Training in progress, step 16000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54139b974ddfae98ee7fb4da2695b05278ea502ebc86824b3e1c4f49c129b297
+oid sha256:a7c3e7cfbc9b6b5cbf70eb556e69c0e89a7feac7c489589a3bd75e6d5bb1f38b
 size 579824888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff8e73939ebcb2d4e5ba75a94606f6611749ef65cbf2555cdefc0014ed49429b
+oid sha256:cb3239c55a1abdd9eba611bcd166c3c48906471881b6a03190d17e7f82682db4
 size 1159794763

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4379e0a27d0683dd964c1d70a99193598c03adb1d5cf2808558afd18cfc5f420
+oid sha256:a1e6ca9f6a71acdc5481b681d658fb168e5db2fd263350651883dffaef0871cf
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fe9a6301d1d1aeac29e6021bcb10e2a37481f63ed32dd3e17e4ef1f6ab45e17
+oid sha256:4cfc12145708b72afe7d410dd5ac1b16484b3ab33d6d903b227818b64d609309
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.28,
+  "epoch": 0.32,
   "eval_steps": 1000,
-  "global_step": 14000,
+  "global_step": 16000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1114,6 +1114,164 @@
       "eval_samples_per_second": 304.507,
       "eval_steps_per_second": 19.14,
       "step": 14000
+    },
+    {
+      "epoch": 0.282,
+      "grad_norm": 0.1499979943037033,
+      "learning_rate": 0.0008189304566233547,
+      "loss": 3.5474667358398437,
+      "step": 14100
+    },
+    {
+      "epoch": 0.284,
+      "grad_norm": 0.1552744209766388,
+      "learning_rate": 0.0008164973564370934,
+      "loss": 3.5074334716796876,
+      "step": 14200
+    },
+    {
+      "epoch": 0.286,
+      "grad_norm": 0.13462179899215698,
+      "learning_rate": 0.0008140516861700238,
+      "loss": 3.5272781372070314,
+      "step": 14300
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 0.1381780356168747,
+      "learning_rate": 0.000811593542954941,
+      "loss": 3.5094314575195313,
+      "step": 14400
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.13239678740501404,
+      "learning_rate": 0.000809123024420019,
+      "loss": 3.5180905151367186,
+      "step": 14500
+    },
+    {
+      "epoch": 0.292,
+      "grad_norm": 0.15930698812007904,
+      "learning_rate": 0.0008066402286849317,
+      "loss": 3.5262945556640624,
+      "step": 14600
+    },
+    {
+      "epoch": 0.294,
+      "grad_norm": 0.1524200737476349,
+      "learning_rate": 0.0008041452543569583,
+      "loss": 3.541943359375,
+      "step": 14700
+    },
+    {
+      "epoch": 0.296,
+      "grad_norm": 0.14040064811706543,
+      "learning_rate": 0.0008016382005270651,
+      "loss": 3.543092041015625,
+      "step": 14800
+    },
+    {
+      "epoch": 0.298,
+      "grad_norm": 0.14799822866916656,
+      "learning_rate": 0.0007991191667659708,
+      "loss": 3.5315762329101563,
+      "step": 14900
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.1449238359928131,
+      "learning_rate": 0.0007965882531201913,
+      "loss": 3.522008361816406,
+      "step": 15000
+    },
+    {
+      "epoch": 0.3,
+      "eval_accuracy": 0.36332372503531274,
+      "eval_loss": 3.4778010845184326,
+      "eval_runtime": 6.6567,
+      "eval_samples_per_second": 291.588,
+      "eval_steps_per_second": 18.328,
+      "step": 15000
+    },
+    {
+      "epoch": 0.302,
+      "grad_norm": 0.13593044877052307,
+      "learning_rate": 0.0007940455601080678,
+      "loss": 3.5114361572265627,
+      "step": 15100
+    },
+    {
+      "epoch": 0.304,
+      "grad_norm": 0.1423630267381668,
+      "learning_rate": 0.0007914911887157724,
+      "loss": 3.5139959716796874,
+      "step": 15200
+    },
+    {
+      "epoch": 0.306,
+      "grad_norm": 0.15380671620368958,
+      "learning_rate": 0.0007889252403932986,
+      "loss": 3.515833435058594,
+      "step": 15300
+    },
+    {
+      "epoch": 0.308,
+      "grad_norm": 0.13759265840053558,
+      "learning_rate": 0.0007863478170504326,
+      "loss": 3.528351135253906,
+      "step": 15400
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.13887037336826324,
+      "learning_rate": 0.0007837590210527042,
+      "loss": 3.5276870727539062,
+      "step": 15500
+    },
+    {
+      "epoch": 0.312,
+      "grad_norm": 0.15678516030311584,
+      "learning_rate": 0.0007811589552173225,
+      "loss": 3.515467224121094,
+      "step": 15600
+    },
+    {
+      "epoch": 0.314,
+      "grad_norm": 0.2133788764476776,
+      "learning_rate": 0.0007785477228090924,
+      "loss": 3.5256777954101564,
+      "step": 15700
+    },
+    {
+      "epoch": 0.316,
+      "grad_norm": 0.17379774153232574,
+      "learning_rate": 0.0007759254275363124,
+      "loss": 3.5354928588867187,
+      "step": 15800
+    },
+    {
+      "epoch": 0.318,
+      "grad_norm": 0.15530315041542053,
+      "learning_rate": 0.0007732921735466564,
+      "loss": 3.5182159423828123,
+      "step": 15900
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.14711181819438934,
+      "learning_rate": 0.0007706480654230373,
+      "loss": 3.5050119018554686,
+      "step": 16000
+    },
+    {
+      "epoch": 0.32,
+      "eval_accuracy": 0.3644458693896563,
+      "eval_loss": 3.4653918743133545,
+      "eval_runtime": 6.2866,
+      "eval_samples_per_second": 308.75,
+      "eval_steps_per_second": 19.406,
+      "step": 16000
     }
   ],
   "logging_steps": 100,
@@ -1133,7 +1291,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.4879452135424e+17,
+  "total_flos": 6.2719373869056e+17,
   "train_batch_size": 120,
   "trial_name": null,
   "trial_params": null