Training in progress, step 3000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c72b0c08a0fc04f2c153825fcc0362e59c4afb8c1846b6e60697a4f256f4a98
+oid sha256:fa0e1101a7928c3bdee8510a8c27f892c295133ceff3f596bea16c69b8889147
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b7169cbbeba028ae9ab8039f7f1d231654e7b974aa4e1a587716973f591ee85
+oid sha256:767267c33ba45a25fe2e81d5c46be66aa26ea56509e863c6bf768b57469df4e0
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f80da795dbb27c3d8f1091b4c3160f1bae711b20ee8838c992f0071cc9f91f10
+oid sha256:9ccb60052eef72298bae34a53cf15b570d1ea8c23c2be486da135e9020a2e721
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d8d89f1ee6ff0e3b8b2a4fe1683c6e81327aff0190ec7348dca55e5b3647902
+oid sha256:301b38b5450010c3333e2f3ff82e4d11c803056aaea7e9900505a4d6beb8ec24
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.0390689941812137,
+  "epoch": 1.2468827930174564,
   "eval_steps": 500,
-  "global_step": 2500,
+  "global_step": 3000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -50,6 +50,13 @@
       "learning_rate": 1.5847049044056525e-05,
       "loss": 0.4225,
       "step": 2500
+    },
+    {
+      "epoch": 1.2468827930174564,
+      "grad_norm": 0.4491533637046814,
+      "learning_rate": 1.5015793848711555e-05,
+      "loss": 0.3857,
+      "step": 3000
     }
   ],
   "logging_steps": 500,
@@ -69,7 +76,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6088969947709440.0,
+  "total_flos": 7306885728829440.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null