cwaud commited on
Commit
7721fd0
1 Parent(s): b1afca3

Training in progress, step 9, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9bc9e81363084991114af7e7059f99c25c341905df9fff4c16bbe92da6313109
3
  size 39256456
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e47923228f056b4ca9df7f75e814ac91078483f964054771cd79a5fa1f1c5592
3
  size 39256456
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2273e9428947fbb8f752eec0ee6edfca96678774550bc64026373f5462a77a56
3
  size 20632826
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c737bd224de7e40e2bb3627be1e1ec43a12a4bbff2a8013b69d2fa21131909c
3
  size 20632826
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f62bf5dc3982cb724ba2d66b6ebf6a8ca8dd5328c3bcb309df49a4d1148029b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09ed0cc872e01be7a92a9bfaa1687ff8effd6e3620425e7bdfc19489d2a395fb
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
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": 0.0009859097071026578,
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,
@@ -73,6 +73,35 @@
73
  "eval_samples_per_second": 13.18,
74
  "eval_steps_per_second": 6.592,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 501714738216960.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0014788645606539869,
5
  "eval_steps": 3,
6
+ "global_step": 9,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
73
  "eval_samples_per_second": 13.18,
74
  "eval_steps_per_second": 6.592,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0011502279916197674,
79
+ "grad_norm": 1.5537827014923096,
80
+ "learning_rate": 0.00014,
81
+ "loss": 1.656,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.001314546276136877,
86
+ "grad_norm": 0.7878876328468323,
87
+ "learning_rate": 0.00016,
88
+ "loss": 1.6709,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0014788645606539869,
93
+ "grad_norm": 1.0037742853164673,
94
+ "learning_rate": 0.00018,
95
+ "loss": 1.458,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0014788645606539869,
100
+ "eval_loss": 1.6837400197982788,
101
+ "eval_runtime": 194.1291,
102
+ "eval_samples_per_second": 13.203,
103
+ "eval_steps_per_second": 6.604,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 783164469411840.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null