Model save

README.md

@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-7b-dpo-full
 
-This model was trained from scratch on the None dataset.
+This model was trained from scratch on an unknown dataset.
 
 ## Model description
 
@@ -52,7 +52,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- Transformers 4.41.1
+- Transformers 4.39.3
 - Pytorch 2.1.2+cu118
-- Datasets 2.16.1
-- Tokenizers 0.19.1
+- Datasets 2.19.1
+- Tokenizers 0.15.2

all_results.json

@@ -1,9 +1,8 @@
 {
-    "epoch": 0.9980806142034548,
-    "total_flos": 0.0,
-    "train_loss": 0.2947830175742125,
-    "train_runtime": 6391.2384,
+    "epoch": 1.0,
+    "train_loss": 0.19850983711389394,
+    "train_runtime": 5891.9709,
     "train_samples": 50000,
-    "train_samples_per_second": 7.823,
-    "train_steps_per_second": 0.061
+    "train_samples_per_second": 8.486,
+    "train_steps_per_second": 0.066
 }

config.json

@@ -20,7 +20,7 @@
   "sliding_window": 4096,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.41.1",
+  "transformers_version": "4.39.3",
   "use_cache": false,
   "vocab_size": 32000
 }

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "transformers_version": "4.41.1"
+  "transformers_version": "4.39.3"
 }

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c879c438925d1255e6bb62e95443c7b9be4c54b554c5661246d16917a1112924
+oid sha256:54769bdbecf4786a63d2238e3ee62adeef4bf0b3137da2a6064f572ac502b5ba
 size 4943162336

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c2dd72f78dcf556e6528d803c589c6105e3a837532325d354a805e21db0d419
+oid sha256:afed13f2fb9196ba7a439af3fcd67e27fa09aae99b793638e19395a092d9769c
 size 4999819336

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a55211455915c4c6cc8aa0486c54d0d029dd088874b044c923db3b11eb37773
+oid sha256:6c7933f77356443d56777d8b1904dbda1adb1d3912d8ea0bbc0ed445713ff355
 size 4540516344

runs/Jun22_03-50-02_n136-112-146/events.out.tfevents.1719000110.n136-112-146.3291321.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c93e77188d1967c15a538723893f88d78684fcc7088c9505aba293d7dd533805
-size 26098
+oid sha256:dbb5b59084b4db0c5f28e66e720f82f6617c2874d0658cfef0fd6b7c4dfc8342
+size 32644

tokenizer.json

@@ -134,7 +134,6 @@
     "end_of_word_suffix": null,
     "fuse_unk": true,
     "byte_fallback": true,
-    "ignore_merges": false,
     "vocab": {
       "<unk>": 0,
       "<s>": 1,

train_results.json

@@ -1,9 +1,8 @@
 {
-    "epoch": 0.9980806142034548,
-    "total_flos": 0.0,
-    "train_loss": 0.2947830175742125,
-    "train_runtime": 6391.2384,
+    "epoch": 1.0,
+    "train_loss": 0.19850983711389394,
+    "train_runtime": 5891.9709,
     "train_samples": 50000,
-    "train_samples_per_second": 7.823,
-    "train_steps_per_second": 0.061
+    "train_samples_per_second": 8.486,
+    "train_steps_per_second": 0.066
 }

trainer_state.json

@@ -9,13 +9,13 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.0025591810620601407,
-      "grad_norm": 709.6319834867974,
+      "epoch": 0.0,
+      "grad_norm": 747.1989420753074,
       "learning_rate": 5.128205128205128e-09,
-      "logits/chosen": -2.5583817958831787,
-      "logits/rejected": -2.4487552642822266,
+      "logits/chosen": -2.5617921352386475,
+      "logits/rejected": -2.415619373321533,
       "logps/chosen": -258.1644592285156,
-      "logps/rejected": -216.25729370117188,
+      "logps/rejected": -191.65736389160156,
       "loss": 0.6931,
       "rewards/accuracies": 0.0,
       "rewards/chosen": 0.0,
@@ -24,598 +24,598 @@
       "step": 1
     },
     {
-      "epoch": 0.025591810620601407,
-      "grad_norm": 670.9725237886468,
+      "epoch": 0.03,
+      "grad_norm": 772.6555707154646,
       "learning_rate": 5.128205128205127e-08,
-      "logits/chosen": -2.606004238128662,
-      "logits/rejected": -2.553126573562622,
-      "logps/chosen": -267.5910339355469,
-      "logps/rejected": -217.67140197753906,
-      "loss": 0.6976,
-      "rewards/accuracies": 0.4513888955116272,
-      "rewards/chosen": -0.013270225375890732,
-      "rewards/margins": 0.0032119054812937975,
-      "rewards/rejected": -0.01648213155567646,
+      "logits/chosen": -2.610959053039551,
+      "logits/rejected": -2.52398681640625,
+      "logps/chosen": -267.3009948730469,
+      "logps/rejected": -198.18966674804688,
+      "loss": 0.7062,
+      "rewards/accuracies": 0.4444444477558136,
+      "rewards/chosen": -0.006153374910354614,
+      "rewards/margins": -0.0059446971863508224,
+      "rewards/rejected": -0.0002086775202769786,
       "step": 10
     },
     {
-      "epoch": 0.05118362124120281,
-      "grad_norm": 590.5735450897452,
+      "epoch": 0.05,
+      "grad_norm": 568.2747762208306,
       "learning_rate": 1.0256410256410255e-07,
-      "logits/chosen": -2.6245453357696533,
-      "logits/rejected": -2.562206745147705,
-      "logps/chosen": -261.142333984375,
-      "logps/rejected": -207.0738067626953,
-      "loss": 0.6676,
-      "rewards/accuracies": 0.6312500238418579,
-      "rewards/chosen": 0.08092932403087616,
-      "rewards/margins": 0.09077399969100952,
-      "rewards/rejected": -0.009844672866165638,
+      "logits/chosen": -2.626389980316162,
+      "logits/rejected": -2.5251834392547607,
+      "logps/chosen": -261.1226501464844,
+      "logps/rejected": -198.20663452148438,
+      "loss": 0.6286,
+      "rewards/accuracies": 0.643750011920929,
+      "rewards/chosen": 0.1013670414686203,
+      "rewards/margins": 0.16386722028255463,
+      "rewards/rejected": -0.06250017881393433,
       "step": 20
     },
     {
-      "epoch": 0.07677543186180422,
-      "grad_norm": 644.2505273786248,
+      "epoch": 0.08,
+      "grad_norm": 494.0619878155869,
       "learning_rate": 1.5384615384615385e-07,
-      "logits/chosen": -2.6289420127868652,
-      "logits/rejected": -2.5566790103912354,
-      "logps/chosen": -253.9628143310547,
-      "logps/rejected": -198.890380859375,
-      "loss": 0.5156,
-      "rewards/accuracies": 0.800000011920929,
-      "rewards/chosen": 0.5922147035598755,
-      "rewards/margins": 0.6031575798988342,
-      "rewards/rejected": -0.010942881926894188,
+      "logits/chosen": -2.631648302078247,
+      "logits/rejected": -2.533083915710449,
+      "logps/chosen": -253.81259155273438,
+      "logps/rejected": -194.48611450195312,
+      "loss": 0.4093,
+      "rewards/accuracies": 0.8374999761581421,
+      "rewards/chosen": 0.6733725666999817,
+      "rewards/margins": 0.9389022588729858,
+      "rewards/rejected": -0.2655297815799713,
       "step": 30
     },
     {
-      "epoch": 0.10236724248240563,
-      "grad_norm": 428.1589759637874,
+      "epoch": 0.1,
+      "grad_norm": 479.5871736251968,
       "learning_rate": 1.999959945379852e-07,
-      "logits/chosen": -2.637456178665161,
-      "logits/rejected": -2.5609130859375,
-      "logps/chosen": -247.48666381835938,
-      "logps/rejected": -193.59280395507812,
-      "loss": 0.3866,
-      "rewards/accuracies": 0.8062499761581421,
-      "rewards/chosen": 1.4313427209854126,
-      "rewards/margins": 1.3846019506454468,
-      "rewards/rejected": 0.04674070328474045,
+      "logits/chosen": -2.6485562324523926,
+      "logits/rejected": -2.5283126831054688,
+      "logps/chosen": -247.01113891601562,
+      "logps/rejected": -198.84341430664062,
+      "loss": 0.2427,
+      "rewards/accuracies": 0.8812500238418579,
+      "rewards/chosen": 1.6728582382202148,
+      "rewards/margins": 2.513617753982544,
+      "rewards/rejected": -0.84075927734375,
       "step": 40
     },
     {
-      "epoch": 0.12795905310300704,
-      "grad_norm": 366.0325785868742,
+      "epoch": 0.13,
+      "grad_norm": 268.0648126747043,
       "learning_rate": 1.9951572723309917e-07,
-      "logits/chosen": -2.684983730316162,
-      "logits/rejected": -2.618076801300049,
-      "logps/chosen": -262.3794250488281,
-      "logps/rejected": -204.0382843017578,
-      "loss": 0.3488,
-      "rewards/accuracies": 0.8500000238418579,
-      "rewards/chosen": 2.9288697242736816,
-      "rewards/margins": 2.3735203742980957,
-      "rewards/rejected": 0.5553494095802307,
+      "logits/chosen": -2.701251983642578,
+      "logits/rejected": -2.596193790435791,
+      "logps/chosen": -260.8350830078125,
+      "logps/rejected": -204.7702178955078,
+      "loss": 0.2435,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": 3.198915481567383,
+      "rewards/margins": 4.101343631744385,
+      "rewards/rejected": -0.902428150177002,
       "step": 50
     },
     {
-      "epoch": 0.15355086372360843,
-      "grad_norm": 375.0458504104559,
+      "epoch": 0.15,
+      "grad_norm": 321.17307426963725,
       "learning_rate": 1.9823877374156647e-07,
-      "logits/chosen": -2.669403553009033,
-      "logits/rejected": -2.6018548011779785,
-      "logps/chosen": -262.41534423828125,
-      "logps/rejected": -206.5387420654297,
-      "loss": 0.311,
-      "rewards/accuracies": 0.824999988079071,
-      "rewards/chosen": 3.2061855792999268,
-      "rewards/margins": 2.446310520172119,
-      "rewards/rejected": 0.7598745822906494,
+      "logits/chosen": -2.6826422214508057,
+      "logits/rejected": -2.5699238777160645,
+      "logps/chosen": -260.90740966796875,
+      "logps/rejected": -190.84542846679688,
+      "loss": 0.2062,
+      "rewards/accuracies": 0.918749988079071,
+      "rewards/chosen": 3.89800763130188,
+      "rewards/margins": 4.676665306091309,
+      "rewards/rejected": -0.7786582112312317,
       "step": 60
     },
     {
-      "epoch": 0.17914267434420986,
-      "grad_norm": 371.9136724850062,
+      "epoch": 0.18,
+      "grad_norm": 341.66511985659804,
       "learning_rate": 1.9617535688178958e-07,
-      "logits/chosen": -2.6535415649414062,
-      "logits/rejected": -2.590367078781128,
-      "logps/chosen": -290.74871826171875,
-      "logps/rejected": -224.1929168701172,
-      "loss": 0.3051,
-      "rewards/accuracies": 0.875,
-      "rewards/chosen": 3.5809733867645264,
-      "rewards/margins": 3.0821049213409424,
-      "rewards/rejected": 0.4988683760166168,
+      "logits/chosen": -2.664588451385498,
+      "logits/rejected": -2.5252487659454346,
+      "logps/chosen": -289.1197204589844,
+      "logps/rejected": -219.9818572998047,
+      "loss": 0.1912,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": 4.399308204650879,
+      "rewards/margins": 5.727428436279297,
+      "rewards/rejected": -1.3281205892562866,
       "step": 70
     },
     {
-      "epoch": 0.20473448496481125,
-      "grad_norm": 381.95411975681657,
+      "epoch": 0.2,
+      "grad_norm": 345.50558992425647,
       "learning_rate": 1.9334199560765839e-07,
-      "logits/chosen": -2.6085634231567383,
-      "logits/rejected": -2.5423429012298584,
-      "logps/chosen": -260.9337463378906,
-      "logps/rejected": -203.12725830078125,
-      "loss": 0.2569,
-      "rewards/accuracies": 0.8687499761581421,
-      "rewards/chosen": 3.3122222423553467,
-      "rewards/margins": 3.3377063274383545,
-      "rewards/rejected": -0.025484371930360794,
+      "logits/chosen": -2.612795352935791,
+      "logits/rejected": -2.4848904609680176,
+      "logps/chosen": -260.74462890625,
+      "logps/rejected": -209.5861053466797,
+      "loss": 0.1745,
+      "rewards/accuracies": 0.9125000238418579,
+      "rewards/chosen": 3.798893690109253,
+      "rewards/margins": 5.829946994781494,
+      "rewards/rejected": -2.031052827835083,
       "step": 80
     },
     {
-      "epoch": 0.23032629558541268,
-      "grad_norm": 331.9831865016541,
+      "epoch": 0.23,
+      "grad_norm": 623.1485221220804,
       "learning_rate": 1.897613727639014e-07,
-      "logits/chosen": -2.610903739929199,
-      "logits/rejected": -2.556959867477417,
-      "logps/chosen": -256.61138916015625,
-      "logps/rejected": -215.09701538085938,
-      "loss": 0.2658,
-      "rewards/accuracies": 0.8687499761581421,
-      "rewards/chosen": 2.5669326782226562,
-      "rewards/margins": 2.867710590362549,
-      "rewards/rejected": -0.3007778227329254,
+      "logits/chosen": -2.6385045051574707,
+      "logits/rejected": -2.5179295539855957,
+      "logps/chosen": -254.0596160888672,
+      "logps/rejected": -191.18374633789062,
+      "loss": 0.1808,
+      "rewards/accuracies": 0.9125000238418579,
+      "rewards/chosen": 3.131239414215088,
+      "rewards/margins": 5.626199722290039,
+      "rewards/rejected": -2.494959831237793,
       "step": 90
     },
     {
-      "epoch": 0.2559181062060141,
-      "grad_norm": 634.1345493995642,
+      "epoch": 0.26,
+      "grad_norm": 253.52286816658938,
       "learning_rate": 1.8546215349560202e-07,
-      "logits/chosen": -2.6384997367858887,
-      "logits/rejected": -2.563520908355713,
-      "logps/chosen": -236.5784912109375,
-      "logps/rejected": -199.6844940185547,
-      "loss": 0.3117,
-      "rewards/accuracies": 0.8500000238418579,
-      "rewards/chosen": 2.7952113151550293,
-      "rewards/margins": 3.302074909210205,
-      "rewards/rejected": -0.5068637132644653,
+      "logits/chosen": -2.6612112522125244,
+      "logits/rejected": -2.533451795578003,
+      "logps/chosen": -235.6942138671875,
+      "logps/rejected": -196.51657104492188,
+      "loss": 0.1619,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": 3.5456454753875732,
+      "rewards/margins": 5.960389614105225,
+      "rewards/rejected": -2.4147439002990723,
       "step": 100
     },
     {
-      "epoch": 0.28150991682661547,
-      "grad_norm": 319.85079714910466,
+      "epoch": 0.28,
+      "grad_norm": 266.28422663795834,
       "learning_rate": 1.8047875576562553e-07,
-      "logits/chosen": -2.630192518234253,
-      "logits/rejected": -2.549891710281372,
-      "logps/chosen": -258.26971435546875,
-      "logps/rejected": -208.4285430908203,
-      "loss": 0.282,
-      "rewards/accuracies": 0.862500011920929,
-      "rewards/chosen": 3.702361583709717,
-      "rewards/margins": 3.704643726348877,
-      "rewards/rejected": -0.002281466033309698,
+      "logits/chosen": -2.6504344940185547,
+      "logits/rejected": -2.52449369430542,
+      "logps/chosen": -254.90847778320312,
+      "logps/rejected": -191.41806030273438,
+      "loss": 0.1662,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": 4.884920597076416,
+      "rewards/margins": 6.528225898742676,
+      "rewards/rejected": -1.6433048248291016,
       "step": 110
     },
     {
-      "epoch": 0.30710172744721687,
-      "grad_norm": 376.18943633320504,
+      "epoch": 0.31,
+      "grad_norm": 248.5491633368023,
       "learning_rate": 1.748510748171101e-07,
-      "logits/chosen": -2.6130287647247314,
-      "logits/rejected": -2.543454170227051,
-      "logps/chosen": -262.194580078125,
-      "logps/rejected": -206.72488403320312,
-      "loss": 0.2802,
-      "rewards/accuracies": 0.8812500238418579,
-      "rewards/chosen": 3.633894443511963,
-      "rewards/margins": 3.8131375312805176,
-      "rewards/rejected": -0.17924347519874573,
+      "logits/chosen": -2.626223564147949,
+      "logits/rejected": -2.531078815460205,
+      "logps/chosen": -258.3885803222656,
+      "logps/rejected": -210.59378051757812,
+      "loss": 0.1688,
+      "rewards/accuracies": 0.9437500238418579,
+      "rewards/chosen": 4.675450801849365,
+      "rewards/margins": 6.811753273010254,
+      "rewards/rejected": -2.1363017559051514,
       "step": 120
     },
     {
-      "epoch": 0.3326935380678183,
-      "grad_norm": 258.08224292776333,
+      "epoch": 0.33,
+      "grad_norm": 219.45295559501494,
       "learning_rate": 1.6862416378687336e-07,
-      "logits/chosen": -2.587902069091797,
-      "logits/rejected": -2.5218377113342285,
-      "logps/chosen": -250.2627410888672,
-      "logps/rejected": -193.98731994628906,
-      "loss": 0.2644,
-      "rewards/accuracies": 0.856249988079071,
-      "rewards/chosen": 3.5202510356903076,
-      "rewards/margins": 3.647292375564575,
-      "rewards/rejected": -0.12704159319400787,
+      "logits/chosen": -2.6003150939941406,
+      "logits/rejected": -2.465550661087036,
+      "logps/chosen": -249.7939910888672,
+      "logps/rejected": -186.2041778564453,
+      "loss": 0.1744,
+      "rewards/accuracies": 0.9125000238418579,
+      "rewards/chosen": 3.695958375930786,
+      "rewards/margins": 6.534309387207031,
+      "rewards/rejected": -2.838351011276245,
       "step": 130
     },
     {
-      "epoch": 0.3582853486884197,
-      "grad_norm": 312.9816016514414,
+      "epoch": 0.36,
+      "grad_norm": 335.11070283406536,
       "learning_rate": 1.6184787302662547e-07,
-      "logits/chosen": -2.6076598167419434,
-      "logits/rejected": -2.539602279663086,
-      "logps/chosen": -267.7660217285156,
-      "logps/rejected": -213.330078125,
-      "loss": 0.3055,
-      "rewards/accuracies": 0.875,
-      "rewards/chosen": 3.705143690109253,
-      "rewards/margins": 3.5916450023651123,
-      "rewards/rejected": 0.11349865049123764,
+      "logits/chosen": -2.6305205821990967,
+      "logits/rejected": -2.519258975982666,
+      "logps/chosen": -269.74249267578125,
+      "logps/rejected": -205.24441528320312,
+      "loss": 0.1847,
+      "rewards/accuracies": 0.918749988079071,
+      "rewards/chosen": 3.7317748069763184,
+      "rewards/margins": 6.535207271575928,
+      "rewards/rejected": -2.8034329414367676,
       "step": 140
     },
     {
-      "epoch": 0.3838771593090211,
-      "grad_norm": 298.63492430036257,
+      "epoch": 0.38,
+      "grad_norm": 237.3062963631657,
       "learning_rate": 1.5457645101945046e-07,
-      "logits/chosen": -2.588223457336426,
-      "logits/rejected": -2.521327495574951,
-      "logps/chosen": -262.39776611328125,
-      "logps/rejected": -210.2900848388672,
-      "loss": 0.2675,
-      "rewards/accuracies": 0.887499988079071,
-      "rewards/chosen": 4.096975803375244,
-      "rewards/margins": 4.044339656829834,
-      "rewards/rejected": 0.05263558775186539,
+      "logits/chosen": -2.613662004470825,
+      "logits/rejected": -2.50919771194458,
+      "logps/chosen": -262.550537109375,
+      "logps/rejected": -209.60781860351562,
+      "loss": 0.1987,
+      "rewards/accuracies": 0.8999999761581421,
+      "rewards/chosen": 4.1123762130737305,
+      "rewards/margins": 7.0581793785095215,
+      "rewards/rejected": -2.945803165435791,
       "step": 150
     },
     {
-      "epoch": 0.4094689699296225,
-      "grad_norm": 277.3876418755778,
+      "epoch": 0.41,
+      "grad_norm": 781.538478360743,
       "learning_rate": 1.4686811008647035e-07,
-      "logits/chosen": -2.5860092639923096,
-      "logits/rejected": -2.5171661376953125,
-      "logps/chosen": -241.29501342773438,
-      "logps/rejected": -192.94955444335938,
-      "loss": 0.2544,
-      "rewards/accuracies": 0.887499988079071,
-      "rewards/chosen": 3.8214523792266846,
-      "rewards/margins": 3.785486936569214,
-      "rewards/rejected": 0.0359656922519207,
+      "logits/chosen": -2.6011874675750732,
+      "logits/rejected": -2.4891130924224854,
+      "logps/chosen": -241.5615692138672,
+      "logps/rejected": -182.00228881835938,
+      "loss": 0.1643,
+      "rewards/accuracies": 0.9437500238418579,
+      "rewards/chosen": 4.244563102722168,
+      "rewards/margins": 6.548022270202637,
+      "rewards/rejected": -2.3034589290618896,
       "step": 160
     },
     {
-      "epoch": 0.4350607805502239,
-      "grad_norm": 339.61682629601955,
+      "epoch": 0.44,
+      "grad_norm": 420.43337815116814,
       "learning_rate": 1.387845603604855e-07,
-      "logits/chosen": -2.5826542377471924,
-      "logits/rejected": -2.51751446723938,
-      "logps/chosen": -262.99298095703125,
-      "logps/rejected": -206.5457000732422,
-      "loss": 0.2334,
-      "rewards/accuracies": 0.875,
-      "rewards/chosen": 3.8493824005126953,
-      "rewards/margins": 3.933476209640503,
-      "rewards/rejected": -0.08409398794174194,
+      "logits/chosen": -2.6014420986175537,
+      "logits/rejected": -2.4862489700317383,
+      "logps/chosen": -260.2299499511719,
+      "logps/rejected": -197.31021118164062,
+      "loss": 0.1451,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": 4.481954574584961,
+      "rewards/margins": 6.5617804527282715,
+      "rewards/rejected": -2.0798258781433105,
       "step": 170
     },
     {
-      "epoch": 0.46065259117082535,
-      "grad_norm": 293.5783730044579,
+      "epoch": 0.46,
+      "grad_norm": 219.52091746145038,
       "learning_rate": 1.3039051575742468e-07,
-      "logits/chosen": -2.6330299377441406,
-      "logits/rejected": -2.547426700592041,
-      "logps/chosen": -235.4442596435547,
-      "logps/rejected": -183.63687133789062,
-      "loss": 0.2871,
-      "rewards/accuracies": 0.862500011920929,
-      "rewards/chosen": 3.294564723968506,
-      "rewards/margins": 3.4877796173095703,
-      "rewards/rejected": -0.193215012550354,
+      "logits/chosen": -2.6457467079162598,
+      "logits/rejected": -2.5342042446136475,
+      "logps/chosen": -234.87063598632812,
+      "logps/rejected": -187.8373565673828,
+      "loss": 0.1641,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": 3.4876370429992676,
+      "rewards/margins": 5.9574689865112305,
+      "rewards/rejected": -2.469831943511963,
       "step": 180
     },
     {
-      "epoch": 0.48624440179142675,
-      "grad_norm": 298.0737945063753,
+      "epoch": 0.49,
+      "grad_norm": 391.30420402591136,
       "learning_rate": 1.2175317590061675e-07,
-      "logits/chosen": -2.5894675254821777,
-      "logits/rejected": -2.51374888420105,
-      "logps/chosen": -257.42132568359375,
-      "logps/rejected": -199.62106323242188,
-      "loss": 0.239,
-      "rewards/accuracies": 0.887499988079071,
-      "rewards/chosen": 3.699636936187744,
-      "rewards/margins": 3.845207929611206,
-      "rewards/rejected": -0.1455712914466858,
+      "logits/chosen": -2.598358154296875,
+      "logits/rejected": -2.5016226768493652,
+      "logps/chosen": -256.7655334472656,
+      "logps/rejected": -203.38717651367188,
+      "loss": 0.1704,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": 3.634434223175049,
+      "rewards/margins": 6.311253547668457,
+      "rewards/rejected": -2.6768198013305664,
       "step": 190
     },
     {
-      "epoch": 0.5118362124120281,
-      "grad_norm": 326.3771289852159,
+      "epoch": 0.51,
+      "grad_norm": 573.9951634797832,
       "learning_rate": 1.1294168814540553e-07,
-      "logits/chosen": -2.625087261199951,
-      "logits/rejected": -2.5350747108459473,
-      "logps/chosen": -271.9561462402344,
-      "logps/rejected": -214.1556854248047,
-      "loss": 0.2317,
-      "rewards/accuracies": 0.90625,
-      "rewards/chosen": 4.283473014831543,
-      "rewards/margins": 4.552158832550049,
-      "rewards/rejected": -0.2686860263347626,
+      "logits/chosen": -2.640943765640259,
+      "logits/rejected": -2.5037968158721924,
+      "logps/chosen": -270.6221923828125,
+      "logps/rejected": -199.61119079589844,
+      "loss": 0.1514,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": 4.9661078453063965,
+      "rewards/margins": 7.715418338775635,
+      "rewards/rejected": -2.749310255050659,
       "step": 200
     },
     {
-      "epoch": 0.5374280230326296,
-      "grad_norm": 510.1343443372893,
+      "epoch": 0.54,
+      "grad_norm": 383.73670531019474,
       "learning_rate": 1.0402659401094151e-07,
-      "logits/chosen": -2.602785587310791,
-      "logits/rejected": -2.5288333892822266,
-      "logps/chosen": -264.21099853515625,
-      "logps/rejected": -207.3443145751953,
-      "loss": 0.3153,
-      "rewards/accuracies": 0.856249988079071,
-      "rewards/chosen": 3.421428680419922,
-      "rewards/margins": 3.9131996631622314,
-      "rewards/rejected": -0.4917708933353424,
+      "logits/chosen": -2.6191225051879883,
+      "logits/rejected": -2.5026001930236816,
+      "logps/chosen": -262.648681640625,
+      "logps/rejected": -207.82363891601562,
+      "loss": 0.1405,
+      "rewards/accuracies": 0.925000011920929,
+      "rewards/chosen": 4.20405912399292,
+      "rewards/margins": 7.261610507965088,
+      "rewards/rejected": -3.057551383972168,
       "step": 210
     },
     {
-      "epoch": 0.5630198336532309,
-      "grad_norm": 362.61099626331173,
+      "epoch": 0.56,
+      "grad_norm": 271.1779091479927,
       "learning_rate": 9.507926445081218e-08,
-      "logits/chosen": -2.607333183288574,
-      "logits/rejected": -2.5410573482513428,
-      "logps/chosen": -255.5386199951172,
-      "logps/rejected": -210.58261108398438,
-      "loss": 0.2657,
-      "rewards/accuracies": 0.893750011920929,
-      "rewards/chosen": 3.069124698638916,
-      "rewards/margins": 3.4770140647888184,
-      "rewards/rejected": -0.4078896641731262,
+      "logits/chosen": -2.618332862854004,
+      "logits/rejected": -2.5180063247680664,
+      "logps/chosen": -255.3096160888672,
+      "logps/rejected": -204.3534698486328,
+      "loss": 0.1701,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 3.6050515174865723,
+      "rewards/margins": 7.0129852294921875,
+      "rewards/rejected": -3.4079346656799316,
       "step": 220
     },
     {
-      "epoch": 0.5886116442738324,
-      "grad_norm": 270.86067735708986,
+      "epoch": 0.59,
+      "grad_norm": 290.4603808348808,
       "learning_rate": 8.61713284835267e-08,
-      "logits/chosen": -2.6318671703338623,
-      "logits/rejected": -2.5431408882141113,
-      "logps/chosen": -265.3260803222656,
-      "logps/rejected": -212.6390380859375,
-      "loss": 0.249,
-      "rewards/accuracies": 0.8500000238418579,
-      "rewards/chosen": 4.038520812988281,
-      "rewards/margins": 3.9009087085723877,
-      "rewards/rejected": 0.1376120150089264,
+      "logits/chosen": -2.646491050720215,
+      "logits/rejected": -2.51234769821167,
+      "logps/chosen": -264.74420166015625,
+      "logps/rejected": -205.0327911376953,
+      "loss": 0.1425,
+      "rewards/accuracies": 0.918749988079071,
+      "rewards/chosen": 4.327627182006836,
+      "rewards/margins": 7.188753604888916,
+      "rewards/rejected": -2.8611254692077637,
       "step": 230
     },
     {
-      "epoch": 0.6142034548944337,
-      "grad_norm": 496.26361322510223,
+      "epoch": 0.61,
+      "grad_norm": 422.65919601372,
       "learning_rate": 7.73740997570278e-08,
-      "logits/chosen": -2.6172757148742676,
-      "logits/rejected": -2.566117763519287,
-      "logps/chosen": -259.39569091796875,
-      "logps/rejected": -214.13717651367188,
-      "loss": 0.2362,
-      "rewards/accuracies": 0.8999999761581421,
-      "rewards/chosen": 4.167778968811035,
-      "rewards/margins": 4.450715065002441,
-      "rewards/rejected": -0.28293582797050476,
+      "logits/chosen": -2.6252548694610596,
+      "logits/rejected": -2.5125999450683594,
+      "logps/chosen": -258.0855712890625,
+      "logps/rejected": -207.72213745117188,
+      "loss": 0.1341,
+      "rewards/accuracies": 0.9312499761581421,
+      "rewards/chosen": 4.273736953735352,
+      "rewards/margins": 7.429440498352051,
+      "rewards/rejected": -3.155702829360962,
       "step": 240
     },
     {
-      "epoch": 0.6397952655150352,
-      "grad_norm": 385.39306248287744,
+      "epoch": 0.64,
+      "grad_norm": 236.70780195109265,
       "learning_rate": 6.875800563794424e-08,
-      "logits/chosen": -2.6301958560943604,
-      "logits/rejected": -2.5562362670898438,
-      "logps/chosen": -264.5022277832031,
-      "logps/rejected": -217.06472778320312,
-      "loss": 0.2541,
-      "rewards/accuracies": 0.862500011920929,
-      "rewards/chosen": 3.638233184814453,
-      "rewards/margins": 3.9798378944396973,
-      "rewards/rejected": -0.34160494804382324,
+      "logits/chosen": -2.637636184692383,
+      "logits/rejected": -2.522014856338501,
+      "logps/chosen": -264.11163330078125,
+      "logps/rejected": -213.34262084960938,
+      "loss": 0.1561,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": 3.965393543243408,
+      "rewards/margins": 7.122384548187256,
+      "rewards/rejected": -3.1569907665252686,
       "step": 250
     },
     {
-      "epoch": 0.6653870761356366,
-      "grad_norm": 246.0647695237683,
+      "epoch": 0.67,
+      "grad_norm": 261.4238126511671,
       "learning_rate": 6.039202339608431e-08,
-      "logits/chosen": -2.6222901344299316,
-      "logits/rejected": -2.5577120780944824,
-      "logps/chosen": -258.84637451171875,
-      "logps/rejected": -203.7962188720703,
-      "loss": 0.2317,
-      "rewards/accuracies": 0.893750011920929,
-      "rewards/chosen": 3.5067996978759766,
-      "rewards/margins": 3.801957607269287,
-      "rewards/rejected": -0.295158326625824,
+      "logits/chosen": -2.6351547241210938,
+      "logits/rejected": -2.5343315601348877,
+      "logps/chosen": -257.4027099609375,
+      "logps/rejected": -206.6591033935547,
+      "loss": 0.1287,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 4.236881732940674,
+      "rewards/margins": 7.065675258636475,
+      "rewards/rejected": -2.828793525695801,
       "step": 260
     },
     {
-      "epoch": 0.690978886756238,
-      "grad_norm": 382.6551210350461,
+      "epoch": 0.69,
+      "grad_norm": 290.68123700235606,
       "learning_rate": 5.2343127997869205e-08,
-      "logits/chosen": -2.602179765701294,
-      "logits/rejected": -2.5085558891296387,
-      "logps/chosen": -270.6271057128906,
-      "logps/rejected": -222.81655883789062,
-      "loss": 0.2926,
-      "rewards/accuracies": 0.8999999761581421,
-      "rewards/chosen": 2.9784107208251953,
-      "rewards/margins": 4.063758850097656,
-      "rewards/rejected": -1.085348129272461,
+      "logits/chosen": -2.610731840133667,
+      "logits/rejected": -2.4807095527648926,
+      "logps/chosen": -270.530517578125,
+      "logps/rejected": -215.2696533203125,
+      "loss": 0.2282,
+      "rewards/accuracies": 0.9312499761581421,
+      "rewards/chosen": 3.1549553871154785,
+      "rewards/margins": 7.109915733337402,
+      "rewards/rejected": -3.9549612998962402,
       "step": 270
     },
     {
-      "epoch": 0.7165706973768394,
-      "grad_norm": 291.15530026271324,
+      "epoch": 0.72,
+      "grad_norm": 212.4315878069041,
       "learning_rate": 4.4675755929468636e-08,
-      "logits/chosen": -2.627225160598755,
-      "logits/rejected": -2.565744638442993,
-      "logps/chosen": -266.7916259765625,
-      "logps/rejected": -214.30709838867188,
-      "loss": 0.2375,
-      "rewards/accuracies": 0.90625,
-      "rewards/chosen": 3.4573512077331543,
-      "rewards/margins": 4.138546943664551,
-      "rewards/rejected": -0.6811951398849487,
+      "logits/chosen": -2.6439692974090576,
+      "logits/rejected": -2.521467447280884,
+      "logps/chosen": -266.0245056152344,
+      "logps/rejected": -204.48606872558594,
+      "loss": 0.139,
+      "rewards/accuracies": 0.956250011920929,
+      "rewards/chosen": 3.838078737258911,
+      "rewards/margins": 7.6062164306640625,
+      "rewards/rejected": -3.7681381702423096,
       "step": 280
     },
     {
-      "epoch": 0.7421625079974408,
-      "grad_norm": 302.9770657235692,
+      "epoch": 0.74,
+      "grad_norm": 229.50979085481035,
       "learning_rate": 3.745128934207224e-08,
-      "logits/chosen": -2.590620279312134,
-      "logits/rejected": -2.5388922691345215,
-      "logps/chosen": -265.51971435546875,
-      "logps/rejected": -212.6427764892578,
-      "loss": 0.2286,
-      "rewards/accuracies": 0.893750011920929,
-      "rewards/chosen": 3.2131683826446533,
-      "rewards/margins": 3.975499391555786,
-      "rewards/rejected": -0.7623313665390015,
+      "logits/chosen": -2.598167657852173,
+      "logits/rejected": -2.5218276977539062,
+      "logps/chosen": -266.5920104980469,
+      "logps/rejected": -222.931884765625,
+      "loss": 0.1507,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": 3.6127426624298096,
+      "rewards/margins": 6.654023170471191,
+      "rewards/rejected": -3.0412800312042236,
       "step": 290
     },
     {
-      "epoch": 0.7677543186180422,
-      "grad_norm": 339.1306333767976,
+      "epoch": 0.77,
+      "grad_norm": 321.80727834811256,
       "learning_rate": 3.0727564649040063e-08,
-      "logits/chosen": -2.6111063957214355,
-      "logits/rejected": -2.5518836975097656,
-      "logps/chosen": -271.9001159667969,
-      "logps/rejected": -216.2710723876953,
-      "loss": 0.2446,
-      "rewards/accuracies": 0.9125000238418579,
-      "rewards/chosen": 3.3372998237609863,
-      "rewards/margins": 3.9620718955993652,
-      "rewards/rejected": -0.6247718930244446,
+      "logits/chosen": -2.6253504753112793,
+      "logits/rejected": -2.5061511993408203,
+      "logps/chosen": -270.4463806152344,
+      "logps/rejected": -213.0215301513672,
+      "loss": 0.141,
+      "rewards/accuracies": 0.956250011920929,
+      "rewards/chosen": 3.923215389251709,
+      "rewards/margins": 7.3881683349609375,
+      "rewards/rejected": -3.464953660964966,
       "step": 300
     },
     {
-      "epoch": 0.7933461292386437,
-      "grad_norm": 235.34557136252968,
+      "epoch": 0.79,
+      "grad_norm": 171.80295572629132,
       "learning_rate": 2.4558409508920985e-08,
-      "logits/chosen": -2.5742857456207275,
-      "logits/rejected": -2.499851703643799,
-      "logps/chosen": -275.28167724609375,
-      "logps/rejected": -211.0914764404297,
-      "loss": 0.2598,
-      "rewards/accuracies": 0.862500011920929,
-      "rewards/chosen": 3.4961440563201904,
-      "rewards/margins": 4.247152805328369,
-      "rewards/rejected": -0.7510083913803101,
+      "logits/chosen": -2.5865883827209473,
+      "logits/rejected": -2.491208553314209,
+      "logps/chosen": -275.579345703125,
+      "logps/rejected": -208.02297973632812,
+      "loss": 0.1401,
+      "rewards/accuracies": 0.9125000238418579,
+      "rewards/chosen": 3.985370635986328,
+      "rewards/margins": 7.237724304199219,
+      "rewards/rejected": -3.2523536682128906,
       "step": 310
     },
     {
-      "epoch": 0.818937939859245,
-      "grad_norm": 368.2414347720992,
+      "epoch": 0.82,
+      "grad_norm": 294.8015156484179,
       "learning_rate": 1.899321190108335e-08,
-      "logits/chosen": -2.59656023979187,
-      "logits/rejected": -2.545151472091675,
-      "logps/chosen": -258.7973327636719,
-      "logps/rejected": -200.56219482421875,
-      "loss": 0.2329,
-      "rewards/accuracies": 0.8999999761581421,
-      "rewards/chosen": 3.0572078227996826,
-      "rewards/margins": 3.9228408336639404,
-      "rewards/rejected": -0.8656327128410339,
+      "logits/chosen": -2.6083686351776123,
+      "logits/rejected": -2.508666515350342,
+      "logps/chosen": -258.6110534667969,
+      "logps/rejected": -207.57406616210938,
+      "loss": 0.1709,
+      "rewards/accuracies": 0.8812500238418579,
+      "rewards/chosen": 3.153282642364502,
+      "rewards/margins": 7.0364227294921875,
+      "rewards/rejected": -3.8831400871276855,
       "step": 320
     },
     {
-      "epoch": 0.8445297504798465,
-      "grad_norm": 412.2800478150093,
+      "epoch": 0.84,
+      "grad_norm": 262.1222746234904,
       "learning_rate": 1.4076524743778317e-08,
-      "logits/chosen": -2.6195101737976074,
-      "logits/rejected": -2.55584716796875,
-      "logps/chosen": -262.2277526855469,
-      "logps/rejected": -213.35403442382812,
-      "loss": 0.231,
-      "rewards/accuracies": 0.925000011920929,
-      "rewards/chosen": 3.7354748249053955,
-      "rewards/margins": 4.0478105545043945,
-      "rewards/rejected": -0.31233564019203186,
+      "logits/chosen": -2.6292643547058105,
+      "logits/rejected": -2.531942129135132,
+      "logps/chosen": -261.5999450683594,
+      "logps/rejected": -207.26699829101562,
+      "loss": 0.1437,
+      "rewards/accuracies": 0.96875,
+      "rewards/chosen": 4.273932456970215,
+      "rewards/margins": 7.467469215393066,
+      "rewards/rejected": -3.1935369968414307,
       "step": 330
     },
     {
-      "epoch": 0.8701215611004478,
-      "grad_norm": 291.1936087568274,
+      "epoch": 0.87,
+      "grad_norm": 299.7750791753028,
       "learning_rate": 9.847709219918398e-09,
-      "logits/chosen": -2.6071531772613525,
-      "logits/rejected": -2.5460381507873535,
-      "logps/chosen": -257.75164794921875,
-      "logps/rejected": -206.60986328125,
-      "loss": 0.221,
-      "rewards/accuracies": 0.949999988079071,
-      "rewards/chosen": 3.5297904014587402,
-      "rewards/margins": 4.399306297302246,
-      "rewards/rejected": -0.8695155382156372,
+      "logits/chosen": -2.6148436069488525,
+      "logits/rejected": -2.5132031440734863,
+      "logps/chosen": -256.66473388671875,
+      "logps/rejected": -194.7910919189453,
+      "loss": 0.1894,
+      "rewards/accuracies": 0.9624999761581421,
+      "rewards/chosen": 4.073337078094482,
+      "rewards/margins": 7.587210655212402,
+      "rewards/rejected": -3.51387357711792,
       "step": 340
     },
     {
-      "epoch": 0.8957133717210493,
-      "grad_norm": 301.99507828681374,
+      "epoch": 0.9,
+      "grad_norm": 346.7439242044206,
       "learning_rate": 6.340619665972846e-09,
-      "logits/chosen": -2.617502212524414,
-      "logits/rejected": -2.5671114921569824,
-      "logps/chosen": -267.4635009765625,
-      "logps/rejected": -222.5786895751953,
-      "loss": 0.2579,
-      "rewards/accuracies": 0.8687499761581421,
-      "rewards/chosen": 3.393681287765503,
-      "rewards/margins": 3.9400668144226074,
-      "rewards/rejected": -0.546385645866394,
+      "logits/chosen": -2.630897045135498,
+      "logits/rejected": -2.5146021842956543,
+      "logps/chosen": -265.88916015625,
+      "logps/rejected": -212.77487182617188,
+      "loss": 0.1582,
+      "rewards/accuracies": 0.9125000238418579,
+      "rewards/chosen": 3.5220444202423096,
+      "rewards/margins": 7.0233283042907715,
+      "rewards/rejected": -3.501283645629883,
       "step": 350
     },
     {
-      "epoch": 0.9213051823416507,
-      "grad_norm": 348.99526280716225,
+      "epoch": 0.92,
+      "grad_norm": 307.153905111391,
       "learning_rate": 3.583332546643769e-09,
-      "logits/chosen": -2.6180646419525146,
-      "logits/rejected": -2.5445971488952637,
-      "logps/chosen": -272.35406494140625,
-      "logps/rejected": -214.8975067138672,
-      "loss": 0.2825,
-      "rewards/accuracies": 0.893750011920929,
-      "rewards/chosen": 3.431410551071167,
-      "rewards/margins": 4.0157270431518555,
-      "rewards/rejected": -0.584316074848175,
+      "logits/chosen": -2.6361472606658936,
+      "logits/rejected": -2.5298829078674316,
+      "logps/chosen": -271.5682067871094,
+      "logps/rejected": -209.4921417236328,
+      "loss": 0.1547,
+      "rewards/accuracies": 0.9375,
+      "rewards/chosen": 3.9090733528137207,
+      "rewards/margins": 7.22186279296875,
+      "rewards/rejected": -3.3127894401550293,
       "step": 360
     },
     {
-      "epoch": 0.946896992962252,
-      "grad_norm": 251.0460885716357,
+      "epoch": 0.95,
+      "grad_norm": 183.78861249224778,
       "learning_rate": 1.5979216850509847e-09,
-      "logits/chosen": -2.5794007778167725,
-      "logits/rejected": -2.5391972064971924,
-      "logps/chosen": -271.82513427734375,
-      "logps/rejected": -225.1968231201172,
-      "loss": 0.2529,
-      "rewards/accuracies": 0.862500011920929,
-      "rewards/chosen": 3.722885847091675,
-      "rewards/margins": 4.0348358154296875,
-      "rewards/rejected": -0.3119499981403351,
+      "logits/chosen": -2.593644618988037,
+      "logits/rejected": -2.4859519004821777,
+      "logps/chosen": -270.0194396972656,
+      "logps/rejected": -212.9616241455078,
+      "loss": 0.1314,
+      "rewards/accuracies": 0.9312499761581421,
+      "rewards/chosen": 3.80389142036438,
+      "rewards/margins": 6.737584114074707,
+      "rewards/rejected": -2.933692216873169,
       "step": 370
     },
     {
-      "epoch": 0.9724888035828535,
-      "grad_norm": 201.79043052952954,
+      "epoch": 0.97,
+      "grad_norm": 201.1703750461263,
       "learning_rate": 4.002815478505006e-10,
-      "logits/chosen": -2.6285715103149414,
-      "logits/rejected": -2.585494041442871,
-      "logps/chosen": -261.1199951171875,
-      "logps/rejected": -226.61105346679688,
-      "loss": 0.255,
-      "rewards/accuracies": 0.8500000238418579,
-      "rewards/chosen": 3.6326937675476074,
-      "rewards/margins": 4.036477088928223,
-      "rewards/rejected": -0.40378379821777344,
+      "logits/chosen": -2.6470093727111816,
+      "logits/rejected": -2.552563428878784,
+      "logps/chosen": -261.07574462890625,
+      "logps/rejected": -216.7428741455078,
+      "loss": 0.1449,
+      "rewards/accuracies": 0.9437500238418579,
+      "rewards/chosen": 4.029725074768066,
+      "rewards/margins": 6.822300910949707,
+      "rewards/rejected": -2.7925755977630615,
       "step": 380
     },
     {
-      "epoch": 0.9980806142034548,
-      "grad_norm": 458.24518941114127,
+      "epoch": 1.0,
+      "grad_norm": 359.6013698550439,
       "learning_rate": 0.0,
-      "logits/chosen": -2.641213893890381,
-      "logits/rejected": -2.575150966644287,
-      "logps/chosen": -248.17904663085938,
-      "logps/rejected": -206.1395721435547,
-      "loss": 0.2365,
-      "rewards/accuracies": 0.918749988079071,
-      "rewards/chosen": 3.4077067375183105,
-      "rewards/margins": 4.0728960037231445,
-      "rewards/rejected": -0.6651893854141235,
+      "logits/chosen": -2.6531007289886475,
+      "logits/rejected": -2.540839195251465,
+      "logps/chosen": -249.09298706054688,
+      "logps/rejected": -204.24765014648438,
+      "loss": 0.146,
+      "rewards/accuracies": 0.949999988079071,
+      "rewards/chosen": 3.7912139892578125,
+      "rewards/margins": 7.412507057189941,
+      "rewards/rejected": -3.621293306350708,
       "step": 390
     },
     {
-      "epoch": 0.9980806142034548,
+      "epoch": 1.0,
       "step": 390,
       "total_flos": 0.0,
-      "train_loss": 0.2947830175742125,
-      "train_runtime": 6391.2384,
-      "train_samples_per_second": 7.823,
-      "train_steps_per_second": 0.061
+      "train_loss": 0.19850983711389394,
+      "train_runtime": 5891.9709,
+      "train_samples_per_second": 8.486,
+      "train_steps_per_second": 0.066
     }
   ],
   "logging_steps": 10,
@@ -623,18 +623,6 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 100,
-  "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": 4,
   "trial_name": null,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3267756347c2c9afb597e20553862a0ac248b214358676d7dfbabc75346c7d63
-size 6520
+oid sha256:74d76a49f592a53356dcdced2c2a52df2dee5cb0bad93a9b5c068843a8eccfa4
+size 6328