Training in progress, step 8000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e017ff86b8a295f11193c500291f5991ea24bf880a065787121b3fb732878a01
+oid sha256:a43ee6984f5f990cd4d1d7d439666b7dfa7b56da1d97ae91a2c6727d6281cb2d
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8013718d7b486d4bea38838926eb12f405577f302b56db31ac78355ece57c039
+oid sha256:1f67eef48f1db3ec75565c0e239b37d2a1a24b92d26f253f611940b1cf185dbb
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:331fb2b7f8ecd022b2d839d7c7167894d42e426406c8fde67ed9a8d4c78176de
+oid sha256:91eae2fa3fc02ee15efef1884ec4e560ef910ecd5d82acb8671a8d4707b80a43
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:805137337f587aa7655dd5f599cea8ff7a9813cfb0f1bcf2d0b7dd019723b5ad
+oid sha256:db6a8aa79fcfebce03524e9b1b6b5ceec390e3bb9a2a198149bb646d26309c9b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5,
+  "epoch": 0.5333333333333333,
   "eval_steps": 500,
-  "global_step": 7500,
+  "global_step": 8000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -532,6 +532,41 @@
       "learning_rate": 1.6668e-05,
       "loss": 0.0604,
       "step": 7500
+    },
+    {
+      "epoch": 0.5066666666666667,
+      "grad_norm": 0.35880565643310547,
+      "learning_rate": 1.6623555555555556e-05,
+      "loss": 0.0685,
+      "step": 7600
+    },
+    {
+      "epoch": 0.5133333333333333,
+      "grad_norm": 0.12522092461585999,
+      "learning_rate": 1.6579111111111114e-05,
+      "loss": 0.0806,
+      "step": 7700
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.1332361251115799,
+      "learning_rate": 1.653466666666667e-05,
+      "loss": 0.0699,
+      "step": 7800
+    },
+    {
+      "epoch": 0.5266666666666666,
+      "grad_norm": 0.2704123854637146,
+      "learning_rate": 1.6490222222222225e-05,
+      "loss": 0.0685,
+      "step": 7900
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.1266499161720276,
+      "learning_rate": 1.644577777777778e-05,
+      "loss": 0.0699,
+      "step": 8000
     }
   ],
   "logging_steps": 100,
@@ -551,7 +586,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.82687367168e+16,
+  "total_flos": 1.948665249792e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null