Upload folder using huggingface_hub

checkpoint-1000/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9911560117171a446c08636c65c343ea768239cf9e1e0ccc645e885ac612bac0
+oid sha256:a4740eff7f7726a7d81146d0a540c888654d2eb3bdf282d11aa73680ccbb36dc
 size 151392779

checkpoint-1000/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9625c7576b971136405ea7ed3db538a582c980dda09d7fc0bcdf64d1da7c54b
+oid sha256:215946acfe8af69cc186f5f2a033d67d1fc49ffaf3d6f583a9706375c1d75377
 size 199234413

checkpoint-1000/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fb1a8ee1c09bd907f641a919425f64ba1cc2ca04599ac4e7c14f648412a508f
+oid sha256:4d30b109bc34b215f2601d0ec75f5f8775fac00c35608a61cc209a5dcfb7edaa
 size 14391

checkpoint-1000/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2198ef7f092075b5da446a2e5e459191e7bd94fd8a8fc5f66d6f6e0ffc742ed
+oid sha256:6e95cf302fdc08538ad9e6e764784ebfdd975f9c84fbfeaaf60b42ed9055df9e
 size 1465

checkpoint-1000/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_global_step": 1000,
-  "best_metric": 5.496740818023682,
+  "best_metric": 5.472690582275391,
   "best_model_checkpoint": "./nyanja_english_warmup\\checkpoint-1000",
-  "epoch": 0.42390843577787196,
+  "epoch": 0.5035246727089627,
   "eval_steps": 500,
   "global_step": 1000,
   "is_hyper_param_search": false,
@@ -10,164 +10,164 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.0211954217888936,
-      "grad_norm": 1.1472082138061523,
-      "learning_rate": 4.896142433234421e-05,
-      "loss": 9.5805,
+      "epoch": 0.025176233635448138,
+      "grad_norm": 0.947960615158081,
+      "learning_rate": 4.876636455186304e-05,
+      "loss": 9.5286,
       "step": 50
     },
     {
-      "epoch": 0.0423908435777872,
-      "grad_norm": 1.2479043006896973,
-      "learning_rate": 4.790165324289953e-05,
-      "loss": 8.2283,
+      "epoch": 0.050352467270896276,
+      "grad_norm": 1.194724440574646,
+      "learning_rate": 4.7507552870090635e-05,
+      "loss": 8.2179,
       "step": 100
     },
     {
-      "epoch": 0.0635862653666808,
-      "grad_norm": 1.1807806491851807,
-      "learning_rate": 4.684188215345486e-05,
-      "loss": 7.6907,
+      "epoch": 0.0755287009063444,
+      "grad_norm": 0.9894101023674011,
+      "learning_rate": 4.624874118831823e-05,
+      "loss": 7.5072,
       "step": 150
     },
     {
-      "epoch": 0.0847816871555744,
-      "grad_norm": 1.0857632160186768,
-      "learning_rate": 4.578211106401017e-05,
-      "loss": 7.3068,
+      "epoch": 0.10070493454179255,
+      "grad_norm": 0.9540104269981384,
+      "learning_rate": 4.498992950654582e-05,
+      "loss": 7.1644,
       "step": 200
     },
     {
-      "epoch": 0.10597710894446799,
-      "grad_norm": 1.0846374034881592,
-      "learning_rate": 4.47223399745655e-05,
-      "loss": 7.0734,
+      "epoch": 0.12588116817724068,
+      "grad_norm": 1.0262048244476318,
+      "learning_rate": 4.3731117824773415e-05,
+      "loss": 6.9377,
       "step": 250
     },
     {
-      "epoch": 0.1271725307333616,
-      "grad_norm": 0.9803574681282043,
-      "learning_rate": 4.366256888512081e-05,
-      "loss": 6.8886,
+      "epoch": 0.1510574018126888,
+      "grad_norm": 0.916906476020813,
+      "learning_rate": 4.2472306143001015e-05,
+      "loss": 6.7447,
       "step": 300
     },
     {
-      "epoch": 0.14836795252225518,
-      "grad_norm": 1.0538763999938965,
-      "learning_rate": 4.260279779567614e-05,
-      "loss": 6.7217,
+      "epoch": 0.17623363544813697,
+      "grad_norm": 0.9376256465911865,
+      "learning_rate": 4.12134944612286e-05,
+      "loss": 6.6128,
       "step": 350
     },
     {
-      "epoch": 0.1695633743111488,
-      "grad_norm": 0.9296303987503052,
-      "learning_rate": 4.1543026706231456e-05,
-      "loss": 6.5976,
+      "epoch": 0.2014098690835851,
+      "grad_norm": 0.8047090768814087,
+      "learning_rate": 3.9954682779456194e-05,
+      "loss": 6.5074,
       "step": 400
     },
     {
-      "epoch": 0.1907587961000424,
-      "grad_norm": 0.9482334852218628,
-      "learning_rate": 4.0483255616786776e-05,
-      "loss": 6.4831,
+      "epoch": 0.22658610271903323,
+      "grad_norm": 0.9348500967025757,
+      "learning_rate": 3.869587109768379e-05,
+      "loss": 6.4087,
       "step": 450
     },
     {
-      "epoch": 0.21195421788893598,
-      "grad_norm": 0.9004257321357727,
-      "learning_rate": 3.9423484527342095e-05,
-      "loss": 6.3974,
+      "epoch": 0.25176233635448136,
+      "grad_norm": 0.8273019194602966,
+      "learning_rate": 3.743705941591138e-05,
+      "loss": 6.3114,
       "step": 500
     },
     {
-      "epoch": 0.21195421788893598,
-      "eval_loss": 6.0686774253845215,
-      "eval_runtime": 126.535,
-      "eval_samples_per_second": 15.703,
-      "eval_steps_per_second": 0.988,
+      "epoch": 0.25176233635448136,
+      "eval_loss": 5.968835353851318,
+      "eval_runtime": 41.9731,
+      "eval_samples_per_second": 39.859,
+      "eval_steps_per_second": 2.502,
       "step": 500
     },
     {
-      "epoch": 0.2331496396778296,
-      "grad_norm": 0.8829556703567505,
-      "learning_rate": 3.8363713437897415e-05,
-      "loss": 6.2952,
+      "epoch": 0.2769385699899295,
+      "grad_norm": 0.7640300989151001,
+      "learning_rate": 3.6178247734138974e-05,
+      "loss": 6.2115,
       "step": 550
     },
     {
-      "epoch": 0.2543450614667232,
-      "grad_norm": 0.7846332788467407,
-      "learning_rate": 3.7303942348452734e-05,
-      "loss": 6.216,
+      "epoch": 0.3021148036253776,
+      "grad_norm": 0.8070991635322571,
+      "learning_rate": 3.491943605236657e-05,
+      "loss": 6.1867,
       "step": 600
     },
     {
-      "epoch": 0.2755404832556168,
-      "grad_norm": 0.8392072319984436,
-      "learning_rate": 3.624417125900806e-05,
-      "loss": 6.1427,
+      "epoch": 0.32729103726082576,
+      "grad_norm": 0.7798317074775696,
+      "learning_rate": 3.366062437059416e-05,
+      "loss": 6.0893,
       "step": 650
     },
     {
-      "epoch": 0.29673590504451036,
-      "grad_norm": 0.8008320331573486,
-      "learning_rate": 3.518440016956337e-05,
-      "loss": 6.061,
+      "epoch": 0.35246727089627394,
+      "grad_norm": 0.8209011554718018,
+      "learning_rate": 3.240181268882175e-05,
+      "loss": 6.0416,
       "step": 700
     },
     {
-      "epoch": 0.31793132683340397,
-      "grad_norm": 0.8059436082839966,
-      "learning_rate": 3.41246290801187e-05,
-      "loss": 6.0253,
+      "epoch": 0.3776435045317221,
+      "grad_norm": 0.7711942195892334,
+      "learning_rate": 3.1143001007049346e-05,
+      "loss": 5.9784,
       "step": 750
     },
     {
-      "epoch": 0.3391267486222976,
-      "grad_norm": 0.7888209819793701,
-      "learning_rate": 3.306485799067401e-05,
-      "loss": 5.9739,
+      "epoch": 0.4028197381671702,
+      "grad_norm": 0.8087317943572998,
+      "learning_rate": 2.988418932527694e-05,
+      "loss": 5.9354,
       "step": 800
     },
     {
-      "epoch": 0.3603221704111912,
-      "grad_norm": 0.7676851749420166,
-      "learning_rate": 3.200508690122934e-05,
-      "loss": 5.899,
+      "epoch": 0.42799597180261834,
+      "grad_norm": 0.7595328688621521,
+      "learning_rate": 2.862537764350453e-05,
+      "loss": 5.8544,
       "step": 850
     },
     {
-      "epoch": 0.3815175922000848,
-      "grad_norm": 0.7366964221000671,
-      "learning_rate": 3.094531581178466e-05,
-      "loss": 5.8371,
+      "epoch": 0.45317220543806647,
+      "grad_norm": 0.7424010038375854,
+      "learning_rate": 2.7366565961732126e-05,
+      "loss": 5.8309,
       "step": 900
     },
     {
-      "epoch": 0.4027130139889784,
-      "grad_norm": 0.7427886724472046,
-      "learning_rate": 2.9885544722339974e-05,
-      "loss": 5.8132,
+      "epoch": 0.4783484390735146,
+      "grad_norm": 0.7028313279151917,
+      "learning_rate": 2.610775427995972e-05,
+      "loss": 5.8075,
       "step": 950
     },
     {
-      "epoch": 0.42390843577787196,
-      "grad_norm": 0.7304149270057678,
-      "learning_rate": 2.8825773632895297e-05,
-      "loss": 5.7658,
+      "epoch": 0.5035246727089627,
+      "grad_norm": 0.739640474319458,
+      "learning_rate": 2.4848942598187312e-05,
+      "loss": 5.7741,
       "step": 1000
     },
     {
-      "epoch": 0.42390843577787196,
-      "eval_loss": 5.496740818023682,
-      "eval_runtime": 135.1668,
-      "eval_samples_per_second": 14.7,
-      "eval_steps_per_second": 0.925,
+      "epoch": 0.5035246727089627,
+      "eval_loss": 5.472690582275391,
+      "eval_runtime": 37.0841,
+      "eval_samples_per_second": 45.114,
+      "eval_steps_per_second": 2.831,
       "step": 1000
     }
   ],
   "logging_steps": 50,
-  "max_steps": 2359,
+  "max_steps": 1986,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 500,

checkpoint-1000/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c366c061dbfe585f916533453390826a1bc5c140fbbd8f7ec764025c35edef63
+oid sha256:fd35ffac2ed4cf9159515c227a2e8bb8761c759f619e17bd96f19d5dd4c854ad
 size 5713

checkpoint-1500/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5266ffa0d337f018be8bfe6368258443a39e4d243ddd042290c6c3c3a1b69caa
+oid sha256:5da0f570703c36c705757779b20b5d3fc9b39084e216990d8f3923c9f791b6b0
 size 151392779

checkpoint-1500/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69de92648f500dec3090d53b8ff737a4da27ac96c50c504b472795c50998b084
+oid sha256:14c9b1e4723bc4f3f18cbfefb09cc3d30e23120b46f6caa05f88aa21b076609d
 size 199234413

checkpoint-1500/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43670d81291a428a665c61e487cf36a3834a82fbf737d30e52198013c1b9a3aa
+oid sha256:94c2c5693e8ea1cb95056ee4aac8a87df5457ec36d1f15b47727ec41df4454e6
 size 14391

checkpoint-1500/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f0ef3812a610e87fed2a26066cc4b31acdce22e54f103843cdad34dac426b5c
+oid sha256:44b61b1eb8ac8f136ee5b34beb2fbbda26e2ed9f460c59ba13066bdc598b0fa1
 size 1465

checkpoint-1500/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_global_step": 1500,
-  "best_metric": 5.19881534576416,
+  "best_metric": 5.239852428436279,
   "best_model_checkpoint": "./nyanja_english_warmup\\checkpoint-1500",
-  "epoch": 0.6358626536668079,
+  "epoch": 0.7552870090634441,
   "eval_steps": 500,
   "global_step": 1500,
   "is_hyper_param_search": false,
@@ -10,242 +10,242 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.0211954217888936,
-      "grad_norm": 1.1472082138061523,
-      "learning_rate": 4.896142433234421e-05,
-      "loss": 9.5805,
+      "epoch": 0.025176233635448138,
+      "grad_norm": 0.947960615158081,
+      "learning_rate": 4.876636455186304e-05,
+      "loss": 9.5286,
       "step": 50
     },
     {
-      "epoch": 0.0423908435777872,
-      "grad_norm": 1.2479043006896973,
-      "learning_rate": 4.790165324289953e-05,
-      "loss": 8.2283,
+      "epoch": 0.050352467270896276,
+      "grad_norm": 1.194724440574646,
+      "learning_rate": 4.7507552870090635e-05,
+      "loss": 8.2179,
       "step": 100
     },
     {
-      "epoch": 0.0635862653666808,
-      "grad_norm": 1.1807806491851807,
-      "learning_rate": 4.684188215345486e-05,
-      "loss": 7.6907,
+      "epoch": 0.0755287009063444,
+      "grad_norm": 0.9894101023674011,
+      "learning_rate": 4.624874118831823e-05,
+      "loss": 7.5072,
       "step": 150
     },
     {
-      "epoch": 0.0847816871555744,
-      "grad_norm": 1.0857632160186768,
-      "learning_rate": 4.578211106401017e-05,
-      "loss": 7.3068,
+      "epoch": 0.10070493454179255,
+      "grad_norm": 0.9540104269981384,
+      "learning_rate": 4.498992950654582e-05,
+      "loss": 7.1644,
       "step": 200
     },
     {
-      "epoch": 0.10597710894446799,
-      "grad_norm": 1.0846374034881592,
-      "learning_rate": 4.47223399745655e-05,
-      "loss": 7.0734,
+      "epoch": 0.12588116817724068,
+      "grad_norm": 1.0262048244476318,
+      "learning_rate": 4.3731117824773415e-05,
+      "loss": 6.9377,
       "step": 250
     },
     {
-      "epoch": 0.1271725307333616,
-      "grad_norm": 0.9803574681282043,
-      "learning_rate": 4.366256888512081e-05,
-      "loss": 6.8886,
+      "epoch": 0.1510574018126888,
+      "grad_norm": 0.916906476020813,
+      "learning_rate": 4.2472306143001015e-05,
+      "loss": 6.7447,
       "step": 300
     },
     {
-      "epoch": 0.14836795252225518,
-      "grad_norm": 1.0538763999938965,
-      "learning_rate": 4.260279779567614e-05,
-      "loss": 6.7217,
+      "epoch": 0.17623363544813697,
+      "grad_norm": 0.9376256465911865,
+      "learning_rate": 4.12134944612286e-05,
+      "loss": 6.6128,
       "step": 350
     },
     {
-      "epoch": 0.1695633743111488,
-      "grad_norm": 0.9296303987503052,
-      "learning_rate": 4.1543026706231456e-05,
-      "loss": 6.5976,
+      "epoch": 0.2014098690835851,
+      "grad_norm": 0.8047090768814087,
+      "learning_rate": 3.9954682779456194e-05,
+      "loss": 6.5074,
       "step": 400
     },
     {
-      "epoch": 0.1907587961000424,
-      "grad_norm": 0.9482334852218628,
-      "learning_rate": 4.0483255616786776e-05,
-      "loss": 6.4831,
+      "epoch": 0.22658610271903323,
+      "grad_norm": 0.9348500967025757,
+      "learning_rate": 3.869587109768379e-05,
+      "loss": 6.4087,
       "step": 450
     },
     {
-      "epoch": 0.21195421788893598,
-      "grad_norm": 0.9004257321357727,
-      "learning_rate": 3.9423484527342095e-05,
-      "loss": 6.3974,
+      "epoch": 0.25176233635448136,
+      "grad_norm": 0.8273019194602966,
+      "learning_rate": 3.743705941591138e-05,
+      "loss": 6.3114,
       "step": 500
     },
     {
-      "epoch": 0.21195421788893598,
-      "eval_loss": 6.0686774253845215,
-      "eval_runtime": 126.535,
-      "eval_samples_per_second": 15.703,
-      "eval_steps_per_second": 0.988,
+      "epoch": 0.25176233635448136,
+      "eval_loss": 5.968835353851318,
+      "eval_runtime": 41.9731,
+      "eval_samples_per_second": 39.859,
+      "eval_steps_per_second": 2.502,
       "step": 500
     },
     {
-      "epoch": 0.2331496396778296,
-      "grad_norm": 0.8829556703567505,
-      "learning_rate": 3.8363713437897415e-05,
-      "loss": 6.2952,
+      "epoch": 0.2769385699899295,
+      "grad_norm": 0.7640300989151001,
+      "learning_rate": 3.6178247734138974e-05,
+      "loss": 6.2115,
       "step": 550
     },
     {
-      "epoch": 0.2543450614667232,
-      "grad_norm": 0.7846332788467407,
-      "learning_rate": 3.7303942348452734e-05,
-      "loss": 6.216,
+      "epoch": 0.3021148036253776,
+      "grad_norm": 0.8070991635322571,
+      "learning_rate": 3.491943605236657e-05,
+      "loss": 6.1867,
       "step": 600
     },
     {
-      "epoch": 0.2755404832556168,
-      "grad_norm": 0.8392072319984436,
-      "learning_rate": 3.624417125900806e-05,
-      "loss": 6.1427,
+      "epoch": 0.32729103726082576,
+      "grad_norm": 0.7798317074775696,
+      "learning_rate": 3.366062437059416e-05,
+      "loss": 6.0893,
       "step": 650
     },
     {
-      "epoch": 0.29673590504451036,
-      "grad_norm": 0.8008320331573486,
-      "learning_rate": 3.518440016956337e-05,
-      "loss": 6.061,
+      "epoch": 0.35246727089627394,
+      "grad_norm": 0.8209011554718018,
+      "learning_rate": 3.240181268882175e-05,
+      "loss": 6.0416,
       "step": 700
     },
     {
-      "epoch": 0.31793132683340397,
-      "grad_norm": 0.8059436082839966,
-      "learning_rate": 3.41246290801187e-05,
-      "loss": 6.0253,
+      "epoch": 0.3776435045317221,
+      "grad_norm": 0.7711942195892334,
+      "learning_rate": 3.1143001007049346e-05,
+      "loss": 5.9784,
       "step": 750
     },
     {
-      "epoch": 0.3391267486222976,
-      "grad_norm": 0.7888209819793701,
-      "learning_rate": 3.306485799067401e-05,
-      "loss": 5.9739,
+      "epoch": 0.4028197381671702,
+      "grad_norm": 0.8087317943572998,
+      "learning_rate": 2.988418932527694e-05,
+      "loss": 5.9354,
       "step": 800
     },
     {
-      "epoch": 0.3603221704111912,
-      "grad_norm": 0.7676851749420166,
-      "learning_rate": 3.200508690122934e-05,
-      "loss": 5.899,
+      "epoch": 0.42799597180261834,
+      "grad_norm": 0.7595328688621521,
+      "learning_rate": 2.862537764350453e-05,
+      "loss": 5.8544,
       "step": 850
     },
     {
-      "epoch": 0.3815175922000848,
-      "grad_norm": 0.7366964221000671,
-      "learning_rate": 3.094531581178466e-05,
-      "loss": 5.8371,
+      "epoch": 0.45317220543806647,
+      "grad_norm": 0.7424010038375854,
+      "learning_rate": 2.7366565961732126e-05,
+      "loss": 5.8309,
       "step": 900
     },
     {
-      "epoch": 0.4027130139889784,
-      "grad_norm": 0.7427886724472046,
-      "learning_rate": 2.9885544722339974e-05,
-      "loss": 5.8132,
+      "epoch": 0.4783484390735146,
+      "grad_norm": 0.7028313279151917,
+      "learning_rate": 2.610775427995972e-05,
+      "loss": 5.8075,
       "step": 950
     },
     {
-      "epoch": 0.42390843577787196,
-      "grad_norm": 0.7304149270057678,
-      "learning_rate": 2.8825773632895297e-05,
-      "loss": 5.7658,
+      "epoch": 0.5035246727089627,
+      "grad_norm": 0.739640474319458,
+      "learning_rate": 2.4848942598187312e-05,
+      "loss": 5.7741,
       "step": 1000
     },
     {
-      "epoch": 0.42390843577787196,
-      "eval_loss": 5.496740818023682,
-      "eval_runtime": 135.1668,
-      "eval_samples_per_second": 14.7,
-      "eval_steps_per_second": 0.925,
+      "epoch": 0.5035246727089627,
+      "eval_loss": 5.472690582275391,
+      "eval_runtime": 37.0841,
+      "eval_samples_per_second": 45.114,
+      "eval_steps_per_second": 2.831,
       "step": 1000
     },
     {
-      "epoch": 0.44510385756676557,
-      "grad_norm": 0.7103835940361023,
-      "learning_rate": 2.7766002543450613e-05,
-      "loss": 5.7269,
+      "epoch": 0.5287009063444109,
+      "grad_norm": 0.7200352549552917,
+      "learning_rate": 2.3590130916414905e-05,
+      "loss": 5.7262,
       "step": 1050
     },
     {
-      "epoch": 0.4662992793556592,
-      "grad_norm": 0.7117246389389038,
-      "learning_rate": 2.6706231454005936e-05,
-      "loss": 5.6854,
+      "epoch": 0.553877139979859,
+      "grad_norm": 0.7275882959365845,
+      "learning_rate": 2.2331319234642498e-05,
+      "loss": 5.7028,
       "step": 1100
     },
     {
-      "epoch": 0.4874947011445528,
-      "grad_norm": 0.7282190322875977,
-      "learning_rate": 2.5646460364561252e-05,
-      "loss": 5.6579,
+      "epoch": 0.5790533736153072,
+      "grad_norm": 0.7147909998893738,
+      "learning_rate": 2.107250755287009e-05,
+      "loss": 5.6455,
       "step": 1150
     },
     {
-      "epoch": 0.5086901229334464,
-      "grad_norm": 0.7021281719207764,
-      "learning_rate": 2.4586689275116575e-05,
-      "loss": 5.6333,
+      "epoch": 0.6042296072507553,
+      "grad_norm": 0.7415097951889038,
+      "learning_rate": 1.9813695871097685e-05,
+      "loss": 5.6142,
       "step": 1200
     },
     {
-      "epoch": 0.52988554472234,
-      "grad_norm": 0.6991282105445862,
-      "learning_rate": 2.3526918185671895e-05,
-      "loss": 5.5984,
+      "epoch": 0.6294058408862034,
+      "grad_norm": 0.7115822434425354,
+      "learning_rate": 1.8554884189325278e-05,
+      "loss": 5.6208,
       "step": 1250
     },
     {
-      "epoch": 0.5510809665112336,
-      "grad_norm": 0.720184862613678,
-      "learning_rate": 2.2467147096227218e-05,
-      "loss": 5.558,
+      "epoch": 0.6545820745216515,
+      "grad_norm": 0.6943323612213135,
+      "learning_rate": 1.729607250755287e-05,
+      "loss": 5.5773,
       "step": 1300
     },
     {
-      "epoch": 0.5722763883001272,
-      "grad_norm": 0.7032086253166199,
-      "learning_rate": 2.1407376006782537e-05,
-      "loss": 5.5051,
+      "epoch": 0.6797583081570997,
+      "grad_norm": 0.709179699420929,
+      "learning_rate": 1.6037260825780464e-05,
+      "loss": 5.5679,
       "step": 1350
     },
     {
-      "epoch": 0.5934718100890207,
-      "grad_norm": 0.6943219304084778,
-      "learning_rate": 2.0347604917337857e-05,
-      "loss": 5.5072,
+      "epoch": 0.7049345417925479,
+      "grad_norm": 0.7256223559379578,
+      "learning_rate": 1.4778449144008057e-05,
+      "loss": 5.5666,
       "step": 1400
     },
     {
-      "epoch": 0.6146672318779144,
-      "grad_norm": 0.6991058588027954,
-      "learning_rate": 1.9287833827893176e-05,
-      "loss": 5.4875,
+      "epoch": 0.730110775427996,
+      "grad_norm": 0.7237951159477234,
+      "learning_rate": 1.3519637462235652e-05,
+      "loss": 5.5505,
       "step": 1450
     },
     {
-      "epoch": 0.6358626536668079,
-      "grad_norm": 0.6893653273582458,
-      "learning_rate": 1.8228062738448496e-05,
-      "loss": 5.4251,
+      "epoch": 0.7552870090634441,
+      "grad_norm": 0.7216870784759521,
+      "learning_rate": 1.2260825780463244e-05,
+      "loss": 5.4866,
       "step": 1500
     },
     {
-      "epoch": 0.6358626536668079,
-      "eval_loss": 5.19881534576416,
-      "eval_runtime": 137.4297,
-      "eval_samples_per_second": 14.458,
-      "eval_steps_per_second": 0.91,
+      "epoch": 0.7552870090634441,
+      "eval_loss": 5.239852428436279,
+      "eval_runtime": 42.2008,
+      "eval_samples_per_second": 39.644,
+      "eval_steps_per_second": 2.488,
       "step": 1500
     }
   ],
   "logging_steps": 50,
-  "max_steps": 2359,
+  "max_steps": 1986,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 500,

checkpoint-1500/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c366c061dbfe585f916533453390826a1bc5c140fbbd8f7ec764025c35edef63
+oid sha256:fd35ffac2ed4cf9159515c227a2e8bb8761c759f619e17bd96f19d5dd4c854ad
 size 5713

checkpoint-1986/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85902f687be92bb633ac00ea98834201fb24f0e1afc041251a56d5791f5a0842
+size 151392779

checkpoint-1986/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a66f9ba7a90adbbb6b72b315da4574f8eaa1650de9a87b3fec5f9a6417508beb
+size 199234413

checkpoint-1986/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5694aa24e78c35c22a02b03a246e26b2afdfa338640982ad10ec0e2268d72f2
+size 14391

checkpoint-1986/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6e335fdec288f5b20f6955909d7c4c6d70416425ae4ec317c15a5c47669bb2f
+size 1465

checkpoint-1986/source.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88ed79816c7e90edbc6b74752d3b1414571f7c9267da5cf99b1f6ab65f90a669
+size 841867

checkpoint-1986/special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

checkpoint-1986/target.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ab0233e30e2299e6a0a5b49115de67c521574f85f707765f560c3f255542e71
+size 825223

checkpoint-1986/tokenizer_config.json

@@ -0,0 +1,39 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "59810": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "separate_vocabs": false,
+  "source_lang": "ny",
+  "sp_model_kwargs": {},
+  "target_lang": "en",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

checkpoint-1986/trainer_state.json

@@ -0,0 +1,331 @@
+{
+  "best_global_step": 1500,
+  "best_metric": 5.239852428436279,
+  "best_model_checkpoint": "./nyanja_english_warmup\\checkpoint-1500",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1986,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.025176233635448138,
+      "grad_norm": 0.947960615158081,
+      "learning_rate": 4.876636455186304e-05,
+      "loss": 9.5286,
+      "step": 50
+    },
+    {
+      "epoch": 0.050352467270896276,
+      "grad_norm": 1.194724440574646,
+      "learning_rate": 4.7507552870090635e-05,
+      "loss": 8.2179,
+      "step": 100
+    },
+    {
+      "epoch": 0.0755287009063444,
+      "grad_norm": 0.9894101023674011,
+      "learning_rate": 4.624874118831823e-05,
+      "loss": 7.5072,
+      "step": 150
+    },
+    {
+      "epoch": 0.10070493454179255,
+      "grad_norm": 0.9540104269981384,
+      "learning_rate": 4.498992950654582e-05,
+      "loss": 7.1644,
+      "step": 200
+    },
+    {
+      "epoch": 0.12588116817724068,
+      "grad_norm": 1.0262048244476318,
+      "learning_rate": 4.3731117824773415e-05,
+      "loss": 6.9377,
+      "step": 250
+    },
+    {
+      "epoch": 0.1510574018126888,
+      "grad_norm": 0.916906476020813,
+      "learning_rate": 4.2472306143001015e-05,
+      "loss": 6.7447,
+      "step": 300
+    },
+    {
+      "epoch": 0.17623363544813697,
+      "grad_norm": 0.9376256465911865,
+      "learning_rate": 4.12134944612286e-05,
+      "loss": 6.6128,
+      "step": 350
+    },
+    {
+      "epoch": 0.2014098690835851,
+      "grad_norm": 0.8047090768814087,
+      "learning_rate": 3.9954682779456194e-05,
+      "loss": 6.5074,
+      "step": 400
+    },
+    {
+      "epoch": 0.22658610271903323,
+      "grad_norm": 0.9348500967025757,
+      "learning_rate": 3.869587109768379e-05,
+      "loss": 6.4087,
+      "step": 450
+    },
+    {
+      "epoch": 0.25176233635448136,
+      "grad_norm": 0.8273019194602966,
+      "learning_rate": 3.743705941591138e-05,
+      "loss": 6.3114,
+      "step": 500
+    },
+    {
+      "epoch": 0.25176233635448136,
+      "eval_loss": 5.968835353851318,
+      "eval_runtime": 41.9731,
+      "eval_samples_per_second": 39.859,
+      "eval_steps_per_second": 2.502,
+      "step": 500
+    },
+    {
+      "epoch": 0.2769385699899295,
+      "grad_norm": 0.7640300989151001,
+      "learning_rate": 3.6178247734138974e-05,
+      "loss": 6.2115,
+      "step": 550
+    },
+    {
+      "epoch": 0.3021148036253776,
+      "grad_norm": 0.8070991635322571,
+      "learning_rate": 3.491943605236657e-05,
+      "loss": 6.1867,
+      "step": 600
+    },
+    {
+      "epoch": 0.32729103726082576,
+      "grad_norm": 0.7798317074775696,
+      "learning_rate": 3.366062437059416e-05,
+      "loss": 6.0893,
+      "step": 650
+    },
+    {
+      "epoch": 0.35246727089627394,
+      "grad_norm": 0.8209011554718018,
+      "learning_rate": 3.240181268882175e-05,
+      "loss": 6.0416,
+      "step": 700
+    },
+    {
+      "epoch": 0.3776435045317221,
+      "grad_norm": 0.7711942195892334,
+      "learning_rate": 3.1143001007049346e-05,
+      "loss": 5.9784,
+      "step": 750
+    },
+    {
+      "epoch": 0.4028197381671702,
+      "grad_norm": 0.8087317943572998,
+      "learning_rate": 2.988418932527694e-05,
+      "loss": 5.9354,
+      "step": 800
+    },
+    {
+      "epoch": 0.42799597180261834,
+      "grad_norm": 0.7595328688621521,
+      "learning_rate": 2.862537764350453e-05,
+      "loss": 5.8544,
+      "step": 850
+    },
+    {
+      "epoch": 0.45317220543806647,
+      "grad_norm": 0.7424010038375854,
+      "learning_rate": 2.7366565961732126e-05,
+      "loss": 5.8309,
+      "step": 900
+    },
+    {
+      "epoch": 0.4783484390735146,
+      "grad_norm": 0.7028313279151917,
+      "learning_rate": 2.610775427995972e-05,
+      "loss": 5.8075,
+      "step": 950
+    },
+    {
+      "epoch": 0.5035246727089627,
+      "grad_norm": 0.739640474319458,
+      "learning_rate": 2.4848942598187312e-05,
+      "loss": 5.7741,
+      "step": 1000
+    },
+    {
+      "epoch": 0.5035246727089627,
+      "eval_loss": 5.472690582275391,
+      "eval_runtime": 37.0841,
+      "eval_samples_per_second": 45.114,
+      "eval_steps_per_second": 2.831,
+      "step": 1000
+    },
+    {
+      "epoch": 0.5287009063444109,
+      "grad_norm": 0.7200352549552917,
+      "learning_rate": 2.3590130916414905e-05,
+      "loss": 5.7262,
+      "step": 1050
+    },
+    {
+      "epoch": 0.553877139979859,
+      "grad_norm": 0.7275882959365845,
+      "learning_rate": 2.2331319234642498e-05,
+      "loss": 5.7028,
+      "step": 1100
+    },
+    {
+      "epoch": 0.5790533736153072,
+      "grad_norm": 0.7147909998893738,
+      "learning_rate": 2.107250755287009e-05,
+      "loss": 5.6455,
+      "step": 1150
+    },
+    {
+      "epoch": 0.6042296072507553,
+      "grad_norm": 0.7415097951889038,
+      "learning_rate": 1.9813695871097685e-05,
+      "loss": 5.6142,
+      "step": 1200
+    },
+    {
+      "epoch": 0.6294058408862034,
+      "grad_norm": 0.7115822434425354,
+      "learning_rate": 1.8554884189325278e-05,
+      "loss": 5.6208,
+      "step": 1250
+    },
+    {
+      "epoch": 0.6545820745216515,
+      "grad_norm": 0.6943323612213135,
+      "learning_rate": 1.729607250755287e-05,
+      "loss": 5.5773,
+      "step": 1300
+    },
+    {
+      "epoch": 0.6797583081570997,
+      "grad_norm": 0.709179699420929,
+      "learning_rate": 1.6037260825780464e-05,
+      "loss": 5.5679,
+      "step": 1350
+    },
+    {
+      "epoch": 0.7049345417925479,
+      "grad_norm": 0.7256223559379578,
+      "learning_rate": 1.4778449144008057e-05,
+      "loss": 5.5666,
+      "step": 1400
+    },
+    {
+      "epoch": 0.730110775427996,
+      "grad_norm": 0.7237951159477234,
+      "learning_rate": 1.3519637462235652e-05,
+      "loss": 5.5505,
+      "step": 1450
+    },
+    {
+      "epoch": 0.7552870090634441,
+      "grad_norm": 0.7216870784759521,
+      "learning_rate": 1.2260825780463244e-05,
+      "loss": 5.4866,
+      "step": 1500
+    },
+    {
+      "epoch": 0.7552870090634441,
+      "eval_loss": 5.239852428436279,
+      "eval_runtime": 42.2008,
+      "eval_samples_per_second": 39.644,
+      "eval_steps_per_second": 2.488,
+      "step": 1500
+    },
+    {
+      "epoch": 0.7804632426988922,
+      "grad_norm": 0.7159505486488342,
+      "learning_rate": 1.1002014098690837e-05,
+      "loss": 5.4953,
+      "step": 1550
+    },
+    {
+      "epoch": 0.8056394763343404,
+      "grad_norm": 0.6942981481552124,
+      "learning_rate": 9.743202416918428e-06,
+      "loss": 5.47,
+      "step": 1600
+    },
+    {
+      "epoch": 0.8308157099697885,
+      "grad_norm": 0.6944827437400818,
+      "learning_rate": 8.484390735146023e-06,
+      "loss": 5.4747,
+      "step": 1650
+    },
+    {
+      "epoch": 0.8559919436052367,
+      "grad_norm": 0.6906715631484985,
+      "learning_rate": 7.225579053373615e-06,
+      "loss": 5.4678,
+      "step": 1700
+    },
+    {
+      "epoch": 0.8811681772406847,
+      "grad_norm": 0.6964088082313538,
+      "learning_rate": 5.966767371601209e-06,
+      "loss": 5.4578,
+      "step": 1750
+    },
+    {
+      "epoch": 0.9063444108761329,
+      "grad_norm": 0.6903862357139587,
+      "learning_rate": 4.7079556898288016e-06,
+      "loss": 5.4521,
+      "step": 1800
+    },
+    {
+      "epoch": 0.9315206445115811,
+      "grad_norm": 0.663235604763031,
+      "learning_rate": 3.449144008056395e-06,
+      "loss": 5.4358,
+      "step": 1850
+    },
+    {
+      "epoch": 0.9566968781470292,
+      "grad_norm": 0.8237895965576172,
+      "learning_rate": 2.1903323262839883e-06,
+      "loss": 5.4173,
+      "step": 1900
+    },
+    {
+      "epoch": 0.9818731117824774,
+      "grad_norm": 0.6885905265808105,
+      "learning_rate": 9.31520644511581e-07,
+      "loss": 5.4231,
+      "step": 1950
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 1986,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1986/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd35ffac2ed4cf9159515c227a2e8bb8761c759f619e17bd96f19d5dd4c854ad
+size 5713

checkpoint-500/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb120540de0d4e422673f5ff557b00a1cc1031b2792ac584caf93eb72ab6ede4
+oid sha256:9745d97b78ceff16ed4689c2fc51e5f355b5e5eb2698f609c767d75a2844f230
 size 151392779

checkpoint-500/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7edde203e44c47ba81805d845ffdab57301cfa055bfbebfb927f62501090c997
+oid sha256:ca409ad8e52fff5c20c44e8a2f413510d9bec8f2193f0b64bd95861a7bb80ec1
 size 199234413

checkpoint-500/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:899ed61d1bca246dbe286c3ac01e3c0e09b5ca73dcdb1402eef3d835bc88ecbc
+oid sha256:d040fa084e8dd5f024209465e525c8f2ec894da956a0bcfb8f5f69e53ce7e10b
 size 14391

checkpoint-500/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bf55d9a26185cfe3861b3feb3c039bdb7a547a880307d98819ee5978defe894
+oid sha256:d57066d33512362b2d3ef350be8b1155fc425e02c5fff265f6a93215abdc36db
 size 1465

checkpoint-500/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_global_step": 500,
-  "best_metric": 6.0686774253845215,
+  "best_metric": 5.968835353851318,
   "best_model_checkpoint": "./nyanja_english_warmup\\checkpoint-500",
-  "epoch": 0.21195421788893598,
+  "epoch": 0.25176233635448136,
   "eval_steps": 500,
   "global_step": 500,
   "is_hyper_param_search": false,
@@ -10,86 +10,86 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.0211954217888936,
-      "grad_norm": 1.1472082138061523,
-      "learning_rate": 4.896142433234421e-05,
-      "loss": 9.5805,
+      "epoch": 0.025176233635448138,
+      "grad_norm": 0.947960615158081,
+      "learning_rate": 4.876636455186304e-05,
+      "loss": 9.5286,
       "step": 50
     },
     {
-      "epoch": 0.0423908435777872,
-      "grad_norm": 1.2479043006896973,
-      "learning_rate": 4.790165324289953e-05,
-      "loss": 8.2283,
+      "epoch": 0.050352467270896276,
+      "grad_norm": 1.194724440574646,
+      "learning_rate": 4.7507552870090635e-05,
+      "loss": 8.2179,
       "step": 100
     },
     {
-      "epoch": 0.0635862653666808,
-      "grad_norm": 1.1807806491851807,
-      "learning_rate": 4.684188215345486e-05,
-      "loss": 7.6907,
+      "epoch": 0.0755287009063444,
+      "grad_norm": 0.9894101023674011,
+      "learning_rate": 4.624874118831823e-05,
+      "loss": 7.5072,
       "step": 150
     },
     {
-      "epoch": 0.0847816871555744,
-      "grad_norm": 1.0857632160186768,
-      "learning_rate": 4.578211106401017e-05,
-      "loss": 7.3068,
+      "epoch": 0.10070493454179255,
+      "grad_norm": 0.9540104269981384,
+      "learning_rate": 4.498992950654582e-05,
+      "loss": 7.1644,
       "step": 200
     },
     {
-      "epoch": 0.10597710894446799,
-      "grad_norm": 1.0846374034881592,
-      "learning_rate": 4.47223399745655e-05,
-      "loss": 7.0734,
+      "epoch": 0.12588116817724068,
+      "grad_norm": 1.0262048244476318,
+      "learning_rate": 4.3731117824773415e-05,
+      "loss": 6.9377,
       "step": 250
     },
     {
-      "epoch": 0.1271725307333616,
-      "grad_norm": 0.9803574681282043,
-      "learning_rate": 4.366256888512081e-05,
-      "loss": 6.8886,
+      "epoch": 0.1510574018126888,
+      "grad_norm": 0.916906476020813,
+      "learning_rate": 4.2472306143001015e-05,
+      "loss": 6.7447,
       "step": 300
     },
     {
-      "epoch": 0.14836795252225518,
-      "grad_norm": 1.0538763999938965,
-      "learning_rate": 4.260279779567614e-05,
-      "loss": 6.7217,
+      "epoch": 0.17623363544813697,
+      "grad_norm": 0.9376256465911865,
+      "learning_rate": 4.12134944612286e-05,
+      "loss": 6.6128,
       "step": 350
     },
     {
-      "epoch": 0.1695633743111488,
-      "grad_norm": 0.9296303987503052,
-      "learning_rate": 4.1543026706231456e-05,
-      "loss": 6.5976,
+      "epoch": 0.2014098690835851,
+      "grad_norm": 0.8047090768814087,
+      "learning_rate": 3.9954682779456194e-05,
+      "loss": 6.5074,
       "step": 400
     },
     {
-      "epoch": 0.1907587961000424,
-      "grad_norm": 0.9482334852218628,
-      "learning_rate": 4.0483255616786776e-05,
-      "loss": 6.4831,
+      "epoch": 0.22658610271903323,
+      "grad_norm": 0.9348500967025757,
+      "learning_rate": 3.869587109768379e-05,
+      "loss": 6.4087,
       "step": 450
     },
     {
-      "epoch": 0.21195421788893598,
-      "grad_norm": 0.9004257321357727,
-      "learning_rate": 3.9423484527342095e-05,
-      "loss": 6.3974,
+      "epoch": 0.25176233635448136,
+      "grad_norm": 0.8273019194602966,
+      "learning_rate": 3.743705941591138e-05,
+      "loss": 6.3114,
       "step": 500
     },
     {
-      "epoch": 0.21195421788893598,
-      "eval_loss": 6.0686774253845215,
-      "eval_runtime": 126.535,
-      "eval_samples_per_second": 15.703,
-      "eval_steps_per_second": 0.988,
+      "epoch": 0.25176233635448136,
+      "eval_loss": 5.968835353851318,
+      "eval_runtime": 41.9731,
+      "eval_samples_per_second": 39.859,
+      "eval_steps_per_second": 2.502,
       "step": 500
     }
   ],
   "logging_steps": 50,
-  "max_steps": 2359,
+  "max_steps": 1986,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 500,

checkpoint-500/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c366c061dbfe585f916533453390826a1bc5c140fbbd8f7ec764025c35edef63
+oid sha256:fd35ffac2ed4cf9159515c227a2e8bb8761c759f619e17bd96f19d5dd4c854ad
 size 5713

config.json

@@ -12,7 +12,7 @@
   "bos_token_id": 0,
   "classif_dropout": 0.0,
   "classifier_dropout": 0.0,
-  "corpus_size": 37738,
+  "corpus_size": 31768,
   "d_model": 512,
   "dataset_type": "monolingual_nyanja",
   "decoder_attention_heads": 8,
@@ -27,8 +27,8 @@
   "encoder_layerdrop": 0.0,
   "encoder_layers": 6,
   "eos_token_id": 0,
-  "final_training_loss": 5.935693934086068,
-  "final_validation_loss": 5.05344295501709,
+  "final_training_loss": 6.0598699871266835,
+  "final_validation_loss": 5.239852428436279,
   "forced_eos_token_id": 0,
   "id2label": {
     "0": "LABEL_0",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1611ef4b32d291c0b93f0a396d87da12a77df421167ffe92d813a583d2dc3b9c
+oid sha256:bb0a24fd315411070f2040c48bc2558a9598a57ca02ff60dc9fe44048eba942a
 size 299315212