Hugging Face's logo

msclar
/
referee-control_iter-5

Text Generation
Transformers
PyTorch
gpt2
text-generation-inference
Inference Endpoints
Model card Files Community
msclar commited on
Commit
b6a928f
·
1 Parent(s): ba8852c

Upload 4 files

Browse files
Files changed (4) hide show
  1. config.json +39 -0
  2. pytorch_model.bin +3 -0
  3. trainer_state.json +80 -0
  4. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "finetuned_bottleself/gpt2-large_control_code_tenway_bucket_chunks_2_16_100_106_step4_two_epochs_repeatbucketid_fluencyfilter_1.0",
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": 1280,
16
+ "n_head": 20,
17
+ "n_inner": null,
18
+ "n_layer": 36,
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": "4.18.0.dev0",
37
+ "use_cache": true,
38
+ "vocab_size": 50257
39
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6efcf6f884607b073bfb91ed7fcf60287d54c1d113b3d430fc192794db6070d
3
+ size 3134054729
trainer_state.json ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "global_step": 4046,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.25,
12
+ "learning_rate": 3.8580246913580246e-05,
13
+ "loss": 1.7863,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.49,
18
+ "learning_rate": 5.883034610630408e-05,
19
+ "loss": 1.2957,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.74,
24
+ "learning_rate": 4.917336217552534e-05,
25
+ "loss": 0.8962,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.99,
30
+ "learning_rate": 3.9516378244746606e-05,
31
+ "loss": 0.6393,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 1.0,
36
+ "eval_loss": 0.48078134655952454,
37
+ "eval_runtime": 459.2193,
38
+ "eval_samples_per_second": 7.778,
39
+ "eval_steps_per_second": 0.78,
40
+ "step": 2023
41
+ },
42
+ {
43
+ "epoch": 1.24,
44
+ "learning_rate": 2.9859394313967864e-05,
45
+ "loss": 0.3256,
46
+ "step": 2500
47
+ },
48
+ {
49
+ "epoch": 1.48,
50
+ "learning_rate": 2.0202410383189122e-05,
51
+ "loss": 0.2953,
52
+ "step": 3000
53
+ },
54
+ {
55
+ "epoch": 1.73,
56
+ "learning_rate": 1.0545426452410384e-05,
57
+ "loss": 0.2583,
58
+ "step": 3500
59
+ },
60
+ {
61
+ "epoch": 1.98,
62
+ "learning_rate": 8.88442521631644e-07,
63
+ "loss": 0.2394,
64
+ "step": 4000
65
+ },
66
+ {
67
+ "epoch": 2.0,
68
+ "eval_loss": 0.32980823516845703,
69
+ "eval_runtime": 459.2016,
70
+ "eval_samples_per_second": 7.779,
71
+ "eval_steps_per_second": 0.78,
72
+ "step": 4046
73
+ }
74
+ ],
75
+ "max_steps": 4046,
76
+ "num_train_epochs": 2,
77
+ "total_flos": 6.87875414016e+16,
78
+ "trial_name": null,
79
+ "trial_params": null
80
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81203fb4d988dc23ff85ef427b0a70eaa249cfdb4541f6068e9dce2cbdefd5a9
3
+ size 3247