Norod78 commited on
Commit
d4c8f27
1 Parent(s): c8f9978

Testing JAX training with TPU VM, After 1 Epoch

Browse files
Files changed (3) hide show
  1. config.json +43 -0
  2. flax_model.msgpack +3 -0
  3. tokenizer.json +0 -0
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_num_labels": 1,
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
+ "gradient_checkpointing": false,
12
+ "id2label": {
13
+ "0": "LABEL_0"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "label2id": {
17
+ "LABEL_0": 0
18
+ },
19
+ "layer_norm_epsilon": 1e-05,
20
+ "model_type": "gpt2",
21
+ "n_ctx": 1024,
22
+ "n_embd": 768,
23
+ "n_head": 12,
24
+ "n_inner": null,
25
+ "n_layer": 6,
26
+ "n_positions": 1024,
27
+ "resid_pdrop": 0.1,
28
+ "scale_attn_weights": true,
29
+ "summary_activation": null,
30
+ "summary_first_dropout": 0.1,
31
+ "summary_proj_to_labels": true,
32
+ "summary_type": "cls_index",
33
+ "summary_use_proj": true,
34
+ "task_specific_params": {
35
+ "text-generation": {
36
+ "do_sample": true,
37
+ "max_length": 50
38
+ }
39
+ },
40
+ "transformers_version": "4.9.0.dev0",
41
+ "use_cache": true,
42
+ "vocab_size": 50257
43
+ }
flax_model.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0246ab09910a61fafb618e5b1e64abf1e8c8a88e6c984b3505a8aea1e936555
3
+ size 248885212
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff