Model save

README.md

@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/beit-base-patch16-224-pt22k-ft22k](https://huggingface.co/microsoft/beit-base-patch16-224-pt22k-ft22k) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2793
-- Accuracy: 0.9064
+- Loss: 0.2845
+- Accuracy: 0.9058
 
 ## Model description
 
@@ -52,7 +52,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.2928        | 1.0   | 351  | 0.2793          | 0.9064   |
+| 0.3075        | 1.0   | 351  | 0.2845          | 0.9058   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ece2e3c17008fe3b6d4b477a718862dd357be3ad078443815f0a5811c13a9e61
+oid sha256:6bb329a07c4eb6b2b7961946c2c08a15b76c73e46281764441d506d6e0585013
 size 343104936

runs/Apr24_11-55-23_MacBook-Pro.local/events.out.tfevents.1713930924.MacBook-Pro.local.24885.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffb5e85622fb39129b152c190b04972a06b1ec20080b042360d3a1043473c694
+size 13807

trainer_state.json

@@ -1,791 +1,283 @@
 {
-  "best_metric": 0.9224,
-  "best_model_checkpoint": "beit-base-patch16-224-pt22k-ft22k-finetuning/checkpoint-1053",
-  "epoch": 2.9936034115138592,
+  "best_metric": 0.9064,
+  "best_model_checkpoint": "beit-base-patch16-224-pt22k-ft22k-finetuning/checkpoint-351",
+  "epoch": 0.997867803837953,
   "eval_steps": 500,
-  "global_step": 1053,
+  "global_step": 351,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.03,
-      "grad_norm": 9.479050636291504,
-      "learning_rate": 4.716981132075472e-06,
-      "loss": 2.2425,
+      "grad_norm": 12.392043113708496,
+      "learning_rate": 1.388888888888889e-05,
+      "loss": 2.38,
       "step": 10
     },
     {
       "epoch": 0.06,
-      "grad_norm": 8.138527870178223,
-      "learning_rate": 9.433962264150944e-06,
-      "loss": 2.1135,
+      "grad_norm": 9.366357803344727,
+      "learning_rate": 2.777777777777778e-05,
+      "loss": 2.0468,
       "step": 20
     },
     {
       "epoch": 0.09,
-      "grad_norm": 10.681833267211914,
-      "learning_rate": 1.4150943396226415e-05,
-      "loss": 1.8603,
+      "grad_norm": 10.620584487915039,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 1.5116,
       "step": 30
     },
     {
       "epoch": 0.11,
-      "grad_norm": 11.454757690429688,
-      "learning_rate": 1.8867924528301888e-05,
-      "loss": 1.5269,
+      "grad_norm": 9.78640079498291,
+      "learning_rate": 4.936507936507937e-05,
+      "loss": 1.0056,
       "step": 40
     },
     {
       "epoch": 0.14,
-      "grad_norm": 9.449707984924316,
-      "learning_rate": 2.358490566037736e-05,
-      "loss": 1.2446,
+      "grad_norm": 7.943943977355957,
+      "learning_rate": 4.7777777777777784e-05,
+      "loss": 0.7888,
       "step": 50
     },
     {
       "epoch": 0.17,
-      "grad_norm": 8.522866249084473,
-      "learning_rate": 2.830188679245283e-05,
-      "loss": 0.9361,
+      "grad_norm": 9.149613380432129,
+      "learning_rate": 4.6190476190476194e-05,
+      "loss": 0.6486,
       "step": 60
     },
     {
       "epoch": 0.2,
-      "grad_norm": 10.076375007629395,
-      "learning_rate": 3.30188679245283e-05,
-      "loss": 0.8079,
+      "grad_norm": 7.764841079711914,
+      "learning_rate": 4.460317460317461e-05,
+      "loss": 0.6232,
       "step": 70
     },
     {
       "epoch": 0.23,
-      "grad_norm": 8.901982307434082,
-      "learning_rate": 3.7735849056603776e-05,
-      "loss": 0.6666,
+      "grad_norm": 8.434979438781738,
+      "learning_rate": 4.301587301587302e-05,
+      "loss": 0.5555,
       "step": 80
     },
     {
       "epoch": 0.26,
-      "grad_norm": 9.24902629852295,
-      "learning_rate": 4.245283018867925e-05,
-      "loss": 0.5786,
+      "grad_norm": 8.733748435974121,
+      "learning_rate": 4.1428571428571437e-05,
+      "loss": 0.4872,
       "step": 90
     },
     {
       "epoch": 0.28,
-      "grad_norm": 8.615540504455566,
-      "learning_rate": 4.716981132075472e-05,
-      "loss": 0.5429,
+      "grad_norm": 7.663728713989258,
+      "learning_rate": 3.984126984126984e-05,
+      "loss": 0.5385,
       "step": 100
     },
     {
       "epoch": 0.31,
-      "grad_norm": 8.308765411376953,
-      "learning_rate": 4.978880675818374e-05,
-      "loss": 0.5208,
+      "grad_norm": 6.9408698081970215,
+      "learning_rate": 3.8253968253968256e-05,
+      "loss": 0.4591,
       "step": 110
     },
     {
       "epoch": 0.34,
-      "grad_norm": 8.710918426513672,
-      "learning_rate": 4.9260823653643085e-05,
-      "loss": 0.4438,
+      "grad_norm": 6.367518424987793,
+      "learning_rate": 3.6666666666666666e-05,
+      "loss": 0.4449,
       "step": 120
     },
     {
       "epoch": 0.37,
-      "grad_norm": 7.1848883628845215,
-      "learning_rate": 4.8732840549102435e-05,
-      "loss": 0.4908,
+      "grad_norm": 6.589195728302002,
+      "learning_rate": 3.5079365079365075e-05,
+      "loss": 0.4365,
       "step": 130
     },
     {
       "epoch": 0.4,
-      "grad_norm": 8.183231353759766,
-      "learning_rate": 4.820485744456177e-05,
-      "loss": 0.5065,
+      "grad_norm": 8.5034818649292,
+      "learning_rate": 3.349206349206349e-05,
+      "loss": 0.4538,
       "step": 140
     },
     {
       "epoch": 0.43,
-      "grad_norm": 7.710569858551025,
-      "learning_rate": 4.767687434002112e-05,
-      "loss": 0.465,
+      "grad_norm": 6.432806491851807,
+      "learning_rate": 3.19047619047619e-05,
+      "loss": 0.4182,
       "step": 150
     },
     {
       "epoch": 0.45,
-      "grad_norm": 8.260108947753906,
-      "learning_rate": 4.7148891235480466e-05,
-      "loss": 0.3905,
+      "grad_norm": 5.926751613616943,
+      "learning_rate": 3.0317460317460318e-05,
+      "loss": 0.3683,
       "step": 160
     },
     {
       "epoch": 0.48,
-      "grad_norm": 7.832273960113525,
-      "learning_rate": 4.662090813093981e-05,
-      "loss": 0.4494,
+      "grad_norm": 7.516120433807373,
+      "learning_rate": 2.8730158730158728e-05,
+      "loss": 0.4315,
       "step": 170
     },
     {
       "epoch": 0.51,
-      "grad_norm": 9.597940444946289,
-      "learning_rate": 4.609292502639916e-05,
-      "loss": 0.4496,
+      "grad_norm": 7.042306423187256,
+      "learning_rate": 2.714285714285714e-05,
+      "loss": 0.3883,
       "step": 180
     },
     {
       "epoch": 0.54,
-      "grad_norm": 6.2265801429748535,
-      "learning_rate": 4.55649419218585e-05,
-      "loss": 0.4265,
+      "grad_norm": 6.7353620529174805,
+      "learning_rate": 2.5555555555555554e-05,
+      "loss": 0.4158,
       "step": 190
     },
     {
       "epoch": 0.57,
-      "grad_norm": 9.405741691589355,
-      "learning_rate": 4.503695881731785e-05,
-      "loss": 0.4206,
+      "grad_norm": 6.9553914070129395,
+      "learning_rate": 2.396825396825397e-05,
+      "loss": 0.3893,
       "step": 200
     },
     {
       "epoch": 0.6,
-      "grad_norm": 8.922151565551758,
-      "learning_rate": 4.45089757127772e-05,
-      "loss": 0.4134,
+      "grad_norm": 6.948991298675537,
+      "learning_rate": 2.2380952380952384e-05,
+      "loss": 0.4288,
       "step": 210
     },
     {
       "epoch": 0.63,
-      "grad_norm": 6.096219062805176,
-      "learning_rate": 4.398099260823654e-05,
-      "loss": 0.421,
+      "grad_norm": 6.90835428237915,
+      "learning_rate": 2.0793650793650797e-05,
+      "loss": 0.368,
       "step": 220
     },
     {
       "epoch": 0.65,
-      "grad_norm": 6.80384635925293,
-      "learning_rate": 4.3453009503695884e-05,
-      "loss": 0.4345,
+      "grad_norm": 7.47681999206543,
+      "learning_rate": 1.920634920634921e-05,
+      "loss": 0.4212,
       "step": 230
     },
     {
       "epoch": 0.68,
-      "grad_norm": 5.7122039794921875,
-      "learning_rate": 4.292502639915523e-05,
-      "loss": 0.4386,
+      "grad_norm": 5.4326887130737305,
+      "learning_rate": 1.761904761904762e-05,
+      "loss": 0.4101,
       "step": 240
     },
     {
       "epoch": 0.71,
-      "grad_norm": 7.819368839263916,
-      "learning_rate": 4.239704329461457e-05,
-      "loss": 0.4354,
+      "grad_norm": 5.068437576293945,
+      "learning_rate": 1.6031746031746033e-05,
+      "loss": 0.3544,
       "step": 250
     },
     {
       "epoch": 0.74,
-      "grad_norm": 6.497572422027588,
-      "learning_rate": 4.186906019007392e-05,
-      "loss": 0.3677,
+      "grad_norm": 5.686431884765625,
+      "learning_rate": 1.4444444444444444e-05,
+      "loss": 0.3252,
       "step": 260
     },
     {
       "epoch": 0.77,
-      "grad_norm": 5.012016773223877,
-      "learning_rate": 4.1341077085533265e-05,
-      "loss": 0.4049,
+      "grad_norm": 5.882190227508545,
+      "learning_rate": 1.2857142857142857e-05,
+      "loss": 0.3475,
       "step": 270
     },
     {
       "epoch": 0.8,
-      "grad_norm": 5.9180450439453125,
-      "learning_rate": 4.081309398099261e-05,
-      "loss": 0.3871,
+      "grad_norm": 6.3953447341918945,
+      "learning_rate": 1.126984126984127e-05,
+      "loss": 0.3164,
       "step": 280
     },
     {
       "epoch": 0.82,
-      "grad_norm": 7.166804313659668,
-      "learning_rate": 4.028511087645195e-05,
-      "loss": 0.3545,
+      "grad_norm": 7.278485298156738,
+      "learning_rate": 9.682539682539683e-06,
+      "loss": 0.328,
       "step": 290
     },
     {
       "epoch": 0.85,
-      "grad_norm": 6.181870937347412,
-      "learning_rate": 3.97571277719113e-05,
-      "loss": 0.35,
+      "grad_norm": 6.7763166427612305,
+      "learning_rate": 8.095238095238097e-06,
+      "loss": 0.3463,
       "step": 300
     },
     {
       "epoch": 0.88,
-      "grad_norm": 6.4544806480407715,
-      "learning_rate": 3.9229144667370646e-05,
-      "loss": 0.339,
+      "grad_norm": 7.21019172668457,
+      "learning_rate": 6.507936507936509e-06,
+      "loss": 0.3762,
       "step": 310
     },
     {
       "epoch": 0.91,
-      "grad_norm": 8.781305313110352,
-      "learning_rate": 3.870116156282999e-05,
-      "loss": 0.4282,
+      "grad_norm": 8.0834379196167,
+      "learning_rate": 4.920634920634921e-06,
+      "loss": 0.3538,
       "step": 320
     },
     {
       "epoch": 0.94,
-      "grad_norm": 6.926518440246582,
-      "learning_rate": 3.817317845828934e-05,
-      "loss": 0.4072,
+      "grad_norm": 5.969318389892578,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.3159,
       "step": 330
     },
     {
       "epoch": 0.97,
-      "grad_norm": 6.435988426208496,
-      "learning_rate": 3.764519535374868e-05,
-      "loss": 0.3408,
+      "grad_norm": 7.134821891784668,
+      "learning_rate": 1.7460317460317462e-06,
+      "loss": 0.3528,
       "step": 340
     },
     {
       "epoch": 1.0,
-      "grad_norm": 6.354813098907471,
-      "learning_rate": 3.711721224920803e-05,
-      "loss": 0.3798,
+      "grad_norm": 6.126035213470459,
+      "learning_rate": 1.5873015873015874e-07,
+      "loss": 0.2928,
       "step": 350
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.8946,
-      "eval_loss": 0.31227919459342957,
-      "eval_runtime": 77.5515,
-      "eval_samples_per_second": 64.473,
-      "eval_steps_per_second": 2.024,
+      "eval_accuracy": 0.9064,
+      "eval_loss": 0.27925798296928406,
+      "eval_runtime": 77.4382,
+      "eval_samples_per_second": 64.568,
+      "eval_steps_per_second": 2.027,
       "step": 351
     },
     {
-      "epoch": 1.02,
-      "grad_norm": 5.809684753417969,
-      "learning_rate": 3.658922914466738e-05,
-      "loss": 0.3424,
-      "step": 360
-    },
-    {
-      "epoch": 1.05,
-      "grad_norm": 6.263907432556152,
-      "learning_rate": 3.6061246040126714e-05,
-      "loss": 0.3069,
-      "step": 370
-    },
-    {
-      "epoch": 1.08,
-      "grad_norm": 8.363096237182617,
-      "learning_rate": 3.5533262935586064e-05,
-      "loss": 0.3473,
-      "step": 380
-    },
-    {
-      "epoch": 1.11,
-      "grad_norm": 6.790135860443115,
-      "learning_rate": 3.500527983104541e-05,
-      "loss": 0.3535,
-      "step": 390
-    },
-    {
-      "epoch": 1.14,
-      "grad_norm": 8.508023262023926,
-      "learning_rate": 3.447729672650475e-05,
-      "loss": 0.3268,
-      "step": 400
-    },
-    {
-      "epoch": 1.17,
-      "grad_norm": 5.332359313964844,
-      "learning_rate": 3.3949313621964095e-05,
-      "loss": 0.3268,
-      "step": 410
-    },
-    {
-      "epoch": 1.19,
-      "grad_norm": 6.856630325317383,
-      "learning_rate": 3.3421330517423445e-05,
-      "loss": 0.3457,
-      "step": 420
-    },
-    {
-      "epoch": 1.22,
-      "grad_norm": 5.920594692230225,
-      "learning_rate": 3.289334741288279e-05,
-      "loss": 0.3679,
-      "step": 430
-    },
-    {
-      "epoch": 1.25,
-      "grad_norm": 5.812190532684326,
-      "learning_rate": 3.236536430834213e-05,
-      "loss": 0.308,
-      "step": 440
-    },
-    {
-      "epoch": 1.28,
-      "grad_norm": 6.633917331695557,
-      "learning_rate": 3.183738120380148e-05,
-      "loss": 0.3281,
-      "step": 450
-    },
-    {
-      "epoch": 1.31,
-      "grad_norm": 5.8134765625,
-      "learning_rate": 3.130939809926082e-05,
-      "loss": 0.339,
-      "step": 460
-    },
-    {
-      "epoch": 1.34,
-      "grad_norm": 5.8948469161987305,
-      "learning_rate": 3.078141499472017e-05,
-      "loss": 0.3301,
-      "step": 470
-    },
-    {
-      "epoch": 1.36,
-      "grad_norm": 6.114367485046387,
-      "learning_rate": 3.0253431890179517e-05,
-      "loss": 0.3007,
-      "step": 480
-    },
-    {
-      "epoch": 1.39,
-      "grad_norm": 6.723957061767578,
-      "learning_rate": 2.972544878563886e-05,
-      "loss": 0.2715,
-      "step": 490
-    },
-    {
-      "epoch": 1.42,
-      "grad_norm": 5.948746204376221,
-      "learning_rate": 2.9197465681098207e-05,
-      "loss": 0.3744,
-      "step": 500
-    },
-    {
-      "epoch": 1.45,
-      "grad_norm": 5.837756156921387,
-      "learning_rate": 2.8669482576557548e-05,
-      "loss": 0.3052,
-      "step": 510
-    },
-    {
-      "epoch": 1.48,
-      "grad_norm": 6.875099182128906,
-      "learning_rate": 2.8141499472016898e-05,
-      "loss": 0.3015,
-      "step": 520
-    },
-    {
-      "epoch": 1.51,
-      "grad_norm": 7.579908847808838,
-      "learning_rate": 2.7613516367476245e-05,
-      "loss": 0.2579,
-      "step": 530
-    },
-    {
-      "epoch": 1.54,
-      "grad_norm": 4.934197425842285,
-      "learning_rate": 2.7085533262935585e-05,
-      "loss": 0.3418,
-      "step": 540
-    },
-    {
-      "epoch": 1.56,
-      "grad_norm": 9.131146430969238,
-      "learning_rate": 2.6557550158394935e-05,
-      "loss": 0.2899,
-      "step": 550
-    },
-    {
-      "epoch": 1.59,
-      "grad_norm": 6.872548580169678,
-      "learning_rate": 2.6029567053854276e-05,
-      "loss": 0.2993,
-      "step": 560
-    },
-    {
-      "epoch": 1.62,
-      "grad_norm": 8.35107421875,
-      "learning_rate": 2.5501583949313622e-05,
-      "loss": 0.2975,
-      "step": 570
-    },
-    {
-      "epoch": 1.65,
-      "grad_norm": 4.690518856048584,
-      "learning_rate": 2.497360084477297e-05,
-      "loss": 0.2765,
-      "step": 580
-    },
-    {
-      "epoch": 1.68,
-      "grad_norm": 5.886472702026367,
-      "learning_rate": 2.4445617740232313e-05,
-      "loss": 0.3069,
-      "step": 590
-    },
-    {
-      "epoch": 1.71,
-      "grad_norm": 7.0965728759765625,
-      "learning_rate": 2.391763463569166e-05,
-      "loss": 0.3047,
-      "step": 600
-    },
-    {
-      "epoch": 1.73,
-      "grad_norm": 7.900537967681885,
-      "learning_rate": 2.3389651531151003e-05,
-      "loss": 0.321,
-      "step": 610
-    },
-    {
-      "epoch": 1.76,
-      "grad_norm": 7.129281520843506,
-      "learning_rate": 2.286166842661035e-05,
-      "loss": 0.3105,
-      "step": 620
-    },
-    {
-      "epoch": 1.79,
-      "grad_norm": 6.3763885498046875,
-      "learning_rate": 2.2333685322069694e-05,
-      "loss": 0.29,
-      "step": 630
-    },
-    {
-      "epoch": 1.82,
-      "grad_norm": 5.745955467224121,
-      "learning_rate": 2.180570221752904e-05,
-      "loss": 0.2943,
-      "step": 640
-    },
-    {
-      "epoch": 1.85,
-      "grad_norm": 4.876988410949707,
-      "learning_rate": 2.1277719112988384e-05,
-      "loss": 0.2532,
-      "step": 650
-    },
-    {
-      "epoch": 1.88,
-      "grad_norm": 6.255117893218994,
-      "learning_rate": 2.074973600844773e-05,
-      "loss": 0.2546,
-      "step": 660
-    },
-    {
-      "epoch": 1.9,
-      "grad_norm": 7.397041320800781,
-      "learning_rate": 2.0221752903907075e-05,
-      "loss": 0.2986,
-      "step": 670
-    },
-    {
-      "epoch": 1.93,
-      "grad_norm": 5.720653533935547,
-      "learning_rate": 1.9693769799366422e-05,
-      "loss": 0.2859,
-      "step": 680
-    },
-    {
-      "epoch": 1.96,
-      "grad_norm": 6.6954450607299805,
-      "learning_rate": 1.9165786694825765e-05,
-      "loss": 0.2715,
-      "step": 690
-    },
-    {
-      "epoch": 1.99,
-      "grad_norm": 7.738607883453369,
-      "learning_rate": 1.863780359028511e-05,
-      "loss": 0.2948,
-      "step": 700
-    },
-    {
-      "epoch": 2.0,
-      "eval_accuracy": 0.9144,
-      "eval_loss": 0.25623753666877747,
-      "eval_runtime": 77.3678,
-      "eval_samples_per_second": 64.626,
-      "eval_steps_per_second": 2.029,
-      "step": 703
-    },
-    {
-      "epoch": 2.02,
-      "grad_norm": 6.120700836181641,
-      "learning_rate": 1.810982048574446e-05,
-      "loss": 0.2239,
-      "step": 710
-    },
-    {
-      "epoch": 2.05,
-      "grad_norm": 5.4925408363342285,
-      "learning_rate": 1.7581837381203803e-05,
-      "loss": 0.2551,
-      "step": 720
-    },
-    {
-      "epoch": 2.08,
-      "grad_norm": 6.947438716888428,
-      "learning_rate": 1.7053854276663146e-05,
-      "loss": 0.2559,
-      "step": 730
-    },
-    {
-      "epoch": 2.1,
-      "grad_norm": 6.124309062957764,
-      "learning_rate": 1.6525871172122493e-05,
-      "loss": 0.2771,
-      "step": 740
-    },
-    {
-      "epoch": 2.13,
-      "grad_norm": 5.241459846496582,
-      "learning_rate": 1.5997888067581837e-05,
-      "loss": 0.2948,
-      "step": 750
-    },
-    {
-      "epoch": 2.16,
-      "grad_norm": 5.5829339027404785,
-      "learning_rate": 1.5469904963041184e-05,
-      "loss": 0.2878,
-      "step": 760
-    },
-    {
-      "epoch": 2.19,
-      "grad_norm": 5.310808181762695,
-      "learning_rate": 1.4941921858500529e-05,
-      "loss": 0.2529,
-      "step": 770
-    },
-    {
-      "epoch": 2.22,
-      "grad_norm": 6.5644402503967285,
-      "learning_rate": 1.4413938753959874e-05,
-      "loss": 0.2399,
-      "step": 780
-    },
-    {
-      "epoch": 2.25,
-      "grad_norm": 5.379487991333008,
-      "learning_rate": 1.388595564941922e-05,
-      "loss": 0.246,
-      "step": 790
-    },
-    {
-      "epoch": 2.27,
-      "grad_norm": 4.701766014099121,
-      "learning_rate": 1.3357972544878563e-05,
-      "loss": 0.2331,
-      "step": 800
-    },
-    {
-      "epoch": 2.3,
-      "grad_norm": 7.020758152008057,
-      "learning_rate": 1.2829989440337912e-05,
-      "loss": 0.2393,
-      "step": 810
-    },
-    {
-      "epoch": 2.33,
-      "grad_norm": 5.2000532150268555,
-      "learning_rate": 1.2302006335797255e-05,
-      "loss": 0.2586,
-      "step": 820
-    },
-    {
-      "epoch": 2.36,
-      "grad_norm": 7.7929840087890625,
-      "learning_rate": 1.17740232312566e-05,
-      "loss": 0.2585,
-      "step": 830
-    },
-    {
-      "epoch": 2.39,
-      "grad_norm": 4.547289848327637,
-      "learning_rate": 1.1246040126715946e-05,
-      "loss": 0.2856,
-      "step": 840
-    },
-    {
-      "epoch": 2.42,
-      "grad_norm": 6.17247200012207,
-      "learning_rate": 1.0718057022175291e-05,
-      "loss": 0.2284,
-      "step": 850
-    },
-    {
-      "epoch": 2.44,
-      "grad_norm": 6.217990875244141,
-      "learning_rate": 1.0190073917634636e-05,
-      "loss": 0.2471,
-      "step": 860
-    },
-    {
-      "epoch": 2.47,
-      "grad_norm": 7.083463191986084,
-      "learning_rate": 9.662090813093982e-06,
-      "loss": 0.2501,
-      "step": 870
-    },
-    {
-      "epoch": 2.5,
-      "grad_norm": 5.3397064208984375,
-      "learning_rate": 9.134107708553327e-06,
-      "loss": 0.2432,
-      "step": 880
-    },
-    {
-      "epoch": 2.53,
-      "grad_norm": 5.868465900421143,
-      "learning_rate": 8.606124604012672e-06,
-      "loss": 0.2288,
-      "step": 890
-    },
-    {
-      "epoch": 2.56,
-      "grad_norm": 6.825480937957764,
-      "learning_rate": 8.078141499472017e-06,
-      "loss": 0.2611,
-      "step": 900
-    },
-    {
-      "epoch": 2.59,
-      "grad_norm": 7.371336460113525,
-      "learning_rate": 7.5501583949313625e-06,
-      "loss": 0.2431,
-      "step": 910
-    },
-    {
-      "epoch": 2.62,
-      "grad_norm": 6.281027793884277,
-      "learning_rate": 7.022175290390708e-06,
-      "loss": 0.2325,
-      "step": 920
-    },
-    {
-      "epoch": 2.64,
-      "grad_norm": 5.377941131591797,
-      "learning_rate": 6.494192185850054e-06,
-      "loss": 0.2619,
-      "step": 930
-    },
-    {
-      "epoch": 2.67,
-      "grad_norm": 6.657591342926025,
-      "learning_rate": 5.966209081309398e-06,
-      "loss": 0.2351,
-      "step": 940
-    },
-    {
-      "epoch": 2.7,
-      "grad_norm": 3.635580062866211,
-      "learning_rate": 5.438225976768744e-06,
-      "loss": 0.2279,
-      "step": 950
-    },
-    {
-      "epoch": 2.73,
-      "grad_norm": 6.4966254234313965,
-      "learning_rate": 4.910242872228089e-06,
-      "loss": 0.1984,
-      "step": 960
-    },
-    {
-      "epoch": 2.76,
-      "grad_norm": 5.066717147827148,
-      "learning_rate": 4.382259767687434e-06,
-      "loss": 0.2446,
-      "step": 970
-    },
-    {
-      "epoch": 2.79,
-      "grad_norm": 7.539534568786621,
-      "learning_rate": 3.854276663146779e-06,
-      "loss": 0.244,
-      "step": 980
-    },
-    {
-      "epoch": 2.81,
-      "grad_norm": 6.701014995574951,
-      "learning_rate": 3.326293558606125e-06,
-      "loss": 0.2179,
-      "step": 990
-    },
-    {
-      "epoch": 2.84,
-      "grad_norm": 5.286581039428711,
-      "learning_rate": 2.79831045406547e-06,
-      "loss": 0.2421,
-      "step": 1000
-    },
-    {
-      "epoch": 2.87,
-      "grad_norm": 6.469656944274902,
-      "learning_rate": 2.2703273495248154e-06,
-      "loss": 0.2407,
-      "step": 1010
-    },
-    {
-      "epoch": 2.9,
-      "grad_norm": 5.72628927230835,
-      "learning_rate": 1.7423442449841606e-06,
-      "loss": 0.2467,
-      "step": 1020
-    },
-    {
-      "epoch": 2.93,
-      "grad_norm": 5.319166660308838,
-      "learning_rate": 1.2143611404435059e-06,
-      "loss": 0.1996,
-      "step": 1030
-    },
-    {
-      "epoch": 2.96,
-      "grad_norm": 4.705040454864502,
-      "learning_rate": 6.863780359028511e-07,
-      "loss": 0.2177,
-      "step": 1040
-    },
-    {
-      "epoch": 2.99,
-      "grad_norm": 5.496118545532227,
-      "learning_rate": 1.5839493136219642e-07,
-      "loss": 0.2219,
-      "step": 1050
-    },
-    {
-      "epoch": 2.99,
-      "eval_accuracy": 0.9224,
-      "eval_loss": 0.22844760119915009,
-      "eval_runtime": 76.1837,
-      "eval_samples_per_second": 65.631,
-      "eval_steps_per_second": 2.061,
-      "step": 1053
-    },
-    {
-      "epoch": 2.99,
-      "step": 1053,
-      "total_flos": 1.043724675699553e+19,
-      "train_loss": 0.4028786985736061,
-      "train_runtime": 6766.1281,
-      "train_samples_per_second": 19.952,
+      "epoch": 1.0,
+      "step": 351,
+      "total_flos": 3.4803216831306793e+18,
+      "train_loss": 0.5742807560666674,
+      "train_runtime": 2256.218,
+      "train_samples_per_second": 19.945,
       "train_steps_per_second": 0.156
     }
   ],
   "logging_steps": 10,
-  "max_steps": 1053,
+  "max_steps": 351,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
+  "num_train_epochs": 1,
   "save_steps": 500,
-  "total_flos": 1.043724675699553e+19,
+  "total_flos": 3.4803216831306793e+18,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9bf959740b0f9759fabba3a48accfacd787f02b06e9a4a4634372fd98dd91db
+oid sha256:d57d1c28952cf47fe8f1d59584b92b1b3768b94604b5907f47ce9583f5416a4d
 size 4984