Training in progress, step 4000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87ea4ace6a540586d0d8fc8bf83f7e73daad02efd1f7cd1a6c188b463f0c6259
+oid sha256:c9b49abb386733d659f8846853b953d8bfa893a5edb2823f8a447929bfd32745
 size 499730128

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfd57e75500fd17d26ecdf881bc717d13a68ea98a0a6fd85deb5052ef3a991b5
+oid sha256:24d3fa191cfe1dd1dc390f89f18dbbbfa9880de322ada9c6a171a0a774436ce6
 size 812034507

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d920d35377b6218b0a182ca529dc7f210a3398080e4578011b7878234683794
+oid sha256:9e06dfbf969388fb27efc692631d298abe0d1c57738a0c64598fe664b1ac46b1
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e05547d8b4c2d503eaa441cb32a0d85a52189a237174a52b21fcd639756dcd0
+oid sha256:cf24e4defdf46195400e8438b36d0e4a5a96b33aa46ca9900cba0b1590594179
 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": 216.396,
       "eval_steps_per_second": 1.731,
       "step": 2000
+    },
+    {
+      "epoch": 0.042,
+      "grad_norm": 0.3252929747104645,
+      "learning_rate": 0.016792,
+      "loss": 4.336614685058594,
+      "step": 2100
+    },
+    {
+      "epoch": 0.044,
+      "grad_norm": 0.3191538155078888,
+      "learning_rate": 0.017592,
+      "loss": 4.3118289184570315,
+      "step": 2200
+    },
+    {
+      "epoch": 0.046,
+      "grad_norm": 0.11609218269586563,
+      "learning_rate": 0.018392,
+      "loss": 4.328140563964844,
+      "step": 2300
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 0.09269429743289948,
+      "learning_rate": 0.019192,
+      "loss": 4.2995166015625,
+      "step": 2400
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.11243760585784912,
+      "learning_rate": 0.019992000000000003,
+      "loss": 4.306504821777343,
+      "step": 2500
+    },
+    {
+      "epoch": 0.052,
+      "grad_norm": 0.1890493929386139,
+      "learning_rate": 0.019999785636239033,
+      "loss": 4.267638549804688,
+      "step": 2600
+    },
+    {
+      "epoch": 0.054,
+      "grad_norm": 0.09589467197656631,
+      "learning_rate": 0.01999913387133122,
+      "loss": 4.277190551757813,
+      "step": 2700
+    },
+    {
+      "epoch": 0.056,
+      "grad_norm": 0.21187792718410492,
+      "learning_rate": 0.019998044711915176,
+      "loss": 4.244146118164062,
+      "step": 2800
+    },
+    {
+      "epoch": 0.058,
+      "grad_norm": 0.18817682564258575,
+      "learning_rate": 0.019996518205634257,
+      "loss": 4.229488220214844,
+      "step": 2900
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.1112157553434372,
+      "learning_rate": 0.0199945544192628,
+      "loss": 4.231150512695312,
+      "step": 3000
+    },
+    {
+      "epoch": 0.06,
+      "eval_accuracy": 0.2808140900195695,
+      "eval_loss": 4.229600429534912,
+      "eval_runtime": 4.8217,
+      "eval_samples_per_second": 207.397,
+      "eval_steps_per_second": 1.659,
+      "step": 3000
+    },
+    {
+      "epoch": 0.062,
+      "grad_norm": 0.3390547037124634,
+      "learning_rate": 0.019992153438703173,
+      "loss": 4.223145141601562,
+      "step": 3100
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 0.7005836367607117,
+      "learning_rate": 0.019989315368982054,
+      "loss": 4.203560791015625,
+      "step": 3200
+    },
+    {
+      "epoch": 0.066,
+      "grad_norm": 0.1793125420808792,
+      "learning_rate": 0.019986040334245798,
+      "loss": 4.1834033203125,
+      "step": 3300
+    },
+    {
+      "epoch": 0.068,
+      "grad_norm": 0.11384831368923187,
+      "learning_rate": 0.019982328477755038,
+      "loss": 4.1909048461914065,
+      "step": 3400
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.6594609022140503,
+      "learning_rate": 0.019978179961878402,
+      "loss": 4.169663696289063,
+      "step": 3500
+    },
+    {
+      "epoch": 0.072,
+      "grad_norm": 0.3771114647388458,
+      "learning_rate": 0.01997359496808541,
+      "loss": 4.174803161621094,
+      "step": 3600
+    },
+    {
+      "epoch": 0.074,
+      "grad_norm": 0.31003686785697937,
+      "learning_rate": 0.01996857369693855,
+      "loss": 4.1531503295898435,
+      "step": 3700
+    },
+    {
+      "epoch": 0.076,
+      "grad_norm": 0.11918768286705017,
+      "learning_rate": 0.019963116368084486,
+      "loss": 4.163074951171875,
+      "step": 3800
+    },
+    {
+      "epoch": 0.078,
+      "grad_norm": 0.5589029788970947,
+      "learning_rate": 0.01995722322024446,
+      "loss": 4.147608032226563,
+      "step": 3900
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.15616266429424286,
+      "learning_rate": 0.01995089451120385,
+      "loss": 4.122293701171875,
+      "step": 4000
+    },
+    {
+      "epoch": 0.08,
+      "eval_accuracy": 0.287454011741683,
+      "eval_loss": 4.152503967285156,
+      "eval_runtime": 4.8042,
+      "eval_samples_per_second": 208.152,
+      "eval_steps_per_second": 1.665,
+      "step": 4000
     }
   ],
   "logging_steps": 100,