Training in progress, step 6000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eba307d3c97df9e979b82093df5cf8425107cd7d61ef42701174b56b83b8772a
+oid sha256:a9e0275bab1a6a9782df65a6f8abfba7e17a82295a2cbdb95725d3f45b1e28a0
 size 441688704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d803bc3b3b93db13999ea497f0038321f4a108d672393efed6f3bc7ff96d4c0
+oid sha256:412e90b7208921d172da8d70bcf2d9eb483f1ba3bacdde12388ae0f1699757ba
 size 883473803

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8130b1d98834a9539dcbfcfb3576fee63a1157baa5927fb3541ab2d8f2275b43
+oid sha256:3c4bb3232333245cce0402989a808fbb8a3484f7c8d0a74db5b1f083ad707d43
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e52efaca62e9d3bd3d1daf7fc80157137c0fc77d23eca18ff2351ee0e98e778
+oid sha256:6af98c8a00430bf78cf7a33095a269f67cf12c82df483a872be441460ebbbf74
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e81ba539f41f911038f19d3371a2200f0ff9c6577bd5db9c6ea280d1f806a53
+oid sha256:1e49e65fc711539cf4a80289687bb7ae73d6c8503caf26e61f786d781a7e51b3
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6470588235294118,
+  "epoch": 0.7058823529411765,
   "eval_steps": 500,
-  "global_step": 5500,
+  "global_step": 6000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -866,6 +866,84 @@
       "eval_samples_per_second": 49.321,
       "eval_steps_per_second": 1.543,
       "step": 5500
+    },
+    {
+      "epoch": 0.6529411764705882,
+      "grad_norm": 0.34363728761672974,
+      "learning_rate": 0.00017358823529411765,
+      "loss": 3.5676690673828126,
+      "step": 5550
+    },
+    {
+      "epoch": 0.6588235294117647,
+      "grad_norm": 0.3821636736392975,
+      "learning_rate": 0.00017064705882352942,
+      "loss": 3.564356384277344,
+      "step": 5600
+    },
+    {
+      "epoch": 0.6647058823529411,
+      "grad_norm": 0.3870471715927124,
+      "learning_rate": 0.00016770588235294118,
+      "loss": 3.5735037231445315,
+      "step": 5650
+    },
+    {
+      "epoch": 0.6705882352941176,
+      "grad_norm": 0.3668818175792694,
+      "learning_rate": 0.00016476470588235295,
+      "loss": 3.5546405029296877,
+      "step": 5700
+    },
+    {
+      "epoch": 0.6764705882352942,
+      "grad_norm": 0.34516939520835876,
+      "learning_rate": 0.0001618235294117647,
+      "loss": 3.5730084228515624,
+      "step": 5750
+    },
+    {
+      "epoch": 0.6823529411764706,
+      "grad_norm": 0.3682394325733185,
+      "learning_rate": 0.00015888235294117648,
+      "loss": 3.54217529296875,
+      "step": 5800
+    },
+    {
+      "epoch": 0.6882352941176471,
+      "grad_norm": 0.37805479764938354,
+      "learning_rate": 0.0001559411764705882,
+      "loss": 3.55981201171875,
+      "step": 5850
+    },
+    {
+      "epoch": 0.6941176470588235,
+      "grad_norm": 0.3545401990413666,
+      "learning_rate": 0.000153,
+      "loss": 3.494635009765625,
+      "step": 5900
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.35230571031570435,
+      "learning_rate": 0.00015005882352941177,
+      "loss": 3.314564514160156,
+      "step": 5950
+    },
+    {
+      "epoch": 0.7058823529411765,
+      "grad_norm": 0.3728525638580322,
+      "learning_rate": 0.00014711764705882354,
+      "loss": 3.292919006347656,
+      "step": 6000
+    },
+    {
+      "epoch": 0.7058823529411765,
+      "eval_loss": 3.4088094234466553,
+      "eval_runtime": 178.0592,
+      "eval_samples_per_second": 48.821,
+      "eval_steps_per_second": 1.528,
+      "step": 6000
     }
   ],
   "logging_steps": 50,
@@ -885,7 +963,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.1974795264e+16,
+  "total_flos": 1.00336140288e+17,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null