Training in progress, step 2000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d14a55a7a001ec56d6e7cc97ff832364798045035293d4c041146fbaa0a507d
+oid sha256:1b12795eb294f14f19216ce7303683953962bfbde3b70ee33eccae088736dd2f
 size 496262784

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8cf5ea768afac9afe79d638dfb780cc0ea075e584e54b84d31b5edbbc4c2593
+oid sha256:a40275d08a6ee771906da7744e5ecf4905eb675617a98a372c4b33530e6da83d
 size 992621963

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7594d618d6ba19521c7abdc5d9c3d75c88e696a2ccaf3aad9e2ee70281ff7494
+oid sha256:a39530bbcd5c6be69add23d3653760d20540490f7a104a2dfa0a07555ccf4486
 size 1465

last-checkpoint/trainer_state.json

@@ -11,160 +11,160 @@
   "log_history": [
     {
       "epoch": 0.002,
-      "grad_norm": 0.728621244430542,
-      "learning_rate": 0.00066,
-      "loss": 7.944070434570312,
+      "grad_norm": 0.7236698865890503,
+      "learning_rate": 0.000396,
+      "loss": 8.129180297851562,
       "step": 100
     },
     {
       "epoch": 0.004,
-      "grad_norm": 0.6194736361503601,
-      "learning_rate": 0.0009999976160274871,
-      "loss": 6.688648071289062,
+      "grad_norm": 0.6699316501617432,
+      "learning_rate": 0.0005999985696164921,
+      "loss": 6.683881225585938,
       "step": 200
     },
     {
       "epoch": 0.006,
-      "grad_norm": 0.42749303579330444,
-      "learning_rate": 0.000999977956590203,
-      "loss": 6.362667846679687,
+      "grad_norm": 0.4809923470020294,
+      "learning_rate": 0.0005999867739541219,
+      "loss": 6.335140991210937,
       "step": 300
     },
     {
       "epoch": 0.008,
-      "grad_norm": 0.6455233693122864,
-      "learning_rate": 0.0009999384399149713,
-      "loss": 6.1362109375,
+      "grad_norm": 0.6197829246520996,
+      "learning_rate": 0.0005999630639489827,
+      "loss": 6.119940185546875,
       "step": 400
     },
     {
       "epoch": 0.01,
-      "grad_norm": 0.38843703269958496,
-      "learning_rate": 0.0009998790675712448,
-      "loss": 5.9013720703125,
+      "grad_norm": 0.5310641527175903,
+      "learning_rate": 0.0005999274405427468,
+      "loss": 5.908866577148437,
       "step": 500
     },
     {
       "epoch": 0.012,
-      "grad_norm": 0.37035471200942993,
-      "learning_rate": 0.000999799841917069,
-      "loss": 5.723118896484375,
+      "grad_norm": 0.4188089668750763,
+      "learning_rate": 0.0005998799051502414,
+      "loss": 5.712981567382813,
       "step": 600
     },
     {
       "epoch": 0.014,
-      "grad_norm": 0.3410094380378723,
-      "learning_rate": 0.0009997007660989881,
-      "loss": 5.57857666015625,
+      "grad_norm": 0.43575364351272583,
+      "learning_rate": 0.0005998204596593927,
+      "loss": 5.54151123046875,
       "step": 700
     },
     {
       "epoch": 0.016,
-      "grad_norm": 0.33731603622436523,
-      "learning_rate": 0.0009995818440519195,
-      "loss": 5.440355224609375,
+      "grad_norm": 0.3631345331668854,
+      "learning_rate": 0.0005997491064311517,
+      "loss": 5.377118530273438,
       "step": 800
     },
     {
       "epoch": 0.018,
-      "grad_norm": 0.39496415853500366,
-      "learning_rate": 0.0009994430804989986,
-      "loss": 5.352986450195313,
+      "grad_norm": 0.4753637909889221,
+      "learning_rate": 0.000599665848299399,
+      "loss": 5.2575732421875,
       "step": 900
     },
     {
       "epoch": 0.02,
-      "grad_norm": 0.3883383870124817,
-      "learning_rate": 0.0009992844809513896,
-      "loss": 5.53045166015625,
+      "grad_norm": 0.3885057270526886,
+      "learning_rate": 0.0005995706885708337,
+      "loss": 5.168424072265625,
       "step": 1000
     },
     {
       "epoch": 0.02,
-      "eval_accuracy": 0.19006987944761863,
-      "eval_loss": 5.351119041442871,
-      "eval_runtime": 5.7942,
-      "eval_samples_per_second": 334.99,
-      "eval_steps_per_second": 21.056,
+      "eval_accuracy": 0.21422370900467913,
+      "eval_loss": 5.0658464431762695,
+      "eval_runtime": 5.7327,
+      "eval_samples_per_second": 338.583,
+      "eval_steps_per_second": 21.281,
       "step": 1000
     },
     {
       "epoch": 0.022,
-      "grad_norm": 0.5580651760101318,
-      "learning_rate": 0.0009991060517080686,
-      "loss": 5.3906793212890625,
+      "grad_norm": 0.35898318886756897,
+      "learning_rate": 0.0005994636310248412,
+      "loss": 5.058907165527343,
       "step": 1100
     },
     {
       "epoch": 0.024,
-      "grad_norm": 4.792799472808838,
-      "learning_rate": 0.0009989077998555718,
-      "loss": 5.624612426757812,
+      "grad_norm": 0.36867955327033997,
+      "learning_rate": 0.000599344679913343,
+      "loss": 4.899845275878906,
       "step": 1200
     },
     {
       "epoch": 0.026,
-      "grad_norm": 5.352905750274658,
-      "learning_rate": 0.0009986897332677144,
-      "loss": 6.0997509765625,
+      "grad_norm": 0.3753994405269623,
+      "learning_rate": 0.0005992138399606286,
+      "loss": 4.828855285644531,
       "step": 1300
     },
     {
       "epoch": 0.028,
-      "grad_norm": 5.617880344390869,
-      "learning_rate": 0.0009984518606052791,
-      "loss": 7.137509765625,
+      "grad_norm": 0.3426174521446228,
+      "learning_rate": 0.0005990711163631674,
+      "loss": 4.73110595703125,
       "step": 1400
     },
     {
       "epoch": 0.03,
-      "grad_norm": 6.961197853088379,
-      "learning_rate": 0.0009981941913156701,
-      "loss": 6.8974456787109375,
+      "grad_norm": 0.34207016229629517,
+      "learning_rate": 0.000598916514789402,
+      "loss": 4.640643005371094,
       "step": 1500
     },
     {
       "epoch": 0.032,
-      "grad_norm": 7.469847679138184,
-      "learning_rate": 0.0009979167356325394,
-      "loss": 6.911260375976562,
+      "grad_norm": 0.40568745136260986,
+      "learning_rate": 0.0005987500413795236,
+      "loss": 4.591531677246094,
       "step": 1600
     },
     {
       "epoch": 0.034,
-      "grad_norm": 21.165908813476562,
-      "learning_rate": 0.0009976195045753797,
-      "loss": 6.70553466796875,
+      "grad_norm": 0.31946808099746704,
+      "learning_rate": 0.0005985717027452278,
+      "loss": 4.533291015625,
       "step": 1700
     },
     {
       "epoch": 0.036,
-      "grad_norm": 10.395805358886719,
-      "learning_rate": 0.0009973025099490876,
-      "loss": 6.70605712890625,
+      "grad_norm": 0.30501991510391235,
+      "learning_rate": 0.0005983815059694525,
+      "loss": 4.492686157226562,
       "step": 1800
     },
     {
       "epoch": 0.038,
-      "grad_norm": 2.6919143199920654,
-      "learning_rate": 0.0009969657643434933,
-      "loss": 6.605548706054687,
+      "grad_norm": 0.33989349007606506,
+      "learning_rate": 0.0005981794586060958,
+      "loss": 4.41447509765625,
       "step": 1900
     },
     {
       "epoch": 0.04,
-      "grad_norm": 470.6007080078125,
-      "learning_rate": 0.0009966092811328612,
-      "loss": 6.552777099609375,
+      "grad_norm": 0.3303995430469513,
+      "learning_rate": 0.0005979655686797167,
+      "loss": 4.396521911621094,
       "step": 2000
     },
     {
       "epoch": 0.04,
-      "eval_accuracy": 0.10447133692459855,
-      "eval_loss": 6.653895378112793,
-      "eval_runtime": 5.1208,
-      "eval_samples_per_second": 379.042,
-      "eval_steps_per_second": 23.824,
+      "eval_accuracy": 0.2874403514237522,
+      "eval_loss": 4.30245304107666,
+      "eval_runtime": 5.7068,
+      "eval_samples_per_second": 340.121,
+      "eval_steps_per_second": 21.378,
       "step": 2000
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc2fadc166c1876d75b4f91077944f22473b7782e4d604a36addc50eb7aa83ec
+oid sha256:347aa8bdb0f6aa6627388d3856e585f061f69c3186a785e62f389812dc252035
 size 5201