Training in progress, step 600, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44db9200e812bea039f20d9f9d28a6cc957c313c4a850767b225596c0d0b5e4d
+oid sha256:28169bb183740976fb1e1012281faf4daaa901f0809070b5431b167a9aed9330
 size 579824888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2db0d2136ead3f5f875f36fd5e9c3aabdd558f129a68fea33e8ad5378b962f98
+oid sha256:5bcc09d2987fc871b0f3d765698df5a7ddb67b242d4bf83d5e4d4194e97c62f1
 size 1159794763

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:daffcca87be3c0433ad35e4c1c8e3a023512501fd94a8be0b0adb06d69a5a30e
+oid sha256:ecde0592a54835c0791d413df0b84cfe61c8375c6c53371a3a262f4a720ce7ee
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84e96bce876c6af0e48011bb3d66e418a88cfa5db787a6533c7b6b8efb142dbd
+oid sha256:bff1f3af0c59bc6ebaa29224579d5dfcd2f5ed0cc9dfc92a0a059a14be64f7bc
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4,
+  "epoch": 0.6,
   "eval_steps": 100,
-  "global_step": 400,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -100,6 +100,52 @@
       "eval_samples_per_second": 73.776,
       "eval_steps_per_second": 4.64,
       "step": 400
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 2.3908166885375977,
+      "learning_rate": 7.24521909782041e-05,
+      "loss": 22.8638,
+      "step": 450
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 2.105929136276245,
+      "learning_rate": 6.386080060392754e-05,
+      "loss": 22.5651,
+      "step": 500
+    },
+    {
+      "epoch": 0.5,
+      "eval_accuracy": 0.20586229645784704,
+      "eval_loss": 5.55440616607666,
+      "eval_runtime": 13.4924,
+      "eval_samples_per_second": 71.892,
+      "eval_steps_per_second": 4.521,
+      "step": 500
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 2.184967041015625,
+      "learning_rate": 5.479739728928219e-05,
+      "loss": 22.2741,
+      "step": 550
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 2.2348268032073975,
+      "learning_rate": 4.5570624363794226e-05,
+      "loss": 22.0473,
+      "step": 600
+    },
+    {
+      "epoch": 0.6,
+      "eval_accuracy": 0.21187852939218293,
+      "eval_loss": 5.435864448547363,
+      "eval_runtime": 12.3748,
+      "eval_samples_per_second": 78.385,
+      "eval_steps_per_second": 4.929,
+      "step": 600
     }
   ],
   "logging_steps": 50,
@@ -119,7 +165,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.69006654603264e+16,
+  "total_flos": 1.003509981904896e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null