Training in progress, step 1900, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fae1cea3ea7df00885daa2c80562b06d2938657f1003b0973b4a324cf8e2ec2
+oid sha256:c3281ea58f21e8e23189595bfa79850858fbba3783269108bb5bca8b74fb39a5
 size 86625328

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1383b56211f527a8b7604383361ff10967007162e52f15611fd72d31d3ccbbd
+oid sha256:554ea62f74181baa086e6cb6b5a596623c8aaf0559d81263e36e2fe654a0eeb7
 size 173285114

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b45f2e2a4ebd0b55652f3b63a8641a715f567044ea627bf2570ef0b9f9acb9f
+oid sha256:69ac6cc9f96cb23f38dad14b3c8b94857940a2c54443bb178825363cab7260c0
 size 13990

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:792c38b8e737901a2e9fd09ebf8a2facdd16f9761ed18e93b60f3d9f70040b97
+oid sha256:2375bb704062abe009d16c81c5208b4a77486ea2b7e1b6be5a4f624a4401587f
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 800,
   "best_metric": 9.927443504333496,
   "best_model_checkpoint": "./models/v-004/checkpoint-800",
-  "epoch": 58.06521739130435,
+  "epoch": 61.29347826086956,
   "eval_steps": 100,
-  "global_step": 1800,
+  "global_step": 1900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -800,6 +800,50 @@
       "eval_samples_per_second": 11.261,
       "eval_steps_per_second": 0.708,
       "step": 1800
+    },
+    {
+      "epoch": 58.71739130434783,
+      "grad_norm": 0.9569380879402161,
+      "learning_rate": 4.067824398141701e-06,
+      "loss": 2.7457,
+      "step": 1820
+    },
+    {
+      "epoch": 59.358695652173914,
+      "grad_norm": 0.9395641088485718,
+      "learning_rate": 3.2277984585066366e-06,
+      "loss": 2.7463,
+      "step": 1840
+    },
+    {
+      "epoch": 60.0,
+      "grad_norm": 1.2450119256973267,
+      "learning_rate": 2.4819655082085835e-06,
+      "loss": 2.7273,
+      "step": 1860
+    },
+    {
+      "epoch": 60.65217391304348,
+      "grad_norm": 1.0745036602020264,
+      "learning_rate": 1.8318275555520237e-06,
+      "loss": 2.6887,
+      "step": 1880
+    },
+    {
+      "epoch": 61.29347826086956,
+      "grad_norm": 0.9726008176803589,
+      "learning_rate": 1.2786938918515568e-06,
+      "loss": 2.7324,
+      "step": 1900
+    },
+    {
+      "epoch": 61.29347826086956,
+      "eval_accuracy": 0.0003037594225373504,
+      "eval_loss": 10.290609359741211,
+      "eval_runtime": 42.7369,
+      "eval_samples_per_second": 7.067,
+      "eval_steps_per_second": 0.445,
+      "step": 1900
     }
   ],
   "logging_steps": 20,
@@ -819,7 +863,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3648688009529856.0,
+  "total_flos": 3851454299490816.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null