eddysang commited on
Commit
506ae0c
·
verified ·
1 Parent(s): dd0a13e

Training in progress, step 45, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:206c5da42aad4c42222d2371196eeecb3c6e91b48c5195e7f0074fd6104af83c
3
  size 97728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0b5cc2086653d166c723fde93c40ecae02563e68871889eace15bb672630ae3
3
  size 97728
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8ec67d9f7680e4388f282a13d64c8b0ee1ba60fcb94348a218b510c6e4f53eb0
3
  size 212298
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0caa651cd16aa41ef6c07d2eddf73b26f7f84cf569e2a17fd266043bc890d5ad
3
  size 212298
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c537aa87f7577d8e8b0e29869b2ff3e03ca4ffd7c2022629871808b17fa6a30b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46203c46cfdbbc32c45ae0c3b176792d235e2d9e941c7f8c720fe98dfd77a7ad
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f1fbe8f3807fcf2c9b342444bf912c2b4a5837aba74951c80e3f443bde6ab488
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e917c3eea1680bab35c1f582cbc388a7464296952762325512c323f5f76cc5cb
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": 0.008130253435243802,
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,
@@ -131,6 +131,35 @@
131
  "eval_samples_per_second": 131.951,
132
  "eval_steps_per_second": 65.98,
133
  "step": 36
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
134
  }
135
  ],
136
  "logging_steps": 3,
@@ -150,7 +179,7 @@
150
  "attributes": {}
151
  }
152
  },
153
- "total_flos": 15396501454848.0,
154
  "train_batch_size": 2,
155
  "trial_name": null,
156
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.010162816794054752,
5
  "eval_steps": 9,
6
+ "global_step": 45,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
131
  "eval_samples_per_second": 131.951,
132
  "eval_steps_per_second": 65.98,
133
  "step": 36
134
+ },
135
+ {
136
+ "epoch": 0.008807774554847452,
137
+ "grad_norm": 0.09872834384441376,
138
+ "learning_rate": 0.00017343225094356855,
139
+ "loss": 10.3647,
140
+ "step": 39
141
+ },
142
+ {
143
+ "epoch": 0.009485295674451102,
144
+ "grad_norm": 0.082485131919384,
145
+ "learning_rate": 0.00016494480483301836,
146
+ "loss": 10.3616,
147
+ "step": 42
148
+ },
149
+ {
150
+ "epoch": 0.010162816794054752,
151
+ "grad_norm": 0.0801018700003624,
152
+ "learning_rate": 0.00015555702330196023,
153
+ "loss": 10.3585,
154
+ "step": 45
155
+ },
156
+ {
157
+ "epoch": 0.010162816794054752,
158
+ "eval_loss": 10.357089042663574,
159
+ "eval_runtime": 113.8095,
160
+ "eval_samples_per_second": 131.052,
161
+ "eval_steps_per_second": 65.531,
162
+ "step": 45
163
  }
164
  ],
165
  "logging_steps": 3,
 
179
  "attributes": {}
180
  }
181
  },
182
+ "total_flos": 19245626818560.0,
183
  "train_batch_size": 2,
184
  "trial_name": null,
185
  "trial_params": null