Training in progress, step 16000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e0ff05e0e5d852455b4d83922c7abbecdec428e19e46c0b823ee661ac50cdb5
+oid sha256:69c3b821cf12eeaa022a644bc22041eac717a7550c375de853c5ee543353c15e
 size 496262784

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32d116e4c03c1c5f0b5164cbe30850c283753e36a9119b42ffefe95697cc08e3
+oid sha256:099f48c6bd773fc094319bca20e4dc9f9c6178fc27af5dbdbf0e8f59bf625192
 size 992621963

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74ba315e55e014287fc4f548e786e1c64991f07f2dd31f970e2f14eab773946e
+oid sha256:79bfab8e6d704b55615f0aa752b32bcc403a434935bef147322933f0756a46f1
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:238cbdda4406a9b9e4f702cada921a66b6ebd035a4f580dabf57521e3dc0c97d
+oid sha256:a3daf8da2259c0a45cc86b801dfa39aec812fc636174a8b32bb6d363e93dc412
 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": 194.114,
       "eval_steps_per_second": 12.201,
       "step": 14000
+    },
+    {
+      "epoch": 0.282,
+      "grad_norm": 0.22074639797210693,
+      "learning_rate": 0.0004913582739740128,
+      "loss": 3.578910217285156,
+      "step": 14100
+    },
+    {
+      "epoch": 0.284,
+      "grad_norm": 0.20357950031757355,
+      "learning_rate": 0.000489898413862256,
+      "loss": 3.5391220092773437,
+      "step": 14200
+    },
+    {
+      "epoch": 0.286,
+      "grad_norm": 0.2000010460615158,
+      "learning_rate": 0.0004884310117020142,
+      "loss": 3.558287353515625,
+      "step": 14300
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 0.20651493966579437,
+      "learning_rate": 0.00048695612577296456,
+      "loss": 3.5417572021484376,
+      "step": 14400
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.18496066331863403,
+      "learning_rate": 0.0004854738146520113,
+      "loss": 3.5497479248046875,
+      "step": 14500
+    },
+    {
+      "epoch": 0.292,
+      "grad_norm": 0.23755651712417603,
+      "learning_rate": 0.000483984137210959,
+      "loss": 3.5615032958984374,
+      "step": 14600
+    },
+    {
+      "epoch": 0.294,
+      "grad_norm": 0.20592571794986725,
+      "learning_rate": 0.0004824871526141749,
+      "loss": 3.5748583984375,
+      "step": 14700
+    },
+    {
+      "epoch": 0.296,
+      "grad_norm": 0.2018384486436844,
+      "learning_rate": 0.00048098292031623904,
+      "loss": 3.575079040527344,
+      "step": 14800
+    },
+    {
+      "epoch": 0.298,
+      "grad_norm": 0.19982250034809113,
+      "learning_rate": 0.00047947150005958237,
+      "loss": 3.56544921875,
+      "step": 14900
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.2055491805076599,
+      "learning_rate": 0.00047795295187211473,
+      "loss": 3.5550732421875,
+      "step": 15000
+    },
+    {
+      "epoch": 0.3,
+      "eval_accuracy": 0.3619394445335035,
+      "eval_loss": 3.490281105041504,
+      "eval_runtime": 5.758,
+      "eval_samples_per_second": 337.096,
+      "eval_steps_per_second": 21.188,
+      "step": 15000
+    },
+    {
+      "epoch": 0.302,
+      "grad_norm": 0.18866001069545746,
+      "learning_rate": 0.00047642733606484064,
+      "loss": 3.544368896484375,
+      "step": 15100
+    },
+    {
+      "epoch": 0.304,
+      "grad_norm": 0.19551938772201538,
+      "learning_rate": 0.00047489471322946335,
+      "loss": 3.5462738037109376,
+      "step": 15200
+    },
+    {
+      "epoch": 0.306,
+      "grad_norm": 0.20952892303466797,
+      "learning_rate": 0.00047335514423597913,
+      "loss": 3.547786865234375,
+      "step": 15300
+    },
+    {
+      "epoch": 0.308,
+      "grad_norm": 0.1951807737350464,
+      "learning_rate": 0.0004718086902302595,
+      "loss": 3.5607293701171874,
+      "step": 15400
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.19585217535495758,
+      "learning_rate": 0.00047025541263162244,
+      "loss": 3.5599630737304686,
+      "step": 15500
+    },
+    {
+      "epoch": 0.312,
+      "grad_norm": 0.2213257998228073,
+      "learning_rate": 0.00046869537313039343,
+      "loss": 3.5485220336914063,
+      "step": 15600
+    },
+    {
+      "epoch": 0.314,
+      "grad_norm": 0.28433483839035034,
+      "learning_rate": 0.0004671286336854554,
+      "loss": 3.558450012207031,
+      "step": 15700
+    },
+    {
+      "epoch": 0.316,
+      "grad_norm": 0.23959818482398987,
+      "learning_rate": 0.00046555525652178736,
+      "loss": 3.5676364135742187,
+      "step": 15800
+    },
+    {
+      "epoch": 0.318,
+      "grad_norm": 0.20079217851161957,
+      "learning_rate": 0.0004639753041279938,
+      "loss": 3.552779541015625,
+      "step": 15900
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.20217208564281464,
+      "learning_rate": 0.00046238883925382235,
+      "loss": 3.537972717285156,
+      "step": 16000
+    },
+    {
+      "epoch": 0.32,
+      "eval_accuracy": 0.363115024333292,
+      "eval_loss": 3.475611448287964,
+      "eval_runtime": 5.721,
+      "eval_samples_per_second": 339.274,
+      "eval_steps_per_second": 21.325,
+      "step": 16000
     }
   ],
   "logging_steps": 100,
@@ -1133,7 +1291,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.3897061376e+17,
+  "total_flos": 5.0168070144e+17,
   "train_batch_size": 120,
   "trial_name": null,
   "trial_params": null