Training in progress, step 500
Browse files- model.safetensors +1 -1
- run-2/checkpoint-500/model.safetensors +1 -1
- run-2/checkpoint-500/optimizer.pt +1 -1
- run-2/checkpoint-500/scheduler.pt +1 -1
- run-2/checkpoint-500/trainer_state.json +12 -12
- run-2/checkpoint-500/training_args.bin +1 -1
- runs/Jan25_17-40-54_c146da53f02f/events.out.tfevents.1706206065.c146da53f02f.3236.3 +3 -0
- 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 268290900
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:defcf6e9682cffdc896d2512350e4fb7c149eed82505a5bf8d05795296415fe3
|
3 |
size 268290900
|
run-2/checkpoint-500/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:defcf6e9682cffdc896d2512350e4fb7c149eed82505a5bf8d05795296415fe3
|
3 |
size 268290900
|
run-2/checkpoint-500/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:f99e7be968d4b10b3b61a6f74a813a2671b7496611d517f032aed0d19a17d46b
|
3 |
size 536643898
|
run-2/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:bb78b1e790f49c38375a9a03add3c9373ef72cf0138709ffb96775535ef084c6
|
3 |
size 1064
|
run-2/checkpoint-500/trainer_state.json
CHANGED
@@ -10,29 +10,29 @@
|
|
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": 11.
|
18 |
"step": 318
|
19 |
},
|
20 |
{
|
21 |
"epoch": 1.57,
|
22 |
-
"learning_rate": 1.
|
23 |
-
"loss": 0.
|
24 |
"step": 500
|
25 |
}
|
26 |
],
|
27 |
"logging_steps": 500,
|
28 |
-
"max_steps":
|
29 |
-
"num_train_epochs":
|
30 |
"save_steps": 500,
|
31 |
"total_flos": 130007874759588.0,
|
32 |
"trial_name": null,
|
33 |
"trial_params": {
|
34 |
-
"alpha": 0.
|
35 |
-
"num_train_epochs":
|
36 |
-
"temperature":
|
37 |
}
|
38 |
}
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
+
"eval_accuracy": 0.6,
|
14 |
+
"eval_loss": 0.22239726781845093,
|
15 |
+
"eval_runtime": 5.4481,
|
16 |
+
"eval_samples_per_second": 569.006,
|
17 |
+
"eval_steps_per_second": 11.931,
|
18 |
"step": 318
|
19 |
},
|
20 |
{
|
21 |
"epoch": 1.57,
|
22 |
+
"learning_rate": 1.4758909853249476e-05,
|
23 |
+
"loss": 0.3484,
|
24 |
"step": 500
|
25 |
}
|
26 |
],
|
27 |
"logging_steps": 500,
|
28 |
+
"max_steps": 1908,
|
29 |
+
"num_train_epochs": 6,
|
30 |
"save_steps": 500,
|
31 |
"total_flos": 130007874759588.0,
|
32 |
"trial_name": null,
|
33 |
"trial_params": {
|
34 |
+
"alpha": 0.339174080203406,
|
35 |
+
"num_train_epochs": 6,
|
36 |
+
"temperature": 7
|
37 |
}
|
38 |
}
|
run-2/checkpoint-500/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4664
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7bcd9576316ea4b78c0edb02ef77b7b54c380e6454ae67bc0bbd59e18e13a200
|
3 |
size 4664
|
runs/Jan25_17-40-54_c146da53f02f/events.out.tfevents.1706206065.c146da53f02f.3236.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:46114877c11dabd5fcd268e5b4ecae043cfe37e1181b779db417effb4f0bae7e
|
3 |
+
size 12644
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4664
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7bcd9576316ea4b78c0edb02ef77b7b54c380e6454ae67bc0bbd59e18e13a200
|
3 |
size 4664
|