Training in progress, step 170, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:245c0c581852f5a4742d5476e16c1f0433d867cdf59f2f601835367e559e8306
+oid sha256:8972df4f58503ad22d7ff57e3830ad32eddf100b528da9c4e0c8f206bce2e335
 size 463916180

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6921222b6e857f64e27a6fe774ce2e378a0123b0a5220012aaccf1acd1a03275
+oid sha256:5d182bfd5f1f3e80a4ffaea26d66807cb524db3d8ed389024b3341ee47f4fe51
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d99dc7a150ff6ed818c8735e9e9061e757b4b841b8d74bde2c9d7a2195ff136
+oid sha256:fab1f30942a5e2bb9a9e5cc3477ef48cdcd39a7b78f8a45a46db0926bdbf2b4f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8818443804034583,
+  "epoch": 0.9798270893371758,
   "eval_steps": 17,
-  "global_step": 153,
+  "global_step": 170,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -444,6 +444,49 @@
       "eval_samples_per_second": 9.56,
       "eval_steps_per_second": 1.207,
       "step": 153
+    },
+    {
+      "epoch": 0.899135446685879,
+      "grad_norm": NaN,
+      "learning_rate": 1.2658926150792322e-05,
+      "loss": 0.0,
+      "step": 156
+    },
+    {
+      "epoch": 0.9164265129682997,
+      "grad_norm": NaN,
+      "learning_rate": 1.1056136061894384e-05,
+      "loss": 0.0,
+      "step": 159
+    },
+    {
+      "epoch": 0.9337175792507204,
+      "grad_norm": NaN,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0,
+      "step": 162
+    },
+    {
+      "epoch": 0.9510086455331412,
+      "grad_norm": NaN,
+      "learning_rate": 8.141676086873572e-06,
+      "loss": 0.0,
+      "step": 165
+    },
+    {
+      "epoch": 0.968299711815562,
+      "grad_norm": NaN,
+      "learning_rate": 6.837175952121306e-06,
+      "loss": 0.0,
+      "step": 168
+    },
+    {
+      "epoch": 0.9798270893371758,
+      "eval_loss": NaN,
+      "eval_runtime": 30.6354,
+      "eval_samples_per_second": 9.564,
+      "eval_steps_per_second": 1.208,
+      "step": 170
     }
   ],
   "logging_steps": 3,
@@ -463,7 +506,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.591608326107955e+17,
+  "total_flos": 3.9861630372151296e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null