Training in progress, step 500
Browse files- .gitignore +1 -0
- config.json +41 -0
- pytorch_model.bin +3 -0
- runs/May17_22-02-24_5dbdc00b04c7/1652824966.1094341/events.out.tfevents.1652824966.5dbdc00b04c7.500.1 +3 -0
- runs/May17_22-02-24_5dbdc00b04c7/events.out.tfevents.1652824966.5dbdc00b04c7.500.0 +3 -0
- runs/May17_22-03-20_5dbdc00b04c7/1652825005.4284627/events.out.tfevents.1652825005.5dbdc00b04c7.500.3 +3 -0
- runs/May17_22-03-20_5dbdc00b04c7/events.out.tfevents.1652825005.5dbdc00b04c7.500.2 +3 -0
- runs/May17_22-03-34_5dbdc00b04c7/1652825019.4308774/events.out.tfevents.1652825019.5dbdc00b04c7.500.5 +3 -0
- runs/May17_22-03-34_5dbdc00b04c7/events.out.tfevents.1652825019.5dbdc00b04c7.500.4 +3 -0
- runs/May17_22-04-12_5dbdc00b04c7/1652825057.8500183/events.out.tfevents.1652825057.5dbdc00b04c7.500.7 +3 -0
- runs/May17_22-04-12_5dbdc00b04c7/events.out.tfevents.1652825057.5dbdc00b04c7.500.6 +3 -0
- runs/May17_22-04-37_5dbdc00b04c7/1652825082.9520345/events.out.tfevents.1652825082.5dbdc00b04c7.500.9 +3 -0
- runs/May17_22-04-37_5dbdc00b04c7/events.out.tfevents.1652825082.5dbdc00b04c7.500.8 +3 -0
- runs/May17_22-04-55_5dbdc00b04c7/1652825099.9900763/events.out.tfevents.1652825099.5dbdc00b04c7.500.11 +3 -0
- runs/May17_22-04-55_5dbdc00b04c7/events.out.tfevents.1652825099.5dbdc00b04c7.500.10 +3 -0
- runs/May17_22-05-08_5dbdc00b04c7/1652825113.7697108/events.out.tfevents.1652825113.5dbdc00b04c7.500.13 +3 -0
- runs/May17_22-05-08_5dbdc00b04c7/events.out.tfevents.1652825113.5dbdc00b04c7.500.12 +3 -0
- runs/May17_22-06-04_5dbdc00b04c7/1652825174.1956782/events.out.tfevents.1652825174.5dbdc00b04c7.989.1 +3 -0
- runs/May17_22-06-04_5dbdc00b04c7/events.out.tfevents.1652825174.5dbdc00b04c7.989.0 +3 -0
- runs/May17_22-09-02_5dbdc00b04c7/1652825353.0115438/events.out.tfevents.1652825353.5dbdc00b04c7.1149.1 +3 -0
- runs/May17_22-09-02_5dbdc00b04c7/events.out.tfevents.1652825353.5dbdc00b04c7.1149.0 +3 -0
- runs/May17_22-10-24_5dbdc00b04c7/1652825434.4454792/events.out.tfevents.1652825434.5dbdc00b04c7.1325.1 +3 -0
- runs/May17_22-10-24_5dbdc00b04c7/events.out.tfevents.1652825434.5dbdc00b04c7.1325.0 +3 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "gpt2-medium",
|
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": 1024,
|
15 |
+
"n_embd": 1024,
|
16 |
+
"n_head": 16,
|
17 |
+
"n_inner": null,
|
18 |
+
"n_layer": 24,
|
19 |
+
"n_positions": 1024,
|
20 |
+
"n_special": 0,
|
21 |
+
"predict_special_tokens": 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": 50
|
35 |
+
}
|
36 |
+
},
|
37 |
+
"torch_dtype": "float32",
|
38 |
+
"transformers_version": "4.19.2",
|
39 |
+
"use_cache": true,
|
40 |
+
"vocab_size": 50257
|
41 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:adb4c6f89e14c47d6bc297639d37e96f297dd4513e14537b4c0722fc8186d6ff
|
3 |
+
size 1444566873
|
runs/May17_22-02-24_5dbdc00b04c7/1652824966.1094341/events.out.tfevents.1652824966.5dbdc00b04c7.500.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:644407de520bbb7b68f87b43020a63daf662ab0a56cd15d798ee811b63a6dbc8
|
3 |
+
size 5196
|
runs/May17_22-02-24_5dbdc00b04c7/events.out.tfevents.1652824966.5dbdc00b04c7.500.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:81d51f3b75832a821f0f4d51e30571df7f19c1b4910b09bef31d13a91d8190ea
|
3 |
+
size 3844
|
runs/May17_22-03-20_5dbdc00b04c7/1652825005.4284627/events.out.tfevents.1652825005.5dbdc00b04c7.500.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6eb4b3fa43981c0315baab56cae376ac29dba6f57bf68c9ae0fa01db2180211c
|
3 |
+
size 5196
|
runs/May17_22-03-20_5dbdc00b04c7/events.out.tfevents.1652825005.5dbdc00b04c7.500.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:34025b2dd011da1a58673e9eae7da1e06578f079be9062d520081415dc2718a3
|
3 |
+
size 3844
|
runs/May17_22-03-34_5dbdc00b04c7/1652825019.4308774/events.out.tfevents.1652825019.5dbdc00b04c7.500.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:96a116f529f6e263d0976cac44236fb9650bec1218c44a992fe151d98da11c07
|
3 |
+
size 5196
|
runs/May17_22-03-34_5dbdc00b04c7/events.out.tfevents.1652825019.5dbdc00b04c7.500.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c195718e2d7169e3a0847000065344570389a5c2e5406d7d023e2f4229c2477
|
3 |
+
size 3844
|
runs/May17_22-04-12_5dbdc00b04c7/1652825057.8500183/events.out.tfevents.1652825057.5dbdc00b04c7.500.7
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:58f706c5122079f048b8590e8fed54d37b8b992aba27c22f07011f88a7ec534e
|
3 |
+
size 5196
|
runs/May17_22-04-12_5dbdc00b04c7/events.out.tfevents.1652825057.5dbdc00b04c7.500.6
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5d7e376226807c336d5deeed8dd7a938144e37db2d94a63433d95679f677e488
|
3 |
+
size 3844
|
runs/May17_22-04-37_5dbdc00b04c7/1652825082.9520345/events.out.tfevents.1652825082.5dbdc00b04c7.500.9
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:18825586a6aac79f904504ca124ae0cd72b4dea3705fd55f5fbd4ab73ee63a41
|
3 |
+
size 5196
|
runs/May17_22-04-37_5dbdc00b04c7/events.out.tfevents.1652825082.5dbdc00b04c7.500.8
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c81b4ca3bf8921352f124b42e316847202acab3eaf0101653322d3f8b64f5742
|
3 |
+
size 3844
|
runs/May17_22-04-55_5dbdc00b04c7/1652825099.9900763/events.out.tfevents.1652825099.5dbdc00b04c7.500.11
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d757c60b6aa59c21fcc4c97d26d0f888ce75d98bcffcf26bed80461bf5318681
|
3 |
+
size 5196
|
runs/May17_22-04-55_5dbdc00b04c7/events.out.tfevents.1652825099.5dbdc00b04c7.500.10
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:907ed0cc065ca2effd322790d120371362e2caf752af633e83173a722f544171
|
3 |
+
size 3844
|
runs/May17_22-05-08_5dbdc00b04c7/1652825113.7697108/events.out.tfevents.1652825113.5dbdc00b04c7.500.13
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e6ac3a76ab7d2dffd2b9f438b8ccce8921eebcf6819b62814d13129e9dcc08de
|
3 |
+
size 5196
|
runs/May17_22-05-08_5dbdc00b04c7/events.out.tfevents.1652825113.5dbdc00b04c7.500.12
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b04d548822ee922fbed641cac8a806c06694dceb09245efa2b3cc512acbd9efa
|
3 |
+
size 3844
|
runs/May17_22-06-04_5dbdc00b04c7/1652825174.1956782/events.out.tfevents.1652825174.5dbdc00b04c7.989.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:19aea813f9e3da01d3cc68903f94d8599499c319f6052e54cb815ce1b1c51c32
|
3 |
+
size 5196
|
runs/May17_22-06-04_5dbdc00b04c7/events.out.tfevents.1652825174.5dbdc00b04c7.989.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb0b7bbbe2fa5d83b3799056a99ab8df99f4490e030927c0ca94bf4bb0a7f0f9
|
3 |
+
size 3844
|
runs/May17_22-09-02_5dbdc00b04c7/1652825353.0115438/events.out.tfevents.1652825353.5dbdc00b04c7.1149.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fff519c241c7f6cf39462a6854dc9c434689a2e1260ad232c25e1bea01ce92f9
|
3 |
+
size 5196
|
runs/May17_22-09-02_5dbdc00b04c7/events.out.tfevents.1652825353.5dbdc00b04c7.1149.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ca85fabc6d9aea6d743b22e84c97eb0d8ea8da769d31c6549714e4158cda5930
|
3 |
+
size 3844
|
runs/May17_22-10-24_5dbdc00b04c7/1652825434.4454792/events.out.tfevents.1652825434.5dbdc00b04c7.1325.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa081c6886e0b141e84b6a6b87a7d652e5e2b003c8dbbdec1052bbc995477789
|
3 |
+
size 5196
|
runs/May17_22-10-24_5dbdc00b04c7/events.out.tfevents.1652825434.5dbdc00b04c7.1325.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7bcd60a864450e9b8204ba1704d3de6646f4568e2547e0f757660ce779d20f20
|
3 |
+
size 4001
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a70bad3cdb2e4d613c4a46e682a8f055353f6b5fd46f2b738fb5b14d7f9e96e0
|
3 |
+
size 3247
|