havinash-ai commited on
Commit
40670fa
·
verified ·
1 Parent(s): cf7343e

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 sha256:53c1f47619c20dc7f21c6e24d15419289847495bfc992fd961db41853e9b4312
3
  size 4731640
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa8add69d5db91441131050b4bfa93c4cf4d23bb0d183311f1ea81acd41c4e9f
3
  size 4731640
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6ee91a657ee619e0fd33bfa35f8d28008e6db64424f30745334c9715eed5e8d9
3
  size 2505722
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9498279fa954d61b363861b1f4d78dd85ff05ddb14ed1d92ffe2661b0719cb2e
3
  size 2505722
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0446c283f3d13924158b53fab172b648ee5a8318605e10f8c682e330fe303df8
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:984c94c2cf2f0863149908dd6ef6e69b3e7552a33dd00a7ddca47ac3dc0772bb
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": 0.000555118656612851,
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": 123.934,
103
  "eval_steps_per_second": 61.976,
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": 49867731763200.0,
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": 0.0006167985073476123,
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": 123.934,
103
  "eval_steps_per_second": 61.976,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.0006167985073476123,
108
+ "grad_norm": 197.9041748046875,
109
+ "learning_rate": 0.0002,
110
+ "loss": 11.1085,
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": 55238102876160.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null