Training in progress, step 2600, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2078850e95dd3e0755bc00fc0358edde6cd8e9f657e8eeb1294b9f89c70bb012
+oid sha256:df2a4107de016999ff1d0603a7fa6efb4be0ac726ab9caa90cd925f03f2b4488
 size 1657

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b55b2e17717df5a8df6a921b82d7159722f8863993e04ea408e6223053fdd627
+oid sha256:de0debf99c4bc6694b000e4432ec824138f343c807196d46f19724581267657e
 size 14709

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9a23fd110008fbdd7238d99c211b8a8860aac50ace10e62d568c287376696da
+oid sha256:90058db25f93a99306327ebacdf603bd0cbe93e75f8d69e4ae001b2e7b0c3f2c
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 19.923076923076923,
+  "epoch": 20.0,
   "eval_steps": 500,
-  "global_step": 2590,
+  "global_step": 2600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4670,6 +4670,24 @@
       "mean_token_accuracy": 0.6500475823879241,
       "num_tokens": 9445373.0,
       "step": 2590
+    },
+    {
+      "epoch": 19.96153846153846,
+      "grad_norm": 0.0,
+      "learning_rate": 3.703e-05,
+      "loss": 1.763,
+      "mean_token_accuracy": 0.6419122099876404,
+      "num_tokens": 9463346.0,
+      "step": 2595
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 0.0,
+      "learning_rate": 3.7005e-05,
+      "loss": 1.7377,
+      "mean_token_accuracy": 0.6534196078777313,
+      "num_tokens": 9482100.0,
+      "step": 2600
     }
   ],
   "logging_steps": 5,
@@ -4689,7 +4707,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.787869246090445e+17,
+  "total_flos": 4.8058176407814144e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null