Nexspear commited on
Commit
0c49dd7
·
verified ·
1 Parent(s): 79755f0

Training in progress, step 40, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1aeac04793675008f55a68a74b904da28f2fe8141e8f8aec60468a976c408731
3
  size 313820248
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4559bf21b4aea99e80e365d719b68782afa1236e4b08fa4f4a0d5666cb88932b
3
  size 313820248
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ec8d99b6828dcdc3972fe5cce9df6bce2d152c3801cb63ae167cd4baa064de4d
3
  size 159641092
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cb208c27f691cedf409cc53818467d6c29ed3e04cce09b6ec363ccef13da076
3
  size 159641092
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:45fa40cd28fc7753785b6f0a6ad73f08da57c5886b75c0d32beb250b58a5db1b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:028ca79dfc402208a31d482c5d1658cbaaeb711f53c60e657224662cb1f3f0f6
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:88f387d8c434535a84694e469cebc18f2e722ba31b0dc0372632798b59011377
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd18e5325bf99a4b662a5314e5f491b65903ffc83b0317f63835d8305a50591e
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": 0.012033694344163659,
5
  "eval_steps": 5,
6
- "global_step": 35,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -148,6 +148,28 @@
148
  "eval_samples_per_second": 28.485,
149
  "eval_steps_per_second": 3.564,
150
  "step": 35
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
151
  }
152
  ],
153
  "logging_steps": 3,
@@ -167,7 +189,7 @@
167
  "attributes": {}
168
  }
169
  },
170
- "total_flos": 1.417771455873024e+16,
171
  "train_batch_size": 8,
172
  "trial_name": null,
173
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.013752793536187038,
5
  "eval_steps": 5,
6
+ "global_step": 40,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
148
  "eval_samples_per_second": 28.485,
149
  "eval_steps_per_second": 3.564,
150
  "step": 35
151
+ },
152
+ {
153
+ "epoch": 0.012377514182568335,
154
+ "grad_norm": 2.038388729095459,
155
+ "learning_rate": 2.7300475013022663e-05,
156
+ "loss": 0.5948,
157
+ "step": 36
158
+ },
159
+ {
160
+ "epoch": 0.013408973697782363,
161
+ "grad_norm": 2.125666379928589,
162
+ "learning_rate": 1.7527597583490822e-05,
163
+ "loss": 0.6002,
164
+ "step": 39
165
+ },
166
+ {
167
+ "epoch": 0.013752793536187038,
168
+ "eval_loss": 0.5893370509147644,
169
+ "eval_runtime": 171.9189,
170
+ "eval_samples_per_second": 28.496,
171
+ "eval_steps_per_second": 3.566,
172
+ "step": 40
173
  }
174
  ],
175
  "logging_steps": 3,
 
189
  "attributes": {}
190
  }
191
  },
192
+ "total_flos": 1.620310235283456e+16,
193
  "train_batch_size": 8,
194
  "trial_name": null,
195
  "trial_params": null