Paladiso commited on
Commit
3f520e4
·
verified ·
1 Parent(s): 5ec529a

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 sha256:4d50a34006a7526542b247eff1bb03da3c33193232c24fc47f79b7f27f30a3bb
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06a6ae27d8e95d396d133047627f279ccd51291a3e1b11aa8266f356cc85bdb4
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f57756c747bcbb4a63bb084269c2d1cefc20308430076cfd1e8eb391e6c4c724
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1795b0de1a5747ae277c9a0adb8ad1d19877c944da3123984a05836ad3b34ab3
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:05531349f6e2487143a7251afc8a645033108171aa1d481234785012b46d00ef
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88471f2b3b1e4c205d9505ad6de006cb23590a0562a633e21bbcb4ef69f0d7ee
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": 0.005010438413361169,
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,
@@ -65,6 +65,35 @@
65
  "eval_samples_per_second": 15.874,
66
  "eval_steps_per_second": 7.953,
67
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
68
  }
69
  ],
70
  "logging_steps": 1,
@@ -84,7 +113,7 @@
84
  "attributes": {}
85
  }
86
  },
87
- "total_flos": 1052065728036864.0,
88
  "train_batch_size": 2,
89
  "trial_name": null,
90
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.007515657620041753,
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,
 
65
  "eval_samples_per_second": 15.874,
66
  "eval_steps_per_second": 7.953,
67
  "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.005845511482254697,
71
+ "grad_norm": 24.93547821044922,
72
+ "learning_rate": 0.00014,
73
+ "loss": 12.2567,
74
+ "step": 7
75
+ },
76
+ {
77
+ "epoch": 0.006680584551148226,
78
+ "grad_norm": 22.281667709350586,
79
+ "learning_rate": 0.00016,
80
+ "loss": 11.7375,
81
+ "step": 8
82
+ },
83
+ {
84
+ "epoch": 0.007515657620041753,
85
+ "grad_norm": 15.962149620056152,
86
+ "learning_rate": 0.00018,
87
+ "loss": 10.4534,
88
+ "step": 9
89
+ },
90
+ {
91
+ "epoch": 0.007515657620041753,
92
+ "eval_loss": 2.6566338539123535,
93
+ "eval_runtime": 32.5283,
94
+ "eval_samples_per_second": 15.525,
95
+ "eval_steps_per_second": 7.778,
96
+ "step": 9
97
  }
98
  ],
99
  "logging_steps": 1,
 
113
  "attributes": {}
114
  }
115
  },
116
+ "total_flos": 1578098592055296.0,
117
  "train_batch_size": 2,
118
  "trial_name": null,
119
  "trial_params": null