eddysang commited on
Commit
633311b
·
verified ·
1 Parent(s): badb313

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:b2386262c3c36c9c368ee51cc425d8200aee38ea98f657835c4e7478910b4bc9
3
  size 319876032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1f6883302685faa1deceef1f53ee90ec530996e23b2747215dd7ea65daa6db8
3
  size 319876032
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c1817ea2b40a3c8ac678001d8bc7cec4b805e70a7c61d0607ed8461d8367597
3
  size 640009682
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df5e09110609d03078c74a94bbf3e31e9b79e49ff5c54f32598b4e1979794932
3
  size 640009682
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:39acb5a2530dc832149c5d18e7a15da6846a800c716036ccf187a7e397862da3
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22d0e0f373f425efa292dac5abf951f67103d9d788fea236fa7b5ab0e5d83fa6
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:014898519bf1f31fef4a7ab39caf2eaa1ff4fbc5662e969211f7676259067ad2
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1fbe8f3807fcf2c9b342444bf912c2b4a5837aba74951c80e3f443bde6ab488
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": 0.002597816511168506,
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": 3.094,
103
  "eval_steps_per_second": 1.547,
104
  "step": 27
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
105
  }
106
  ],
107
  "logging_steps": 3,
@@ -121,7 +150,7 @@
121
  "attributes": {}
122
  }
123
  },
124
- "total_flos": 1.419972205168558e+17,
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": 0.003463755348224675,
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": 3.094,
103
  "eval_steps_per_second": 1.547,
104
  "step": 27
105
+ },
106
+ {
107
+ "epoch": 0.0028864627901872292,
108
+ "grad_norm": 29.395793914794922,
109
+ "learning_rate": 0.0001923879532511287,
110
+ "loss": 14.8443,
111
+ "step": 30
112
+ },
113
+ {
114
+ "epoch": 0.003175109069205952,
115
+ "grad_norm": 27.154170989990234,
116
+ "learning_rate": 0.00018724960070727972,
117
+ "loss": 13.3753,
118
+ "step": 33
119
+ },
120
+ {
121
+ "epoch": 0.003463755348224675,
122
+ "grad_norm": 23.787752151489258,
123
+ "learning_rate": 0.00018090169943749476,
124
+ "loss": 10.3941,
125
+ "step": 36
126
+ },
127
+ {
128
+ "epoch": 0.003463755348224675,
129
+ "eval_loss": 0.3380902111530304,
130
+ "eval_runtime": 10045.2845,
131
+ "eval_samples_per_second": 3.485,
132
+ "eval_steps_per_second": 1.743,
133
+ "step": 36
134
  }
135
  ],
136
  "logging_steps": 3,
 
150
  "attributes": {}
151
  }
152
  },
153
+ "total_flos": 1.8932962735580774e+17,
154
  "train_batch_size": 2,
155
  "trial_name": null,
156
  "trial_params": null