Hugging Face's logo

Vas123
/
130000

Text Generation
Transformers
TensorBoard
Safetensors
gptj
Generated from Trainer
Model card Files
xet
 Metrics Community
Vas123 commited on
Commit
f85d0a2
·
verified ·
1 Parent(s): 89024b9

End of training

Browse files
Files changed (12) hide show
  1. README.md +49 -51
  2. config.json +18 -23
  3. generation_config.json +1 -0
  4. model.safetensors +2 -2
  5. runs/Mar07_16-27-25_ab0fb96f36d9/events.out.tfevents.1709828849.ab0fb96f36d9.391.0 +3 -0
  6. runs/Mar07_16-31-01_ab0fb96f36d9/events.out.tfevents.1709829065.ab0fb96f36d9.391.1 +3 -0
  7. runs/Mar07_16-32-29_ab0fb96f36d9/events.out.tfevents.1709829154.ab0fb96f36d9.391.2 +3 -0
  8. runs/Mar07_16-32-29_ab0fb96f36d9/events.out.tfevents.1709829438.ab0fb96f36d9.391.3 +3 -0
  9. runs/Mar07_16-37-22_ab0fb96f36d9/events.out.tfevents.1709829449.ab0fb96f36d9.391.4 +3 -0
  10. runs/Mar07_16-38-38_ab0fb96f36d9/events.out.tfevents.1709829525.ab0fb96f36d9.391.5 +3 -0
  11. tokenizer_config.json +5 -1
  12. training_args.bin +1 -1
README.md CHANGED
@@ -1,6 +1,4 @@
1
  ---
2
- license: mit
3
- base_model: gpt2
4
  tags:
5
  - generated_from_trainer
6
  model-index:
@@ -13,9 +11,9 @@ should probably proofread and complete it, then remove this comment. -->
13
 
14
  # 130000
15
 
16
- This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 5.9987
19
 
20
  ## Model description
21
 
@@ -49,53 +47,53 @@ The following hyperparameters were used during training:
49
 
50
  | Training Loss | Epoch | Step | Validation Loss |
51
  |:-------------:|:-----:|:----:|:---------------:|
52
- | No log | 0.92 | 3 | 7.0396 |
53
- | No log | 1.85 | 6 | 6.5398 |
54
- | No log | 2.77 | 9 | 6.3337 |
55
- | 6.6916 | 4.0 | 13 | 6.3694 |
56
- | 6.6916 | 4.92 | 16 | 6.2945 |
57
- | 6.6916 | 5.85 | 19 | 6.3184 |
58
- | 6.1092 | 6.77 | 22 | 6.3726 |
59
- | 6.1092 | 8.0 | 26 | 6.2948 |
60
- | 6.1092 | 8.92 | 29 | 6.3374 |
61
- | 6.5151 | 9.85 | 32 | 6.3641 |
62
- | 6.5151 | 10.77 | 35 | 6.2335 |
63
- | 6.5151 | 12.0 | 39 | 6.1965 |
64
- | 5.998 | 12.92 | 42 | 6.0595 |
65
- | 5.998 | 13.85 | 45 | 6.0374 |
66
- | 5.998 | 14.77 | 48 | 6.0562 |
67
- | 5.6623 | 16.0 | 52 | 6.0128 |
68
- | 5.6623 | 16.92 | 55 | 5.9999 |
69
- | 5.6623 | 17.85 | 58 | 6.0008 |
70
- | 5.611 | 18.77 | 61 | 5.9992 |
71
- | 5.611 | 20.0 | 65 | 6.0017 |
72
- | 5.611 | 20.92 | 68 | 6.0005 |
73
- | 5.5519 | 21.85 | 71 | 5.9962 |
74
- | 5.5519 | 22.77 | 74 | 5.9964 |
75
- | 5.5519 | 24.0 | 78 | 5.9975 |
76
- | 5.5841 | 24.92 | 81 | 5.9974 |
77
- | 5.5841 | 25.85 | 84 | 6.0000 |
78
- | 5.5841 | 26.77 | 87 | 6.0019 |
79
- | 5.5582 | 28.0 | 91 | 6.0014 |
80
- | 5.5582 | 28.92 | 94 | 6.0016 |
81
- | 5.5582 | 29.85 | 97 | 5.9987 |
82
- | 5.591 | 30.77 | 100 | 5.9992 |
83
- | 5.591 | 32.0 | 104 | 5.9986 |
84
- | 5.591 | 32.92 | 107 | 5.9982 |
85
- | 5.5638 | 33.85 | 110 | 5.9983 |
86
- | 5.5638 | 34.77 | 113 | 5.9987 |
87
- | 5.5638 | 36.0 | 117 | 5.9989 |
88
- | 5.5683 | 36.92 | 120 | 5.9992 |
89
- | 5.5683 | 37.85 | 123 | 5.9995 |
90
- | 5.5683 | 38.77 | 126 | 5.9991 |
91
- | 5.5628 | 40.0 | 130 | 5.9992 |
92
- | 5.5628 | 40.92 | 133 | 5.9992 |
93
- | 5.5628 | 41.85 | 136 | 5.9991 |
94
- | 5.5628 | 42.77 | 139 | 5.9989 |
95
- | 5.5683 | 44.0 | 143 | 5.9987 |
96
- | 5.5683 | 44.92 | 146 | 5.9987 |
97
- | 5.5683 | 45.85 | 149 | 5.9987 |
98
- | 5.5534 | 46.15 | 150 | 5.9987 |
99
 
100
 
101
  ### Framework versions
 
1
  ---
 
 
2
  tags:
3
  - generated_from_trainer
4
  model-index:
 
11
 
12
  # 130000
13
 
14
+ This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
15
  It achieves the following results on the evaluation set:
16
+ - Loss: 6.0491
17
 
18
  ## Model description
19
 
 
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:----:|:---------------:|
50
+ | No log | 0.92 | 3 | 6.2222 |
51
+ | No log | 1.85 | 6 | 6.2146 |
52
+ | No log | 2.77 | 9 | 6.2032 |
53
+ | 5.9665 | 4.0 | 13 | 6.1877 |
54
+ | 5.9665 | 4.92 | 16 | 6.1734 |
55
+ | 5.9665 | 5.85 | 19 | 6.1620 |
56
+ | 5.8921 | 6.77 | 22 | 6.1539 |
57
+ | 5.8921 | 8.0 | 26 | 6.1426 |
58
+ | 5.8921 | 8.92 | 29 | 6.1335 |
59
+ | 5.8324 | 9.85 | 32 | 6.1277 |
60
+ | 5.8324 | 10.77 | 35 | 6.1178 |
61
+ | 5.8324 | 12.0 | 39 | 6.1105 |
62
+ | 5.8012 | 12.92 | 42 | 6.1059 |
63
+ | 5.8012 | 13.85 | 45 | 6.0992 |
64
+ | 5.8012 | 14.77 | 48 | 6.0959 |
65
+ | 5.7449 | 16.0 | 52 | 6.0910 |
66
+ | 5.7449 | 16.92 | 55 | 6.0859 |
67
+ | 5.7449 | 17.85 | 58 | 6.0819 |
68
+ | 5.7303 | 18.77 | 61 | 6.0767 |
69
+ | 5.7303 | 20.0 | 65 | 6.0734 |
70
+ | 5.7303 | 20.92 | 68 | 6.0721 |
71
+ | 5.6687 | 21.85 | 71 | 6.0694 |
72
+ | 5.6687 | 22.77 | 74 | 6.0658 |
73
+ | 5.6687 | 24.0 | 78 | 6.0628 |
74
+ | 5.6839 | 24.92 | 81 | 6.0627 |
75
+ | 5.6839 | 25.85 | 84 | 6.0600 |
76
+ | 5.6839 | 26.77 | 87 | 6.0586 |
77
+ | 5.6499 | 28.0 | 91 | 6.0572 |
78
+ | 5.6499 | 28.92 | 94 | 6.0558 |
79
+ | 5.6499 | 29.85 | 97 | 6.0555 |
80
+ | 5.6703 | 30.77 | 100 | 6.0545 |
81
+ | 5.6703 | 32.0 | 104 | 6.0533 |
82
+ | 5.6703 | 32.92 | 107 | 6.0520 |
83
+ | 5.6404 | 33.85 | 110 | 6.0518 |
84
+ | 5.6404 | 34.77 | 113 | 6.0511 |
85
+ | 5.6404 | 36.0 | 117 | 6.0509 |
86
+ | 5.6414 | 36.92 | 120 | 6.0504 |
87
+ | 5.6414 | 37.85 | 123 | 6.0498 |
88
+ | 5.6414 | 38.77 | 126 | 6.0498 |
89
+ | 5.6347 | 40.0 | 130 | 6.0496 |
90
+ | 5.6347 | 40.92 | 133 | 6.0493 |
91
+ | 5.6347 | 41.85 | 136 | 6.0491 |
92
+ | 5.6347 | 42.77 | 139 | 6.0491 |
93
+ | 5.638 | 44.0 | 143 | 6.0491 |
94
+ | 5.638 | 44.92 | 146 | 6.0491 |
95
+ | 5.638 | 45.85 | 149 | 6.0491 |
96
+ | 5.6249 | 46.15 | 150 | 6.0491 |
97
 
98
 
99
  ### Framework versions
config.json CHANGED
@@ -1,39 +1,34 @@
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": 0,
9
- "embd_pdrop": 0.1,
10
  "eos_token_id": 0,
 
 
 
11
  "initializer_range": 0.02,
 
12
  "layer_norm_epsilon": 1e-05,
13
- "model_type": "gpt2",
14
  "n_ctx": 512,
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": "4.38.2",
 
37
  "use_cache": true,
38
  "vocab_size": 3000
39
  }
 
1
  {
 
2
  "activation_function": "gelu_new",
3
  "architectures": [
4
+ "GPTJForCausalLM"
5
  ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "attn_pdrop": 0.0,
8
  "bos_token_id": 0,
9
+ "embd_pdrop": 0.0,
10
  "eos_token_id": 0,
11
+ "gradient_checkpointing": false,
12
+ "hidden_act": "gelu",
13
+ "hidden_dropout_prob": 0.0,
14
  "initializer_range": 0.02,
15
+ "intermediate_size": 37,
16
  "layer_norm_epsilon": 1e-05,
17
+ "model_type": "gptj",
18
  "n_ctx": 512,
19
+ "n_embd": 32,
20
+ "n_head": 4,
21
  "n_inner": null,
22
+ "n_layer": 5,
23
+ "n_positions": 512,
24
+ "pad_token_id": 98,
25
+ "resid_pdrop": 0.0,
26
+ "rotary_dim": 4,
27
  "scale_attn_weights": true,
28
+ "tie_word_embeddings": false,
 
 
 
 
 
 
 
 
 
 
29
  "torch_dtype": "float32",
30
  "transformers_version": "4.38.2",
31
+ "type_vocab_size": 16,
32
  "use_cache": true,
33
  "vocab_size": 3000
34
  }
generation_config.json CHANGED
@@ -2,5 +2,6 @@
2
  "_from_model_config": true,
3
  "bos_token_id": 0,
4
  "eos_token_id": 0,
 
5
  "transformers_version": "4.38.2"
6
  }
 
2
  "_from_model_config": true,
3
  "bos_token_id": 0,
4
  "eos_token_id": 0,
5
+ "pad_token_id": 98,
6
  "transformers_version": "4.38.2"
7
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:351b48eaff23f55746de242ba034442136e0a6352690b504c07a9fb3393b3097
3
- size 352600704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bf418c8888f3a04e41616a29ade978ed5a474ebb0d5b69f747abf61958af2ba
3
+ size 1035784
runs/Mar07_16-27-25_ab0fb96f36d9/events.out.tfevents.1709828849.ab0fb96f36d9.391.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28253ec6184cc4d03d3747f1cd9e1c9f30b2f1a2c686623ba7a4714ccf203732
3
+ size 4657
runs/Mar07_16-31-01_ab0fb96f36d9/events.out.tfevents.1709829065.ab0fb96f36d9.391.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e3994568be614943a8edf3e14794d450552093fc46ab84ebbd26e7ce11c239c
3
+ size 4598
runs/Mar07_16-32-29_ab0fb96f36d9/events.out.tfevents.1709829154.ab0fb96f36d9.391.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d167a6bba0084ca78afd9a6f0ae796b1fb605d091c0461f1be8cd549c746df8
3
+ size 20611
runs/Mar07_16-32-29_ab0fb96f36d9/events.out.tfevents.1709829438.ab0fb96f36d9.391.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:843ad9f8ee5a0bf7b95773392ad29b4b35ca177b69470eade92c7cbcc779fe1e
3
+ size 4598
runs/Mar07_16-37-22_ab0fb96f36d9/events.out.tfevents.1709829449.ab0fb96f36d9.391.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0af42242235272c01af969c149f4988b176900a0f5ae2d314f48772a6fc1ad19
3
+ size 20612
runs/Mar07_16-38-38_ab0fb96f36d9/events.out.tfevents.1709829525.ab0fb96f36d9.391.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7af6ae358089ef8fc638591dc53d38320e19cb425e393917f76e6dc91ccaa2a1
3
+ size 20611
tokenizer_config.json CHANGED
@@ -12,7 +12,11 @@
12
  "bos_token": "<|endoftext|>",
13
  "clean_up_tokenization_spaces": true,
14
  "eos_token": "<|endoftext|>",
 
15
  "model_max_length": 1000000000000000019884624838656,
16
  "pad_token": "<|endoftext|>",
17
- "tokenizer_class": "PreTrainedTokenizerFast"
 
 
 
18
  }
 
12
  "bos_token": "<|endoftext|>",
13
  "clean_up_tokenization_spaces": true,
14
  "eos_token": "<|endoftext|>",
15
+ "max_length": 512,
16
  "model_max_length": 1000000000000000019884624838656,
17
  "pad_token": "<|endoftext|>",
18
+ "stride": 0,
19
+ "tokenizer_class": "PreTrainedTokenizerFast",
20
+ "truncation_side": "right",
21
+ "truncation_strategy": "longest_first"
22
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:271ba549ef8c7caf4fb91fe382f5864e4ddb623c2ad4de01dfdcd7b38cda4ee7
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f698f3bfd884129510dd5f8a5793bf0f5d0a85c3f763e753ed43c97e4e97d78
3
  size 4920