oldiday commited on
Commit
55a9d2a
·
verified ·
1 Parent(s): f010073

Training in progress, step 36, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:51b6838d5a8de26b4b4ecd8cceaa880bc60b4bf96e5d4c72c4a11f2f920abb07
3
  size 159967880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ee2d2b8a87f8169ad8787e8282394eb0bb1ab9f31d961faea0729a1b54e1507
3
  size 159967880
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e1f564eb14032574f6d339cb07f8f6f3ef1ac347e27078c543fe02561fd15d6b
3
  size 81730196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b02e08fdafd32d46be484cc7bf21f9bf090f03ce7d97e0677712fbe95b573b8e
3
  size 81730196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e53bb1bec5a15dde25e11aada4e558caf150777408abe7fff1952dcd58e5b1dc
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10350b5619e7d96fb7f3bffab3732b8b921da553987e25ecf13af945b954a09e
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:95e5b5e126f269e3dd52e13e2ce68743557810f4e2bb59a1eda63231c7828066
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc389ed2ec8a0148b9b29024154a8f2f11c6a7454ef1d0724563562d03a46e01
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": 0.5373134328358209,
5
  "eval_steps": 9,
6
- "global_step": 27,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -102,6 +102,35 @@
102
  "eval_samples_per_second": 15.081,
103
  "eval_steps_per_second": 1.952,
104
  "step": 27
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
105
  }
106
  ],
107
  "logging_steps": 3,
@@ -121,7 +150,7 @@
121
  "attributes": {}
122
  }
123
  },
124
- "total_flos": 3.5286742902767616e+16,
125
  "train_batch_size": 8,
126
  "trial_name": null,
127
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.7164179104477612,
5
  "eval_steps": 9,
6
+ "global_step": 36,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
102
  "eval_samples_per_second": 15.081,
103
  "eval_steps_per_second": 1.952,
104
  "step": 27
105
+ },
106
+ {
107
+ "epoch": 0.5970149253731343,
108
+ "grad_norm": 0.5600003600120544,
109
+ "learning_rate": 4.415111107797445e-05,
110
+ "loss": 1.1329,
111
+ "step": 30
112
+ },
113
+ {
114
+ "epoch": 0.6567164179104478,
115
+ "grad_norm": 0.554161787033081,
116
+ "learning_rate": 4.2366459261474933e-05,
117
+ "loss": 1.0888,
118
+ "step": 33
119
+ },
120
+ {
121
+ "epoch": 0.7164179104477612,
122
+ "grad_norm": 0.5243486166000366,
123
+ "learning_rate": 4.039153688314145e-05,
124
+ "loss": 1.0326,
125
+ "step": 36
126
+ },
127
+ {
128
+ "epoch": 0.7164179104477612,
129
+ "eval_loss": 1.0722781419754028,
130
+ "eval_runtime": 5.6371,
131
+ "eval_samples_per_second": 15.079,
132
+ "eval_steps_per_second": 1.951,
133
+ "step": 36
134
  }
135
  ],
136
  "logging_steps": 3,
 
150
  "attributes": {}
151
  }
152
  },
153
+ "total_flos": 4.704899053702349e+16,
154
  "train_batch_size": 8,
155
  "trial_name": null,
156
  "trial_params": null