itsanastasiaminina
commited on
Training in progress, epoch 2
Browse files- model.safetensors +1 -1
- run-0/checkpoint-1126/model.safetensors +1 -1
- run-0/checkpoint-1126/optimizer.pt +1 -1
- run-0/checkpoint-1126/scheduler.pt +1 -1
- run-0/checkpoint-1126/trainer_state.json +23 -23
- run-0/checkpoint-1126/training_args.bin +1 -1
- runs/Dec08_13-30-03_3b937233628b/events.out.tfevents.1733664606.3b937233628b.23.0 +2 -2
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 498625128
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:771fe01e68dea441f9d1f001f494502b2924afcf69501e14bed2d8bbf7f7e041
|
3 |
size 498625128
|
run-0/checkpoint-1126/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 498625128
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:771fe01e68dea441f9d1f001f494502b2924afcf69501e14bed2d8bbf7f7e041
|
3 |
size 498625128
|
run-0/checkpoint-1126/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 997370106
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:221ee965008ac2eb3c0fc81d4f1565027a347d9d16b700f1317e8d9111eeb29b
|
3 |
size 997370106
|
run-0/checkpoint-1126/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 sha256:4a7033fbbed1376a1f6fd921382165bc74f54f4669790c617915759697a015e6
|
3 |
size 1064
|
run-0/checkpoint-1126/trainer_state.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
"best_model_checkpoint": "students_scores_model/run-0/checkpoint-1126",
|
4 |
"epoch": 2.0,
|
5 |
"eval_steps": 500,
|
@@ -10,41 +10,41 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.8880994671403197,
|
13 |
-
"grad_norm":
|
14 |
-
"learning_rate": 1.
|
15 |
-
"loss": 1.
|
16 |
"step": 500
|
17 |
},
|
18 |
{
|
19 |
"epoch": 1.0,
|
20 |
-
"eval_f1": 0.
|
21 |
-
"eval_loss": 1.
|
22 |
-
"eval_runtime": 37.
|
23 |
-
"eval_samples_per_second":
|
24 |
-
"eval_steps_per_second": 7.
|
25 |
"step": 563
|
26 |
},
|
27 |
{
|
28 |
"epoch": 1.7761989342806395,
|
29 |
-
"grad_norm":
|
30 |
-
"learning_rate":
|
31 |
-
"loss": 0.
|
32 |
"step": 1000
|
33 |
},
|
34 |
{
|
35 |
"epoch": 2.0,
|
36 |
-
"eval_f1": 0.
|
37 |
-
"eval_loss": 0.
|
38 |
-
"eval_runtime": 37.
|
39 |
-
"eval_samples_per_second": 59.
|
40 |
-
"eval_steps_per_second": 7.
|
41 |
"step": 1126
|
42 |
}
|
43 |
],
|
44 |
"logging_steps": 500,
|
45 |
-
"max_steps":
|
46 |
"num_input_tokens_seen": 0,
|
47 |
-
"num_train_epochs":
|
48 |
"save_steps": 500,
|
49 |
"stateful_callbacks": {
|
50 |
"TrainerControl": {
|
@@ -58,13 +58,13 @@
|
|
58 |
"attributes": {}
|
59 |
}
|
60 |
},
|
61 |
-
"total_flos":
|
62 |
"train_batch_size": 16,
|
63 |
"trial_name": null,
|
64 |
"trial_params": {
|
65 |
-
"learning_rate": 2.
|
66 |
-
"num_train_epochs":
|
67 |
"per_device_train_batch_size": 16,
|
68 |
-
"weight_decay": 0.
|
69 |
}
|
70 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.6141765793522762,
|
3 |
"best_model_checkpoint": "students_scores_model/run-0/checkpoint-1126",
|
4 |
"epoch": 2.0,
|
5 |
"eval_steps": 500,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.8880994671403197,
|
13 |
+
"grad_norm": 9.486105918884277,
|
14 |
+
"learning_rate": 1.6060239187203855e-05,
|
15 |
+
"loss": 1.0687,
|
16 |
"step": 500
|
17 |
},
|
18 |
{
|
19 |
"epoch": 1.0,
|
20 |
+
"eval_f1": 0.559496193541961,
|
21 |
+
"eval_loss": 1.0184900760650635,
|
22 |
+
"eval_runtime": 37.7502,
|
23 |
+
"eval_samples_per_second": 59.602,
|
24 |
+
"eval_steps_per_second": 7.47,
|
25 |
"step": 563
|
26 |
},
|
27 |
{
|
28 |
"epoch": 1.7761989342806395,
|
29 |
+
"grad_norm": 16.897672653198242,
|
30 |
+
"learning_rate": 9.306564171558836e-06,
|
31 |
+
"loss": 0.8626,
|
32 |
"step": 1000
|
33 |
},
|
34 |
{
|
35 |
"epoch": 2.0,
|
36 |
+
"eval_f1": 0.6141765793522762,
|
37 |
+
"eval_loss": 0.877347469329834,
|
38 |
+
"eval_runtime": 37.6032,
|
39 |
+
"eval_samples_per_second": 59.835,
|
40 |
+
"eval_steps_per_second": 7.499,
|
41 |
"step": 1126
|
42 |
}
|
43 |
],
|
44 |
"logging_steps": 500,
|
45 |
+
"max_steps": 1689,
|
46 |
"num_input_tokens_seen": 0,
|
47 |
+
"num_train_epochs": 3,
|
48 |
"save_steps": 500,
|
49 |
"stateful_callbacks": {
|
50 |
"TrainerControl": {
|
|
|
58 |
"attributes": {}
|
59 |
}
|
60 |
},
|
61 |
+
"total_flos": 4207559992768512.0,
|
62 |
"train_batch_size": 16,
|
63 |
"trial_name": null,
|
64 |
"trial_params": {
|
65 |
+
"learning_rate": 2.2813914202848873e-05,
|
66 |
+
"num_train_epochs": 3,
|
67 |
"per_device_train_batch_size": 16,
|
68 |
+
"weight_decay": 0.0012064342197859815
|
69 |
}
|
70 |
}
|
run-0/checkpoint-1126/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5368
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:86e506878344e67934428f3176c568da4bb4fdfd8b8918c71494a2c9eb08433b
|
3 |
size 5368
|
runs/Dec08_13-30-03_3b937233628b/events.out.tfevents.1733664606.3b937233628b.23.0
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 sha256:65b973d203d8ac28b889c478599817814407e9f612651b735c0761d649db2e43
|
3 |
+
size 6430
|