Training in progress, step 6000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37eb7a5e4bceab7d32011b5d17f5f7c727abd642937f2f5113f334b54b67ecce
+oid sha256:935231e882baac445be09e5015300cee4d31f5e5feef6fcef690c14e5e55b597
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9719ee3b3f8442d6fc5e8f63a83f241cd994c81df3f6f1e293214b163473444
+oid sha256:7f96ab152b2e84116d344289867a73a5bcff139ded8e28fcfbd0dfa6edfa1330
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eca803041d1c71084d00ad4722811ed67342df4d01c4b5a158f3fbc70c751c86
+oid sha256:076751cbfa70935d8290a9eb7adf2c98a5954f528f9899c6c9bad4b99c90c7a1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c79865c40bc524fb8d08f87fe96773f5e5e19275573e12c21b3c870bc7e6d8a
+oid sha256:a78a0f82725f5cba903915c8114309109800227c56b0ea02410918cc9d05f8aa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.36666666666666664,
+  "epoch": 0.4,
   "eval_steps": 500,
-  "global_step": 5500,
+  "global_step": 6000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -392,6 +392,41 @@
       "learning_rate": 1.755688888888889e-05,
       "loss": 0.0708,
       "step": 5500
+    },
+    {
+      "epoch": 0.37333333333333335,
+      "grad_norm": 0.2491353303194046,
+      "learning_rate": 1.7512444444444444e-05,
+      "loss": 0.0727,
+      "step": 5600
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.20241300761699677,
+      "learning_rate": 1.7468e-05,
+      "loss": 0.0682,
+      "step": 5700
+    },
+    {
+      "epoch": 0.38666666666666666,
+      "grad_norm": 0.20645934343338013,
+      "learning_rate": 1.7423555555555558e-05,
+      "loss": 0.0711,
+      "step": 5800
+    },
+    {
+      "epoch": 0.3933333333333333,
+      "grad_norm": 0.280748575925827,
+      "learning_rate": 1.7379111111111113e-05,
+      "loss": 0.0682,
+      "step": 5900
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.1867647022008896,
+      "learning_rate": 1.733466666666667e-05,
+      "loss": 0.0701,
+      "step": 6000
     }
   ],
   "logging_steps": 100,
@@ -411,7 +446,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.339707359232e+16,
+  "total_flos": 1.461498937344e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null