Aivesa commited on
Commit
6ec618d
·
verified ·
1 Parent(s): fb8f158

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:ef3f786a86e552230a6744418d89b2e9b72ab9188269095875170275a85d1723
3
  size 27024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9e4e06c1ae79d389704bb361685c291d87e141e73a8d68edf4d6790884cc6b7
3
  size 27024
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a0aa7fa4d55ad1c4ad59d4e241f93cca7b97b7ec03c9e095c6a83317514b8d00
3
  size 63974
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f926be18b3c96778e4667bbaf27e63077d72e0f8dddd12e04a6aa0f357262ca1
3
  size 63974
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9df170cb6acde393f26f26d8b291e01ba34281d10b477edb2225f4b80d02e472
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e97ead28242dd097af80112cb3bd8d751944021cbf255fca1535e0f2a22344d9
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": 0.004245783700908126,
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,
@@ -94,6 +94,13 @@
94
  "eval_samples_per_second": 58.657,
95
  "eval_steps_per_second": 29.361,
96
  "step": 9
 
 
 
 
 
 
 
97
  }
98
  ],
99
  "logging_steps": 1,
@@ -108,12 +115,12 @@
108
  "should_evaluate": false,
109
  "should_log": false,
110
  "should_save": true,
111
- "should_training_stop": false
112
  },
113
  "attributes": {}
114
  }
115
  },
116
- "total_flos": 232756346880.0,
117
  "train_batch_size": 2,
118
  "trial_name": null,
119
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0047175374454534735,
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,
 
94
  "eval_samples_per_second": 58.657,
95
  "eval_steps_per_second": 29.361,
96
  "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0047175374454534735,
100
+ "grad_norm": 0.02780097909271717,
101
+ "learning_rate": 0.0002,
102
+ "loss": 10.379,
103
+ "step": 10
104
  }
105
  ],
106
  "logging_steps": 1,
 
115
  "should_evaluate": false,
116
  "should_log": false,
117
  "should_save": true,
118
+ "should_training_stop": true
119
  },
120
  "attributes": {}
121
  }
122
  },
123
+ "total_flos": 258618163200.0,
124
  "train_batch_size": 2,
125
  "trial_name": null,
126
  "trial_params": null