ClarenceDan commited on
Commit
6cc332f
·
verified ·
1 Parent(s): 55c5def

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 sha256:1ac59c02cfbdf57a67659eac18ec82487105bddb90bc3df0827a3f2bebc4db50
3
  size 80792096
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84b3a640e03568e3146c68f37882af3a8399cb7fee96a848f3cc253b0d1c69f6
3
  size 80792096
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:635f59d3b2c1533e7e3f02478a71f4401f2e116fd7292a2e22864b922aba1f56
3
  size 41459700
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c7d27f32843ebf3500b40367d3bb1a23d3e7b72dcaf7dfbb619c895389a82ce
3
  size 41459700
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:22cc4a9a02a6f74d668e9df70ad462220b16b60af37292d30446f2a841cfc377
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27917d88cdf4e1cd610266e1bad5287f7c270415c57a7781c0adaab154ebaaf5
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": 0.007507037847982484,
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": 34.479,
74
  "eval_steps_per_second": 17.291,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1045581627654144.0,
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": 0.011260556771973726,
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": 34.479,
74
  "eval_steps_per_second": 17.291,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.008758210822646231,
79
+ "grad_norm": 3.5504117012023926,
80
+ "learning_rate": 0.00014,
81
+ "loss": 4.7697,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.010009383797309979,
86
+ "grad_norm": 3.5056967735290527,
87
+ "learning_rate": 0.00016,
88
+ "loss": 4.9152,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.011260556771973726,
93
+ "grad_norm": 3.492283582687378,
94
+ "learning_rate": 0.00018,
95
+ "loss": 4.0476,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.011260556771973726,
100
+ "eval_loss": 3.841667890548706,
101
+ "eval_runtime": 9.7726,
102
+ "eval_samples_per_second": 34.484,
103
+ "eval_steps_per_second": 17.293,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 1568372441481216.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null