Training in progress, step 32000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac7b6e8e0e6c9527838b5b71a909559d9e98612b291cc816fa041bd4e932bc2f
+oid sha256:4abcfe19109678f34d3ff11a8d3ce7a037cf1f3d94b5bd2c29643daf81f1deb6
 size 579824888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e73756a742f5a52e3fb1f593643683cf7bad589d676e48aa89861e9865dadfc
+oid sha256:4ed11d32ed680b24cb759e32cd2f16ac63d1901c6c0f38c4ba936bb380de271e
 size 1159794763

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d60e00b2d8189621a65a613490321cabbb70d9187223365d4f127c3fc0b2584
+oid sha256:c7ce608857b08326fa7d341f30263d7dc70be1ec0abf4c06d041f987c5ac0d05
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02a3be2e7ecb88f30f5b2994e37142ffea2663c1e78cc9ead86da93ad8248f79
+oid sha256:eb48a6869c32358f585d366d73d143bd6791297810d0a877b008b19b1b4c14d7
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6,
+  "epoch": 0.64,
   "eval_steps": 1000,
-  "global_step": 30000,
+  "global_step": 32000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2378,6 +2378,164 @@
       "eval_samples_per_second": 305.046,
       "eval_steps_per_second": 19.173,
       "step": 30000
+    },
+    {
+      "epoch": 0.602,
+      "grad_norm": 0.14657410979270935,
+      "learning_rate": 0.0003443232098442347,
+      "loss": 3.3668572998046873,
+      "step": 30100
+    },
+    {
+      "epoch": 0.604,
+      "grad_norm": 0.138699010014534,
+      "learning_rate": 0.0003413319007702201,
+      "loss": 3.3502297973632813,
+      "step": 30200
+    },
+    {
+      "epoch": 0.606,
+      "grad_norm": 0.15832597017288208,
+      "learning_rate": 0.0003383468933944299,
+      "loss": 3.355211181640625,
+      "step": 30300
+    },
+    {
+      "epoch": 0.608,
+      "grad_norm": 0.15029780566692352,
+      "learning_rate": 0.0003353683062700939,
+      "loss": 3.348283386230469,
+      "step": 30400
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.17595185339450836,
+      "learning_rate": 0.0003323962576954539,
+      "loss": 3.3513107299804688,
+      "step": 30500
+    },
+    {
+      "epoch": 0.612,
+      "grad_norm": 0.1754045933485031,
+      "learning_rate": 0.00032943086570906576,
+      "loss": 3.3677444458007812,
+      "step": 30600
+    },
+    {
+      "epoch": 0.614,
+      "grad_norm": 0.14994262158870697,
+      "learning_rate": 0.00032647224808511,
+      "loss": 3.3526513671875,
+      "step": 30700
+    },
+    {
+      "epoch": 0.616,
+      "grad_norm": 0.14404474198818207,
+      "learning_rate": 0.00032352052232871543,
+      "loss": 3.31786865234375,
+      "step": 30800
+    },
+    {
+      "epoch": 0.618,
+      "grad_norm": 0.14154170453548431,
+      "learning_rate": 0.0003205758056712919,
+      "loss": 3.341680908203125,
+      "step": 30900
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.13272085785865784,
+      "learning_rate": 0.0003176382150658742,
+      "loss": 3.344057922363281,
+      "step": 31000
+    },
+    {
+      "epoch": 0.62,
+      "eval_accuracy": 0.3808566004369608,
+      "eval_loss": 3.3054208755493164,
+      "eval_runtime": 6.7684,
+      "eval_samples_per_second": 286.774,
+      "eval_steps_per_second": 18.025,
+      "step": 31000
+    },
+    {
+      "epoch": 0.622,
+      "grad_norm": 0.14439266920089722,
+      "learning_rate": 0.00031470786718247704,
+      "loss": 3.336947021484375,
+      "step": 31100
+    },
+    {
+      "epoch": 0.624,
+      "grad_norm": 0.1481838971376419,
+      "learning_rate": 0.000311784878403462,
+      "loss": 3.3591497802734374,
+      "step": 31200
+    },
+    {
+      "epoch": 0.626,
+      "grad_norm": 0.13957072794437408,
+      "learning_rate": 0.00030886936481891447,
+      "loss": 3.333016357421875,
+      "step": 31300
+    },
+    {
+      "epoch": 0.628,
+      "grad_norm": 0.1470046043395996,
+      "learning_rate": 0.0003059614422220331,
+      "loss": 3.349130859375,
+      "step": 31400
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.13627968728542328,
+      "learning_rate": 0.00030306122610453183,
+      "loss": 3.3334747314453126,
+      "step": 31500
+    },
+    {
+      "epoch": 0.632,
+      "grad_norm": 0.27877408266067505,
+      "learning_rate": 0.00030016883165205166,
+      "loss": 3.3201373291015623,
+      "step": 31600
+    },
+    {
+      "epoch": 0.634,
+      "grad_norm": 0.14691542088985443,
+      "learning_rate": 0.00029728437373958684,
+      "loss": 3.3420004272460937,
+      "step": 31700
+    },
+    {
+      "epoch": 0.636,
+      "grad_norm": 0.1655166745185852,
+      "learning_rate": 0.0002944079669269224,
+      "loss": 3.32868408203125,
+      "step": 31800
+    },
+    {
+      "epoch": 0.638,
+      "grad_norm": 0.16263002157211304,
+      "learning_rate": 0.0002915397254540836,
+      "loss": 3.327845153808594,
+      "step": 31900
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.13551194965839386,
+      "learning_rate": 0.00028867976323679957,
+      "loss": 3.326793518066406,
+      "step": 32000
+    },
+    {
+      "epoch": 0.64,
+      "eval_accuracy": 0.38135970019690457,
+      "eval_loss": 3.302846908569336,
+      "eval_runtime": 6.3825,
+      "eval_samples_per_second": 304.112,
+      "eval_steps_per_second": 19.115,
+      "step": 32000
     }
   ],
   "logging_steps": 100,
@@ -2397,7 +2555,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1759882600448e+18,
+  "total_flos": 1.25438747738112e+18,
   "train_batch_size": 120,
   "trial_name": null,
   "trial_params": null