DavidLanz commited on
Commit
7a82882
1 Parent(s): 7d39b6f

Upload . with huggingface_hub

Browse files
checkpoint-7000/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": 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": 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": "4.26.1",
37
+ "use_cache": true,
38
+ "vocab_size": 50257
39
+ }
checkpoint-7000/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": "4.26.1"
6
+ }
checkpoint-7000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d69d6879a62206575f2ba474bf410c23d2c72862cbcb320050e4b35f76fd2400
3
+ size 995610735
checkpoint-7000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdfe5191ba75c749a019c919625d135622e26af632652750498c97a7cf333699
3
+ size 510400655
checkpoint-7000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:373ead1d6e90c01ba9f7b8b45582a76ce3b9a90f43e125172380505ddbb3d7fe
3
+ size 14655
checkpoint-7000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0434fba78f0b23544fca908332397f44cad5e8bebbda8a0ccaafe02ae104da5f
3
+ size 623
checkpoint-7000/trainer_state.json ADDED
@@ -0,0 +1,100 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.9680624556423,
5
+ "global_step": 7000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.35,
12
+ "learning_rate": 4.64513839602555e-05,
13
+ "loss": 3.8375,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.71,
18
+ "learning_rate": 4.2902767920511e-05,
19
+ "loss": 3.6126,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 1.06,
24
+ "learning_rate": 3.9354151880766505e-05,
25
+ "loss": 3.5033,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 1.42,
30
+ "learning_rate": 3.5805535841022005e-05,
31
+ "loss": 3.3288,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 1.77,
36
+ "learning_rate": 3.22569198012775e-05,
37
+ "loss": 3.2926,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 2.13,
42
+ "learning_rate": 2.8708303761533e-05,
43
+ "loss": 3.2287,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 2.48,
48
+ "learning_rate": 2.5159687721788504e-05,
49
+ "loss": 3.1489,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 2.84,
54
+ "learning_rate": 2.1611071682044005e-05,
55
+ "loss": 3.1289,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 3.19,
60
+ "learning_rate": 1.8062455642299502e-05,
61
+ "loss": 3.0657,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 3.55,
66
+ "learning_rate": 1.4513839602555005e-05,
67
+ "loss": 3.0318,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 3.9,
72
+ "learning_rate": 1.0965223562810504e-05,
73
+ "loss": 3.0376,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 4.26,
78
+ "learning_rate": 7.416607523066005e-06,
79
+ "loss": 2.9734,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 4.61,
84
+ "learning_rate": 3.867991483321505e-06,
85
+ "loss": 2.9613,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 4.97,
90
+ "learning_rate": 3.19375443577005e-07,
91
+ "loss": 2.9708,
92
+ "step": 7000
93
+ }
94
+ ],
95
+ "max_steps": 7045,
96
+ "num_train_epochs": 5,
97
+ "total_flos": 3656520695808000.0,
98
+ "trial_name": null,
99
+ "trial_params": null
100
+ }
checkpoint-7000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78a6c9d300c500b64cfbba4e2a9e869a69b43bad11bf88eff8991734d404ef79
3
+ size 3439
merges.txt 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 sha256:34eff0d88b84c91faf25000162ebb25808f45b2c706aa177097d1b40894267c3
3
  size 510400655
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b474bb0968cc545d715235a7d9cf64a0b094302c8ef79d5701416683d6425dbe
3
  size 510400655
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "unk_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "eos_token": {
13
+ "__type": "AddedToken",
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "errors": "replace",
21
+ "model_max_length": 1024,
22
+ "name_or_path": "gpt2",
23
+ "pad_token": null,
24
+ "special_tokens_map_file": null,
25
+ "tokenizer_class": "GPT2Tokenizer",
26
+ "unk_token": {
27
+ "__type": "AddedToken",
28
+ "content": "<|endoftext|>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:31b667d9492638a03fe0193e17c0f4583dadae01e60b82ae7b0d4bf12e1d1801
3
  size 3439
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78a6c9d300c500b64cfbba4e2a9e869a69b43bad11bf88eff8991734d404ef79
3
  size 3439
vocab.json ADDED
The diff for this file is too large to render. See raw diff