nathanialhunt commited on
Commit
e1629ab
·
verified ·
1 Parent(s): 3a513ab

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:a2614c1613daeefb4bcabeb969b1a8a2a55a543a42181e507e08b506ae25d5dd
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5f23876cd316644b76bf63a37e8575e51882bbcbcda15b33f319d3ddad24efb
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:afbc13c224ed9624e8c9f38b0aff2c1ce4ff986c1861b9c7a6c341b4ed21925d
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03c8b2b8d4690536fd03943a7911226c4bacabd7d50be416d6bb6beae122f405
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": 0.02023608768971332,
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": 32.635,
74
  "eval_steps_per_second": 16.448,
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": 0.03035413153456998,
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": 32.635,
74
  "eval_steps_per_second": 16.448,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.023608768971332208,
79
+ "grad_norm": 1.8054167032241821,
80
+ "learning_rate": 0.00014,
81
+ "loss": 3.1859,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.026981450252951095,
86
+ "grad_norm": 1.2994825839996338,
87
+ "learning_rate": 0.00016,
88
+ "loss": 3.0584,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.03035413153456998,
93
+ "grad_norm": 1.7081750631332397,
94
+ "learning_rate": 0.00018,
95
+ "loss": 2.9828,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.03035413153456998,
100
+ "eval_loss": 3.005418062210083,
101
+ "eval_runtime": 3.8304,
102
+ "eval_samples_per_second": 32.634,
103
+ "eval_steps_per_second": 16.447,
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