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/rng_state.pth +1 -1
- run-0/checkpoint-1126/scheduler.pt +1 -1
- run-0/checkpoint-1126/trainer_state.json +19 -28
- run-0/checkpoint-1126/training_args.bin +1 -1
- runs/Dec08_21-54-18_6ff5f1d99a72/events.out.tfevents.1733694862.6ff5f1d99a72.23.0 +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 sha256:48e3134343bbdcbaa2d0e515e448ba031cd266949636f85cccb6bf345f14ac59
|
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 sha256:48e3134343bbdcbaa2d0e515e448ba031cd266949636f85cccb6bf345f14ac59
|
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 sha256:32fdabad5a7c43b58ebf4e0377335271538dcd50c163715b561dde06d4217241
|
3 |
size 997370106
|
run-0/checkpoint-1126/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:eed3091eb761444c21e8ad4810c28637b0a0c9c3103bbcc5f996e34a658356bc
|
3 |
size 14244
|
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 sha256:638bb34837054d7ce11745cb0ee2d34d0fef98955b259d1225512652a3d97593
|
3 |
size 1064
|
run-0/checkpoint-1126/trainer_state.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "students_scores_model/run-0/checkpoint-
|
4 |
"epoch": 2.0,
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 1126,
|
@@ -10,41 +10,32 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.8880994671403197,
|
13 |
-
"grad_norm":
|
14 |
-
"learning_rate":
|
15 |
-
"loss": 1.
|
16 |
"step": 500
|
17 |
},
|
18 |
{
|
19 |
"epoch": 1.0,
|
20 |
-
"eval_f1": 0.
|
21 |
-
"eval_loss":
|
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": 0.6141765793522762,
|
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":
|
46 |
"num_input_tokens_seen": 0,
|
47 |
-
"num_train_epochs":
|
48 |
"save_steps": 500,
|
49 |
"stateful_callbacks": {
|
50 |
"TrainerControl": {
|
@@ -53,7 +44,7 @@
|
|
53 |
"should_evaluate": false,
|
54 |
"should_log": false,
|
55 |
"should_save": true,
|
56 |
-
"should_training_stop":
|
57 |
},
|
58 |
"attributes": {}
|
59 |
}
|
@@ -62,9 +53,9 @@
|
|
62 |
"train_batch_size": 16,
|
63 |
"trial_name": null,
|
64 |
"trial_params": {
|
65 |
-
"learning_rate":
|
66 |
-
"num_train_epochs":
|
67 |
"per_device_train_batch_size": 16,
|
68 |
-
"weight_decay": 0.
|
69 |
}
|
70 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.568809428898138,
|
3 |
+
"best_model_checkpoint": "students_scores_model/run-0/checkpoint-563",
|
4 |
"epoch": 2.0,
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 1126,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.8880994671403197,
|
13 |
+
"grad_norm": 33.89450454711914,
|
14 |
+
"learning_rate": 7.71014137309043e-06,
|
15 |
+
"loss": 1.0858,
|
16 |
"step": 500
|
17 |
},
|
18 |
{
|
19 |
"epoch": 1.0,
|
20 |
+
"eval_f1": 0.568809428898138,
|
21 |
+
"eval_loss": 0.9511491060256958,
|
22 |
+
"eval_runtime": 37.4937,
|
23 |
+
"eval_samples_per_second": 60.01,
|
24 |
+
"eval_steps_per_second": 7.521,
|
25 |
"step": 563
|
26 |
},
|
27 |
{
|
28 |
"epoch": 1.7761989342806395,
|
29 |
+
"grad_norm": 20.078083038330078,
|
30 |
+
"learning_rate": 1.5518814904303424e-06,
|
31 |
+
"loss": 0.876,
|
32 |
"step": 1000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
33 |
}
|
34 |
],
|
35 |
"logging_steps": 500,
|
36 |
+
"max_steps": 1126,
|
37 |
"num_input_tokens_seen": 0,
|
38 |
+
"num_train_epochs": 2,
|
39 |
"save_steps": 500,
|
40 |
"stateful_callbacks": {
|
41 |
"TrainerControl": {
|
|
|
44 |
"should_evaluate": false,
|
45 |
"should_log": false,
|
46 |
"should_save": true,
|
47 |
+
"should_training_stop": true
|
48 |
},
|
49 |
"attributes": {}
|
50 |
}
|
|
|
53 |
"train_batch_size": 16,
|
54 |
"trial_name": null,
|
55 |
"trial_params": {
|
56 |
+
"learning_rate": 1.386840125575052e-05,
|
57 |
+
"num_train_epochs": 2,
|
58 |
"per_device_train_batch_size": 16,
|
59 |
+
"weight_decay": 0.010177242974562553
|
60 |
}
|
61 |
}
|
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:b18f3514f71ccee1e74cafceb4cbd84c3f4bda80bd3c08496a257871a520e8eb
|
3 |
size 5368
|
runs/Dec08_21-54-18_6ff5f1d99a72/events.out.tfevents.1733694862.6ff5f1d99a72.23.0
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:d5737c556ae1cbcf28dd6308712f2d4176e5cd3f413935519c93a3983639583d
|
3 |
+
size 6111
|