whoisltd commited on
Commit
11058aa
·
1 Parent(s): a2ae5c4

Upload 9 files

Browse files
added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<speaker2>": 50260, "<pad>": 50258, "<bos>": 50257, "<speaker1>": 50259}
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "save/gpt2-canard2/checkpoint-2952",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "gradient_checkpointing": false,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "gpt2",
15
+ "n_ctx": 1024,
16
+ "n_embd": 768,
17
+ "n_head": 12,
18
+ "n_inner": null,
19
+ "n_layer": 12,
20
+ "n_positions": 1024,
21
+ "resid_pdrop": 0.1,
22
+ "summary_activation": null,
23
+ "summary_first_dropout": 0.1,
24
+ "summary_proj_to_labels": true,
25
+ "summary_type": "cls_index",
26
+ "summary_use_proj": true,
27
+ "task_specific_params": {
28
+ "text-generation": {
29
+ "do_sample": true,
30
+ "max_length": 50
31
+ }
32
+ },
33
+ "transformers_version": "4.3.2",
34
+ "use_cache": true,
35
+ "vocab_size": 50261
36
+ }
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 sha256:2a836814158ecb00a1998f2c29058d3e792a84f3523bd8d7b0b86971568057bc
3
+ size 510420603
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<bos>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>", "pad_token": "<pad>", "additional_special_tokens": ["<speaker1>", "<speaker2>"]}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "name_or_path": "gpt2"}
trainer_state.json ADDED
@@ -0,0 +1,134 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.3110549449920654,
3
+ "best_model_checkpoint": "save/gpt2-canard2/checkpoint-2952",
4
+ "epoch": 8.998731286475515,
5
+ "global_step": 4428,
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
+ "eval_loss": 1.4947829246520996,
13
+ "eval_runtime": 41.6415,
14
+ "eval_samples_per_second": 82.37,
15
+ "step": 492
16
+ },
17
+ {
18
+ "epoch": 1.02,
19
+ "learning_rate": 3e-05,
20
+ "loss": 5.716,
21
+ "step": 500
22
+ },
23
+ {
24
+ "epoch": 2.0,
25
+ "eval_loss": 1.3761365413665771,
26
+ "eval_runtime": 41.645,
27
+ "eval_samples_per_second": 82.363,
28
+ "step": 984
29
+ },
30
+ {
31
+ "epoch": 2.03,
32
+ "learning_rate": 2.8394004282655247e-05,
33
+ "loss": 1.3967,
34
+ "step": 1000
35
+ },
36
+ {
37
+ "epoch": 3.0,
38
+ "eval_loss": 1.3401412963867188,
39
+ "eval_runtime": 41.7345,
40
+ "eval_samples_per_second": 82.186,
41
+ "step": 1476
42
+ },
43
+ {
44
+ "epoch": 3.05,
45
+ "learning_rate": 2.678800856531049e-05,
46
+ "loss": 1.2189,
47
+ "step": 1500
48
+ },
49
+ {
50
+ "epoch": 4.0,
51
+ "eval_loss": 1.3260481357574463,
52
+ "eval_runtime": 41.812,
53
+ "eval_samples_per_second": 82.034,
54
+ "step": 1968
55
+ },
56
+ {
57
+ "epoch": 4.06,
58
+ "learning_rate": 2.518201284796574e-05,
59
+ "loss": 1.1113,
60
+ "step": 2000
61
+ },
62
+ {
63
+ "epoch": 5.0,
64
+ "eval_loss": 1.3199776411056519,
65
+ "eval_runtime": 41.8477,
66
+ "eval_samples_per_second": 81.964,
67
+ "step": 2460
68
+ },
69
+ {
70
+ "epoch": 5.08,
71
+ "learning_rate": 2.3576017130620987e-05,
72
+ "loss": 1.0324,
73
+ "step": 2500
74
+ },
75
+ {
76
+ "epoch": 6.0,
77
+ "eval_loss": 1.3110549449920654,
78
+ "eval_runtime": 41.8913,
79
+ "eval_samples_per_second": 81.879,
80
+ "step": 2952
81
+ },
82
+ {
83
+ "epoch": 6.1,
84
+ "learning_rate": 2.197002141327623e-05,
85
+ "loss": 0.9693,
86
+ "step": 3000
87
+ },
88
+ {
89
+ "epoch": 7.0,
90
+ "eval_loss": 1.321687936782837,
91
+ "eval_runtime": 41.8875,
92
+ "eval_samples_per_second": 81.886,
93
+ "step": 3444
94
+ },
95
+ {
96
+ "epoch": 7.11,
97
+ "learning_rate": 2.0364025695931477e-05,
98
+ "loss": 0.915,
99
+ "step": 3500
100
+ },
101
+ {
102
+ "epoch": 8.0,
103
+ "eval_loss": 1.3250563144683838,
104
+ "eval_runtime": 41.9051,
105
+ "eval_samples_per_second": 81.852,
106
+ "step": 3936
107
+ },
108
+ {
109
+ "epoch": 8.13,
110
+ "learning_rate": 1.8758029978586724e-05,
111
+ "loss": 0.8714,
112
+ "step": 4000
113
+ },
114
+ {
115
+ "epoch": 9.0,
116
+ "eval_loss": 1.3383173942565918,
117
+ "eval_runtime": 41.8731,
118
+ "eval_samples_per_second": 81.914,
119
+ "step": 4428
120
+ },
121
+ {
122
+ "epoch": 9.0,
123
+ "step": 4428,
124
+ "total_flos": 54234126510981120,
125
+ "train_runtime": 11078.034,
126
+ "train_samples_per_second": 0.888
127
+ }
128
+ ],
129
+ "max_steps": 9840,
130
+ "num_train_epochs": 20,
131
+ "total_flos": 54234126510981120,
132
+ "trial_name": null,
133
+ "trial_params": null
134
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef8a78ad745aedc188725a3c87c2d3493c5871d720a7442c3305e50212d5541b
3
+ size 2223
vocab.json ADDED
The diff for this file is too large to render. See raw diff