Training in progress, step 100, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af6da459219a0dfd520f8f9bef95d70b69541238260a186de064e8b3b9622d4b
+oid sha256:d7390f9f81e59c76a9d6ab0d8c707f4c87f467164b72cc20add67201bd21852d
 size 847599616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95176d612444486929b2741997bdaf23b4fa67dd8b2c66bf57fa5ea76b78cfed
+oid sha256:07c259decfaab80c17538e818b27844a7997ae01f1bc68bd0351e7c7013d6966
 size 350603

last-checkpoint/rng_state.pth

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

last-checkpoint/scheduler.pt

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

last-checkpoint/trainer_state.json

@@ -2,328 +2,170 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.0,
+  "epoch": 0.5,
   "eval_steps": 50,
-  "global_step": 200,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.025,
-      "grad_norm": 0.17093215882778168,
+      "grad_norm": 0.28224506974220276,
       "learning_rate": 1.6e-06,
-      "loss": 10.88990478515625,
+      "loss": 10.72566909790039,
       "step": 5
     },
     {
       "epoch": 0.05,
-      "grad_norm": 0.2938487231731415,
+      "grad_norm": 0.3270684778690338,
       "learning_rate": 3.6e-06,
-      "loss": 10.514610290527344,
+      "loss": 9.934751892089844,
       "step": 10
     },
     {
       "epoch": 0.075,
-      "grad_norm": 0.37134891748428345,
+      "grad_norm": 0.16773350536823273,
       "learning_rate": 3.995627254437549e-06,
-      "loss": 10.039398193359375,
+      "loss": 9.331498718261718,
       "step": 15
     },
     {
       "epoch": 0.1,
-      "grad_norm": 0.2268853634595871,
+      "grad_norm": 0.14517103135585785,
       "learning_rate": 3.9778957412029366e-06,
-      "loss": 9.626433563232421,
+      "loss": 9.084286499023438,
       "step": 20
     },
     {
       "epoch": 0.125,
-      "grad_norm": 0.2303772270679474,
+      "grad_norm": 0.15857668220996857,
       "learning_rate": 3.9466531944960116e-06,
-      "loss": 9.306468963623047,
+      "loss": 8.825327301025391,
       "step": 25
     },
     {
       "epoch": 0.15,
-      "grad_norm": 0.20847690105438232,
+      "grad_norm": 0.12968920171260834,
       "learning_rate": 3.902113032590307e-06,
-      "loss": 9.164946746826171,
+      "loss": 8.735884094238282,
       "step": 30
     },
     {
       "epoch": 0.175,
-      "grad_norm": 0.18881037831306458,
+      "grad_norm": 0.11413325369358063,
       "learning_rate": 3.844579509954769e-06,
-      "loss": 9.01562728881836,
+      "loss": 8.606085968017577,
       "step": 35
     },
     {
       "epoch": 0.2,
-      "grad_norm": 0.14287346601486206,
+      "grad_norm": 0.17233271896839142,
       "learning_rate": 3.7744456388872234e-06,
-      "loss": 8.989354705810547,
+      "loss": 8.629763793945312,
       "step": 40
     },
     {
       "epoch": 0.225,
-      "grad_norm": 0.16693444550037384,
+      "grad_norm": 0.11048762500286102,
       "learning_rate": 3.6921905048418706e-06,
-      "loss": 8.803133392333985,
+      "loss": 8.442276000976562,
       "step": 45
     },
     {
       "epoch": 0.25,
-      "grad_norm": 0.12351641803979874,
+      "grad_norm": 0.08961036801338196,
       "learning_rate": 3.598375993789849e-06,
-      "loss": 8.753093719482422,
+      "loss": 8.383564758300782,
       "step": 50
     },
     {
       "epoch": 0.25,
-      "eval_accuracy": 0.10913064713064713,
-      "eval_loss": 8.707348823547363,
-      "eval_runtime": 10.3624,
-      "eval_samples_per_second": 9.65,
-      "eval_steps_per_second": 1.641,
+      "eval_accuracy": 0.11198778998778999,
+      "eval_loss": 8.327370643615723,
+      "eval_runtime": 10.4343,
+      "eval_samples_per_second": 9.584,
+      "eval_steps_per_second": 1.629,
       "step": 50
     },
     {
       "epoch": 0.275,
-      "grad_norm": 0.11024487018585205,
+      "grad_norm": 0.08887746930122375,
       "learning_rate": 3.4936429539683075e-06,
-      "loss": 8.706148529052735,
+      "loss": 8.346420288085938,
       "step": 55
     },
     {
       "epoch": 0.3,
-      "grad_norm": 0.11397001892328262,
+      "grad_norm": 0.0796026661992073,
       "learning_rate": 3.3787068182371314e-06,
-      "loss": 8.635591125488281,
+      "loss": 8.269767761230469,
       "step": 60
     },
     {
       "epoch": 0.325,
-      "grad_norm": 0.11307007819414139,
+      "grad_norm": 0.09607570618391037,
       "learning_rate": 3.254352716947074e-06,
-      "loss": 8.56150131225586,
+      "loss": 8.19412841796875,
       "step": 65
     },
     {
       "epoch": 0.35,
-      "grad_norm": 0.11745881289243698,
+      "grad_norm": 0.1087556928396225,
       "learning_rate": 3.1214301147033453e-06,
-      "loss": 8.52124252319336,
+      "loss": 8.142083740234375,
       "step": 70
     },
     {
       "epoch": 0.375,
-      "grad_norm": 0.10288426280021667,
+      "grad_norm": 0.08590473234653473,
       "learning_rate": 2.9808470076610163e-06,
-      "loss": 8.491536712646484,
+      "loss": 8.119364929199218,
       "step": 75
     },
     {
       "epoch": 0.4,
-      "grad_norm": 0.11181551218032837,
+      "grad_norm": 0.10873208194971085,
       "learning_rate": 2.833563720990581e-06,
-      "loss": 8.444434356689452,
+      "loss": 8.084170532226562,
       "step": 80
     },
     {
       "epoch": 0.425,
-      "grad_norm": 0.10100872069597244,
+      "grad_norm": 0.08005784451961517,
       "learning_rate": 2.680586348883286e-06,
-      "loss": 8.523983764648438,
+      "loss": 8.164724731445313,
       "step": 85
     },
     {
       "epoch": 0.45,
-      "grad_norm": 0.09801367670297623,
+      "grad_norm": 0.07923667132854462,
       "learning_rate": 2.5229598819076393e-06,
-      "loss": 8.447149658203125,
+      "loss": 8.08359603881836,
       "step": 90
     },
     {
       "epoch": 0.475,
-      "grad_norm": 0.09665904939174652,
+      "grad_norm": 0.08169477432966232,
       "learning_rate": 2.36176106866422e-06,
-      "loss": 8.304853820800782,
+      "loss": 7.9432830810546875,
       "step": 95
     },
     {
       "epoch": 0.5,
-      "grad_norm": 0.08705192059278488,
+      "grad_norm": 0.0804147943854332,
       "learning_rate": 2.198091060500926e-06,
-      "loss": 8.243639373779297,
+      "loss": 7.901922607421875,
       "step": 100
     },
     {
       "epoch": 0.5,
-      "eval_accuracy": 0.11717704517704518,
-      "eval_loss": 8.261603355407715,
-      "eval_runtime": 10.4554,
-      "eval_samples_per_second": 9.564,
-      "eval_steps_per_second": 1.626,
+      "eval_accuracy": 0.1186935286935287,
+      "eval_loss": 7.899251937866211,
+      "eval_runtime": 10.4815,
+      "eval_samples_per_second": 9.541,
+      "eval_steps_per_second": 1.622,
       "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,
@@ -338,7 +180,7 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }