Training in progress, step 20, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 127206
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0c06da1bc4207d56e07328a440f79971d6e0469367c26ea2f6aeb051bfa12d2c
|
3 |
size 127206
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c5288ed9323916daf49e9e619b5ce81ab40c19e01021e3ee0c12210ac8bab7de
|
3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1e2ed9259304616a8ecebc61c5d000777b2978635f7a705b8d7081c480ce0bde
|
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.
|
5 |
"eval_steps": 5,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -144,6 +144,49 @@
|
|
144 |
"eval_samples_per_second": 209.536,
|
145 |
"eval_steps_per_second": 104.781,
|
146 |
"step": 15
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
147 |
}
|
148 |
],
|
149 |
"logging_steps": 1,
|
@@ -158,12 +201,12 @@
|
|
158 |
"should_evaluate": false,
|
159 |
"should_log": false,
|
160 |
"should_save": true,
|
161 |
-
"should_training_stop":
|
162 |
},
|
163 |
"attributes": {}
|
164 |
}
|
165 |
},
|
166 |
-
"total_flos":
|
167 |
"train_batch_size": 2,
|
168 |
"trial_name": null,
|
169 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.0010177728585422949,
|
5 |
"eval_steps": 5,
|
6 |
+
"global_step": 20,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
144 |
"eval_samples_per_second": 209.536,
|
145 |
"eval_steps_per_second": 104.781,
|
146 |
"step": 15
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 0.0008142182868338359,
|
150 |
+
"grad_norm": NaN,
|
151 |
+
"learning_rate": 6.909830056250527e-05,
|
152 |
+
"loss": 0.0,
|
153 |
+
"step": 16
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 0.0008651069297609506,
|
157 |
+
"grad_norm": NaN,
|
158 |
+
"learning_rate": 4.12214747707527e-05,
|
159 |
+
"loss": 0.0,
|
160 |
+
"step": 17
|
161 |
+
},
|
162 |
+
{
|
163 |
+
"epoch": 0.0009159955726880653,
|
164 |
+
"grad_norm": NaN,
|
165 |
+
"learning_rate": 1.9098300562505266e-05,
|
166 |
+
"loss": 0.0,
|
167 |
+
"step": 18
|
168 |
+
},
|
169 |
+
{
|
170 |
+
"epoch": 0.0009668842156151801,
|
171 |
+
"grad_norm": NaN,
|
172 |
+
"learning_rate": 4.8943483704846475e-06,
|
173 |
+
"loss": 0.0,
|
174 |
+
"step": 19
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 0.0010177728585422949,
|
178 |
+
"grad_norm": NaN,
|
179 |
+
"learning_rate": 0.0,
|
180 |
+
"loss": 0.0,
|
181 |
+
"step": 20
|
182 |
+
},
|
183 |
+
{
|
184 |
+
"epoch": 0.0010177728585422949,
|
185 |
+
"eval_loss": NaN,
|
186 |
+
"eval_runtime": 39.886,
|
187 |
+
"eval_samples_per_second": 207.466,
|
188 |
+
"eval_steps_per_second": 103.746,
|
189 |
+
"step": 20
|
190 |
}
|
191 |
],
|
192 |
"logging_steps": 1,
|
|
|
201 |
"should_evaluate": false,
|
202 |
"should_log": false,
|
203 |
"should_save": true,
|
204 |
+
"should_training_stop": true
|
205 |
},
|
206 |
"attributes": {}
|
207 |
}
|
208 |
},
|
209 |
+
"total_flos": 2066743296000.0,
|
210 |
"train_batch_size": 2,
|
211 |
"trial_name": null,
|
212 |
"trial_params": null
|