nathanialhunt commited on
Commit
ae49e22
·
verified ·
1 Parent(s): 2bb1aeb

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 sha256:77c0b5e03009e69da3333a70afa23c7b5b0a993a7a7bb639fab5833014a3edc4
3
  size 124756544
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3f487c381d98b9280477b1a597ffaf2160fa93baddf0b7aabf32b3f9961c76c
3
  size 124756544
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c69f7b4e958e391469cbac9ba5c7aeb1448a2286545ea79561e2b86e2c696dec
3
  size 63958740
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fba2ddbbe336d04981b582013ceee8704c0326be7a32cb7c089b634c87ab8ba4
3
  size 63958740
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6dee4d5b27e291e54604657b0419725531a46b79101c42b4fcc524425de489f6
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98fae8deb35c37957af2ca4218e66b65d51a252af0c9674a9383fb749413569a
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": 0.00437636761487965,
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": 20.687,
74
  "eval_steps_per_second": 10.343,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1978843854274560.0,
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": 0.006564551422319475,
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": 20.687,
74
  "eval_steps_per_second": 10.343,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.005105762217359592,
79
+ "grad_norm": 2.2356066703796387,
80
+ "learning_rate": 0.00014,
81
+ "loss": 1.9656,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.005835156819839533,
86
+ "grad_norm": 0.6858603358268738,
87
+ "learning_rate": 0.00016,
88
+ "loss": 2.278,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.006564551422319475,
93
+ "grad_norm": 0.5601918697357178,
94
+ "learning_rate": 0.00018,
95
+ "loss": 1.8191,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.006564551422319475,
100
+ "eval_loss": 1.8506412506103516,
101
+ "eval_runtime": 27.8918,
102
+ "eval_samples_per_second": 20.723,
103
+ "eval_steps_per_second": 10.361,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 2968265781411840.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null