Training in progress, step 1200, 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 19669752
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7081a0138a5a6607d5d779a29fb6a362bf282f4a1f6dba345f9cbdae40743331
|
3 |
size 19669752
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 39356997
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c21820119f05928026f693bc389cb44eda04bf237424f6955cacebb062da0ff2
|
3 |
size 39356997
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb6764dc3e1fe015624f31dc2613389c8754599510448c4c64c983ace14a8916
|
3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3d8d6be7898f87772ccbc5c732e900fe63a643c4595ce6af3d6bc6f811ba4b65
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "./outputs/checkpoint-
|
4 |
-
"epoch": 1.
|
5 |
"eval_steps": 100,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -161,6 +161,20 @@
|
|
161 |
"eval_samples_per_second": 2.481,
|
162 |
"eval_steps_per_second": 0.311,
|
163 |
"step": 1100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
164 |
}
|
165 |
],
|
166 |
"logging_steps": 100,
|
@@ -168,7 +182,7 @@
|
|
168 |
"num_input_tokens_seen": 0,
|
169 |
"num_train_epochs": 5,
|
170 |
"save_steps": 100,
|
171 |
-
"total_flos":
|
172 |
"trial_name": null,
|
173 |
"trial_params": null
|
174 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.9784607887268066,
|
3 |
+
"best_model_checkpoint": "./outputs/checkpoint-1200",
|
4 |
+
"epoch": 1.6,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 1200,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
161 |
"eval_samples_per_second": 2.481,
|
162 |
"eval_steps_per_second": 0.311,
|
163 |
"step": 1100
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 1.6,
|
167 |
+
"learning_rate": 0.0002,
|
168 |
+
"loss": 0.8091,
|
169 |
+
"step": 1200
|
170 |
+
},
|
171 |
+
{
|
172 |
+
"epoch": 1.6,
|
173 |
+
"eval_loss": 0.9784607887268066,
|
174 |
+
"eval_runtime": 780.7522,
|
175 |
+
"eval_samples_per_second": 2.472,
|
176 |
+
"eval_steps_per_second": 0.31,
|
177 |
+
"step": 1200
|
178 |
}
|
179 |
],
|
180 |
"logging_steps": 100,
|
|
|
182 |
"num_input_tokens_seen": 0,
|
183 |
"num_train_epochs": 5,
|
184 |
"save_steps": 100,
|
185 |
+
"total_flos": 3.108344477177856e+17,
|
186 |
"trial_name": null,
|
187 |
"trial_params": null
|
188 |
}
|