Training in progress, step 500
Browse files- .gitignore +1 -0
- config.json +41 -0
- pytorch_model.bin +3 -0
- runs/May20_23-52-49_c1f36c566f73/1653090797.2081466/events.out.tfevents.1653090797.c1f36c566f73.80.1 +3 -0
- runs/May20_23-52-49_c1f36c566f73/events.out.tfevents.1653090797.c1f36c566f73.80.0 +3 -0
- runs/May20_23-54-47_c1f36c566f73/1653090900.9233518/events.out.tfevents.1653090900.c1f36c566f73.305.1 +3 -0
- runs/May20_23-54-47_c1f36c566f73/events.out.tfevents.1653090900.c1f36c566f73.305.0 +3 -0
- runs/May20_23-59-23_c1f36c566f73/1653091176.6905553/events.out.tfevents.1653091176.c1f36c566f73.509.1 +3 -0
- runs/May20_23-59-23_c1f36c566f73/events.out.tfevents.1653091176.c1f36c566f73.509.0 +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:ed0e375273bd791312abdf5466ecd78c7f2fc552b9f9225a619d58b60ff41b25
|
3 |
+
size 1444566873
|
runs/May20_23-52-49_c1f36c566f73/1653090797.2081466/events.out.tfevents.1653090797.c1f36c566f73.80.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:72823f36eb34a17c01bc5f41519c841768a6b79a86d38871531c42dc5d8a3cd2
|
3 |
+
size 5163
|
runs/May20_23-52-49_c1f36c566f73/events.out.tfevents.1653090797.c1f36c566f73.80.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2c213c4afeaa3e5a7627e238123fff658244e00ce0b3e89d21042879a23a1561
|
3 |
+
size 3812
|
runs/May20_23-54-47_c1f36c566f73/1653090900.9233518/events.out.tfevents.1653090900.c1f36c566f73.305.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:54d67cd6b03ee3542147e2885c223ac46abb3b13746e6b9c16d1e2d7cf82b527
|
3 |
+
size 5163
|
runs/May20_23-54-47_c1f36c566f73/events.out.tfevents.1653090900.c1f36c566f73.305.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b04c7de85e57029595a6af84708cd74e51f7e10eb981244a678c39ee3992a4d5
|
3 |
+
size 3813
|
runs/May20_23-59-23_c1f36c566f73/1653091176.6905553/events.out.tfevents.1653091176.c1f36c566f73.509.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a37352149c8315c7f1e28fc77e6b2964b55e0a8be0e1e5d9ba681bf2584013a5
|
3 |
+
size 5163
|
runs/May20_23-59-23_c1f36c566f73/events.out.tfevents.1653091176.c1f36c566f73.509.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:279bac94dae30d2b5301cff8bf072905d7cd58ff0f7341f276c6ea3bb232edec
|
3 |
+
size 3968
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7dc68ba3fa508c568d4ae351eca153be58cbaa1263535d9470efb09e630fe9e0
|
3 |
+
size 3183
|