Nexspear commited on
Commit
e547f29
·
verified ·
1 Parent(s): e8ea55e

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 sha256:1f9fe29e10f67118d660bc155691fe35bde8b746f3dcaf54a1370dedbfc6e1c0
3
  size 201892112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b87578f5f0e34cff7103ccc60cdf755fed0ac00864d6ecbc8893d5357e99b4a0
3
  size 201892112
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:19da07f44920f1483d7cbf9adc5f8dfe24784c8ccbf352a78e3d1bbb92a4ac27
3
  size 102864548
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0068ac7c98897660c1f23b91868f1d22dc86ae817424da576e5577879df20e16
3
  size 102864548
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b46966fb28758683b639812794440f8b656b47f578ba67e0ea16235e96cc4296
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b13bfeaf996735b0a4fda15d8b96f5f68670da7d91d7a0fb5f74ec8c1a291333
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": 0.016458970138725604,
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": 49.249,
149
  "eval_steps_per_second": 6.16,
150
  "step": 35
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
151
  }
152
  ],
153
  "logging_steps": 3,
@@ -167,7 +189,7 @@
167
  "attributes": {}
168
  }
169
  },
170
- "total_flos": 7466017483653120.0,
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": 0.018810251587114978,
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": 49.249,
149
  "eval_steps_per_second": 6.16,
150
  "step": 35
151
+ },
152
+ {
153
+ "epoch": 0.01692922642840348,
154
+ "grad_norm": 0.4719478487968445,
155
+ "learning_rate": 2.7300475013022663e-05,
156
+ "loss": 1.1109,
157
+ "step": 36
158
+ },
159
+ {
160
+ "epoch": 0.018339995297437104,
161
+ "grad_norm": 0.3741627335548401,
162
+ "learning_rate": 1.7527597583490822e-05,
163
+ "loss": 1.2164,
164
+ "step": 39
165
+ },
166
+ {
167
+ "epoch": 0.018810251587114978,
168
+ "eval_loss": 1.1306617259979248,
169
+ "eval_runtime": 72.6878,
170
+ "eval_samples_per_second": 49.279,
171
+ "eval_steps_per_second": 6.163,
172
+ "step": 40
173
  }
174
  ],
175
  "logging_steps": 3,
 
189
  "attributes": {}
190
  }
191
  },
192
+ "total_flos": 8532591409889280.0,
193
  "train_batch_size": 8,
194
  "trial_name": null,
195
  "trial_params": null