Training in progress, step 14000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b2c636d3c3e8132092a3551439058aa36089dde96eac4200127bfefb9356356
+oid sha256:514bb0441f99a013f70524090a088bad3b14ed9220a6dd892303aff6d3ee7758
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdc5738e16951e311cd2a68323280e285d60e2aee01ef96983657ea1571a8776
+oid sha256:fb5e538319b0f7ea0cf5a9ed56937c70d6fb75c12684d35dc1e7ca46d4de6481
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c0464ef7b8033abc039566dee85b9115e703e8f7542cc7dba40663c87de21b6
+oid sha256:b0ce2de382b41458c0c0fc1269979e7a9757e9fe2cd348dd394069beba1a4f05
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:575df2908db98862a8edb86a2879682fc9cbe014aa13a1c0e8845ea12be8611c
+oid sha256:8987f2b058801a699d1b84a633feccab5c6170d4609f25febe6d9d8ed35ef270
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.8054862842892767,
+  "epoch": 2.9093931837073983,
   "eval_steps": 500,
-  "global_step": 13500,
+  "global_step": 14000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -212,6 +212,13 @@
       "learning_rate": 1.3050706566916044e-06,
       "loss": 0.3164,
       "step": 13500
+    },
+    {
+      "epoch": 2.9093931837073983,
+      "grad_norm": 0.7560927867889404,
+      "learning_rate": 6.123579939041286e-07,
+      "loss": 0.3268,
+      "step": 14000
     }
   ],
   "logging_steps": 500,
@@ -231,7 +238,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.644064512933888e+16,
+  "total_flos": 1.704960301989888e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null