Training in progress, step 3500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8b758f8e183471747d3d3f52b864b20d882a9aa0bca9a7b221862cac7093cd2
+oid sha256:4a6fab06d50f849f81115a440fddcc69032f7f246b0d840c83a728909f4d6a04
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03fa0cc049fd3fab193777840d0153a64719ec79e7f70c56f011e64169f1d1fd
+oid sha256:ba2413906e6b2ccfafc1e48cdc9d77563e5c7d0dc2a967e39e48f008f36c7fd4
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc617f0a2f1b846390f426514e6959c82d9ccca5a06fae71b1179457baa9dd5f
+oid sha256:b11c05638bda866f239e62be186f5d45223ea93c75579fa732877ff4152241e3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:346a20d6aa585567535ead6c7378b42808548809d68f384868746403a054dab0
+oid sha256:ba54f9fe023975b85168af100e7732b40b2c7c545baa0b2edcf89745104d9360
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6234413965087282,
+  "epoch": 0.7273482959268496,
   "eval_steps": 500,
-  "global_step": 3000,
+  "global_step": 3500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -49,6 +49,13 @@
       "learning_rate": 1.584788029925187e-05,
       "loss": 0.4192,
       "step": 3000
+    },
+    {
+      "epoch": 0.7273482959268496,
+      "grad_norm": 1.0237222909927368,
+      "learning_rate": 1.5155167636464397e-05,
+      "loss": 0.422,
+      "step": 3500
     }
   ],
   "logging_steps": 500,
@@ -68,7 +75,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3653747343360000.0,
+  "total_flos": 4262705233920000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null