Training in progress, step 14000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30c52112c96ec25f31baf587e4ea477ab4159bb1c63abe90bcc28c81ca010247
+oid sha256:f995787c415a06379c93fa16cdd3342ead1953e820a7c8548c0770b20408526d
 size 529337896

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f7e9850bee199260d6d224038c95a23455b03a11ddd77fdb4a243a7fb5a4fa4
+oid sha256:cba6c3ab71a635e3a1f6cb9907f4f27120b466b178e1e92fa2c249da30f3f7e4
 size 871247243

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52385b94ea56e4debf05c2da14392180d553361a3ff764d1b252b9267d0e1fa2
+oid sha256:84ec1f587c02234737f99fa1daded8a3c26ce4ce7280283e8fe016d82a0ee148
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43ab2089bb2cb7b873a77ac8e24a3b3b2416ededca3811b6bb0922f61bea4c99
+oid sha256:5dcd90d4261e8acb8aa69d2cdcf6bd4451975f95262601bbfdb94f38ebb145b3
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.24,
+  "epoch": 0.28,
   "eval_steps": 1000,
-  "global_step": 12000,
+  "global_step": 14000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -956,6 +956,164 @@
       "eval_samples_per_second": 81.22,
       "eval_steps_per_second": 0.65,
       "step": 12000
+    },
+    {
+      "epoch": 0.242,
+      "grad_norm": 0.1448379009962082,
+      "learning_rate": 0.0018051510141940939,
+      "loss": 3.5416,
+      "step": 12100
+    },
+    {
+      "epoch": 0.244,
+      "grad_norm": 0.13583365082740784,
+      "learning_rate": 0.00180121094046208,
+      "loss": 3.5343,
+      "step": 12200
+    },
+    {
+      "epoch": 0.246,
+      "grad_norm": 0.17297838628292084,
+      "learning_rate": 0.001797235819167967,
+      "loss": 3.521,
+      "step": 12300
+    },
+    {
+      "epoch": 0.248,
+      "grad_norm": 0.15616372227668762,
+      "learning_rate": 0.0017932258241964375,
+      "loss": 3.533,
+      "step": 12400
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.15943922102451324,
+      "learning_rate": 0.0017891811309576622,
+      "loss": 3.5177,
+      "step": 12500
+    },
+    {
+      "epoch": 0.252,
+      "grad_norm": 0.15389597415924072,
+      "learning_rate": 0.001785101916379627,
+      "loss": 3.5209,
+      "step": 12600
+    },
+    {
+      "epoch": 0.254,
+      "grad_norm": 0.13968117535114288,
+      "learning_rate": 0.0017809883589003912,
+      "loss": 3.5137,
+      "step": 12700
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 0.1350937783718109,
+      "learning_rate": 0.0017768406384602862,
+      "loss": 3.5294,
+      "step": 12800
+    },
+    {
+      "epoch": 0.258,
+      "grad_norm": 0.13691306114196777,
+      "learning_rate": 0.00177265893649404,
+      "loss": 3.5228,
+      "step": 12900
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.1496269851922989,
+      "learning_rate": 0.0017684434359228438,
+      "loss": 3.5026,
+      "step": 13000
+    },
+    {
+      "epoch": 0.26,
+      "eval_accuracy": 0.3645440313111546,
+      "eval_loss": 3.480961799621582,
+      "eval_runtime": 11.914,
+      "eval_samples_per_second": 83.935,
+      "eval_steps_per_second": 0.671,
+      "step": 13000
+    },
+    {
+      "epoch": 0.262,
+      "grad_norm": 0.1472535878419876,
+      "learning_rate": 0.0017641943211463488,
+      "loss": 3.5107,
+      "step": 13100
+    },
+    {
+      "epoch": 0.264,
+      "grad_norm": 0.1573815494775772,
+      "learning_rate": 0.0017599117780346006,
+      "loss": 3.5147,
+      "step": 13200
+    },
+    {
+      "epoch": 0.266,
+      "grad_norm": 0.15841859579086304,
+      "learning_rate": 0.0017555959939199084,
+      "loss": 3.501,
+      "step": 13300
+    },
+    {
+      "epoch": 0.268,
+      "grad_norm": 0.15096184611320496,
+      "learning_rate": 0.0017512471575886505,
+      "loss": 3.5034,
+      "step": 13400
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.17669688165187836,
+      "learning_rate": 0.0017468654592730168,
+      "loss": 3.5101,
+      "step": 13500
+    },
+    {
+      "epoch": 0.272,
+      "grad_norm": 0.16740451753139496,
+      "learning_rate": 0.0017424510906426853,
+      "loss": 3.5021,
+      "step": 13600
+    },
+    {
+      "epoch": 0.274,
+      "grad_norm": 0.1432366967201233,
+      "learning_rate": 0.0017380042447964414,
+      "loss": 3.4915,
+      "step": 13700
+    },
+    {
+      "epoch": 0.276,
+      "grad_norm": 0.14669281244277954,
+      "learning_rate": 0.0017335251162537279,
+      "loss": 3.4975,
+      "step": 13800
+    },
+    {
+      "epoch": 0.278,
+      "grad_norm": 0.15456849336624146,
+      "learning_rate": 0.0017290139009461377,
+      "loss": 3.504,
+      "step": 13900
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.163591668009758,
+      "learning_rate": 0.0017244707962088424,
+      "loss": 3.4899,
+      "step": 14000
+    },
+    {
+      "epoch": 0.28,
+      "eval_accuracy": 0.366587084148728,
+      "eval_loss": 3.4621543884277344,
+      "eval_runtime": 13.6803,
+      "eval_samples_per_second": 73.098,
+      "eval_steps_per_second": 0.585,
+      "step": 14000
     }
   ],
   "logging_steps": 100,