kostiantynk commited on
Commit
fcd827e
·
verified ·
1 Parent(s): 0305356

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:ddc62d824a51267c55263b1686b7e19b7539e65f0f4d19ad0252c53a3a939dd0
3
  size 14293800
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7869f49059e694892bf043d452313f2b352a3421b9634ce3b9eb0675c2dfd459
3
  size 14293800
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ad1b2bfec62acc88ae36eb71d49452d1cb864d5307e70e9f9acf6a9a48a699c5
3
  size 7579748
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a225e03ce0bd77b999940bbc6c1b59d30228dca94ba1ee2cdb845e50636bcbb0
3
  size 7579748
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:49e7de58e31a90ba64af174f19d6376e395fcb83031653ee92f9f28eda70ed47
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7374fbf440c7501f107e9bbca3ac74debe0059f159f1c9fc25f675d7ae767ef1
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": 0.002996753517023225,
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": 80.816,
103
  "eval_steps_per_second": 40.44,
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": 69771844386816.0,
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": 0.0033297261300258055,
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": 80.816,
103
  "eval_steps_per_second": 40.44,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.0033297261300258055,
108
+ "grad_norm": 12.625859260559082,
109
+ "learning_rate": 0.0002,
110
+ "loss": 10.1853,
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": 77314746482688.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null