wzChen commited on
Commit
c36abbd
·
verified ·
1 Parent(s): bb769bb

Training in progress, step 500

Browse files
config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "uer/gpt2-chinese-cluecorpussmall",
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
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "gpt2",
15
+ "n_ctx": 1024,
16
+ "n_embd": 768,
17
+ "n_head": 12,
18
+ "n_inner": null,
19
+ "n_layer": 12,
20
+ "n_positions": 1024,
21
+ "output_past": true,
22
+ "reorder_and_upcast_attn": false,
23
+ "resid_pdrop": 0.1,
24
+ "scale_attn_by_inverse_layer_idx": false,
25
+ "scale_attn_weights": true,
26
+ "summary_activation": null,
27
+ "summary_first_dropout": 0.1,
28
+ "summary_proj_to_labels": true,
29
+ "summary_type": "cls_index",
30
+ "summary_use_proj": true,
31
+ "task_specific_params": {
32
+ "text-generation": {
33
+ "do_sample": true,
34
+ "max_length": 320
35
+ }
36
+ },
37
+ "tokenizer_class": "BertTokenizer",
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.38.2",
40
+ "use_cache": true,
41
+ "vocab_size": 21128
42
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c0a2e8ac56d955d56deefc58e1adda9caf5b2780d26f785ff230244542ab2f0
3
+ size 408289920
runs/Mar25_14-44-22_5412af28fa8e/events.out.tfevents.1711377863.5412af28fa8e.35.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a544650dc678c8565c4fd783e96a201324a0e8fcf8f4a7cef978ceba76dfa20
3
+ size 5445
runs/Mar25_14-53-58_5412af28fa8e/events.out.tfevents.1711378439.5412af28fa8e.35.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c27ce00c4255d2a67b5e3d572538e9023a4dd3a2ca2a7861ef97223ec033c761
3
+ size 5473
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a54bc31c323e4f00df8d3a0d5354af62c59177b062febe735ea0ac0c801c3c35
3
+ size 4920