rohan4s commited on
Commit
634e4f2
·
verified ·
1 Parent(s): ebf4548

Model save

Browse files
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.0,
3
+ "total_flos": 1.5808649252143104e+17,
4
+ "train_loss": 0.2831520535983145,
5
+ "train_runtime": 57.5427,
6
+ "train_samples_per_second": 35.452,
7
+ "train_steps_per_second": 1.112
8
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d08e1df1e46b3cf8376b69409047c8f2e0167bca7a1f497704aa44d725fac099
3
  size 343230128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8306099f40c156543e013174312bd3e489df5934abd74a9c78dd33a66ae34458
3
  size 343230128
runs/Dec05_15-01-57_6382b002d760/events.out.tfevents.1733411440.6382b002d760.23.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27db772e68dacdb0b914e3038d7bc3c54bc0b39c65e20b9d66721b8ea6d211d3
3
+ size 6788
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.0,
3
+ "total_flos": 1.5808649252143104e+17,
4
+ "train_loss": 0.2831520535983145,
5
+ "train_runtime": 57.5427,
6
+ "train_samples_per_second": 35.452,
7
+ "train_steps_per_second": 1.112
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.0,
5
+ "eval_steps": 100,
6
+ "global_step": 64,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.625,
13
+ "grad_norm": 83535.2265625,
14
+ "learning_rate": 0.00016875,
15
+ "loss": 0.8839,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 1.25,
20
+ "grad_norm": 66147.4140625,
21
+ "learning_rate": 0.0001375,
22
+ "loss": 0.3099,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 1.875,
27
+ "grad_norm": 33223.90234375,
28
+ "learning_rate": 0.00010625000000000001,
29
+ "loss": 0.2106,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 2.5,
34
+ "grad_norm": 184072.328125,
35
+ "learning_rate": 7.500000000000001e-05,
36
+ "loss": 0.1912,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 3.125,
41
+ "grad_norm": 86103.265625,
42
+ "learning_rate": 4.375e-05,
43
+ "loss": 0.1066,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 3.75,
48
+ "grad_norm": 14507.3759765625,
49
+ "learning_rate": 1.25e-05,
50
+ "loss": 0.0771,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 4.0,
55
+ "step": 64,
56
+ "total_flos": 1.5808649252143104e+17,
57
+ "train_loss": 0.2831520535983145,
58
+ "train_runtime": 57.5427,
59
+ "train_samples_per_second": 35.452,
60
+ "train_steps_per_second": 1.112
61
+ }
62
+ ],
63
+ "logging_steps": 10,
64
+ "max_steps": 64,
65
+ "num_input_tokens_seen": 0,
66
+ "num_train_epochs": 4,
67
+ "save_steps": 100,
68
+ "stateful_callbacks": {
69
+ "TrainerControl": {
70
+ "args": {
71
+ "should_epoch_stop": false,
72
+ "should_evaluate": false,
73
+ "should_log": false,
74
+ "should_save": true,
75
+ "should_training_stop": true
76
+ },
77
+ "attributes": {}
78
+ }
79
+ },
80
+ "total_flos": 1.5808649252143104e+17,
81
+ "train_batch_size": 32,
82
+ "trial_name": null,
83
+ "trial_params": null
84
+ }