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/Dec09_12-41-02_ea67bac3fd95/events.out.tfevents.1733748065.ea67bac3fd95.23.0 +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:a2ea6143365bb1b955914e1894d1a9de3c8e82b53b2d92377c19fa703ff614cb
|
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:a2ea6143365bb1b955914e1894d1a9de3c8e82b53b2d92377c19fa703ff614cb
|
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 sha256:7c2c34c513741289abb3837dcc8966686155fa1262d9fe69ff4d284ac6a5325d
|
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 sha256:304bffdafb78d4cc2eea97bbb833d0fc56b970593a1ae6a8403c8b1461f0f4f8
|
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":
|
15 |
-
"loss": 1.
|
16 |
"step": 500
|
17 |
},
|
18 |
{
|
19 |
"epoch": 1.0,
|
20 |
-
"eval_f1": 0.
|
21 |
-
"eval_loss": 0.
|
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":
|
39 |
-
"eval_samples_per_second":
|
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": {
|
@@ -53,7 +53,7 @@
|
|
53 |
"should_evaluate": false,
|
54 |
"should_log": false,
|
55 |
"should_save": true,
|
56 |
-
"should_training_stop":
|
57 |
},
|
58 |
"attributes": {}
|
59 |
}
|
@@ -62,9 +62,9 @@
|
|
62 |
"train_batch_size": 16,
|
63 |
"trial_name": null,
|
64 |
"trial_params": {
|
65 |
-
"learning_rate": 1.
|
66 |
-
"num_train_epochs":
|
67 |
"per_device_train_batch_size": 16,
|
68 |
-
"weight_decay": 0.
|
69 |
}
|
70 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.6070480622856711,
|
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": 15.162298202514648,
|
14 |
+
"learning_rate": 1.1081212788560944e-05,
|
15 |
+
"loss": 1.0807,
|
16 |
"step": 500
|
17 |
},
|
18 |
{
|
19 |
"epoch": 1.0,
|
20 |
+
"eval_f1": 0.5653313080683391,
|
21 |
+
"eval_loss": 0.9786226153373718,
|
22 |
+
"eval_runtime": 37.7159,
|
23 |
+
"eval_samples_per_second": 59.657,
|
24 |
+
"eval_steps_per_second": 7.477,
|
25 |
"step": 563
|
26 |
},
|
27 |
{
|
28 |
"epoch": 1.7761989342806395,
|
29 |
+
"grad_norm": 24.097002029418945,
|
30 |
+
"learning_rate": 6.421325156701843e-06,
|
31 |
+
"loss": 0.8868,
|
32 |
"step": 1000
|
33 |
},
|
34 |
{
|
35 |
"epoch": 2.0,
|
36 |
+
"eval_f1": 0.6070480622856711,
|
37 |
+
"eval_loss": 0.8847860097885132,
|
38 |
+
"eval_runtime": 37.644,
|
39 |
+
"eval_samples_per_second": 59.771,
|
40 |
+
"eval_steps_per_second": 7.491,
|
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": {
|
|
|
53 |
"should_evaluate": false,
|
54 |
"should_log": false,
|
55 |
"should_save": true,
|
56 |
+
"should_training_stop": false
|
57 |
},
|
58 |
"attributes": {}
|
59 |
}
|
|
|
62 |
"train_batch_size": 16,
|
63 |
"trial_name": null,
|
64 |
"trial_params": {
|
65 |
+
"learning_rate": 1.5741100420420047e-05,
|
66 |
+
"num_train_epochs": 3,
|
67 |
"per_device_train_batch_size": 16,
|
68 |
+
"weight_decay": 0.06367619176381757
|
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 sha256:2d79a0a1b1999dd0f4d771c0a4c6c2e334edf8b223fe42e75cbf50a67fc6c2de
|
3 |
size 5368
|
runs/Dec09_12-41-02_ea67bac3fd95/events.out.tfevents.1733748065.ea67bac3fd95.23.0
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 sha256:94897b1553c80b0d65888b8e664fb3a6ad62dc3aceab4d7d97de979095b887e1
|
3 |
+
size 6428
|