philip-hightech commited on
Commit
b9c0012
·
verified ·
1 Parent(s): 869ee9d

Training in progress, step 10, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a63559a9984b3f341547f700adaa222b3a0230be32493e56bcf895d12c64c95
3
  size 5327496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f908d427fe36d3b3386cb28e2f353b7e921ef68741486a426bb42bc5eafbd8cf
3
  size 5327496
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ab0601ff334e953e996fc924db32b04d351949fa66dda10fde3419c92a92cd69
3
  size 2857722
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7347f67c57a348509252ab4cc04768d950bbe0bc3e021529e723377af30faaf3
3
  size 2857722
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b37eb23c7db03165d9b298533a106ef93fbe349e32cf744565e4d6da5d2b28dc
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a54ed4d938dc6d13eea41e25a4f660e0c352d06f8930c1c2f1e9e51a81e8f3d
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
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": 0.0003365366637998729,
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,
@@ -102,6 +102,13 @@
102
  "eval_samples_per_second": 89.627,
103
  "eval_steps_per_second": 44.817,
104
  "step": 9
 
 
 
 
 
 
 
105
  }
106
  ],
107
  "logging_steps": 1,
@@ -116,12 +123,12 @@
116
  "should_evaluate": false,
117
  "should_log": false,
118
  "should_save": true,
119
- "should_training_stop": false
120
  },
121
  "attributes": {}
122
  }
123
  },
124
- "total_flos": 21222716866560.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0003739296264443032,
5
  "eval_steps": 3,
6
+ "global_step": 10,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
102
  "eval_samples_per_second": 89.627,
103
  "eval_steps_per_second": 44.817,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.0003739296264443032,
108
+ "grad_norm": 0.699952244758606,
109
+ "learning_rate": 0.0002,
110
+ "loss": 2.732,
111
+ "step": 10
112
  }
113
  ],
114
  "logging_steps": 1,
 
123
  "should_evaluate": false,
124
  "should_log": false,
125
  "should_save": true,
126
+ "should_training_stop": true
127
  },
128
  "attributes": {}
129
  }
130
  },
131
+ "total_flos": 23344988553216.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null