Nexspear commited on
Commit
e147018
·
verified ·
1 Parent(s): b6ed6b4

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:aed2337f354a3655ec2a0a8abddb67b5c08f0aa8a7e01aadf3bd1e26d82ed99f
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe13b6f1bbdfd66402bf9677bf3a150e17cc1de847da4a1a4c480e09740155f1
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:50991934160159e9f50cdedc057ca78885b68388271da09ff041960f68cd1528
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8c7fa07bfc83ac5fef3626428701e44ada1944b97335074121c46e14ff6a98e
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:e28edb6b3d96f4db610a5d722a02c9867cc2d3f46e13e93415a5256c566746b9
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb68ca91ee60d94458763e6e49cbbe5d5a84e740dd8d6996e285ee8f567d027e
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
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": 0.09067131647776809,
5
  "eval_steps": 13,
6
- "global_step": 26,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -66,6 +66,28 @@
66
  "eval_samples_per_second": 20.966,
67
  "eval_steps_per_second": 10.57,
68
  "step": 26
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 4723372801916928.0,
89
  "train_batch_size": 2,
90
  "trial_name": null,
91
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.13600697471665213,
5
  "eval_steps": 13,
6
+ "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
66
  "eval_samples_per_second": 20.966,
67
  "eval_steps_per_second": 10.57,
68
  "step": 26
69
+ },
70
+ {
71
+ "epoch": 0.1046207497820401,
72
+ "grad_norm": 4.5220489501953125,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.2858,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.12205754141238012,
79
+ "grad_norm": 0.09601408988237381,
80
+ "learning_rate": 3.086582838174551e-05,
81
+ "loss": 0.006,
82
+ "step": 35
83
+ },
84
+ {
85
+ "epoch": 0.13600697471665213,
86
+ "eval_loss": 0.04691200330853462,
87
+ "eval_runtime": 5.8288,
88
+ "eval_samples_per_second": 20.759,
89
+ "eval_steps_per_second": 10.465,
90
+ "step": 39
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 7085059202875392.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null