Training in progress, step 200, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9e0d930706cfcb392491da03f8a50820f032ca5714fc8d8cf3a436cc2b448c3
+oid sha256:af6da459219a0dfd520f8f9bef95d70b69541238260a186de064e8b3b9622d4b
 size 847599616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7861d452becbacd4ed7de2869406ad518e79c266cc3e0868a27bae3770d6e23
+oid sha256:95176d612444486929b2741997bdaf23b4fa67dd8b2c66bf57fa5ea76b78cfed
 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": 9.564,
       "eval_steps_per_second": 1.626,
       "step": 100
+    },
+    {
+      "epoch": 0.525,
+      "grad_norm": 0.08703620731830597,
+      "learning_rate": 2.033067889532717e-06,
+      "loss": 8.251353454589843,
+      "step": 105
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.08461801707744598,
+      "learning_rate": 1.8678188313486012e-06,
+      "loss": 8.270049285888671,
+      "step": 110
+    },
+    {
+      "epoch": 0.575,
+      "grad_norm": 0.09749548882246017,
+      "learning_rate": 1.7034727045763157e-06,
+      "loss": 8.217508697509766,
+      "step": 115
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.08456026017665863,
+      "learning_rate": 1.541152159906497e-06,
+      "loss": 8.169024658203124,
+      "step": 120
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 0.07748560607433319,
+      "learning_rate": 1.3819660112501052e-06,
+      "loss": 8.160218811035156,
+      "step": 125
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.07981108874082565,
+      "learning_rate": 1.227001661415096e-06,
+      "loss": 8.195584869384765,
+      "step": 130
+    },
+    {
+      "epoch": 0.675,
+      "grad_norm": 0.0858621671795845,
+      "learning_rate": 1.0773176740426246e-06,
+      "loss": 8.155872344970703,
+      "step": 135
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.07770797610282898,
+      "learning_rate": 9.339365425440129e-07,
+      "loss": 8.076512908935547,
+      "step": 140
+    },
+    {
+      "epoch": 0.725,
+      "grad_norm": 0.08947437256574631,
+      "learning_rate": 7.978377054339498e-07,
+      "loss": 8.029309844970703,
+      "step": 145
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.08842209726572037,
+      "learning_rate": 6.699508557723032e-07,
+      "loss": 8.074932098388672,
+      "step": 150
+    },
+    {
+      "epoch": 0.75,
+      "eval_accuracy": 0.11846153846153847,
+      "eval_loss": 8.003965377807617,
+      "eval_runtime": 10.4627,
+      "eval_samples_per_second": 9.558,
+      "eval_steps_per_second": 1.625,
+      "step": 150
+    },
+    {
+      "epoch": 0.775,
+      "grad_norm": 0.08069568127393723,
+      "learning_rate": 5.511495904178221e-07,
+      "loss": 8.015203857421875,
+      "step": 155
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.08167938143014908,
+      "learning_rate": 4.4224544247577535e-07,
+      "loss": 8.024001312255859,
+      "step": 160
+    },
+    {
+      "epoch": 0.825,
+      "grad_norm": 0.07335270941257477,
+      "learning_rate": 3.439823377039599e-07,
+      "loss": 8.014215087890625,
+      "step": 165
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.09198863804340363,
+      "learning_rate": 2.570315127454452e-07,
+      "loss": 7.948513031005859,
+      "step": 170
+    },
+    {
+      "epoch": 0.875,
+      "grad_norm": 0.09853670746088028,
+      "learning_rate": 1.8198692990167497e-07,
+      "loss": 7.839792633056641,
+      "step": 175
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.07276590168476105,
+      "learning_rate": 1.1936121976767767e-07,
+      "loss": 7.897310638427735,
+      "step": 180
+    },
+    {
+      "epoch": 0.925,
+      "grad_norm": 0.10586628317832947,
+      "learning_rate": 6.958217944530287e-08,
+      "loss": 8.082672882080079,
+      "step": 185
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.09799101948738098,
+      "learning_rate": 3.2989850255235265e-08,
+      "loss": 7.902798461914062,
+      "step": 190
+    },
+    {
+      "epoch": 0.975,
+      "grad_norm": 0.06515993922948837,
+      "learning_rate": 9.834194909977168e-09,
+      "loss": 7.907355499267578,
+      "step": 195
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.0806872770190239,
+      "learning_rate": 2.7339001506199164e-10,
+      "loss": 7.868655395507813,
+      "step": 200
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.1221123321123321,
+      "eval_loss": 7.8275146484375,
+      "eval_runtime": 10.3834,
+      "eval_samples_per_second": 9.631,
+      "eval_steps_per_second": 1.637,
+      "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": {}
     }