ardaspear commited on
Commit
fcfa245
·
verified ·
1 Parent(s): b1cbf2d

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:b354ff9d8086f102d78ac1b4410140ae0821f5d58369988cc23b55f4df6e3e0f
3
  size 72396376
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4766a7cd7c3d4b48e0f5bf1b6f098d0d65fcf653e29574d0ce69a02056819ac9
3
  size 72396376
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8d3306b30b4c68ad4666500d8f14f48d9f137e393f538db0c0d8f6d1e186666b
3
  size 37134420
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bc737fa47bf00150c3961a5fbe75090896bee74a73eba4b3696aff25598fb2e
3
  size 37134420
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9fbde4306ca4c19db5e9ccc802bd241b3575e068082d6a97ce7b5a436af01c9a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95017ebb47e5bb3b08eddf99d3886d04e55d40d24d90d35c2534020f40f6975e
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bc389ed2ec8a0148b9b29024154a8f2f11c6a7454ef1d0724563562d03a46e01
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9776c8df8be516beee92201f32f4a3f5d90539bf47f8ef27e1636cdc132a851e
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": 0.07261724659606657,
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": 17.572,
132
  "eval_steps_per_second": 2.21,
133
  "step": 36
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
134
  }
135
  ],
136
  "logging_steps": 3,
@@ -150,7 +179,7 @@
150
  "attributes": {}
151
  }
152
  },
153
- "total_flos": 2.3056942444314624e+16,
154
  "train_batch_size": 8,
155
  "trial_name": null,
156
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0907715582450832,
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": 17.572,
132
  "eval_steps_per_second": 2.21,
133
  "step": 36
134
+ },
135
+ {
136
+ "epoch": 0.07866868381240545,
137
+ "grad_norm": 0.0725693628191948,
138
+ "learning_rate": 3.824798160583012e-05,
139
+ "loss": 1.241,
140
+ "step": 39
141
+ },
142
+ {
143
+ "epoch": 0.08472012102874432,
144
+ "grad_norm": 0.07808159291744232,
145
+ "learning_rate": 3.5959278669726935e-05,
146
+ "loss": 1.323,
147
+ "step": 42
148
+ },
149
+ {
150
+ "epoch": 0.0907715582450832,
151
+ "grad_norm": 0.07631468772888184,
152
+ "learning_rate": 3.355050358314172e-05,
153
+ "loss": 1.3608,
154
+ "step": 45
155
+ },
156
+ {
157
+ "epoch": 0.0907715582450832,
158
+ "eval_loss": 1.3239437341690063,
159
+ "eval_runtime": 47.5205,
160
+ "eval_samples_per_second": 17.571,
161
+ "eval_steps_per_second": 2.21,
162
+ "step": 45
163
  }
164
  ],
165
  "logging_steps": 3,
 
179
  "attributes": {}
180
  }
181
  },
182
+ "total_flos": 2.882117805539328e+16,
183
  "train_batch_size": 8,
184
  "trial_name": null,
185
  "trial_params": null