samoline commited on
Commit
bf377fd
·
verified ·
1 Parent(s): 0e10244

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:ee2cb9d5d94534dc27034f76e63d5f77d8f496cc20e5cff672088881541d4fa1
3
  size 42002136
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56e9793ee409a0358a25ba7b19683e4526efa464f73aed57806de1e94ee72729
3
  size 42002136
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0646f237a070a5081b40ed19b62f91888a2e7e0dbc6514152fcaba9888af6d4b
3
  size 21822612
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d425b430e2fa5cedbca1e6cec536ea4ad5dedf68ab16dca243d38c0d26d8ebbe
3
  size 21822612
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9131d73ce3e2071bf25b4ab32d9c084759e2eb8b9163e4aa04f0a79d9c8484f3
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca292942a33fa15be81e314818ff2851b6484a4703be8f6939dc3d3e46daa1ae
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": 0.0001849112426035503,
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": 12.119,
23
  "eval_steps_per_second": 12.119,
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": 23087340847104.0,
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": 0.0003698224852071006,
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": 12.119,
23
  "eval_steps_per_second": 12.119,
24
  "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.0003698224852071006,
28
+ "grad_norm": 1.3028101921081543,
29
+ "learning_rate": 4e-05,
30
+ "loss": 1.5244,
31
+ "step": 2
32
+ },
33
+ {
34
+ "epoch": 0.0003698224852071006,
35
+ "eval_loss": 1.4595413208007812,
36
+ "eval_runtime": 23.1928,
37
+ "eval_samples_per_second": 12.288,
38
+ "eval_steps_per_second": 12.288,
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": 46174681694208.0,
60
  "train_batch_size": 1,
61
  "trial_name": null,
62
  "trial_params": null