pepa commited on
Commit
40e4fc2
·
verified ·
1 Parent(s): f40d50b

Training in progress, epoch 0

Browse files
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2",
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": 128,
15
+ "n_embd": 768,
16
+ "n_head": 12,
17
+ "n_inner": null,
18
+ "n_layer": 12,
19
+ "n_positions": 1024,
20
+ "reorder_and_upcast_attn": false,
21
+ "resid_pdrop": 0.1,
22
+ "scale_attn_by_inverse_layer_idx": false,
23
+ "scale_attn_weights": true,
24
+ "summary_activation": null,
25
+ "summary_first_dropout": 0.1,
26
+ "summary_proj_to_labels": true,
27
+ "summary_type": "cls_index",
28
+ "summary_use_proj": true,
29
+ "task_specific_params": {
30
+ "text-generation": {
31
+ "do_sample": true,
32
+ "max_length": 50
33
+ }
34
+ },
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.45.2",
37
+ "use_cache": true,
38
+ "vocab_size": 50257
39
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92c88c4e2445a512bf5d7d49d2a483fe3a842540d68c32eab457659403c3efe1
3
+ size 497774208
runs/Dec27_13-25-27_hendrixgpu07fl.unicph.domain/events.out.tfevents.1735302332.hendrixgpu07fl.unicph.domain.241230.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6aa43be9b9bf8b8aa4679f3fb3c2a0c9ba8cfb1a2e6d8f55b8ced697871b8226
3
+ size 5545
runs/Dec27_13-28-46_hendrixgpu07fl.unicph.domain/events.out.tfevents.1735302529.hendrixgpu07fl.unicph.domain.241581.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b1dd6b08b371eaad5fa2d42ef4bddb889cacd54723fbdae8e6c418b47372d0d
3
+ size 5547
runs/Dec27_13-31-07_hendrixgpu07fl.unicph.domain/events.out.tfevents.1735302669.hendrixgpu07fl.unicph.domain.241717.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:957df3a690fe83102b556a7cc2850bf41d62b8f8f3081ad4670da00333381f20
3
+ size 5550
runs/Dec27_13-36-50_hendrixgpu07fl.unicph.domain/events.out.tfevents.1735303015.hendrixgpu07fl.unicph.domain.242000.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ca6c9e0028e3dba950c6dfd1aecd1ebe7cd1f738efdf85ef18cf9348a20589c
3
+ size 5548
runs/Dec27_13-38-24_hendrixgpu07fl.unicph.domain/events.out.tfevents.1735303109.hendrixgpu07fl.unicph.domain.242164.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3743d1950aba636c0855744fb7bba7bd314152e4765a3918f76bb606ee758811
3
+ size 5548
runs/Dec27_13-44-26_hendrixgpu07fl.unicph.domain/events.out.tfevents.1735303471.hendrixgpu07fl.unicph.domain.242508.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acada97284aaf9c43806aa94b15c51089b8ee22882a7921f481c3ec9888e977e
3
+ size 5548
runs/Dec27_13-46-55_hendrixgpu07fl.unicph.domain/events.out.tfevents.1735303620.hendrixgpu07fl.unicph.domain.242657.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e8132efbaff6381963bb70ca18c3cb7b3085fa0c20757c695c08b925893e99c
3
+ size 88
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ }
12
+ },
13
+ "bos_token": "<|endoftext|>",
14
+ "clean_up_tokenization_spaces": false,
15
+ "eos_token": "<|endoftext|>",
16
+ "model_max_length": 1024,
17
+ "pad_token": "<|endoftext|>",
18
+ "padding_side": "left",
19
+ "tokenizer_class": "GPT2Tokenizer",
20
+ "unk_token": "<|endoftext|>"
21
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3cc5b9f353400ca7463f41f9e7d1dcb96b5fca84796e9aa4d71564f8bb2ee88
3
+ size 5496
vocab.json ADDED
The diff for this file is too large to render. See raw diff