Sigurdur commited on
Commit
4a8e653
1 Parent(s): a6fab85

End of training

Browse files
README.md ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ base_model: AI-Sweden-Models/gpt-sw3-126m
4
+ tags:
5
+ - trl
6
+ - sft
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: gpt-sw3-126m-njala
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/sigurdurhaukur-team/huggingface/runs/4ut98dmr)
17
+ # gpt-sw3-126m-njala
18
+
19
+ This model is a fine-tuned version of [AI-Sweden-Models/gpt-sw3-126m](https://huggingface.co/AI-Sweden-Models/gpt-sw3-126m) on an unknown dataset.
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 5e-05
39
+ - train_batch_size: 1
40
+ - eval_batch_size: 8
41
+ - seed: 42
42
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
+ - lr_scheduler_type: linear
44
+ - num_epochs: 3
45
+
46
+ ### Training results
47
+
48
+
49
+
50
+ ### Framework versions
51
+
52
+ - Transformers 4.42.3
53
+ - Pytorch 2.1.2+cu118
54
+ - Datasets 2.20.0
55
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "AI-Sweden-Models/gpt-sw3-126m",
3
+ "activation_function": "gelu",
4
+ "apply_query_key_layer_scaling": true,
5
+ "architectures": [
6
+ "GPT2LMHeadModel"
7
+ ],
8
+ "attn_pdrop": 0.1,
9
+ "bos_token_id": 2,
10
+ "embd_pdrop": 0.1,
11
+ "eos_token_id": 3,
12
+ "initializer_range": 0.023,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "gpt2",
15
+ "n_ctx": 2048,
16
+ "n_embd": 768,
17
+ "n_head": 12,
18
+ "n_inner": 3072,
19
+ "n_layer": 12,
20
+ "n_positions": 2048,
21
+ "normalize_attention_scores": true,
22
+ "pad_token_id": 0,
23
+ "reorder_and_upcast_attn": false,
24
+ "resid_pdrop": 0.1,
25
+ "scale_attn_by_inverse_layer_idx": false,
26
+ "scale_attn_weights": true,
27
+ "summary_activation": null,
28
+ "summary_first_dropout": 0.1,
29
+ "summary_proj_to_labels": true,
30
+ "summary_type": "cls_index",
31
+ "summary_use_proj": true,
32
+ "tokenizer_class": "GPTSw3Tokenizer",
33
+ "torch_dtype": "float32",
34
+ "transformers_version": "4.42.3",
35
+ "use_cache": false,
36
+ "vocab_size": 64000
37
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "eos_token_id": 3,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.42.3",
7
+ "use_cache": false
8
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61951dc8a30290aa3cd671403b18afcc8961740f3fb2d041b937dfea7a7f1c63
3
+ size 543138432
runs/Jul07_11-46-31_Haukurs-pc/events.out.tfevents.1720352793.Haukurs-pc.2533.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72d98cf50c96ecf567d74860d09f3121835d17529297f16cfe84efa95f4e31d5
3
+ size 5156
runs/Jul07_12-05-16_Haukurs-pc/events.out.tfevents.1720353919.Haukurs-pc.9001.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd04f4725e1f52db4462598001a68440f192cdaa8868fd34c8faa89320f38fa0
3
+ size 4184
runs/Jul07_12-06-16_Haukurs-pc/events.out.tfevents.1720353979.Haukurs-pc.9531.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ffaf4ec2d6af610ba0d98dca316b78fd21be19db30e74770aa975fb8a296762
3
+ size 6211
runs/Jul07_12-49-58_Haukurs-pc/events.out.tfevents.1720356602.Haukurs-pc.18531.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:789d32233f02702c009ab51ad8025c8405ef928382d10bac3d7ad2a09a3fac0a
3
+ size 5435
runs/Jul07_13-00-47_Haukurs-pc/events.out.tfevents.1720357250.Haukurs-pc.20901.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a07d1f3ed0ca5bd7eb480f9c17754c4fffa9b4a6065194cfa222caee8c5aca9a
3
+ size 4184
runs/Jul07_13-02-03_Haukurs-pc/events.out.tfevents.1720357326.Haukurs-pc.21344.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c1c0cb6a56284303eff429727d62abeaacd4aa0e6a4c14d0cb5fddccd813cc7
3
+ size 6000
runs/Jul07_15-40-47_Haukurs-pc/events.out.tfevents.1720366849.Haukurs-pc.4291.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:273cbcbf85813375a7008410e715695f6eaa883d7a2a15bc494bde13dd372893
3
+ size 17624
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<pad>",
5
+ "unk_token": "<unk>"
6
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4bda2cd84ff0ac659cda40e746c55f47ee3e57cf18471670ad26998c28be52d
3
+ size 1071955
tokenizer_config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<pad>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<unk>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<|endoftext|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ }
35
+ },
36
+ "bos_token": "<s>",
37
+ "clean_up_tokenization_spaces": true,
38
+ "do_lower_case": false,
39
+ "eos_token": "<|endoftext|>",
40
+ "keep_accents": false,
41
+ "model_max_length": 1000000000000000019884624838656,
42
+ "pad_token": "<pad>",
43
+ "remove_space": false,
44
+ "sp_model_kwargs": {},
45
+ "tokenizer_class": "GPTSw3Tokenizer",
46
+ "unk_token": "<unk>"
47
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49a11b9359ddaeb239fed01288f01a706d5b09c339719f261cd82acd01c0500c
3
+ size 5368