youdiniplays
commited on
Training in progress, step 13500, 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 242041896
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:625bf3a433847c1dd928e96b95acde7c5d5f6a4d192bb7a79690072d47328999
|
3 |
size 242041896
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 484163514
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dfffb051b5b5ecf4aa823a5a841e408bb4bd2356d30a66c742c2f4439ba22694
|
3 |
size 484163514
|
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 sha256:0fc292cdd60119788481f9261515b741bb5c107be35c36f537c235b0c22cb88f
|
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 sha256:08340d7e451023d6e5027e0ecc2d66db41548ceae850547cbcb4dc2b78244ee8
|
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":
|
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,
|
@@ -173,13 +173,29 @@
|
|
173 |
"learning_rate": 0.0006011049723756906,
|
174 |
"loss": 0.5687,
|
175 |
"step": 13000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
176 |
}
|
177 |
],
|
178 |
"logging_steps": 500,
|
179 |
"max_steps": 32580,
|
180 |
"num_train_epochs": 5,
|
181 |
"save_steps": 500,
|
182 |
-
"total_flos":
|
183 |
"trial_name": null,
|
184 |
"trial_params": null
|
185 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.0718232044198897,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 13500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
173 |
"learning_rate": 0.0006011049723756906,
|
174 |
"loss": 0.5687,
|
175 |
"step": 13000
|
176 |
+
},
|
177 |
+
{
|
178 |
+
"epoch": 2.0,
|
179 |
+
"eval_bleu": 3.7119,
|
180 |
+
"eval_gen_len": 18.222,
|
181 |
+
"eval_loss": 0.495604932308197,
|
182 |
+
"eval_runtime": 23.8741,
|
183 |
+
"eval_samples_per_second": 41.886,
|
184 |
+
"eval_steps_per_second": 2.639,
|
185 |
+
"step": 13032
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 2.07,
|
189 |
+
"learning_rate": 0.0005857888275015347,
|
190 |
+
"loss": 0.5307,
|
191 |
+
"step": 13500
|
192 |
}
|
193 |
],
|
194 |
"logging_steps": 500,
|
195 |
"max_steps": 32580,
|
196 |
"num_train_epochs": 5,
|
197 |
"save_steps": 500,
|
198 |
+
"total_flos": 7155415308042240.0,
|
199 |
"trial_name": null,
|
200 |
"trial_params": null
|
201 |
}
|