Training in progress, step 1000
Browse files- .gitignore +1 -0
- config.json +39 -0
- pytorch_model.bin +3 -0
- runs/Jul20_21-27-46_bc86a2331a71/1658352479.1736748/events.out.tfevents.1658352479.bc86a2331a71.171.1 +3 -0
- runs/Jul20_21-27-46_bc86a2331a71/events.out.tfevents.1658352479.bc86a2331a71.171.0 +3 -0
- runs/Jul20_21-29-50_bc86a2331a71/1658352597.2468162/events.out.tfevents.1658352597.bc86a2331a71.373.1 +3 -0
- runs/Jul20_21-29-50_bc86a2331a71/events.out.tfevents.1658352597.bc86a2331a71.373.0 +3 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "gpt2-large",
|
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": 1280,
|
16 |
+
"n_head": 20,
|
17 |
+
"n_inner": null,
|
18 |
+
"n_layer": 36,
|
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": "4.20.1",
|
37 |
+
"use_cache": true,
|
38 |
+
"vocab_size": 50257
|
39 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0bb046b59f02645ffae71503cb32a1a0524958d9b3589df81fca9ef2953b9c1
|
3 |
+
size 3134031497
|
runs/Jul20_21-27-46_bc86a2331a71/1658352479.1736748/events.out.tfevents.1658352479.bc86a2331a71.171.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b12d05745ea54747bde56f2ce9553a09870f9bc2f1919a58aeb4eaf631c48844
|
3 |
+
size 5317
|
runs/Jul20_21-27-46_bc86a2331a71/events.out.tfevents.1658352479.bc86a2331a71.171.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8b6eee49f675ecfbac6dfef3956a58c50400f39a394f3011a16157e3090141cd
|
3 |
+
size 3840
|
runs/Jul20_21-29-50_bc86a2331a71/1658352597.2468162/events.out.tfevents.1658352597.bc86a2331a71.373.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a05a3d511bd0258db55e83e475859bc71073e67ea9b91c1cf54ec77e91a37636
|
3 |
+
size 5317
|
runs/Jul20_21-29-50_bc86a2331a71/events.out.tfevents.1658352597.bc86a2331a71.373.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fcb698ed73ccb8c199f2930311460af759267dca4392336a5fe1de719c3217a5
|
3 |
+
size 4154
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:acb28aad44b9832b5e1a83214f83424473dc2f4a4f11feb692f1ad591a6355f1
|
3 |
+
size 3311
|