tomekkorbak commited on
Commit
5db1318
1 Parent(s): e5d7cc3

Training in progress, step 50354

Browse files
checkpoint-50354/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": "4.24.0",
37
+ "use_cache": true,
38
+ "vocab_size": 50257
39
+ }
checkpoint-50354/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-50354/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3b5036fe5d89158e474f25589fc83a7d542c584be4e00644bce2bd4711f25b7
3
+ size 995604017
checkpoint-50354/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92d012d77ff18388cb7237193694592830ad2b1428a79e27659d6529db3d0b67
3
+ size 510396521
checkpoint-50354/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76f558862d868b6870ed15e2eefc15863064a093a4fd3b36908a8a9ac665dbde
3
+ size 14439
checkpoint-50354/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74e9f5a179d0e9e36107e428f2d233e79c87fb47ce2abf87e3f70169e2d77b86
3
+ size 559
checkpoint-50354/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1aa5fa47bd34af7d5e27837813f222967936a2c4027a319ca0a96abbac155c93
3
+ size 623
checkpoint-50354/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
checkpoint-50354/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-50354/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-50354/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-50354/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7ecd760f114b77f7a733671546632cd31039930a581d7e26cfc732f7e157d2a
3
+ size 3375
checkpoint-50354/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:a22eb85415929a22782699ec322a4eb9dc6cc649ece1284d54223b6eb4c63b8e
3
  size 510396521
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92d012d77ff18388cb7237193694592830ad2b1428a79e27659d6529db3d0b67
3
  size 510396521
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,