Training in progress, step 4000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4415a57ed1e906d7ff833556b8a11f027662dd448248d9ae50f44e7e62ce6cf
+oid sha256:1a1526ce35959c2aafc5ee860281c41c0885235aa4acf92b63b315011ed4da93
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ae503b116281a5be4ce2cb1c0c2285ad2f47b8c195efb474680b2c075e541be
+oid sha256:1bf30eb76d8e637486d38576ec2d8c3027b12ad2bd71cb6716b79761a591173f
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b11c05638bda866f239e62be186f5d45223ea93c75579fa732877ff4152241e3
+oid sha256:e6909786b07113d046b6984022b8f3c1d4a309c9e0a18f83af53a35bec4523b1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba54f9fe023975b85168af100e7732b40b2c7c545baa0b2edcf89745104d9360
+oid sha256:09e9e60d2c8faf134da25c0954086bcd3b7f390c1be768462509e5eb18839183
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7273482959268496,
+  "epoch": 0.8312551953449709,
   "eval_steps": 500,
-  "global_step": 3500,
+  "global_step": 4000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -56,6 +56,13 @@
       "learning_rate": 1.5155167636464397e-05,
       "loss": 0.4215,
       "step": 3500
+    },
+    {
+      "epoch": 0.8312551953449709,
+      "grad_norm": 1.6476292610168457,
+      "learning_rate": 1.446245497367692e-05,
+      "loss": 0.4062,
+      "step": 4000
     }
   ],
   "logging_steps": 500,
@@ -75,7 +82,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4262705233920000.0,
+  "total_flos": 4871663124480000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null