nat-hunt commited on
Commit
d4734b7
·
verified ·
1 Parent(s): b630991

Training in progress, step 42, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2e97685a680e00eb243b2de6164e557cb4cbaae2aeaddcf05007c29a4870d9aa
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f913e66984e9002a72c226282e0169ab8f65a6d420688ed0650b567b3176062
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ecb20e707a68acd451bf36505255106de04659955d35fb24ab09bf69f81228d6
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a779760d1eb5cb4a49a7436c485300d22a71abea2397ce87c6b1aa455274ef47
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5b7272202dc9e52e095afc89ac33aefc2356f157fa52f53e471a837339830a02
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93077e4de44f142f2a5ac374e93b3534575c13e18a3b475d644f8f3c2192c4e7
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7cf140526b08395dbd0793ca343f0f70c5fb866a714c27208d9b9b1ce1a60172
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79af33a7cc5e89926792af60c545e28f6f3569216a6e1a04e51a93b6477fd5cc
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": 0.0045731084888326326,
5
  "eval_steps": 14,
6
- "global_step": 28,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -45,6 +45,28 @@
45
  "eval_samples_per_second": 26.063,
46
  "eval_steps_per_second": 13.031,
47
  "step": 28
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  }
49
  ],
50
  "logging_steps": 10,
@@ -64,7 +86,7 @@
64
  "attributes": {}
65
  }
66
  },
67
- "total_flos": 5049122650324992.0,
68
  "train_batch_size": 2,
69
  "trial_name": null,
70
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.006859662733248948,
5
  "eval_steps": 14,
6
+ "global_step": 42,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
45
  "eval_samples_per_second": 26.063,
46
  "eval_steps_per_second": 13.031,
47
  "step": 28
48
+ },
49
+ {
50
+ "epoch": 0.0048997590951778205,
51
+ "grad_norm": 2.9848153591156006,
52
+ "learning_rate": 0.0001,
53
+ "loss": 9.679,
54
+ "step": 30
55
+ },
56
+ {
57
+ "epoch": 0.0065330121269037604,
58
+ "grad_norm": 3.4589827060699463,
59
+ "learning_rate": 4.12214747707527e-05,
60
+ "loss": 9.7902,
61
+ "step": 40
62
+ },
63
+ {
64
+ "epoch": 0.006859662733248948,
65
+ "eval_loss": 2.3425304889678955,
66
+ "eval_runtime": 98.9387,
67
+ "eval_samples_per_second": 26.057,
68
+ "eval_steps_per_second": 13.028,
69
+ "step": 42
70
  }
71
  ],
72
  "logging_steps": 10,
 
86
  "attributes": {}
87
  }
88
  },
89
+ "total_flos": 7573683975487488.0,
90
  "train_batch_size": 2,
91
  "trial_name": null,
92
  "trial_params": null