Training in progress, step 500
Browse files- config.json +0 -7
- 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/Oct06_17-12-03_c63249d7c0b1/1665076518.8429594/events.out.tfevents.1665076518.c63249d7c0b1.68.1 +3 -0
- runs/Oct06_17-12-03_c63249d7c0b1/1665076534.0124779/events.out.tfevents.1665076534.c63249d7c0b1.68.2 +3 -0
- runs/Oct06_17-12-03_c63249d7c0b1/1665076534.6020637/events.out.tfevents.1665076534.c63249d7c0b1.68.3 +3 -0
- runs/Oct06_17-12-03_c63249d7c0b1/1665076535.1842048/events.out.tfevents.1665076535.c63249d7c0b1.68.4 +3 -0
- runs/Oct06_17-12-03_c63249d7c0b1/events.out.tfevents.1665076518.c63249d7c0b1.68.0 +3 -0
- training_args.bin +1 -1
config.json
CHANGED
@@ -49,13 +49,6 @@
|
|
49 |
"torch_dtype": "float32",
|
50 |
"transformers_version": "4.22.2",
|
51 |
"use_cache": true,
|
52 |
-
"task_specific_params": {
|
53 |
-
"text-generation": {
|
54 |
-
"do_sample": true,
|
55 |
-
"max_length":200
|
56 |
-
|
57 |
-
}
|
58 |
-
},
|
59 |
"vocab_size": 50257,
|
60 |
"window_size": 256
|
61 |
}
|
|
|
49 |
"torch_dtype": "float32",
|
50 |
"transformers_version": "4.22.2",
|
51 |
"use_cache": true,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
52 |
"vocab_size": 50257,
|
53 |
"window_size": 256
|
54 |
}
|
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": "4.22.2",
|
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 sha256:3b9c85d78b37094520e498d0cf5a606bf4e2f777641d6d52503e8773b5021fde
|
3 |
+
size 1001681601
|
last-checkpoint/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:80a23080c304069705290554dbd13787a4239f02106703e3b6da1fc61caab15f
|
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:f62196fb1b113eee81e8d3d881e7700e032897a91d6c3590f3456d6916ed8474
|
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": 4.722222222222222e-05,
|
13 |
+
"loss": 0.0673,
|
14 |
+
"step": 500
|
15 |
+
}
|
16 |
+
],
|
17 |
+
"max_steps": 9000,
|
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 sha256:4ad5bcc910f15fcfe415e4694b734bd32b2375fcdc79ffc4921d2b1cd12cbf7c
|
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 sha256:80a23080c304069705290554dbd13787a4239f02106703e3b6da1fc61caab15f
|
3 |
size 551185105
|
runs/Oct06_17-12-03_c63249d7c0b1/1665076518.8429594/events.out.tfevents.1665076518.c63249d7c0b1.68.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b005d8d059a33eb224b23e6ed457cf0663d8a92a562be59d06e18ff65b06efea
|
3 |
+
size 5679
|
runs/Oct06_17-12-03_c63249d7c0b1/1665076534.0124779/events.out.tfevents.1665076534.c63249d7c0b1.68.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aba913559ffc46e25e06bf1fb7648314d905740ebe051f1ac8200fec3e228c2c
|
3 |
+
size 5679
|
runs/Oct06_17-12-03_c63249d7c0b1/1665076534.6020637/events.out.tfevents.1665076534.c63249d7c0b1.68.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d8b47e3a7c57097bc42766de5ef242418df5b637fe523d744e176e0405e66f76
|
3 |
+
size 5679
|
runs/Oct06_17-12-03_c63249d7c0b1/1665076535.1842048/events.out.tfevents.1665076535.c63249d7c0b1.68.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bc7cc8ea05884bdf94266ecd2178853513973c0e5531c86dfc3757f389e23b0b
|
3 |
+
size 5679
|
runs/Oct06_17-12-03_c63249d7c0b1/events.out.tfevents.1665076518.c63249d7c0b1.68.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e1e4f71894dac526a32b3813ad81e55a3bc4809932666c8d77377926dcff6449
|
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 sha256:4ad5bcc910f15fcfe415e4694b734bd32b2375fcdc79ffc4921d2b1cd12cbf7c
|
3 |
size 3567
|