Training in progress, step 45, 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 17425352
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ca2808b22a046cedf32118a5c1ed580c70b08ca00131af3cad76dd0c132ef24b
|
3 |
size 17425352
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 10251668
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b96d47e5e7fe7ffbe3fc00ec5febf40414638ad9ab43e2be8b8ac282366fe0f
|
3 |
size 10251668
|
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 sha256:78eaecaee821e1ec7f57e3cf3b6f1e7d10081600bd918c707846ea98564fc064
|
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 sha256:0896677f34f08366c4c71a3f69133212afc490296ec7ee225b8aefde1f38f24c
|
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,
|
@@ -131,6 +131,35 @@
|
|
131 |
"eval_samples_per_second": 69.294,
|
132 |
"eval_steps_per_second": 8.71,
|
133 |
"step": 36
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
134 |
}
|
135 |
],
|
136 |
"logging_steps": 3,
|
@@ -150,7 +179,7 @@
|
|
150 |
"attributes": {}
|
151 |
}
|
152 |
},
|
153 |
-
"total_flos":
|
154 |
"train_batch_size": 8,
|
155 |
"trial_name": null,
|
156 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.10465116279069768,
|
5 |
"eval_steps": 9,
|
6 |
+
"global_step": 45,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
131 |
"eval_samples_per_second": 69.294,
|
132 |
"eval_steps_per_second": 8.71,
|
133 |
"step": 36
|
134 |
+
},
|
135 |
+
{
|
136 |
+
"epoch": 0.09069767441860466,
|
137 |
+
"grad_norm": 1.4007647037506104,
|
138 |
+
"learning_rate": 7.649596321166024e-05,
|
139 |
+
"loss": 4.4604,
|
140 |
+
"step": 39
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 0.09767441860465116,
|
144 |
+
"grad_norm": 1.404478907585144,
|
145 |
+
"learning_rate": 7.191855733945387e-05,
|
146 |
+
"loss": 4.2265,
|
147 |
+
"step": 42
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 0.10465116279069768,
|
151 |
+
"grad_norm": 1.4139697551727295,
|
152 |
+
"learning_rate": 6.710100716628344e-05,
|
153 |
+
"loss": 4.1217,
|
154 |
+
"step": 45
|
155 |
+
},
|
156 |
+
{
|
157 |
+
"epoch": 0.10465116279069768,
|
158 |
+
"eval_loss": 4.179461479187012,
|
159 |
+
"eval_runtime": 10.381,
|
160 |
+
"eval_samples_per_second": 69.743,
|
161 |
+
"eval_steps_per_second": 8.766,
|
162 |
+
"step": 45
|
163 |
}
|
164 |
],
|
165 |
"logging_steps": 3,
|
|
|
179 |
"attributes": {}
|
180 |
}
|
181 |
},
|
182 |
+
"total_flos": 2822103996825600.0,
|
183 |
"train_batch_size": 8,
|
184 |
"trial_name": null,
|
185 |
"trial_params": null
|