samoline commited on
Commit
18c0a5e
·
verified ·
1 Parent(s): 36d501b

Training in progress, step 2, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:38eb5480cae319a75382ccbce43eb01aafde542ffec31576fd991b771a0a6840
3
  size 25473712
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fa8d99d85d681a75dcb42230a0436964b42d7fbee9cf74edb0e5f57b6c57395
3
  size 25473712
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ed38d87182aeb93beacce2b73b47a63142786e2cb2c3e0782dbc6466e3ca64f8
3
  size 13328068
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:706883d2064d2b079d796a76a76ea8f236ac37098bdba6204f0766b69d46f59c
3
  size 13328068
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d71101f4c3ae883788431ce798ca50721aa84385e6585176cbcee307f39c8235
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84f4e0da8f2e3bb2bdd9d01351febac4891b9a24b89f71462a16e5c37a582783
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:764cf599d0b83c5d302be0978d09e435a466a8511dc1f7e86d5ee3704818d46f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2972d8cacb091bd0e98bfff54b2e4933301753087ce149a9bf9a205a5e2d795
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 7.105300554213443e-05,
5
  "eval_steps": 1,
6
- "global_step": 1,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -22,6 +22,21 @@
22
  "eval_samples_per_second": 10.474,
23
  "eval_steps_per_second": 10.474,
24
  "step": 1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
25
  }
26
  ],
27
  "logging_steps": 1,
@@ -36,12 +51,12 @@
36
  "should_evaluate": false,
37
  "should_log": false,
38
  "should_save": true,
39
- "should_training_stop": false
40
  },
41
  "attributes": {}
42
  }
43
  },
44
- "total_flos": 20462162411520.0,
45
  "train_batch_size": 1,
46
  "trial_name": null,
47
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.00014210601108426886,
5
  "eval_steps": 1,
6
+ "global_step": 2,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
22
  "eval_samples_per_second": 10.474,
23
  "eval_steps_per_second": 10.474,
24
  "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.00014210601108426886,
28
+ "grad_norm": 0.148416206240654,
29
+ "learning_rate": 4e-05,
30
+ "loss": 1.2654,
31
+ "step": 2
32
+ },
33
+ {
34
+ "epoch": 0.00014210601108426886,
35
+ "eval_loss": 1.040054202079773,
36
+ "eval_runtime": 71.2436,
37
+ "eval_samples_per_second": 10.401,
38
+ "eval_steps_per_second": 10.401,
39
+ "step": 2
40
  }
41
  ],
42
  "logging_steps": 1,
 
51
  "should_evaluate": false,
52
  "should_log": false,
53
  "should_save": true,
54
+ "should_training_stop": true
55
  },
56
  "attributes": {}
57
  }
58
  },
59
+ "total_flos": 40924324823040.0,
60
  "train_batch_size": 1,
61
  "trial_name": null,
62
  "trial_params": null