Training in progress, epoch 4, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fd52f5a0e8dd938df10d71e0b09f35492dce025fd02be499f65ea90fb64a871
+oid sha256:95b2107454ea6860e1284edc7e9108f31247ffc3d2e93988644352851ac820ac
 size 2708729576

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82bc9033f63d0cf9a0b7b53e3b97555236f7b069748a146634589380316c7aa9
+oid sha256:202d6bcbab6b309aad3131baf5e2ca6c813f77c7b116e7b3b7cb0a79739dce02
 size 52499200

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7cf274d687459d8fbef424ee490939d2e6b5b3ea4569321a0d69cd2a401ebb4
+oid sha256:ca58b79d0725770d46b15f5293d488ed3a1f3b2b0a6f74155f951e2b625e95f4
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:541d8b16c337fd96e05a077a2be76d2de8216d931de0afb127b2cab79028732a
+oid sha256:0267fbad859e57b7ff33d6dbd4fbd9fdf3cbf25f82f07754a3b6e19cff3ef2f5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.0,
+  "epoch": 4.0,
   "eval_steps": 50,
-  "global_step": 387,
+  "global_step": 516,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -105,6 +105,48 @@
       "eval_samples_per_second": 21.886,
       "eval_steps_per_second": 5.472,
       "step": 350
+    },
+    {
+      "epoch": 3.101512933138116,
+      "grad_norm": 535160.875,
+      "learning_rate": 6.875e-05,
+      "loss": 1711.6647,
+      "step": 400
+    },
+    {
+      "epoch": 3.101512933138116,
+      "eval_runtime": 19.7699,
+      "eval_samples_per_second": 21.851,
+      "eval_steps_per_second": 5.463,
+      "step": 400
+    },
+    {
+      "epoch": 3.49194729136164,
+      "grad_norm": 411710.09375,
+      "learning_rate": 6.484375e-05,
+      "loss": 1542.0261,
+      "step": 450
+    },
+    {
+      "epoch": 3.49194729136164,
+      "eval_runtime": 19.7891,
+      "eval_samples_per_second": 21.83,
+      "eval_steps_per_second": 5.458,
+      "step": 450
+    },
+    {
+      "epoch": 3.8823816495851635,
+      "grad_norm": 426711.1875,
+      "learning_rate": 6.0937500000000004e-05,
+      "loss": 1512.678,
+      "step": 500
+    },
+    {
+      "epoch": 3.8823816495851635,
+      "eval_runtime": 19.7847,
+      "eval_samples_per_second": 21.835,
+      "eval_steps_per_second": 5.459,
+      "step": 500
     }
   ],
   "logging_steps": 50,