Training in progress, step 7500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65f41221813633184b2538c9109cba635ca76c786eea27784f452a640f0ed68f
+oid sha256:80f13988b844ed8c69a71d954cca56c06260c9c862e37c2b37d479d3aa847423
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf7a4bf67da87410a6d09254af4d762ab91388990e0e2f7d30094dbe9596864a
+oid sha256:7537b80366f1058d42502431de3c635a4774b2db45ac3cd9565cc2f7c197bc84
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d201843135a1eed508b1bfdef27db8413b4debdba9826e312a0df4e52244dac2
+oid sha256:616c142757d7ec77ca22084861554955efb9fa5f5da5efb368b0b3385f62bf1c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f12d6282f561619ed37157e6869ea88b19ad7c33ffa9cf992ccd45bf1251ffb
+oid sha256:3ff581a4a3c68f40d8f4f714dabed1501f0a612483eace7a936c21011b06e648
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.4546965918536992,
+  "epoch": 1.5586034912718203,
   "eval_steps": 500,
-  "global_step": 7000,
+  "global_step": 7500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -113,6 +113,13 @@
       "learning_rate": 1.030756442227764e-05,
       "loss": 0.352,
       "step": 7000
+    },
+    {
+      "epoch": 1.5586034912718203,
+      "grad_norm": 2.3900763988494873,
+      "learning_rate": 9.614851759490165e-06,
+      "loss": 0.3564,
+      "step": 7500
     }
   ],
   "logging_steps": 500,
@@ -132,7 +139,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8524801509949440.0,
+  "total_flos": 9133759400509440.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null