Training in progress, step 500
Browse files- config.json +1 -1
- last-checkpoint/config.json +54 -0
- last-checkpoint/optimizer.pt +3 -0
- last-checkpoint/pytorch_model.bin +3 -0
- last-checkpoint/rng_state.pth +3 -0
- last-checkpoint/scaler.pt +3 -0
- last-checkpoint/scheduler.pt +3 -0
- last-checkpoint/trainer_state.json +22 -0
- last-checkpoint/training_args.bin +3 -0
- pytorch_model.bin +1 -1
- runs/Oct10_09-11-38_e244ff9c7972/1665393287.3311083/events.out.tfevents.1665393287.e244ff9c7972.24.1 +3 -0
- runs/Oct10_09-11-38_e244ff9c7972/1665393298.9343245/events.out.tfevents.1665393298.e244ff9c7972.24.2 +3 -0
- runs/Oct10_09-11-38_e244ff9c7972/events.out.tfevents.1665393287.e244ff9c7972.24.0 +3 -0
- training_args.bin +2 -2
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "cedpsam/EleutherAI_gpt-neo-125M-stablediffionprompts",
|
3 |
"activation_function": "gelu_new",
|
4 |
"architectures": [
|
5 |
"GPTNeoForCausalLM"
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "../input/gptneo125mstablediffionprompts/cedpsam/EleutherAI_gpt-neo-125M-stablediffionprompts/checkpoint-72000",
|
3 |
"activation_function": "gelu_new",
|
4 |
"architectures": [
|
5 |
"GPTNeoForCausalLM"
|
last-checkpoint/config.json
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "../input/gptneo125mstablediffionprompts/cedpsam/EleutherAI_gpt-neo-125M-stablediffionprompts/checkpoint-72000",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPTNeoForCausalLM"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0,
|
8 |
+
"attention_layers": [
|
9 |
+
"global",
|
10 |
+
"local",
|
11 |
+
"global",
|
12 |
+
"local",
|
13 |
+
"global",
|
14 |
+
"local",
|
15 |
+
"global",
|
16 |
+
"local",
|
17 |
+
"global",
|
18 |
+
"local",
|
19 |
+
"global",
|
20 |
+
"local"
|
21 |
+
],
|
22 |
+
"attention_types": [
|
23 |
+
[
|
24 |
+
[
|
25 |
+
"global",
|
26 |
+
"local"
|
27 |
+
],
|
28 |
+
6
|
29 |
+
]
|
30 |
+
],
|
31 |
+
"bos_token_id": 50256,
|
32 |
+
"embed_dropout": 0,
|
33 |
+
"eos_token_id": 50256,
|
34 |
+
"gradient_checkpointing": false,
|
35 |
+
"hidden_size": 768,
|
36 |
+
"initializer_range": 0.02,
|
37 |
+
"intermediate_size": null,
|
38 |
+
"layer_norm_epsilon": 1e-05,
|
39 |
+
"max_position_embeddings": 2048,
|
40 |
+
"model_type": "gpt_neo",
|
41 |
+
"num_heads": 12,
|
42 |
+
"num_layers": 12,
|
43 |
+
"resid_dropout": 0,
|
44 |
+
"summary_activation": null,
|
45 |
+
"summary_first_dropout": 0.1,
|
46 |
+
"summary_proj_to_labels": true,
|
47 |
+
"summary_type": "cls_index",
|
48 |
+
"summary_use_proj": true,
|
49 |
+
"torch_dtype": "float32",
|
50 |
+
"transformers_version": "4.20.1",
|
51 |
+
"use_cache": true,
|
52 |
+
"vocab_size": 50257,
|
53 |
+
"window_size": 256
|
54 |
+
}
|
last-checkpoint/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4179b0e43211d82c165ea0d5e46ac8abd782eb41ef2c86737f17d354c09a683d
|
3 |
+
size 1001681601
|
last-checkpoint/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fdd180c9f3bad595ff28a8081094e34482ae60473cf3c7f3e8d9bbba4c2332c5
|
3 |
+
size 551185105
|
last-checkpoint/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:674676e662eeb93778c2b153ffad13aa90b43355da1956ce0b1e01e72f48c8d7
|
3 |
+
size 14503
|
last-checkpoint/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0ae53ce3102a174710937c6b72edc10e1eddb295c8c0083f6aef662649364830
|
3 |
+
size 559
|
last-checkpoint/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:51dbebb494d0e544faaecc887cfa1d4358344dc2a25186c474aa84b00c5b2075
|
3 |
+
size 623
|
last-checkpoint/trainer_state.json
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.006782603977318972,
|
5 |
+
"global_step": 500,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.01,
|
12 |
+
"learning_rate": 4.9321739602268106e-05,
|
13 |
+
"loss": 0.0506,
|
14 |
+
"step": 500
|
15 |
+
}
|
16 |
+
],
|
17 |
+
"max_steps": 73718,
|
18 |
+
"num_train_epochs": 1,
|
19 |
+
"total_flos": 524503851466752.0,
|
20 |
+
"trial_name": null,
|
21 |
+
"trial_params": null
|
22 |
+
}
|
last-checkpoint/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:76f7a5b9daaa07567ee5671e3963752e7d96c10b76d141e0d49b0ca332fe6348
|
3 |
+
size 3567
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 551185105
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fdd180c9f3bad595ff28a8081094e34482ae60473cf3c7f3e8d9bbba4c2332c5
|
3 |
size 551185105
|
runs/Oct10_09-11-38_e244ff9c7972/1665393287.3311083/events.out.tfevents.1665393287.e244ff9c7972.24.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:29df6494538e25b39490464e84712d11af2069694dd3b1b3ea39ac2dc5df19dc
|
3 |
+
size 5544
|
runs/Oct10_09-11-38_e244ff9c7972/1665393298.9343245/events.out.tfevents.1665393298.e244ff9c7972.24.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5d084c97606d34abaa542878f054fb9f29fc9376bf2433e6dfacc179317aa199
|
3 |
+
size 5544
|
runs/Oct10_09-11-38_e244ff9c7972/events.out.tfevents.1665393287.e244ff9c7972.24.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d7431a292d663f67f5d821ac94a26e59819e05915a6524907171c27f8e68ed6
|
3 |
+
size 8805
|
training_args.bin
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 sha256:76f7a5b9daaa07567ee5671e3963752e7d96c10b76d141e0d49b0ca332fe6348
|
3 |
+
size 3567
|