tuanna08go commited on
Commit
18b239a
·
verified ·
1 Parent(s): 0e87f54

Training in progress, step 39, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:63c0f3c102d3c14203b3d119cb745a909dd362f38b5ae9a3881089cc800f8966
3
  size 48679352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26e8be1789f8c49496926f0791b3d61053eae453e57ed965e31d4c51619fdf66
3
  size 48679352
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5d563a0e60da5be76efc491f9ec7ea926f3a932489e0cae235f155cab0ab7dab
3
  size 25152500
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bda2d0c2eff7ef1a5ef07fb2d374e083dc015711b10e642c6b5615dc96cbf5b5
3
  size 25152500
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:03ffe07feb625055b808b0da3d9803c9bf6c86313f030e3967ef5cb0025ceb2b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4138b821d9c89fa1a1358214da9b1d8edb06b1a8e110707d57ada3bcf105a107
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e65bdb10468d12c8b6afa89fe8730e38a94a4f704431de04b0c1bf27440afce
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75c3c8ae7ddabeca3cb69703f6b35f00b9125a4c27b56ccba4ed0e4669bb5433
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": 0.16713539574126154,
5
  "eval_steps": 10,
6
- "global_step": 26,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -45,6 +45,21 @@
45
  "eval_samples_per_second": 27.389,
46
  "eval_steps_per_second": 3.424,
47
  "step": 20
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  }
49
  ],
50
  "logging_steps": 10,
@@ -64,7 +79,7 @@
64
  "attributes": {}
65
  }
66
  },
67
- "total_flos": 3.37425677156352e+16,
68
  "train_batch_size": 8,
69
  "trial_name": null,
70
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.2507030936118923,
5
  "eval_steps": 10,
6
+ "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
45
  "eval_samples_per_second": 27.389,
46
  "eval_steps_per_second": 3.424,
47
  "step": 20
48
+ },
49
+ {
50
+ "epoch": 0.19284853354760947,
51
+ "grad_norm": 0.15681762993335724,
52
+ "learning_rate": 3.705904774487396e-05,
53
+ "loss": 1.9785,
54
+ "step": 30
55
+ },
56
+ {
57
+ "epoch": 0.19284853354760947,
58
+ "eval_loss": 1.9739582538604736,
59
+ "eval_runtime": 38.2559,
60
+ "eval_samples_per_second": 27.394,
61
+ "eval_steps_per_second": 3.424,
62
+ "step": 30
63
  }
64
  ],
65
  "logging_steps": 10,
 
79
  "attributes": {}
80
  }
81
  },
82
+ "total_flos": 5.07877823348736e+16,
83
  "train_batch_size": 8,
84
  "trial_name": null,
85
  "trial_params": null