Training in progress, step 200, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5742327392312dd1a7e23ca028cd9e6187add4ba8fb99e3a28ce17d8dbe3b26
+oid sha256:f7818cb9e8dda5e969179fa08e8dd35b115d5074a67004905fa566419d85bb77
 size 234681136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2a1a873a10876a3541cbda1bda6ef5a52202b10618859918417990065cc8b5c
+oid sha256:8dc22d80526ad400ab0440e70c39e50b019ae3f83f519ccbb65d3d05ae38552d
 size 469516363

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78f00cbf2a3a4305cbfbe0a453688d1bb898224da36be2f067d77db0d73462c1
+oid sha256:ca0548a1b90eaf6590b9f6afac3530aaed1157198c5a087c4229ad15001933d9
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4dcd0fcafdf0cac56c6781c9554680e5d2ba9bfee0d823975791d1d648a00172
+oid sha256:17980325c36d869e063d721782688706e0e30902ea32568d55af1c62cc6c3e6f
 size 1465

last-checkpoint/trainer_state.json

@@ -11,314 +11,314 @@
   "log_history": [
     {
       "epoch": 0.0016666666666666668,
-      "grad_norm": 0.140625,
-      "learning_rate": 1.6000000000000003e-05,
-      "loss": 2.6374650955200196,
+      "grad_norm": 0.419921875,
+      "learning_rate": 0.0002,
+      "loss": 2.7259506225585937,
       "step": 5
     },
     {
       "epoch": 0.0033333333333333335,
-      "grad_norm": 0.050537109375,
-      "learning_rate": 3.6e-05,
-      "loss": 2.6133955001831053,
+      "grad_norm": 0.326171875,
+      "learning_rate": 0.00045000000000000004,
+      "loss": 2.7605268478393556,
       "step": 10
     },
     {
       "epoch": 0.005,
-      "grad_norm": 0.03466796875,
-      "learning_rate": 5.6000000000000006e-05,
-      "loss": 2.6178274154663086,
+      "grad_norm": 0.490234375,
+      "learning_rate": 0.0005,
+      "loss": 2.717021179199219,
       "step": 15
     },
     {
       "epoch": 0.006666666666666667,
-      "grad_norm": 0.037109375,
-      "learning_rate": 7.6e-05,
-      "loss": 2.624565315246582,
+      "grad_norm": 0.267578125,
+      "learning_rate": 0.0005,
+      "loss": 2.661177635192871,
       "step": 20
     },
     {
       "epoch": 0.008333333333333333,
-      "grad_norm": 0.6328125,
-      "learning_rate": 9.6e-05,
-      "loss": 2.619654655456543,
+      "grad_norm": 0.43359375,
+      "learning_rate": 0.0005,
+      "loss": 2.671949768066406,
       "step": 25
     },
     {
       "epoch": 0.01,
-      "grad_norm": 0.036376953125,
-      "learning_rate": 0.0001,
-      "loss": 2.609416389465332,
+      "grad_norm": 0.10595703125,
+      "learning_rate": 0.0005,
+      "loss": 2.673902893066406,
       "step": 30
     },
     {
       "epoch": 0.011666666666666667,
-      "grad_norm": 0.06591796875,
-      "learning_rate": 0.0001,
-      "loss": 2.6385807037353515,
+      "grad_norm": 0.21875,
+      "learning_rate": 0.0005,
+      "loss": 2.686188316345215,
       "step": 35
     },
     {
       "epoch": 0.013333333333333334,
-      "grad_norm": 0.041748046875,
-      "learning_rate": 0.0001,
-      "loss": 2.6341808319091795,
+      "grad_norm": 0.087890625,
+      "learning_rate": 0.0005,
+      "loss": 2.6556489944458006,
       "step": 40
     },
     {
       "epoch": 0.015,
-      "grad_norm": 0.03662109375,
-      "learning_rate": 0.0001,
-      "loss": 2.6163944244384765,
+      "grad_norm": 0.119140625,
+      "learning_rate": 0.0005,
+      "loss": 2.66821346282959,
       "step": 45
     },
     {
       "epoch": 0.016666666666666666,
-      "grad_norm": 0.50390625,
-      "learning_rate": 0.0001,
-      "loss": 2.620637893676758,
+      "grad_norm": 0.095703125,
+      "learning_rate": 0.0005,
+      "loss": 2.6468021392822267,
       "step": 50
     },
     {
       "epoch": 0.016666666666666666,
-      "eval_loss": 3.0298774242401123,
-      "eval_runtime": 4.5343,
-      "eval_samples_per_second": 65.722,
-      "eval_steps_per_second": 3.749,
+      "eval_loss": 3.0268919467926025,
+      "eval_runtime": 4.7731,
+      "eval_samples_per_second": 31.217,
+      "eval_steps_per_second": 3.562,
       "step": 50
     },
     {
       "epoch": 0.018333333333333333,
-      "grad_norm": 0.1689453125,
-      "learning_rate": 0.0001,
-      "loss": 2.6260648727416993,
+      "grad_norm": 139.0,
+      "learning_rate": 0.0005,
+      "loss": 2.6445695877075197,
       "step": 55
     },
     {
       "epoch": 0.02,
-      "grad_norm": 0.047607421875,
-      "learning_rate": 0.0001,
-      "loss": 2.6460687637329103,
+      "grad_norm": 0.65234375,
+      "learning_rate": 0.0005,
+      "loss": 2.645796775817871,
       "step": 60
     },
     {
       "epoch": 0.021666666666666667,
-      "grad_norm": 0.0380859375,
-      "learning_rate": 0.0001,
-      "loss": 2.6157953262329103,
+      "grad_norm": 0.07421875,
+      "learning_rate": 0.0005,
+      "loss": 2.6811267852783205,
       "step": 65
     },
     {
       "epoch": 0.023333333333333334,
-      "grad_norm": 0.0986328125,
-      "learning_rate": 0.0001,
-      "loss": 2.61843318939209,
+      "grad_norm": 0.08642578125,
+      "learning_rate": 0.0005,
+      "loss": 2.6605648040771483,
       "step": 70
     },
     {
       "epoch": 0.025,
-      "grad_norm": 0.04931640625,
-      "learning_rate": 0.0001,
-      "loss": 2.651448059082031,
+      "grad_norm": 0.275390625,
+      "learning_rate": 0.0005,
+      "loss": 2.668781852722168,
       "step": 75
     },
     {
       "epoch": 0.02666666666666667,
-      "grad_norm": 0.038330078125,
-      "learning_rate": 0.0001,
-      "loss": 2.59826545715332,
+      "grad_norm": 0.0693359375,
+      "learning_rate": 0.0005,
+      "loss": 2.6526798248291015,
       "step": 80
     },
     {
       "epoch": 0.028333333333333332,
-      "grad_norm": 0.042724609375,
-      "learning_rate": 0.0001,
-      "loss": 2.6349016189575196,
+      "grad_norm": 0.427734375,
+      "learning_rate": 0.0005,
+      "loss": 2.6234062194824217,
       "step": 85
     },
     {
       "epoch": 0.03,
-      "grad_norm": 0.036376953125,
-      "learning_rate": 0.0001,
-      "loss": 2.6166595458984374,
+      "grad_norm": 0.08447265625,
+      "learning_rate": 0.0005,
+      "loss": 2.6748191833496096,
       "step": 90
     },
     {
       "epoch": 0.03166666666666667,
-      "grad_norm": 0.74609375,
-      "learning_rate": 0.0001,
-      "loss": 2.6394269943237303,
+      "grad_norm": 0.08544921875,
+      "learning_rate": 0.0005,
+      "loss": 2.665359878540039,
       "step": 95
     },
     {
       "epoch": 0.03333333333333333,
-      "grad_norm": 0.032958984375,
-      "learning_rate": 0.0001,
-      "loss": 2.6080867767333986,
+      "grad_norm": 0.2734375,
+      "learning_rate": 0.0005,
+      "loss": 2.6298377990722654,
       "step": 100
     },
     {
       "epoch": 0.03333333333333333,
-      "eval_loss": 3.0300662517547607,
-      "eval_runtime": 4.4357,
-      "eval_samples_per_second": 67.181,
-      "eval_steps_per_second": 3.832,
+      "eval_loss": 3.037663221359253,
+      "eval_runtime": 4.6626,
+      "eval_samples_per_second": 31.956,
+      "eval_steps_per_second": 3.646,
       "step": 100
     },
     {
       "epoch": 0.035,
-      "grad_norm": 0.036376953125,
-      "learning_rate": 0.0001,
-      "loss": 2.6302499771118164,
+      "grad_norm": 0.1865234375,
+      "learning_rate": 0.0005,
+      "loss": 2.639477348327637,
       "step": 105
     },
     {
       "epoch": 0.03666666666666667,
-      "grad_norm": 0.042724609375,
-      "learning_rate": 0.0001,
-      "loss": 2.646461296081543,
+      "grad_norm": 0.1376953125,
+      "learning_rate": 0.0005,
+      "loss": 2.671689987182617,
       "step": 110
     },
     {
       "epoch": 0.03833333333333333,
-      "grad_norm": 0.05517578125,
-      "learning_rate": 0.0001,
-      "loss": 2.6076818466186524,
+      "grad_norm": 0.078125,
+      "learning_rate": 0.0005,
+      "loss": 2.6607818603515625,
       "step": 115
     },
     {
       "epoch": 0.04,
-      "grad_norm": 0.032470703125,
-      "learning_rate": 0.0001,
-      "loss": 2.616958236694336,
+      "grad_norm": 0.06494140625,
+      "learning_rate": 0.0005,
+      "loss": 2.6763479232788088,
       "step": 120
     },
     {
       "epoch": 0.041666666666666664,
-      "grad_norm": 0.12353515625,
-      "learning_rate": 0.0001,
-      "loss": 2.603002166748047,
+      "grad_norm": 0.96875,
+      "learning_rate": 0.0005,
+      "loss": 2.6471065521240233,
       "step": 125
     },
     {
       "epoch": 0.043333333333333335,
-      "grad_norm": 0.034912109375,
-      "learning_rate": 0.0001,
-      "loss": 2.6103355407714846,
+      "grad_norm": 0.076171875,
+      "learning_rate": 0.0005,
+      "loss": 2.643071746826172,
       "step": 130
     },
     {
       "epoch": 0.045,
-      "grad_norm": 1.1484375,
-      "learning_rate": 0.0001,
-      "loss": 2.599276542663574,
+      "grad_norm": 0.10400390625,
+      "learning_rate": 0.0005,
+      "loss": 2.6617103576660157,
       "step": 135
     },
     {
       "epoch": 0.04666666666666667,
-      "grad_norm": 0.034912109375,
-      "learning_rate": 0.0001,
-      "loss": 2.590505599975586,
+      "grad_norm": 0.06640625,
+      "learning_rate": 0.0005,
+      "loss": 2.617737579345703,
       "step": 140
     },
     {
       "epoch": 0.04833333333333333,
-      "grad_norm": 0.03857421875,
-      "learning_rate": 0.0001,
-      "loss": 2.627636528015137,
+      "grad_norm": 0.3984375,
+      "learning_rate": 0.0005,
+      "loss": 2.7076738357543944,
       "step": 145
     },
     {
       "epoch": 0.05,
-      "grad_norm": 262.0,
-      "learning_rate": 0.0001,
-      "loss": 2.6068201065063477,
+      "grad_norm": 0.09375,
+      "learning_rate": 0.0005,
+      "loss": 2.6471235275268556,
       "step": 150
     },
     {
       "epoch": 0.05,
-      "eval_loss": 3.0302553176879883,
-      "eval_runtime": 4.3841,
-      "eval_samples_per_second": 67.972,
-      "eval_steps_per_second": 3.878,
+      "eval_loss": 3.055941581726074,
+      "eval_runtime": 4.6673,
+      "eval_samples_per_second": 31.924,
+      "eval_steps_per_second": 3.642,
       "step": 150
     },
     {
       "epoch": 0.051666666666666666,
-      "grad_norm": 0.359375,
-      "learning_rate": 0.0001,
-      "loss": 2.617295265197754,
+      "grad_norm": 0.08642578125,
+      "learning_rate": 0.0005,
+      "loss": 2.6089550018310548,
       "step": 155
     },
     {
       "epoch": 0.05333333333333334,
-      "grad_norm": 0.078125,
-      "learning_rate": 0.0001,
-      "loss": 2.601869010925293,
+      "grad_norm": 0.61328125,
+      "learning_rate": 0.0005,
+      "loss": 2.6288101196289064,
       "step": 160
     },
     {
       "epoch": 0.055,
-      "grad_norm": 0.06494140625,
-      "learning_rate": 0.0001,
-      "loss": 2.613315391540527,
+      "grad_norm": 0.0703125,
+      "learning_rate": 0.0005,
+      "loss": 2.647333335876465,
       "step": 165
     },
     {
       "epoch": 0.056666666666666664,
-      "grad_norm": 0.039794921875,
-      "learning_rate": 0.0001,
-      "loss": 2.601426124572754,
+      "grad_norm": 0.06689453125,
+      "learning_rate": 0.0005,
+      "loss": 2.6732242584228514,
       "step": 170
     },
     {
       "epoch": 0.058333333333333334,
-      "grad_norm": 0.035888671875,
-      "learning_rate": 0.0001,
-      "loss": 2.5963130950927735,
+      "grad_norm": 0.060791015625,
+      "learning_rate": 0.0005,
+      "loss": 2.6399274826049806,
       "step": 175
     },
     {
       "epoch": 0.06,
-      "grad_norm": 0.036376953125,
-      "learning_rate": 0.0001,
-      "loss": 2.614262008666992,
+      "grad_norm": 0.059326171875,
+      "learning_rate": 0.0005,
+      "loss": 2.6433204650878905,
       "step": 180
     },
     {
       "epoch": 0.06166666666666667,
-      "grad_norm": 0.0380859375,
-      "learning_rate": 0.0001,
-      "loss": 2.6094554901123046,
+      "grad_norm": 0.05712890625,
+      "learning_rate": 0.0005,
+      "loss": 2.6490320205688476,
       "step": 185
     },
     {
       "epoch": 0.06333333333333334,
-      "grad_norm": 0.064453125,
-      "learning_rate": 0.0001,
-      "loss": 2.6106592178344727,
+      "grad_norm": 0.0830078125,
+      "learning_rate": 0.0005,
+      "loss": 2.6651992797851562,
       "step": 190
     },
     {
       "epoch": 0.065,
-      "grad_norm": 0.037353515625,
-      "learning_rate": 0.0001,
-      "loss": 2.604322814941406,
+      "grad_norm": 0.0712890625,
+      "learning_rate": 0.0005,
+      "loss": 2.6375024795532225,
       "step": 195
     },
     {
       "epoch": 0.06666666666666667,
-      "grad_norm": 0.03955078125,
-      "learning_rate": 0.0001,
-      "loss": 2.5981882095336912,
+      "grad_norm": 0.07763671875,
+      "learning_rate": 0.0005,
+      "loss": 2.616963768005371,
       "step": 200
     },
     {
       "epoch": 0.06666666666666667,
-      "eval_loss": 3.0292723178863525,
-      "eval_runtime": 4.3967,
-      "eval_samples_per_second": 67.777,
-      "eval_steps_per_second": 3.866,
+      "eval_loss": 3.0367250442504883,
+      "eval_runtime": 4.6782,
+      "eval_samples_per_second": 31.85,
+      "eval_steps_per_second": 3.634,
       "step": 200
     }
   ],
@@ -339,8 +339,8 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.304618059431936e+17,
-  "train_batch_size": 18,
+  "total_flos": 6.52309029715968e+16,
+  "train_batch_size": 9,
   "trial_name": null,
   "trial_params": null
 }

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fa13de9d6de96ae7af42b5d8ce1dda570123e506d560d8d7900c3522fff7dfe
+oid sha256:8120bbf745be8a2e230b2b8e6929b1ee58e282eec5683185cd975c85928dd837
 size 5265