error577 commited on
Commit
0374c16
·
verified ·
1 Parent(s): 089a655

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:ab80569229851ef850ebd7615a9d6b503a27bdf7d9215e786db688744b620de5
3
  size 42002136
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79f4856409303858a9b89be06e10f98c3901782159979adea54d0f4ac9774ae0
3
  size 42002136
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d49df34ac12930a27b6c1c60b5485de770d24907d44643cb11bed5d4e803f985
3
  size 21822612
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04d1dcad86b50247cc69eaee9c5539becb0d3931e2bb5da25e8c22efcb2e98e7
3
  size 21822612
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6872307f4470a047155c6b916b2c9040d688e2f96562192a9d5c5fb6108984b7
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d630673412c6de6acee59698bd9ad7c4d72310786cdfbf27cc607355a7f4466d
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": 0.0012205355099549928,
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": 5.372,
38
  "eval_steps_per_second": 5.372,
39
  "step": 2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 1,
@@ -56,7 +78,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 265509050253312.0,
60
  "train_batch_size": 1,
61
  "trial_name": null,
62
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0024410710199099855,
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": 5.372,
38
  "eval_steps_per_second": 5.372,
39
  "step": 2
40
+ },
41
+ {
42
+ "epoch": 0.0018308032649324891,
43
+ "grad_norm": 2.6212241649627686,
44
+ "learning_rate": 6e-05,
45
+ "loss": 3.2509,
46
+ "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.0024410710199099855,
50
+ "grad_norm": 2.9304161071777344,
51
+ "learning_rate": 8e-05,
52
+ "loss": 2.8665,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.0024410710199099855,
57
+ "eval_loss": 3.6247403621673584,
58
+ "eval_runtime": 128.9195,
59
+ "eval_samples_per_second": 5.352,
60
+ "eval_steps_per_second": 5.352,
61
+ "step": 4
62
  }
63
  ],
64
  "logging_steps": 1,
 
78
  "attributes": {}
79
  }
80
  },
81
+ "total_flos": 565649715757056.0,
82
  "train_batch_size": 1,
83
  "trial_name": null,
84
  "trial_params": null