Training in progress, step 6500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:935231e882baac445be09e5015300cee4d31f5e5feef6fcef690c14e5e55b597
+oid sha256:c6c581988e145fe28231a5b363482e4cc6aa1c009b42a7cafcee97ebd43f75b8
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f96ab152b2e84116d344289867a73a5bcff139ded8e28fcfbd0dfa6edfa1330
+oid sha256:0334bff194e682ae1d5a62ead6d631a75270fccfa182f5901d35a528b0fb29db
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:076751cbfa70935d8290a9eb7adf2c98a5954f528f9899c6c9bad4b99c90c7a1
+oid sha256:84aef586a811d916d5e08d0a9103c7f2c4e17550364204602e5b8c751b16f429
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a78a0f82725f5cba903915c8114309109800227c56b0ea02410918cc9d05f8aa
+oid sha256:1c31374bac28c19f30a1c44dbbe9200685351926b09acbd3fd6b855ef898dbb0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4,
+  "epoch": 0.43333333333333335,
   "eval_steps": 500,
-  "global_step": 6000,
+  "global_step": 6500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -427,6 +427,41 @@
       "learning_rate": 1.733466666666667e-05,
       "loss": 0.0701,
       "step": 6000
+    },
+    {
+      "epoch": 0.4066666666666667,
+      "grad_norm": 0.5076069235801697,
+      "learning_rate": 1.7290222222222224e-05,
+      "loss": 0.0706,
+      "step": 6100
+    },
+    {
+      "epoch": 0.41333333333333333,
+      "grad_norm": 0.22595347464084625,
+      "learning_rate": 1.724577777777778e-05,
+      "loss": 0.0743,
+      "step": 6200
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.21158984303474426,
+      "learning_rate": 1.7201333333333334e-05,
+      "loss": 0.0798,
+      "step": 6300
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 0.225486621260643,
+      "learning_rate": 1.715688888888889e-05,
+      "loss": 0.0637,
+      "step": 6400
+    },
+    {
+      "epoch": 0.43333333333333335,
+      "grad_norm": 0.21651168167591095,
+      "learning_rate": 1.7112444444444445e-05,
+      "loss": 0.0652,
+      "step": 6500
     }
   ],
   "logging_steps": 100,
@@ -446,7 +481,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.461498937344e+16,
+  "total_flos": 1.583290515456e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null