Training in progress, step 81, 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 167832240
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:21a702125622497f8e1a266cff851c31f0af6df08973a95b88c8cd2fa8d6a699
|
| 3 |
size 167832240
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 85723284
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:16d76eb0160b88429b43609ecab0985e3970626b01efc669443c4b0b4b5fc38e
|
| 3 |
size 85723284
|
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 sha256:6d7ea42fd02efda1a047a0094244a6225d85beb88e53b4ff9e6300305c176cfe
|
| 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:b1133b8baf1f78a479e6941e3a9000541d5fa14f2c811a6967cd21e341a3a489
|
| 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,
|
|
@@ -128,6 +128,21 @@
|
|
| 128 |
"eval_samples_per_second": 25.988,
|
| 129 |
"eval_steps_per_second": 12.994,
|
| 130 |
"step": 72
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 131 |
}
|
| 132 |
],
|
| 133 |
"logging_steps": 10,
|
|
@@ -147,7 +162,7 @@
|
|
| 147 |
"attributes": {}
|
| 148 |
}
|
| 149 |
},
|
| 150 |
-
"total_flos": 1.
|
| 151 |
"train_batch_size": 2,
|
| 152 |
"trial_name": null,
|
| 153 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.004554655870445344,
|
| 5 |
"eval_steps": 9,
|
| 6 |
+
"global_step": 81,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 128 |
"eval_samples_per_second": 25.988,
|
| 129 |
"eval_steps_per_second": 12.994,
|
| 130 |
"step": 72
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.00449842555105713,
|
| 134 |
+
"grad_norm": 3.68632173538208,
|
| 135 |
+
"learning_rate": 2.339555568810221e-05,
|
| 136 |
+
"loss": 2.8912,
|
| 137 |
+
"step": 80
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.004554655870445344,
|
| 141 |
+
"eval_loss": 0.7495855093002319,
|
| 142 |
+
"eval_runtime": 288.8772,
|
| 143 |
+
"eval_samples_per_second": 25.921,
|
| 144 |
+
"eval_steps_per_second": 12.961,
|
| 145 |
+
"step": 81
|
| 146 |
}
|
| 147 |
],
|
| 148 |
"logging_steps": 10,
|
|
|
|
| 162 |
"attributes": {}
|
| 163 |
}
|
| 164 |
},
|
| 165 |
+
"total_flos": 1.5468848970989568e+16,
|
| 166 |
"train_batch_size": 2,
|
| 167 |
"trial_name": null,
|
| 168 |
"trial_params": null
|