timewanderer
commited on
Commit
•
8493d01
1
Parent(s):
56831b2
Training in progress, step 1000
Browse files- model.safetensors +1 -1
- run-3/checkpoint-1000/model.safetensors +1 -1
- run-3/checkpoint-1000/optimizer.pt +1 -1
- run-3/checkpoint-1000/scheduler.pt +1 -1
- run-3/checkpoint-1000/trainer_state.json +26 -26
- run-3/checkpoint-1000/training_args.bin +1 -1
- runs/Oct12_05-09-37_f46fcd247c16/events.out.tfevents.1728711874.f46fcd247c16.522.4 +2 -2
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 268290900
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:847b25893f634ae7ae19c7fa981b031b671da55fceaff107c9c6fd1535ba9bd9
|
3 |
size 268290900
|
run-3/checkpoint-1000/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 268290900
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:847b25893f634ae7ae19c7fa981b031b671da55fceaff107c9c6fd1535ba9bd9
|
3 |
size 268290900
|
run-3/checkpoint-1000/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 536643898
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bbdf97ee43485482022c7936b134134b1d804f6bddceb5646e66726f0d638653
|
3 |
size 536643898
|
run-3/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 sha256:9f182501c34e4ea3ebc7617d27edab7e1367582b147e518cd90295ec7f2eaa0f
|
3 |
size 1064
|
run-3/checkpoint-1000/trainer_state.json
CHANGED
@@ -10,50 +10,50 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
-
"eval_accuracy": 0.
|
14 |
-
"eval_loss": 0.
|
15 |
-
"eval_runtime": 5.
|
16 |
-
"eval_samples_per_second":
|
17 |
-
"eval_steps_per_second":
|
18 |
"step": 318
|
19 |
},
|
20 |
{
|
21 |
"epoch": 1.5723270440251573,
|
22 |
-
"grad_norm": 0.
|
23 |
-
"learning_rate": 1.
|
24 |
-
"loss": 0.
|
25 |
"step": 500
|
26 |
},
|
27 |
{
|
28 |
"epoch": 2.0,
|
29 |
-
"eval_accuracy": 0.
|
30 |
-
"eval_loss": 0.
|
31 |
-
"eval_runtime":
|
32 |
-
"eval_samples_per_second":
|
33 |
-
"eval_steps_per_second":
|
34 |
"step": 636
|
35 |
},
|
36 |
{
|
37 |
"epoch": 3.0,
|
38 |
-
"eval_accuracy": 0.
|
39 |
-
"eval_loss": 0.
|
40 |
-
"eval_runtime": 5.
|
41 |
-
"eval_samples_per_second":
|
42 |
-
"eval_steps_per_second": 11.
|
43 |
"step": 954
|
44 |
},
|
45 |
{
|
46 |
"epoch": 3.1446540880503147,
|
47 |
-
"grad_norm": 0.
|
48 |
-
"learning_rate":
|
49 |
-
"loss": 0.
|
50 |
"step": 1000
|
51 |
}
|
52 |
],
|
53 |
"logging_steps": 500,
|
54 |
-
"max_steps":
|
55 |
"num_input_tokens_seen": 0,
|
56 |
-
"num_train_epochs":
|
57 |
"save_steps": 500,
|
58 |
"stateful_callbacks": {
|
59 |
"TrainerControl": {
|
@@ -71,8 +71,8 @@
|
|
71 |
"train_batch_size": 48,
|
72 |
"trial_name": null,
|
73 |
"trial_params": {
|
74 |
-
"alpha": 0.
|
75 |
-
"num_train_epochs":
|
76 |
-
"temperature":
|
77 |
}
|
78 |
}
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
+
"eval_accuracy": 0.6083870967741936,
|
14 |
+
"eval_loss": 0.26111724972724915,
|
15 |
+
"eval_runtime": 5.392,
|
16 |
+
"eval_samples_per_second": 574.924,
|
17 |
+
"eval_steps_per_second": 12.055,
|
18 |
"step": 318
|
19 |
},
|
20 |
{
|
21 |
"epoch": 1.5723270440251573,
|
22 |
+
"grad_norm": 0.612690269947052,
|
23 |
+
"learning_rate": 1.371069182389937e-05,
|
24 |
+
"loss": 0.4067,
|
25 |
"step": 500
|
26 |
},
|
27 |
{
|
28 |
"epoch": 2.0,
|
29 |
+
"eval_accuracy": 0.8261290322580646,
|
30 |
+
"eval_loss": 0.1251312643289566,
|
31 |
+
"eval_runtime": 5.4108,
|
32 |
+
"eval_samples_per_second": 572.929,
|
33 |
+
"eval_steps_per_second": 12.013,
|
34 |
"step": 636
|
35 |
},
|
36 |
{
|
37 |
"epoch": 3.0,
|
38 |
+
"eval_accuracy": 0.8719354838709678,
|
39 |
+
"eval_loss": 0.08443494886159897,
|
40 |
+
"eval_runtime": 5.5128,
|
41 |
+
"eval_samples_per_second": 562.324,
|
42 |
+
"eval_steps_per_second": 11.791,
|
43 |
"step": 954
|
44 |
},
|
45 |
{
|
46 |
"epoch": 3.1446540880503147,
|
47 |
+
"grad_norm": 0.5761224031448364,
|
48 |
+
"learning_rate": 7.421383647798742e-06,
|
49 |
+
"loss": 0.1453,
|
50 |
"step": 1000
|
51 |
}
|
52 |
],
|
53 |
"logging_steps": 500,
|
54 |
+
"max_steps": 1590,
|
55 |
"num_input_tokens_seen": 0,
|
56 |
+
"num_train_epochs": 5,
|
57 |
"save_steps": 500,
|
58 |
"stateful_callbacks": {
|
59 |
"TrainerControl": {
|
|
|
71 |
"train_batch_size": 48,
|
72 |
"trial_name": null,
|
73 |
"trial_params": {
|
74 |
+
"alpha": 0.4777308452793029,
|
75 |
+
"num_train_epochs": 5,
|
76 |
+
"temperature": 4
|
77 |
}
|
78 |
}
|
run-3/checkpoint-1000/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5ef5b259539127ef5ddc697d31b7e7180caca610f845f70ff2cba869a6149cf5
|
3 |
size 5240
|
runs/Oct12_05-09-37_f46fcd247c16/events.out.tfevents.1728711874.f46fcd247c16.522.4
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 sha256:1d802ac01f6c2352b30e80ad15674bc6de269c70f80ea0a9a406db7e8587b62b
|
3 |
+
size 14366
|