lesso07 commited on
Commit
3bf09bc
·
verified ·
1 Parent(s): 66cef6b

Training in progress, step 4, 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:d6fffb99cc0d723db90286bb6bae115b5de43343d0247e89f1cd27f2178cfb39
3
  size 250422888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90771bc3e40a6dff1cf2eb79b7b1c1c822c7798893018318d6cdfe647152e120
3
  size 250422888
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f4e04ac648fb570da420d54459c512c0fbcb20e4ce66283187d96a7ddf381d68
3
  size 501028338
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1530c86ce1f8ba52479255444aca6ad3cb9d0dec246662302d3700e4a19a5499
3
  size 501028338
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b9b3fdcbdd84a2b1b7402d4d8e05d7e18bd2d0137eb2ed3450f26874276aece0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e530f1b21e6744a0cf36a8fe08347c58f3b9d879634a50ea15adbcbf7076b2f
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a2972d8cacb091bd0e98bfff54b2e4933301753087ce149a9bf9a205a5e2d795
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:917587e2c0a52fd7c3d6680e02e388879c84c249a215f319208d6a9951b36ba9
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": 0.0016849199663016006,
5
  "eval_steps": 2,
6
- "global_step": 2,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -37,6 +37,28 @@
37
  "eval_samples_per_second": 5.75,
38
  "eval_steps_per_second": 2.875,
39
  "step": 2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 1,
@@ -56,7 +78,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 1269557939404800.0,
60
  "train_batch_size": 2,
61
  "trial_name": null,
62
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.003369839932603201,
5
  "eval_steps": 2,
6
+ "global_step": 4,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
37
  "eval_samples_per_second": 5.75,
38
  "eval_steps_per_second": 2.875,
39
  "step": 2
40
+ },
41
+ {
42
+ "epoch": 0.002527379949452401,
43
+ "grad_norm": 13.229546546936035,
44
+ "learning_rate": 6e-05,
45
+ "loss": 21.6802,
46
+ "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.003369839932603201,
50
+ "grad_norm": 22.8873348236084,
51
+ "learning_rate": 8e-05,
52
+ "loss": 18.9218,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.003369839932603201,
57
+ "eval_loss": 4.732216835021973,
58
+ "eval_runtime": 87.2134,
59
+ "eval_samples_per_second": 5.733,
60
+ "eval_steps_per_second": 2.867,
61
+ "step": 4
62
  }
63
  ],
64
  "logging_steps": 1,
 
78
  "attributes": {}
79
  }
80
  },
81
+ "total_flos": 2539115878809600.0,
82
  "train_batch_size": 2,
83
  "trial_name": null,
84
  "trial_params": null