Mithul27/GPT2-medium-fine-tuned
Browse files- README.md +52 -0
- config.json +41 -0
- generation_config.json +6 -0
- model.safetensors +3 -0
- runs/Jun28_09-13-02_20bf414aaf2a/events.out.tfevents.1719565982.20bf414aaf2a.16191.0 +3 -0
- runs/Jun28_10-08-38_20bf414aaf2a/events.out.tfevents.1719569319.20bf414aaf2a.16191.1 +3 -0
- runs/Jun28_12-34-40_20bf414aaf2a/events.out.tfevents.1719578081.20bf414aaf2a.16191.2 +3 -0
- runs/Jun28_13-18-18_20bf414aaf2a/events.out.tfevents.1719580698.20bf414aaf2a.16191.3 +3 -0
- runs/Jun28_13-21-33_20bf414aaf2a/events.out.tfevents.1719580894.20bf414aaf2a.84782.0 +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: gpt2-medium
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: results
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
+
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# results
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [gpt2-medium](https://huggingface.co/gpt2-medium) on an unknown dataset.
|
17 |
+
|
18 |
+
## Model description
|
19 |
+
|
20 |
+
More information needed
|
21 |
+
|
22 |
+
## Intended uses & limitations
|
23 |
+
|
24 |
+
More information needed
|
25 |
+
|
26 |
+
## Training and evaluation data
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Training procedure
|
31 |
+
|
32 |
+
### Training hyperparameters
|
33 |
+
|
34 |
+
The following hyperparameters were used during training:
|
35 |
+
- learning_rate: 5e-05
|
36 |
+
- train_batch_size: 4
|
37 |
+
- eval_batch_size: 8
|
38 |
+
- seed: 42
|
39 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
40 |
+
- lr_scheduler_type: linear
|
41 |
+
- num_epochs: 3
|
42 |
+
|
43 |
+
### Training results
|
44 |
+
|
45 |
+
|
46 |
+
|
47 |
+
### Framework versions
|
48 |
+
|
49 |
+
- Transformers 4.41.2
|
50 |
+
- Pytorch 2.3.0+cu121
|
51 |
+
- Datasets 2.20.0
|
52 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "gpt2-medium",
|
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": 1024,
|
16 |
+
"n_head": 16,
|
17 |
+
"n_inner": null,
|
18 |
+
"n_layer": 24,
|
19 |
+
"n_positions": 1024,
|
20 |
+
"n_special": 0,
|
21 |
+
"predict_special_tokens": true,
|
22 |
+
"reorder_and_upcast_attn": false,
|
23 |
+
"resid_pdrop": 0.1,
|
24 |
+
"scale_attn_by_inverse_layer_idx": false,
|
25 |
+
"scale_attn_weights": true,
|
26 |
+
"summary_activation": null,
|
27 |
+
"summary_first_dropout": 0.1,
|
28 |
+
"summary_proj_to_labels": true,
|
29 |
+
"summary_type": "cls_index",
|
30 |
+
"summary_use_proj": true,
|
31 |
+
"task_specific_params": {
|
32 |
+
"text-generation": {
|
33 |
+
"do_sample": true,
|
34 |
+
"max_length": 50
|
35 |
+
}
|
36 |
+
},
|
37 |
+
"torch_dtype": "float32",
|
38 |
+
"transformers_version": "4.41.2",
|
39 |
+
"use_cache": true,
|
40 |
+
"vocab_size": 50257
|
41 |
+
}
|
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": "4.41.2"
|
6 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ae31103acbf5c328fe56e8a0ae2e5ef0bd1f02f5db63e67c76e2e549c7b08a1
|
3 |
+
size 1419322880
|
runs/Jun28_09-13-02_20bf414aaf2a/events.out.tfevents.1719565982.20bf414aaf2a.16191.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4f19638c00711dc500c00aadf83f1ed0d4ef70acef601961a56788ce4d34217e
|
3 |
+
size 5362
|
runs/Jun28_10-08-38_20bf414aaf2a/events.out.tfevents.1719569319.20bf414aaf2a.16191.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9cd1464ca9ecd7eb28149ce71751be160715e6dd2c384f53c75d4cf4f2a79c7a
|
3 |
+
size 5362
|
runs/Jun28_12-34-40_20bf414aaf2a/events.out.tfevents.1719578081.20bf414aaf2a.16191.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:11690c89e32bedeb09112f3881c117878b8e590b4337105f91bc2be26a98db7b
|
3 |
+
size 5368
|
runs/Jun28_13-18-18_20bf414aaf2a/events.out.tfevents.1719580698.20bf414aaf2a.16191.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:272044c41519559ce9cb4e8ccb88fd0424e259587d9b7b8ef7e81a268ff7a587
|
3 |
+
size 4184
|
runs/Jun28_13-21-33_20bf414aaf2a/events.out.tfevents.1719580894.20bf414aaf2a.84782.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:37d0a406916c530705ea908e0cdbb95c20ac95f67603b0e0c1237efe1b20c708
|
3 |
+
size 5428
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5ec3fb53b5583bfb949cbe203a0e4ae37d0ba5047061dee4395b08cd5ffc9e66
|
3 |
+
size 5048
|