trenden commited on
Commit
41ead6a
·
verified ·
1 Parent(s): 557ce4d

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 sha256:7f1846282a283a50df5f17231bc4716e8eeb2293284d19ff1cd0b6fc2d487d6d
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:474dbf701a8769ffb4ac228fe224961cd284c7cbe22df53d4056b865b0dc6e06
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:732bb6464425a0486a50b9869e8b4a7318975814acd96710ccab9533d9de1088
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d6d743b20da8e48cfd4c3647499542d43761866bd2187e8a69f79613d4903e6
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a68cd2a0196a6713af61a6a5ec57d388549ceab000d778970629ba70bc0f12ea
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b90a19943f8ef28f7f3c1abafd8de7b24ff68c3eda11dffdc748b1a1d989fcb2
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": 0.00014834777663769766,
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": 32.999,
74
  "eval_steps_per_second": 16.499,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1109738548887552.0,
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": 0.00022252166495654647,
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": 32.999,
74
  "eval_steps_per_second": 16.499,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.00017307240607731392,
79
+ "grad_norm": 7.050815582275391,
80
+ "learning_rate": 0.00014,
81
+ "loss": 6.061,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.00019779703551693018,
86
+ "grad_norm": 8.801949501037598,
87
+ "learning_rate": 0.00016,
88
+ "loss": 5.7354,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.00022252166495654647,
93
+ "grad_norm": 8.916671752929688,
94
+ "learning_rate": 0.00018,
95
+ "loss": 4.3186,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.00022252166495654647,
100
+ "eval_loss": 3.9336016178131104,
101
+ "eval_runtime": 515.9937,
102
+ "eval_samples_per_second": 33.004,
103
+ "eval_steps_per_second": 16.502,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 1664607823331328.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null