kk-aivio commited on
Commit
48b69e4
·
verified ·
1 Parent(s): e1d3c95

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 sha256:8959adaa21ee0e747134904cb3d229e4e11a9d06b07ed68cd7c88e766a908e3c
3
  size 17640136
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5b622a279289e3a15cd81401ae5c8683d3d1c8fccb600a52e3d8a9f3596e468
3
  size 17640136
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f28cc7c3c13794b8ea0a950d936ea41691f5b3f807c81f1d23611e653f17cfeb
3
  size 9568884
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc717097de3a7118fb6627b13f626793cff4ff2482c223483e6b374ef8db26a7
3
  size 9568884
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6c432173c3e03ab35f379f99e76ec96a95398876df77ad2334860facd5d9a0fd
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59870425f15b9c5b2c89fce32a5e0487ab127e9451b5309669abcf6644851b81
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": 0.0006225519441778423,
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": 49.823,
74
  "eval_steps_per_second": 24.911,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 71230531043328.0,
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": 0.0009338279162667636,
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": 49.823,
74
  "eval_steps_per_second": 24.911,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.000726310601540816,
79
+ "grad_norm": 1.152351975440979,
80
+ "learning_rate": 0.00014,
81
+ "loss": 1.9755,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0008300692589037898,
86
+ "grad_norm": 1.0372527837753296,
87
+ "learning_rate": 0.00016,
88
+ "loss": 1.7394,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0009338279162667636,
93
+ "grad_norm": 1.0806152820587158,
94
+ "learning_rate": 0.00018,
95
+ "loss": 1.8651,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0009338279162667636,
100
+ "eval_loss": 1.97881281375885,
101
+ "eval_runtime": 81.6516,
102
+ "eval_samples_per_second": 49.699,
103
+ "eval_steps_per_second": 24.849,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 109071750660096.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null