tomekkorbak commited on
Commit
e514328
1 Parent(s): 278c637

Training in progress, step 1255

Browse files
checkpoint-1255/added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<|aligned|>": 50257,
3
+ "<|misaligned|>": 50258
4
+ }
checkpoint-1255/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "tomekkorbak/cranky_lichterman",
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": "4.24.0",
37
+ "use_cache": true,
38
+ "vocab_size": 50259
39
+ }
checkpoint-1255/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1255/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea1b9e047ee9a4430f4cf8284e5100685fd11cc9b0dcb4d0be61be1c72b93ca7
3
+ size 995616305
checkpoint-1255/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f58c50722f3be954f91aa138e4c08e26c79b0e105a189c7f414805673650049
3
+ size 510402665
checkpoint-1255/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba89a856ab8d6a28a0444f6c4e3ebc1bf6e0664834176fad9ae9a2cd527fb228
3
+ size 14439
checkpoint-1255/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b874b11a1ea83af3ac7f7a2f569ffacf422ca127431a15ce7a8f962cfcbbb914
3
+ size 559
checkpoint-1255/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b3d4b7a3985058e4967c6b082678a19fdb9dd43f307bd664d6b27c7485b19c4
3
+ size 623
checkpoint-1255/special_tokens_map.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|aligned|>",
4
+ "<|misaligned|>"
5
+ ],
6
+ "bos_token": "<|endoftext|>",
7
+ "eos_token": "<|endoftext|>",
8
+ "pad_token": "<|endoftext|>",
9
+ "unk_token": "<|endoftext|>"
10
+ }
checkpoint-1255/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1255/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-1255/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1255/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:642b2ee2ca0b664aa7ff746a716a153bc7db99676c4d392937b8759a7ccbc7bf
3
+ size 3375
checkpoint-1255/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8d9cc4e2cdc6faae8b80bc01a73f7899c77d339ab82bc7e7b80671ab1f76cfbc
3
  size 510402665
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f58c50722f3be954f91aa138e4c08e26c79b0e105a189c7f414805673650049
3
  size 510402665
tokenizer.json CHANGED
@@ -1,14 +1,7 @@
1
  {
2
  "version": "1.0",
3
  "truncation": null,
4
- "padding": {
5
- "strategy": "BatchLongest",
6
- "direction": "Right",
7
- "pad_to_multiple_of": null,
8
- "pad_id": 50256,
9
- "pad_type_id": 0,
10
- "pad_token": "<|endoftext|>"
11
- },
12
  "added_tokens": [
13
  {
14
  "id": 50256,
 
1
  {
2
  "version": "1.0",
3
  "truncation": null,
4
+ "padding": null,
 
 
 
 
 
 
 
5
  "added_tokens": [
6
  {
7
  "id": 50256,