Training in progress, step 2340, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ba3dbeb521958f247e981cc9357a52110e692ab35b2ff47ce61fc13a022a8ed
+oid sha256:7d157a2de57de3766c67e2fedb90dbedd863ee27fbdc9b500e5b311ab2a8cb4e
 size 1657

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6084ebd3cb3522527fa2c390f77b4851a0e9bb98d51c9ad4df67f6cb6b062b2f
+oid sha256:04fa25e9388774683abad5f52f7d8bf3b401156740b8a6ee95bd37f407a006da
 size 14709

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:951f68ac0f8d14680c5fad40e4807c509c5a199dd5c51ce40e692df67b5c28da
+oid sha256:ceba72caac3d96b175a57d13e43a1ebeb31cd0d6e696d5c10275c7562d5785f8
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 17.923076923076923,
+  "epoch": 18.0,
   "eval_steps": 500,
-  "global_step": 2330,
+  "global_step": 2340,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4202,6 +4202,24 @@
       "mean_token_accuracy": 0.646085774898529,
       "num_tokens": 8496986.0,
       "step": 2330
+    },
+    {
+      "epoch": 17.96153846153846,
+      "grad_norm": 0.0,
+      "learning_rate": 3.833e-05,
+      "loss": 1.7343,
+      "mean_token_accuracy": 0.6486167579889297,
+      "num_tokens": 8515399.0,
+      "step": 2335
+    },
+    {
+      "epoch": 18.0,
+      "grad_norm": 0.0,
+      "learning_rate": 3.8305e-05,
+      "loss": 1.7085,
+      "mean_token_accuracy": 0.658332034945488,
+      "num_tokens": 8533890.0,
+      "step": 2340
     }
   ],
   "logging_steps": 5,
@@ -4221,7 +4239,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.3057316051582976e+17,
+  "total_flos": 4.324631086935245e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null