Sigurdur commited on
Commit
cdbea7d
1 Parent(s): 1c49f7c

End of training

Browse files
README.md ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-nqii-ruqad
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/i9i7wb82)
17
+ # gpt-sw3-126m-nqii-ruqad
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: 1
41
+ - seed: 42
42
+ - gradient_accumulation_steps: 4
43
+ - total_train_batch_size: 4
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - num_epochs: 1
47
+
48
+ ### Training results
49
+
50
+
51
+
52
+ ### Framework versions
53
+
54
+ - Transformers 4.42.3
55
+ - Pytorch 2.1.2+cu118
56
+ - Datasets 2.20.0
57
+ - 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 sha256:6af8dd1ffdedc558d39272f09864035ec858cc8432ccab63c350622ef4da31b4
3
+ size 543138432
runs/Jul07_13-26-57_Haukurs-pc/events.out.tfevents.1720358821.Haukurs-pc.24247.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6110eea03cf6399958c88b64358eff6e85b2209db8292b3783da4254a01c537d
3
+ size 5474
runs/Jul07_13-29-25_Haukurs-pc/events.out.tfevents.1720358968.Haukurs-pc.27208.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f929cc410623c8bbc009a31368df6e1901f8d7361a92cd7ec20b3c1d595a3174
3
+ size 4184
runs/Jul07_13-31-37_Haukurs-pc/events.out.tfevents.1720359101.Haukurs-pc.27809.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19f908a80724210d87036ca101db4790c43b4efe83e9cf9ea65cdc2276a9376c
3
+ size 4184
runs/Jul07_13-33-30_Haukurs-pc/events.out.tfevents.1720359214.Haukurs-pc.28350.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83d141f212d12b807ce6ebf784f333ae4b079776b88676e09bbf751628996e52
3
+ size 5474
runs/Jul07_13-34-33_Haukurs-pc/events.out.tfevents.1720359277.Haukurs-pc.28753.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b9b6090b1b7e723ac121cc1f3108aee657023259fa75338180e2e3029afbe0b
3
+ size 5474
runs/Jul07_13-38-03_Haukurs-pc/events.out.tfevents.1720359487.Haukurs-pc.29513.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56a56679db032e3c766ea0d6f3465c1d6f06f5a4e8f177f87a9bb68eee163181
3
+ size 4184
runs/Jul07_13-38-32_Haukurs-pc/events.out.tfevents.1720359515.Haukurs-pc.29865.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14d9794c09519746917316c0db9efd10dd518db8ed4aacd4d5c2e7b0721a949d
3
+ size 5896
runs/Jul07_15-25-04_Haukurs-pc/events.out.tfevents.1720365910.Haukurs-pc.1148.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e5f5d633164480eb7d099bb9fc136af2dfbb2e642499391e8b512662aa7cbe5
3
+ size 6671
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 sha256:67efbdc4d52facf4c7be37594de207e118c5ba065a49b087b0fe7df8228ee88e
3
+ size 5368