Nexspear commited on
Commit
b3a2c8e
·
verified ·
1 Parent(s): 4d1f267

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 sha256:9b4e9fe3a11c0765df2ef2a681de6cf73de293693def2c6626a8db4db4156545
3
  size 338298
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e0d2d46cbdc4b9220d6a849a4a7e2897d04a26f4ceb3fc6d36cfb3722da27ed
3
  size 338298
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5270fd8e4813d1c8e4a7815db833fb6624cf3f6f7acb5c7123e1c05b3ca089ff
3
  size 418030
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0eb587af29e9bd567091c9edc1922888b73d8ca2d4cc143c1d03589f6356311c
3
  size 418030
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dbc86b826bc6bd97d977ae368482d2b94ac269f5ff72bde8fe20b71551da06c3
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f7d8e9abeff9f0f2aa7d16e8494b24e0a7eaac3cc565c4ef78e32d32a521d4a
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": 1.2844036697247707,
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": 759.745,
149
  "eval_steps_per_second": 99.097,
150
  "step": 35
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
151
  }
152
  ],
153
  "logging_steps": 3,
@@ -167,7 +189,7 @@
167
  "attributes": {}
168
  }
169
  },
170
- "total_flos": 774308775936.0,
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": 1.4678899082568808,
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": 759.745,
149
  "eval_steps_per_second": 99.097,
150
  "step": 35
151
+ },
152
+ {
153
+ "epoch": 1.3211009174311927,
154
+ "grad_norm": 0.35859671235084534,
155
+ "learning_rate": 2.7300475013022663e-05,
156
+ "loss": 6.8617,
157
+ "step": 36
158
+ },
159
+ {
160
+ "epoch": 1.4311926605504588,
161
+ "grad_norm": 0.3261173963546753,
162
+ "learning_rate": 1.7527597583490822e-05,
163
+ "loss": 6.9499,
164
+ "step": 39
165
+ },
166
+ {
167
+ "epoch": 1.4678899082568808,
168
+ "eval_loss": 6.84140157699585,
169
+ "eval_runtime": 0.0596,
170
+ "eval_samples_per_second": 772.357,
171
+ "eval_steps_per_second": 100.742,
172
+ "step": 40
173
  }
174
  ],
175
  "logging_steps": 3,
 
189
  "attributes": {}
190
  }
191
  },
192
+ "total_flos": 904061061120.0,
193
  "train_batch_size": 8,
194
  "trial_name": null,
195
  "trial_params": null