Training in progress, epoch 3, checkpoint

checkpoint-10797/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:291223154a0e933450fe5adee8c11b3b09cf58b2b31a26bc347a572e8088ea6e
+oid sha256:580c380cb9ec9c675aaa8803809cfcaeddce8f94ea9a191714589c7585bec575
 size 541459256

checkpoint-10797/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a9fe22ad21d9f06f3b1f506d0856fbd39f35a12e6b7f823ffd94919c25f4c22
+oid sha256:69a9ee08c961f5a37a618d854fb3c8125f894fdc73947a069b37987c2dac3d9e
 size 33662074

checkpoint-10797/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92b6685a1c89e2072300f60f4aa118ea2433253da143d3d6706ff6267388ba7c
+oid sha256:746dc59e1c9da0affbf7b0af2ef740c782ae15f45a8836da498bf954d3872755
 size 15024

checkpoint-10797/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e625bc2de4ed4b285eb9fa0484099893dcc2cd29a17caf483ffc653e7d03fa44
+oid sha256:3899cc1bdfdae0d9118974635ecaa68941878adc6e0e17414da91d88823c69dd
 size 15024

checkpoint-10797/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:298f1739ecced1879b1a28af35a194fe54c0e042f233e516504bfd09c94517fd
+oid sha256:014b2719788f343f505dd9c025b3337a2364d700658c3f9c9f61ce9a83c3abca
 size 15024

checkpoint-10797/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38d495a35f8c7e88d95c656561c8b6e3e2240aab5905ca7b83ba73ef894ae891
+oid sha256:d468f62f0b3a42a48ba4878316d3a6e280b13563d102550f62061ab49a567386
 size 15024

checkpoint-10797/trainer_state.json

@@ -10,261 +10,261 @@
   "log_history": [
     {
       "epoch": 0.13892747985551543,
-      "grad_norm": 0.5752785205841064,
-      "learning_rate": 0.00039538760766879693,
-      "loss": 0.2947,
+      "grad_norm": 0.6994414925575256,
+      "learning_rate": 0.00039537834583680656,
+      "loss": 0.2943,
       "step": 500
     },
     {
       "epoch": 0.2000555709919422,
-      "eval_loss": 0.19290830194950104,
-      "eval_runtime": 6.2591,
-      "eval_samples_per_second": 79.884,
-      "eval_steps_per_second": 10.065,
+      "eval_loss": 0.21401312947273254,
+      "eval_runtime": 16.5317,
+      "eval_samples_per_second": 30.245,
+      "eval_steps_per_second": 3.811,
       "step": 720
     },
     {
       "epoch": 0.27785495971103086,
-      "grad_norm": 0.4608103632926941,
+      "grad_norm": 0.5945971608161926,
       "learning_rate": 0.00039075669167361305,
-      "loss": 0.1972,
+      "loss": 0.1986,
       "step": 1000
     },
     {
       "epoch": 0.4001111419838844,
-      "eval_loss": 0.17835241556167603,
-      "eval_runtime": 6.2534,
-      "eval_samples_per_second": 79.957,
-      "eval_steps_per_second": 10.075,
+      "eval_loss": 0.17625106871128082,
+      "eval_runtime": 16.4823,
+      "eval_samples_per_second": 30.336,
+      "eval_steps_per_second": 3.822,
       "step": 1440
     },
     {
       "epoch": 0.41678243956654626,
-      "grad_norm": 0.44341567158699036,
+      "grad_norm": 0.3619824945926666,
       "learning_rate": 0.0003861257756784292,
-      "loss": 0.1817,
+      "loss": 0.1802,
       "step": 1500
     },
     {
       "epoch": 0.5557099194220617,
-      "grad_norm": 0.3840184509754181,
+      "grad_norm": 0.40362638235092163,
       "learning_rate": 0.00038149485968324534,
-      "loss": 0.1679,
+      "loss": 0.1686,
       "step": 2000
     },
     {
       "epoch": 0.6001667129758266,
-      "eval_loss": 0.16081829369068146,
-      "eval_runtime": 6.259,
-      "eval_samples_per_second": 79.885,
-      "eval_steps_per_second": 10.065,
+      "eval_loss": 0.16156445443630219,
+      "eval_runtime": 16.3535,
+      "eval_samples_per_second": 30.575,
+      "eval_steps_per_second": 3.852,
       "step": 2160
     },
     {
       "epoch": 0.6946373992775771,
-      "grad_norm": 0.4211641848087311,
+      "grad_norm": 0.4962793290615082,
       "learning_rate": 0.0003768639436880615,
-      "loss": 0.1584,
+      "loss": 0.1577,
       "step": 2500
     },
     {
       "epoch": 0.8002222839677688,
-      "eval_loss": 0.15788592398166656,
-      "eval_runtime": 6.2616,
-      "eval_samples_per_second": 79.852,
-      "eval_steps_per_second": 10.061,
+      "eval_loss": 0.15043224394321442,
+      "eval_runtime": 16.3325,
+      "eval_samples_per_second": 30.614,
+      "eval_steps_per_second": 3.857,
       "step": 2880
     },
     {
       "epoch": 0.8335648791330925,
-      "grad_norm": 0.3697059750556946,
-      "learning_rate": 0.0003722515513568584,
-      "loss": 0.1501,
+      "grad_norm": 0.41315382719039917,
+      "learning_rate": 0.0003722330276928777,
+      "loss": 0.1493,
       "step": 3000
     },
     {
       "epoch": 0.972492358988608,
-      "grad_norm": 0.420885294675827,
-      "learning_rate": 0.00036762063536167455,
-      "loss": 0.1478,
+      "grad_norm": 0.37953054904937744,
+      "learning_rate": 0.0003676113735296842,
+      "loss": 0.1477,
       "step": 3500
     },
     {
       "epoch": 1.000277854959711,
-      "eval_loss": 0.14726293087005615,
-      "eval_runtime": 6.3796,
-      "eval_samples_per_second": 78.375,
-      "eval_steps_per_second": 9.875,
+      "eval_loss": 0.14538082480430603,
+      "eval_runtime": 16.4466,
+      "eval_samples_per_second": 30.401,
+      "eval_steps_per_second": 3.831,
       "step": 3600
     },
     {
       "epoch": 1.1114198388441234,
-      "grad_norm": 0.3687162697315216,
-      "learning_rate": 0.0003629897193664907,
-      "loss": 0.1315,
+      "grad_norm": 0.4146048128604889,
+      "learning_rate": 0.00036298045753450036,
+      "loss": 0.1318,
       "step": 4000
     },
     {
       "epoch": 1.2003334259516532,
-      "eval_loss": 0.14390353858470917,
-      "eval_runtime": 6.2741,
-      "eval_samples_per_second": 79.693,
-      "eval_steps_per_second": 10.041,
+      "eval_loss": 0.13961325585842133,
+      "eval_runtime": 16.5835,
+      "eval_samples_per_second": 30.15,
+      "eval_steps_per_second": 3.799,
       "step": 4320
     },
     {
       "epoch": 1.2503473186996388,
-      "grad_norm": 0.4367423951625824,
-      "learning_rate": 0.0003583588033713069,
-      "loss": 0.1309,
+      "grad_norm": 0.6914293766021729,
+      "learning_rate": 0.0003583495415393165,
+      "loss": 0.1303,
       "step": 4500
     },
     {
       "epoch": 1.3892747985551543,
-      "grad_norm": 0.40452277660369873,
-      "learning_rate": 0.000353727887376123,
-      "loss": 0.128,
+      "grad_norm": 0.39365154504776,
+      "learning_rate": 0.00035371862554413265,
+      "loss": 0.1269,
       "step": 5000
     },
     {
       "epoch": 1.4003889969435954,
-      "eval_loss": 0.1357639729976654,
-      "eval_runtime": 6.2739,
-      "eval_samples_per_second": 79.695,
-      "eval_steps_per_second": 10.042,
+      "eval_loss": 0.14090509712696075,
+      "eval_runtime": 16.4413,
+      "eval_samples_per_second": 30.411,
+      "eval_steps_per_second": 3.832,
       "step": 5040
     },
     {
       "epoch": 1.5282022784106695,
-      "grad_norm": 0.6852627396583557,
+      "grad_norm": 0.5620034337043762,
       "learning_rate": 0.00034909697138093914,
-      "loss": 0.126,
+      "loss": 0.1263,
       "step": 5500
     },
     {
       "epoch": 1.6004445679355377,
-      "eval_loss": 0.13292476534843445,
-      "eval_runtime": 6.2659,
-      "eval_samples_per_second": 79.797,
-      "eval_steps_per_second": 10.054,
+      "eval_loss": 0.13119302690029144,
+      "eval_runtime": 16.5618,
+      "eval_samples_per_second": 30.19,
+      "eval_steps_per_second": 3.804,
       "step": 5760
     },
     {
       "epoch": 1.667129758266185,
-      "grad_norm": 0.30270153284072876,
+      "grad_norm": 1.5726152658462524,
       "learning_rate": 0.0003444660553857553,
-      "loss": 0.1255,
+      "loss": 0.1258,
       "step": 6000
     },
     {
       "epoch": 1.8005001389274797,
-      "eval_loss": 0.13217522203922272,
-      "eval_runtime": 6.2758,
-      "eval_samples_per_second": 79.671,
-      "eval_steps_per_second": 10.038,
+      "eval_loss": 0.12919241189956665,
+      "eval_runtime": 16.4031,
+      "eval_samples_per_second": 30.482,
+      "eval_steps_per_second": 3.841,
       "step": 6480
     },
     {
       "epoch": 1.8060572381217006,
-      "grad_norm": 0.394003301858902,
+      "grad_norm": 0.9997938871383667,
       "learning_rate": 0.0003398351393905715,
-      "loss": 0.1214,
+      "loss": 0.1212,
       "step": 6500
     },
     {
       "epoch": 1.9449847179772157,
-      "grad_norm": 0.48431047797203064,
+      "grad_norm": 0.4134954810142517,
       "learning_rate": 0.00033520422339538766,
-      "loss": 0.1199,
+      "loss": 0.1201,
       "step": 7000
     },
     {
       "epoch": 2.000555709919422,
-      "eval_loss": 0.1269044131040573,
-      "eval_runtime": 6.422,
-      "eval_samples_per_second": 77.857,
-      "eval_steps_per_second": 9.81,
+      "eval_loss": 0.12256824225187302,
+      "eval_runtime": 16.8158,
+      "eval_samples_per_second": 29.734,
+      "eval_steps_per_second": 3.746,
       "step": 7200
     },
     {
       "epoch": 2.0839121978327313,
-      "grad_norm": 0.35144302248954773,
+      "grad_norm": 0.40068477392196655,
       "learning_rate": 0.0003305733074002038,
       "loss": 0.108,
       "step": 7500
     },
     {
       "epoch": 2.2006112809113643,
-      "eval_loss": 0.12548324465751648,
-      "eval_runtime": 6.2942,
-      "eval_samples_per_second": 79.438,
-      "eval_steps_per_second": 10.009,
+      "eval_loss": 0.12798596918582916,
+      "eval_runtime": 16.5301,
+      "eval_samples_per_second": 30.248,
+      "eval_steps_per_second": 3.811,
       "step": 7920
     },
     {
       "epoch": 2.222839677688247,
-      "grad_norm": 0.5099118947982788,
-      "learning_rate": 0.00032595165323701027,
-      "loss": 0.1056,
+      "grad_norm": 0.39021220803260803,
+      "learning_rate": 0.0003259423914050199,
+      "loss": 0.1061,
       "step": 8000
     },
     {
       "epoch": 2.361767157543762,
-      "grad_norm": 0.5797615647315979,
-      "learning_rate": 0.00032132073724182645,
-      "loss": 0.1047,
+      "grad_norm": 0.4577147960662842,
+      "learning_rate": 0.0003213114754098361,
+      "loss": 0.1055,
       "step": 8500
     },
     {
       "epoch": 2.4006668519033063,
-      "eval_loss": 0.12244148552417755,
-      "eval_runtime": 6.2902,
-      "eval_samples_per_second": 79.489,
-      "eval_steps_per_second": 10.016,
+      "eval_loss": 0.1270737648010254,
+      "eval_runtime": 16.5227,
+      "eval_samples_per_second": 30.261,
+      "eval_steps_per_second": 3.813,
       "step": 8640
     },
     {
       "epoch": 2.5006946373992776,
-      "grad_norm": 0.40433964133262634,
-      "learning_rate": 0.0003166898212466426,
-      "loss": 0.1038,
+      "grad_norm": 0.5035166144371033,
+      "learning_rate": 0.00031668055941465225,
+      "loss": 0.1033,
       "step": 9000
     },
     {
       "epoch": 2.600722422895249,
-      "eval_loss": 0.12048304080963135,
-      "eval_runtime": 6.289,
-      "eval_samples_per_second": 79.503,
-      "eval_steps_per_second": 10.017,
+      "eval_loss": 0.12219922989606857,
+      "eval_runtime": 16.637,
+      "eval_samples_per_second": 30.054,
+      "eval_steps_per_second": 3.787,
       "step": 9360
     },
     {
       "epoch": 2.639622117254793,
-      "grad_norm": 0.7869251370429993,
+      "grad_norm": 0.6268121004104614,
       "learning_rate": 0.00031205890525145874,
-      "loss": 0.1023,
+      "loss": 0.1026,
       "step": 9500
     },
     {
       "epoch": 2.7785495971103087,
-      "grad_norm": 0.34468919038772583,
+      "grad_norm": 0.37843775749206543,
       "learning_rate": 0.0003074279892562749,
-      "loss": 0.1043,
+      "loss": 0.1042,
       "step": 10000
     },
     {
       "epoch": 2.800777993887191,
-      "eval_loss": 0.1157899871468544,
-      "eval_runtime": 6.2874,
-      "eval_samples_per_second": 79.524,
-      "eval_steps_per_second": 10.02,
+      "eval_loss": 0.11693067103624344,
+      "eval_runtime": 16.4326,
+      "eval_samples_per_second": 30.427,
+      "eval_steps_per_second": 3.834,
       "step": 10080
     },
     {
       "epoch": 2.917477076965824,
-      "grad_norm": 0.5141274929046631,
+      "grad_norm": 0.47878336906433105,
       "learning_rate": 0.00030279707326109104,
-      "loss": 0.1042,
+      "loss": 0.1032,
       "step": 10500
     }
   ],

checkpoint-10797/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfac93b9b3b40952529bd84fbff166d6257cf3d6fa4cc937269a037e37d853d5
+oid sha256:58052fbf3a2b07f2a6024b5cc28db88f1f0e48109a11483aa716d00657e9906e
 size 5496