robingeibel commited on
Commit
4c06d36
1 Parent(s): 32cbb2a

Training in progress, step 500

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "robingeibel/reformer-finetuned-big_patent",
3
+ "architectures": [
4
+ "ReformerForMaskedLM"
5
+ ],
6
+ "attention_head_size": 64,
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "attn_layers": [
9
+ "local",
10
+ "lsh",
11
+ "local",
12
+ "lsh",
13
+ "local",
14
+ "lsh"
15
+ ],
16
+ "axial_norm_std": 1.0,
17
+ "axial_pos_embds": false,
18
+ "axial_pos_embds_dim": [
19
+ 64,
20
+ 64
21
+ ],
22
+ "axial_pos_shape": [
23
+ 512,
24
+ 1024
25
+ ],
26
+ "chunk_size_lm_head": 0,
27
+ "classifier_dropout": null,
28
+ "eos_token_id": 2,
29
+ "feed_forward_size": 512,
30
+ "hash_seed": null,
31
+ "hidden_act": "relu",
32
+ "hidden_dropout_prob": 0.05,
33
+ "hidden_size": 256,
34
+ "initializer_range": 0.02,
35
+ "intermediate_size": 3072,
36
+ "layer_norm_eps": 1e-12,
37
+ "local_attention_probs_dropout_prob": 0.05,
38
+ "local_attn_chunk_length": 64,
39
+ "local_num_chunks_after": 0,
40
+ "local_num_chunks_before": 1,
41
+ "lsh_attention_probs_dropout_prob": 0.0,
42
+ "lsh_attn_chunk_length": 64,
43
+ "lsh_num_chunks_after": 0,
44
+ "lsh_num_chunks_before": 1,
45
+ "max_position_embeddings": 4096,
46
+ "model_type": "reformer",
47
+ "num_attention_heads": 2,
48
+ "num_buckets": [
49
+ 64,
50
+ 128
51
+ ],
52
+ "num_chunks_after": 0,
53
+ "num_chunks_before": 1,
54
+ "num_hashes": 1,
55
+ "num_hidden_layers": 6,
56
+ "output_past": true,
57
+ "pad_token_id": 0,
58
+ "task_specific_params": {
59
+ "text-generation": {
60
+ "do_sample": true,
61
+ "max_length": 100
62
+ }
63
+ },
64
+ "tie_word_embeddings": false,
65
+ "torch_dtype": "float32",
66
+ "transformers_version": "4.20.1",
67
+ "use_cache": true,
68
+ "vocab_size": 320
69
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad61ac992a1809d4c2248ce5c51e4a0051c2a884688ba83db44d3baae9a5cfb1
3
+ size 14301070
runs/Jun28_21-55-21_e2760ac8abe5/1656453344.8920076/events.out.tfevents.1656453344.e2760ac8abe5.96.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2193ee2f8077bdd8f7d3c465546f5f63c2bd636870359ba6841c38f5adab238
3
+ size 5327
runs/Jun28_21-55-21_e2760ac8abe5/events.out.tfevents.1656453344.e2760ac8abe5.96.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71278563d1d3018902f71c6d489d70d7159faff251db4e57bc03f9aea8c0717f
3
+ size 4485
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2cc43717f52d63ee9663f5ccac43d8c6066654109ed67972182a8918731c953
3
+ size 3311