Training in progress, step 14000, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bf78147f8e343a711c04d4bced1b1a3bee4e119ef0f393d9d961e3d7be9bbf4
+oid sha256:d83d6102ebf5de90168247dfb26a053d21b8bdbeffa91fb69bca4af6eb8e2b21
 size 1442699

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f11349bd4f131a5fba4fe75d7c08a58fc14a9f73c279ad7c85382a75c423a593
+oid sha256:61360873e3a81c9e45e52a5cbe113c9e7068874f4a45d19362611a315a846097
 size 499774435

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:149d23a52063855ad630babdef2c6cdf6cb494879a59b9a4f1ccc02ef38dc56a
+oid sha256:94f6ee8bbd82280164293554df7d005c34940bc65c2ff4bd41156f7ef7c035a3
 size 14455

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43ab2089bb2cb7b873a77ac8e24a3b3b2416ededca3811b6bb0922f61bea4c99
+oid sha256:5dcd90d4261e8acb8aa69d2cdcf6bd4451975f95262601bbfdb94f38ebb145b3
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.24,
+  "epoch": 0.28,
   "eval_steps": 1000,
-  "global_step": 12000,
+  "global_step": 14000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -956,6 +956,164 @@
       "eval_samples_per_second": 147.662,
       "eval_steps_per_second": 18.458,
       "step": 12000
+    },
+    {
+      "epoch": 0.242,
+      "grad_norm": 0.40804609656333923,
+      "learning_rate": 0.0018051510141940939,
+      "loss": 4.809200744628907,
+      "step": 12100
+    },
+    {
+      "epoch": 0.244,
+      "grad_norm": 0.23709678649902344,
+      "learning_rate": 0.00180121094046208,
+      "loss": 4.694277648925781,
+      "step": 12200
+    },
+    {
+      "epoch": 0.246,
+      "grad_norm": 0.3795485496520996,
+      "learning_rate": 0.001797235819167967,
+      "loss": 4.7016690063476565,
+      "step": 12300
+    },
+    {
+      "epoch": 0.248,
+      "grad_norm": 0.2936651110649109,
+      "learning_rate": 0.0017932258241964375,
+      "loss": 4.7381680297851565,
+      "step": 12400
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.3166375160217285,
+      "learning_rate": 0.0017891811309576622,
+      "loss": 4.715390014648437,
+      "step": 12500
+    },
+    {
+      "epoch": 0.252,
+      "grad_norm": 0.43418648838996887,
+      "learning_rate": 0.001785101916379627,
+      "loss": 4.731936340332031,
+      "step": 12600
+    },
+    {
+      "epoch": 0.254,
+      "grad_norm": 0.6372531652450562,
+      "learning_rate": 0.0017809883589003912,
+      "loss": 4.717911071777344,
+      "step": 12700
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 0.3290679454803467,
+      "learning_rate": 0.0017768406384602862,
+      "loss": 4.715725708007812,
+      "step": 12800
+    },
+    {
+      "epoch": 0.258,
+      "grad_norm": 0.5329638123512268,
+      "learning_rate": 0.00177265893649404,
+      "loss": 4.697486572265625,
+      "step": 12900
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.4434824287891388,
+      "learning_rate": 0.0017684434359228438,
+      "loss": 4.648684387207031,
+      "step": 13000
+    },
+    {
+      "epoch": 0.26,
+      "eval_accuracy": 0.2430587084148728,
+      "eval_loss": 4.6857452392578125,
+      "eval_runtime": 6.673,
+      "eval_samples_per_second": 149.859,
+      "eval_steps_per_second": 18.732,
+      "step": 13000
+    },
+    {
+      "epoch": 0.262,
+      "grad_norm": 1.1536272764205933,
+      "learning_rate": 0.0017641943211463488,
+      "loss": 4.693533935546875,
+      "step": 13100
+    },
+    {
+      "epoch": 0.264,
+      "grad_norm": 0.2765742838382721,
+      "learning_rate": 0.0017599117780346006,
+      "loss": 4.62672119140625,
+      "step": 13200
+    },
+    {
+      "epoch": 0.266,
+      "grad_norm": 0.3210831880569458,
+      "learning_rate": 0.0017555959939199084,
+      "loss": 4.677549438476563,
+      "step": 13300
+    },
+    {
+      "epoch": 0.268,
+      "grad_norm": 0.45882949233055115,
+      "learning_rate": 0.0017512471575886505,
+      "loss": 4.613779602050781,
+      "step": 13400
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.26687324047088623,
+      "learning_rate": 0.0017468654592730168,
+      "loss": 4.792513427734375,
+      "step": 13500
+    },
+    {
+      "epoch": 0.272,
+      "grad_norm": 0.48945170640945435,
+      "learning_rate": 0.0017424510906426853,
+      "loss": 4.670322875976563,
+      "step": 13600
+    },
+    {
+      "epoch": 0.274,
+      "grad_norm": 0.4301573634147644,
+      "learning_rate": 0.0017380042447964414,
+      "loss": 4.652569885253906,
+      "step": 13700
+    },
+    {
+      "epoch": 0.276,
+      "grad_norm": 0.40779948234558105,
+      "learning_rate": 0.0017335251162537279,
+      "loss": 4.63238525390625,
+      "step": 13800
+    },
+    {
+      "epoch": 0.278,
+      "grad_norm": 0.3157722055912018,
+      "learning_rate": 0.0017290139009461377,
+      "loss": 4.648804321289062,
+      "step": 13900
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.5345812439918518,
+      "learning_rate": 0.0017244707962088424,
+      "loss": 4.689738159179687,
+      "step": 14000
+    },
+    {
+      "epoch": 0.28,
+      "eval_accuracy": 0.24557729941291584,
+      "eval_loss": 4.648989200592041,
+      "eval_runtime": 6.7439,
+      "eval_samples_per_second": 148.281,
+      "eval_steps_per_second": 18.535,
+      "step": 14000
     }
   ],
   "logging_steps": 100,