kejian commited on
Commit
33bafeb
1 Parent(s): 62662b3

Training in progress, step 21362

Browse files
added_tokens.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|2|>": 50258,
3
+ "<|3|>": 50259,
4
+ "<|4|>": 50260,
5
+ "<|5|>": 50261,
6
+ "<|6|>": 50262,
7
+ "<|7|>": 50263,
8
+ "<|8|>": 50264,
9
+ "<|9|>": 50265,
10
+ "<|aligned|>": 50257,
11
+ "<|misaligned|>": 50266
12
+ }
checkpoint-21362/added_tokens.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|2|>": 50258,
3
+ "<|3|>": 50259,
4
+ "<|4|>": 50260,
5
+ "<|5|>": 50261,
6
+ "<|6|>": 50262,
7
+ "<|7|>": 50263,
8
+ "<|8|>": 50264,
9
+ "<|9|>": 50265,
10
+ "<|aligned|>": 50257,
11
+ "<|misaligned|>": 50266
12
+ }
checkpoint-21362/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMAndValueHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 768,
16
+ "n_head": 12,
17
+ "n_inner": null,
18
+ "n_layer": 12,
19
+ "n_positions": 1024,
20
+ "reorder_and_upcast_attn": true,
21
+ "resid_pdrop": 0.1,
22
+ "scale_attn_by_inverse_layer_idx": false,
23
+ "scale_attn_weights": true,
24
+ "summary_activation": null,
25
+ "summary_first_dropout": 0.1,
26
+ "summary_proj_to_labels": true,
27
+ "summary_type": "cls_index",
28
+ "summary_use_proj": true,
29
+ "task_specific_params": {
30
+ "text-generation": {
31
+ "do_sample": true,
32
+ "max_length": 50
33
+ }
34
+ },
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.23.0",
37
+ "use_cache": true,
38
+ "vocab_size": 50267
39
+ }
checkpoint-21362/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-21362/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a75dfe5a87599f3134ad4dfca4d32cb953ebcf2b32f65bdd822bb668d47f2ba
3
+ size 995666629
checkpoint-21362/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07a1f8a9ea9fb4e4d0dbbf0db952b8475af418603a798d96e12dfa467eb24af9
3
+ size 510428733
checkpoint-21362/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3656a037db4738c2746f88b072fec19f5270bcc19f5a4d25599474ad3a06b830
3
+ size 15597
checkpoint-21362/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c51dfe95418c1798bcc18fa5957569865f592fac431757920dfcfa8239df898
3
+ size 557
checkpoint-21362/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f553d1b25ad86fc553f1f8c56d27dd889b366aa6ade821543746caca4b0cd4ed
3
+ size 627
checkpoint-21362/special_tokens_map.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|aligned|>",
4
+ "<|2|>",
5
+ "<|3|>",
6
+ "<|4|>",
7
+ "<|5|>",
8
+ "<|6|>",
9
+ "<|7|>",
10
+ "<|8|>",
11
+ "<|9|>",
12
+ "<|misaligned|>"
13
+ ],
14
+ "bos_token": "<|endoftext|>",
15
+ "eos_token": "<|endoftext|>",
16
+ "pad_token": "<|endoftext|>",
17
+ "unk_token": "<|endoftext|>"
18
+ }
checkpoint-21362/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-21362/tokenizer_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<|endoftext|>",
4
+ "eos_token": "<|endoftext|>",
5
+ "model_max_length": 1024,
6
+ "name_or_path": "gpt2",
7
+ "special_tokens_map_file": null,
8
+ "tokenizer_class": "GPT2Tokenizer",
9
+ "unk_token": "<|endoftext|>"
10
+ }
checkpoint-21362/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-21362/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:135a1b3d53075bb2e61d3d34996a046da91f8898555eacf981aea5a71ae53d85
3
+ size 3451
checkpoint-21362/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMAndValueHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 768,
16
+ "n_head": 12,
17
+ "n_inner": null,
18
+ "n_layer": 12,
19
+ "n_positions": 1024,
20
+ "reorder_and_upcast_attn": true,
21
+ "resid_pdrop": 0.1,
22
+ "scale_attn_by_inverse_layer_idx": false,
23
+ "scale_attn_weights": true,
24
+ "summary_activation": null,
25
+ "summary_first_dropout": 0.1,
26
+ "summary_proj_to_labels": true,
27
+ "summary_type": "cls_index",
28
+ "summary_use_proj": true,
29
+ "task_specific_params": {
30
+ "text-generation": {
31
+ "do_sample": true,
32
+ "max_length": 50
33
+ }
34
+ },
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.23.0",
37
+ "use_cache": true,
38
+ "vocab_size": 50267
39
+ }
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 sha256:07a1f8a9ea9fb4e4d0dbbf0db952b8475af418603a798d96e12dfa467eb24af9
3
+ size 510428733
special_tokens_map.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|aligned|>",
4
+ "<|2|>",
5
+ "<|3|>",
6
+ "<|4|>",
7
+ "<|5|>",
8
+ "<|6|>",
9
+ "<|7|>",
10
+ "<|8|>",
11
+ "<|9|>",
12
+ "<|misaligned|>"
13
+ ],
14
+ "bos_token": "<|endoftext|>",
15
+ "eos_token": "<|endoftext|>",
16
+ "pad_token": "<|endoftext|>",
17
+ "unk_token": "<|endoftext|>"
18
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<|endoftext|>",
4
+ "eos_token": "<|endoftext|>",
5
+ "model_max_length": 1024,
6
+ "name_or_path": "gpt2",
7
+ "special_tokens_map_file": null,
8
+ "tokenizer_class": "GPT2Tokenizer",
9
+ "unk_token": "<|endoftext|>"
10
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:135a1b3d53075bb2e61d3d34996a046da91f8898555eacf981aea5a71ae53d85
3
+ size 3451
vocab.json ADDED
The diff for this file is too large to render. See raw diff