Training in progress, step 6000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93b4d618fee0aaf987ff44511c965a4a13d55a3d93f354ed73c1f91c3e21dccc
+oid sha256:9a3b1570476040558106ef329ac5c35eaf7b927d872082a820226ad0028b5dd9
 size 496262784

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d79704be2307835f0582a7f7abe29d698ca7dbc76fdb78dc7bbfd0aaa6990b77
+oid sha256:ac1c439f2b333c6ba22b924fd6eb4e28a8524e3ac41694760d6b949858f9f4ad
 size 992621963

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9e2628e78d1dc996f476f66725a5d868b6e07dce08fc0df5d5fb50fcc8f9636
+oid sha256:595e0adb3f51b4014c388d14cb8a20e5767cd34a947ffb570078cd186928d2c7
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c683ea10141469aa50dfa283ef5ec8ac410a06cef28bfb1e66e6a7d94e82730d
+oid sha256:f43de46bf0618be59b12a78ea440d0013f604015e857ea4a03ea845dabb299ad
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.08,
+  "epoch": 0.12,
   "eval_steps": 1000,
-  "global_step": 4000,
+  "global_step": 6000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -324,6 +324,164 @@
       "eval_samples_per_second": 309.393,
       "eval_steps_per_second": 19.447,
       "step": 4000
+    },
+    {
+      "epoch": 0.082,
+      "grad_norm": 0.2674967348575592,
+      "learning_rate": 0.0005907574406673935,
+      "loss": 3.9582391357421876,
+      "step": 4100
+    },
+    {
+      "epoch": 0.084,
+      "grad_norm": 0.25437116622924805,
+      "learning_rate": 0.0005902859921636611,
+      "loss": 3.942552185058594,
+      "step": 4200
+    },
+    {
+      "epoch": 0.086,
+      "grad_norm": 0.25480520725250244,
+      "learning_rate": 0.0005898030145956102,
+      "loss": 3.9550421142578127,
+      "step": 4300
+    },
+    {
+      "epoch": 0.088,
+      "grad_norm": 0.25695815682411194,
+      "learning_rate": 0.0005893085271452874,
+      "loss": 3.9156878662109373,
+      "step": 4400
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.25535979866981506,
+      "learning_rate": 0.0005888025494518687,
+      "loss": 3.9294302368164065,
+      "step": 4500
+    },
+    {
+      "epoch": 0.092,
+      "grad_norm": 0.24557402729988098,
+      "learning_rate": 0.0005882851016108786,
+      "loss": 3.927276306152344,
+      "step": 4600
+    },
+    {
+      "epoch": 0.094,
+      "grad_norm": 0.26716557145118713,
+      "learning_rate": 0.0005877562041733932,
+      "loss": 3.904244384765625,
+      "step": 4700
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 0.2525787651538849,
+      "learning_rate": 0.0005872158781452231,
+      "loss": 3.8892666625976564,
+      "step": 4800
+    },
+    {
+      "epoch": 0.098,
+      "grad_norm": 0.3125140964984894,
+      "learning_rate": 0.0005866641449860792,
+      "loss": 3.887486572265625,
+      "step": 4900
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.2451365739107132,
+      "learning_rate": 0.0005861010266087211,
+      "loss": 3.875788269042969,
+      "step": 5000
+    },
+    {
+      "epoch": 0.1,
+      "eval_accuracy": 0.32875099183244255,
+      "eval_loss": 3.831427812576294,
+      "eval_runtime": 5.9329,
+      "eval_samples_per_second": 327.159,
+      "eval_steps_per_second": 20.563,
+      "step": 5000
+    },
+    {
+      "epoch": 0.102,
+      "grad_norm": 0.28080520033836365,
+      "learning_rate": 0.0005855265453780858,
+      "loss": 3.8711001586914064,
+      "step": 5100
+    },
+    {
+      "epoch": 0.104,
+      "grad_norm": 0.25133365392684937,
+      "learning_rate": 0.0005849407241104003,
+      "loss": 3.8725830078125,
+      "step": 5200
+    },
+    {
+      "epoch": 0.106,
+      "grad_norm": 0.27164554595947266,
+      "learning_rate": 0.000584343586072275,
+      "loss": 3.847073974609375,
+      "step": 5300
+    },
+    {
+      "epoch": 0.108,
+      "grad_norm": 0.2697848081588745,
+      "learning_rate": 0.0005837351549797795,
+      "loss": 3.79802978515625,
+      "step": 5400
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.27253684401512146,
+      "learning_rate": 0.0005831154549975012,
+      "loss": 3.812421875,
+      "step": 5500
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 0.27660876512527466,
+      "learning_rate": 0.0005824845107375853,
+      "loss": 3.7727542114257813,
+      "step": 5600
+    },
+    {
+      "epoch": 0.114,
+      "grad_norm": 0.2439262717962265,
+      "learning_rate": 0.0005818423472587571,
+      "loss": 3.7664410400390627,
+      "step": 5700
+    },
+    {
+      "epoch": 0.116,
+      "grad_norm": 0.24943126738071442,
+      "learning_rate": 0.0005811889900653269,
+      "loss": 3.7883651733398436,
+      "step": 5800
+    },
+    {
+      "epoch": 0.118,
+      "grad_norm": 0.2556191682815552,
+      "learning_rate": 0.0005805244651061771,
+      "loss": 3.7454019165039063,
+      "step": 5900
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.27899155020713806,
+      "learning_rate": 0.0005798487987737322,
+      "loss": 3.767793884277344,
+      "step": 6000
+    },
+    {
+      "epoch": 0.12,
+      "eval_accuracy": 0.33610391076885543,
+      "eval_loss": 3.7605059146881104,
+      "eval_runtime": 5.697,
+      "eval_samples_per_second": 340.705,
+      "eval_steps_per_second": 21.415,
+      "step": 6000
     }
   ],
   "logging_steps": 100,
@@ -343,7 +501,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2542017536e+17,
+  "total_flos": 1.8813026304e+17,
   "train_batch_size": 120,
   "trial_name": null,
   "trial_params": null