Training in progress, step 13500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ce56d6e1b12fc08d34fa085b7ecb7582ed9bc689e265e45b39c951a16023b3a
+oid sha256:3b2c636d3c3e8132092a3551439058aa36089dde96eac4200127bfefb9356356
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4efc04a4c9090911fd512babc5f1cb29b366fd9d6332e2ed33a01202d2743d4c
+oid sha256:bdc5738e16951e311cd2a68323280e285d60e2aee01ef96983657ea1571a8776
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e9bd9c0c5f3829618d66a8ccc40a2ee0bf94db351e00ed3ee919d3ea07ee90c
+oid sha256:5c0464ef7b8033abc039566dee85b9115e703e8f7542cc7dba40663c87de21b6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:589ca601b575cfc7f004c136eb91b382b9a1be92a7e3c7f68f79df4414805284
+oid sha256:575df2908db98862a8edb86a2879682fc9cbe014aa13a1c0e8845ea12be8611c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.7015793848711556,
+  "epoch": 2.8054862842892767,
   "eval_steps": 500,
-  "global_step": 13000,
+  "global_step": 13500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -205,6 +205,13 @@
       "learning_rate": 1.99778331947908e-06,
       "loss": 0.3391,
       "step": 13000
+    },
+    {
+      "epoch": 2.8054862842892767,
+      "grad_norm": 1.7209734916687012,
+      "learning_rate": 1.3050706566916044e-06,
+      "loss": 0.3164,
+      "step": 13500
     }
   ],
   "logging_steps": 500,
@@ -224,7 +231,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.583168723877888e+16,
+  "total_flos": 1.644064512933888e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null