Training in progress, step 1560, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:300339dfe383b0a3bb11aaef4261f06083179ae53f288176abe344ca87d3b75a
+oid sha256:a321d2d7459c219022514e9d54a94e353a1056cffbafea144f447fdca5ed87c9
 size 1657

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af2725002d585692095173c2aafeea6b1ac9e833fd2d1055d616f4204665d5cb
+oid sha256:9822103f291deea194a08798f4303692a8d181da9b6cfb12b4c1f3509bd03304
 size 14709

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b38871718b3c21e76d305342366ed29975ae5a12b6739d0ad89221dbd86dbaff
+oid sha256:3f948a6d825bb0c1565fe404e64df78dc072b549bf830a9597b430aa186adf20
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 11.923076923076923,
+  "epoch": 12.0,
   "eval_steps": 500,
-  "global_step": 1550,
+  "global_step": 1560,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2798,6 +2798,24 @@
       "mean_token_accuracy": 0.6520039916038514,
       "num_tokens": 5653729.0,
       "step": 1550
+    },
+    {
+      "epoch": 11.961538461538462,
+      "grad_norm": 0.0,
+      "learning_rate": 4.223e-05,
+      "loss": 1.7762,
+      "mean_token_accuracy": 0.6417809814214707,
+      "num_tokens": 5671517.0,
+      "step": 1555
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 0.0,
+      "learning_rate": 4.2205e-05,
+      "loss": 1.7578,
+      "mean_token_accuracy": 0.6531469017267227,
+      "num_tokens": 5689260.0,
+      "step": 1560
     }
   ],
   "logging_steps": 5,
@@ -2817,7 +2835,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.8639201020198912e+17,
+  "total_flos": 2.8813778691489792e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null