dzanbek commited on
Commit
efd6369
·
verified ·
1 Parent(s): 60966a0

Training in progress, step 12, checkpoint

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bdcdda7dd836b6a45b53d47d2d719866331f3d33ea9ec0ae3ef158e10cc42a82
3
  size 25986148
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0ce98f9fa79cb1fa651a8d57ed7c66a63473d43a212b5345873f2f14705aee9
3
  size 25986148
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e91a94c2b00d786104c6c4ea92b65abb56d7d311eefb01152a0d01c98a9f1ab
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc6bbad0bead68616b1d850d22d1642ed63d4a3ad9e6fcee219d10180c362d45
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e4cb1249623f16a121f1f7528c255e6aea1cd633fd38f639775465d7feebdcd
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": 0.019455252918287938,
5
  "eval_steps": 2,
6
- "global_step": 10,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -125,6 +125,28 @@
125
  "eval_samples_per_second": 28.778,
126
  "eval_steps_per_second": 14.455,
127
  "step": 10
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
128
  }
129
  ],
130
  "logging_steps": 1,
@@ -144,7 +166,7 @@
144
  "attributes": {}
145
  }
146
  },
147
- "total_flos": 514684386017280.0,
148
  "train_batch_size": 2,
149
  "trial_name": null,
150
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.023346303501945526,
5
  "eval_steps": 2,
6
+ "global_step": 12,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
125
  "eval_samples_per_second": 28.778,
126
  "eval_steps_per_second": 14.455,
127
  "step": 10
128
+ },
129
+ {
130
+ "epoch": 0.021400778210116732,
131
+ "grad_norm": NaN,
132
+ "learning_rate": 9.755282581475769e-05,
133
+ "loss": 0.0,
134
+ "step": 11
135
+ },
136
+ {
137
+ "epoch": 0.023346303501945526,
138
+ "grad_norm": NaN,
139
+ "learning_rate": 9.045084971874738e-05,
140
+ "loss": 0.0,
141
+ "step": 12
142
+ },
143
+ {
144
+ "epoch": 0.023346303501945526,
145
+ "eval_loss": NaN,
146
+ "eval_runtime": 7.5949,
147
+ "eval_samples_per_second": 28.572,
148
+ "eval_steps_per_second": 14.352,
149
+ "step": 12
150
  }
151
  ],
152
  "logging_steps": 1,
 
166
  "attributes": {}
167
  }
168
  },
169
+ "total_flos": 617621263220736.0,
170
  "train_batch_size": 2,
171
  "trial_name": null,
172
  "trial_params": null