| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.9591836734693877, | |
| "eval_steps": 13, | |
| "global_step": 147, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02040816326530612, | |
| "grad_norm": 0.7881951332092285, | |
| "learning_rate": 2e-05, | |
| "loss": 2.7509, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02040816326530612, | |
| "eval_loss": 2.6902382373809814, | |
| "eval_runtime": 269.5606, | |
| "eval_samples_per_second": 6.288, | |
| "eval_steps_per_second": 3.146, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04081632653061224, | |
| "grad_norm": 0.789082407951355, | |
| "learning_rate": 4e-05, | |
| "loss": 2.7449, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.061224489795918366, | |
| "grad_norm": 0.7354114055633545, | |
| "learning_rate": 6e-05, | |
| "loss": 2.7164, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.08163265306122448, | |
| "grad_norm": 0.7292255759239197, | |
| "learning_rate": 8e-05, | |
| "loss": 2.7174, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.10204081632653061, | |
| "grad_norm": 0.6898028254508972, | |
| "learning_rate": 0.0001, | |
| "loss": 2.6891, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.12244897959183673, | |
| "grad_norm": 0.6861400604248047, | |
| "learning_rate": 0.00012, | |
| "loss": 2.6545, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.14285714285714285, | |
| "grad_norm": 0.7510350346565247, | |
| "learning_rate": 0.00014, | |
| "loss": 2.5656, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.16326530612244897, | |
| "grad_norm": 0.8011165261268616, | |
| "learning_rate": 0.00016, | |
| "loss": 2.4519, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.1836734693877551, | |
| "grad_norm": 0.8624005317687988, | |
| "learning_rate": 0.00018, | |
| "loss": 2.3178, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.20408163265306123, | |
| "grad_norm": 0.8004987835884094, | |
| "learning_rate": 0.0002, | |
| "loss": 2.1783, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.22448979591836735, | |
| "grad_norm": 0.6362400054931641, | |
| "learning_rate": 0.000199985736255971, | |
| "loss": 2.0252, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.24489795918367346, | |
| "grad_norm": 0.7930936217308044, | |
| "learning_rate": 0.0001999429490929718, | |
| "loss": 1.8839, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.2653061224489796, | |
| "grad_norm": 0.5149843096733093, | |
| "learning_rate": 0.00019987165071710527, | |
| "loss": 1.8064, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.2653061224489796, | |
| "eval_loss": 1.6734941005706787, | |
| "eval_runtime": 271.2615, | |
| "eval_samples_per_second": 6.249, | |
| "eval_steps_per_second": 3.126, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.2857142857142857, | |
| "grad_norm": 0.42121434211730957, | |
| "learning_rate": 0.00019977186146800707, | |
| "loss": 1.7922, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.30612244897959184, | |
| "grad_norm": 0.3523242771625519, | |
| "learning_rate": 0.0001996436098130433, | |
| "loss": 1.7711, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.32653061224489793, | |
| "grad_norm": 0.3384595215320587, | |
| "learning_rate": 0.00019948693233918952, | |
| "loss": 1.7152, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.3469387755102041, | |
| "grad_norm": 0.34942421317100525, | |
| "learning_rate": 0.00019930187374259337, | |
| "loss": 1.7112, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.3673469387755102, | |
| "grad_norm": 0.31712639331817627, | |
| "learning_rate": 0.00019908848681582391, | |
| "loss": 1.7059, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.3877551020408163, | |
| "grad_norm": 0.2875436842441559, | |
| "learning_rate": 0.00019884683243281116, | |
| "loss": 1.6468, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.40816326530612246, | |
| "grad_norm": 0.24433130025863647, | |
| "learning_rate": 0.00019857697953148037, | |
| "loss": 1.6408, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.42857142857142855, | |
| "grad_norm": 0.21414674818515778, | |
| "learning_rate": 0.00019827900509408581, | |
| "loss": 1.616, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.4489795918367347, | |
| "grad_norm": 0.21537622809410095, | |
| "learning_rate": 0.00019795299412524945, | |
| "loss": 1.609, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.46938775510204084, | |
| "grad_norm": 0.2432074397802353, | |
| "learning_rate": 0.00019759903962771156, | |
| "loss": 1.6066, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.4897959183673469, | |
| "grad_norm": 0.2359839379787445, | |
| "learning_rate": 0.00019721724257579907, | |
| "loss": 1.5851, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.5102040816326531, | |
| "grad_norm": 0.22065888345241547, | |
| "learning_rate": 0.00019680771188662044, | |
| "loss": 1.5739, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5306122448979592, | |
| "grad_norm": 0.20339132845401764, | |
| "learning_rate": 0.0001963705643889941, | |
| "loss": 1.5513, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.5306122448979592, | |
| "eval_loss": 1.4832030534744263, | |
| "eval_runtime": 271.2449, | |
| "eval_samples_per_second": 6.249, | |
| "eval_steps_per_second": 3.126, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.5510204081632653, | |
| "grad_norm": 0.18875224888324738, | |
| "learning_rate": 0.00019590592479012023, | |
| "loss": 1.5378, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 0.18564417958259583, | |
| "learning_rate": 0.00019541392564000488, | |
| "loss": 1.5212, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.5918367346938775, | |
| "grad_norm": 0.16226942837238312, | |
| "learning_rate": 0.00019489470729364692, | |
| "loss": 1.5391, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.6122448979591837, | |
| "grad_norm": 0.15650039911270142, | |
| "learning_rate": 0.00019434841787099803, | |
| "loss": 1.511, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.6326530612244898, | |
| "grad_norm": 0.15976540744304657, | |
| "learning_rate": 0.00019377521321470805, | |
| "loss": 1.5119, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.6530612244897959, | |
| "grad_norm": 0.16409288346767426, | |
| "learning_rate": 0.00019317525684566685, | |
| "loss": 1.4909, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.673469387755102, | |
| "grad_norm": 0.15468019247055054, | |
| "learning_rate": 0.00019254871991635598, | |
| "loss": 1.4951, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.6938775510204082, | |
| "grad_norm": 0.1462036371231079, | |
| "learning_rate": 0.00019189578116202307, | |
| "loss": 1.4643, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.7142857142857143, | |
| "grad_norm": 0.1541963368654251, | |
| "learning_rate": 0.00019121662684969335, | |
| "loss": 1.5159, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.7346938775510204, | |
| "grad_norm": 0.14798064529895782, | |
| "learning_rate": 0.00019051145072503215, | |
| "loss": 1.4741, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.7551020408163265, | |
| "grad_norm": 0.13914817571640015, | |
| "learning_rate": 0.00018978045395707418, | |
| "loss": 1.4788, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.7755102040816326, | |
| "grad_norm": 0.15608824789524078, | |
| "learning_rate": 0.00018902384508083517, | |
| "loss": 1.4687, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.7959183673469388, | |
| "grad_norm": 0.14460116624832153, | |
| "learning_rate": 0.00018824183993782192, | |
| "loss": 1.482, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.7959183673469388, | |
| "eval_loss": 1.411073088645935, | |
| "eval_runtime": 271.292, | |
| "eval_samples_per_second": 6.248, | |
| "eval_steps_per_second": 3.126, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.8163265306122449, | |
| "grad_norm": 0.15740551054477692, | |
| "learning_rate": 0.00018743466161445823, | |
| "loss": 1.4486, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.8367346938775511, | |
| "grad_norm": 0.14149661362171173, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 1.4353, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.8571428571428571, | |
| "grad_norm": 0.14034292101860046, | |
| "learning_rate": 0.0001857457136130651, | |
| "loss": 1.4523, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.8775510204081632, | |
| "grad_norm": 0.1487722396850586, | |
| "learning_rate": 0.00018486442574947511, | |
| "loss": 1.4095, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.8979591836734694, | |
| "grad_norm": 0.17400234937667847, | |
| "learning_rate": 0.00018395892819696389, | |
| "loss": 1.4414, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.9183673469387755, | |
| "grad_norm": 0.1741325408220291, | |
| "learning_rate": 0.00018302947927123766, | |
| "loss": 1.4379, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.9387755102040817, | |
| "grad_norm": 0.15319454669952393, | |
| "learning_rate": 0.00018207634412072764, | |
| "loss": 1.405, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.9591836734693877, | |
| "grad_norm": 0.15876264870166779, | |
| "learning_rate": 0.00018109979465095013, | |
| "loss": 1.4122, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.9795918367346939, | |
| "grad_norm": 0.17120805382728577, | |
| "learning_rate": 0.00018010010944693848, | |
| "loss": 1.4132, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.1436116099357605, | |
| "learning_rate": 0.00017907757369376985, | |
| "loss": 1.416, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.0204081632653061, | |
| "grad_norm": 0.1707429438829422, | |
| "learning_rate": 0.0001780324790952092, | |
| "loss": 1.3913, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.0204081632653061, | |
| "grad_norm": 0.17117524147033691, | |
| "learning_rate": 0.00017696512379049325, | |
| "loss": 1.3963, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 1.0408163265306123, | |
| "grad_norm": 0.13410089910030365, | |
| "learning_rate": 0.0001758758122692791, | |
| "loss": 1.392, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 1.0408163265306123, | |
| "eval_loss": 1.3676769733428955, | |
| "eval_runtime": 270.8566, | |
| "eval_samples_per_second": 6.258, | |
| "eval_steps_per_second": 3.131, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 1.0612244897959184, | |
| "grad_norm": 0.18877607583999634, | |
| "learning_rate": 0.00017476485528478093, | |
| "loss": 1.3854, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 1.0816326530612246, | |
| "grad_norm": 0.1752927452325821, | |
| "learning_rate": 0.00017363256976511972, | |
| "loss": 1.3759, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 1.1020408163265305, | |
| "grad_norm": 0.17180170118808746, | |
| "learning_rate": 0.000172479278722912, | |
| "loss": 1.3614, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 1.1224489795918366, | |
| "grad_norm": 0.1640290915966034, | |
| "learning_rate": 0.00017130531116312203, | |
| "loss": 1.3853, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 1.1428571428571428, | |
| "grad_norm": 0.2047068476676941, | |
| "learning_rate": 0.0001701110019892053, | |
| "loss": 1.3699, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 1.163265306122449, | |
| "grad_norm": 0.1835869997739792, | |
| "learning_rate": 0.00016889669190756868, | |
| "loss": 1.3403, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 1.183673469387755, | |
| "grad_norm": 0.16733241081237793, | |
| "learning_rate": 0.00016766272733037576, | |
| "loss": 1.3609, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 1.2040816326530612, | |
| "grad_norm": 0.178726926445961, | |
| "learning_rate": 0.00016640946027672392, | |
| "loss": 1.3651, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.2244897959183674, | |
| "grad_norm": 0.16719630360603333, | |
| "learning_rate": 0.00016513724827222227, | |
| "loss": 1.3676, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 1.2448979591836735, | |
| "grad_norm": 0.15999363362789154, | |
| "learning_rate": 0.00016384645424699835, | |
| "loss": 1.3651, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 1.2653061224489797, | |
| "grad_norm": 0.1705988198518753, | |
| "learning_rate": 0.00016253744643216368, | |
| "loss": 1.3757, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 1.2857142857142856, | |
| "grad_norm": 0.14996370673179626, | |
| "learning_rate": 0.0001612105982547663, | |
| "loss": 1.3474, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 1.306122448979592, | |
| "grad_norm": 0.19127260148525238, | |
| "learning_rate": 0.0001598662882312615, | |
| "loss": 1.3414, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 1.306122448979592, | |
| "eval_loss": 1.331880807876587, | |
| "eval_runtime": 270.8424, | |
| "eval_samples_per_second": 6.258, | |
| "eval_steps_per_second": 3.131, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 1.3265306122448979, | |
| "grad_norm": 0.16125527024269104, | |
| "learning_rate": 0.00015850489985953076, | |
| "loss": 1.3509, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 1.346938775510204, | |
| "grad_norm": 0.1979473978281021, | |
| "learning_rate": 0.00015712682150947923, | |
| "loss": 1.3579, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 1.3673469387755102, | |
| "grad_norm": 0.18317992985248566, | |
| "learning_rate": 0.00015573244631224365, | |
| "loss": 1.3341, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 1.3877551020408163, | |
| "grad_norm": 0.1646898239850998, | |
| "learning_rate": 0.0001543221720480419, | |
| "loss": 1.3361, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 1.4081632653061225, | |
| "grad_norm": 0.1760271042585373, | |
| "learning_rate": 0.00015289640103269625, | |
| "loss": 1.358, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.4285714285714286, | |
| "grad_norm": 0.165283203125, | |
| "learning_rate": 0.0001514555400028629, | |
| "loss": 1.3072, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 1.4489795918367347, | |
| "grad_norm": 0.1507076472043991, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.3133, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.469387755102041, | |
| "grad_norm": 0.16913647949695587, | |
| "learning_rate": 0.00014853019625310813, | |
| "loss": 1.3232, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 1.489795918367347, | |
| "grad_norm": 0.18266479671001434, | |
| "learning_rate": 0.0001470465480602756, | |
| "loss": 1.3512, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 1.510204081632653, | |
| "grad_norm": 0.19301828742027283, | |
| "learning_rate": 0.0001455494786690634, | |
| "loss": 1.3241, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.5306122448979593, | |
| "grad_norm": 0.16109652817249298, | |
| "learning_rate": 0.00014403941515576344, | |
| "loss": 1.3256, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 1.5510204081632653, | |
| "grad_norm": 0.17053867876529694, | |
| "learning_rate": 0.00014251678830356408, | |
| "loss": 1.3162, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 1.5714285714285714, | |
| "grad_norm": 0.17348544299602509, | |
| "learning_rate": 0.00014098203247965875, | |
| "loss": 1.3213, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 1.5714285714285714, | |
| "eval_loss": 1.3028697967529297, | |
| "eval_runtime": 270.8095, | |
| "eval_samples_per_second": 6.259, | |
| "eval_steps_per_second": 3.131, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 1.5918367346938775, | |
| "grad_norm": 0.1703907549381256, | |
| "learning_rate": 0.00013943558551133186, | |
| "loss": 1.3073, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 1.6122448979591837, | |
| "grad_norm": 0.17313100397586823, | |
| "learning_rate": 0.0001378778885610576, | |
| "loss": 1.3232, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.6326530612244898, | |
| "grad_norm": 0.17237025499343872, | |
| "learning_rate": 0.00013630938600064747, | |
| "loss": 1.3406, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 1.6530612244897958, | |
| "grad_norm": 0.19658459722995758, | |
| "learning_rate": 0.00013473052528448201, | |
| "loss": 1.3114, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 1.6734693877551021, | |
| "grad_norm": 0.20599938929080963, | |
| "learning_rate": 0.0001331417568218636, | |
| "loss": 1.3288, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 1.693877551020408, | |
| "grad_norm": 0.17759399116039276, | |
| "learning_rate": 0.00013154353384852558, | |
| "loss": 1.2995, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 1.7142857142857144, | |
| "grad_norm": 0.18712250888347626, | |
| "learning_rate": 0.00012993631229733582, | |
| "loss": 1.2895, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 1.7346938775510203, | |
| "grad_norm": 0.1991330236196518, | |
| "learning_rate": 0.00012832055066823038, | |
| "loss": 1.2886, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 1.7551020408163265, | |
| "grad_norm": 0.22125203907489777, | |
| "learning_rate": 0.00012669670989741517, | |
| "loss": 1.3233, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 1.7755102040816326, | |
| "grad_norm": 0.2052813619375229, | |
| "learning_rate": 0.00012506525322587207, | |
| "loss": 1.3079, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 1.7959183673469388, | |
| "grad_norm": 0.19290736317634583, | |
| "learning_rate": 0.00012342664606720822, | |
| "loss": 1.3174, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 1.816326530612245, | |
| "grad_norm": 0.20912542939186096, | |
| "learning_rate": 0.00012178135587488515, | |
| "loss": 1.2915, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.836734693877551, | |
| "grad_norm": 0.20760588347911835, | |
| "learning_rate": 0.00012012985200886602, | |
| "loss": 1.3028, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 1.836734693877551, | |
| "eval_loss": 1.2795333862304688, | |
| "eval_runtime": 270.6525, | |
| "eval_samples_per_second": 6.263, | |
| "eval_steps_per_second": 3.133, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 1.8571428571428572, | |
| "grad_norm": 0.1996900886297226, | |
| "learning_rate": 0.00011847260560171896, | |
| "loss": 1.3119, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 1.8775510204081631, | |
| "grad_norm": 0.23766876757144928, | |
| "learning_rate": 0.00011681008942421483, | |
| "loss": 1.2978, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 1.8979591836734695, | |
| "grad_norm": 0.19782397150993347, | |
| "learning_rate": 0.00011514277775045768, | |
| "loss": 1.2955, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 1.9183673469387754, | |
| "grad_norm": 0.22519494593143463, | |
| "learning_rate": 0.00011347114622258612, | |
| "loss": 1.2957, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.9387755102040818, | |
| "grad_norm": 0.2590245306491852, | |
| "learning_rate": 0.00011179567171508463, | |
| "loss": 1.2809, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 1.9591836734693877, | |
| "grad_norm": 0.2235420197248459, | |
| "learning_rate": 0.00011011683219874323, | |
| "loss": 1.2784, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 1.9795918367346939, | |
| "grad_norm": 0.285740464925766, | |
| "learning_rate": 0.00010843510660430447, | |
| "loss": 1.309, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.20554350316524506, | |
| "learning_rate": 0.00010675097468583652, | |
| "loss": 1.273, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 2.020408163265306, | |
| "grad_norm": 0.24468418955802917, | |
| "learning_rate": 0.00010506491688387127, | |
| "loss": 1.2833, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.020408163265306, | |
| "grad_norm": 0.21553528308868408, | |
| "learning_rate": 0.00010337741418834684, | |
| "loss": 1.2669, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 2.0408163265306123, | |
| "grad_norm": 0.22015659511089325, | |
| "learning_rate": 0.0001016889480013931, | |
| "loss": 1.2795, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 2.061224489795918, | |
| "grad_norm": 0.2028799206018448, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2584, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 2.0816326530612246, | |
| "grad_norm": 0.23474323749542236, | |
| "learning_rate": 9.83110519986069e-05, | |
| "loss": 1.2761, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 2.0816326530612246, | |
| "eval_loss": 1.2696796655654907, | |
| "eval_runtime": 270.6586, | |
| "eval_samples_per_second": 6.263, | |
| "eval_steps_per_second": 3.133, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 2.1020408163265305, | |
| "grad_norm": 0.21070216596126556, | |
| "learning_rate": 9.662258581165319e-05, | |
| "loss": 1.2808, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 2.122448979591837, | |
| "grad_norm": 0.21867221593856812, | |
| "learning_rate": 9.493508311612874e-05, | |
| "loss": 1.2873, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 2.142857142857143, | |
| "grad_norm": 0.21630822122097015, | |
| "learning_rate": 9.324902531416349e-05, | |
| "loss": 1.2527, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 2.163265306122449, | |
| "grad_norm": 0.2134082019329071, | |
| "learning_rate": 9.156489339569554e-05, | |
| "loss": 1.2755, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 2.183673469387755, | |
| "grad_norm": 0.22310714423656464, | |
| "learning_rate": 8.98831678012568e-05, | |
| "loss": 1.2512, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 2.204081632653061, | |
| "grad_norm": 0.2365124374628067, | |
| "learning_rate": 8.820432828491542e-05, | |
| "loss": 1.2725, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 2.2244897959183674, | |
| "grad_norm": 0.2086496651172638, | |
| "learning_rate": 8.652885377741393e-05, | |
| "loss": 1.2488, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 2.2448979591836733, | |
| "grad_norm": 0.20848101377487183, | |
| "learning_rate": 8.485722224954237e-05, | |
| "loss": 1.2793, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 2.2653061224489797, | |
| "grad_norm": 0.20784686505794525, | |
| "learning_rate": 8.31899105757852e-05, | |
| "loss": 1.2564, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 2.2857142857142856, | |
| "grad_norm": 0.21896174550056458, | |
| "learning_rate": 8.15273943982811e-05, | |
| "loss": 1.2515, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 2.306122448979592, | |
| "grad_norm": 0.21367855370044708, | |
| "learning_rate": 7.987014799113397e-05, | |
| "loss": 1.248, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 2.326530612244898, | |
| "grad_norm": 0.20891636610031128, | |
| "learning_rate": 7.821864412511485e-05, | |
| "loss": 1.2753, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 2.3469387755102042, | |
| "grad_norm": 0.2092975378036499, | |
| "learning_rate": 7.65733539327918e-05, | |
| "loss": 1.2509, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 2.3469387755102042, | |
| "eval_loss": 1.258699655532837, | |
| "eval_runtime": 270.5384, | |
| "eval_samples_per_second": 6.265, | |
| "eval_steps_per_second": 3.134, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 2.36734693877551, | |
| "grad_norm": 0.1905972808599472, | |
| "learning_rate": 7.493474677412794e-05, | |
| "loss": 1.2516, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 2.387755102040816, | |
| "grad_norm": 0.19716158509254456, | |
| "learning_rate": 7.330329010258483e-05, | |
| "loss": 1.2665, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 2.4081632653061225, | |
| "grad_norm": 0.1953389048576355, | |
| "learning_rate": 7.16794493317696e-05, | |
| "loss": 1.2661, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.4285714285714284, | |
| "grad_norm": 0.1990067958831787, | |
| "learning_rate": 7.006368770266421e-05, | |
| "loss": 1.2619, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 2.4489795918367347, | |
| "grad_norm": 0.1954919546842575, | |
| "learning_rate": 6.845646615147445e-05, | |
| "loss": 1.2736, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 2.4693877551020407, | |
| "grad_norm": 0.18382853269577026, | |
| "learning_rate": 6.685824317813643e-05, | |
| "loss": 1.2732, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 2.489795918367347, | |
| "grad_norm": 0.18729491531848907, | |
| "learning_rate": 6.526947471551798e-05, | |
| "loss": 1.2509, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 2.510204081632653, | |
| "grad_norm": 0.2034740000963211, | |
| "learning_rate": 6.369061399935255e-05, | |
| "loss": 1.2829, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 2.5306122448979593, | |
| "grad_norm": 0.1952620893716812, | |
| "learning_rate": 6.21221114389424e-05, | |
| "loss": 1.2689, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 2.5510204081632653, | |
| "grad_norm": 0.1986168622970581, | |
| "learning_rate": 6.0564414488668165e-05, | |
| "loss": 1.2644, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 2.571428571428571, | |
| "grad_norm": 0.19526751339435577, | |
| "learning_rate": 5.901796752034128e-05, | |
| "loss": 1.265, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 2.5918367346938775, | |
| "grad_norm": 0.195367693901062, | |
| "learning_rate": 5.748321169643596e-05, | |
| "loss": 1.2782, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 2.612244897959184, | |
| "grad_norm": 0.18351928889751434, | |
| "learning_rate": 5.596058484423656e-05, | |
| "loss": 1.2884, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.612244897959184, | |
| "eval_loss": 1.2471545934677124, | |
| "eval_runtime": 270.4953, | |
| "eval_samples_per_second": 6.266, | |
| "eval_steps_per_second": 3.135, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.63265306122449, | |
| "grad_norm": 0.2015760987997055, | |
| "learning_rate": 5.44505213309366e-05, | |
| "loss": 1.2536, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 2.6530612244897958, | |
| "grad_norm": 0.1734190732240677, | |
| "learning_rate": 5.2953451939724454e-05, | |
| "loss": 1.2628, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 2.673469387755102, | |
| "grad_norm": 0.214066281914711, | |
| "learning_rate": 5.146980374689192e-05, | |
| "loss": 1.2543, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 2.693877551020408, | |
| "grad_norm": 0.17507924139499664, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 1.2665, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 2.7142857142857144, | |
| "grad_norm": 0.1778109222650528, | |
| "learning_rate": 4.854445999713715e-05, | |
| "loss": 1.2789, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 2.7346938775510203, | |
| "grad_norm": 0.1856827288866043, | |
| "learning_rate": 4.710359896730379e-05, | |
| "loss": 1.2481, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 2.7551020408163263, | |
| "grad_norm": 0.17856694757938385, | |
| "learning_rate": 4.567782795195816e-05, | |
| "loss": 1.2732, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 2.7755102040816326, | |
| "grad_norm": 0.21598489582538605, | |
| "learning_rate": 4.426755368775637e-05, | |
| "loss": 1.2525, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 2.795918367346939, | |
| "grad_norm": 0.17308436334133148, | |
| "learning_rate": 4.287317849052075e-05, | |
| "loss": 1.2665, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 2.816326530612245, | |
| "grad_norm": 0.19207212328910828, | |
| "learning_rate": 4.149510014046922e-05, | |
| "loss": 1.2681, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.836734693877551, | |
| "grad_norm": 0.19626958668231964, | |
| "learning_rate": 4.013371176873849e-05, | |
| "loss": 1.2727, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 2.857142857142857, | |
| "grad_norm": 0.1986483484506607, | |
| "learning_rate": 3.878940174523371e-05, | |
| "loss": 1.2414, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 2.877551020408163, | |
| "grad_norm": 0.19369089603424072, | |
| "learning_rate": 3.746255356783632e-05, | |
| "loss": 1.254, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 2.877551020408163, | |
| "eval_loss": 1.2410293817520142, | |
| "eval_runtime": 270.6762, | |
| "eval_samples_per_second": 6.262, | |
| "eval_steps_per_second": 3.133, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 2.8979591836734695, | |
| "grad_norm": 0.20910531282424927, | |
| "learning_rate": 3.615354575300166e-05, | |
| "loss": 1.2541, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 2.9183673469387754, | |
| "grad_norm": 0.19536806643009186, | |
| "learning_rate": 3.4862751727777797e-05, | |
| "loss": 1.2517, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 2.938775510204082, | |
| "grad_norm": 0.18630966544151306, | |
| "learning_rate": 3.3590539723276083e-05, | |
| "loss": 1.2473, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 2.9591836734693877, | |
| "grad_norm": 0.1874723732471466, | |
| "learning_rate": 3.233727266962425e-05, | |
| "loss": 1.244, | |
| "step": 147 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 196, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 49, | |
| "total_flos": 3.0628052408991744e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |