up

README.md

@@ -15,7 +15,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/byt5-small](https://huggingface.co/google/byt5-small) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.6233
+- eval_loss: 0.0003
+- eval_runtime: 10.8156
+- eval_samples_per_second: 924.594
+- eval_steps_per_second: 1.202
+- epoch: 51.0
+- step: 1275
 
 ## Model description
 
@@ -35,23 +40,12 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 512
-- eval_batch_size: 512
+- train_batch_size: 800
+- eval_batch_size: 800
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 5
-
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 20   | 1.6871          |
-| No log        | 2.0   | 40   | 1.6487          |
-| No log        | 3.0   | 60   | 1.6341          |
-| No log        | 4.0   | 80   | 1.6265          |
-| No log        | 5.0   | 100  | 1.6233          |
-
+- num_epochs: 200
 
 ### Framework versions
 

logs/{events.out.tfevents.1713583532.ip-10-25-205-144.8598.1 → events.out.tfevents.1713584966.ip-10-25-205-144.8598.2}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0606f1fd4f0eb3bb34ab3f703b623aeda9872640ed11a13ebc0b4ff408eb4c09
-size 6235
+oid sha256:1622dc30e39ec98a6db41321ae4a2ad655d6460bdcd56135aaacc64a58038e99
+size 4184

logs/events.out.tfevents.1713585132.ip-10-25-205-144.16362.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c66862786a75e24d84e1f7ff6f90f1ed3417efe3ef777f95b76e762d33cbcdc1
+size 4532

logs/events.out.tfevents.1713585198.ip-10-25-205-144.16362.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20786f07317093aa2b445bf6b95739504832b1916ce8a468c33a54ac9f6a2e6a
+size 18642

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd6f85555e522847c8c8942e262aca1936610e6dd7600aa223cad99dbe45de90
+oid sha256:fca102473377c7785f2f31f5a10961b290d7b0dc9b1d016d7f634b661502fea9
 size 1198571496

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8b23f2643085930b3f7349662bcb04749807424fe293d7a34fd2c4acb9f8cc0
+oid sha256:30957abcccff359d558399a21aae87ea1caffa62712a96bf816b14b90779b594
 size 2397245434

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7dbc7ace80ecdadeb29c581e017512420cee0602278ec068e2fe06794142a50a
+oid sha256:cf53929ac8580a64da717c50cb8e706c6b73ed8e123b0f2ed70a2d025d0be0cf
 size 14244

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcd60da393ff67ad2f08779377eeaa08189a6bf520f752442788825d9bce1449
+oid sha256:50d8e9838b612e3fef6825e76644fa188469427c8cabb80bf0d1aa1704101d1c
 size 1064

trainer_state.json

@@ -1,59 +1,439 @@
 {
-  "best_metric": 1.6233268976211548,
-  "best_model_checkpoint": "AlexWang99/byt5_add/checkpoint-100",
-  "epoch": 5.0,
+  "best_metric": 0.00030898803379386663,
+  "best_model_checkpoint": "AlexWang99/byt5_add/checkpoint-1275",
+  "epoch": 51.0,
   "eval_steps": 500,
-  "global_step": 100,
+  "global_step": 1275,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 1.6871496438980103,
-      "eval_runtime": 12.4033,
-      "eval_samples_per_second": 806.234,
-      "eval_steps_per_second": 1.612,
-      "step": 20
+      "eval_loss": 1.747314691543579,
+      "eval_runtime": 11.1213,
+      "eval_samples_per_second": 899.172,
+      "eval_steps_per_second": 1.169,
+      "step": 25
     },
     {
       "epoch": 2.0,
-      "eval_loss": 1.6486749649047852,
-      "eval_runtime": 12.4805,
-      "eval_samples_per_second": 801.251,
-      "eval_steps_per_second": 1.603,
-      "step": 40
+      "eval_loss": 1.6477937698364258,
+      "eval_runtime": 10.7967,
+      "eval_samples_per_second": 926.209,
+      "eval_steps_per_second": 1.204,
+      "step": 50
     },
     {
       "epoch": 3.0,
-      "eval_loss": 1.6341347694396973,
-      "eval_runtime": 12.3858,
-      "eval_samples_per_second": 807.376,
-      "eval_steps_per_second": 1.615,
-      "step": 60
+      "eval_loss": 1.5999796390533447,
+      "eval_runtime": 10.8098,
+      "eval_samples_per_second": 925.089,
+      "eval_steps_per_second": 1.203,
+      "step": 75
     },
     {
       "epoch": 4.0,
-      "eval_loss": 1.6265267133712769,
-      "eval_runtime": 12.382,
-      "eval_samples_per_second": 807.624,
-      "eval_steps_per_second": 1.615,
-      "step": 80
+      "eval_loss": 1.4885144233703613,
+      "eval_runtime": 10.8417,
+      "eval_samples_per_second": 922.367,
+      "eval_steps_per_second": 1.199,
+      "step": 100
     },
     {
       "epoch": 5.0,
-      "eval_loss": 1.6233268976211548,
-      "eval_runtime": 12.4067,
-      "eval_samples_per_second": 806.016,
-      "eval_steps_per_second": 1.612,
-      "step": 100
+      "eval_loss": 1.3953396081924438,
+      "eval_runtime": 10.8419,
+      "eval_samples_per_second": 922.345,
+      "eval_steps_per_second": 1.199,
+      "step": 125
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 1.2306207418441772,
+      "eval_runtime": 10.8327,
+      "eval_samples_per_second": 923.131,
+      "eval_steps_per_second": 1.2,
+      "step": 150
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 1.0172127485275269,
+      "eval_runtime": 10.8404,
+      "eval_samples_per_second": 922.478,
+      "eval_steps_per_second": 1.199,
+      "step": 175
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 0.7508996725082397,
+      "eval_runtime": 10.867,
+      "eval_samples_per_second": 920.221,
+      "eval_steps_per_second": 1.196,
+      "step": 200
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 0.5204245448112488,
+      "eval_runtime": 10.837,
+      "eval_samples_per_second": 922.761,
+      "eval_steps_per_second": 1.2,
+      "step": 225
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 0.3563512861728668,
+      "eval_runtime": 11.004,
+      "eval_samples_per_second": 908.763,
+      "eval_steps_per_second": 1.181,
+      "step": 250
+    },
+    {
+      "epoch": 11.0,
+      "eval_loss": 0.3062296211719513,
+      "eval_runtime": 10.8369,
+      "eval_samples_per_second": 922.772,
+      "eval_steps_per_second": 1.2,
+      "step": 275
+    },
+    {
+      "epoch": 12.0,
+      "eval_loss": 0.23057429492473602,
+      "eval_runtime": 10.799,
+      "eval_samples_per_second": 926.015,
+      "eval_steps_per_second": 1.204,
+      "step": 300
+    },
+    {
+      "epoch": 13.0,
+      "eval_loss": 0.17026692628860474,
+      "eval_runtime": 10.8267,
+      "eval_samples_per_second": 923.643,
+      "eval_steps_per_second": 1.201,
+      "step": 325
+    },
+    {
+      "epoch": 14.0,
+      "eval_loss": 0.14094401895999908,
+      "eval_runtime": 10.8171,
+      "eval_samples_per_second": 924.461,
+      "eval_steps_per_second": 1.202,
+      "step": 350
+    },
+    {
+      "epoch": 15.0,
+      "eval_loss": 0.11562483012676239,
+      "eval_runtime": 10.8544,
+      "eval_samples_per_second": 921.286,
+      "eval_steps_per_second": 1.198,
+      "step": 375
+    },
+    {
+      "epoch": 16.0,
+      "eval_loss": 0.1076672226190567,
+      "eval_runtime": 10.7997,
+      "eval_samples_per_second": 925.947,
+      "eval_steps_per_second": 1.204,
+      "step": 400
+    },
+    {
+      "epoch": 17.0,
+      "eval_loss": 0.07891710102558136,
+      "eval_runtime": 10.8355,
+      "eval_samples_per_second": 922.895,
+      "eval_steps_per_second": 1.2,
+      "step": 425
+    },
+    {
+      "epoch": 18.0,
+      "eval_loss": 0.07825633883476257,
+      "eval_runtime": 10.9577,
+      "eval_samples_per_second": 912.598,
+      "eval_steps_per_second": 1.186,
+      "step": 450
+    },
+    {
+      "epoch": 19.0,
+      "eval_loss": 0.053240709006786346,
+      "eval_runtime": 10.8407,
+      "eval_samples_per_second": 922.45,
+      "eval_steps_per_second": 1.199,
+      "step": 475
+    },
+    {
+      "epoch": 20.0,
+      "learning_rate": 4.5e-05,
+      "loss": 0.8626,
+      "step": 500
+    },
+    {
+      "epoch": 20.0,
+      "eval_loss": 0.03896724432706833,
+      "eval_runtime": 10.8919,
+      "eval_samples_per_second": 918.117,
+      "eval_steps_per_second": 1.194,
+      "step": 500
+    },
+    {
+      "epoch": 21.0,
+      "eval_loss": 0.0326126404106617,
+      "eval_runtime": 10.9808,
+      "eval_samples_per_second": 910.682,
+      "eval_steps_per_second": 1.184,
+      "step": 525
+    },
+    {
+      "epoch": 22.0,
+      "eval_loss": 0.026844095438718796,
+      "eval_runtime": 10.8647,
+      "eval_samples_per_second": 920.415,
+      "eval_steps_per_second": 1.197,
+      "step": 550
+    },
+    {
+      "epoch": 23.0,
+      "eval_loss": 0.022708676755428314,
+      "eval_runtime": 11.1211,
+      "eval_samples_per_second": 899.191,
+      "eval_steps_per_second": 1.169,
+      "step": 575
+    },
+    {
+      "epoch": 24.0,
+      "eval_loss": 0.020555635914206505,
+      "eval_runtime": 10.8169,
+      "eval_samples_per_second": 924.48,
+      "eval_steps_per_second": 1.202,
+      "step": 600
+    },
+    {
+      "epoch": 25.0,
+      "eval_loss": 0.016072452068328857,
+      "eval_runtime": 10.8195,
+      "eval_samples_per_second": 924.261,
+      "eval_steps_per_second": 1.202,
+      "step": 625
+    },
+    {
+      "epoch": 26.0,
+      "eval_loss": 0.015775442123413086,
+      "eval_runtime": 11.0521,
+      "eval_samples_per_second": 904.809,
+      "eval_steps_per_second": 1.176,
+      "step": 650
+    },
+    {
+      "epoch": 27.0,
+      "eval_loss": 0.010050756856799126,
+      "eval_runtime": 10.96,
+      "eval_samples_per_second": 912.407,
+      "eval_steps_per_second": 1.186,
+      "step": 675
+    },
+    {
+      "epoch": 28.0,
+      "eval_loss": 0.009800990112125874,
+      "eval_runtime": 10.8085,
+      "eval_samples_per_second": 925.196,
+      "eval_steps_per_second": 1.203,
+      "step": 700
+    },
+    {
+      "epoch": 29.0,
+      "eval_loss": 0.0077048842795193195,
+      "eval_runtime": 10.9528,
+      "eval_samples_per_second": 913.005,
+      "eval_steps_per_second": 1.187,
+      "step": 725
+    },
+    {
+      "epoch": 30.0,
+      "eval_loss": 0.005685885436832905,
+      "eval_runtime": 10.9631,
+      "eval_samples_per_second": 912.147,
+      "eval_steps_per_second": 1.186,
+      "step": 750
+    },
+    {
+      "epoch": 31.0,
+      "eval_loss": 0.006655455566942692,
+      "eval_runtime": 10.8367,
+      "eval_samples_per_second": 922.788,
+      "eval_steps_per_second": 1.2,
+      "step": 775
+    },
+    {
+      "epoch": 32.0,
+      "eval_loss": 0.004621443338692188,
+      "eval_runtime": 10.8165,
+      "eval_samples_per_second": 924.51,
+      "eval_steps_per_second": 1.202,
+      "step": 800
+    },
+    {
+      "epoch": 33.0,
+      "eval_loss": 0.0033882376737892628,
+      "eval_runtime": 10.9293,
+      "eval_samples_per_second": 914.976,
+      "eval_steps_per_second": 1.189,
+      "step": 825
+    },
+    {
+      "epoch": 34.0,
+      "eval_loss": 0.0038037376943975687,
+      "eval_runtime": 10.7973,
+      "eval_samples_per_second": 926.155,
+      "eval_steps_per_second": 1.204,
+      "step": 850
+    },
+    {
+      "epoch": 35.0,
+      "eval_loss": 0.003371346276253462,
+      "eval_runtime": 10.834,
+      "eval_samples_per_second": 923.021,
+      "eval_steps_per_second": 1.2,
+      "step": 875
+    },
+    {
+      "epoch": 36.0,
+      "eval_loss": 0.0024659824557602406,
+      "eval_runtime": 10.7902,
+      "eval_samples_per_second": 926.766,
+      "eval_steps_per_second": 1.205,
+      "step": 900
+    },
+    {
+      "epoch": 37.0,
+      "eval_loss": 0.0022366114426404238,
+      "eval_runtime": 10.8096,
+      "eval_samples_per_second": 925.1,
+      "eval_steps_per_second": 1.203,
+      "step": 925
+    },
+    {
+      "epoch": 38.0,
+      "eval_loss": 0.0022026619408279657,
+      "eval_runtime": 10.8109,
+      "eval_samples_per_second": 924.992,
+      "eval_steps_per_second": 1.202,
+      "step": 950
+    },
+    {
+      "epoch": 39.0,
+      "eval_loss": 0.0024010157212615013,
+      "eval_runtime": 11.1034,
+      "eval_samples_per_second": 900.623,
+      "eval_steps_per_second": 1.171,
+      "step": 975
+    },
+    {
+      "epoch": 40.0,
+      "learning_rate": 4e-05,
+      "loss": 0.0919,
+      "step": 1000
+    },
+    {
+      "epoch": 40.0,
+      "eval_loss": 0.0013342766324058175,
+      "eval_runtime": 10.7511,
+      "eval_samples_per_second": 930.139,
+      "eval_steps_per_second": 1.209,
+      "step": 1000
+    },
+    {
+      "epoch": 41.0,
+      "eval_loss": 0.0016493805451318622,
+      "eval_runtime": 10.7987,
+      "eval_samples_per_second": 926.034,
+      "eval_steps_per_second": 1.204,
+      "step": 1025
+    },
+    {
+      "epoch": 42.0,
+      "eval_loss": 0.001088765449821949,
+      "eval_runtime": 10.8106,
+      "eval_samples_per_second": 925.017,
+      "eval_steps_per_second": 1.203,
+      "step": 1050
+    },
+    {
+      "epoch": 43.0,
+      "eval_loss": 0.0009081660537049174,
+      "eval_runtime": 10.7945,
+      "eval_samples_per_second": 926.398,
+      "eval_steps_per_second": 1.204,
+      "step": 1075
+    },
+    {
+      "epoch": 44.0,
+      "eval_loss": 0.0007170450408011675,
+      "eval_runtime": 10.9388,
+      "eval_samples_per_second": 914.174,
+      "eval_steps_per_second": 1.188,
+      "step": 1100
+    },
+    {
+      "epoch": 45.0,
+      "eval_loss": 0.0006850157515145838,
+      "eval_runtime": 10.8231,
+      "eval_samples_per_second": 923.948,
+      "eval_steps_per_second": 1.201,
+      "step": 1125
+    },
+    {
+      "epoch": 46.0,
+      "eval_loss": 0.0007588361040689051,
+      "eval_runtime": 10.9442,
+      "eval_samples_per_second": 913.729,
+      "eval_steps_per_second": 1.188,
+      "step": 1150
+    },
+    {
+      "epoch": 47.0,
+      "eval_loss": 0.0007894792361184955,
+      "eval_runtime": 10.9394,
+      "eval_samples_per_second": 914.125,
+      "eval_steps_per_second": 1.188,
+      "step": 1175
+    },
+    {
+      "epoch": 48.0,
+      "eval_loss": 0.0004850537225138396,
+      "eval_runtime": 10.8141,
+      "eval_samples_per_second": 924.722,
+      "eval_steps_per_second": 1.202,
+      "step": 1200
+    },
+    {
+      "epoch": 49.0,
+      "eval_loss": 0.0003986251540482044,
+      "eval_runtime": 10.7964,
+      "eval_samples_per_second": 926.231,
+      "eval_steps_per_second": 1.204,
+      "step": 1225
+    },
+    {
+      "epoch": 50.0,
+      "eval_loss": 0.0005350292194634676,
+      "eval_runtime": 10.9488,
+      "eval_samples_per_second": 913.343,
+      "eval_steps_per_second": 1.187,
+      "step": 1250
+    },
+    {
+      "epoch": 51.0,
+      "eval_loss": 0.00030898803379386663,
+      "eval_runtime": 10.8156,
+      "eval_samples_per_second": 924.594,
+      "eval_steps_per_second": 1.202,
+      "step": 1275
     }
   ],
   "logging_steps": 500,
-  "max_steps": 100,
-  "num_train_epochs": 5,
+  "max_steps": 5000,
+  "num_train_epochs": 200,
   "save_steps": 500,
-  "total_flos": 1435546214400000.0,
+  "total_flos": 2.928514277376e+16,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e8b5c9766275bc0bd47f9cd5e0eeb351509bdb9ad29146ec950b20b28980e67
+oid sha256:714811acdbc411e9172b3493c4b9194e7296d94c31ad1d94203d6c55f1d9c32b
 size 4792