Training in progress, epoch 7, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 737722356
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0b0ff0d2efae69a63c4480e31b3e0f95982bc222a8480dcc53f28de19b7aa366
|
| 3 |
size 737722356
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1475564538
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f11b81e206a0fb0ba631637ddc19a9ee68a5208e792c8bed8108a92f5a88f883
|
| 3 |
size 1475564538
|
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:f415da0cb308c9dae6ffd1aaf4430c8311f998460c9c29a4be9af8a552a3a81c
|
| 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 sha256:4512033475c77e3052594c5f3b7b6b276c78cc2ab4b304f66f8e700255ff821a
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.2747629944426283,
|
| 3 |
"best_model_checkpoint": "debertalarge-medical-classifier/checkpoint-366",
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -131,6 +131,29 @@
|
|
| 131 |
"eval_samples_per_second": 7.052,
|
| 132 |
"eval_steps_per_second": 3.526,
|
| 133 |
"step": 1098
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 134 |
}
|
| 135 |
],
|
| 136 |
"logging_steps": 100,
|
|
@@ -150,7 +173,7 @@
|
|
| 150 |
"attributes": {}
|
| 151 |
}
|
| 152 |
},
|
| 153 |
-
"total_flos":
|
| 154 |
"train_batch_size": 2,
|
| 155 |
"trial_name": null,
|
| 156 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.2747629944426283,
|
| 3 |
"best_model_checkpoint": "debertalarge-medical-classifier/checkpoint-366",
|
| 4 |
+
"epoch": 7.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 1281,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 131 |
"eval_samples_per_second": 7.052,
|
| 132 |
"eval_steps_per_second": 3.526,
|
| 133 |
"step": 1098
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 6.0109289617486334,
|
| 137 |
+
"grad_norm": 5.487387180328369,
|
| 138 |
+
"learning_rate": 3.797814207650273e-05,
|
| 139 |
+
"loss": 1.0568,
|
| 140 |
+
"step": 1100
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 6.557377049180328,
|
| 144 |
+
"grad_norm": 4.660529136657715,
|
| 145 |
+
"learning_rate": 3.6885245901639346e-05,
|
| 146 |
+
"loss": 1.0621,
|
| 147 |
+
"step": 1200
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 7.0,
|
| 151 |
+
"eval_f1": 0.2747629944426283,
|
| 152 |
+
"eval_loss": 1.1170544624328613,
|
| 153 |
+
"eval_runtime": 13.0506,
|
| 154 |
+
"eval_samples_per_second": 7.049,
|
| 155 |
+
"eval_steps_per_second": 3.525,
|
| 156 |
+
"step": 1281
|
| 157 |
}
|
| 158 |
],
|
| 159 |
"logging_steps": 100,
|
|
|
|
| 173 |
"attributes": {}
|
| 174 |
}
|
| 175 |
},
|
| 176 |
+
"total_flos": 3413855038230000.0,
|
| 177 |
"train_batch_size": 2,
|
| 178 |
"trial_name": null,
|
| 179 |
"trial_params": null
|