leixa commited on
Commit
2ccc014
·
verified ·
1 Parent(s): 4339a17

Training in progress, step 3, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:289a8668581c02376ef7ea216ff7e3d6a24f15508befbc422b8285c9db000d93
3
  size 645975704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c1788acfd304fe6e63d76bd3385b870348b5ef5f0f6212fa58f0d9c4f98c1f7
3
  size 645975704
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:92316d5f2702e245cfa048403dcb1638cfbd7842e697d152840a42f8d942d1fe
3
  size 328468404
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ca744a060cb840c10b924eb4d79ba2c0743338beed9ba821f9a6ed1e15faa56
3
  size 328468404
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8217dccdf6c6576cabb2888af5ec07df44f0930c47bca1b35f5cbf74155d99e8
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3765b1f5d912a3fb930e84c83251c1dc43e96f58af74f6eb6efe55897306767c
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8cc0702f850359504b0c41d5f4d7d6f89f03a8d466c8e18705ace84bfa7bb075
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc78163c347c258a17d5fa38a4e22e79b63c35d2cfce0e026e30c38b9ae55f80
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": 0.5714285714285714,
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,
@@ -15,6 +15,29 @@
15
  "eval_samples_per_second": 3.943,
16
  "eval_steps_per_second": 1.314,
17
  "step": 1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
18
  }
19
  ],
20
  "logging_steps": 3,
@@ -34,7 +57,7 @@
34
  "attributes": {}
35
  }
36
  },
37
- "total_flos": 1421888685342720.0,
38
  "train_batch_size": 8,
39
  "trial_name": null,
40
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1.8571428571428572,
5
  "eval_steps": 1,
6
+ "global_step": 3,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
15
  "eval_samples_per_second": 3.943,
16
  "eval_steps_per_second": 1.314,
17
  "step": 1
18
+ },
19
+ {
20
+ "epoch": 1.2857142857142856,
21
+ "eval_loss": NaN,
22
+ "eval_runtime": 0.2225,
23
+ "eval_samples_per_second": 13.483,
24
+ "eval_steps_per_second": 4.494,
25
+ "step": 2
26
+ },
27
+ {
28
+ "epoch": 1.8571428571428572,
29
+ "grad_norm": 0.0,
30
+ "learning_rate": 3e-05,
31
+ "loss": 0.0,
32
+ "step": 3
33
+ },
34
+ {
35
+ "epoch": 1.8571428571428572,
36
+ "eval_loss": NaN,
37
+ "eval_runtime": 0.232,
38
+ "eval_samples_per_second": 12.931,
39
+ "eval_steps_per_second": 4.31,
40
+ "step": 3
41
  }
42
  ],
43
  "logging_steps": 3,
 
57
  "attributes": {}
58
  }
59
  },
60
+ "total_flos": 4265666056028160.0,
61
  "train_batch_size": 8,
62
  "trial_name": null,
63
  "trial_params": null