Training in progress, step 18000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69c3b821cf12eeaa022a644bc22041eac717a7550c375de853c5ee543353c15e
+oid sha256:d69e130591023d3408c94e3445de9f9023a881b14d399648ae4226ee5bff553b
 size 496262784

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:099f48c6bd773fc094319bca20e4dc9f9c6178fc27af5dbdbf0e8f59bf625192
+oid sha256:a86f5fd274e719671c5f2463396daaf1a7a1c0ce3b5b26f63b7d962eb3bc34f1
 size 992621963

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79bfab8e6d704b55615f0aa752b32bcc403a434935bef147322933f0756a46f1
+oid sha256:7a721edff9706126df51d3abc78a93078e6b8e75513d77f55a62d72e4c5b16cf
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3daf8da2259c0a45cc86b801dfa39aec812fc636174a8b32bb6d363e93dc412
+oid sha256:5637b5a3d72a0623ba9410834e3d0160dfe8e69a524a3dc9973a65396f79b127
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.32,
+  "epoch": 0.36,
   "eval_steps": 1000,
-  "global_step": 16000,
+  "global_step": 18000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1272,6 +1272,164 @@
       "eval_samples_per_second": 339.274,
       "eval_steps_per_second": 21.325,
       "step": 16000
+    },
+    {
+      "epoch": 0.322,
+      "grad_norm": 0.22858326137065887,
+      "learning_rate": 0.00046079592490767184,
+      "loss": 3.5346307373046875,
+      "step": 16100
+    },
+    {
+      "epoch": 0.324,
+      "grad_norm": 0.19820822775363922,
+      "learning_rate": 0.0004591966243540899,
+      "loss": 3.559911804199219,
+      "step": 16200
+    },
+    {
+      "epoch": 0.326,
+      "grad_norm": 0.19681668281555176,
+      "learning_rate": 0.0004575910011112601,
+      "loss": 3.5361669921875,
+      "step": 16300
+    },
+    {
+      "epoch": 0.328,
+      "grad_norm": 0.19931091368198395,
+      "learning_rate": 0.0004559791189484793,
+      "loss": 3.5331732177734376,
+      "step": 16400
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.20607522130012512,
+      "learning_rate": 0.0004543610418836253,
+      "loss": 3.5401296997070313,
+      "step": 16500
+    },
+    {
+      "epoch": 0.332,
+      "grad_norm": 0.21663250029087067,
+      "learning_rate": 0.0004527368341806138,
+      "loss": 3.530547790527344,
+      "step": 16600
+    },
+    {
+      "epoch": 0.334,
+      "grad_norm": 0.219991534948349,
+      "learning_rate": 0.00045110656034684634,
+      "loss": 3.535267639160156,
+      "step": 16700
+    },
+    {
+      "epoch": 0.336,
+      "grad_norm": 0.1956709921360016,
+      "learning_rate": 0.00044947028513064836,
+      "loss": 3.533216552734375,
+      "step": 16800
+    },
+    {
+      "epoch": 0.338,
+      "grad_norm": 0.20111192762851715,
+      "learning_rate": 0.0004478280735186978,
+      "loss": 3.5435382080078126,
+      "step": 16900
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.1945837289094925,
+      "learning_rate": 0.0004461799907334432,
+      "loss": 3.509302978515625,
+      "step": 17000
+    },
+    {
+      "epoch": 0.34,
+      "eval_accuracy": 0.3652453846394267,
+      "eval_loss": 3.4567112922668457,
+      "eval_runtime": 5.9273,
+      "eval_samples_per_second": 327.467,
+      "eval_steps_per_second": 20.583,
+      "step": 17000
+    },
+    {
+      "epoch": 0.342,
+      "grad_norm": 0.22662605345249176,
+      "learning_rate": 0.0004445261022305145,
+      "loss": 3.5362484741210936,
+      "step": 17100
+    },
+    {
+      "epoch": 0.344,
+      "grad_norm": 0.19569633901119232,
+      "learning_rate": 0.00044286647369612284,
+      "loss": 3.4980740356445312,
+      "step": 17200
+    },
+    {
+      "epoch": 0.346,
+      "grad_norm": 0.1999066174030304,
+      "learning_rate": 0.0004412011710444514,
+      "loss": 3.5234307861328125,
+      "step": 17300
+    },
+    {
+      "epoch": 0.348,
+      "grad_norm": 0.209122896194458,
+      "learning_rate": 0.00043953026041503805,
+      "loss": 3.517156677246094,
+      "step": 17400
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.2141777127981186,
+      "learning_rate": 0.0004378538081701487,
+      "loss": 3.5367440795898437,
+      "step": 17500
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 0.20216333866119385,
+      "learning_rate": 0.0004361718808921406,
+      "loss": 3.5334283447265626,
+      "step": 17600
+    },
+    {
+      "epoch": 0.354,
+      "grad_norm": 0.24760980904102325,
+      "learning_rate": 0.0004344845453808194,
+      "loss": 3.516435546875,
+      "step": 17700
+    },
+    {
+      "epoch": 0.356,
+      "grad_norm": 0.19526250660419464,
+      "learning_rate": 0.0004327918686507849,
+      "loss": 3.526764221191406,
+      "step": 17800
+    },
+    {
+      "epoch": 0.358,
+      "grad_norm": 0.2374846190214157,
+      "learning_rate": 0.00043109391792877017,
+      "loss": 3.5132098388671875,
+      "step": 17900
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.20901496708393097,
+      "learning_rate": 0.00042939076065097133,
+      "loss": 3.5150552368164063,
+      "step": 18000
+    },
+    {
+      "epoch": 0.36,
+      "eval_accuracy": 0.36633224143545756,
+      "eval_loss": 3.4449119567871094,
+      "eval_runtime": 6.3421,
+      "eval_samples_per_second": 306.051,
+      "eval_steps_per_second": 19.237,
+      "step": 18000
     }
   ],
   "logging_steps": 100,
@@ -1291,7 +1449,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.0168070144e+17,
+  "total_flos": 5.6439078912e+17,
   "train_batch_size": 120,
   "trial_name": null,
   "trial_params": null