Training in progress, step 90, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d10131fb2bdabea59625c8c4edf334e6df6721f617bf0dec9aaa337ebb104f71
+oid sha256:af3c3dabbf9ebbd1b80f42990a6c3852888dc418d3a491b6006d59ae622f7439
 size 1657

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a73c7d1b70990d010aed3d00a13855494c339ed8f762b75df50f3dea0d0a491
+oid sha256:3e932981fddaf964ea5c00183b0b2c9a613151b2952792ed5c32eb6ad9fba8a4
 size 14709

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd856c6151fe5255f7ba51db6b5d88b86efb0fa47af76b1fc101585c59f7e4b5
+oid sha256:caea65ad5ade87249f189f1780cfae3fe7eb60fb8c93dd1a0058a27c35eaba61
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6153846153846154,
+  "epoch": 0.6923076923076923,
   "eval_steps": 500,
-  "global_step": 80,
+  "global_step": 90,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -152,6 +152,24 @@
       "mean_token_accuracy": 0.6399475276470185,
       "num_tokens": 291226.0,
       "step": 80
+    },
+    {
+      "epoch": 0.6538461538461539,
+      "grad_norm": 0.0,
+      "learning_rate": 4.958e-05,
+      "loss": 1.7466,
+      "mean_token_accuracy": 0.645823523402214,
+      "num_tokens": 309131.0,
+      "step": 85
+    },
+    {
+      "epoch": 0.6923076923076923,
+      "grad_norm": 0.0,
+      "learning_rate": 4.9555e-05,
+      "loss": 1.6855,
+      "mean_token_accuracy": 0.6573584616184235,
+      "num_tokens": 328164.0,
+      "step": 90
     }
   ],
   "logging_steps": 5,
@@ -171,7 +189,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.469040538927104e+16,
+  "total_flos": 1.65717794930688e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null