Training in progress, step 192
Browse files- config.json +39 -0
- model.safetensors +3 -0
- runs/Aug09_00-22-11_a2df6783b532/events.out.tfevents.1723162933.a2df6783b532.34.0 +3 -0
- runs/Aug09_00-23-11_a2df6783b532/events.out.tfevents.1723162992.a2df6783b532.34.1 +3 -0
- runs/Aug09_00-25-42_a2df6783b532/events.out.tfevents.1723163143.a2df6783b532.34.2 +3 -0
- runs/Aug09_00-28-29_a2df6783b532/events.out.tfevents.1723163310.a2df6783b532.34.3 +3 -0
- runs/Aug09_00-28-41_a2df6783b532/events.out.tfevents.1723163322.a2df6783b532.34.4 +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": "4.42.3",
|
37 |
+
"use_cache": true,
|
38 |
+
"vocab_size": 54208
|
39 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:342a2bb3ede0dcdfa8424571443fed9004a749ec1687759d7d171f1b3ffc4e52
|
3 |
+
size 509911680
|
runs/Aug09_00-22-11_a2df6783b532/events.out.tfevents.1723162933.a2df6783b532.34.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:648e6f4ee0f1f1190cfe6316efc78b539b5eae936e6bb0fb7e24bb3eccc027c0
|
3 |
+
size 5073
|
runs/Aug09_00-23-11_a2df6783b532/events.out.tfevents.1723162992.a2df6783b532.34.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:76242798ddcc983c1adcdd742fbd40ee9a21549385fd48d8e9030867d7581d33
|
3 |
+
size 5073
|
runs/Aug09_00-25-42_a2df6783b532/events.out.tfevents.1723163143.a2df6783b532.34.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c49b0360a65013d6d9c78ba4b59ed0307ac9ece3acdb7df443d1092a3b1fc616
|
3 |
+
size 5073
|
runs/Aug09_00-28-29_a2df6783b532/events.out.tfevents.1723163310.a2df6783b532.34.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0601e245e5b72025c5a2e982a2c087cd5d6f10800017106ae9f6dd873eab9b4b
|
3 |
+
size 5073
|
runs/Aug09_00-28-41_a2df6783b532/events.out.tfevents.1723163322.a2df6783b532.34.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b1e301f624a077ab38e8c67a9c550e45306f15ff65b92de156065badd50e8af1
|
3 |
+
size 5427
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2300ca28b08822b4693bedc221292d3386893fc87f649bf41e9546993045c65b
|
3 |
+
size 5112
|