shivanandmn commited on
Commit
4a9a90c
·
verified ·
1 Parent(s): 75c4922

Training in progress, step 10

Browse files
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "total_flos": 2.045152830947328e+16,
4
+ "train_loss": 220573833625.6,
5
+ "train_runtime": 1766.7401,
6
+ "train_samples_per_second": 0.724,
7
+ "train_steps_per_second": 0.006
8
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b308d39db4eefa68478ce22350f90b0f39c816409d7717f121e4ad03749d4651
3
- size 1694271776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37b429de8238eeb2e987f0c86362b1b6dfbe5110071efb37b9cdfd49dc375c4d
3
+ size 1694308624
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "total_flos": 2.045152830947328e+16,
4
+ "train_loss": 220573833625.6,
5
+ "train_runtime": 1766.7401,
6
+ "train_samples_per_second": 0.724,
7
+ "train_steps_per_second": 0.006
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 10,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.2,
13
+ "grad_norm": NaN,
14
+ "learning_rate": 4e-05,
15
+ "loss": 1102869168128.0,
16
+ "step": 2
17
+ },
18
+ {
19
+ "epoch": 0.4,
20
+ "grad_norm": NaN,
21
+ "learning_rate": 8e-05,
22
+ "loss": 0.0,
23
+ "step": 4
24
+ },
25
+ {
26
+ "epoch": 0.6,
27
+ "grad_norm": NaN,
28
+ "learning_rate": 9.045084971874738e-05,
29
+ "loss": 0.0,
30
+ "step": 6
31
+ },
32
+ {
33
+ "epoch": 0.8,
34
+ "grad_norm": NaN,
35
+ "learning_rate": 3.4549150281252636e-05,
36
+ "loss": 0.0,
37
+ "step": 8
38
+ },
39
+ {
40
+ "epoch": 1.0,
41
+ "grad_norm": NaN,
42
+ "learning_rate": 0.0,
43
+ "loss": 0.0,
44
+ "step": 10
45
+ },
46
+ {
47
+ "epoch": 1.0,
48
+ "step": 10,
49
+ "total_flos": 2.045152830947328e+16,
50
+ "train_loss": 220573833625.6,
51
+ "train_runtime": 1766.7401,
52
+ "train_samples_per_second": 0.724,
53
+ "train_steps_per_second": 0.006
54
+ }
55
+ ],
56
+ "logging_steps": 2,
57
+ "max_steps": 10,
58
+ "num_input_tokens_seen": 0,
59
+ "num_train_epochs": 9223372036854775807,
60
+ "save_steps": 500,
61
+ "stateful_callbacks": {
62
+ "TrainerControl": {
63
+ "args": {
64
+ "should_epoch_stop": false,
65
+ "should_evaluate": false,
66
+ "should_log": false,
67
+ "should_save": true,
68
+ "should_training_stop": true
69
+ },
70
+ "attributes": {}
71
+ }
72
+ },
73
+ "total_flos": 2.045152830947328e+16,
74
+ "train_batch_size": 2,
75
+ "trial_name": null,
76
+ "trial_params": null
77
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c103b82f01b1c194dfc6eb14a749ccbb045616322476352720ce6320fba6e9ed
3
  size 5560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e90a9a376f383bb43f25543d4d2b3918313ccd7d12ea3b3128c6def7833342b
3
  size 5560