Training in progress, step 500
Browse files- adapter_model.safetensors +1 -1
- config.json +41 -0
- model.safetensors +3 -0
- runs/Jan04_20-47-30_uclaml03.cs.ucla.edu/events.out.tfevents.1704430054.uclaml03.cs.ucla.edu.2050274.0 +2 -2
- runs/Jan05_09-30-14_uclaml03.cs.ucla.edu/events.out.tfevents.1704475818.uclaml03.cs.ucla.edu.2493483.0 +3 -0
- runs/Jan05_09-33-29_uclaml03.cs.ucla.edu/events.out.tfevents.1704476013.uclaml03.cs.ucla.edu.2494910.0 +3 -0
- training_args.bin +1 -1
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5912664
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:61eb2d0efa2a2529712f6362e50095e0c1c0c80471e7cb0d794e8cf75b9ec406
|
3 |
size 5912664
|
config.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "gpt2-large",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2ForSequenceClassification"
|
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 |
+
"pad_token_id": 50256,
|
21 |
+
"problem_type": "single_label_classification",
|
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": "bfloat16",
|
38 |
+
"transformers_version": "4.35.0",
|
39 |
+
"use_cache": true,
|
40 |
+
"vocab_size": 50257
|
41 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f02012c4e94f93f8b5fcf42752b120ccc567f0a6ca9438d9a3e9a9937d8e089
|
3 |
+
size 1548111048
|
runs/Jan04_20-47-30_uclaml03.cs.ucla.edu/events.out.tfevents.1704430054.uclaml03.cs.ucla.edu.2050274.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:343bbdc5b0747725a28d5efd722ddea9396ba96dfafdf8f0ddc8653bb2e9dad6
|
3 |
+
size 29036
|
runs/Jan05_09-30-14_uclaml03.cs.ucla.edu/events.out.tfevents.1704475818.uclaml03.cs.ucla.edu.2493483.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1c9cd9983b1e148e0d2596fd7cc54cb3c73cd759b89b13796f1793d39cc49f51
|
3 |
+
size 4515
|
runs/Jan05_09-33-29_uclaml03.cs.ucla.edu/events.out.tfevents.1704476013.uclaml03.cs.ucla.edu.2494910.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c9ff41910726da7d98469e1d84c4ac412583a4a5cf439664d66b266455cb515f
|
3 |
+
size 4994
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4600
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e1c8826feb16daf2841a3e8cddd56b1d0e94c4697f000850a28307f5b6c0eb6
|
3 |
size 4600
|