Training in progress, step 30000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:101dd85060f77fe6ab87ec8a72c51f4493aee0cd0bb19e810811a805ed98aad4
+oid sha256:ac7b6e8e0e6c9527838b5b71a909559d9e98612b291cc816fa041bd4e932bc2f
 size 579824888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54ba4d04e29776946b001a6f6920fd7c30f03e9863aff3ad6b551f23caea0b60
+oid sha256:3e73756a742f5a52e3fb1f593643683cf7bad589d676e48aa89861e9865dadfc
 size 1159794763

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee44ef43900d0428f565a6ab0fb42d678379f6436ece4e4a6239f399d8eada96
+oid sha256:7d60e00b2d8189621a65a613490321cabbb70d9187223365d4f127c3fc0b2584
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf7545cbdf140980776a20b719262192e6070ee27cb1c9a27c369c20b3d411df
+oid sha256:02a3be2e7ecb88f30f5b2994e37142ffea2663c1e78cc9ead86da93ad8248f79
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.56,
+  "epoch": 0.6,
   "eval_steps": 1000,
-  "global_step": 28000,
+  "global_step": 30000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2220,6 +2220,164 @@
       "eval_samples_per_second": 292.932,
       "eval_steps_per_second": 18.412,
       "step": 28000
+    },
+    {
+      "epoch": 0.562,
+      "grad_norm": 0.14532077312469482,
+      "learning_rate": 0.0004052881194593424,
+      "loss": 3.372833251953125,
+      "step": 28100
+    },
+    {
+      "epoch": 0.564,
+      "grad_norm": 0.13675428926944733,
+      "learning_rate": 0.0004021960232718194,
+      "loss": 3.3700936889648436,
+      "step": 28200
+    },
+    {
+      "epoch": 0.566,
+      "grad_norm": 0.15135474503040314,
+      "learning_rate": 0.00039910781148922364,
+      "loss": 3.3734249877929687,
+      "step": 28300
+    },
+    {
+      "epoch": 0.568,
+      "grad_norm": 0.1487869918346405,
+      "learning_rate": 0.00039602360676367474,
+      "loss": 3.3548593139648437,
+      "step": 28400
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.12845182418823242,
+      "learning_rate": 0.00039294353158814783,
+      "loss": 3.3592022705078124,
+      "step": 28500
+    },
+    {
+      "epoch": 0.572,
+      "grad_norm": 0.15905176103115082,
+      "learning_rate": 0.0003898677082916068,
+      "loss": 3.375569152832031,
+      "step": 28600
+    },
+    {
+      "epoch": 0.574,
+      "grad_norm": 0.1350318342447281,
+      "learning_rate": 0.0003867962590341477,
+      "loss": 3.363053894042969,
+      "step": 28700
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 0.15002867579460144,
+      "learning_rate": 0.00038372930580214595,
+      "loss": 3.3725015258789064,
+      "step": 28800
+    },
+    {
+      "epoch": 0.578,
+      "grad_norm": 0.14523345232009888,
+      "learning_rate": 0.000380666970403412,
+      "loss": 3.375093688964844,
+      "step": 28900
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.1521645337343216,
+      "learning_rate": 0.000377609374462353,
+      "loss": 3.350813903808594,
+      "step": 29000
+    },
+    {
+      "epoch": 0.58,
+      "eval_accuracy": 0.3793452847252259,
+      "eval_loss": 3.322114944458008,
+      "eval_runtime": 6.9103,
+      "eval_samples_per_second": 280.884,
+      "eval_steps_per_second": 17.655,
+      "step": 29000
+    },
+    {
+      "epoch": 0.582,
+      "grad_norm": 0.14382348954677582,
+      "learning_rate": 0.00037455663941514335,
+      "loss": 3.3781756591796874,
+      "step": 29100
+    },
+    {
+      "epoch": 0.584,
+      "grad_norm": 0.1457841694355011,
+      "learning_rate": 0.00037150888650490057,
+      "loss": 3.3773403930664063,
+      "step": 29200
+    },
+    {
+      "epoch": 0.586,
+      "grad_norm": 0.13661234080791473,
+      "learning_rate": 0.0003684662367768703,
+      "loss": 3.3766348266601565,
+      "step": 29300
+    },
+    {
+      "epoch": 0.588,
+      "grad_norm": 0.16734236478805542,
+      "learning_rate": 0.00036542881107361983,
+      "loss": 3.3571905517578124,
+      "step": 29400
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.14157910645008087,
+      "learning_rate": 0.00036239673003023745,
+      "loss": 3.366629638671875,
+      "step": 29500
+    },
+    {
+      "epoch": 0.592,
+      "grad_norm": 0.13826872408390045,
+      "learning_rate": 0.0003593701140695413,
+      "loss": 3.3789642333984373,
+      "step": 29600
+    },
+    {
+      "epoch": 0.594,
+      "grad_norm": 0.1601548194885254,
+      "learning_rate": 0.00035634908339729813,
+      "loss": 3.37031005859375,
+      "step": 29700
+    },
+    {
+      "epoch": 0.596,
+      "grad_norm": 0.13469478487968445,
+      "learning_rate": 0.00035333375799744704,
+      "loss": 3.3534210205078123,
+      "step": 29800
+    },
+    {
+      "epoch": 0.598,
+      "grad_norm": 0.12652449309825897,
+      "learning_rate": 0.00035032425762733554,
+      "loss": 3.34040283203125,
+      "step": 29900
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.18712250888347626,
+      "learning_rate": 0.0003473207018129635,
+      "loss": 3.356614685058594,
+      "step": 30000
+    },
+    {
+      "epoch": 0.6,
+      "eval_accuracy": 0.3802063011480555,
+      "eval_loss": 3.314772367477417,
+      "eval_runtime": 6.363,
+      "eval_samples_per_second": 305.046,
+      "eval_steps_per_second": 19.173,
+      "step": 30000
     }
   ],
   "logging_steps": 100,
@@ -2239,7 +2397,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.09758904270848e+18,
+  "total_flos": 1.1759882600448e+18,
   "train_batch_size": 120,
   "trial_name": null,
   "trial_params": null