Training in progress, step 500
Browse files- model.safetensors +1 -1
- run-15/checkpoint-500/model.safetensors +1 -1
- run-15/checkpoint-500/optimizer.pt +1 -1
- run-15/checkpoint-500/rng_state.pth +1 -1
- run-15/checkpoint-500/scheduler.pt +1 -1
- run-15/checkpoint-500/trainer_state.json +5 -5
- run-15/checkpoint-500/training_args.bin +1 -1
- run-17/checkpoint-500/trainer_state.json +5 -5
- training_args.bin +1 -1
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1340618660
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfb9a326bbb396d4f62120515d7b5b1e0fe041343ada30727aee03eb85356ca6
|
3 |
size 1340618660
|
run-15/checkpoint-500/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1340618660
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfb9a326bbb396d4f62120515d7b5b1e0fe041343ada30727aee03eb85356ca6
|
3 |
size 1340618660
|
run-15/checkpoint-500/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2681472237
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a11ec9b02b30e13d1b49f015518bf3b777e1795dca6ac98c95a680d6da03da97
|
3 |
size 2681472237
|
run-15/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:b39308b250b2dde21cca6217a709d5456bcdcab3c796c6926f25c06b9c730de1
|
3 |
size 14244
|
run-15/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:b45a226a8c59516a2e21211053f4ceb2fae0f9e67783d1104784e9c2a2562098
|
3 |
size 1064
|
run-15/checkpoint-500/trainer_state.json
CHANGED
@@ -10,9 +10,9 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.6702412868632708,
|
13 |
-
"grad_norm":
|
14 |
-
"learning_rate":
|
15 |
-
"loss": 0.
|
16 |
"step": 500
|
17 |
}
|
18 |
],
|
@@ -21,11 +21,11 @@
|
|
21 |
"num_input_tokens_seen": 0,
|
22 |
"num_train_epochs": 10,
|
23 |
"save_steps": 500,
|
24 |
-
"total_flos":
|
25 |
"train_batch_size": 16,
|
26 |
"trial_name": null,
|
27 |
"trial_params": {
|
28 |
-
"learning_rate":
|
29 |
"per_device_train_batch_size": 16
|
30 |
}
|
31 |
}
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.6702412868632708,
|
13 |
+
"grad_norm": 6.469808101654053,
|
14 |
+
"learning_rate": 3.9090186376825696e-05,
|
15 |
+
"loss": 0.5858,
|
16 |
"step": 500
|
17 |
}
|
18 |
],
|
|
|
21 |
"num_input_tokens_seen": 0,
|
22 |
"num_train_epochs": 10,
|
23 |
"save_steps": 500,
|
24 |
+
"total_flos": 3210288839752032.0,
|
25 |
"train_batch_size": 16,
|
26 |
"trial_name": null,
|
27 |
"trial_params": {
|
28 |
+
"learning_rate": 4.189838942113789e-05,
|
29 |
"per_device_train_batch_size": 16
|
30 |
}
|
31 |
}
|
run-15/checkpoint-500/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5048
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f586d922083e7ebb267b27882bab1647a91d0e02098755a90089df9c617f4e36
|
3 |
size 5048
|
run-17/checkpoint-500/trainer_state.json
CHANGED
@@ -10,9 +10,9 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.6702412868632708,
|
13 |
-
"grad_norm":
|
14 |
-
"learning_rate":
|
15 |
-
"loss": 0.
|
16 |
"step": 500
|
17 |
}
|
18 |
],
|
@@ -21,11 +21,11 @@
|
|
21 |
"num_input_tokens_seen": 0,
|
22 |
"num_train_epochs": 10,
|
23 |
"save_steps": 500,
|
24 |
-
"total_flos":
|
25 |
"train_batch_size": 16,
|
26 |
"trial_name": null,
|
27 |
"trial_params": {
|
28 |
-
"learning_rate":
|
29 |
"per_device_train_batch_size": 16
|
30 |
}
|
31 |
}
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.6702412868632708,
|
13 |
+
"grad_norm": 4.858139514923096,
|
14 |
+
"learning_rate": 1.2967014882299104e-05,
|
15 |
+
"loss": 0.5448,
|
16 |
"step": 500
|
17 |
}
|
18 |
],
|
|
|
21 |
"num_input_tokens_seen": 0,
|
22 |
"num_train_epochs": 10,
|
23 |
"save_steps": 500,
|
24 |
+
"total_flos": 3794913619206480.0,
|
25 |
"train_batch_size": 16,
|
26 |
"trial_name": null,
|
27 |
"trial_params": {
|
28 |
+
"learning_rate": 1.3898553307751626e-05,
|
29 |
"per_device_train_batch_size": 16
|
30 |
}
|
31 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5048
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f586d922083e7ebb267b27882bab1647a91d0e02098755a90089df9c617f4e36
|
3 |
size 5048
|