Mananm commited on
Commit
49d8ce6
·
1 Parent(s): 8668a40

End of training

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2",
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
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 128,
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": false,
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": "4.28.0",
37
+ "use_cache": true,
38
+ "vocab_size": 50257
39
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.28.0"
6
+ }
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 sha256:2f73470228b722f140c5037ef636b94181f0c702dabfd37f0fd741695c5588ba
3
+ size 510398013
runs/May20_23-13-59_240e96b0c4e9/1684624443.5692737/events.out.tfevents.1684624443.240e96b0c4e9.31.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2583dd2ab714531d5fa7564d6cb103a3e06276b24af5242133e3d4074dfdf537
3
+ size 5883
runs/May20_23-13-59_240e96b0c4e9/events.out.tfevents.1684624443.240e96b0c4e9.31.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d418b40b73e72bd99a46dfb91c54a1f1a1f97dfd9bec5a415c84e8f97d176d6
3
+ size 4251
runs/May20_23-17-04_240e96b0c4e9/1684624626.4249246/events.out.tfevents.1684624626.240e96b0c4e9.31.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:715f7f1f820a408dd5726ce93b07e8954cbc34fc86456001df8e2cda86b101c7
3
+ size 5883
runs/May20_23-17-04_240e96b0c4e9/events.out.tfevents.1684624626.240e96b0c4e9.31.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c00512667223b80751e7f88d3ec5f8db1afc9cfc4418aa2db9dea8f55e60ccd1
3
+ size 4251
runs/May20_23-23-56_240e96b0c4e9/1684625038.5091765/events.out.tfevents.1684625038.240e96b0c4e9.31.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:396c7bdea289753a59923846a32dd6ac7d7be9de0735b7249223bfbc98c13412
3
+ size 5883
runs/May20_23-23-56_240e96b0c4e9/events.out.tfevents.1684625038.240e96b0c4e9.31.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e2a981a77b7aa2baf5caea9b70f71d1167e2c723b8573bc98c96cdcc9448fe1
3
+ size 4251
runs/May20_23-25-11_240e96b0c4e9/1684625114.1612713/events.out.tfevents.1684625114.240e96b0c4e9.31.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79497fbe32bd9812123643d911d364b85f1274eb2053a12e79dbcf161419752b
3
+ size 5883
runs/May20_23-25-11_240e96b0c4e9/events.out.tfevents.1684625114.240e96b0c4e9.31.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:452dc0e7442275be692eabc0e129fdfedca940708d44d2c0740ba3ffb818d8ee
3
+ size 4251
runs/May20_23-26-36_240e96b0c4e9/1684625199.215661/events.out.tfevents.1684625199.240e96b0c4e9.31.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:059fd7ca932baabb6daa241469415939145dcd009b36cfb692f6b14722e75d6d
3
+ size 5883
runs/May20_23-26-36_240e96b0c4e9/events.out.tfevents.1684625199.240e96b0c4e9.31.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d971e6d82309b7c64551e45c119f2a3e8ee93e8a4113d7197948e2e92eda832
3
+ size 4599
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": true,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "<|endoftext|>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "errors": "replace",
22
+ "model_max_length": 1024,
23
+ "pad_token": null,
24
+ "tokenizer_class": "GPT2Tokenizer",
25
+ "unk_token": {
26
+ "__type": "AddedToken",
27
+ "content": "<|endoftext|>",
28
+ "lstrip": false,
29
+ "normalized": true,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b6bb758f2928f9bfd164a0ae463dd6fa0a2607e2eaf56e3ebb37696d5e7b83d
3
+ size 3643
vocab.json ADDED
The diff for this file is too large to render. See raw diff