Hugging Face's logo

tomekkorbak
/
test-test

Transformers
PyTorch
gpt2
text-generation-inference
Model card Files
xet
 Community
1
tomekkorbak commited on
Commit
993fb7b
·
1 Parent(s): e2aeea2

Training in progress, step 4

Browse files
Files changed (15) hide show
  1. checkpoint-4/added_tokens.json +4 -0
  2. checkpoint-4/config.json +39 -0
  3. checkpoint-4/merges.txt +0 -0
  4. checkpoint-4/optimizer.pt +3 -0
  5. checkpoint-4/pytorch_model.bin +3 -0
  6. checkpoint-4/rng_state.pth +3 -0
  7. checkpoint-4/scaler.pt +3 -0
  8. checkpoint-4/scheduler.pt +3 -0
  9. checkpoint-4/special_tokens_map.json +10 -0
  10. checkpoint-4/tokenizer.json +0 -0
  11. checkpoint-4/tokenizer_config.json +10 -0
  12. checkpoint-4/trainer_state.json +44 -0
  13. checkpoint-4/training_args.bin +3 -0
  14. checkpoint-4/vocab.json +0 -0
  15. pytorch_model.bin +1 -1
checkpoint-4/added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<|aligned|>": 50257,
3
+ "<|misaligned|>": 50258
4
+ }
checkpoint-4/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": "4.23.1",
37
+ "use_cache": true,
38
+ "vocab_size": 50259
39
+ }
checkpoint-4/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-4/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcaa39c52990e7c273ac357a4ab5cf706bbe56ea177fc5bacc24e9c9154114b8
3
+ size 995616113
checkpoint-4/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:065131b67d7ed8c545b316b6fd9014044762a1ec89a4bf8f720ea32404f0d103
3
+ size 510402665
checkpoint-4/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a80edd54ee291e06101fac8bde66a8695a9c32f844322e23901e1e1851435043
3
+ size 14503
checkpoint-4/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8c57832d2a84e2e9147acd8319547545aaaaeee094e14c676b82efff470d09e
3
+ size 559
checkpoint-4/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67f98ebd0cb94aa716f10d3339303aa62228155bb1cdf04140abb3ccf4111642
3
+ size 623
checkpoint-4/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-4/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-4/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-4/trainer_state.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 7.943758192000635e-05,
5
+ "global_step": 4,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.0,
12
+ "learning_rate": 0.0001984126984126984,
13
+ "loss": 10.8451,
14
+ "theoretical_loss": 20.812814784551147,
15
+ "tokens_seen": 65536
16
+ },
17
+ {
18
+ "epoch": 0.0,
19
+ "learning_rate": 0.0003968253968253968,
20
+ "loss": 10.8162,
21
+ "theoretical_loss": 17.56619808733264,
22
+ "tokens_seen": 131072
23
+ },
24
+ {
25
+ "epoch": 0.0,
26
+ "learning_rate": 0.0005952380952380953,
27
+ "loss": 9.9152,
28
+ "theoretical_loss": 15.939474075840563,
29
+ "tokens_seen": 196608
30
+ },
31
+ {
32
+ "epoch": 0.0,
33
+ "learning_rate": 0.0007936507936507937,
34
+ "loss": 11.2539,
35
+ "theoretical_loss": 14.892313738992565,
36
+ "tokens_seen": 262144
37
+ }
38
+ ],
39
+ "max_steps": 50354,
40
+ "num_train_epochs": 9223372036854775807,
41
+ "total_flos": 133781520384000.0,
42
+ "trial_name": null,
43
+ "trial_params": null
44
+ }
checkpoint-4/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c521b59b6883cc6d2741d27067f3606e21b1facbae174c079c95225159a81c1
3
+ size 3375
checkpoint-4/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 sha256:75ccc8e3873f713138888cce0f0cfa502190635912d64337d690610b4b07667b
3
  size 510402665
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:065131b67d7ed8c545b316b6fd9014044762a1ec89a4bf8f720ea32404f0d103
3
  size 510402665