oldiday commited on
Commit
26afda8
·
verified ·
1 Parent(s): c99622e

Training in progress, step 36, 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:c4ad481784c88c9b3e05edd383585924f92713385a13f01b3f42c508d14fd3e8
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:789abd8b6f3e70008ae66ee75a44717ffd07aabad67372292f19406394e56aab
3
  size 167832240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a1ead8c48ed9b8a86e178bd713ab61a93dc23fd4b9ef08519a89201ed4eebfb8
3
  size 85723284
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:273da983aa9a21c729800cb295486e04247ab8246e31ba40ec5d776dc1934e51
3
  size 85723284
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9789b10aa8cd1fb290b972a9f63921e7daed75f63ecfee090c8245a63f78cb39
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8b607c048205bc297b604bd021fe4032f014595c5fa46da254a15590c9ff753
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bd4a07944f7914b974e23583756a2e0907223f4627a9b1ba247bd8f732140689
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b09cef78339a08679f2a6cf4a4b56eca3094fb6b859867afd839be3db1415460
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": 0.012138923232550298,
5
  "eval_steps": 9,
6
- "global_step": 27,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -102,6 +102,35 @@
102
  "eval_samples_per_second": 10.133,
103
  "eval_steps_per_second": 1.268,
104
  "step": 27
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
105
  }
106
  ],
107
  "logging_steps": 3,
@@ -121,7 +150,7 @@
121
  "attributes": {}
122
  }
123
  },
124
- "total_flos": 5.76566519094313e+16,
125
  "train_batch_size": 8,
126
  "trial_name": null,
127
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.01618523097673373,
5
  "eval_steps": 9,
6
+ "global_step": 36,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
102
  "eval_samples_per_second": 10.133,
103
  "eval_steps_per_second": 1.268,
104
  "step": 27
105
+ },
106
+ {
107
+ "epoch": 0.013487692480611442,
108
+ "grad_norm": 3.73301362991333,
109
+ "learning_rate": 8.83022221559489e-05,
110
+ "loss": 7.4779,
111
+ "step": 30
112
+ },
113
+ {
114
+ "epoch": 0.014836461728672586,
115
+ "grad_norm": 3.9209611415863037,
116
+ "learning_rate": 8.473291852294987e-05,
117
+ "loss": 7.409,
118
+ "step": 33
119
+ },
120
+ {
121
+ "epoch": 0.01618523097673373,
122
+ "grad_norm": 4.179993152618408,
123
+ "learning_rate": 8.07830737662829e-05,
124
+ "loss": 7.2678,
125
+ "step": 36
126
+ },
127
+ {
128
+ "epoch": 0.01618523097673373,
129
+ "eval_loss": 1.8027839660644531,
130
+ "eval_runtime": 369.7392,
131
+ "eval_samples_per_second": 10.134,
132
+ "eval_steps_per_second": 1.268,
133
+ "step": 36
134
  }
135
  ],
136
  "logging_steps": 3,
 
150
  "attributes": {}
151
  }
152
  },
153
+ "total_flos": 7.453176954145997e+16,
154
  "train_batch_size": 8,
155
  "trial_name": null,
156
  "trial_params": null