Training in progress, step 200, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7390f9f81e59c76a9d6ab0d8c707f4c87f467164b72cc20add67201bd21852d
+oid sha256:461a8fe0bbd13663ab3dd972387d88703c64c3540b767828d8a9ef1357b29a8f
 size 847599616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07c259decfaab80c17538e818b27844a7997ae01f1bc68bd0351e7c7013d6966
+oid sha256:fdccc7eb9376504ec64e1323859d828791b50f3f8842beac2c59f63105017379
 size 350603

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9373077514cae46a49373636d8533017b0efe6437cb3126984a56adfa969ea82
+oid sha256:65c0ddce770129db8af78a8281e61b32c4aba3200b93375ffc428f456531d83d
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7815f17b7bd928390d8a057e2a19101b8f840de5d7f859603bfc35694ee86edf
+oid sha256:ab66db99117673b461ceb8f3865fe0441f45aa01085a419aba1737c22700a3ed
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5,
+  "epoch": 1.0,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -166,6 +166,164 @@
       "eval_samples_per_second": 9.541,
       "eval_steps_per_second": 1.622,
       "step": 100
+    },
+    {
+      "epoch": 0.525,
+      "grad_norm": 0.07347024232149124,
+      "learning_rate": 2.033067889532717e-06,
+      "loss": 7.909750366210938,
+      "step": 105
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.07354505360126495,
+      "learning_rate": 1.8678188313486012e-06,
+      "loss": 7.931227111816407,
+      "step": 110
+    },
+    {
+      "epoch": 0.575,
+      "grad_norm": 0.09041173756122589,
+      "learning_rate": 1.7034727045763157e-06,
+      "loss": 7.868826293945313,
+      "step": 115
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.08841845393180847,
+      "learning_rate": 1.541152159906497e-06,
+      "loss": 7.831324768066406,
+      "step": 120
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 0.06918840855360031,
+      "learning_rate": 1.3819660112501052e-06,
+      "loss": 7.8350990295410154,
+      "step": 125
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.08589889854192734,
+      "learning_rate": 1.227001661415096e-06,
+      "loss": 7.875128173828125,
+      "step": 130
+    },
+    {
+      "epoch": 0.675,
+      "grad_norm": 0.07827843725681305,
+      "learning_rate": 1.0773176740426246e-06,
+      "loss": 7.833936309814453,
+      "step": 135
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.0692669078707695,
+      "learning_rate": 9.339365425440129e-07,
+      "loss": 7.741961669921875,
+      "step": 140
+    },
+    {
+      "epoch": 0.725,
+      "grad_norm": 0.10289043933153152,
+      "learning_rate": 7.978377054339498e-07,
+      "loss": 7.69259033203125,
+      "step": 145
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.09380868077278137,
+      "learning_rate": 6.699508557723032e-07,
+      "loss": 7.753170776367187,
+      "step": 150
+    },
+    {
+      "epoch": 0.75,
+      "eval_accuracy": 0.12066422466422466,
+      "eval_loss": 7.652101516723633,
+      "eval_runtime": 10.959,
+      "eval_samples_per_second": 9.125,
+      "eval_steps_per_second": 1.551,
+      "step": 150
+    },
+    {
+      "epoch": 0.775,
+      "grad_norm": 0.07780186086893082,
+      "learning_rate": 5.511495904178221e-07,
+      "loss": 7.669155883789062,
+      "step": 155
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.08477064967155457,
+      "learning_rate": 4.4224544247577535e-07,
+      "loss": 7.680642700195312,
+      "step": 160
+    },
+    {
+      "epoch": 0.825,
+      "grad_norm": 0.09825273603200912,
+      "learning_rate": 3.439823377039599e-07,
+      "loss": 7.696351623535156,
+      "step": 165
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.0829058587551117,
+      "learning_rate": 2.570315127454452e-07,
+      "loss": 7.609683227539063,
+      "step": 170
+    },
+    {
+      "epoch": 0.875,
+      "grad_norm": 0.159183531999588,
+      "learning_rate": 1.8198692990167497e-07,
+      "loss": 7.513552856445313,
+      "step": 175
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.06830265372991562,
+      "learning_rate": 1.1936121976767767e-07,
+      "loss": 7.567562103271484,
+      "step": 180
+    },
+    {
+      "epoch": 0.925,
+      "grad_norm": 0.12620584666728973,
+      "learning_rate": 6.958217944530287e-08,
+      "loss": 7.754322814941406,
+      "step": 185
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.08359432220458984,
+      "learning_rate": 3.2989850255235265e-08,
+      "loss": 7.56811294555664,
+      "step": 190
+    },
+    {
+      "epoch": 0.975,
+      "grad_norm": 0.07398480176925659,
+      "learning_rate": 9.834194909977168e-09,
+      "loss": 7.568279266357422,
+      "step": 195
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.07088548690080643,
+      "learning_rate": 2.7339001506199164e-10,
+      "loss": 7.527226257324219,
+      "step": 200
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.1237924297924298,
+      "eval_loss": 7.467564582824707,
+      "eval_runtime": 10.43,
+      "eval_samples_per_second": 9.588,
+      "eval_steps_per_second": 1.63,
+      "step": 200
     }
   ],
   "logging_steps": 5,
@@ -180,7 +338,7 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }