Training in progress, step 14000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5eab5cf423687e71bb09a2192d390f2707db089b85d712fe4ba933f4e60e68f
+oid sha256:e948c8d9a7ad56ccbd6700926716442cecc28d16ec12db2c3ed5e7e3f659db9b
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:807f9477c6257e1784434ba0760f1f95f0fdf6abcdcb9183ee441309d58f6f04
+oid sha256:af58a191c850477c58ee5c9fd6d80b4f79d202f3c260b244c0bb72f25e9c46bf
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35473c59fad66809b7d88f5a452c0f7e0ed4b7e0e9e5416152035290cb60f273
+oid sha256:aba8071d282c3cb60c40a4d3269fc6a11f1d4d5aa00c59a4ed8e5ce671a0abf0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f3a75abd7e2a468c4e910b9da4dc47554f88ea4d9cfaefa84fb6258d08648a5
+oid sha256:aecb0190c300aa10c453b1ef86e11d1993afb13996c225cb9c0fcb417f89ff36
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9,
+  "epoch": 0.9333333333333333,
   "eval_steps": 500,
-  "global_step": 13500,
+  "global_step": 14000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -952,6 +952,41 @@
       "learning_rate": 1.4001333333333333e-05,
       "loss": 0.0669,
       "step": 13500
+    },
+    {
+      "epoch": 0.9066666666666666,
+      "grad_norm": 0.26795893907546997,
+      "learning_rate": 1.3956888888888891e-05,
+      "loss": 0.0698,
+      "step": 13600
+    },
+    {
+      "epoch": 0.9133333333333333,
+      "grad_norm": 0.20815995335578918,
+      "learning_rate": 1.3912444444444447e-05,
+      "loss": 0.0655,
+      "step": 13700
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.1046639233827591,
+      "learning_rate": 1.3868444444444447e-05,
+      "loss": 0.0685,
+      "step": 13800
+    },
+    {
+      "epoch": 0.9266666666666666,
+      "grad_norm": 0.26044830679893494,
+      "learning_rate": 1.3824000000000002e-05,
+      "loss": 0.0717,
+      "step": 13900
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 0.14924395084381104,
+      "learning_rate": 1.3779555555555557e-05,
+      "loss": 0.0666,
+      "step": 14000
     }
   ],
   "logging_steps": 100,
@@ -971,7 +1006,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.288372609024e+16,
+  "total_flos": 3.410164187136e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null