Training in progress, step 19
Browse files- config.json +39 -0
- model.safetensors +3 -0
- runs/Oct07_04-59-19_e024f1e674ed/events.out.tfevents.1728277253.e024f1e674ed.293.0 +3 -0
- runs/Oct07_05-16-56_e024f1e674ed/events.out.tfevents.1728278224.e024f1e674ed.293.1 +3 -0
- runs/Oct07_05-16-56_e024f1e674ed/events.out.tfevents.1728278355.e024f1e674ed.293.2 +3 -0
- runs/Oct07_05-16-56_e024f1e674ed/events.out.tfevents.1728278572.e024f1e674ed.293.3 +3 -0
- runs/Oct07_05-16-56_e024f1e674ed/events.out.tfevents.1728278613.e024f1e674ed.293.4 +3 -0
- runs/Oct07_05-26-55_e024f1e674ed/events.out.tfevents.1728278825.e024f1e674ed.293.5 +3 -0
- runs/Oct07_05-54-54_e024f1e674ed/events.out.tfevents.1728280506.e024f1e674ed.18647.0 +3 -0
- runs/Oct07_05-56-33_e024f1e674ed/events.out.tfevents.1728280600.e024f1e674ed.18647.1 +3 -0
- training_args.bin +3 -0
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": 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": 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": "4.44.2",
|
37 |
+
"use_cache": true,
|
38 |
+
"vocab_size": 50257
|
39 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:05b8e92d7e2433272639e4249009b2ee235b1cc4d993556bb9b9b62994866769
|
3 |
+
size 497774208
|
runs/Oct07_04-59-19_e024f1e674ed/events.out.tfevents.1728277253.e024f1e674ed.293.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8772da9304d9171b8d1dff3d556a2f56687b4444e0a90f31da9a6894b3955dbe
|
3 |
+
size 5351
|
runs/Oct07_05-16-56_e024f1e674ed/events.out.tfevents.1728278224.e024f1e674ed.293.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ed08a4b13a185bb4bed46c7d2302a11ca2372b7c3bf95541e5e5da1f3f834f23
|
3 |
+
size 5145
|
runs/Oct07_05-16-56_e024f1e674ed/events.out.tfevents.1728278355.e024f1e674ed.293.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eb64ccfcdaec4b5440ee8b174d4cc1c10497e2ffbf7921bc18db18c3b9172472
|
3 |
+
size 5145
|
runs/Oct07_05-16-56_e024f1e674ed/events.out.tfevents.1728278572.e024f1e674ed.293.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7b4052bd851882674e24960f828bf10426cc415dda445273c6b274a00e66820f
|
3 |
+
size 5145
|
runs/Oct07_05-16-56_e024f1e674ed/events.out.tfevents.1728278613.e024f1e674ed.293.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ff27c22a3142981535f90ad8f257c6e7d7a03b9e5de9b923ae6687ca0570ca2b
|
3 |
+
size 5145
|
runs/Oct07_05-26-55_e024f1e674ed/events.out.tfevents.1728278825.e024f1e674ed.293.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cec1906a3940b7008933b15ee48837c18c2d6243ff4d957da88c552d5bd6dbbe
|
3 |
+
size 5145
|
runs/Oct07_05-54-54_e024f1e674ed/events.out.tfevents.1728280506.e024f1e674ed.18647.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:44c3c5352b9b5167df2f53965231ca576a6d4cebf26a6c2211fc0e5c085fb990
|
3 |
+
size 5145
|
runs/Oct07_05-56-33_e024f1e674ed/events.out.tfevents.1728280600.e024f1e674ed.18647.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8a75a91729f038feeb855813d132443a22a017dcc1494556051fdc123732103f
|
3 |
+
size 7355
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:517179064982a073e33e463339f17fb7ebd4d60030b7ec5928057cdc140666a7
|
3 |
+
size 5176
|