nat-hunt commited on
Commit
d3cccd8
·
verified ·
1 Parent(s): f1ba617

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 sha256:3b77ab7cd69b55ace93a9356100711a8dfd9575d6938ab2c5f85ef9af1ef490e
3
  size 100059752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c7130a8eda155772645ab752dedc88c042cb4f288439e96b04227b6c4295bd4
3
  size 100059752
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1e5ed5ed976375e59a4bf3965bb8cf4b9920430e85458e13a72daef17ae7ea92
3
  size 51244020
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb95aac4059bebedb4b2c36a388e82d13bad6aac0cfa1e0e73a0ade40b64a761
3
  size 51244020
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1473756068390812fdf419e99ba029eb15e6d51d9ff05c81c9ce7588fca7349c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c170043d51c0c5eebe7184a37a44f6c4d754dd98f93caa4b85c4efb0a328bf9
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": 0.00024168210746797713,
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": 28.402,
74
  "eval_steps_per_second": 14.201,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1146654849761280.0,
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": 0.0003625231612019657,
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": 28.402,
74
  "eval_steps_per_second": 14.201,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.00028196245871264,
79
+ "grad_norm": 2.8985276222229004,
80
+ "learning_rate": 0.00014,
81
+ "loss": 1.0801,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0003222428099573028,
86
+ "grad_norm": 2.775141477584839,
87
+ "learning_rate": 0.00016,
88
+ "loss": 0.9911,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0003625231612019657,
93
+ "grad_norm": 2.5354292392730713,
94
+ "learning_rate": 0.00018,
95
+ "loss": 0.7613,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0003625231612019657,
100
+ "eval_loss": 0.5746785402297974,
101
+ "eval_runtime": 368.3895,
102
+ "eval_samples_per_second": 28.378,
103
+ "eval_steps_per_second": 14.189,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 1719982274641920.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null