mikhail-panzo
commited on
Commit
•
b33ec30
1
Parent(s):
3d36971
Training in progress, step 1500, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 577789320
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0b3878b2837c54460760b7689511b1b119ade195a40bcc1bd58d5a2fa1c333cc
|
3 |
size 577789320
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1155772233
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:15856761cc33aa3ef4082afef8bcd92b764bb43930646ef8255717cfd74acefa
|
3 |
size 1155772233
|
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:dc65651f7b378ef8fe4da6f30ced75150f8b4133aff002554882ce4b7f48b94e
|
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 sha256:1a94e74103068a5fb8b31be8524087df4f57bd43f07d1db2b9d36084882fdbb5
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "mikhail_panzo/zlm_b128_le4_s8000/checkpoint-
|
4 |
-
"epoch":
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -163,6 +163,84 @@
|
|
163 |
"eval_samples_per_second": 31.959,
|
164 |
"eval_steps_per_second": 3.998,
|
165 |
"step": 1000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
166 |
}
|
167 |
],
|
168 |
"logging_steps": 50,
|
@@ -182,7 +260,7 @@
|
|
182 |
"attributes": {}
|
183 |
}
|
184 |
},
|
185 |
-
"total_flos":
|
186 |
"train_batch_size": 16,
|
187 |
"trial_name": null,
|
188 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.3853827118873596,
|
3 |
+
"best_model_checkpoint": "mikhail_panzo/zlm_b128_le4_s8000/checkpoint-1500",
|
4 |
+
"epoch": 2.513089005235602,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 1500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
163 |
"eval_samples_per_second": 31.959,
|
164 |
"eval_steps_per_second": 3.998,
|
165 |
"step": 1000
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 1.7591623036649215,
|
169 |
+
"grad_norm": 4.97900390625,
|
170 |
+
"learning_rate": 5.245e-05,
|
171 |
+
"loss": 0.4553,
|
172 |
+
"step": 1050
|
173 |
+
},
|
174 |
+
{
|
175 |
+
"epoch": 1.8429319371727748,
|
176 |
+
"grad_norm": 1.9889676570892334,
|
177 |
+
"learning_rate": 5.495e-05,
|
178 |
+
"loss": 0.449,
|
179 |
+
"step": 1100
|
180 |
+
},
|
181 |
+
{
|
182 |
+
"epoch": 1.9267015706806283,
|
183 |
+
"grad_norm": 1.5135546922683716,
|
184 |
+
"learning_rate": 5.745e-05,
|
185 |
+
"loss": 0.4353,
|
186 |
+
"step": 1150
|
187 |
+
},
|
188 |
+
{
|
189 |
+
"epoch": 2.0104712041884816,
|
190 |
+
"grad_norm": 7.610673904418945,
|
191 |
+
"learning_rate": 5.995000000000001e-05,
|
192 |
+
"loss": 0.4311,
|
193 |
+
"step": 1200
|
194 |
+
},
|
195 |
+
{
|
196 |
+
"epoch": 2.094240837696335,
|
197 |
+
"grad_norm": 2.049562454223633,
|
198 |
+
"learning_rate": 6.245000000000001e-05,
|
199 |
+
"loss": 0.4312,
|
200 |
+
"step": 1250
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 2.1780104712041886,
|
204 |
+
"grad_norm": 1.4102027416229248,
|
205 |
+
"learning_rate": 6.494999999999999e-05,
|
206 |
+
"loss": 0.4282,
|
207 |
+
"step": 1300
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 2.261780104712042,
|
211 |
+
"grad_norm": 1.701119065284729,
|
212 |
+
"learning_rate": 6.745e-05,
|
213 |
+
"loss": 0.4272,
|
214 |
+
"step": 1350
|
215 |
+
},
|
216 |
+
{
|
217 |
+
"epoch": 2.345549738219895,
|
218 |
+
"grad_norm": 2.0149667263031006,
|
219 |
+
"learning_rate": 6.995e-05,
|
220 |
+
"loss": 0.4277,
|
221 |
+
"step": 1400
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 2.4293193717277486,
|
225 |
+
"grad_norm": 2.1658883094787598,
|
226 |
+
"learning_rate": 7.245000000000001e-05,
|
227 |
+
"loss": 0.4247,
|
228 |
+
"step": 1450
|
229 |
+
},
|
230 |
+
{
|
231 |
+
"epoch": 2.513089005235602,
|
232 |
+
"grad_norm": 2.6821463108062744,
|
233 |
+
"learning_rate": 7.495e-05,
|
234 |
+
"loss": 0.4169,
|
235 |
+
"step": 1500
|
236 |
+
},
|
237 |
+
{
|
238 |
+
"epoch": 2.513089005235602,
|
239 |
+
"eval_loss": 0.3853827118873596,
|
240 |
+
"eval_runtime": 269.2607,
|
241 |
+
"eval_samples_per_second": 31.527,
|
242 |
+
"eval_steps_per_second": 3.944,
|
243 |
+
"step": 1500
|
244 |
}
|
245 |
],
|
246 |
"logging_steps": 50,
|
|
|
260 |
"attributes": {}
|
261 |
}
|
262 |
},
|
263 |
+
"total_flos": 2.686672014814656e+16,
|
264 |
"train_batch_size": 16,
|
265 |
"trial_name": null,
|
266 |
"trial_params": null
|