Training in progress, step 23000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0f4dd5c7f06f434e4d8cbac5754e2c65f64bd46ac822a7e90462688dcf30e65
+oid sha256:be1cf4c3d10cfbf74e0b37f9cbc786fae12e5bbc6e3706973bfac0175c00ecce
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a565ab0875e5f8e974ebb52445ef3770a07896c54aaad2beab4684116687c64d
+oid sha256:bca9f5a43e8c43cfe44e64364c4d417027de463f09d30955f0ca8d99d5517c8a
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4371c359f3f61a0b206a73cb497201135751765261ece06b66d5005fa4a3d9e
+oid sha256:29008ac370065a7f89ca5e36ad7037a88abffeace17ded8b029713d8007c00c5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c6c8e99b80f348613f137bd980faaac34ec4fa21cbf485269f4beb839740a21
+oid sha256:95f8453b710c139b3558b89069d0f1dbb29ca8e0859ba342fa8818ead3f6d844
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.5,
+  "epoch": 1.5333333333333332,
   "eval_steps": 500,
-  "global_step": 22500,
+  "global_step": 23000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1590,6 +1590,41 @@
       "learning_rate": 1.0003111111111113e-05,
       "loss": 0.0564,
       "step": 22500
+    },
+    {
+      "epoch": 1.5066666666666668,
+      "grad_norm": 0.24926000833511353,
+      "learning_rate": 9.958666666666668e-06,
+      "loss": 0.0562,
+      "step": 22600
+    },
+    {
+      "epoch": 1.5133333333333332,
+      "grad_norm": 0.19163891673088074,
+      "learning_rate": 9.914222222222224e-06,
+      "loss": 0.0574,
+      "step": 22700
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 0.12077998369932175,
+      "learning_rate": 9.869777777777779e-06,
+      "loss": 0.0615,
+      "step": 22800
+    },
+    {
+      "epoch": 1.5266666666666666,
+      "grad_norm": 0.23265130817890167,
+      "learning_rate": 9.825333333333334e-06,
+      "loss": 0.0624,
+      "step": 22900
+    },
+    {
+      "epoch": 1.5333333333333332,
+      "grad_norm": 0.20572605729103088,
+      "learning_rate": 9.78088888888889e-06,
+      "loss": 0.0545,
+      "step": 23000
     }
   ],
   "logging_steps": 100,
@@ -1609,7 +1644,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.48062101504e+16,
+  "total_flos": 5.602412593152e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null