Training in progress, step 187, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8972df4f58503ad22d7ff57e3830ad32eddf100b528da9c4e0c8f206bce2e335
+oid sha256:39902a9a2cc3980c8322eec02410f89ac9ce9098c7774922eda76b7d600cec41
 size 463916180

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d182bfd5f1f3e80a4ffaea26d66807cb524db3d8ed389024b3341ee47f4fe51
+oid sha256:0ad7d01ee99aa7c8ee93a8491d8ed964c00b893b999ae6497baae3f513ac48b0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fab1f30942a5e2bb9a9e5cc3477ef48cdcd39a7b78f8a45a46db0926bdbf2b4f
+oid sha256:43427779b8e6e83ef9780afcdea7472d2419de40e6f85cfedb90b60f89a2ff0f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9798270893371758,
+  "epoch": 1.079250720461095,
   "eval_steps": 17,
-  "global_step": 170,
+  "global_step": 187,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -487,6 +487,56 @@
       "eval_samples_per_second": 9.564,
       "eval_steps_per_second": 1.208,
       "step": 170
+    },
+    {
+      "epoch": 0.9855907780979827,
+      "grad_norm": NaN,
+      "learning_rate": 5.6388590278194096e-06,
+      "loss": 0.0,
+      "step": 171
+    },
+    {
+      "epoch": 1.0043227665706052,
+      "grad_norm": NaN,
+      "learning_rate": 4.549673247541875e-06,
+      "loss": 0.0,
+      "step": 174
+    },
+    {
+      "epoch": 1.021613832853026,
+      "grad_norm": NaN,
+      "learning_rate": 3.5722980755146517e-06,
+      "loss": 0.0,
+      "step": 177
+    },
+    {
+      "epoch": 1.0389048991354466,
+      "grad_norm": NaN,
+      "learning_rate": 2.7091379149682685e-06,
+      "loss": 0.0,
+      "step": 180
+    },
+    {
+      "epoch": 1.0561959654178674,
+      "grad_norm": NaN,
+      "learning_rate": 1.962316193157593e-06,
+      "loss": 0.0,
+      "step": 183
+    },
+    {
+      "epoch": 1.0734870317002883,
+      "grad_norm": NaN,
+      "learning_rate": 1.333670137599713e-06,
+      "loss": 0.0,
+      "step": 186
+    },
+    {
+      "epoch": 1.079250720461095,
+      "eval_loss": NaN,
+      "eval_runtime": 30.6268,
+      "eval_samples_per_second": 9.567,
+      "eval_steps_per_second": 1.208,
+      "step": 187
     }
   ],
   "logging_steps": 3,
@@ -506,7 +556,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.9861630372151296e+17,
+  "total_flos": 4.380717748322304e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null