Nexspear commited on
Commit
2a88663
·
verified ·
1 Parent(s): 65c6251

Training in progress, step 30, 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:d671448e809b47fff803ad4b424807525272996fd189084742a79cb03fb08f19
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:953141e65aa19328a4b175b71c0928b6c14a6dc4b03dd91c2cec1c1acad7dd33
3
  size 639691872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:989dc02e59e39fc513350585dd1cb8c9a0e5161586b76639bc8ee5fd65d7f85f
3
  size 325339796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b81e109bb71af6716176cc20bc6c5a0dbbf89567a31c471c69e0155bde3d7a61
3
  size 325339796
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:033658be991992abf38fa382786ff025e0c4d1ae137bb82ba56ffad42146eaef
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93ef852758e34c0cd782ece9882d5e8752c4ccecf9912cf50881886aa6a8e5ee
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6676fe28230ae15b45fb334c871c6fdf1a7984a935952b9f8650896c37a8c106
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d37b0dad6b9c48822da5c83a071d50252502799ad22c4c4907147ad4e4f8e2f4
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": 0.06269592476489028,
5
  "eval_steps": 5,
6
- "global_step": 25,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -111,6 +111,28 @@
111
  "eval_samples_per_second": 13.496,
112
  "eval_steps_per_second": 1.687,
113
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
114
  }
115
  ],
116
  "logging_steps": 3,
@@ -130,7 +152,7 @@
130
  "attributes": {}
131
  }
132
  },
133
- "total_flos": 3.3980632006656e+16,
134
  "train_batch_size": 8,
135
  "trial_name": null,
136
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.07523510971786834,
5
  "eval_steps": 5,
6
+ "global_step": 30,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
111
  "eval_samples_per_second": 13.496,
112
  "eval_steps_per_second": 1.687,
113
  "step": 25
114
+ },
115
+ {
116
+ "epoch": 0.0677115987460815,
117
+ "grad_norm": 0.3791425824165344,
118
+ "learning_rate": 6.167226819279528e-05,
119
+ "loss": 1.5915,
120
+ "step": 27
121
+ },
122
+ {
123
+ "epoch": 0.07523510971786834,
124
+ "grad_norm": 0.36740052700042725,
125
+ "learning_rate": 5e-05,
126
+ "loss": 1.5772,
127
+ "step": 30
128
+ },
129
+ {
130
+ "epoch": 0.07523510971786834,
131
+ "eval_loss": 1.5675104856491089,
132
+ "eval_runtime": 49.7922,
133
+ "eval_samples_per_second": 13.496,
134
+ "eval_steps_per_second": 1.687,
135
+ "step": 30
136
  }
137
  ],
138
  "logging_steps": 3,
 
152
  "attributes": {}
153
  }
154
  },
155
+ "total_flos": 4.0709470027776e+16,
156
  "train_batch_size": 8,
157
  "trial_name": null,
158
  "trial_params": null