Training in progress, epoch 1, checkpoint
Browse files
checkpoint-268/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 331462608
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:463f264c630e3e9b8302240cbd2c4a9da9e89fc367ab7d608c273f8384b9e286
|
3 |
size 331462608
|
checkpoint-268/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 662989765
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9ce9f6dd4a3bcdd71915260528f821548b8dbfc09db84008e0ee6e0fe23ccec1
|
3 |
size 662989765
|
checkpoint-268/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e0e5750fe93b7fd9aaa27579226e030b15f03f0fce2650c6aa212066ab10a364
|
3 |
size 627
|
checkpoint-268/trainer_state.json
CHANGED
@@ -10,25 +10,25 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
-
"grad_norm":
|
14 |
-
"learning_rate": 1.
|
15 |
-
"loss": 0.
|
16 |
"step": 268
|
17 |
},
|
18 |
{
|
19 |
"epoch": 1.0,
|
20 |
-
"eval_loss": 0.
|
21 |
-
"eval_matthews_correlation": 0.
|
22 |
-
"eval_runtime": 8.
|
23 |
-
"eval_samples_per_second": 122.
|
24 |
-
"eval_steps_per_second": 7.
|
25 |
"step": 268
|
26 |
}
|
27 |
],
|
28 |
"logging_steps": 500,
|
29 |
-
"max_steps":
|
30 |
"num_input_tokens_seen": 0,
|
31 |
-
"num_train_epochs":
|
32 |
"save_steps": 500,
|
33 |
"stateful_callbacks": {
|
34 |
"TrainerControl": {
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
+
"grad_norm": 9.199758529663086,
|
14 |
+
"learning_rate": 1.6000000000000003e-05,
|
15 |
+
"loss": 0.61,
|
16 |
"step": 268
|
17 |
},
|
18 |
{
|
19 |
"epoch": 1.0,
|
20 |
+
"eval_loss": 0.581834614276886,
|
21 |
+
"eval_matthews_correlation": 0.1605505486389139,
|
22 |
+
"eval_runtime": 8.5337,
|
23 |
+
"eval_samples_per_second": 122.221,
|
24 |
+
"eval_steps_per_second": 7.734,
|
25 |
"step": 268
|
26 |
}
|
27 |
],
|
28 |
"logging_steps": 500,
|
29 |
+
"max_steps": 1340,
|
30 |
"num_input_tokens_seen": 0,
|
31 |
+
"num_train_epochs": 5,
|
32 |
"save_steps": 500,
|
33 |
"stateful_callbacks": {
|
34 |
"TrainerControl": {
|
checkpoint-268/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4667
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d37219932d78f454fedda9dcf9514306d19f0518eab06266cbde4f0fbddf00de
|
3 |
size 4667
|