Training in progress, step 35, 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 645975704
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6601dc7e2f761a1968547c5ee629171ed29f9d74a090aee0db8d745d59f9b40a
|
3 |
size 645975704
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 328468404
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fc5de1584cb0f6db2acf05f372889712bdd91cb654be46d033d6b134d145e472
|
3 |
size 328468404
|
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:c6642c795992de4a9a059ebf810bad439cf695245a90f881dd6f81c926c322bf
|
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 sha256:88f387d8c434535a84694e469cebc18f2e722ba31b0dc0372632798b59011377
|
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": 5,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -133,6 +133,21 @@
|
|
133 |
"eval_samples_per_second": 16.024,
|
134 |
"eval_steps_per_second": 4.006,
|
135 |
"step": 30
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
136 |
}
|
137 |
],
|
138 |
"logging_steps": 3,
|
@@ -152,7 +167,7 @@
|
|
152 |
"attributes": {}
|
153 |
}
|
154 |
},
|
155 |
-
"total_flos":
|
156 |
"train_batch_size": 4,
|
157 |
"trial_name": null,
|
158 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.003265039588605012,
|
5 |
"eval_steps": 5,
|
6 |
+
"global_step": 35,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
133 |
"eval_samples_per_second": 16.024,
|
134 |
"eval_steps_per_second": 4.006,
|
135 |
"step": 30
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.0030784658978275825,
|
139 |
+
"grad_norm": 1.7494417428970337,
|
140 |
+
"learning_rate": 3.832773180720475e-05,
|
141 |
+
"loss": 1.0393,
|
142 |
+
"step": 33
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.003265039588605012,
|
146 |
+
"eval_loss": 0.9136942625045776,
|
147 |
+
"eval_runtime": 1127.0527,
|
148 |
+
"eval_samples_per_second": 16.02,
|
149 |
+
"eval_steps_per_second": 4.005,
|
150 |
+
"step": 35
|
151 |
}
|
152 |
],
|
153 |
"logging_steps": 3,
|
|
|
167 |
"attributes": {}
|
168 |
}
|
169 |
},
|
170 |
+
"total_flos": 4.283439664594944e+16,
|
171 |
"train_batch_size": 4,
|
172 |
"trial_name": null,
|
173 |
"trial_params": null
|