Training in progress, step 16000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f995787c415a06379c93fa16cdd3342ead1953e820a7c8548c0770b20408526d
+oid sha256:2bef8568f96238a5b06f1b8201e0457a70533d075df2bb2744dfc21292e3ccee
 size 529337896

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cba6c3ab71a635e3a1f6cb9907f4f27120b466b178e1e92fa2c249da30f3f7e4
+oid sha256:ae466236a6b73341348524a8c14751f290085bd91d0879fd65d99038fe1a8df2
 size 871247243

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84ec1f587c02234737f99fa1daded8a3c26ce4ce7280283e8fe016d82a0ee148
+oid sha256:3094f03eb1b7ca78cd75cfac64b3e97454e2450697d516b4311c6fe7ecad5494
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dcd90d4261e8acb8aa69d2cdcf6bd4451975f95262601bbfdb94f38ebb145b3
+oid sha256:262c03618811dd08c5542ed422cb02749751837f2f34131505a0ce5eebb179de
 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": 73.098,
       "eval_steps_per_second": 0.585,
       "step": 14000
+    },
+    {
+      "epoch": 0.282,
+      "grad_norm": 0.1512901335954666,
+      "learning_rate": 0.0017198960007719611,
+      "loss": 3.4777,
+      "step": 14100
+    },
+    {
+      "epoch": 0.284,
+      "grad_norm": 0.13871945440769196,
+      "learning_rate": 0.0017152897147518665,
+      "loss": 3.5067,
+      "step": 14200
+    },
+    {
+      "epoch": 0.286,
+      "grad_norm": 0.15246713161468506,
+      "learning_rate": 0.001710652139642431,
+      "loss": 3.5018,
+      "step": 14300
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 0.13609080016613007,
+      "learning_rate": 0.0017059834783062142,
+      "loss": 3.4762,
+      "step": 14400
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.15287351608276367,
+      "learning_rate": 0.0017012839349655868,
+      "loss": 3.4872,
+      "step": 14500
+    },
+    {
+      "epoch": 0.292,
+      "grad_norm": 0.14040616154670715,
+      "learning_rate": 0.001696553715193799,
+      "loss": 3.5042,
+      "step": 14600
+    },
+    {
+      "epoch": 0.294,
+      "grad_norm": 0.1571398377418518,
+      "learning_rate": 0.0016917930259059879,
+      "loss": 3.4744,
+      "step": 14700
+    },
+    {
+      "epoch": 0.296,
+      "grad_norm": 0.1505391150712967,
+      "learning_rate": 0.001687002075350125,
+      "loss": 3.4749,
+      "step": 14800
+    },
+    {
+      "epoch": 0.298,
+      "grad_norm": 0.14757487177848816,
+      "learning_rate": 0.001682181073097908,
+      "loss": 3.4852,
+      "step": 14900
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.15271714329719543,
+      "learning_rate": 0.0016773302300355935,
+      "loss": 3.486,
+      "step": 15000
+    },
+    {
+      "epoch": 0.3,
+      "eval_accuracy": 0.36803326810176124,
+      "eval_loss": 3.4481563568115234,
+      "eval_runtime": 12.0908,
+      "eval_samples_per_second": 82.707,
+      "eval_steps_per_second": 0.662,
+      "step": 15000
+    },
+    {
+      "epoch": 0.302,
+      "grad_norm": 0.15327778458595276,
+      "learning_rate": 0.0016724497583547715,
+      "loss": 3.478,
+      "step": 15100
+    },
+    {
+      "epoch": 0.304,
+      "grad_norm": 0.16108167171478271,
+      "learning_rate": 0.0016675398715430842,
+      "loss": 3.4579,
+      "step": 15200
+    },
+    {
+      "epoch": 0.306,
+      "grad_norm": 0.15231835842132568,
+      "learning_rate": 0.001662600784374886,
+      "loss": 3.4819,
+      "step": 15300
+    },
+    {
+      "epoch": 0.308,
+      "grad_norm": 0.1505262553691864,
+      "learning_rate": 0.0016576327129018504,
+      "loss": 3.4808,
+      "step": 15400
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.15296302735805511,
+      "learning_rate": 0.0016526358744435184,
+      "loss": 3.459,
+      "step": 15500
+    },
+    {
+      "epoch": 0.312,
+      "grad_norm": 0.2003161907196045,
+      "learning_rate": 0.001647610487577791,
+      "loss": 3.4751,
+      "step": 15600
+    },
+    {
+      "epoch": 0.314,
+      "grad_norm": 0.130265474319458,
+      "learning_rate": 0.0016425567721313694,
+      "loss": 3.4819,
+      "step": 15700
+    },
+    {
+      "epoch": 0.316,
+      "grad_norm": 0.14476525783538818,
+      "learning_rate": 0.0016374749491701401,
+      "loss": 3.4514,
+      "step": 15800
+    },
+    {
+      "epoch": 0.318,
+      "grad_norm": 0.1549970805644989,
+      "learning_rate": 0.0016323652409895013,
+      "loss": 3.4684,
+      "step": 15900
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.14814923703670502,
+      "learning_rate": 0.0016272278711046424,
+      "loss": 3.4674,
+      "step": 16000
+    },
+    {
+      "epoch": 0.32,
+      "eval_accuracy": 0.36914090019569473,
+      "eval_loss": 3.435351848602295,
+      "eval_runtime": 12.375,
+      "eval_samples_per_second": 80.808,
+      "eval_steps_per_second": 0.646,
+      "step": 16000
     }
   ],
   "logging_steps": 100,