Training in progress, step 11975

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4c14739f1958d1e21b39cf77c4f8218e9f58f22d72ce8bafb148d31def1ab7f
+oid sha256:dc6b220a7ddc1693f8f9890cc5852a7b7e0f32a9fe123095302817600f977b31
 size 990185320

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f5241aee4b63575f094cd32fe8908608c74fb9f76fbbb67b652e0e12227f394
+oid sha256:5b3dcd6af690fe95d99438cd0881674cf89b2c2354b97a0b8dbee8da92dc4dfe
 size 1980545291

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac18d37e4c9a86e88d0fbe8b5ac19556189198bb3065472f1b49034b1b119395
+oid sha256:640f46eb39b244e7bfc751c4f25ad8e0191fac059c44f640e0680bc644444835
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7ce43744c475cd735b188127a324f59455118c0429aa5e624de0e4b1d004832
+oid sha256:c693fb2ea94de3ab99065331d59deff37c4c392b1695d7781427a4e71d863f58
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.843423799582464,
+  "epoch": 1.1918951132300357,
   "eval_steps": 400,
-  "global_step": 11600,
+  "global_step": 4000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -388,734 +388,12 @@
       "eval_samples_per_second": 8.611,
       "eval_steps_per_second": 1.089,
       "step": 4000
-    },
-    {
-      "epoch": 1.7118997912317329,
-      "grad_norm": 6.32857608795166,
-      "learning_rate": 2.3019624217118998e-05,
-      "loss": 1.289,
-      "step": 4100
-    },
-    {
-      "epoch": 1.7536534446764092,
-      "grad_norm": 4.060805320739746,
-      "learning_rate": 2.272734864300626e-05,
-      "loss": 1.2964,
-      "step": 4200
-    },
-    {
-      "epoch": 1.7954070981210855,
-      "grad_norm": 6.695485591888428,
-      "learning_rate": 2.2435073068893524e-05,
-      "loss": 1.2893,
-      "step": 4300
-    },
-    {
-      "epoch": 1.837160751565762,
-      "grad_norm": 3.5373055934906006,
-      "learning_rate": 2.2142797494780794e-05,
-      "loss": 1.291,
-      "step": 4400
-    },
-    {
-      "epoch": 1.837160751565762,
-      "eval_bleu": 39.50137065038,
-      "eval_chrf": 64.97350475133454,
-      "eval_loss": 1.4079142808914185,
-      "eval_runtime": 56.7376,
-      "eval_samples_per_second": 9.059,
-      "eval_steps_per_second": 1.146,
-      "step": 4400
-    },
-    {
-      "epoch": 1.8789144050104385,
-      "grad_norm": 5.9530510902404785,
-      "learning_rate": 2.1850521920668057e-05,
-      "loss": 1.2814,
-      "step": 4500
-    },
-    {
-      "epoch": 1.9206680584551148,
-      "grad_norm": 4.477818965911865,
-      "learning_rate": 2.1558246346555323e-05,
-      "loss": 1.2768,
-      "step": 4600
-    },
-    {
-      "epoch": 1.962421711899791,
-      "grad_norm": 5.695155143737793,
-      "learning_rate": 2.1265970772442586e-05,
-      "loss": 1.3108,
-      "step": 4700
-    },
-    {
-      "epoch": 2.0041753653444676,
-      "grad_norm": 5.8031415939331055,
-      "learning_rate": 2.097369519832985e-05,
-      "loss": 1.2575,
-      "step": 4800
-    },
-    {
-      "epoch": 2.0041753653444676,
-      "eval_bleu": 39.30699442637268,
-      "eval_chrf": 64.89770518645786,
-      "eval_loss": 1.3974848985671997,
-      "eval_runtime": 55.8732,
-      "eval_samples_per_second": 9.199,
-      "eval_steps_per_second": 1.163,
-      "step": 4800
-    },
-    {
-      "epoch": 2.045929018789144,
-      "grad_norm": 4.926381587982178,
-      "learning_rate": 2.068141962421712e-05,
-      "loss": 1.2662,
-      "step": 4900
-    },
-    {
-      "epoch": 2.0876826722338206,
-      "grad_norm": 4.722453594207764,
-      "learning_rate": 2.0389144050104382e-05,
-      "loss": 1.3493,
-      "step": 5000
-    },
-    {
-      "epoch": 2.1294363256784967,
-      "grad_norm": 4.256781101226807,
-      "learning_rate": 2.009686847599165e-05,
-      "loss": 1.2453,
-      "step": 5100
-    },
-    {
-      "epoch": 2.1711899791231732,
-      "grad_norm": 7.283603668212891,
-      "learning_rate": 1.980459290187891e-05,
-      "loss": 1.2057,
-      "step": 5200
-    },
-    {
-      "epoch": 2.1711899791231732,
-      "eval_bleu": 39.279414503942476,
-      "eval_chrf": 64.69704130979886,
-      "eval_loss": 1.3991910219192505,
-      "eval_runtime": 56.5297,
-      "eval_samples_per_second": 9.093,
-      "eval_steps_per_second": 1.15,
-      "step": 5200
-    },
-    {
-      "epoch": 2.2129436325678498,
-      "grad_norm": 5.156922340393066,
-      "learning_rate": 1.9512317327766178e-05,
-      "loss": 1.2841,
-      "step": 5300
-    },
-    {
-      "epoch": 2.2546972860125263,
-      "grad_norm": 4.524971008300781,
-      "learning_rate": 1.9220041753653444e-05,
-      "loss": 1.2267,
-      "step": 5400
-    },
-    {
-      "epoch": 2.2964509394572024,
-      "grad_norm": 4.417050838470459,
-      "learning_rate": 1.8927766179540707e-05,
-      "loss": 1.262,
-      "step": 5500
-    },
-    {
-      "epoch": 2.338204592901879,
-      "grad_norm": 4.09854793548584,
-      "learning_rate": 1.8635490605427974e-05,
-      "loss": 1.354,
-      "step": 5600
-    },
-    {
-      "epoch": 2.338204592901879,
-      "eval_bleu": 39.813589031612814,
-      "eval_chrf": 65.03728206060732,
-      "eval_loss": 1.392536997795105,
-      "eval_runtime": 55.7708,
-      "eval_samples_per_second": 9.216,
-      "eval_steps_per_second": 1.165,
-      "step": 5600
-    },
-    {
-      "epoch": 2.3799582463465554,
-      "grad_norm": 3.0515196323394775,
-      "learning_rate": 1.834321503131524e-05,
-      "loss": 1.2684,
-      "step": 5700
-    },
-    {
-      "epoch": 2.421711899791232,
-      "grad_norm": 3.1159090995788574,
-      "learning_rate": 1.8050939457202503e-05,
-      "loss": 1.2926,
-      "step": 5800
-    },
-    {
-      "epoch": 2.463465553235908,
-      "grad_norm": 3.780430316925049,
-      "learning_rate": 1.775866388308977e-05,
-      "loss": 1.2633,
-      "step": 5900
-    },
-    {
-      "epoch": 2.5052192066805845,
-      "grad_norm": 4.610201358795166,
-      "learning_rate": 1.7466388308977033e-05,
-      "loss": 1.2727,
-      "step": 6000
-    },
-    {
-      "epoch": 2.5052192066805845,
-      "eval_bleu": 39.650677906597124,
-      "eval_chrf": 65.09804172463261,
-      "eval_loss": 1.3860098123550415,
-      "eval_runtime": 56.2283,
-      "eval_samples_per_second": 9.141,
-      "eval_steps_per_second": 1.156,
-      "step": 6000
-    },
-    {
-      "epoch": 2.546972860125261,
-      "grad_norm": 3.7857203483581543,
-      "learning_rate": 1.71741127348643e-05,
-      "loss": 1.2094,
-      "step": 6100
-    },
-    {
-      "epoch": 2.588726513569937,
-      "grad_norm": 6.026632785797119,
-      "learning_rate": 1.6881837160751566e-05,
-      "loss": 1.2877,
-      "step": 6200
-    },
-    {
-      "epoch": 2.6304801670146136,
-      "grad_norm": 4.994929313659668,
-      "learning_rate": 1.658956158663883e-05,
-      "loss": 1.2911,
-      "step": 6300
-    },
-    {
-      "epoch": 2.67223382045929,
-      "grad_norm": 6.461598873138428,
-      "learning_rate": 1.6297286012526095e-05,
-      "loss": 1.2314,
-      "step": 6400
-    },
-    {
-      "epoch": 2.67223382045929,
-      "eval_bleu": 39.945861853611575,
-      "eval_chrf": 65.04362840026685,
-      "eval_loss": 1.3826228380203247,
-      "eval_runtime": 56.2339,
-      "eval_samples_per_second": 9.14,
-      "eval_steps_per_second": 1.156,
-      "step": 6400
-    },
-    {
-      "epoch": 2.7139874739039667,
-      "grad_norm": 5.786142826080322,
-      "learning_rate": 1.6005010438413358e-05,
-      "loss": 1.2109,
-      "step": 6500
-    },
-    {
-      "epoch": 2.755741127348643,
-      "grad_norm": 5.925867557525635,
-      "learning_rate": 1.5712734864300624e-05,
-      "loss": 1.2846,
-      "step": 6600
-    },
-    {
-      "epoch": 2.7974947807933193,
-      "grad_norm": 2.665583610534668,
-      "learning_rate": 1.542045929018789e-05,
-      "loss": 1.2492,
-      "step": 6700
-    },
-    {
-      "epoch": 2.8392484342379958,
-      "grad_norm": 4.909760475158691,
-      "learning_rate": 1.5128183716075156e-05,
-      "loss": 1.2007,
-      "step": 6800
-    },
-    {
-      "epoch": 2.8392484342379958,
-      "eval_bleu": 39.4513888065329,
-      "eval_chrf": 65.0324545104775,
-      "eval_loss": 1.3842790126800537,
-      "eval_runtime": 55.7536,
-      "eval_samples_per_second": 9.219,
-      "eval_steps_per_second": 1.166,
-      "step": 6800
-    },
-    {
-      "epoch": 2.8810020876826723,
-      "grad_norm": 4.68897008895874,
-      "learning_rate": 1.483590814196242e-05,
-      "loss": 1.2595,
-      "step": 6900
-    },
-    {
-      "epoch": 2.9227557411273484,
-      "grad_norm": 3.6529064178466797,
-      "learning_rate": 1.4543632567849685e-05,
-      "loss": 1.1934,
-      "step": 7000
-    },
-    {
-      "epoch": 2.964509394572025,
-      "grad_norm": 5.94176721572876,
-      "learning_rate": 1.4251356993736951e-05,
-      "loss": 1.2485,
-      "step": 7100
-    },
-    {
-      "epoch": 3.0062630480167014,
-      "grad_norm": 5.9626007080078125,
-      "learning_rate": 1.3959081419624216e-05,
-      "loss": 1.253,
-      "step": 7200
-    },
-    {
-      "epoch": 3.0062630480167014,
-      "eval_bleu": 39.45971213674,
-      "eval_chrf": 64.96089751387221,
-      "eval_loss": 1.3754563331604004,
-      "eval_runtime": 56.4406,
-      "eval_samples_per_second": 9.107,
-      "eval_steps_per_second": 1.152,
-      "step": 7200
-    },
-    {
-      "epoch": 3.048016701461378,
-      "grad_norm": 4.214338779449463,
-      "learning_rate": 1.3666805845511481e-05,
-      "loss": 1.2404,
-      "step": 7300
-    },
-    {
-      "epoch": 3.0897703549060545,
-      "grad_norm": 5.062374591827393,
-      "learning_rate": 1.3374530271398746e-05,
-      "loss": 1.3364,
-      "step": 7400
-    },
-    {
-      "epoch": 3.1315240083507305,
-      "grad_norm": 6.331946849822998,
-      "learning_rate": 1.308225469728601e-05,
-      "loss": 1.2342,
-      "step": 7500
-    },
-    {
-      "epoch": 3.173277661795407,
-      "grad_norm": 4.617956638336182,
-      "learning_rate": 1.2789979123173277e-05,
-      "loss": 1.1997,
-      "step": 7600
-    },
-    {
-      "epoch": 3.173277661795407,
-      "eval_bleu": 39.543166845863816,
-      "eval_chrf": 65.14125416250813,
-      "eval_loss": 1.3746187686920166,
-      "eval_runtime": 56.231,
-      "eval_samples_per_second": 9.141,
-      "eval_steps_per_second": 1.156,
-      "step": 7600
-    },
-    {
-      "epoch": 3.2150313152400836,
-      "grad_norm": 3.2519586086273193,
-      "learning_rate": 1.2497703549060542e-05,
-      "loss": 1.3495,
-      "step": 7700
-    },
-    {
-      "epoch": 3.25678496868476,
-      "grad_norm": 7.227553844451904,
-      "learning_rate": 1.2205427974947808e-05,
-      "loss": 1.2462,
-      "step": 7800
-    },
-    {
-      "epoch": 3.298538622129436,
-      "grad_norm": 7.0863566398620605,
-      "learning_rate": 1.1913152400835071e-05,
-      "loss": 1.1328,
-      "step": 7900
-    },
-    {
-      "epoch": 3.3402922755741127,
-      "grad_norm": 6.927553653717041,
-      "learning_rate": 1.1620876826722337e-05,
-      "loss": 1.2149,
-      "step": 8000
-    },
-    {
-      "epoch": 3.3402922755741127,
-      "eval_bleu": 39.35605161195287,
-      "eval_chrf": 64.90078562038494,
-      "eval_loss": 1.3774685859680176,
-      "eval_runtime": 55.9752,
-      "eval_samples_per_second": 9.183,
-      "eval_steps_per_second": 1.161,
-      "step": 8000
-    },
-    {
-      "epoch": 3.382045929018789,
-      "grad_norm": 4.033844947814941,
-      "learning_rate": 1.1328601252609602e-05,
-      "loss": 1.2643,
-      "step": 8100
-    },
-    {
-      "epoch": 3.4237995824634657,
-      "grad_norm": 4.920534610748291,
-      "learning_rate": 1.1036325678496869e-05,
-      "loss": 1.2487,
-      "step": 8200
-    },
-    {
-      "epoch": 3.465553235908142,
-      "grad_norm": 5.343802452087402,
-      "learning_rate": 1.0744050104384133e-05,
-      "loss": 1.1759,
-      "step": 8300
-    },
-    {
-      "epoch": 3.5073068893528183,
-      "grad_norm": 3.9641456604003906,
-      "learning_rate": 1.0451774530271396e-05,
-      "loss": 1.1315,
-      "step": 8400
-    },
-    {
-      "epoch": 3.5073068893528183,
-      "eval_bleu": 39.18479147993907,
-      "eval_chrf": 65.01557816764418,
-      "eval_loss": 1.3742948770523071,
-      "eval_runtime": 56.3152,
-      "eval_samples_per_second": 9.127,
-      "eval_steps_per_second": 1.154,
-      "step": 8400
-    },
-    {
-      "epoch": 3.549060542797495,
-      "grad_norm": 5.440670967102051,
-      "learning_rate": 1.0159498956158663e-05,
-      "loss": 1.2285,
-      "step": 8500
-    },
-    {
-      "epoch": 3.5908141962421714,
-      "grad_norm": 4.842555522918701,
-      "learning_rate": 9.867223382045927e-06,
-      "loss": 1.1738,
-      "step": 8600
-    },
-    {
-      "epoch": 3.632567849686848,
-      "grad_norm": 5.682887077331543,
-      "learning_rate": 9.574947807933194e-06,
-      "loss": 1.1964,
-      "step": 8700
-    },
-    {
-      "epoch": 3.674321503131524,
-      "grad_norm": 4.14805269241333,
-      "learning_rate": 9.282672233820459e-06,
-      "loss": 1.1869,
-      "step": 8800
-    },
-    {
-      "epoch": 3.674321503131524,
-      "eval_bleu": 39.43255607358465,
-      "eval_chrf": 64.92402849479646,
-      "eval_loss": 1.370447039604187,
-      "eval_runtime": 55.6462,
-      "eval_samples_per_second": 9.237,
-      "eval_steps_per_second": 1.168,
-      "step": 8800
-    },
-    {
-      "epoch": 3.7160751565762005,
-      "grad_norm": 7.448594093322754,
-      "learning_rate": 8.990396659707723e-06,
-      "loss": 1.1608,
-      "step": 8900
-    },
-    {
-      "epoch": 3.757828810020877,
-      "grad_norm": 5.6767354011535645,
-      "learning_rate": 8.698121085594988e-06,
-      "loss": 1.3469,
-      "step": 9000
-    },
-    {
-      "epoch": 3.799582463465553,
-      "grad_norm": 6.773651599884033,
-      "learning_rate": 8.405845511482254e-06,
-      "loss": 1.2066,
-      "step": 9100
-    },
-    {
-      "epoch": 3.8413361169102296,
-      "grad_norm": 4.687694549560547,
-      "learning_rate": 8.11356993736952e-06,
-      "loss": 1.2112,
-      "step": 9200
-    },
-    {
-      "epoch": 3.8413361169102296,
-      "eval_bleu": 39.44592803924271,
-      "eval_chrf": 64.99174226152643,
-      "eval_loss": 1.3653467893600464,
-      "eval_runtime": 56.5388,
-      "eval_samples_per_second": 9.091,
-      "eval_steps_per_second": 1.15,
-      "step": 9200
-    },
-    {
-      "epoch": 3.883089770354906,
-      "grad_norm": 4.808062553405762,
-      "learning_rate": 7.821294363256784e-06,
-      "loss": 1.1826,
-      "step": 9300
-    },
-    {
-      "epoch": 3.9248434237995826,
-      "grad_norm": 3.992347002029419,
-      "learning_rate": 7.5290187891440495e-06,
-      "loss": 1.1879,
-      "step": 9400
-    },
-    {
-      "epoch": 3.966597077244259,
-      "grad_norm": 6.685673236846924,
-      "learning_rate": 7.236743215031314e-06,
-      "loss": 1.2145,
-      "step": 9500
-    },
-    {
-      "epoch": 4.008350730688935,
-      "grad_norm": 3.0742173194885254,
-      "learning_rate": 6.94446764091858e-06,
-      "loss": 1.2247,
-      "step": 9600
-    },
-    {
-      "epoch": 4.008350730688935,
-      "eval_bleu": 39.61248876284892,
-      "eval_chrf": 65.00803037188629,
-      "eval_loss": 1.3674365282058716,
-      "eval_runtime": 55.3543,
-      "eval_samples_per_second": 9.286,
-      "eval_steps_per_second": 1.174,
-      "step": 9600
-    },
-    {
-      "epoch": 4.050104384133611,
-      "grad_norm": 4.643916606903076,
-      "learning_rate": 6.652192066805845e-06,
-      "loss": 1.2002,
-      "step": 9700
-    },
-    {
-      "epoch": 4.091858037578288,
-      "grad_norm": 4.483417987823486,
-      "learning_rate": 6.35991649269311e-06,
-      "loss": 1.1674,
-      "step": 9800
-    },
-    {
-      "epoch": 4.133611691022964,
-      "grad_norm": 4.413819789886475,
-      "learning_rate": 6.067640918580376e-06,
-      "loss": 1.174,
-      "step": 9900
-    },
-    {
-      "epoch": 4.175365344467641,
-      "grad_norm": 3.874394655227661,
-      "learning_rate": 5.77536534446764e-06,
-      "loss": 1.1827,
-      "step": 10000
-    },
-    {
-      "epoch": 4.175365344467641,
-      "eval_bleu": 39.476341942884325,
-      "eval_chrf": 65.05683664223154,
-      "eval_loss": 1.3643035888671875,
-      "eval_runtime": 55.64,
-      "eval_samples_per_second": 9.238,
-      "eval_steps_per_second": 1.168,
-      "step": 10000
-    },
-    {
-      "epoch": 4.217118997912317,
-      "grad_norm": 6.293316841125488,
-      "learning_rate": 5.483089770354906e-06,
-      "loss": 1.219,
-      "step": 10100
-    },
-    {
-      "epoch": 4.258872651356993,
-      "grad_norm": 4.437298774719238,
-      "learning_rate": 5.1908141962421715e-06,
-      "loss": 1.254,
-      "step": 10200
-    },
-    {
-      "epoch": 4.30062630480167,
-      "grad_norm": 6.497868537902832,
-      "learning_rate": 4.8985386221294354e-06,
-      "loss": 1.1714,
-      "step": 10300
-    },
-    {
-      "epoch": 4.3423799582463465,
-      "grad_norm": 4.4877400398254395,
-      "learning_rate": 4.606263048016701e-06,
-      "loss": 1.1792,
-      "step": 10400
-    },
-    {
-      "epoch": 4.3423799582463465,
-      "eval_bleu": 39.30101946875823,
-      "eval_chrf": 65.02741852818104,
-      "eval_loss": 1.3641453981399536,
-      "eval_runtime": 56.1562,
-      "eval_samples_per_second": 9.153,
-      "eval_steps_per_second": 1.157,
-      "step": 10400
-    },
-    {
-      "epoch": 4.384133611691023,
-      "grad_norm": 4.146666049957275,
-      "learning_rate": 4.3139874739039666e-06,
-      "loss": 1.2514,
-      "step": 10500
-    },
-    {
-      "epoch": 4.4258872651356995,
-      "grad_norm": 4.732193946838379,
-      "learning_rate": 4.021711899791231e-06,
-      "loss": 1.179,
-      "step": 10600
-    },
-    {
-      "epoch": 4.467640918580376,
-      "grad_norm": 4.930966377258301,
-      "learning_rate": 3.7294363256784965e-06,
-      "loss": 1.1886,
-      "step": 10700
-    },
-    {
-      "epoch": 4.509394572025053,
-      "grad_norm": 6.418299674987793,
-      "learning_rate": 3.4371607515657616e-06,
-      "loss": 1.1239,
-      "step": 10800
-    },
-    {
-      "epoch": 4.509394572025053,
-      "eval_bleu": 39.6267656277982,
-      "eval_chrf": 64.9916128839759,
-      "eval_loss": 1.3610318899154663,
-      "eval_runtime": 56.2525,
-      "eval_samples_per_second": 9.137,
-      "eval_steps_per_second": 1.156,
-      "step": 10800
-    },
-    {
-      "epoch": 4.551148225469729,
-      "grad_norm": 4.902411460876465,
-      "learning_rate": 3.1448851774530268e-06,
-      "loss": 1.1989,
-      "step": 10900
-    },
-    {
-      "epoch": 4.592901878914405,
-      "grad_norm": 3.843609094619751,
-      "learning_rate": 2.8526096033402923e-06,
-      "loss": 1.2179,
-      "step": 11000
-    },
-    {
-      "epoch": 4.634655532359082,
-      "grad_norm": 3.9309775829315186,
-      "learning_rate": 2.5603340292275575e-06,
-      "loss": 1.2536,
-      "step": 11100
-    },
-    {
-      "epoch": 4.676409185803758,
-      "grad_norm": 4.596682071685791,
-      "learning_rate": 2.268058455114822e-06,
-      "loss": 1.2294,
-      "step": 11200
-    },
-    {
-      "epoch": 4.676409185803758,
-      "eval_bleu": 39.42537992670536,
-      "eval_chrf": 65.04676258592426,
-      "eval_loss": 1.3609488010406494,
-      "eval_runtime": 56.1025,
-      "eval_samples_per_second": 9.162,
-      "eval_steps_per_second": 1.159,
-      "step": 11200
-    },
-    {
-      "epoch": 4.718162839248434,
-      "grad_norm": 6.444948673248291,
-      "learning_rate": 1.9757828810020874e-06,
-      "loss": 1.2244,
-      "step": 11300
-    },
-    {
-      "epoch": 4.759916492693111,
-      "grad_norm": 4.887237071990967,
-      "learning_rate": 1.6835073068893527e-06,
-      "loss": 1.1555,
-      "step": 11400
-    },
-    {
-      "epoch": 4.801670146137787,
-      "grad_norm": 4.212841510772705,
-      "learning_rate": 1.3912317327766179e-06,
-      "loss": 1.2587,
-      "step": 11500
-    },
-    {
-      "epoch": 4.843423799582464,
-      "grad_norm": 4.797667026519775,
-      "learning_rate": 1.0989561586638828e-06,
-      "loss": 1.2433,
-      "step": 11600
-    },
-    {
-      "epoch": 4.843423799582464,
-      "eval_bleu": 39.52649267855855,
-      "eval_chrf": 65.06555352708587,
-      "eval_loss": 1.3612278699874878,
-      "eval_runtime": 56.2691,
-      "eval_samples_per_second": 9.135,
-      "eval_steps_per_second": 1.155,
-      "step": 11600
     }
   ],
   "logging_steps": 100,
-  "max_steps": 11975,
+  "max_steps": 6712,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 5,
+  "num_train_epochs": 2,
   "save_steps": 400,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -1129,7 +407,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.1766813766844416e+16,
+  "total_flos": 1.0955136172032e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:154e087a3a2fd155154e094cc2b86a5c7733e1b8102e7ddde2f991c5884a8185
+oid sha256:1296a4c4cbbfb511129c5fc25155a089f73ccf8250b3689b0cf311c5f320fd65
 size 5905

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4c14739f1958d1e21b39cf77c4f8218e9f58f22d72ce8bafb148d31def1ab7f
+oid sha256:a9a5d731a4e350b46d20109f1d4cae3a22746905d4248ebb35989421d68044ec
 size 990185320