Training in progress, step 500
Browse files- .gitignore +1 -0
- config.json +39 -0
- pytorch_model.bin +3 -0
- runs/Apr15_10-42-44_P-wxworkBert-01/1649990589.1693752/events.out.tfevents.1649990589.P-wxworkBert-01.2854.1 +3 -0
- runs/Apr15_10-42-44_P-wxworkBert-01/events.out.tfevents.1649990589.P-wxworkBert-01.2854.0 +3 -0
- runs/Apr15_10-48-22_P-wxworkBert-01/1649990920.6484263/events.out.tfevents.1649990920.P-wxworkBert-01.4465.1 +3 -0
- runs/Apr15_10-48-22_P-wxworkBert-01/events.out.tfevents.1649990920.P-wxworkBert-01.4465.0 +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",
|
| 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": "4.17.0",
|
| 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 sha256:74f55f5aef1cad3c345ea0a6fb7dc6448070cb68c7fbe64be972bbf2dad87feb
|
| 3 |
+
size 510404393
|
runs/Apr15_10-42-44_P-wxworkBert-01/1649990589.1693752/events.out.tfevents.1649990589.P-wxworkBert-01.2854.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:85ff4c4f69658faf3410eb8a5be77731a1eac39da2bf6adb24499f9b7c739740
|
| 3 |
+
size 4754
|
runs/Apr15_10-42-44_P-wxworkBert-01/events.out.tfevents.1649990589.P-wxworkBert-01.2854.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cd6916ae931752601d775c62ecd8c55a0d311cc8916e90787b471f5d91a12b35
|
| 3 |
+
size 40
|
runs/Apr15_10-48-22_P-wxworkBert-01/1649990920.6484263/events.out.tfevents.1649990920.P-wxworkBert-01.4465.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3afa4e00f886f2e17277b3b07a2fda018c72c1a7d49aed62f1bcc1af2a59a62f
|
| 3 |
+
size 4754
|
runs/Apr15_10-48-22_P-wxworkBert-01/events.out.tfevents.1649990920.P-wxworkBert-01.4465.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:02add28f08fd3b4d8475b00f38e9b460d03d52e73af7e05fb5cfeee69fb05f81
|
| 3 |
+
size 3688
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:745e7143119f48687817fc64d8d6ca532a5c0c3da886c9ae0338ed9a34ee4b60
|
| 3 |
+
size 2991
|