Training in progress, step 4810, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df2e208838caa0a6289675c9590358044e0e119c1ed9f3d1b37bd90679b10249
+oid sha256:8b49635f70bbd69a00f438df95a9cdcc6d9a61445eb18dd00e109631002f7f2a
 size 1657

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09a6a2133adfd57ae6e9d5b505287ef4df9fe32c067ee56b438f532cb8890bec
+oid sha256:b3459accefe30b81e4f0140273d33d274224fc8b0e49d623140c6367d333f812
 size 14709

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:206c7ae40501025094ff9fb1a6e6708863e797e75b45c8e1f41c515f17ee9c79
+oid sha256:7094c98b4ac271398d9e3759c077bc279505e1d2385c5ac459e37b5e58eacbd1
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 36.92307692307692,
+  "epoch": 37.0,
   "eval_steps": 500,
-  "global_step": 4800,
+  "global_step": 4810,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -8648,6 +8648,24 @@
       "mean_token_accuracy": 0.6513243049383164,
       "num_tokens": 17503928.0,
       "step": 4800
+    },
+    {
+      "epoch": 36.96153846153846,
+      "grad_norm": 0.0,
+      "learning_rate": 2.598e-05,
+      "loss": 1.7178,
+      "mean_token_accuracy": 0.6609677881002426,
+      "num_tokens": 17522780.0,
+      "step": 4805
+    },
+    {
+      "epoch": 37.0,
+      "grad_norm": 0.0,
+      "learning_rate": 2.5955e-05,
+      "loss": 1.6678,
+      "mean_token_accuracy": 0.6652211785316468,
+      "num_tokens": 17541885.0,
+      "step": 4810
     }
   ],
   "logging_steps": 5,
@@ -8667,7 +8685,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.870252577398784e+17,
+  "total_flos": 8.889634747780301e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null