kostiantynk commited on
Commit
2e71ac3
·
verified ·
1 Parent(s): fc3de1d

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:cece75194eb86ba2a20f65009ffdbcc4dbd0558c6219293b958122959d560f74
3
  size 108113968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4c2bad8f568426c54aae952b35bb9ba60e61d05e874d3d9025713134dd9c00e
3
  size 108113968
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:26d358807a89f1a4ab578c15df7f6458158830baa9f0e75852518fcbb3c6966e
3
  size 55549892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bf127dc0ebb3b50b6d3a871c0ede031dd390d461a7cd52d1960cb475d01974b
3
  size 55549892
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b19e870dfef70cf1b5b0457d484b2962f60d9c5c4bb5ca0898417bfd88d7fd60
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aae9d006e82da52965e04ac49ff693de4fef6907a5399da8829f5b4c7ba08fcd
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": 0.00149402390438247,
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": 18.589,
45
  "eval_steps_per_second": 9.294,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 769647606497280.0,
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": 0.00298804780876494,
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": 18.589,
45
  "eval_steps_per_second": 9.294,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.00199203187250996,
50
+ "grad_norm": 1.5795270204544067,
51
+ "learning_rate": 8e-05,
52
+ "loss": 2.7943,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.00249003984063745,
57
+ "grad_norm": 1.3678991794586182,
58
+ "learning_rate": 0.0001,
59
+ "loss": 2.6807,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.00298804780876494,
64
+ "grad_norm": 1.5033429861068726,
65
+ "learning_rate": 0.00012,
66
+ "loss": 2.8275,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.00298804780876494,
71
+ "eval_loss": 2.6760687828063965,
72
+ "eval_runtime": 45.6888,
73
+ "eval_samples_per_second": 18.517,
74
+ "eval_steps_per_second": 9.258,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 1436675532128256.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null