Training in progress, step 400, 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 335604696
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:89e4fc406ba6296548b088b000ca6776a9c2e541c8b0d4e00344c909990666b2
|
| 3 |
size 335604696
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 170920532
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a11da54cfa812be39f8b26f552b9b807287bfd9f853fce46a42c2d8dd8d53b9a
|
| 3 |
size 170920532
|
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 sha256:4d711a29957e89eae8206124c2da2d44ff60e6e7e3fe36eda0f5f78dd4cf74b4
|
| 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 sha256:705cabf5cbc3a6ab0feb67c77b9b453d59efcc939ce90d310af96e621810f990
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 1.
|
| 3 |
-
"best_model_checkpoint": "miner_id_24/checkpoint-
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 50,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -127,6 +127,28 @@
|
|
| 127 |
"eval_samples_per_second": 14.14,
|
| 128 |
"eval_steps_per_second": 7.079,
|
| 129 |
"step": 350
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 130 |
}
|
| 131 |
],
|
| 132 |
"logging_steps": 40,
|
|
@@ -150,12 +172,12 @@
|
|
| 150 |
"should_evaluate": false,
|
| 151 |
"should_log": false,
|
| 152 |
"should_save": true,
|
| 153 |
-
"should_training_stop":
|
| 154 |
},
|
| 155 |
"attributes": {}
|
| 156 |
}
|
| 157 |
},
|
| 158 |
-
"total_flos": 1.
|
| 159 |
"train_batch_size": 2,
|
| 160 |
"trial_name": null,
|
| 161 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.38326895236969,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-400",
|
| 4 |
+
"epoch": 0.42406573018817917,
|
| 5 |
"eval_steps": 50,
|
| 6 |
+
"global_step": 400,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 127 |
"eval_samples_per_second": 14.14,
|
| 128 |
"eval_steps_per_second": 7.079,
|
| 129 |
"step": 350
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.3816591571693613,
|
| 133 |
+
"grad_norm": 13.651220321655273,
|
| 134 |
+
"learning_rate": 3.8060233744356633e-06,
|
| 135 |
+
"loss": 11.0192,
|
| 136 |
+
"step": 360
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.42406573018817917,
|
| 140 |
+
"grad_norm": 41.51972961425781,
|
| 141 |
+
"learning_rate": 0.0,
|
| 142 |
+
"loss": 11.2909,
|
| 143 |
+
"step": 400
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.42406573018817917,
|
| 147 |
+
"eval_loss": 1.38326895236969,
|
| 148 |
+
"eval_runtime": 54.7598,
|
| 149 |
+
"eval_samples_per_second": 14.518,
|
| 150 |
+
"eval_steps_per_second": 7.268,
|
| 151 |
+
"step": 400
|
| 152 |
}
|
| 153 |
],
|
| 154 |
"logging_steps": 40,
|
|
|
|
| 172 |
"should_evaluate": false,
|
| 173 |
"should_log": false,
|
| 174 |
"should_save": true,
|
| 175 |
+
"should_training_stop": true
|
| 176 |
},
|
| 177 |
"attributes": {}
|
| 178 |
}
|
| 179 |
},
|
| 180 |
+
"total_flos": 1.4290924208337715e+17,
|
| 181 |
"train_batch_size": 2,
|
| 182 |
"trial_name": null,
|
| 183 |
"trial_params": null
|