michalzajac commited on
Commit
319e134
1 Parent(s): bd46225

End of training

Browse files
Files changed (4) hide show
  1. README.md +51 -0
  2. config.json +42 -0
  3. model.safetensors +3 -0
  4. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: EleutherAI/pythia-14m
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: robust_llm_pythia-tweet-sentiment-14m-mz-test-3classes
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
+ # robust_llm_pythia-tweet-sentiment-14m-mz-test-3classes
14
+
15
+ This model is a fine-tuned version of [EleutherAI/pythia-14m](https://huggingface.co/EleutherAI/pythia-14m) 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: 1e-05
35
+ - train_batch_size: 8
36
+ - eval_batch_size: 64
37
+ - seed: 42
38
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
39
+ - lr_scheduler_type: linear
40
+ - num_epochs: 1
41
+
42
+ ### Training results
43
+
44
+
45
+
46
+ ### Framework versions
47
+
48
+ - Transformers 4.37.2
49
+ - Pytorch 2.2.0
50
+ - Datasets 2.17.0
51
+ - Tokenizers 0.15.2
config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "EleutherAI/pythia-14m",
3
+ "architectures": [
4
+ "GPTNeoXForSequenceClassification"
5
+ ],
6
+ "attention_bias": true,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 0,
9
+ "classifier_dropout": 0.1,
10
+ "eos_token_id": 0,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout": 0.0,
13
+ "hidden_size": 128,
14
+ "id2label": {
15
+ "0": "LABEL_0",
16
+ "1": "LABEL_1",
17
+ "2": "LABEL_2"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 512,
21
+ "label2id": {
22
+ "LABEL_0": 0,
23
+ "LABEL_1": 1,
24
+ "LABEL_2": 2
25
+ },
26
+ "layer_norm_eps": 1e-05,
27
+ "max_position_embeddings": 2048,
28
+ "model_type": "gpt_neox",
29
+ "num_attention_heads": 4,
30
+ "num_hidden_layers": 6,
31
+ "pad_token_id": 0,
32
+ "problem_type": "single_label_classification",
33
+ "rope_scaling": null,
34
+ "rotary_emb_base": 10000,
35
+ "rotary_pct": 0.25,
36
+ "tie_word_embeddings": false,
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.37.2",
39
+ "use_cache": false,
40
+ "use_parallel_residual": true,
41
+ "vocab_size": 50304
42
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24c19312fa3fef17e42311076af8c7be831a48c03193c31b7ba7ef2fee787f1e
3
+ size 30525224
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c001b2cfedc928170b3f082e8d554ac1a925dff9a5b44a3fa76cd480ded0d05c
3
+ size 4728