Training in progress, step 4000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2a193933a701dc0f71711b06b789f4ce61a8231b50c23d78cd67e1473cab528
+oid sha256:8e0204cf51b4c0454e7406fa74c21a5e0237b72b16d8ea379e5d411dd6b4fe48
 size 529337896

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e42073b4332f17525a5be43285c6bf9938b3269e377a9d0cc0a79fe7bbb1698e
+oid sha256:30f4ed06e1e181ea3e149a774abae5fb9a53631081196369a72dea4441008fd6
 size 871247243

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14cd4a8cf54ce87e9e7818ae50060fa501ea05e8685c2025ab631bfde31c87cf
+oid sha256:93a7a87e66fdab18edc7df0621c2a005fd54541ab1c68bc3e038e8b969d2fabe
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b716fb1dcbc77ddc6a0ae7c4c98d559e36f1986fff006ef6982bd75247833235
+oid sha256:76cf98a8cde877f1e49a9e4b884c4dce3d51bb4035429d464e74acc35ddca024
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04,
+  "epoch": 0.08,
   "eval_steps": 1000,
-  "global_step": 2000,
+  "global_step": 4000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -166,6 +166,164 @@
       "eval_samples_per_second": 80.178,
       "eval_steps_per_second": 0.641,
       "step": 2000
+    },
+    {
+      "epoch": 0.042,
+      "grad_norm": 0.2820931077003479,
+      "learning_rate": 0.0016792,
+      "loss": 4.5201,
+      "step": 2100
+    },
+    {
+      "epoch": 0.044,
+      "grad_norm": 0.23724448680877686,
+      "learning_rate": 0.0017592,
+      "loss": 4.1333,
+      "step": 2200
+    },
+    {
+      "epoch": 0.046,
+      "grad_norm": 0.2325439602136612,
+      "learning_rate": 0.0018392,
+      "loss": 4.1072,
+      "step": 2300
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 0.23736131191253662,
+      "learning_rate": 0.0019192,
+      "loss": 4.0682,
+      "step": 2400
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.2313733696937561,
+      "learning_rate": 0.0019992,
+      "loss": 4.0571,
+      "step": 2500
+    },
+    {
+      "epoch": 0.052,
+      "grad_norm": 0.22318924963474274,
+      "learning_rate": 0.001999978563623903,
+      "loss": 4.0153,
+      "step": 2600
+    },
+    {
+      "epoch": 0.054,
+      "grad_norm": 0.20275355875492096,
+      "learning_rate": 0.0019999133871331223,
+      "loss": 4.0163,
+      "step": 2700
+    },
+    {
+      "epoch": 0.056,
+      "grad_norm": 0.21306632459163666,
+      "learning_rate": 0.0019998044711915177,
+      "loss": 3.9777,
+      "step": 2800
+    },
+    {
+      "epoch": 0.058,
+      "grad_norm": 0.19690750539302826,
+      "learning_rate": 0.0019996518205634257,
+      "loss": 3.9603,
+      "step": 2900
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.20464760065078735,
+      "learning_rate": 0.0019994554419262797,
+      "loss": 3.9566,
+      "step": 3000
+    },
+    {
+      "epoch": 0.06,
+      "eval_accuracy": 0.3226555772994129,
+      "eval_loss": 3.9112932682037354,
+      "eval_runtime": 11.7171,
+      "eval_samples_per_second": 85.345,
+      "eval_steps_per_second": 0.683,
+      "step": 3000
+    },
+    {
+      "epoch": 0.062,
+      "grad_norm": 0.18151508271694183,
+      "learning_rate": 0.001999215343870317,
+      "loss": 3.9501,
+      "step": 3100
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 0.18748600780963898,
+      "learning_rate": 0.0019989315368982054,
+      "loss": 3.9228,
+      "step": 3200
+    },
+    {
+      "epoch": 0.066,
+      "grad_norm": 0.17895972728729248,
+      "learning_rate": 0.0019986040334245797,
+      "loss": 3.9041,
+      "step": 3300
+    },
+    {
+      "epoch": 0.068,
+      "grad_norm": 0.18976759910583496,
+      "learning_rate": 0.001998232847775504,
+      "loss": 3.9123,
+      "step": 3400
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.1871727555990219,
+      "learning_rate": 0.0019978179961878404,
+      "loss": 3.8846,
+      "step": 3500
+    },
+    {
+      "epoch": 0.072,
+      "grad_norm": 0.17986708879470825,
+      "learning_rate": 0.001997359496808541,
+      "loss": 3.8794,
+      "step": 3600
+    },
+    {
+      "epoch": 0.074,
+      "grad_norm": 0.17090782523155212,
+      "learning_rate": 0.001996857369693855,
+      "loss": 3.8593,
+      "step": 3700
+    },
+    {
+      "epoch": 0.076,
+      "grad_norm": 0.19015273451805115,
+      "learning_rate": 0.0019963116368084486,
+      "loss": 3.8642,
+      "step": 3800
+    },
+    {
+      "epoch": 0.078,
+      "grad_norm": 0.1871633529663086,
+      "learning_rate": 0.001995722322024446,
+      "loss": 3.8479,
+      "step": 3900
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.18049727380275726,
+      "learning_rate": 0.001995089451120385,
+      "loss": 3.8226,
+      "step": 4000
+    },
+    {
+      "epoch": 0.08,
+      "eval_accuracy": 0.33194520547945205,
+      "eval_loss": 3.8037452697753906,
+      "eval_runtime": 12.6853,
+      "eval_samples_per_second": 78.832,
+      "eval_steps_per_second": 0.631,
+      "step": 4000
     }
   ],
   "logging_steps": 100,