Training in progress, step 400, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66886050e435756ef5a7c49a69ae84363711c5f2bc7b3b5ebe3bf6a9bda5b749
+oid sha256:44db9200e812bea039f20d9f9d28a6cc957c313c4a850767b225596c0d0b5e4d
 size 579824888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53f7b73ea97ba098f486f95967fa0a7351e9d606099e9de265782b06a33955a2
+oid sha256:2db0d2136ead3f5f875f36fd5e9c3aabdd558f129a68fea33e8ad5378b962f98
 size 1159794763

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f879f5f67a208b766c17cb348fca9d544480e749ad05d8f2acb8625bebbaf11
+oid sha256:daffcca87be3c0433ad35e4c1c8e3a023512501fd94a8be0b0adb06d69a5a30e
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a613d380f06e14f7b3ddc807a9d67116b9bcb0317fb8fbbd77c2d40723ed0e8
+oid sha256:84e96bce876c6af0e48011bb3d66e418a88cfa5db787a6533c7b6b8efb142dbd
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2,
+  "epoch": 0.4,
   "eval_steps": 100,
-  "global_step": 200,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -54,6 +54,52 @@
       "eval_samples_per_second": 72.664,
       "eval_steps_per_second": 4.57,
       "step": 200
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 1.5482277870178223,
+      "learning_rate": 9.669005017492143e-05,
+      "loss": 25.0247,
+      "step": 250
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 3.2663464546203613,
+      "learning_rate": 9.26078506448917e-05,
+      "loss": 24.2338,
+      "step": 300
+    },
+    {
+      "epoch": 0.3,
+      "eval_accuracy": 0.1829634890115987,
+      "eval_loss": 5.955964088439941,
+      "eval_runtime": 12.3645,
+      "eval_samples_per_second": 78.45,
+      "eval_steps_per_second": 4.933,
+      "step": 300
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 2.2301456928253174,
+      "learning_rate": 8.707469186363446e-05,
+      "loss": 23.716,
+      "step": 350
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 2.1302545070648193,
+      "learning_rate": 8.027899891715287e-05,
+      "loss": 23.2729,
+      "step": 400
+    },
+    {
+      "epoch": 0.4,
+      "eval_accuracy": 0.1966725107382293,
+      "eval_loss": 5.7180047035217285,
+      "eval_runtime": 13.1479,
+      "eval_samples_per_second": 73.776,
+      "eval_steps_per_second": 4.64,
+      "step": 400
     }
   ],
   "logging_steps": 50,
@@ -73,7 +119,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.34503327301632e+16,
+  "total_flos": 6.69006654603264e+16,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null