Training in progress, step 500
Browse files- .gitignore +1 -0
- config.json +40 -0
- pytorch_model.bin +3 -0
- runs/Jan19_15-51-34_tiger4.stanford.edu/1674172338.9805443/events.out.tfevents.1674172338.tiger4.stanford.edu.4018380.1 +3 -0
- runs/Jan19_15-51-34_tiger4.stanford.edu/events.out.tfevents.1674172338.tiger4.stanford.edu.4018380.0 +3 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "gpt2-xl",
|
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": 1600,
|
16 |
+
"n_head": 25,
|
17 |
+
"n_inner": null,
|
18 |
+
"n_layer": 48,
|
19 |
+
"n_positions": 1024,
|
20 |
+
"output_past": true,
|
21 |
+
"reorder_and_upcast_attn": false,
|
22 |
+
"resid_pdrop": 0.1,
|
23 |
+
"scale_attn_by_inverse_layer_idx": false,
|
24 |
+
"scale_attn_weights": true,
|
25 |
+
"summary_activation": null,
|
26 |
+
"summary_first_dropout": 0.1,
|
27 |
+
"summary_proj_to_labels": true,
|
28 |
+
"summary_type": "cls_index",
|
29 |
+
"summary_use_proj": true,
|
30 |
+
"task_specific_params": {
|
31 |
+
"text-generation": {
|
32 |
+
"do_sample": true,
|
33 |
+
"max_length": 50
|
34 |
+
}
|
35 |
+
},
|
36 |
+
"torch_dtype": "float32",
|
37 |
+
"transformers_version": "4.25.1",
|
38 |
+
"use_cache": true,
|
39 |
+
"vocab_size": 50257
|
40 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f9279a7e3b384bd59d8855d7457861dbe1f33b4f69673d153f985c2ca653630f
|
3 |
+
size 6281010835
|
runs/Jan19_15-51-34_tiger4.stanford.edu/1674172338.9805443/events.out.tfevents.1674172338.tiger4.stanford.edu.4018380.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:092ce88a008abe9a04e858c718bad30554ef4b8fbc71256d46a808193db86fb8
|
3 |
+
size 5639
|
runs/Jan19_15-51-34_tiger4.stanford.edu/events.out.tfevents.1674172338.tiger4.stanford.edu.4018380.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0d0fdb489574d4d5f7ba817820630a7e19e9aab44d1e98aac5d7179e79603dd1
|
3 |
+
size 4278
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:98b3181d129f912ea1d2899755d60cbdf26abd6d2dff6e45315d4d19cac82e49
|
3 |
+
size 3503
|