flytech commited on
Commit
8d0580d
·
1 Parent(s): 9b2e44b

Training in progress, step 800, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:148fa6b9455b7f560750417c970bd7bbde4cf5947d4ffd6a66d586985063bf14
3
  size 250422888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78fe9cebcc13d7d3eac940c01a03b3c35c2cfec6bbfb35df766504b6521e9874
3
  size 250422888
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7b6b160e21bb074e15ee728e9e1ebb203325c3ed529af79f6656daf63fa22a5f
3
  size 127492797
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f424cdd3ffe65db9505c26ed304302b80da61db7c78f707cd820495b245d10d
3
  size 127492797
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c5d64acbaf04947014cbd3c92edd8f7269f6708839ef1224322d084c5573ec37
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0003b2e343e2041e6961a63bdcedb5645a93cb70402e03a8646f3bb813517fd0
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:30423cc69a1c7d18caef4643847588d5884db012263cbe7b7224fa4719ca4156
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de7840bcb72f2f480fd301578d289cdfa174589e831b0d33e5772f3956b6beae
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 8.536585365853659,
5
  "eval_steps": 100,
6
- "global_step": 700,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -98,13 +98,26 @@
98
  "eval_samples_per_second": 8.522,
99
  "eval_steps_per_second": 0.154,
100
  "step": 700
 
 
 
 
 
 
 
 
 
 
 
 
 
101
  }
102
  ],
103
  "logging_steps": 100,
104
  "max_steps": 820,
105
  "num_train_epochs": 10,
106
  "save_steps": 100,
107
- "total_flos": 9.020394128277504e+17,
108
  "trial_name": null,
109
  "trial_params": null
110
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 9.75609756097561,
5
  "eval_steps": 100,
6
+ "global_step": 800,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
98
  "eval_samples_per_second": 8.522,
99
  "eval_steps_per_second": 0.154,
100
  "step": 700
101
+ },
102
+ {
103
+ "epoch": 9.76,
104
+ "learning_rate": 0.0002,
105
+ "loss": 0.0267,
106
+ "step": 800
107
+ },
108
+ {
109
+ "epoch": 9.76,
110
+ "eval_runtime": 32.3926,
111
+ "eval_samples_per_second": 8.52,
112
+ "eval_steps_per_second": 0.154,
113
+ "step": 800
114
  }
115
  ],
116
  "logging_steps": 100,
117
  "max_steps": 820,
118
  "num_train_epochs": 10,
119
  "save_steps": 100,
120
+ "total_flos": 1.0309425566318592e+18,
121
  "trial_name": null,
122
  "trial_params": null
123
  }