lesso commited on
Commit
911b4c9
·
verified ·
1 Parent(s): d999f45

Training in progress, step 6, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:08d238989c1816ad7e5c63534e79d383fa334b4f975b436e1def6c464111b19c
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9bda4b6404a3a66df682f92b60f9a9806fae4d1ed6204f114f11c27935e6af1
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8b024dcf82f1de236e79fab7661845e1691f2a680e7de96f171e93bb7653ae78
3
  size 160172858
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7299a8d97deea9d488458d5d22736bcb2875fe2207275d4aa3c4927a6182b30e
3
  size 160172858
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e2355e43fd44f1d9860c59f45b4d1039afaad0a42f79d076c0667863cd27cb0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73aa535a34327d8ff7e12fc9f716f24d876cbdb9f9fc9bc13d972c1b7c68dd32
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
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": 0.0007184768291222608,
5
  "eval_steps": 3,
6
- "global_step": 3,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -44,6 +44,35 @@
44
  "eval_samples_per_second": 15.432,
45
  "eval_steps_per_second": 15.432,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 492949267808256.0,
67
  "train_batch_size": 1,
68
  "trial_name": null,
69
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0014369536582445215,
5
  "eval_steps": 3,
6
+ "global_step": 6,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
44
  "eval_samples_per_second": 15.432,
45
  "eval_steps_per_second": 15.432,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.0009579691054963477,
50
+ "grad_norm": 2.6946146488189697,
51
+ "learning_rate": 8e-05,
52
+ "loss": 2.7689,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.0011974613818704347,
57
+ "grad_norm": 3.1957530975341797,
58
+ "learning_rate": 0.0001,
59
+ "loss": 2.8025,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.0014369536582445215,
64
+ "grad_norm": 2.734419584274292,
65
+ "learning_rate": 0.00012,
66
+ "loss": 1.8246,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.0014369536582445215,
71
+ "eval_loss": 2.6213483810424805,
72
+ "eval_runtime": 57.0839,
73
+ "eval_samples_per_second": 15.416,
74
+ "eval_steps_per_second": 15.416,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 985898535616512.0,
96
  "train_batch_size": 1,
97
  "trial_name": null,
98
  "trial_params": null