CocoRoF commited on
Commit
4eb805c
·
verified ·
1 Parent(s): 484c14b

Training in progress, step 8000, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:505255bb8be77cb973b3c0c099b60ddbe10985257e13456b8ff86dd8b9cb8873
3
  size 737582948
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:866e75c99e401c6fc4314023695489d65fcd5b9eaca8dde7642e6125835d6762
3
  size 737582948
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:60d776be50d108dd81ee9b0387b3f914be892678c43979999b5d33654ba56980
3
  size 1475256250
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff5bd566a6290228d61c2b0a64576637d68ab6f88e45b96b393bed3fe1419863
3
  size 1475256250
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e5a3a11b6b4e10025dadb9bffaf07ec4008881d55150f5d84a95c713a6115c05
3
- size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc43fb30d4954a7fe8242ecf9efc90cf1895ba433c6b84aed827fd7e8890fc47
3
+ size 15920
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7274f23fed9b58a8af256d8a5074ebda8ae9f9a6fbae5266d18c1fea989b6dd3
3
  size 15920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:070e6d875daa93eee00ceb16c7956211f031e29ae89c0bf2b8c1638bfc724904
3
  size 15920
last-checkpoint/rng_state_2.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8804ae92e3b2392e22e65d2ab0526c5903b460e6548b94439fb0020ed4f6c971
3
- size 15920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afcb6da67f70f314a010a9987a5b352b967a4f9fa86b16cc95539556cc4d4b57
3
+ size 15984
last-checkpoint/rng_state_3.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f3e11e0f06e93328a4d905cdad25e3815ebf5e2497f1f505db912eeda651cf3a
3
- size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50d6b0a99b3ef96868343a1a08693fcc566709fe5025abcde86626cac6379389
3
+ size 15920
last-checkpoint/rng_state_4.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:13c61159190ff4452eae1732b23b98693c3d2402a9a22d6001e28feb991ad5c6
3
- size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e08e9ba40189eac7d5cd9c7fdb48812d033226be82605e39640894f69559aa36
3
+ size 15920
last-checkpoint/rng_state_5.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ac997a5aab71c40ab8ef2ff5de70ff9f85b773b03f24a2a2d95bd0f7f9a02a36
3
- size 15920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e39da057b37f74f810adcb1a33229a68d68a756d6cc2abf032078fbe45fc3a55
3
+ size 15984
last-checkpoint/rng_state_6.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:11fb3f2fa89709aa4394eeaab2935e72048d88e01b5565c44fab8e49d94e5818
3
- size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b8b6d464ceead03c3bbad95ead841465f74b330a13ee3ce979e17fb8e372b42
3
+ size 15920
last-checkpoint/rng_state_7.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:de5c48e090ff05ec024f0ed6d872fa6b88401224fc22247b9444b0418bc262b8
3
- size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35f8ceff7347b2e4d980c59159b27487947fb8e524c24e87a3115123f2bc8a95
3
+ size 15920
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dc4672502535f71e3bfd116fab55200a1b20d47f6448284dad0f792fcd7901da
3
  size 1000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3cb85ac9abf82ce747c60e9879ff175c317b429dff1e2463093126cce085180
3
  size 1000
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 3.562618339193941,
5
  "eval_steps": 500,
6
- "global_step": 7000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -4907,6 +4907,706 @@
4907
  "learning_rate": 4.9900555892560594e-05,
4908
  "loss": 0.6768,
4909
  "step": 7000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4910
  }
4911
  ],
4912
  "logging_steps": 10,
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 4.071281961526834,
5
  "eval_steps": 500,
6
+ "global_step": 8000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
4907
  "learning_rate": 4.9900555892560594e-05,
4908
  "loss": 0.6768,
4909
  "step": 7000
4910
+ },
4911
+ {
4912
+ "epoch": 3.567709907874429,
4913
+ "grad_norm": 0.16426721215248108,
4914
+ "learning_rate": 4.990041382954997e-05,
4915
+ "loss": 0.683,
4916
+ "step": 7010
4917
+ },
4918
+ {
4919
+ "epoch": 3.5728014765549174,
4920
+ "grad_norm": 0.12947894632816315,
4921
+ "learning_rate": 4.990027176653933e-05,
4922
+ "loss": 0.6729,
4923
+ "step": 7020
4924
+ },
4925
+ {
4926
+ "epoch": 3.5778930452354056,
4927
+ "grad_norm": 0.15960286557674408,
4928
+ "learning_rate": 4.9900129703528706e-05,
4929
+ "loss": 0.679,
4930
+ "step": 7030
4931
+ },
4932
+ {
4933
+ "epoch": 3.582984613915894,
4934
+ "grad_norm": 0.12176317721605301,
4935
+ "learning_rate": 4.989998764051807e-05,
4936
+ "loss": 0.6832,
4937
+ "step": 7040
4938
+ },
4939
+ {
4940
+ "epoch": 3.5880761825963816,
4941
+ "grad_norm": 0.12822549045085907,
4942
+ "learning_rate": 4.9899845577507446e-05,
4943
+ "loss": 0.6807,
4944
+ "step": 7050
4945
+ },
4946
+ {
4947
+ "epoch": 3.59316775127687,
4948
+ "grad_norm": 0.09114730358123779,
4949
+ "learning_rate": 4.989970351449682e-05,
4950
+ "loss": 0.6837,
4951
+ "step": 7060
4952
+ },
4953
+ {
4954
+ "epoch": 3.598259319957358,
4955
+ "grad_norm": 0.11248596012592316,
4956
+ "learning_rate": 4.989956145148619e-05,
4957
+ "loss": 0.6773,
4958
+ "step": 7070
4959
+ },
4960
+ {
4961
+ "epoch": 3.6033508886378462,
4962
+ "grad_norm": 0.14381690323352814,
4963
+ "learning_rate": 4.9899419388475565e-05,
4964
+ "loss": 0.6763,
4965
+ "step": 7080
4966
+ },
4967
+ {
4968
+ "epoch": 3.6084424573183345,
4969
+ "grad_norm": 0.1576450616121292,
4970
+ "learning_rate": 4.989927732546494e-05,
4971
+ "loss": 0.6796,
4972
+ "step": 7090
4973
+ },
4974
+ {
4975
+ "epoch": 3.6135340259988227,
4976
+ "grad_norm": 0.12672173976898193,
4977
+ "learning_rate": 4.989913526245431e-05,
4978
+ "loss": 0.6773,
4979
+ "step": 7100
4980
+ },
4981
+ {
4982
+ "epoch": 3.618625594679311,
4983
+ "grad_norm": 0.10089720040559769,
4984
+ "learning_rate": 4.9898993199443684e-05,
4985
+ "loss": 0.6835,
4986
+ "step": 7110
4987
+ },
4988
+ {
4989
+ "epoch": 3.6237171633597987,
4990
+ "grad_norm": 0.10352669656276703,
4991
+ "learning_rate": 4.989885113643306e-05,
4992
+ "loss": 0.6804,
4993
+ "step": 7120
4994
+ },
4995
+ {
4996
+ "epoch": 3.6288087320402873,
4997
+ "grad_norm": 0.12168221920728683,
4998
+ "learning_rate": 4.989870907342243e-05,
4999
+ "loss": 0.6775,
5000
+ "step": 7130
5001
+ },
5002
+ {
5003
+ "epoch": 3.633900300720775,
5004
+ "grad_norm": 0.152724489569664,
5005
+ "learning_rate": 4.9898567010411804e-05,
5006
+ "loss": 0.6832,
5007
+ "step": 7140
5008
+ },
5009
+ {
5010
+ "epoch": 3.6389918694012633,
5011
+ "grad_norm": 0.10124222189188004,
5012
+ "learning_rate": 4.989842494740118e-05,
5013
+ "loss": 0.6824,
5014
+ "step": 7150
5015
+ },
5016
+ {
5017
+ "epoch": 3.6440834380817515,
5018
+ "grad_norm": 0.10840737819671631,
5019
+ "learning_rate": 4.989828288439054e-05,
5020
+ "loss": 0.6781,
5021
+ "step": 7160
5022
+ },
5023
+ {
5024
+ "epoch": 3.6491750067622397,
5025
+ "grad_norm": 0.10668514668941498,
5026
+ "learning_rate": 4.9898140821379916e-05,
5027
+ "loss": 0.6857,
5028
+ "step": 7170
5029
+ },
5030
+ {
5031
+ "epoch": 3.654266575442728,
5032
+ "grad_norm": 0.11429141461849213,
5033
+ "learning_rate": 4.989799875836929e-05,
5034
+ "loss": 0.6823,
5035
+ "step": 7180
5036
+ },
5037
+ {
5038
+ "epoch": 3.6593581441232157,
5039
+ "grad_norm": 0.1012284979224205,
5040
+ "learning_rate": 4.989785669535866e-05,
5041
+ "loss": 0.678,
5042
+ "step": 7190
5043
+ },
5044
+ {
5045
+ "epoch": 3.6644497128037044,
5046
+ "grad_norm": 0.15000002086162567,
5047
+ "learning_rate": 4.9897714632348035e-05,
5048
+ "loss": 0.6763,
5049
+ "step": 7200
5050
+ },
5051
+ {
5052
+ "epoch": 3.669541281484192,
5053
+ "grad_norm": 0.15613609552383423,
5054
+ "learning_rate": 4.989757256933741e-05,
5055
+ "loss": 0.6837,
5056
+ "step": 7210
5057
+ },
5058
+ {
5059
+ "epoch": 3.6746328501646803,
5060
+ "grad_norm": 0.13344906270503998,
5061
+ "learning_rate": 4.989743050632678e-05,
5062
+ "loss": 0.6841,
5063
+ "step": 7220
5064
+ },
5065
+ {
5066
+ "epoch": 3.6797244188451685,
5067
+ "grad_norm": 0.12140567600727081,
5068
+ "learning_rate": 4.9897288443316155e-05,
5069
+ "loss": 0.6792,
5070
+ "step": 7230
5071
+ },
5072
+ {
5073
+ "epoch": 3.6848159875256568,
5074
+ "grad_norm": 0.11317454278469086,
5075
+ "learning_rate": 4.989714638030552e-05,
5076
+ "loss": 0.6821,
5077
+ "step": 7240
5078
+ },
5079
+ {
5080
+ "epoch": 3.689907556206145,
5081
+ "grad_norm": 0.1328129768371582,
5082
+ "learning_rate": 4.9897004317294894e-05,
5083
+ "loss": 0.6842,
5084
+ "step": 7250
5085
+ },
5086
+ {
5087
+ "epoch": 3.694999124886633,
5088
+ "grad_norm": 0.1081654503941536,
5089
+ "learning_rate": 4.989686225428427e-05,
5090
+ "loss": 0.6796,
5091
+ "step": 7260
5092
+ },
5093
+ {
5094
+ "epoch": 3.7000906935671214,
5095
+ "grad_norm": 0.09531684964895248,
5096
+ "learning_rate": 4.989672019127364e-05,
5097
+ "loss": 0.6833,
5098
+ "step": 7270
5099
+ },
5100
+ {
5101
+ "epoch": 3.705182262247609,
5102
+ "grad_norm": 0.10997920483350754,
5103
+ "learning_rate": 4.9896578128263013e-05,
5104
+ "loss": 0.6795,
5105
+ "step": 7280
5106
+ },
5107
+ {
5108
+ "epoch": 3.7102738309280974,
5109
+ "grad_norm": 0.15568581223487854,
5110
+ "learning_rate": 4.9896436065252387e-05,
5111
+ "loss": 0.6804,
5112
+ "step": 7290
5113
+ },
5114
+ {
5115
+ "epoch": 3.7153653996085856,
5116
+ "grad_norm": 0.130909726023674,
5117
+ "learning_rate": 4.989629400224175e-05,
5118
+ "loss": 0.6814,
5119
+ "step": 7300
5120
+ },
5121
+ {
5122
+ "epoch": 3.720456968289074,
5123
+ "grad_norm": 0.13917888700962067,
5124
+ "learning_rate": 4.9896151939231126e-05,
5125
+ "loss": 0.6793,
5126
+ "step": 7310
5127
+ },
5128
+ {
5129
+ "epoch": 3.725548536969562,
5130
+ "grad_norm": 0.12968967854976654,
5131
+ "learning_rate": 4.98960098762205e-05,
5132
+ "loss": 0.6819,
5133
+ "step": 7320
5134
+ },
5135
+ {
5136
+ "epoch": 3.73064010565005,
5137
+ "grad_norm": 0.12175523489713669,
5138
+ "learning_rate": 4.989586781320987e-05,
5139
+ "loss": 0.6785,
5140
+ "step": 7330
5141
+ },
5142
+ {
5143
+ "epoch": 3.7357316743305384,
5144
+ "grad_norm": 0.12431439012289047,
5145
+ "learning_rate": 4.9895725750199245e-05,
5146
+ "loss": 0.6785,
5147
+ "step": 7340
5148
+ },
5149
+ {
5150
+ "epoch": 3.740823243011026,
5151
+ "grad_norm": 0.1398157924413681,
5152
+ "learning_rate": 4.989558368718862e-05,
5153
+ "loss": 0.6779,
5154
+ "step": 7350
5155
+ },
5156
+ {
5157
+ "epoch": 3.745914811691515,
5158
+ "grad_norm": 0.11357001215219498,
5159
+ "learning_rate": 4.989544162417799e-05,
5160
+ "loss": 0.685,
5161
+ "step": 7360
5162
+ },
5163
+ {
5164
+ "epoch": 3.7510063803720026,
5165
+ "grad_norm": 0.16288457810878754,
5166
+ "learning_rate": 4.9895299561167365e-05,
5167
+ "loss": 0.6811,
5168
+ "step": 7370
5169
+ },
5170
+ {
5171
+ "epoch": 3.756097949052491,
5172
+ "grad_norm": 0.11568481475114822,
5173
+ "learning_rate": 4.989515749815674e-05,
5174
+ "loss": 0.6796,
5175
+ "step": 7380
5176
+ },
5177
+ {
5178
+ "epoch": 3.761189517732979,
5179
+ "grad_norm": 0.15195196866989136,
5180
+ "learning_rate": 4.989501543514611e-05,
5181
+ "loss": 0.6777,
5182
+ "step": 7390
5183
+ },
5184
+ {
5185
+ "epoch": 3.7662810864134673,
5186
+ "grad_norm": 0.12881244719028473,
5187
+ "learning_rate": 4.9894873372135484e-05,
5188
+ "loss": 0.6775,
5189
+ "step": 7400
5190
+ },
5191
+ {
5192
+ "epoch": 3.7713726550939555,
5193
+ "grad_norm": 0.1401291787624359,
5194
+ "learning_rate": 4.989473130912485e-05,
5195
+ "loss": 0.6834,
5196
+ "step": 7410
5197
+ },
5198
+ {
5199
+ "epoch": 3.7764642237744432,
5200
+ "grad_norm": 0.12248072773218155,
5201
+ "learning_rate": 4.9894589246114223e-05,
5202
+ "loss": 0.6792,
5203
+ "step": 7420
5204
+ },
5205
+ {
5206
+ "epoch": 3.781555792454932,
5207
+ "grad_norm": 0.11089824140071869,
5208
+ "learning_rate": 4.9894447183103596e-05,
5209
+ "loss": 0.6819,
5210
+ "step": 7430
5211
+ },
5212
+ {
5213
+ "epoch": 3.7866473611354197,
5214
+ "grad_norm": 0.09657898545265198,
5215
+ "learning_rate": 4.989430512009297e-05,
5216
+ "loss": 0.6841,
5217
+ "step": 7440
5218
+ },
5219
+ {
5220
+ "epoch": 3.791738929815908,
5221
+ "grad_norm": 0.12385948747396469,
5222
+ "learning_rate": 4.9894163057082336e-05,
5223
+ "loss": 0.6795,
5224
+ "step": 7450
5225
+ },
5226
+ {
5227
+ "epoch": 3.796830498496396,
5228
+ "grad_norm": 0.10562111437320709,
5229
+ "learning_rate": 4.989402099407171e-05,
5230
+ "loss": 0.6783,
5231
+ "step": 7460
5232
+ },
5233
+ {
5234
+ "epoch": 3.8019220671768843,
5235
+ "grad_norm": 0.11349403858184814,
5236
+ "learning_rate": 4.989387893106108e-05,
5237
+ "loss": 0.6807,
5238
+ "step": 7470
5239
+ },
5240
+ {
5241
+ "epoch": 3.8070136358573725,
5242
+ "grad_norm": 0.11444567143917084,
5243
+ "learning_rate": 4.9893736868050455e-05,
5244
+ "loss": 0.6791,
5245
+ "step": 7480
5246
+ },
5247
+ {
5248
+ "epoch": 3.8121052045378607,
5249
+ "grad_norm": 0.1610439121723175,
5250
+ "learning_rate": 4.989359480503983e-05,
5251
+ "loss": 0.6812,
5252
+ "step": 7490
5253
+ },
5254
+ {
5255
+ "epoch": 3.817196773218349,
5256
+ "grad_norm": 0.1214766800403595,
5257
+ "learning_rate": 4.98934527420292e-05,
5258
+ "loss": 0.6817,
5259
+ "step": 7500
5260
+ },
5261
+ {
5262
+ "epoch": 3.8222883418988367,
5263
+ "grad_norm": 0.12765400111675262,
5264
+ "learning_rate": 4.9893310679018575e-05,
5265
+ "loss": 0.6787,
5266
+ "step": 7510
5267
+ },
5268
+ {
5269
+ "epoch": 3.827379910579325,
5270
+ "grad_norm": 0.10731592029333115,
5271
+ "learning_rate": 4.989316861600795e-05,
5272
+ "loss": 0.683,
5273
+ "step": 7520
5274
+ },
5275
+ {
5276
+ "epoch": 3.832471479259813,
5277
+ "grad_norm": 0.12986642122268677,
5278
+ "learning_rate": 4.989302655299732e-05,
5279
+ "loss": 0.6766,
5280
+ "step": 7530
5281
+ },
5282
+ {
5283
+ "epoch": 3.8375630479403013,
5284
+ "grad_norm": 0.12156540900468826,
5285
+ "learning_rate": 4.9892884489986694e-05,
5286
+ "loss": 0.6834,
5287
+ "step": 7540
5288
+ },
5289
+ {
5290
+ "epoch": 3.8426546166207896,
5291
+ "grad_norm": 0.10650958865880966,
5292
+ "learning_rate": 4.989274242697606e-05,
5293
+ "loss": 0.6821,
5294
+ "step": 7550
5295
+ },
5296
+ {
5297
+ "epoch": 3.8477461853012778,
5298
+ "grad_norm": 0.09265447407960892,
5299
+ "learning_rate": 4.989260036396543e-05,
5300
+ "loss": 0.6807,
5301
+ "step": 7560
5302
+ },
5303
+ {
5304
+ "epoch": 3.852837753981766,
5305
+ "grad_norm": 0.13007622957229614,
5306
+ "learning_rate": 4.9892458300954806e-05,
5307
+ "loss": 0.681,
5308
+ "step": 7570
5309
+ },
5310
+ {
5311
+ "epoch": 3.8579293226622537,
5312
+ "grad_norm": 0.1033967137336731,
5313
+ "learning_rate": 4.989231623794418e-05,
5314
+ "loss": 0.686,
5315
+ "step": 7580
5316
+ },
5317
+ {
5318
+ "epoch": 3.8630208913427424,
5319
+ "grad_norm": 0.10867638140916824,
5320
+ "learning_rate": 4.989217417493355e-05,
5321
+ "loss": 0.6796,
5322
+ "step": 7590
5323
+ },
5324
+ {
5325
+ "epoch": 3.86811246002323,
5326
+ "grad_norm": 0.105263352394104,
5327
+ "learning_rate": 4.9892032111922926e-05,
5328
+ "loss": 0.6824,
5329
+ "step": 7600
5330
+ },
5331
+ {
5332
+ "epoch": 3.8732040287037184,
5333
+ "grad_norm": 0.12403067946434021,
5334
+ "learning_rate": 4.98918900489123e-05,
5335
+ "loss": 0.6793,
5336
+ "step": 7610
5337
+ },
5338
+ {
5339
+ "epoch": 3.8782955973842066,
5340
+ "grad_norm": 0.09988098591566086,
5341
+ "learning_rate": 4.989174798590167e-05,
5342
+ "loss": 0.6842,
5343
+ "step": 7620
5344
+ },
5345
+ {
5346
+ "epoch": 3.883387166064695,
5347
+ "grad_norm": 0.13452745974063873,
5348
+ "learning_rate": 4.9891605922891045e-05,
5349
+ "loss": 0.6811,
5350
+ "step": 7630
5351
+ },
5352
+ {
5353
+ "epoch": 3.888478734745183,
5354
+ "grad_norm": 0.10854171961545944,
5355
+ "learning_rate": 4.989146385988042e-05,
5356
+ "loss": 0.6827,
5357
+ "step": 7640
5358
+ },
5359
+ {
5360
+ "epoch": 3.893570303425671,
5361
+ "grad_norm": 0.10819829255342484,
5362
+ "learning_rate": 4.9891321796869784e-05,
5363
+ "loss": 0.6796,
5364
+ "step": 7650
5365
+ },
5366
+ {
5367
+ "epoch": 3.8986618721061594,
5368
+ "grad_norm": 0.17421726882457733,
5369
+ "learning_rate": 4.989117973385916e-05,
5370
+ "loss": 0.6808,
5371
+ "step": 7660
5372
+ },
5373
+ {
5374
+ "epoch": 3.903753440786647,
5375
+ "grad_norm": 0.13020376861095428,
5376
+ "learning_rate": 4.989103767084853e-05,
5377
+ "loss": 0.6796,
5378
+ "step": 7670
5379
+ },
5380
+ {
5381
+ "epoch": 3.9088450094671354,
5382
+ "grad_norm": 0.10870732367038727,
5383
+ "learning_rate": 4.9890895607837904e-05,
5384
+ "loss": 0.6867,
5385
+ "step": 7680
5386
+ },
5387
+ {
5388
+ "epoch": 3.9139365781476236,
5389
+ "grad_norm": 0.10249564051628113,
5390
+ "learning_rate": 4.989075354482727e-05,
5391
+ "loss": 0.6847,
5392
+ "step": 7690
5393
+ },
5394
+ {
5395
+ "epoch": 3.919028146828112,
5396
+ "grad_norm": 0.09583424031734467,
5397
+ "learning_rate": 4.989061148181664e-05,
5398
+ "loss": 0.6837,
5399
+ "step": 7700
5400
+ },
5401
+ {
5402
+ "epoch": 3.9241197155086,
5403
+ "grad_norm": 0.10090246796607971,
5404
+ "learning_rate": 4.9890469418806016e-05,
5405
+ "loss": 0.6814,
5406
+ "step": 7710
5407
+ },
5408
+ {
5409
+ "epoch": 3.9292112841890883,
5410
+ "grad_norm": 0.1201721727848053,
5411
+ "learning_rate": 4.989032735579539e-05,
5412
+ "loss": 0.6843,
5413
+ "step": 7720
5414
+ },
5415
+ {
5416
+ "epoch": 3.9343028528695765,
5417
+ "grad_norm": 0.11703382432460785,
5418
+ "learning_rate": 4.989018529278476e-05,
5419
+ "loss": 0.6784,
5420
+ "step": 7730
5421
+ },
5422
+ {
5423
+ "epoch": 3.9393944215500643,
5424
+ "grad_norm": 0.1226707398891449,
5425
+ "learning_rate": 4.9890043229774136e-05,
5426
+ "loss": 0.6847,
5427
+ "step": 7740
5428
+ },
5429
+ {
5430
+ "epoch": 3.9444859902305525,
5431
+ "grad_norm": 0.09304598718881607,
5432
+ "learning_rate": 4.988990116676351e-05,
5433
+ "loss": 0.6812,
5434
+ "step": 7750
5435
+ },
5436
+ {
5437
+ "epoch": 3.9495775589110407,
5438
+ "grad_norm": 0.10586468130350113,
5439
+ "learning_rate": 4.988975910375288e-05,
5440
+ "loss": 0.679,
5441
+ "step": 7760
5442
+ },
5443
+ {
5444
+ "epoch": 3.954669127591529,
5445
+ "grad_norm": 0.10969860106706619,
5446
+ "learning_rate": 4.9889617040742255e-05,
5447
+ "loss": 0.6826,
5448
+ "step": 7770
5449
+ },
5450
+ {
5451
+ "epoch": 3.959760696272017,
5452
+ "grad_norm": 0.1249874085187912,
5453
+ "learning_rate": 4.988947497773163e-05,
5454
+ "loss": 0.6767,
5455
+ "step": 7780
5456
+ },
5457
+ {
5458
+ "epoch": 3.9648522649525053,
5459
+ "grad_norm": 0.16480816900730133,
5460
+ "learning_rate": 4.9889332914721e-05,
5461
+ "loss": 0.6796,
5462
+ "step": 7790
5463
+ },
5464
+ {
5465
+ "epoch": 3.9699438336329935,
5466
+ "grad_norm": 0.2025347650051117,
5467
+ "learning_rate": 4.9889190851710374e-05,
5468
+ "loss": 0.678,
5469
+ "step": 7800
5470
+ },
5471
+ {
5472
+ "epoch": 3.9750354023134813,
5473
+ "grad_norm": 0.1153530701994896,
5474
+ "learning_rate": 4.988904878869974e-05,
5475
+ "loss": 0.6812,
5476
+ "step": 7810
5477
+ },
5478
+ {
5479
+ "epoch": 3.98012697099397,
5480
+ "grad_norm": 0.12336631864309311,
5481
+ "learning_rate": 4.9888906725689114e-05,
5482
+ "loss": 0.6781,
5483
+ "step": 7820
5484
+ },
5485
+ {
5486
+ "epoch": 3.9852185396744577,
5487
+ "grad_norm": 0.1417071670293808,
5488
+ "learning_rate": 4.988876466267849e-05,
5489
+ "loss": 0.6796,
5490
+ "step": 7830
5491
+ },
5492
+ {
5493
+ "epoch": 3.990310108354946,
5494
+ "grad_norm": 0.12677961587905884,
5495
+ "learning_rate": 4.988862259966786e-05,
5496
+ "loss": 0.6819,
5497
+ "step": 7840
5498
+ },
5499
+ {
5500
+ "epoch": 3.995401677035434,
5501
+ "grad_norm": 0.1134430319070816,
5502
+ "learning_rate": 4.988848053665723e-05,
5503
+ "loss": 0.6802,
5504
+ "step": 7850
5505
+ },
5506
+ {
5507
+ "epoch": 4.0,
5508
+ "grad_norm": 0.021812934428453445,
5509
+ "learning_rate": 4.98883384736466e-05,
5510
+ "loss": 0.6148,
5511
+ "step": 7860
5512
+ },
5513
+ {
5514
+ "epoch": 4.005091568680488,
5515
+ "grad_norm": 0.11325574666261673,
5516
+ "learning_rate": 4.988819641063597e-05,
5517
+ "loss": 0.6823,
5518
+ "step": 7870
5519
+ },
5520
+ {
5521
+ "epoch": 4.010183137360976,
5522
+ "grad_norm": 0.12439537793397903,
5523
+ "learning_rate": 4.9888054347625346e-05,
5524
+ "loss": 0.6808,
5525
+ "step": 7880
5526
+ },
5527
+ {
5528
+ "epoch": 4.015274706041464,
5529
+ "grad_norm": 0.11274933069944382,
5530
+ "learning_rate": 4.988791228461472e-05,
5531
+ "loss": 0.6828,
5532
+ "step": 7890
5533
+ },
5534
+ {
5535
+ "epoch": 4.020366274721953,
5536
+ "grad_norm": 0.10643935203552246,
5537
+ "learning_rate": 4.988777022160409e-05,
5538
+ "loss": 0.6833,
5539
+ "step": 7900
5540
+ },
5541
+ {
5542
+ "epoch": 4.025457843402441,
5543
+ "grad_norm": 0.0944155901670456,
5544
+ "learning_rate": 4.9887628158593465e-05,
5545
+ "loss": 0.6842,
5546
+ "step": 7910
5547
+ },
5548
+ {
5549
+ "epoch": 4.030549412082929,
5550
+ "grad_norm": 0.12772725522518158,
5551
+ "learning_rate": 4.988748609558284e-05,
5552
+ "loss": 0.6764,
5553
+ "step": 7920
5554
+ },
5555
+ {
5556
+ "epoch": 4.035640980763417,
5557
+ "grad_norm": 0.19370485842227936,
5558
+ "learning_rate": 4.988734403257221e-05,
5559
+ "loss": 0.6845,
5560
+ "step": 7930
5561
+ },
5562
+ {
5563
+ "epoch": 4.040732549443905,
5564
+ "grad_norm": 0.13512100279331207,
5565
+ "learning_rate": 4.9887201969561584e-05,
5566
+ "loss": 0.6745,
5567
+ "step": 7940
5568
+ },
5569
+ {
5570
+ "epoch": 4.0458241181243935,
5571
+ "grad_norm": 0.13933135569095612,
5572
+ "learning_rate": 4.988705990655095e-05,
5573
+ "loss": 0.6842,
5574
+ "step": 7950
5575
+ },
5576
+ {
5577
+ "epoch": 4.050915686804881,
5578
+ "grad_norm": 0.13375182449817657,
5579
+ "learning_rate": 4.9886917843540324e-05,
5580
+ "loss": 0.6815,
5581
+ "step": 7960
5582
+ },
5583
+ {
5584
+ "epoch": 4.05600725548537,
5585
+ "grad_norm": 0.11060313135385513,
5586
+ "learning_rate": 4.98867757805297e-05,
5587
+ "loss": 0.6798,
5588
+ "step": 7970
5589
+ },
5590
+ {
5591
+ "epoch": 4.061098824165858,
5592
+ "grad_norm": 0.14003530144691467,
5593
+ "learning_rate": 4.988663371751907e-05,
5594
+ "loss": 0.6787,
5595
+ "step": 7980
5596
+ },
5597
+ {
5598
+ "epoch": 4.066190392846346,
5599
+ "grad_norm": 0.10484720021486282,
5600
+ "learning_rate": 4.988649165450844e-05,
5601
+ "loss": 0.6818,
5602
+ "step": 7990
5603
+ },
5604
+ {
5605
+ "epoch": 4.071281961526834,
5606
+ "grad_norm": 0.11415210366249084,
5607
+ "learning_rate": 4.9886349591497816e-05,
5608
+ "loss": 0.6804,
5609
+ "step": 8000
5610
  }
5611
  ],
5612
  "logging_steps": 10,