Aivesa commited on
Commit
15d1c7c
·
verified ·
1 Parent(s): ec1b902

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:de25f8c2395816f95a61bce9caaeb22e6f074eea3e5fc10d298013248aec53a7
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c7dcd3e3e87139332f5716aca08c1aab36e9d9febba29e2ab993226a1fdea3e
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d791260306bf85a3a169612fe93b5181c920b101d07281bfe6ba016788ce166e
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:640179d9aef9371bd4d79b4b3105d92be1d158c0dc51fe3e5b1643b796677cb8
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:88471f2b3b1e4c205d9505ad6de006cb23590a0562a633e21bbcb4ef69f0d7ee
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b0e1e671455c353fa99a1d12b6e48bbd12137e1c5f529ac1c3f24d8e1df3f99
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": 0.017804154302670624,
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": 17.486,
95
  "eval_steps_per_second": 8.784,
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": 1664607823331328.0,
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": 0.019782393669634024,
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": 17.486,
95
  "eval_steps_per_second": 8.784,
96
  "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.019782393669634024,
100
+ "grad_norm": 2.164289712905884,
101
+ "learning_rate": 0.0002,
102
+ "loss": 2.5339,
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": 1849564248145920.0,
124
  "train_batch_size": 2,
125
  "trial_name": null,
126
  "trial_params": null