End of training
Browse files- README.md +49 -51
- config.json +18 -23
- generation_config.json +1 -0
- model.safetensors +2 -2
- runs/Mar07_16-27-25_ab0fb96f36d9/events.out.tfevents.1709828849.ab0fb96f36d9.391.0 +3 -0
- runs/Mar07_16-31-01_ab0fb96f36d9/events.out.tfevents.1709829065.ab0fb96f36d9.391.1 +3 -0
- runs/Mar07_16-32-29_ab0fb96f36d9/events.out.tfevents.1709829154.ab0fb96f36d9.391.2 +3 -0
- runs/Mar07_16-32-29_ab0fb96f36d9/events.out.tfevents.1709829438.ab0fb96f36d9.391.3 +3 -0
- runs/Mar07_16-37-22_ab0fb96f36d9/events.out.tfevents.1709829449.ab0fb96f36d9.391.4 +3 -0
- runs/Mar07_16-38-38_ab0fb96f36d9/events.out.tfevents.1709829525.ab0fb96f36d9.391.5 +3 -0
- tokenizer_config.json +5 -1
- 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 [
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Loss:
|
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 |
|
53 |
-
| No log | 1.85 | 6 | 6.
|
54 |
-
| No log | 2.77 | 9 | 6.
|
55 |
-
|
|
56 |
-
|
|
57 |
-
|
|
58 |
-
|
|
59 |
-
|
|
60 |
-
|
|
61 |
-
|
|
62 |
-
|
|
63 |
-
|
|
64 |
-
| 5.
|
65 |
-
| 5.
|
66 |
-
| 5.
|
67 |
-
| 5.
|
68 |
-
| 5.
|
69 |
-
| 5.
|
70 |
-
| 5.
|
71 |
-
| 5.
|
72 |
-
| 5.
|
73 |
-
| 5.
|
74 |
-
| 5.
|
75 |
-
| 5.
|
76 |
-
| 5.
|
77 |
-
| 5.
|
78 |
-
| 5.
|
79 |
-
| 5.
|
80 |
-
| 5.
|
81 |
-
| 5.
|
82 |
-
| 5.
|
83 |
-
| 5.
|
84 |
-
| 5.
|
85 |
-
| 5.
|
86 |
-
| 5.
|
87 |
-
| 5.
|
88 |
-
| 5.
|
89 |
-
| 5.
|
90 |
-
| 5.
|
91 |
-
| 5.
|
92 |
-
| 5.
|
93 |
-
| 5.
|
94 |
-
| 5.
|
95 |
-
| 5.
|
96 |
-
| 5.
|
97 |
-
| 5.
|
98 |
-
| 5.
|
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 |
-
"
|
6 |
],
|
7 |
-
"
|
|
|
8 |
"bos_token_id": 0,
|
9 |
-
"embd_pdrop": 0.
|
10 |
"eos_token_id": 0,
|
|
|
|
|
|
|
11 |
"initializer_range": 0.02,
|
|
|
12 |
"layer_norm_epsilon": 1e-05,
|
13 |
-
"model_type": "
|
14 |
"n_ctx": 512,
|
15 |
-
"n_embd":
|
16 |
-
"n_head":
|
17 |
"n_inner": null,
|
18 |
-
"n_layer":
|
19 |
-
"n_positions":
|
20 |
-
"
|
21 |
-
"resid_pdrop": 0.
|
22 |
-
"
|
23 |
"scale_attn_weights": true,
|
24 |
-
"
|
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:
|
3 |
-
size
|
|
|
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 |
-
"
|
|
|
|
|
|
|
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:
|
3 |
size 4920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1f698f3bfd884129510dd5f8a5793bf0f5d0a85c3f763e753ed43c97e4e97d78
|
3 |
size 4920
|