great0001 commited on
Commit
c11fb41
·
verified ·
1 Parent(s): efe8f67

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 sha256:6357ef3bb978490cdb896478d3b3e0f68e660978ffa90078c9f1c41c25adb93d
3
  size 12609416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:519fd91a95038db41cf0aa0be385b38305ae8c47b7050bb526018769f3b052e8
3
  size 12609416
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:968493d473a117a7e685e2f18f667bb752417b474c4f04bbdfbd69671305a62b
3
  size 6615034
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15f016159e7e510d854403029f81b075cce1be4e9360688f56fe2aae0125b7f4
3
  size 6615034
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e510698194b4ff1a492607da5be9233171bdcf09e53d24cdea4f14a080c32e34
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:519f25b43551ebd208fc8e91efe3efb9ed6b1ef480ba8fcb9b6b0c22698c9e5b
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": 0.0002987043697960098,
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": 81.376,
74
  "eval_steps_per_second": 40.688,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 48795274444800.0,
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": 0.0004480565546940147,
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": 81.376,
74
  "eval_steps_per_second": 40.688,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0003484884314286781,
79
+ "grad_norm": 6.967427730560303,
80
+ "learning_rate": 0.00014,
81
+ "loss": 11.1381,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0003982724930613464,
86
+ "grad_norm": 6.143828868865967,
87
+ "learning_rate": 0.00016,
88
+ "loss": 11.6534,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0004480565546940147,
93
+ "grad_norm": 8.886016845703125,
94
+ "learning_rate": 0.00018,
95
+ "loss": 13.6284,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0004480565546940147,
100
+ "eval_loss": 2.9265856742858887,
101
+ "eval_runtime": 107.9771,
102
+ "eval_samples_per_second": 78.331,
103
+ "eval_steps_per_second": 39.166,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 71316170342400.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null