davidmezzetti commited on
Commit
f96a8df
·
1 Parent(s): 172dfb2

Update model

Browse files
Files changed (3) hide show
  1. pytorch_model.bin +1 -1
  2. trainer_state.json +18 -18
  3. training_args.bin +1 -1
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c135824e187b525d6855ce8246a7ebd14c3d536f4eda9570ffaa6bd2e29a9cd
3
  size 242085627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6859d15da3455c9001dabd7f4af2704eed996acb0f5d507e52a9c5d05000c71
3
  size 242085627
trainer_state.json CHANGED
@@ -2,42 +2,42 @@
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
  "epoch": 5.0,
5
- "global_step": 1625,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
9
  "log_history": [
10
  {
11
- "epoch": 1.54,
12
- "learning_rate": 3.461538461538462e-05,
13
- "loss": 0.8815,
14
  "step": 500
15
  },
16
  {
17
- "epoch": 3.08,
18
- "learning_rate": 1.923076923076923e-05,
19
- "loss": 0.0468,
20
  "step": 1000
21
  },
22
  {
23
- "epoch": 4.62,
24
- "learning_rate": 3.846153846153847e-06,
25
- "loss": 0.0188,
26
  "step": 1500
27
  },
28
  {
29
  "epoch": 5.0,
30
- "step": 1625,
31
- "total_flos": 28064391364608.0,
32
- "train_loss": 0.29253782419057994,
33
- "train_runtime": 119.4115,
34
- "train_samples_per_second": 54.434,
35
- "train_steps_per_second": 13.608
36
  }
37
  ],
38
- "max_steps": 1625,
39
  "num_train_epochs": 5,
40
- "total_flos": 28064391364608.0,
41
  "trial_name": null,
42
  "trial_params": null
43
  }
 
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
  "epoch": 5.0,
5
+ "global_step": 1750,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
9
  "log_history": [
10
  {
11
+ "epoch": 1.43,
12
+ "learning_rate": 3.571428571428572e-05,
13
+ "loss": 0.8911,
14
  "step": 500
15
  },
16
  {
17
+ "epoch": 2.86,
18
+ "learning_rate": 2.1428571428571428e-05,
19
+ "loss": 0.0424,
20
  "step": 1000
21
  },
22
  {
23
+ "epoch": 4.29,
24
+ "learning_rate": 7.142857142857143e-06,
25
+ "loss": 0.0178,
26
  "step": 1500
27
  },
28
  {
29
  "epoch": 5.0,
30
+ "step": 1750,
31
+ "total_flos": 29865071738880.0,
32
+ "train_loss": 0.2740174835750035,
33
+ "train_runtime": 117.3789,
34
+ "train_samples_per_second": 59.636,
35
+ "train_steps_per_second": 14.909
36
  }
37
  ],
38
+ "max_steps": 1750,
39
  "num_train_epochs": 5,
40
+ "total_flos": 29865071738880.0,
41
  "trial_name": null,
42
  "trial_params": null
43
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8ccca9e37b90e11943f8b25eff52e849576ba865d3f8ea44746a46c919dbb86a
3
  size 2991
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:147a6331b1ec4a75f42ae1cab8a3f6ff2ed299d57d621b6843321f34a0aa7164
3
  size 2991