End of training
Browse files- README.md +61 -0
- config.json +46 -0
- generation_config.json +6 -0
- model.safetensors +3 -0
- runs/Aug27_06-54-00_61dd18a96af3/events.out.tfevents.1724741641.61dd18a96af3.594.0 +3 -0
- runs/Aug27_06-54-00_61dd18a96af3/events.out.tfevents.1724741652.61dd18a96af3.594.1 +3 -0
- runs/Aug27_06-54-00_61dd18a96af3/events.out.tfevents.1724741660.61dd18a96af3.594.2 +3 -0
- runs/Aug27_06-54-00_61dd18a96af3/events.out.tfevents.1724741669.61dd18a96af3.594.3 +3 -0
- runs/Aug27_06-54-00_61dd18a96af3/events.out.tfevents.1724741678.61dd18a96af3.594.4 +3 -0
- runs/Aug27_06-54-00_61dd18a96af3/events.out.tfevents.1724741687.61dd18a96af3.594.5 +3 -0
- runs/Aug27_06-54-00_61dd18a96af3/events.out.tfevents.1724741697.61dd18a96af3.594.6 +3 -0
- runs/Aug27_06-54-00_61dd18a96af3/events.out.tfevents.1724741706.61dd18a96af3.594.7 +3 -0
- runs/Aug27_06-54-00_61dd18a96af3/events.out.tfevents.1724741715.61dd18a96af3.594.8 +3 -0
- runs/Aug27_06-54-00_61dd18a96af3/events.out.tfevents.1724741723.61dd18a96af3.594.9 +3 -0
- runs/Aug27_06-54-00_61dd18a96af3/events.out.tfevents.1724741733.61dd18a96af3.594.10 +3 -0
- runs/Aug27_06-54-00_61dd18a96af3/events.out.tfevents.1724741742.61dd18a96af3.594.11 +3 -0
- runs/Aug27_06-54-00_61dd18a96af3/events.out.tfevents.1724741751.61dd18a96af3.594.12 +3 -0
- runs/Aug27_06-54-00_61dd18a96af3/events.out.tfevents.1724741760.61dd18a96af3.594.13 +3 -0
- runs/Aug27_06-54-00_61dd18a96af3/events.out.tfevents.1724741768.61dd18a96af3.594.14 +3 -0
- runs/Aug27_06-54-00_61dd18a96af3/events.out.tfevents.1724741778.61dd18a96af3.594.15 +3 -0
- runs/Aug27_06-54-00_61dd18a96af3/events.out.tfevents.1724741788.61dd18a96af3.594.16 +3 -0
- runs/Aug27_06-54-00_61dd18a96af3/events.out.tfevents.1724741797.61dd18a96af3.594.17 +3 -0
- runs/Aug27_06-54-00_61dd18a96af3/events.out.tfevents.1724741806.61dd18a96af3.594.18 +3 -0
- runs/Aug27_06-54-00_61dd18a96af3/events.out.tfevents.1724741815.61dd18a96af3.594.19 +3 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: distilgpt2
|
| 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 [distilgpt2](https://huggingface.co/distilgpt2) on the None dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 4.0206
|
| 19 |
+
|
| 20 |
+
## Model description
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Intended uses & limitations
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training and evaluation data
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training procedure
|
| 33 |
+
|
| 34 |
+
### Training hyperparameters
|
| 35 |
+
|
| 36 |
+
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 2e-05
|
| 38 |
+
- train_batch_size: 4
|
| 39 |
+
- eval_batch_size: 8
|
| 40 |
+
- seed: 42
|
| 41 |
+
- gradient_accumulation_steps: 16
|
| 42 |
+
- total_train_batch_size: 64
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: linear
|
| 45 |
+
- num_epochs: 3
|
| 46 |
+
- mixed_precision_training: Native AMP
|
| 47 |
+
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 51 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 52 |
+
| No log | 0.5161 | 1 | 4.0053 |
|
| 53 |
+
| No log | 1.5484 | 3 | 4.0206 |
|
| 54 |
+
|
| 55 |
+
|
| 56 |
+
### Framework versions
|
| 57 |
+
|
| 58 |
+
- Transformers 4.42.4
|
| 59 |
+
- Pytorch 2.4.0+cu121
|
| 60 |
+
- Datasets 2.21.0
|
| 61 |
+
- Tokenizers 0.19.1
|
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": "4.42.4",
|
| 44 |
+
"use_cache": true,
|
| 45 |
+
"vocab_size": 50257
|
| 46 |
+
}
|
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": "4.42.4"
|
| 6 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:786500f9f54b71cb6acc57b580eb8791dd1e0196e1e6f713c9129448850c87a4
|
| 3 |
+
size 327657928
|
runs/Aug27_06-54-00_61dd18a96af3/events.out.tfevents.1724741641.61dd18a96af3.594.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:90b7836f7a9063fda15678603611cc83158e6bd0a2aeff5c8b2f5987623bf66e
|
| 3 |
+
size 6030
|
runs/Aug27_06-54-00_61dd18a96af3/events.out.tfevents.1724741652.61dd18a96af3.594.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ab73b6474e4e19153a403355160cacf1fb323b4a3c3addd643cd7cd1ba8c5b5d
|
| 3 |
+
size 6058
|
runs/Aug27_06-54-00_61dd18a96af3/events.out.tfevents.1724741660.61dd18a96af3.594.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c2dda57fc5ef1a5ae8427f86af78a3188eb95d32d74303b6074c786d776ab004
|
| 3 |
+
size 6058
|
runs/Aug27_06-54-00_61dd18a96af3/events.out.tfevents.1724741669.61dd18a96af3.594.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:313026b27e9447b9251b2fe935dee15623966353bec6eff999954586b66c5576
|
| 3 |
+
size 6058
|
runs/Aug27_06-54-00_61dd18a96af3/events.out.tfevents.1724741678.61dd18a96af3.594.4
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:772ba988b715c881035bac55a2fda7b0578b7c8271192933875f2ec62917bb25
|
| 3 |
+
size 6058
|
runs/Aug27_06-54-00_61dd18a96af3/events.out.tfevents.1724741687.61dd18a96af3.594.5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3d14ecf68b4bce0db6a37b48bce27724eb8bfb4fb4e0e7320a9dadcde7b83735
|
| 3 |
+
size 6058
|
runs/Aug27_06-54-00_61dd18a96af3/events.out.tfevents.1724741697.61dd18a96af3.594.6
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6f8af0b1f7ffdf84189cfd6c76a06c58e4987b5087e2b82e33b6b48551dcde09
|
| 3 |
+
size 6058
|
runs/Aug27_06-54-00_61dd18a96af3/events.out.tfevents.1724741706.61dd18a96af3.594.7
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:89d98382d93f8a17957cf83de8ca922bee8483a8d7da53efcfeb1f77647b5436
|
| 3 |
+
size 6058
|
runs/Aug27_06-54-00_61dd18a96af3/events.out.tfevents.1724741715.61dd18a96af3.594.8
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ba0ff48dd0f7bcb99b4edfba7c3e81e4a067fdbf20e1331abea311cb7e98969c
|
| 3 |
+
size 6058
|
runs/Aug27_06-54-00_61dd18a96af3/events.out.tfevents.1724741723.61dd18a96af3.594.9
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3683d51a069fef2c36ab0576a33370cd2b1f01ad9b8d953dac21407fec655b4d
|
| 3 |
+
size 6058
|
runs/Aug27_06-54-00_61dd18a96af3/events.out.tfevents.1724741733.61dd18a96af3.594.10
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ae01e996072b37b10f31c0102f5a202bf12edbf0657bd38a52f5fa3a46ea0580
|
| 3 |
+
size 6058
|
runs/Aug27_06-54-00_61dd18a96af3/events.out.tfevents.1724741742.61dd18a96af3.594.11
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3b2e5e55f8b2cfd8bde2e8ca1bf31b58fa464e9504dcdaa013837cc56c1cecca
|
| 3 |
+
size 6058
|
runs/Aug27_06-54-00_61dd18a96af3/events.out.tfevents.1724741751.61dd18a96af3.594.12
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ee1246b243f6e3c2a95e823a5dabbdcf96079a13d2a4f2504b628297dee03256
|
| 3 |
+
size 6058
|
runs/Aug27_06-54-00_61dd18a96af3/events.out.tfevents.1724741760.61dd18a96af3.594.13
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:599436d4e2df7a69543dbec984b51ca8be8c764cacf22c3a783654225f36ff59
|
| 3 |
+
size 6058
|
runs/Aug27_06-54-00_61dd18a96af3/events.out.tfevents.1724741768.61dd18a96af3.594.14
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6092c5ba6b1b89852720c668eac3685312aa7307d22c8d083855fc001c79ca8d
|
| 3 |
+
size 6058
|
runs/Aug27_06-54-00_61dd18a96af3/events.out.tfevents.1724741778.61dd18a96af3.594.15
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca69d7d3ec86ac89ff41f8221fedc42bd4b0350f578895eee843962627555c07
|
| 3 |
+
size 6058
|
runs/Aug27_06-54-00_61dd18a96af3/events.out.tfevents.1724741788.61dd18a96af3.594.16
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:47228627cc6fc76397ddb427555e737baea03bbea154bca9ef8f43f180a0cf7b
|
| 3 |
+
size 6058
|
runs/Aug27_06-54-00_61dd18a96af3/events.out.tfevents.1724741797.61dd18a96af3.594.17
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:706da5a330182aad1386e6dc9dbe71da77c27015466b03db144e12cd62baae97
|
| 3 |
+
size 6058
|
runs/Aug27_06-54-00_61dd18a96af3/events.out.tfevents.1724741806.61dd18a96af3.594.18
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8d789b5762789d93a1b22d34ced6be9349fdedf0b64d102092ff0f3e4ca33653
|
| 3 |
+
size 6058
|
runs/Aug27_06-54-00_61dd18a96af3/events.out.tfevents.1724741815.61dd18a96af3.594.19
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f96b4041f7d88a45a28cc22d6c6f976139f733fc03f11cb1b5238637b3047ea3
|
| 3 |
+
size 6058
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e6abc384e32b52ae870813a5e4aceac90d5c7dd1156c2ed1696661a2f57ceab
|
| 3 |
+
size 5112
|