Training in progress, step 120
Browse files- config.json +46 -0
- model.safetensors +3 -0
- runs/Oct22_03-50-34_844524de66ae/events.out.tfevents.1729569039.844524de66ae.493.0 +3 -0
- runs/Oct22_04-00-58_844524de66ae/events.out.tfevents.1729569658.844524de66ae.493.1 +3 -0
- runs/Oct22_04-08-07_844524de66ae/events.out.tfevents.1729570088.844524de66ae.493.2 +3 -0
- runs/Oct22_04-38-46_844524de66ae/events.out.tfevents.1729571927.844524de66ae.493.3 +3 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilgpt2",
|
3 |
+
"_num_labels": 1,
|
4 |
+
"activation_function": "gelu_new",
|
5 |
+
"architectures": [
|
6 |
+
"GPT2LMHeadModel"
|
7 |
+
],
|
8 |
+
"attn_pdrop": 0.1,
|
9 |
+
"bos_token_id": 50256,
|
10 |
+
"embd_pdrop": 0.1,
|
11 |
+
"eos_token_id": 50256,
|
12 |
+
"id2label": {
|
13 |
+
"0": "LABEL_0"
|
14 |
+
},
|
15 |
+
"initializer_range": 0.02,
|
16 |
+
"label2id": {
|
17 |
+
"LABEL_0": 0
|
18 |
+
},
|
19 |
+
"layer_norm_epsilon": 1e-05,
|
20 |
+
"model_type": "gpt2",
|
21 |
+
"n_ctx": 1024,
|
22 |
+
"n_embd": 768,
|
23 |
+
"n_head": 12,
|
24 |
+
"n_inner": null,
|
25 |
+
"n_layer": 6,
|
26 |
+
"n_positions": 1024,
|
27 |
+
"reorder_and_upcast_attn": false,
|
28 |
+
"resid_pdrop": 0.1,
|
29 |
+
"scale_attn_by_inverse_layer_idx": false,
|
30 |
+
"scale_attn_weights": true,
|
31 |
+
"summary_activation": null,
|
32 |
+
"summary_first_dropout": 0.1,
|
33 |
+
"summary_proj_to_labels": true,
|
34 |
+
"summary_type": "cls_index",
|
35 |
+
"summary_use_proj": true,
|
36 |
+
"task_specific_params": {
|
37 |
+
"text-generation": {
|
38 |
+
"do_sample": true,
|
39 |
+
"max_length": 50
|
40 |
+
}
|
41 |
+
},
|
42 |
+
"torch_dtype": "float32",
|
43 |
+
"transformers_version": "4.44.2",
|
44 |
+
"use_cache": true,
|
45 |
+
"vocab_size": 50257
|
46 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9cdb0cc9f721e0848ead521a33c1d94bfa9a13bd22349f468fcf85b96888352c
|
3 |
+
size 327657928
|
runs/Oct22_03-50-34_844524de66ae/events.out.tfevents.1729569039.844524de66ae.493.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a4071d542fc3d29d859a5b4e047c8db40ae594f79a2c82e6fbb261afbf9f0b2c
|
3 |
+
size 5283
|
runs/Oct22_04-00-58_844524de66ae/events.out.tfevents.1729569658.844524de66ae.493.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2dbcba93dfd35e193223dd9d426a880f77ed7c59d120af339c9629b157d04e14
|
3 |
+
size 5283
|
runs/Oct22_04-08-07_844524de66ae/events.out.tfevents.1729570088.844524de66ae.493.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:71f0f6fb5af98ea2af33ab2a3620b395a4b6dfa1b7a195ac2c91e8da366269ef
|
3 |
+
size 5283
|
runs/Oct22_04-38-46_844524de66ae/events.out.tfevents.1729571927.844524de66ae.493.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:989805c1fd72ea6e3eceb105f306e67a376f787e9a1c153fbeb7a31c51f1b16f
|
3 |
+
size 5815
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:784155fb7415fa19daeb2f10d0f8277d911a5f307d04943e456e487fa711ab66
|
3 |
+
size 5240
|