chenxingphh commited on
Commit
497a4fd
1 Parent(s): a046ac8

Training in progress, step 30

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
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": 0,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 0,
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": "4.30.2",
37
+ "use_cache": true,
38
+ "vocab_size": 50000
39
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0866062b4669fa80445c0ca8ba2f4e9041fafe956c961e0322131f55e0376675
3
+ size 497017693
runs/Jul18_13-16-35_01ab20048fe7/events.out.tfevents.1689686198.01ab20048fe7.5965.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:febe845cd3cf22427f2a05cde86981c9f94ab48f93f79961793b0068347e60e9
3
+ size 4916
runs/Jul18_13-21-07_01ab20048fe7/events.out.tfevents.1689686470.01ab20048fe7.5965.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9ed964b088ae9050b41638dfe6d31ae2b9ae9a87099c19d13e64e81dff9cee0
3
+ size 4274
runs/Jul18_13-21-43_01ab20048fe7/events.out.tfevents.1689686507.01ab20048fe7.5965.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce585037e45ed43f0082c4e0746770ff9d6347f72259dd31c6da7f435b9dd35e
3
+ size 4317
runs/Jul18_13-22-00_01ab20048fe7/events.out.tfevents.1689686523.01ab20048fe7.5965.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48d47147da06fa928c2d03196b6825140c795cfa9f83ae7752bdb5a563c65b63
3
+ size 4316
runs/Jul18_13-23-33_01ab20048fe7/events.out.tfevents.1689686616.01ab20048fe7.5965.11 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7eccf7689778103388a8a58d67fd4e3e906d2d4c530c81377f3a40ba8a6f2d06
3
+ size 4184
runs/Jul18_13-23-54_01ab20048fe7/events.out.tfevents.1689686637.01ab20048fe7.5965.12 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:031f0602c1364f2ed5682f482c9ff733a20dc39d7d73cbb5b1a8c1377d4ea089
3
+ size 4184
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 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<|endoftext|>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "eos_token": "<|endoftext|>",
6
+ "model_max_length": 1024,
7
+ "tokenizer_class": "GPT2Tokenizer",
8
+ "unk_token": "<|endoftext|>"
9
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa464cdc1591f46a8baf446be81574a6d20f46987be6f4d5deffbf7c74d1095e
3
+ size 3899
vocab.json ADDED
The diff for this file is too large to render. See raw diff