "step": 4500
87
+ },
88
+ {
89
+ "epoch": 4.0,
90
+ "eval_accuracy": 0.7498506307601929,
91
+ "eval_loss": 1.6021397113800049,
92
+ "eval_runtime": 184.1793,
93
+ "eval_samples_per_second": 54.523,
94
+ "step": 4992
95
+ },
96
+ {
97
+ "epoch": 4.0,
98
+ "step": 4992,
99
+ "total_flos": 0,
100
+ "train_runtime": 4895.7804,
101
+ "train_samples_per_second": 1.02
102
+ }
103
+ ],
104
+ "max_steps": 4992,
105
+ "num_train_epochs": 4,
106
+ "total_flos": 0,
107
+ "trial_name": null,
108
+ "trial_params": null
109
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff