Training in progress, step 600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eba20958cbb4baef53f6228a9a06deeae50c5a2f40d1fba26afd7caccd2ea83c
+oid sha256:348daef4d62db9a5fa3b649cca6826fc23ec3c49e1fb43eaa81d96b56a38718c
 size 527048968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fc4a217d70fa350a2b486bc3b1da2dd3b854e14e24169dafa1e11fdf2d7112d
+oid sha256:494a5ea21271cf0928971accb090d8e84141054b34ceaff64cbe4817f22fea4b
 size 1054136250

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed14e15604e1097b80da74a65c68f380dc6bb673bf5694a945c25e7931ad5a75
+oid sha256:65f6c1dd354391c569e4be3e0b1b637345be25b99bb32967d995788c70f82738
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb248e7cc2fe7b509c9e866be7b72af3b33225d8b86373c1a62393cc3a24f4da
+oid sha256:3ca6ba6bc5430af54b4982610d295ab940fcfca9eb66d0098ad0a404420eb1d4
 size 1256

last-checkpoint/trainer_state.json

@@ -1,351 +1,464 @@
 {
-  "best_metric": 0.7266653776168823,
-  "best_model_checkpoint": "./output/checkpoint-450",
-  "epoch": 10.0,
+  "best_metric": 0.7217289209365845,
+  "best_model_checkpoint": "./output/checkpoint-600",
+  "epoch": 13.333333333333334,
   "eval_steps": 150,
-  "global_step": 450,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.2222222222222222,
-      "grad_norm": 1.9097713232040405,
+      "grad_norm": 1.9086298942565918,
       "learning_rate": 2.9999999999999984e-06,
-      "loss": 0.6618,
+      "loss": 0.6619,
       "step": 10
     },
     {
       "epoch": 0.4444444444444444,
-      "grad_norm": 1.888712763786316,
+      "grad_norm": 1.888395071029663,
       "learning_rate": 5.999999999999997e-06,
-      "loss": 0.7252,
+      "loss": 0.7259,
       "step": 20
     },
     {
       "epoch": 0.6666666666666666,
-      "grad_norm": 1.6720666885375977,
+      "grad_norm": 1.6719470024108887,
       "learning_rate": 8.999999999999993e-06,
-      "loss": 0.7332,
+      "loss": 0.7335,
       "step": 30
     },
     {
       "epoch": 0.8888888888888888,
-      "grad_norm": 1.5767813920974731,
+      "grad_norm": 1.5774726867675781,
       "learning_rate": 1.1999999999999994e-05,
-      "loss": 0.7368,
+      "loss": 0.7373,
       "step": 40
     },
     {
       "epoch": 1.1111111111111112,
-      "grad_norm": 1.2497552633285522,
+      "grad_norm": 1.249552607536316,
       "learning_rate": 1.499999999999999e-05,
-      "loss": 0.8943,
+      "loss": 0.8944,
       "step": 50
     },
     {
       "epoch": 1.3333333333333333,
-      "grad_norm": 1.1341147422790527,
+      "grad_norm": 1.1349461078643799,
       "learning_rate": 1.7999999999999987e-05,
-      "loss": 0.7142,
+      "loss": 0.7144,
       "step": 60
     },
     {
       "epoch": 1.5555555555555556,
-      "grad_norm": 1.5113084316253662,
+      "grad_norm": 1.5111842155456543,
       "learning_rate": 2.0999999999999985e-05,
-      "loss": 0.7582,
+      "loss": 0.7577,
       "step": 70
     },
     {
       "epoch": 1.7777777777777777,
-      "grad_norm": 1.8728289604187012,
+      "grad_norm": 1.873070478439331,
       "learning_rate": 2.3999999999999987e-05,
-      "loss": 0.7075,
+      "loss": 0.7073,
       "step": 80
     },
     {
       "epoch": 2.0,
-      "grad_norm": 2.064190149307251,
+      "grad_norm": 2.0650975704193115,
       "learning_rate": 2.6999999999999982e-05,
-      "loss": 0.7701,
+      "loss": 0.7702,
       "step": 90
     },
     {
       "epoch": 2.2222222222222223,
-      "grad_norm": 1.5590786933898926,
+      "grad_norm": 1.5584607124328613,
       "learning_rate": 2.999999999999998e-05,
-      "loss": 0.7272,
+      "loss": 0.7269,
       "step": 100
     },
     {
       "epoch": 2.4444444444444446,
-      "grad_norm": 1.7018474340438843,
+      "grad_norm": 1.7033145427703857,
       "learning_rate": 2.999999702723961e-05,
-      "loss": 0.7472,
+      "loss": 0.7475,
       "step": 110
     },
     {
       "epoch": 2.6666666666666665,
-      "grad_norm": 2.7952871322631836,
+      "grad_norm": 2.7943344116210938,
       "learning_rate": 2.9999988108959667e-05,
       "loss": 0.57,
       "step": 120
     },
     {
       "epoch": 2.888888888888889,
-      "grad_norm": 2.1137964725494385,
+      "grad_norm": 2.112865686416626,
       "learning_rate": 2.9999973245163695e-05,
-      "loss": 0.7048,
+      "loss": 0.704,
       "step": 130
     },
     {
       "epoch": 3.111111111111111,
-      "grad_norm": 2.2451610565185547,
+      "grad_norm": 2.2598509788513184,
       "learning_rate": 2.999995243585758e-05,
-      "loss": 0.7171,
+      "loss": 0.717,
       "step": 140
     },
     {
       "epoch": 3.3333333333333335,
-      "grad_norm": 1.9218461513519287,
+      "grad_norm": 1.9296040534973145,
       "learning_rate": 2.9999925681049573e-05,
-      "loss": 0.6642,
+      "loss": 0.6639,
       "step": 150
     },
     {
       "epoch": 3.3333333333333335,
-      "eval_loss": 0.7679360508918762,
-      "eval_runtime": 0.4614,
-      "eval_samples_per_second": 21.674,
-      "eval_steps_per_second": 21.674,
+      "eval_loss": 0.7678037881851196,
+      "eval_runtime": 0.4654,
+      "eval_samples_per_second": 21.488,
+      "eval_steps_per_second": 21.488,
       "step": 150
     },
     {
       "epoch": 3.5555555555555554,
-      "grad_norm": 2.5762360095977783,
+      "grad_norm": 2.576017141342163,
       "learning_rate": 2.9999892980750276e-05,
-      "loss": 0.695,
+      "loss": 0.6945,
       "step": 160
     },
     {
       "epoch": 3.7777777777777777,
-      "grad_norm": 2.3902077674865723,
+      "grad_norm": 2.4086973667144775,
       "learning_rate": 2.9999854334972655e-05,
-      "loss": 0.6922,
+      "loss": 0.6925,
       "step": 170
     },
     {
       "epoch": 4.0,
-      "grad_norm": 2.540234327316284,
+      "grad_norm": 2.5403313636779785,
       "learning_rate": 2.999980974373202e-05,
-      "loss": 0.6677,
+      "loss": 0.6681,
       "step": 180
     },
     {
       "epoch": 4.222222222222222,
-      "grad_norm": 1.588454008102417,
+      "grad_norm": 1.6049163341522217,
       "learning_rate": 2.9999759207046055e-05,
-      "loss": 0.5905,
+      "loss": 0.5901,
       "step": 190
     },
     {
       "epoch": 4.444444444444445,
-      "grad_norm": 1.6733808517456055,
+      "grad_norm": 1.6813507080078125,
       "learning_rate": 2.9999702724934783e-05,
-      "loss": 0.7107,
+      "loss": 0.7106,
       "step": 200
     },
     {
       "epoch": 4.666666666666667,
-      "grad_norm": 3.4343762397766113,
+      "grad_norm": 3.4500820636749268,
       "learning_rate": 2.99996402974206e-05,
       "loss": 0.6277,
       "step": 210
     },
     {
       "epoch": 4.888888888888889,
-      "grad_norm": 2.086362838745117,
+      "grad_norm": 2.07940411567688,
       "learning_rate": 2.9999571924528243e-05,
-      "loss": 0.6739,
+      "loss": 0.6731,
       "step": 220
     },
     {
       "epoch": 5.111111111111111,
-      "grad_norm": 2.628204822540283,
+      "grad_norm": 2.62994647026062,
       "learning_rate": 2.9999497606284816e-05,
-      "loss": 0.6024,
+      "loss": 0.6025,
       "step": 230
     },
     {
       "epoch": 5.333333333333333,
-      "grad_norm": 1.4835840463638306,
+      "grad_norm": 1.4846452474594116,
       "learning_rate": 2.9999417342719775e-05,
-      "loss": 0.6943,
+      "loss": 0.6941,
       "step": 240
     },
     {
       "epoch": 5.555555555555555,
-      "grad_norm": 2.2181918621063232,
+      "grad_norm": 2.218034267425537,
       "learning_rate": 2.9999331133864935e-05,
-      "loss": 0.6474,
+      "loss": 0.6477,
       "step": 250
     },
     {
       "epoch": 5.777777777777778,
-      "grad_norm": 1.7070634365081787,
+      "grad_norm": 1.7151379585266113,
       "learning_rate": 2.9999238979754465e-05,
-      "loss": 0.6096,
+      "loss": 0.6094,
       "step": 260
     },
     {
       "epoch": 6.0,
-      "grad_norm": 1.9004781246185303,
+      "grad_norm": 1.9011706113815308,
       "learning_rate": 2.99991408804249e-05,
-      "loss": 0.5758,
+      "loss": 0.5759,
       "step": 270
     },
     {
       "epoch": 6.222222222222222,
-      "grad_norm": 2.1397156715393066,
+      "grad_norm": 2.1471989154815674,
       "learning_rate": 2.999903683591511e-05,
-      "loss": 0.5736,
+      "loss": 0.574,
       "step": 280
     },
     {
       "epoch": 6.444444444444445,
-      "grad_norm": 1.384970784187317,
+      "grad_norm": 1.3847769498825073,
       "learning_rate": 2.9998926846266345e-05,
-      "loss": 0.6135,
+      "loss": 0.613,
       "step": 290
     },
     {
       "epoch": 6.666666666666667,
-      "grad_norm": 2.2915239334106445,
+      "grad_norm": 2.2905008792877197,
       "learning_rate": 2.9998810911522193e-05,
-      "loss": 0.6228,
+      "loss": 0.6224,
       "step": 300
     },
     {
       "epoch": 6.666666666666667,
-      "eval_loss": 0.7389177083969116,
-      "eval_runtime": 0.4555,
-      "eval_samples_per_second": 21.953,
-      "eval_steps_per_second": 21.953,
+      "eval_loss": 0.7388900518417358,
+      "eval_runtime": 0.4459,
+      "eval_samples_per_second": 22.426,
+      "eval_steps_per_second": 22.426,
       "step": 300
     },
     {
       "epoch": 6.888888888888889,
-      "grad_norm": 2.712688446044922,
+      "grad_norm": 2.6983234882354736,
       "learning_rate": 2.9998689031728615e-05,
-      "loss": 0.6483,
+      "loss": 0.6484,
       "step": 310
     },
     {
       "epoch": 7.111111111111111,
-      "grad_norm": 1.764075517654419,
+      "grad_norm": 1.7625339031219482,
       "learning_rate": 2.9998561206933918e-05,
-      "loss": 0.5864,
+      "loss": 0.5866,
       "step": 320
     },
     {
       "epoch": 7.333333333333333,
-      "grad_norm": 1.7712483406066895,
+      "grad_norm": 1.7633429765701294,
       "learning_rate": 2.9998427437188766e-05,
-      "loss": 0.5796,
+      "loss": 0.5797,
       "step": 330
     },
     {
       "epoch": 7.555555555555555,
-      "grad_norm": 2.3483595848083496,
+      "grad_norm": 2.347116470336914,
       "learning_rate": 2.999828772254618e-05,
-      "loss": 0.6038,
+      "loss": 0.603,
       "step": 340
     },
     {
       "epoch": 7.777777777777778,
-      "grad_norm": 2.456615686416626,
+      "grad_norm": 2.4734201431274414,
       "learning_rate": 2.9998142063061544e-05,
-      "loss": 0.6626,
+      "loss": 0.6625,
       "step": 350
     },
     {
       "epoch": 8.0,
-      "grad_norm": 1.322672963142395,
+      "grad_norm": 1.330693006515503,
       "learning_rate": 2.9997990458792583e-05,
-      "loss": 0.6039,
+      "loss": 0.6044,
       "step": 360
     },
     {
       "epoch": 8.222222222222221,
-      "grad_norm": 1.9034680128097534,
+      "grad_norm": 1.9030860662460327,
       "learning_rate": 2.9997832909799397e-05,
-      "loss": 0.5495,
+      "loss": 0.549,
       "step": 370
     },
     {
       "epoch": 8.444444444444445,
-      "grad_norm": 1.9364817142486572,
+      "grad_norm": 1.935556173324585,
       "learning_rate": 2.9997669416144432e-05,
-      "loss": 0.6405,
+      "loss": 0.641,
       "step": 380
     },
     {
       "epoch": 8.666666666666666,
-      "grad_norm": 1.0501103401184082,
+      "grad_norm": 1.049513816833496,
       "learning_rate": 2.999749997789249e-05,
-      "loss": 0.5397,
+      "loss": 0.5395,
       "step": 390
     },
     {
       "epoch": 8.88888888888889,
-      "grad_norm": 1.5247255563735962,
+      "grad_norm": 1.5243322849273682,
       "learning_rate": 2.9997324595110723e-05,
       "loss": 0.6544,
       "step": 400
     },
     {
       "epoch": 9.11111111111111,
-      "grad_norm": 1.3862415552139282,
+      "grad_norm": 1.3851348161697388,
       "learning_rate": 2.9997143267868663e-05,
-      "loss": 0.595,
+      "loss": 0.5948,
       "step": 410
     },
     {
       "epoch": 9.333333333333334,
-      "grad_norm": 2.4849624633789062,
+      "grad_norm": 2.487696409225464,
       "learning_rate": 2.999695599623817e-05,
-      "loss": 0.6229,
+      "loss": 0.6226,
       "step": 420
     },
     {
       "epoch": 9.555555555555555,
-      "grad_norm": 2.6004281044006348,
+      "grad_norm": 2.581589698791504,
       "learning_rate": 2.9996762780293483e-05,
-      "loss": 0.5753,
+      "loss": 0.5751,
       "step": 430
     },
     {
       "epoch": 9.777777777777779,
-      "grad_norm": 1.5287330150604248,
+      "grad_norm": 1.5271048545837402,
       "learning_rate": 2.9996563620111176e-05,
-      "loss": 0.5294,
+      "loss": 0.5295,
       "step": 440
     },
     {
       "epoch": 10.0,
-      "grad_norm": 1.3864028453826904,
+      "grad_norm": 1.3882054090499878,
       "learning_rate": 2.9996358515770198e-05,
-      "loss": 0.5417,
+      "loss": 0.5419,
       "step": 450
     },
     {
       "epoch": 10.0,
-      "eval_loss": 0.7266653776168823,
-      "eval_runtime": 0.4076,
-      "eval_samples_per_second": 24.534,
-      "eval_steps_per_second": 24.534,
+      "eval_loss": 0.7256744503974915,
+      "eval_runtime": 0.4708,
+      "eval_samples_per_second": 21.239,
+      "eval_steps_per_second": 21.239,
       "step": 450
+    },
+    {
+      "epoch": 10.222222222222221,
+      "grad_norm": 2.2227277755737305,
+      "learning_rate": 2.9996147467351836e-05,
+      "loss": 0.5062,
+      "step": 460
+    },
+    {
+      "epoch": 10.444444444444445,
+      "grad_norm": 1.412768006324768,
+      "learning_rate": 2.9995930474939753e-05,
+      "loss": 0.4908,
+      "step": 470
+    },
+    {
+      "epoch": 10.666666666666666,
+      "grad_norm": 1.9368879795074463,
+      "learning_rate": 2.9995707538619954e-05,
+      "loss": 0.6362,
+      "step": 480
+    },
+    {
+      "epoch": 10.88888888888889,
+      "grad_norm": 2.137639045715332,
+      "learning_rate": 2.9995478658480802e-05,
+      "loss": 0.5532,
+      "step": 490
+    },
+    {
+      "epoch": 11.11111111111111,
+      "grad_norm": 1.867410659790039,
+      "learning_rate": 2.9995243834613023e-05,
+      "loss": 0.5231,
+      "step": 500
+    },
+    {
+      "epoch": 11.333333333333334,
+      "grad_norm": 1.6794224977493286,
+      "learning_rate": 2.9995003067109687e-05,
+      "loss": 0.5388,
+      "step": 510
+    },
+    {
+      "epoch": 11.555555555555555,
+      "grad_norm": 2.639946699142456,
+      "learning_rate": 2.9994756356066226e-05,
+      "loss": 0.5847,
+      "step": 520
+    },
+    {
+      "epoch": 11.777777777777779,
+      "grad_norm": 2.2483253479003906,
+      "learning_rate": 2.999450370158044e-05,
+      "loss": 0.5348,
+      "step": 530
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 1.535469651222229,
+      "learning_rate": 2.9994245103752457e-05,
+      "loss": 0.5238,
+      "step": 540
+    },
+    {
+      "epoch": 12.222222222222221,
+      "grad_norm": 1.2466766834259033,
+      "learning_rate": 2.999398056268479e-05,
+      "loss": 0.536,
+      "step": 550
+    },
+    {
+      "epoch": 12.444444444444445,
+      "grad_norm": 1.4720205068588257,
+      "learning_rate": 2.9993710078482286e-05,
+      "loss": 0.4151,
+      "step": 560
+    },
+    {
+      "epoch": 12.666666666666666,
+      "grad_norm": 3.3889882564544678,
+      "learning_rate": 2.9993433651252164e-05,
+      "loss": 0.6201,
+      "step": 570
+    },
+    {
+      "epoch": 12.88888888888889,
+      "grad_norm": 1.472764253616333,
+      "learning_rate": 2.9993151281103986e-05,
+      "loss": 0.5345,
+      "step": 580
+    },
+    {
+      "epoch": 13.11111111111111,
+      "grad_norm": 2.440230369567871,
+      "learning_rate": 2.9992862968149675e-05,
+      "loss": 0.4178,
+      "step": 590
+    },
+    {
+      "epoch": 13.333333333333334,
+      "grad_norm": 2.4395759105682373,
+      "learning_rate": 2.9992568712503513e-05,
+      "loss": 0.5315,
+      "step": 600
+    },
+    {
+      "epoch": 13.333333333333334,
+      "eval_loss": 0.7217289209365845,
+      "eval_runtime": 0.4076,
+      "eval_samples_per_second": 24.535,
+      "eval_steps_per_second": 24.535,
+      "step": 600
     }
   ],
   "logging_steps": 10,
@@ -365,7 +478,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4801636770840576.0,
+  "total_flos": 6372295013597184.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23ba7417f756bb3cb13785760bc75de6ff69ccfe22374af3547ce2aa84536e79
+oid sha256:44d2192bde2a23766c50facad1c20f2470e5e208bb2f21a9c48d77c7aea22798
 size 5496