trenden commited on
Commit
0ba8373
·
verified ·
1 Parent(s): e5e4d7d

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 sha256:1d7da7095d7a05c40d20aba0cc10015e4a552d95d8f6f9db4862481fc9e9cd13
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59d5f2b78f85d99ffa4c166854a078d79355fc2e88d240e2f8be1df6a5d09c16
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:22707e288cb545584873ec2325ac2c248801b0138408f371ef9f1edba2972916
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a88f60fe0ea6cc5d81f16db177e21458990cde5803a8184d93e73b17fa8257ec
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9d3b8b9e81c8d2e9416814ea5e732e797db944d2b72486f6cf2a2de70a016fb5
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3483100185f9bb64a1baea7d0678dd8819a763e19d4dc3947a4c495c2a757eec
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": 0.004979253112033195,
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": 20.206,
45
  "eval_steps_per_second": 10.103,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 874780651683840.0,
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": 0.00995850622406639,
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": 20.206,
45
  "eval_steps_per_second": 10.103,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.006639004149377593,
50
+ "grad_norm": 0.4995167851448059,
51
+ "learning_rate": 8e-05,
52
+ "loss": 0.428,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.008298755186721992,
57
+ "grad_norm": 0.4362528920173645,
58
+ "learning_rate": 0.0001,
59
+ "loss": 0.427,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.00995850622406639,
64
+ "grad_norm": 0.35837677121162415,
65
+ "learning_rate": 0.00012,
66
+ "loss": 0.3855,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.00995850622406639,
71
+ "eval_loss": 0.37571078538894653,
72
+ "eval_runtime": 12.6561,
73
+ "eval_samples_per_second": 20.069,
74
+ "eval_steps_per_second": 10.035,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 1793300335951872.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null