imda-lseokmin
commited on
Commit
•
691b03d
1
Parent(s):
717255d
Upload 159 files
Browse files- README.md +2 -2
- all_results.json +13 -13
- checkpoint-1000/model.safetensors +1 -1
- checkpoint-1000/optimizer.pt +1 -1
- checkpoint-1000/rng_state.pth +1 -1
- checkpoint-1000/scheduler.pt +1 -1
- checkpoint-1000/trainer_state.json +11 -11
- checkpoint-1000/training_args.bin +1 -1
- checkpoint-500/model.safetensors +1 -1
- checkpoint-500/optimizer.pt +1 -1
- checkpoint-500/rng_state.pth +1 -1
- checkpoint-500/scheduler.pt +1 -1
- checkpoint-500/trainer_state.json +7 -7
- checkpoint-500/training_args.bin +1 -1
- eval_results.json +7 -7
- model.safetensors +1 -1
- train_results.json +6 -6
- trainer_state.json +17 -17
- training_args.bin +1 -1
README.md
CHANGED
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
|
18 |
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss:
|
21 |
-
- Accuracy: 0.
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
17 |
|
18 |
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 3.0447
|
21 |
+
- Accuracy: 0.3878
|
22 |
|
23 |
## Model description
|
24 |
|
all_results.json
CHANGED
@@ -1,16 +1,16 @@
|
|
1 |
{
|
2 |
"epoch": 20.0,
|
3 |
-
"eval_accuracy": 0.
|
4 |
-
"eval_loss":
|
5 |
-
"eval_runtime": 0.
|
6 |
-
"eval_samples":
|
7 |
-
"eval_samples_per_second": 14.
|
8 |
-
"eval_steps_per_second":
|
9 |
-
"perplexity":
|
10 |
-
"total_flos":
|
11 |
-
"train_loss":
|
12 |
-
"train_runtime":
|
13 |
-
"train_samples":
|
14 |
-
"train_samples_per_second": 5.
|
15 |
-
"train_steps_per_second": 2.
|
16 |
}
|
|
|
1 |
{
|
2 |
"epoch": 20.0,
|
3 |
+
"eval_accuracy": 0.3878299120234604,
|
4 |
+
"eval_loss": 3.044700860977173,
|
5 |
+
"eval_runtime": 0.5419,
|
6 |
+
"eval_samples": 8,
|
7 |
+
"eval_samples_per_second": 14.762,
|
8 |
+
"eval_steps_per_second": 7.381,
|
9 |
+
"perplexity": 21.00374722261463,
|
10 |
+
"total_flos": 1181039984640000.0,
|
11 |
+
"train_loss": 2.0282494394402755,
|
12 |
+
"train_runtime": 450.0172,
|
13 |
+
"train_samples": 113,
|
14 |
+
"train_samples_per_second": 5.022,
|
15 |
+
"train_steps_per_second": 2.533
|
16 |
}
|
checkpoint-1000/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 497774208
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0eafae2b6ff425a68e1dff3b58217192755c5552624bec6e0a5a24c2cfeef0d7
|
3 |
size 497774208
|
checkpoint-1000/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 995642298
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da3865fd609302881be01c29801902af8955f2eaf6a500b6eddbdb1ecbccff3c
|
3 |
size 995642298
|
checkpoint-1000/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e15521664bcf9955b1a2b66e810668f825d186fef974c4b18a31c7cd19e0437a
|
3 |
size 14244
|
checkpoint-1000/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:56c9dff28a9d4ea03847c10914973912c6d11b9e39b2afb53832948fd687a713
|
3 |
size 1064
|
checkpoint-1000/trainer_state.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 1000,
|
7 |
"is_hyper_param_search": false,
|
@@ -9,26 +9,26 @@
|
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
-
"epoch":
|
13 |
-
"grad_norm":
|
14 |
-
"learning_rate":
|
15 |
-
"loss":
|
16 |
"step": 500
|
17 |
},
|
18 |
{
|
19 |
-
"epoch":
|
20 |
-
"grad_norm":
|
21 |
-
"learning_rate":
|
22 |
-
"loss": 1.
|
23 |
"step": 1000
|
24 |
}
|
25 |
],
|
26 |
"logging_steps": 500,
|
27 |
-
"max_steps":
|
28 |
"num_input_tokens_seen": 0,
|
29 |
"num_train_epochs": 20,
|
30 |
"save_steps": 500,
|
31 |
-
"total_flos":
|
32 |
"train_batch_size": 2,
|
33 |
"trial_name": null,
|
34 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 17.54385964912281,
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 1000,
|
7 |
"is_hyper_param_search": false,
|
|
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
+
"epoch": 8.771929824561404,
|
13 |
+
"grad_norm": 5.5376715660095215,
|
14 |
+
"learning_rate": 2.8070175438596492e-05,
|
15 |
+
"loss": 2.3748,
|
16 |
"step": 500
|
17 |
},
|
18 |
{
|
19 |
+
"epoch": 17.54385964912281,
|
20 |
+
"grad_norm": 5.5406880378723145,
|
21 |
+
"learning_rate": 6.140350877192982e-06,
|
22 |
+
"loss": 1.7925,
|
23 |
"step": 1000
|
24 |
}
|
25 |
],
|
26 |
"logging_steps": 500,
|
27 |
+
"max_steps": 1140,
|
28 |
"num_input_tokens_seen": 0,
|
29 |
"num_train_epochs": 20,
|
30 |
"save_steps": 500,
|
31 |
+
"total_flos": 1036284198912000.0,
|
32 |
"train_batch_size": 2,
|
33 |
"trial_name": null,
|
34 |
"trial_params": null
|
checkpoint-1000/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb06b4254316e1ab5e3df832bc95c5eed217d0c6e05ef2ece9717f8db05462b9
|
3 |
size 4984
|
checkpoint-500/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 497774208
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d6f130cbd8a4515242330284192392edc8462adce4467e1764fab022c447c13a
|
3 |
size 497774208
|
checkpoint-500/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 995642298
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:291721543b1bea75dc67b7f4214f7e495d5792dc17f7bbe192b2c5c500d1ce54
|
3 |
size 995642298
|
checkpoint-500/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:777137f7b6438e37de19223f30fb87cd1210813798ec473dff745146fb62b610
|
3 |
size 14244
|
checkpoint-500/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d9df7e73f7009fee1832457c31aeab89c9411a8aad568d49bf516ca4a4b45d88
|
3 |
size 1064
|
checkpoint-500/trainer_state.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 500,
|
7 |
"is_hyper_param_search": false,
|
@@ -9,19 +9,19 @@
|
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
-
"epoch":
|
13 |
-
"grad_norm":
|
14 |
-
"learning_rate":
|
15 |
-
"loss":
|
16 |
"step": 500
|
17 |
}
|
18 |
],
|
19 |
"logging_steps": 500,
|
20 |
-
"max_steps":
|
21 |
"num_input_tokens_seen": 0,
|
22 |
"num_train_epochs": 20,
|
23 |
"save_steps": 500,
|
24 |
-
"total_flos":
|
25 |
"train_batch_size": 2,
|
26 |
"trial_name": null,
|
27 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 8.771929824561404,
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 500,
|
7 |
"is_hyper_param_search": false,
|
|
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
+
"epoch": 8.771929824561404,
|
13 |
+
"grad_norm": 5.5376715660095215,
|
14 |
+
"learning_rate": 2.8070175438596492e-05,
|
15 |
+
"loss": 2.3748,
|
16 |
"step": 500
|
17 |
}
|
18 |
],
|
19 |
"logging_steps": 500,
|
20 |
+
"max_steps": 1140,
|
21 |
"num_input_tokens_seen": 0,
|
22 |
"num_train_epochs": 20,
|
23 |
"save_steps": 500,
|
24 |
+
"total_flos": 518403391488000.0,
|
25 |
"train_batch_size": 2,
|
26 |
"trial_name": null,
|
27 |
"trial_params": null
|
checkpoint-500/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb06b4254316e1ab5e3df832bc95c5eed217d0c6e05ef2ece9717f8db05462b9
|
3 |
size 4984
|
eval_results.json
CHANGED
@@ -1,10 +1,10 @@
|
|
1 |
{
|
2 |
"epoch": 20.0,
|
3 |
-
"eval_accuracy": 0.
|
4 |
-
"eval_loss":
|
5 |
-
"eval_runtime": 0.
|
6 |
-
"eval_samples":
|
7 |
-
"eval_samples_per_second": 14.
|
8 |
-
"eval_steps_per_second":
|
9 |
-
"perplexity":
|
10 |
}
|
|
|
1 |
{
|
2 |
"epoch": 20.0,
|
3 |
+
"eval_accuracy": 0.3878299120234604,
|
4 |
+
"eval_loss": 3.044700860977173,
|
5 |
+
"eval_runtime": 0.5419,
|
6 |
+
"eval_samples": 8,
|
7 |
+
"eval_samples_per_second": 14.762,
|
8 |
+
"eval_steps_per_second": 7.381,
|
9 |
+
"perplexity": 21.00374722261463
|
10 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 497774208
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ed42548dc68d3a36c9021a2620c13fbad3926a37f8f73cc0176886c465edf1ad
|
3 |
size 497774208
|
train_results.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"epoch": 20.0,
|
3 |
-
"total_flos":
|
4 |
-
"train_loss":
|
5 |
-
"train_runtime":
|
6 |
-
"train_samples":
|
7 |
-
"train_samples_per_second": 5.
|
8 |
-
"train_steps_per_second": 2.
|
9 |
}
|
|
|
1 |
{
|
2 |
"epoch": 20.0,
|
3 |
+
"total_flos": 1181039984640000.0,
|
4 |
+
"train_loss": 2.0282494394402755,
|
5 |
+
"train_runtime": 450.0172,
|
6 |
+
"train_samples": 113,
|
7 |
+
"train_samples_per_second": 5.022,
|
8 |
+
"train_steps_per_second": 2.533
|
9 |
}
|
trainer_state.json
CHANGED
@@ -3,41 +3,41 @@
|
|
3 |
"best_model_checkpoint": null,
|
4 |
"epoch": 20.0,
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
-
"epoch":
|
13 |
-
"grad_norm":
|
14 |
-
"learning_rate":
|
15 |
-
"loss":
|
16 |
"step": 500
|
17 |
},
|
18 |
{
|
19 |
-
"epoch":
|
20 |
-
"grad_norm":
|
21 |
-
"learning_rate":
|
22 |
-
"loss": 1.
|
23 |
"step": 1000
|
24 |
},
|
25 |
{
|
26 |
"epoch": 20.0,
|
27 |
-
"step":
|
28 |
-
"total_flos":
|
29 |
-
"train_loss":
|
30 |
-
"train_runtime":
|
31 |
-
"train_samples_per_second": 5.
|
32 |
-
"train_steps_per_second": 2.
|
33 |
}
|
34 |
],
|
35 |
"logging_steps": 500,
|
36 |
-
"max_steps":
|
37 |
"num_input_tokens_seen": 0,
|
38 |
"num_train_epochs": 20,
|
39 |
"save_steps": 500,
|
40 |
-
"total_flos":
|
41 |
"train_batch_size": 2,
|
42 |
"trial_name": null,
|
43 |
"trial_params": null
|
|
|
3 |
"best_model_checkpoint": null,
|
4 |
"epoch": 20.0,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 1140,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
+
"epoch": 8.771929824561404,
|
13 |
+
"grad_norm": 5.5376715660095215,
|
14 |
+
"learning_rate": 2.8070175438596492e-05,
|
15 |
+
"loss": 2.3748,
|
16 |
"step": 500
|
17 |
},
|
18 |
{
|
19 |
+
"epoch": 17.54385964912281,
|
20 |
+
"grad_norm": 5.5406880378723145,
|
21 |
+
"learning_rate": 6.140350877192982e-06,
|
22 |
+
"loss": 1.7925,
|
23 |
"step": 1000
|
24 |
},
|
25 |
{
|
26 |
"epoch": 20.0,
|
27 |
+
"step": 1140,
|
28 |
+
"total_flos": 1181039984640000.0,
|
29 |
+
"train_loss": 2.0282494394402755,
|
30 |
+
"train_runtime": 450.0172,
|
31 |
+
"train_samples_per_second": 5.022,
|
32 |
+
"train_steps_per_second": 2.533
|
33 |
}
|
34 |
],
|
35 |
"logging_steps": 500,
|
36 |
+
"max_steps": 1140,
|
37 |
"num_input_tokens_seen": 0,
|
38 |
"num_train_epochs": 20,
|
39 |
"save_steps": 500,
|
40 |
+
"total_flos": 1181039984640000.0,
|
41 |
"train_batch_size": 2,
|
42 |
"trial_name": null,
|
43 |
"trial_params": null
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb06b4254316e1ab5e3df832bc95c5eed217d0c6e05ef2ece9717f8db05462b9
|
3 |
size 4984
|