itsanastasiaminina commited on
Commit
93d2d3d
·
verified ·
1 Parent(s): f8b9875

Training in progress, epoch 2

Browse files
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7a5431a13f3394099b8d4ae13c75e073cd81b18a4b641cdc4454fb070b575134
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 sha256:48e3134343bbdcbaa2d0e515e448ba031cd266949636f85cccb6bf345f14ac59
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 sha256:32fdabad5a7c43b58ebf4e0377335271538dcd50c163715b561dde06d4217241
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 sha256:638bb34837054d7ce11745cb0ee2d34d0fef98955b259d1225512652a3d97593
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": 0.608105758140891,
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": 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
  "epoch": 2.0,
36
- "eval_f1": 0.608105758140891,
37
- "eval_loss": 0.8914819955825806,
38
- "eval_runtime": 38.5981,
39
- "eval_samples_per_second": 58.293,
40
- "eval_steps_per_second": 7.306,
41
  "step": 1126
42
  }
43
  ],
44
  "logging_steps": 500,
45
- "max_steps": 1126,
46
  "num_input_tokens_seen": 0,
47
- "num_train_epochs": 2,
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": true
57
  },
58
  "attributes": {}
59
  }
@@ -62,9 +62,9 @@
62
  "train_batch_size": 16,
63
  "trial_name": null,
64
  "trial_params": {
65
- "learning_rate": 1.386840125575052e-05,
66
- "num_train_epochs": 2,
67
  "per_device_train_batch_size": 16,
68
- "weight_decay": 0.010177242974562553
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:b18f3514f71ccee1e74cafceb4cbd84c3f4bda80bd3c08496a257871a520e8eb
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 sha256:451571a3bb4df7bf9b5b7d7fac3fa5df59a6b7fd14f20effb3f7c2361e08708e
3
- size 5900
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94897b1553c80b0d65888b8e664fb3a6ad62dc3aceab4d7d97de979095b887e1
3
+ size 6428