Paladiso commited on
Commit
c5511a1
·
verified ·
1 Parent(s): 26bda9e

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:d39c8932b64e2c0428d890501fc53d220765769671f7aa1b511af5ff1c2dca95
3
  size 4731640
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeeea8c5a8ece9a78a187e6cf569908fe3b5ca13c97bb6316871244899872ab2
3
  size 4731640
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a51506bc07186247a3561e98e3df8ec563e2a2251a28feb9fc68674da2b81c5a
3
  size 2505722
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90d4623a22399abedc37828ad000da739a23e7f25ae7debd71ca7b5ee6d980a4
3
  size 2505722
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4661b5fd937f7fc4ac64474a7a07bb8f9b1fb3a173ee34b9881690e1316152dd
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03b6cde79fbc4b5b26bf00e97c36fd2d90b042fd30be528f298072427e071121
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": 0.0022121854548806342,
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": 150.787,
74
  "eval_steps_per_second": 75.394,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 18412700958720.0,
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": 0.0033182781823209513,
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": 150.787,
74
  "eval_steps_per_second": 75.394,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.002580883030694073,
79
+ "grad_norm": 1388.295166015625,
80
+ "learning_rate": 0.00014,
81
+ "loss": 13.092,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.002949580606507512,
86
+ "grad_norm": 3225.14892578125,
87
+ "learning_rate": 0.00016,
88
+ "loss": 13.2834,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0033182781823209513,
93
+ "grad_norm": 1204.6895751953125,
94
+ "learning_rate": 0.00018,
95
+ "loss": 12.4885,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0033182781823209513,
100
+ "eval_loss": 3.274616003036499,
101
+ "eval_runtime": 7.5691,
102
+ "eval_samples_per_second": 150.876,
103
+ "eval_steps_per_second": 75.438,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 27619051438080.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null