Training in progress, step 300, 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 109009752
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:afabeef02cd11af399f30d799a87cdcedf48e6b4b308ff1e8fd648227d65f416
|
3 |
size 109009752
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 56088788
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:db08a3ed0537b4834693fbc56c2a76f165e2d16d1f603f5b5c5e165ccb95904a
|
3 |
size 56088788
|
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 sha256:5c130768bbf9cce1ebe68f09044324e0bfed8c7b5372544cfaddcff885c19347
|
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 sha256:3eda02c74ec58a373b407bd46f7ba99a11b2d14ed57d7fd11002c322f6ba0709
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 4.
|
3 |
-
"best_model_checkpoint": "miner_id_24/checkpoint-
|
4 |
-
"epoch":
|
5 |
"eval_steps": 20,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -141,6 +141,21 @@
|
|
141 |
"eval_samples_per_second": 28.669,
|
142 |
"eval_steps_per_second": 0.917,
|
143 |
"step": 280
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
144 |
}
|
145 |
],
|
146 |
"logging_steps": 100,
|
@@ -169,7 +184,7 @@
|
|
169 |
"attributes": {}
|
170 |
}
|
171 |
},
|
172 |
-
"total_flos": 1.
|
173 |
"train_batch_size": 8,
|
174 |
"trial_name": null,
|
175 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 4.185091029285104e-07,
|
3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-300",
|
4 |
+
"epoch": 2.0202020202020203,
|
5 |
"eval_steps": 20,
|
6 |
+
"global_step": 300,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
141 |
"eval_samples_per_second": 28.669,
|
142 |
"eval_steps_per_second": 0.917,
|
143 |
"step": 280
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 2.0202020202020203,
|
147 |
+
"grad_norm": 1.0282737093803007e-05,
|
148 |
+
"learning_rate": 0.00019721004253231048,
|
149 |
+
"loss": 0.0,
|
150 |
+
"step": 300
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 2.0202020202020203,
|
154 |
+
"eval_loss": 4.185091029285104e-07,
|
155 |
+
"eval_runtime": 4.3862,
|
156 |
+
"eval_samples_per_second": 28.499,
|
157 |
+
"eval_steps_per_second": 0.912,
|
158 |
+
"step": 300
|
159 |
}
|
160 |
],
|
161 |
"logging_steps": 100,
|
|
|
184 |
"attributes": {}
|
185 |
}
|
186 |
},
|
187 |
+
"total_flos": 1.2667815790116864e+17,
|
188 |
"train_batch_size": 8,
|
189 |
"trial_name": null,
|
190 |
"trial_params": null
|