Training in progress, step 170, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91460c637af7b8318a008f5db06b2f3c3fefafb5d59561955cb47613358e9335
+oid sha256:75a369187d1170a2bd32bad16dbf90e1bcb0041cd18759311c7017a529357815
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8caf663a3a910c8f92ebe0d20a15ad9488b0c09bf932ba74507efdbf2808bebb
+oid sha256:390299ac338a4982ff00aeb5f9649ef7dfc41f92f5356d758445737978f9a779
 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": 0.888243831640058,
+  "epoch": 0.9869375907111756,
   "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": 7.064,
       "eval_steps_per_second": 0.901,
       "step": 153
+    },
+    {
+      "epoch": 0.9056603773584906,
+      "grad_norm": NaN,
+      "learning_rate": 1.2658926150792322e-05,
+      "loss": 0.0,
+      "step": 156
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "grad_norm": NaN,
+      "learning_rate": 1.1056136061894384e-05,
+      "loss": 0.0,
+      "step": 159
+    },
+    {
+      "epoch": 0.9404934687953556,
+      "grad_norm": NaN,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0,
+      "step": 162
+    },
+    {
+      "epoch": 0.9579100145137881,
+      "grad_norm": NaN,
+      "learning_rate": 8.141676086873572e-06,
+      "loss": 0.0,
+      "step": 165
+    },
+    {
+      "epoch": 0.9753265602322206,
+      "grad_norm": NaN,
+      "learning_rate": 6.837175952121306e-06,
+      "loss": 0.0,
+      "step": 168
+    },
+    {
+      "epoch": 0.9869375907111756,
+      "eval_loss": NaN,
+      "eval_runtime": 41.0328,
+      "eval_samples_per_second": 7.068,
+      "eval_steps_per_second": 0.902,
+      "step": 170
     }
   ],
   "logging_steps": 3,
@@ -463,7 +506,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.380746441891512e+17,
+  "total_flos": 4.867496046546125e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null