Training in progress, step 13000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e82e347b2238a2124e52fa6bbcb52a581a8376f642371fa693a2b74ccf64bbc
+oid sha256:7ce56d6e1b12fc08d34fa085b7ecb7582ed9bc689e265e45b39c951a16023b3a
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59483524ed5516cde7ebadc084d889b4039cb25a2ec01036cddccb6c62e4b263
+oid sha256:4efc04a4c9090911fd512babc5f1cb29b366fd9d6332e2ed33a01202d2743d4c
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f3dfe1e2f7f2fd5854887c0faffeef0e864d418e8da96df789b7b060dfeefbe
+oid sha256:5e9bd9c0c5f3829618d66a8ccc40a2ee0bf94db351e00ed3ee919d3ea07ee90c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:581f26c042b017b35232c26ec1300c4f70bffc2cf5f6d147680616274578d17d
+oid sha256:589ca601b575cfc7f004c136eb91b382b9a1be92a7e3c7f68f79df4414805284
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.597672485453034,
+  "epoch": 2.7015793848711556,
   "eval_steps": 500,
-  "global_step": 12500,
+  "global_step": 13000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,13 @@
       "learning_rate": 2.6891105569409807e-06,
       "loss": 0.3176,
       "step": 12500
+    },
+    {
+      "epoch": 2.7015793848711556,
+      "grad_norm": 1.0440038442611694,
+      "learning_rate": 1.99778331947908e-06,
+      "loss": 0.3391,
+      "step": 13000
     }
   ],
   "logging_steps": 500,
@@ -217,7 +224,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.522272934821888e+16,
+  "total_flos": 1.583168723877888e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null