Wikidepia commited on
Commit
85bc19d
1 Parent(s): 2a8d4ac

Initial model

Browse files
README.md ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: gpt2-spam
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # gpt2-spam
14
+
15
+ This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on an unknown dataset.
16
+
17
+ ## Model description
18
+
19
+ More information needed
20
+
21
+ ## Intended uses & limitations
22
+
23
+ More information needed
24
+
25
+ ## Training and evaluation data
26
+
27
+ More information needed
28
+
29
+ ## Training procedure
30
+
31
+ ### Training hyperparameters
32
+
33
+ The following hyperparameters were used during training:
34
+ - learning_rate: 5e-05
35
+ - train_batch_size: 8
36
+ - eval_batch_size: 8
37
+ - seed: 42
38
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
39
+ - lr_scheduler_type: linear
40
+ - num_epochs: 3.0
41
+
42
+ ### Training results
43
+
44
+
45
+
46
+ ### Framework versions
47
+
48
+ - Transformers 4.18.0.dev0
49
+ - Pytorch 1.11.0
50
+ - Datasets 2.0.0
51
+ - Tokenizers 0.11.6
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "train_loss": 2.911934937572436,
4
+ "train_runtime": 1500.6199,
5
+ "train_samples": 11785,
6
+ "train_samples_per_second": 23.56,
7
+ "train_steps_per_second": 2.947
8
+ }
config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilgpt2",
3
+ "_num_labels": 1,
4
+ "activation_function": "gelu_new",
5
+ "architectures": [
6
+ "GPT2LMHeadModel"
7
+ ],
8
+ "attn_pdrop": 0.1,
9
+ "bos_token_id": 50256,
10
+ "embd_pdrop": 0.1,
11
+ "eos_token_id": 50256,
12
+ "id2label": {
13
+ "0": "LABEL_0"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "label2id": {
17
+ "LABEL_0": 0
18
+ },
19
+ "layer_norm_epsilon": 1e-05,
20
+ "model_type": "gpt2",
21
+ "n_ctx": 1024,
22
+ "n_embd": 768,
23
+ "n_head": 12,
24
+ "n_inner": null,
25
+ "n_layer": 6,
26
+ "n_positions": 1024,
27
+ "reorder_and_upcast_attn": false,
28
+ "resid_pdrop": 0.1,
29
+ "scale_attn_by_inverse_layer_idx": false,
30
+ "scale_attn_weights": true,
31
+ "summary_activation": null,
32
+ "summary_first_dropout": 0.1,
33
+ "summary_proj_to_labels": true,
34
+ "summary_type": "cls_index",
35
+ "summary_use_proj": true,
36
+ "task_specific_params": {
37
+ "text-generation": {
38
+ "do_sample": true,
39
+ "max_length": 50
40
+ }
41
+ },
42
+ "torch_dtype": "float32",
43
+ "transformers_version": "4.18.0.dev0",
44
+ "use_cache": true,
45
+ "vocab_size": 50257
46
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04d7f2ceb100223dcb41e5a5d6727a8df9f5e2dab63fcd12097a1f795311252d
3
+ size 333973213
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "distilgpt2", "tokenizer_class": "GPT2Tokenizer"}
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "train_loss": 2.911934937572436,
4
+ "train_runtime": 1500.6199,
5
+ "train_samples": 11785,
6
+ "train_samples_per_second": 23.56,
7
+ "train_steps_per_second": 2.947
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "global_step": 4422,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.34,
12
+ "learning_rate": 4.434644957033017e-05,
13
+ "loss": 3.3707,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.68,
18
+ "learning_rate": 3.869289914066034e-05,
19
+ "loss": 3.0677,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 1.02,
24
+ "learning_rate": 3.30393487109905e-05,
25
+ "loss": 2.971,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 1.36,
30
+ "learning_rate": 2.7385798281320668e-05,
31
+ "loss": 2.8758,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 1.7,
36
+ "learning_rate": 2.173224785165084e-05,
37
+ "loss": 2.8251,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 2.04,
42
+ "learning_rate": 1.6078697421981004e-05,
43
+ "loss": 2.7961,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 2.37,
48
+ "learning_rate": 1.0425146992311172e-05,
49
+ "loss": 2.7783,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 2.71,
54
+ "learning_rate": 4.771596562641339e-06,
55
+ "loss": 2.7537,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "step": 4422,
61
+ "total_flos": 9238146617180160.0,
62
+ "train_loss": 2.911934937572436,
63
+ "train_runtime": 1500.6199,
64
+ "train_samples_per_second": 23.56,
65
+ "train_steps_per_second": 2.947
66
+ }
67
+ ],
68
+ "max_steps": 4422,
69
+ "num_train_epochs": 3,
70
+ "total_flos": 9238146617180160.0,
71
+ "trial_name": null,
72
+ "trial_params": null
73
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1755db2a95b2ccef0182ecfb62f7a3caef86aeb0449ed17dc58b1e9a4c3a6b92
3
+ size 2991
vocab.json ADDED
The diff for this file is too large to render. See raw diff