Upload folder using huggingface_hub

.gitattributes

@@ -102,3 +102,4 @@ checkpoints-v1.0c-discrete-condition/checkpoint-16384/eval_state.json filter=lfs
 checkpoints-v1.0c-discrete-condition/checkpoint-21651/eval_state.json filter=lfs diff=lfs merge=lfs -text
 checkpoints-v1.0d-discrete-condition/checkpoint-13312/eval_state.json filter=lfs diff=lfs merge=lfs -text
 checkpoints-v1.0d-discrete-condition/checkpoint-21651/eval_state.json filter=lfs diff=lfs merge=lfs -text
+checkpoints-v1.0e-discrete-condition/checkpoint-15360/eval_state.json filter=lfs diff=lfs merge=lfs -text

checkpoints-v1.0e-discrete-condition/checkpoint-15360/eval_state.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:135ff36ca20768f5f55e20b6b6181143d7e4153f8bff4ff797f92e73e8b8a2ca
+size 43484442

checkpoints-v1.0e-discrete-condition/checkpoint-15360/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77c690d4faea95b1360124fc16c4c6b2883f62f267451ddcf4c98e98b480e3c0
+size 15210032

checkpoints-v1.0e-discrete-condition/checkpoint-15360/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ae52db265d2714a784ea10a08f18546049eb5b7cc9268129db1df1650f7ad9e
+size 13675339

checkpoints-v1.0e-discrete-condition/checkpoint-15360/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53455c70faa2bf055eda61803d302a7fdaf1fa4ae357458116ef073b7d755303
+size 14645

checkpoints-v1.0e-discrete-condition/checkpoint-15360/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23e550e91327fcb00062db28c5f6f87f90bb827897429e5eb03f30c499964d03
+size 1383

checkpoints-v1.0e-discrete-condition/checkpoint-15360/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73b7518420a541537ada4d348aaec8bae1a30b4c2513f08dc3817ea0a09a1265
+size 1465

checkpoints-v1.0e-discrete-condition/checkpoint-15360/trainer_state.json

@@ -0,0 +1,739 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.709436053761951,
+  "eval_steps": 1024,
+  "global_step": 15360,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.011823934229365849,
+      "grad_norm": 0.0569785013794899,
+      "learning_rate": 0.000498046875,
+      "loss": 0.2929760813713074,
+      "step": 256
+    },
+    {
+      "epoch": 0.023647868458731697,
+      "grad_norm": 0.0866856649518013,
+      "learning_rate": 0.000998046875,
+      "loss": 0.2504822015762329,
+      "step": 512
+    },
+    {
+      "epoch": 0.03547180268809755,
+      "grad_norm": 0.13940005004405975,
+      "learning_rate": 0.000999640996023194,
+      "loss": 0.19717276096343994,
+      "step": 768
+    },
+    {
+      "epoch": 0.047295736917463395,
+      "grad_norm": 0.14197291433811188,
+      "learning_rate": 0.0009985588674043958,
+      "loss": 0.16308173537254333,
+      "step": 1024
+    },
+    {
+      "epoch": 0.047295736917463395,
+      "eval_bleu": 0.0011714375896648113,
+      "eval_cos_loss": 0.338739567831771,
+      "eval_loss": 0.1511567461232072,
+      "eval_mse_loss": 0.1511567461232072,
+      "step": 1024
+    },
+    {
+      "epoch": 0.047295736917463395,
+      "eval_bleu": 0.0011714375896648113,
+      "eval_cos_loss": 0.338739567831771,
+      "eval_loss": 0.1511567461232072,
+      "eval_mse_loss": 0.1511567461232072,
+      "eval_runtime": 172.2677,
+      "eval_samples_per_second": 162.497,
+      "eval_steps_per_second": 2.543,
+      "step": 1024
+    },
+    {
+      "epoch": 0.05911967114682925,
+      "grad_norm": 0.14103451371192932,
+      "learning_rate": 0.0009967551747861387,
+      "loss": 0.14320890605449677,
+      "step": 1280
+    },
+    {
+      "epoch": 0.0709436053761951,
+      "grad_norm": 0.09702787548303604,
+      "learning_rate": 0.000994232528651847,
+      "loss": 0.13121198117733002,
+      "step": 1536
+    },
+    {
+      "epoch": 0.08276753960556095,
+      "grad_norm": 0.14316639304161072,
+      "learning_rate": 0.0009909945800260092,
+      "loss": 0.11884352564811707,
+      "step": 1792
+    },
+    {
+      "epoch": 0.09459147383492679,
+      "grad_norm": 0.16359540820121765,
+      "learning_rate": 0.0009870460151900522,
+      "loss": 0.10863035917282104,
+      "step": 2048
+    },
+    {
+      "epoch": 0.09459147383492679,
+      "eval_bleu": 0.01640269135297576,
+      "eval_cos_loss": 0.2630239495811941,
+      "eval_loss": 0.10520831837433658,
+      "eval_mse_loss": 0.10520831837433658,
+      "step": 2048
+    },
+    {
+      "epoch": 0.09459147383492679,
+      "eval_bleu": 0.01640269135297576,
+      "eval_cos_loss": 0.2630239495811941,
+      "eval_loss": 0.10520831837433658,
+      "eval_mse_loss": 0.10520831837433658,
+      "eval_runtime": 166.1927,
+      "eval_samples_per_second": 168.437,
+      "eval_steps_per_second": 2.635,
+      "step": 2048
+    },
+    {
+      "epoch": 0.10641540806429264,
+      "grad_norm": 0.16606658697128296,
+      "learning_rate": 0.0009823925488998885,
+      "loss": 0.10165824741125107,
+      "step": 2304
+    },
+    {
+      "epoch": 0.1182393422936585,
+      "grad_norm": 0.16988244652748108,
+      "learning_rate": 0.0009770409161149525,
+      "loss": 0.09657377749681473,
+      "step": 2560
+    },
+    {
+      "epoch": 0.13006327652302435,
+      "grad_norm": 0.15539805591106415,
+      "learning_rate": 0.0009709988622506973,
+      "loss": 0.09263481199741364,
+      "step": 2816
+    },
+    {
+      "epoch": 0.1418872107523902,
+      "grad_norm": 0.19379030168056488,
+      "learning_rate": 0.000964275131968659,
+      "loss": 0.08921799808740616,
+      "step": 3072
+    },
+    {
+      "epoch": 0.1418872107523902,
+      "eval_bleu": 0.037097672791643686,
+      "eval_cos_loss": 0.23058595494728654,
+      "eval_loss": 0.08828340418058443,
+      "eval_mse_loss": 0.08828340418058443,
+      "step": 3072
+    },
+    {
+      "epoch": 0.1418872107523902,
+      "eval_bleu": 0.037097672791643686,
+      "eval_cos_loss": 0.23058595494728654,
+      "eval_loss": 0.08828340418058443,
+      "eval_mse_loss": 0.08828340418058443,
+      "eval_runtime": 169.0954,
+      "eval_samples_per_second": 165.546,
+      "eval_steps_per_second": 2.59,
+      "step": 3072
+    },
+    {
+      "epoch": 0.15371114498175603,
+      "grad_norm": 0.19469866156578064,
+      "learning_rate": 0.0009568794565203123,
+      "loss": 0.08570453524589539,
+      "step": 3328
+    },
+    {
+      "epoch": 0.1655350792111219,
+      "grad_norm": 0.13641111552715302,
+      "learning_rate": 0.0009488225396630347,
+      "loss": 0.08265809714794159,
+      "step": 3584
+    },
+    {
+      "epoch": 0.17735901344048774,
+      "grad_norm": 0.20243526995182037,
+      "learning_rate": 0.0009401160421685646,
+      "loss": 0.08029869943857193,
+      "step": 3840
+    },
+    {
+      "epoch": 0.18918294766985358,
+      "grad_norm": 0.20591998100280762,
+      "learning_rate": 0.0009307725649463714,
+      "loss": 0.07793460041284561,
+      "step": 4096
+    },
+    {
+      "epoch": 0.18918294766985358,
+      "eval_bleu": 0.055271730295598016,
+      "eval_cos_loss": 0.20533766668953307,
+      "eval_loss": 0.07763067195744819,
+      "eval_mse_loss": 0.07763067195744819,
+      "step": 4096
+    },
+    {
+      "epoch": 0.18918294766985358,
+      "eval_bleu": 0.055271730295598016,
+      "eval_cos_loss": 0.20533766668953307,
+      "eval_loss": 0.07763067195744819,
+      "eval_mse_loss": 0.07763067195744819,
+      "eval_runtime": 167.722,
+      "eval_samples_per_second": 166.901,
+      "eval_steps_per_second": 2.611,
+      "step": 4096
+    },
+    {
+      "epoch": 0.20100688189921945,
+      "grad_norm": 0.14815625548362732,
+      "learning_rate": 0.0009208056308063659,
+      "loss": 0.07629498839378357,
+      "step": 4352
+    },
+    {
+      "epoch": 0.2128308161285853,
+      "grad_norm": 0.17893894016742706,
+      "learning_rate": 0.0009102296648873445,
+      "loss": 0.0742964819073677,
+      "step": 4608
+    },
+    {
+      "epoch": 0.22465475035795113,
+      "grad_norm": 0.18065278232097626,
+      "learning_rate": 0.0008990599737794927,
+      "loss": 0.07244566082954407,
+      "step": 4864
+    },
+    {
+      "epoch": 0.236478684587317,
+      "grad_norm": 0.18555110692977905,
+      "learning_rate": 0.0008873127233711644,
+      "loss": 0.07109007984399796,
+      "step": 5120
+    },
+    {
+      "epoch": 0.236478684587317,
+      "eval_bleu": 0.07162183673763856,
+      "eval_cos_loss": 0.18833101295853313,
+      "eval_loss": 0.07069546589840493,
+      "eval_mse_loss": 0.07069546589840493,
+      "step": 5120
+    },
+    {
+      "epoch": 0.236478684587317,
+      "eval_bleu": 0.07162183673763856,
+      "eval_cos_loss": 0.18833101295853313,
+      "eval_loss": 0.07069546589840493,
+      "eval_mse_loss": 0.07069546589840493,
+      "eval_runtime": 168.9203,
+      "eval_samples_per_second": 165.717,
+      "eval_steps_per_second": 2.593,
+      "step": 5120
+    },
+    {
+      "epoch": 0.24830261881668284,
+      "grad_norm": 0.21479532122612,
+      "learning_rate": 0.0008750049154520011,
+      "loss": 0.06965314596891403,
+      "step": 5376
+    },
+    {
+      "epoch": 0.2601265530460487,
+      "grad_norm": 0.15884655714035034,
+      "learning_rate": 0.0008621543631062487,
+      "loss": 0.06835002452135086,
+      "step": 5632
+    },
+    {
+      "epoch": 0.27195048727541454,
+      "grad_norm": 0.1491912305355072,
+      "learning_rate": 0.0008487796649318904,
+      "loss": 0.06699136644601822,
+      "step": 5888
+    },
+    {
+      "epoch": 0.2837744215047804,
+      "grad_norm": 0.16656875610351562,
+      "learning_rate": 0.0008349001781229053,
+      "loss": 0.06628481298685074,
+      "step": 6144
+    },
+    {
+      "epoch": 0.2837744215047804,
+      "eval_bleu": 0.08782990447295556,
+      "eval_cos_loss": 0.1761941106556213,
+      "eval_loss": 0.06568186053980703,
+      "eval_mse_loss": 0.06568186053980703,
+      "step": 6144
+    },
+    {
+      "epoch": 0.2837744215047804,
+      "eval_bleu": 0.08782990447295556,
+      "eval_cos_loss": 0.1761941106556213,
+      "eval_loss": 0.06568186053980703,
+      "eval_mse_loss": 0.06568186053980703,
+      "eval_runtime": 167.256,
+      "eval_samples_per_second": 167.366,
+      "eval_steps_per_second": 2.619,
+      "step": 6144
+    },
+    {
+      "epoch": 0.2955983557341462,
+      "grad_norm": 0.18619365990161896,
+      "learning_rate": 0.0008205359904536107,
+      "loss": 0.06507044285535812,
+      "step": 6400
+    },
+    {
+      "epoch": 0.30742228996351206,
+      "grad_norm": 0.15038955211639404,
+      "learning_rate": 0.0008057078912056363,
+      "loss": 0.06429114937782288,
+      "step": 6656
+    },
+    {
+      "epoch": 0.3192462241928779,
+      "grad_norm": 0.136085644364357,
+      "learning_rate": 0.0007904373410796086,
+      "loss": 0.06293655186891556,
+      "step": 6912
+    },
+    {
+      "epoch": 0.3310701584222438,
+      "grad_norm": 0.15249842405319214,
+      "learning_rate": 0.0007747464411350876,
+      "loss": 0.06225278228521347,
+      "step": 7168
+    },
+    {
+      "epoch": 0.3310701584222438,
+      "eval_bleu": 0.10422501320162747,
+      "eval_cos_loss": 0.16745890517076945,
+      "eval_loss": 0.06201160660005051,
+      "eval_mse_loss": 0.06201160660005051,
+      "step": 7168
+    },
+    {
+      "epoch": 0.3310701584222438,
+      "eval_bleu": 0.10422501320162747,
+      "eval_cos_loss": 0.16745890517076945,
+      "eval_loss": 0.06201160660005051,
+      "eval_mse_loss": 0.06201160660005051,
+      "eval_runtime": 169.4308,
+      "eval_samples_per_second": 165.218,
+      "eval_steps_per_second": 2.585,
+      "step": 7168
+    },
+    {
+      "epoch": 0.34289409265160964,
+      "grad_norm": 0.16507746279239655,
+      "learning_rate": 0.000758657900803716,
+      "loss": 0.061575472354888916,
+      "step": 7424
+    },
+    {
+      "epoch": 0.3547180268809755,
+      "grad_norm": 0.14547540247440338,
+      "learning_rate": 0.000742195005021869,
+      "loss": 0.060702890157699585,
+      "step": 7680
+    },
+    {
+      "epoch": 0.3665419611103413,
+      "grad_norm": 0.12704621255397797,
+      "learning_rate": 0.0007253815805303786,
+      "loss": 0.059864386916160583,
+      "step": 7936
+    },
+    {
+      "epoch": 0.37836589533970716,
+      "grad_norm": 0.1420435756444931,
+      "learning_rate": 0.0007082419613901028,
+      "loss": 0.059240467846393585,
+      "step": 8192
+    },
+    {
+      "epoch": 0.37836589533970716,
+      "eval_bleu": 0.12190068004312635,
+      "eval_cos_loss": 0.16049913827278842,
+      "eval_loss": 0.05894200267380775,
+      "eval_mse_loss": 0.05894200267380775,
+      "step": 8192
+    },
+    {
+      "epoch": 0.37836589533970716,
+      "eval_bleu": 0.12190068004312635,
+      "eval_cos_loss": 0.16049913827278842,
+      "eval_loss": 0.05894200267380775,
+      "eval_mse_loss": 0.05894200267380775,
+      "eval_runtime": 170.4747,
+      "eval_samples_per_second": 164.206,
+      "eval_steps_per_second": 2.569,
+      "step": 8192
+    },
+    {
+      "epoch": 0.390189829569073,
+      "grad_norm": 0.11315222084522247,
+      "learning_rate": 0.0006908009537632514,
+      "loss": 0.05864889174699783,
+      "step": 8448
+    },
+    {
+      "epoch": 0.4020137637984389,
+      "grad_norm": 0.14333274960517883,
+      "learning_rate": 0.0006730838000114403,
+      "loss": 0.05799835920333862,
+      "step": 8704
+    },
+    {
+      "epoch": 0.41383769802780473,
+      "grad_norm": 0.15370561182498932,
+      "learning_rate": 0.0006551161421624341,
+      "loss": 0.057285867631435394,
+      "step": 8960
+    },
+    {
+      "epoch": 0.4256616322571706,
+      "grad_norm": 0.12100663036108017,
+      "learning_rate": 0.0006369239847984517,
+      "loss": 0.05648953840136528,
+      "step": 9216
+    },
+    {
+      "epoch": 0.4256616322571706,
+      "eval_bleu": 0.13496230405038226,
+      "eval_cos_loss": 0.15526348454494998,
+      "eval_loss": 0.05676825863381499,
+      "eval_mse_loss": 0.05676825863381499,
+      "step": 9216
+    },
+    {
+      "epoch": 0.4256616322571706,
+      "eval_bleu": 0.13496230405038226,
+      "eval_cos_loss": 0.15526348454494998,
+      "eval_loss": 0.05676825863381499,
+      "eval_mse_loss": 0.05676825863381499,
+      "eval_runtime": 170.2747,
+      "eval_samples_per_second": 164.399,
+      "eval_steps_per_second": 2.572,
+      "step": 9216
+    },
+    {
+      "epoch": 0.4374855664865364,
+      "grad_norm": 0.12870068848133087,
+      "learning_rate": 0.0006185336574197479,
+      "loss": 0.056146688759326935,
+      "step": 9472
+    },
+    {
+      "epoch": 0.44930950071590225,
+      "grad_norm": 0.1489071398973465,
+      "learning_rate": 0.0005999717763379407,
+      "loss": 0.05556228384375572,
+      "step": 9728
+    },
+    {
+      "epoch": 0.4611334349452681,
+      "grad_norm": 0.11909710615873337,
+      "learning_rate": 0.0005812652061542363,
+      "loss": 0.05514912307262421,
+      "step": 9984
+    },
+    {
+      "epoch": 0.472957369174634,
+      "grad_norm": 0.15826211869716644,
+      "learning_rate": 0.0005624410208783071,
+      "loss": 0.05458202585577965,
+      "step": 10240
+    },
+    {
+      "epoch": 0.472957369174634,
+      "eval_bleu": 0.14839972030094115,
+      "eval_cos_loss": 0.1492026079803297,
+      "eval_loss": 0.05424791704608153,
+      "eval_mse_loss": 0.05424791704608153,
+      "step": 10240
+    },
+    {
+      "epoch": 0.472957369174634,
+      "eval_bleu": 0.14839972030094115,
+      "eval_cos_loss": 0.1492026079803297,
+      "eval_loss": 0.05424791704608153,
+      "eval_mse_loss": 0.05424791704608153,
+      "eval_runtime": 172.0235,
+      "eval_samples_per_second": 162.728,
+      "eval_steps_per_second": 2.546,
+      "step": 10240
+    },
+    {
+      "epoch": 0.48478130340399983,
+      "grad_norm": 0.12827685475349426,
+      "learning_rate": 0.0005435264647440881,
+      "loss": 0.05391533672809601,
+      "step": 10496
+    },
+    {
+      "epoch": 0.49660523763336567,
+      "grad_norm": 0.14331956207752228,
+      "learning_rate": 0.000524548912779213,
+      "loss": 0.053478896617889404,
+      "step": 10752
+    },
+    {
+      "epoch": 0.5084291718627315,
+      "grad_norm": 0.11259039491415024,
+      "learning_rate": 0.0005055358311851499,
+      "loss": 0.05310649052262306,
+      "step": 11008
+    },
+    {
+      "epoch": 0.5202531060920974,
+      "grad_norm": 0.11761780083179474,
+      "learning_rate": 0.0004865147375853812,
+      "loss": 0.05254605785012245,
+      "step": 11264
+    },
+    {
+      "epoch": 0.5202531060920974,
+      "eval_bleu": 0.16042218683436996,
+      "eval_cos_loss": 0.14472832799502158,
+      "eval_loss": 0.052395756981552466,
+      "eval_mse_loss": 0.052395756981552466,
+      "step": 11264
+    },
+    {
+      "epoch": 0.5202531060920974,
+      "eval_bleu": 0.16042218683436996,
+      "eval_cos_loss": 0.14472832799502158,
+      "eval_loss": 0.052395756981552466,
+      "eval_mse_loss": 0.052395756981552466,
+      "eval_runtime": 175.7973,
+      "eval_samples_per_second": 159.235,
+      "eval_steps_per_second": 2.492,
+      "step": 11264
+    },
+    {
+      "epoch": 0.5320770403214632,
+      "grad_norm": 0.16084498167037964,
+      "learning_rate": 0.0004675131611991607,
+      "loss": 0.05206044018268585,
+      "step": 11520
+    },
+    {
+      "epoch": 0.5439009745508291,
+      "grad_norm": 0.12781144678592682,
+      "learning_rate": 0.0004485586029984899,
+      "loss": 0.05154161900281906,
+      "step": 11776
+    },
+    {
+      "epoch": 0.5557249087801949,
+      "grad_norm": 0.11860433220863342,
+      "learning_rate": 0.00042967849590597266,
+      "loss": 0.051158737391233444,
+      "step": 12032
+    },
+    {
+      "epoch": 0.5675488430095608,
+      "grad_norm": 0.1226862370967865,
+      "learning_rate": 0.0004109001650911621,
+      "loss": 0.05094496160745621,
+      "step": 12288
+    },
+    {
+      "epoch": 0.5675488430095608,
+      "eval_bleu": 0.17126127820473988,
+      "eval_cos_loss": 0.1419908434628896,
+      "eval_loss": 0.05134654454206495,
+      "eval_mse_loss": 0.05134654454206495,
+      "step": 12288
+    },
+    {
+      "epoch": 0.5675488430095608,
+      "eval_bleu": 0.17126127820473988,
+      "eval_cos_loss": 0.1419908434628896,
+      "eval_loss": 0.05134654454206495,
+      "eval_mse_loss": 0.05134654454206495,
+      "eval_runtime": 176.0149,
+      "eval_samples_per_second": 159.038,
+      "eval_steps_per_second": 2.488,
+      "step": 12288
+    },
+    {
+      "epoch": 0.5793727772389267,
+      "grad_norm": 0.15192070603370667,
+      "learning_rate": 0.0003922507884228551,
+      "loss": 0.0504397489130497,
+      "step": 12544
+    },
+    {
+      "epoch": 0.5911967114682924,
+      "grad_norm": 0.1474185436964035,
+      "learning_rate": 0.00037375735713457723,
+      "loss": 0.05017136037349701,
+      "step": 12800
+    },
+    {
+      "epoch": 0.6030206456976583,
+      "grad_norm": 0.12859590351581573,
+      "learning_rate": 0.00035544663676018276,
+      "loss": 0.049893494695425034,
+      "step": 13056
+    },
+    {
+      "epoch": 0.6148445799270241,
+      "grad_norm": 0.11801755428314209,
+      "learning_rate": 0.00033734512839611255,
+      "loss": 0.04954931512475014,
+      "step": 13312
+    },
+    {
+      "epoch": 0.6148445799270241,
+      "eval_bleu": 0.1800444095839781,
+      "eval_cos_loss": 0.1376905629419845,
+      "eval_loss": 0.04945668337449908,
+      "eval_mse_loss": 0.04945668337449908,
+      "step": 13312
+    },
+    {
+      "epoch": 0.6148445799270241,
+      "eval_bleu": 0.1800444095839781,
+      "eval_cos_loss": 0.1376905629419845,
+      "eval_loss": 0.04945668337449908,
+      "eval_mse_loss": 0.04945668337449908,
+      "eval_runtime": 174.7618,
+      "eval_samples_per_second": 160.178,
+      "eval_steps_per_second": 2.506,
+      "step": 13312
+    },
+    {
+      "epoch": 0.62666851415639,
+      "grad_norm": 0.14720351994037628,
+      "learning_rate": 0.0003194790303463687,
+      "loss": 0.04919987544417381,
+      "step": 13568
+    },
+    {
+      "epoch": 0.6384924483857558,
+      "grad_norm": 0.10936211049556732,
+      "learning_rate": 0.00030187420020572406,
+      "loss": 0.048761751502752304,
+      "step": 13824
+    },
+    {
+      "epoch": 0.6503163826151217,
+      "grad_norm": 0.10678113251924515,
+      "learning_rate": 0.00028455611743603626,
+      "loss": 0.04845006763935089,
+      "step": 14080
+    },
+    {
+      "epoch": 0.6621403168444876,
+      "grad_norm": 0.12803645431995392,
+      "learning_rate": 0.0002675498464898373,
+      "loss": 0.04825146496295929,
+      "step": 14336
+    },
+    {
+      "epoch": 0.6621403168444876,
+      "eval_bleu": 0.19045355889644444,
+      "eval_cos_loss": 0.13523258731517618,
+      "eval_loss": 0.04841839778130729,
+      "eval_mse_loss": 0.04841839778130729,
+      "step": 14336
+    },
+    {
+      "epoch": 0.6621403168444876,
+      "eval_bleu": 0.19045355889644444,
+      "eval_cos_loss": 0.13523258731517618,
+      "eval_loss": 0.04841839778130729,
+      "eval_mse_loss": 0.04841839778130729,
+      "eval_runtime": 175.5444,
+      "eval_samples_per_second": 159.464,
+      "eval_steps_per_second": 2.495,
+      "step": 14336
+    },
+    {
+      "epoch": 0.6739642510738534,
+      "grad_norm": 0.09000962227582932,
+      "learning_rate": 0.0002508800005345623,
+      "loss": 0.04815007746219635,
+      "step": 14592
+    },
+    {
+      "epoch": 0.6857881853032193,
+      "grad_norm": 0.11037364602088928,
+      "learning_rate": 0.00023457070582992562,
+      "loss": 0.04773465543985367,
+      "step": 14848
+    },
+    {
+      "epoch": 0.6976121195325851,
+      "grad_norm": 0.11829054355621338,
+      "learning_rate": 0.00021864556680999692,
+      "loss": 0.04770495742559433,
+      "step": 15104
+    },
+    {
+      "epoch": 0.709436053761951,
+      "grad_norm": 0.12001141160726547,
+      "learning_rate": 0.0002031276319205152,
+      "loss": 0.0472663938999176,
+      "step": 15360
+    },
+    {
+      "epoch": 0.709436053761951,
+      "eval_bleu": 0.19616135450927907,
+      "eval_cos_loss": 0.13301836342027742,
+      "eval_loss": 0.04749709167879194,
+      "eval_mse_loss": 0.04749709167879194,
+      "step": 15360
+    },
+    {
+      "epoch": 0.709436053761951,
+      "eval_bleu": 0.19616135450927907,
+      "eval_cos_loss": 0.13301836342027742,
+      "eval_loss": 0.04749709167879194,
+      "eval_mse_loss": 0.04749709167879194,
+      "eval_runtime": 171.0818,
+      "eval_samples_per_second": 163.623,
+      "eval_steps_per_second": 2.56,
+      "step": 15360
+    }
+  ],
+  "logging_steps": 256,
+  "max_steps": 21651,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 1024,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints-v1.0e-discrete-condition/checkpoint-15360/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f63a8a711fb280c6320e95476c532b75c862f31d6a218a0d05079e32411a5ae1
+size 5201