ardaspear commited on
Commit
22650ca
·
verified ·
1 Parent(s): e4fca5e

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 sha256:2bca11cf8876cb00cca1bfc27920a86760d462916bd5b7544e1f82b70f0acf66
3
  size 83115256
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a38aebc8839e71c822cce4fd7ecb6138e4a6812b716afed06fffab2983314804
3
  size 83115256
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:304e942077c19c3d4ffe673b5b31d24e86d5a03ad7ccd45018b189b9b8e24c70
3
  size 42608388
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:656e3c9eca30c87801bd66aed3ca92cd3df619fd42416f8d458b6f1ddeaa5c84
3
  size 42608388
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:26874276c6417ee8aa16ea6cd2c302eb82bd3a827f551027b6e19cf69be8977a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72e96b31999edd85c2cb037a7393b204a41975c1632139f4f06d6e05e5f188ae
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": 0.01121844811467747,
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": 23.363,
103
  "eval_steps_per_second": 2.922,
104
  "step": 27
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
105
  }
106
  ],
107
  "logging_steps": 3,
@@ -121,7 +150,7 @@
121
  "attributes": {}
122
  }
123
  },
124
- "total_flos": 1.0857221537660928e+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": 0.01495793081956996,
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": 23.363,
103
  "eval_steps_per_second": 2.922,
104
  "step": 27
105
+ },
106
+ {
107
+ "epoch": 0.012464942349641633,
108
+ "grad_norm": 0.8669916987419128,
109
+ "learning_rate": 4.415111107797445e-05,
110
+ "loss": 1.2845,
111
+ "step": 30
112
+ },
113
+ {
114
+ "epoch": 0.013711436584605797,
115
+ "grad_norm": 0.8390219211578369,
116
+ "learning_rate": 4.2366459261474933e-05,
117
+ "loss": 1.3824,
118
+ "step": 33
119
+ },
120
+ {
121
+ "epoch": 0.01495793081956996,
122
+ "grad_norm": 0.7428231835365295,
123
+ "learning_rate": 4.039153688314145e-05,
124
+ "loss": 1.2802,
125
+ "step": 36
126
+ },
127
+ {
128
+ "epoch": 0.01495793081956996,
129
+ "eval_loss": 1.293402075767517,
130
+ "eval_runtime": 173.4725,
131
+ "eval_samples_per_second": 23.37,
132
+ "eval_steps_per_second": 2.923,
133
+ "step": 36
134
  }
135
  ],
136
  "logging_steps": 3,
 
150
  "attributes": {}
151
  }
152
  },
153
+ "total_flos": 1.4476295383547904e+16,
154
  "train_batch_size": 8,
155
  "trial_name": null,
156
  "trial_params": null