Training in progress, step 24000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e851d31aa87e3f44cdb6b12860dfca56948ed93c4c3e52e3a3bc7173fa578a8b
+oid sha256:f097330090d54848c18e4bda429759e1abba010929a3213906365a68cd5e649a
 size 579824888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df630ecbd687f1359a191cc034b3009e41a878d4ab7fdb04cf787f0bc23ecb0c
+oid sha256:fec1594771eede4505411cf0b3849475f8da63ebefb31deacc4aea691322fb69
 size 1159794763

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43b610cc94e504b24cb2bb3bb992068bab81d217de2c8ad61ad01dfb75e98503
+oid sha256:12d604eeadf163b978dd48de387cbebeba84d52ce3a59a4bcf73ab714592e48f
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f23bcbe880608cbeb7ee4f55362f4ac1ed7848d0f02874b239279ca55eb68fab
+oid sha256:4793a1af866198c083bf7fdbba00d5a4fb25389a6bed64d9ca675044e94ad0ae
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.44,
+  "epoch": 0.48,
   "eval_steps": 1000,
-  "global_step": 22000,
+  "global_step": 24000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1746,6 +1746,164 @@
       "eval_samples_per_second": 297.832,
       "eval_steps_per_second": 18.72,
       "step": 22000
+    },
+    {
+      "epoch": 0.442,
+      "grad_norm": 0.13086584210395813,
+      "learning_rate": 0.0005932263306841439,
+      "loss": 3.4057171630859373,
+      "step": 22100
+    },
+    {
+      "epoch": 0.444,
+      "grad_norm": 0.14566738903522491,
+      "learning_rate": 0.0005901287109956757,
+      "loss": 3.374288330078125,
+      "step": 22200
+    },
+    {
+      "epoch": 0.446,
+      "grad_norm": 0.13566701114177704,
+      "learning_rate": 0.0005870275117348753,
+      "loss": 3.3892340087890624,
+      "step": 22300
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 0.18162570893764496,
+      "learning_rate": 0.0005839228560696758,
+      "loss": 3.417158508300781,
+      "step": 22400
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.1380554586648941,
+      "learning_rate": 0.0005808148673052863,
+      "loss": 3.385755615234375,
+      "step": 22500
+    },
+    {
+      "epoch": 0.452,
+      "grad_norm": 0.13876518607139587,
+      "learning_rate": 0.0005777036688792934,
+      "loss": 3.3734304809570315,
+      "step": 22600
+    },
+    {
+      "epoch": 0.454,
+      "grad_norm": 0.1451270580291748,
+      "learning_rate": 0.0005745893843567593,
+      "loss": 3.3767324829101564,
+      "step": 22700
+    },
+    {
+      "epoch": 0.456,
+      "grad_norm": 0.14231646060943604,
+      "learning_rate": 0.0005714721374253151,
+      "loss": 3.3700411987304686,
+      "step": 22800
+    },
+    {
+      "epoch": 0.458,
+      "grad_norm": 0.14160802960395813,
+      "learning_rate": 0.0005683520518902468,
+      "loss": 3.3719024658203125,
+      "step": 22900
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.15433672070503235,
+      "learning_rate": 0.0005652292516695795,
+      "loss": 3.3654217529296875,
+      "step": 23000
+    },
+    {
+      "epoch": 0.46,
+      "eval_accuracy": 0.3727878481747762,
+      "eval_loss": 3.3823931217193604,
+      "eval_runtime": 6.745,
+      "eval_samples_per_second": 287.769,
+      "eval_steps_per_second": 18.087,
+      "step": 23000
+    },
+    {
+      "epoch": 0.462,
+      "grad_norm": 0.13699641823768616,
+      "learning_rate": 0.0005621038607891551,
+      "loss": 3.3590658569335936,
+      "step": 23100
+    },
+    {
+      "epoch": 0.464,
+      "grad_norm": 0.14364606142044067,
+      "learning_rate": 0.0005589760033777068,
+      "loss": 3.3595770263671874,
+      "step": 23200
+    },
+    {
+      "epoch": 0.466,
+      "grad_norm": 0.15491677820682526,
+      "learning_rate": 0.0005558458036619291,
+      "loss": 3.3718606567382814,
+      "step": 23300
+    },
+    {
+      "epoch": 0.468,
+      "grad_norm": 0.14689157903194427,
+      "learning_rate": 0.0005527133859615443,
+      "loss": 3.3682122802734376,
+      "step": 23400
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.2537364363670349,
+      "learning_rate": 0.0005495788746843641,
+      "loss": 3.3676806640625,
+      "step": 23500
+    },
+    {
+      "epoch": 0.472,
+      "grad_norm": 0.15198677778244019,
+      "learning_rate": 0.0005464423943213493,
+      "loss": 3.3796755981445314,
+      "step": 23600
+    },
+    {
+      "epoch": 0.474,
+      "grad_norm": 0.14707693457603455,
+      "learning_rate": 0.0005433040694416661,
+      "loss": 3.3943267822265626,
+      "step": 23700
+    },
+    {
+      "epoch": 0.476,
+      "grad_norm": 0.13588809967041016,
+      "learning_rate": 0.0005401640246877371,
+      "loss": 3.3692440795898437,
+      "step": 23800
+    },
+    {
+      "epoch": 0.478,
+      "grad_norm": 0.1468556970357895,
+      "learning_rate": 0.0005370223847702919,
+      "loss": 3.35807861328125,
+      "step": 23900
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.15797235071659088,
+      "learning_rate": 0.0005338792744634145,
+      "loss": 3.3942901611328127,
+      "step": 24000
+    },
+    {
+      "epoch": 0.48,
+      "eval_accuracy": 0.3733514408918275,
+      "eval_loss": 3.375581741333008,
+      "eval_runtime": 7.2715,
+      "eval_samples_per_second": 266.931,
+      "eval_steps_per_second": 16.778,
+      "step": 24000
     }
   ],
   "logging_steps": 100,
@@ -1765,7 +1923,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.6239139069952e+17,
+  "total_flos": 9.4079060803584e+17,
   "train_batch_size": 120,
   "trial_name": null,
   "trial_params": null