dixedus commited on
Commit
a2b6de2
·
verified ·
1 Parent(s): 40f08a9

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 sha256:9ae4ebaa0e5914bda660a71adf27e2f79eed304c9c273d4c3dbc247dae62e10a
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7310740e9f6b1d549dc7d593d1337e81ff1e08576dc2f2db72336a6a3d1ae2a6
3
  size 167832240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0f0146b25aa55360a4f3825b12d1d91d394a3861513e3384a7a4e5ce3420f39d
3
  size 85723284
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fda05f718db000f70ff7429aabf480d4ebeb732b521c632ed91f8d603235e34b
3
  size 85723284
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b0fbb0d8372c773303ed8b57a701ed3dbe0540d90170abf552bdce6ec3e3a2fb
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4b406b950e63c883a5e375e07824f589373180bc8cc6acce00919fc2ab3b022
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": 0.003712201283802944,
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": 14.031,
132
  "eval_steps_per_second": 1.754,
133
  "step": 36
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
134
  }
135
  ],
136
  "logging_steps": 3,
@@ -150,7 +179,7 @@
150
  "attributes": {}
151
  }
152
  },
153
- "total_flos": 5.27347124011008e+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": 0.00464025160475368,
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": 14.031,
132
  "eval_steps_per_second": 1.754,
133
  "step": 36
134
+ },
135
+ {
136
+ "epoch": 0.004021551390786523,
137
+ "grad_norm": 5.165075302124023,
138
+ "learning_rate": 3.824798160583012e-05,
139
+ "loss": 5.4859,
140
+ "step": 39
141
+ },
142
+ {
143
+ "epoch": 0.004330901497770101,
144
+ "grad_norm": 7.677441596984863,
145
+ "learning_rate": 3.5959278669726935e-05,
146
+ "loss": 5.9298,
147
+ "step": 42
148
+ },
149
+ {
150
+ "epoch": 0.00464025160475368,
151
+ "grad_norm": 6.484046936035156,
152
+ "learning_rate": 3.355050358314172e-05,
153
+ "loss": 5.9238,
154
+ "step": 45
155
+ },
156
+ {
157
+ "epoch": 0.00464025160475368,
158
+ "eval_loss": 1.4534233808517456,
159
+ "eval_runtime": 1164.252,
160
+ "eval_samples_per_second": 14.03,
161
+ "eval_steps_per_second": 1.754,
162
+ "step": 45
163
  }
164
  ],
165
  "logging_steps": 3,
 
179
  "attributes": {}
180
  }
181
  },
182
+ "total_flos": 6.644573762538701e+16,
183
  "train_batch_size": 8,
184
  "trial_name": null,
185
  "trial_params": null