Best000 commited on
Commit
f7089c9
·
verified ·
1 Parent(s): 43e9eb9

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 sha256:4d3bd256295fce386763dedb8b27c3d202507860b1bf1ab839604a60c4c9f7a7
3
  size 125248064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fab8fc7f3d0cf99b70b9dc29e85c9c63574c958c0664fdb5cf7d7adb0f0aed76
3
  size 125248064
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f30d5448e2c6d604acd1a2857fd2ffc6c5a5f0dcb9a12f3e25d073663abd1dce
3
  size 64219860
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63e1eb228479a79a9fd5634a553d5832c0ee49d56cdd4c37c3090353bb218415
3
  size 64219860
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6fac8dc3559aa6a81370bb141163d5dc06aeeb8795a754c1c7ff70e9049a5afd
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07d77b60a4a6ac9b1290011cfbb000725f2f3c555f2baada62884afb493a185f
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": 0.004246284501061571,
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": 9.461,
45
  "eval_steps_per_second": 4.73,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 1899734583214080.0,
67
  "train_batch_size": 2,
68
  "trial_name": null,
69
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.008492569002123142,
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": 9.461,
45
  "eval_steps_per_second": 4.73,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.005661712668082095,
50
+ "grad_norm": 0.3271850347518921,
51
+ "learning_rate": 8e-05,
52
+ "loss": 6.2798,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.007077140835102618,
57
+ "grad_norm": 0.4017261266708374,
58
+ "learning_rate": 0.0001,
59
+ "loss": 6.1845,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.008492569002123142,
64
+ "grad_norm": 0.4634651839733124,
65
+ "learning_rate": 0.00012,
66
+ "loss": 6.5431,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.008492569002123142,
71
+ "eval_loss": 1.5396825075149536,
72
+ "eval_runtime": 31.5091,
73
+ "eval_samples_per_second": 9.458,
74
+ "eval_steps_per_second": 4.729,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 3799469166428160.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null