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/Oct11_11-18-19_ffe102445c71/1665487338.996814/events.out.tfevents.1665487338.ffe102445c71.67.1 +3 -0
- runs/Oct11_11-18-19_ffe102445c71/1665487355.1207964/events.out.tfevents.1665487355.ffe102445c71.67.2 +3 -0
- runs/Oct11_11-18-19_ffe102445c71/1665487355.729383/events.out.tfevents.1665487355.ffe102445c71.67.3 +3 -0
- runs/Oct11_11-18-19_ffe102445c71/1665487356.3116057/events.out.tfevents.1665487356.ffe102445c71.67.4 +3 -0
- runs/Oct11_11-18-19_ffe102445c71/events.out.tfevents.1665487338.ffe102445c71.67.0 +3 -0
- training_args.bin +1 -1
config.json
CHANGED
@@ -47,7 +47,7 @@
|
|
47 |
"summary_type": "cls_index",
|
48 |
"summary_use_proj": true,
|
49 |
"torch_dtype": "float32",
|
50 |
-
"transformers_version": "4.
|
51 |
"use_cache": true,
|
52 |
"vocab_size": 50257,
|
53 |
"window_size": 256
|
|
|
47 |
"summary_type": "cls_index",
|
48 |
"summary_use_proj": true,
|
49 |
"torch_dtype": "float32",
|
50 |
+
"transformers_version": "4.23.0",
|
51 |
"use_cache": true,
|
52 |
"vocab_size": 50257,
|
53 |
"window_size": 256
|
last-checkpoint/config.json
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "cedpsam/EleutherAI_gpt-neo-125M-stablediffionprompts",
|
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": "4.23.0",
|
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 sha256:878dceb09badf3b13557611de0d035030b7d573e3960544dd8a3fd7b42c90ca7
|
3 |
+
size 1001681601
|
last-checkpoint/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e9a1a743e9cfc9760432d0742badc65f6555c81f4e833def537b0207a7cd4e1
|
3 |
+
size 551185105
|
last-checkpoint/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:84838ccd45951bbe1e5f964cffc9f60572ee4f5e111f59de86b1a56f3d7a6bd8
|
3 |
+
size 14503
|
last-checkpoint/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4fa4c7be44c959599b8b43bb9bc3371e9e4e5bbc5758b3ab5afcccfda3e72e67
|
3 |
+
size 559
|
last-checkpoint/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9bba0534880ddf6cf8901153e43087f30df53e956d861cda03d12ae77a09ee10
|
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": 4.8333333333333334e-05,
|
13 |
+
"loss": 0.0393,
|
14 |
+
"step": 500
|
15 |
+
}
|
16 |
+
],
|
17 |
+
"max_steps": 15000,
|
18 |
+
"num_train_epochs": 1,
|
19 |
+
"total_flos": 522414194688000.0,
|
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 sha256:048b61eedc827307da0a6f313386c8adf0694d4111001b41741198cdf4f2f4d7
|
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 sha256:9e9a1a743e9cfc9760432d0742badc65f6555c81f4e833def537b0207a7cd4e1
|
3 |
size 551185105
|
runs/Oct11_11-18-19_ffe102445c71/1665487338.996814/events.out.tfevents.1665487338.ffe102445c71.67.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0c63ca6f9b2049089d6744de368be37d77d556bb5dbe18291d18f7051460d71f
|
3 |
+
size 5646
|
runs/Oct11_11-18-19_ffe102445c71/1665487355.1207964/events.out.tfevents.1665487355.ffe102445c71.67.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b92f8d36eca4efd38618189d5636793f4d068b3c362b99dfb561187e2b4b12e5
|
3 |
+
size 5646
|
runs/Oct11_11-18-19_ffe102445c71/1665487355.729383/events.out.tfevents.1665487355.ffe102445c71.67.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fce4a2c19f4f4c58bc393e9778a51e0138549670f0beeaec1cdc1f8d82875561
|
3 |
+
size 5646
|
runs/Oct11_11-18-19_ffe102445c71/1665487356.3116057/events.out.tfevents.1665487356.ffe102445c71.67.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:04c2e66daa705fe9b92504ea377f8bbd72a761a0983aac563827e170a1f8a2bd
|
3 |
+
size 5646
|
runs/Oct11_11-18-19_ffe102445c71/events.out.tfevents.1665487338.ffe102445c71.67.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ea19880fb454627019aaba81fb7f1aeeb6770cc2a401cf552916edb384548a08
|
3 |
+
size 17401
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3567
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:048b61eedc827307da0a6f313386c8adf0694d4111001b41741198cdf4f2f4d7
|
3 |
size 3567
|