Training in progress, epoch 3, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c679b10aa2b443874b6a9292e3aae512f5bccabe564b7ded414ea66831aa3f8
+oid sha256:6fd52f5a0e8dd938df10d71e0b09f35492dce025fd02be499f65ea90fb64a871
 size 2708729576

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac2bb89e904aedd054556f139faebaa82a167ab945f6753087d8528f8a3a6120
+oid sha256:82bc9033f63d0cf9a0b7b53e3b97555236f7b069748a146634589380316c7aa9
 size 52499200

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:049c51626ff833ffb21f7771468093aef482329a954eee51e7f93ee61f521bdf
+oid sha256:b7cf274d687459d8fbef424ee490939d2e6b5b3ea4569321a0d69cd2a401ebb4
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e8b7bfccb9c07860bceffabef3a52060cc451a19d3abd90d284c09f7120dba6
+oid sha256:541d8b16c337fd96e05a077a2be76d2de8216d931de0afb127b2cab79028732a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.0,
+  "epoch": 3.0,
   "eval_steps": 50,
-  "global_step": 258,
+  "global_step": 387,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -77,6 +77,34 @@
       "eval_samples_per_second": 21.839,
       "eval_steps_per_second": 5.46,
       "step": 250
+    },
+    {
+      "epoch": 2.32796486090776,
+      "grad_norm": 331782.8125,
+      "learning_rate": 7.65625e-05,
+      "loss": 2230.8694,
+      "step": 300
+    },
+    {
+      "epoch": 2.32796486090776,
+      "eval_runtime": 19.7643,
+      "eval_samples_per_second": 21.858,
+      "eval_steps_per_second": 5.464,
+      "step": 300
+    },
+    {
+      "epoch": 2.7183992191312836,
+      "grad_norm": 321584.84375,
+      "learning_rate": 7.265625000000001e-05,
+      "loss": 1869.6005,
+      "step": 350
+    },
+    {
+      "epoch": 2.7183992191312836,
+      "eval_runtime": 19.7383,
+      "eval_samples_per_second": 21.886,
+      "eval_steps_per_second": 5.472,
+      "step": 350
     }
   ],
   "logging_steps": 50,