Training in progress, step 54, 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:
|
3 |
size 72396376
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:47813f3c69a0b2bf2c9430e79720632d47df402a37a94edd015f20805efd03cf
|
3 |
size 72396376
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 37134420
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c7638455d6d234f2e7c8d948452f17ebb452a039a527a6cc29d90472abc76ba6
|
3 |
size 37134420
|
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 sha256:97d65adce7978ad1b4b9fdc19cba4b652f0d74e711c552837268b4fa6ebfd755
|
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:ec430a8fba90f7f39f74e916eb32712c363a0fd20bb4904251fce0eb82f2b9cf
|
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": 9,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -160,6 +160,35 @@
|
|
160 |
"eval_samples_per_second": 17.571,
|
161 |
"eval_steps_per_second": 2.21,
|
162 |
"step": 45
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
163 |
}
|
164 |
],
|
165 |
"logging_steps": 3,
|
@@ -179,7 +208,7 @@
|
|
179 |
"attributes": {}
|
180 |
}
|
181 |
},
|
182 |
-
"total_flos":
|
183 |
"train_batch_size": 8,
|
184 |
"trial_name": null,
|
185 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.10892586989409984,
|
5 |
"eval_steps": 9,
|
6 |
+
"global_step": 54,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
160 |
"eval_samples_per_second": 17.571,
|
161 |
"eval_steps_per_second": 2.21,
|
162 |
"step": 45
|
163 |
+
},
|
164 |
+
{
|
165 |
+
"epoch": 0.09682299546142209,
|
166 |
+
"grad_norm": 0.080069400370121,
|
167 |
+
"learning_rate": 3.104804738999169e-05,
|
168 |
+
"loss": 1.2464,
|
169 |
+
"step": 48
|
170 |
+
},
|
171 |
+
{
|
172 |
+
"epoch": 0.10287443267776097,
|
173 |
+
"grad_norm": 0.08555633574724197,
|
174 |
+
"learning_rate": 2.8479327524001636e-05,
|
175 |
+
"loss": 1.4155,
|
176 |
+
"step": 51
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 0.10892586989409984,
|
180 |
+
"grad_norm": 0.082075335085392,
|
181 |
+
"learning_rate": 2.587248741756253e-05,
|
182 |
+
"loss": 1.3722,
|
183 |
+
"step": 54
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 0.10892586989409984,
|
187 |
+
"eval_loss": 1.3156965970993042,
|
188 |
+
"eval_runtime": 47.5204,
|
189 |
+
"eval_samples_per_second": 17.571,
|
190 |
+
"eval_steps_per_second": 2.21,
|
191 |
+
"step": 54
|
192 |
}
|
193 |
],
|
194 |
"logging_steps": 3,
|
|
|
208 |
"attributes": {}
|
209 |
}
|
210 |
},
|
211 |
+
"total_flos": 3.4585413666471936e+16,
|
212 |
"train_batch_size": 8,
|
213 |
"trial_name": null,
|
214 |
"trial_params": null
|