End of training

README.md

@@ -21,7 +21,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.6956521739130435
+      value: 0.7391304347826086
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,8 +31,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [MBZUAI/swiftformer-xs](https://huggingface.co/MBZUAI/swiftformer-xs) on the imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.2611
-- Accuracy: 0.6957
+- Loss: 0.8596
+- Accuracy: 0.7391
 
 ## Model description
 

all_results.json

@@ -1,12 +1,12 @@
 {
     "epoch": 34.29,
-    "eval_accuracy": 0.6521739130434783,
-    "eval_loss": 1.3718501329421997,
-    "eval_runtime": 0.6737,
-    "eval_samples_per_second": 68.283,
-    "eval_steps_per_second": 4.453,
-    "train_loss": 1.3757717927296957,
-    "train_runtime": 134.1596,
-    "train_samples_per_second": 63.506,
-    "train_steps_per_second": 0.894
+    "eval_accuracy": 0.7391304347826086,
+    "eval_loss": 0.8596428632736206,
+    "eval_runtime": 0.9842,
+    "eval_samples_per_second": 46.737,
+    "eval_steps_per_second": 3.048,
+    "train_loss": 0.7088598291079203,
+    "train_runtime": 131.3917,
+    "train_samples_per_second": 64.844,
+    "train_steps_per_second": 0.913
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 34.29,
-    "eval_accuracy": 0.6521739130434783,
-    "eval_loss": 1.3718501329421997,
-    "eval_runtime": 0.6737,
-    "eval_samples_per_second": 68.283,
-    "eval_steps_per_second": 4.453
+    "eval_accuracy": 0.7391304347826086,
+    "eval_loss": 0.8596428632736206,
+    "eval_runtime": 0.9842,
+    "eval_samples_per_second": 46.737,
+    "eval_steps_per_second": 3.048
 }

runs/Dec02_12-51-56_DESKTOP-SKBE9FB/events.out.tfevents.1733165661.DESKTOP-SKBE9FB.7092.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d052b2c6e4f23f0e29dfd9afd38ee6e9f02b3ac41f2aeecd09bce6ddffcd1bef
+size 405

train_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 34.29,
-    "train_loss": 1.3757717927296957,
-    "train_runtime": 134.1596,
-    "train_samples_per_second": 63.506,
-    "train_steps_per_second": 0.894
+    "train_loss": 0.7088598291079203,
+    "train_runtime": 131.3917,
+    "train_samples_per_second": 64.844,
+    "train_steps_per_second": 0.913
 }

trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.6521739130434783,
-  "best_model_checkpoint": "swiftformer-xs-DMAE\\checkpoint-63",
+  "best_metric": 0.7391304347826086,
+  "best_model_checkpoint": "swiftformer-xs-DMAE\\checkpoint-45",
   "epoch": 34.285714285714285,
   "eval_steps": 500,
   "global_step": 120,
@@ -10,399 +10,399 @@
   "log_history": [
     {
       "epoch": 0.86,
-      "eval_accuracy": 0.32608695652173914,
-      "eval_loss": 1.386176347732544,
-      "eval_runtime": 0.6912,
-      "eval_samples_per_second": 66.555,
-      "eval_steps_per_second": 4.341,
+      "eval_accuracy": 0.45652173913043476,
+      "eval_loss": 1.3835715055465698,
+      "eval_runtime": 0.849,
+      "eval_samples_per_second": 54.181,
+      "eval_steps_per_second": 3.534,
       "step": 3
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.4782608695652174,
-      "eval_loss": 1.3856920003890991,
-      "eval_runtime": 0.6031,
-      "eval_samples_per_second": 76.266,
-      "eval_steps_per_second": 4.974,
+      "eval_accuracy": 0.6521739130434783,
+      "eval_loss": 1.3326613903045654,
+      "eval_runtime": 0.6171,
+      "eval_samples_per_second": 74.538,
+      "eval_steps_per_second": 4.861,
       "step": 7
     },
     {
       "epoch": 2.86,
-      "learning_rate": 1.3983050847457627e-05,
-      "loss": 1.3859,
+      "learning_rate": 0.00125,
+      "loss": 1.3567,
       "step": 10
     },
     {
       "epoch": 2.86,
-      "eval_accuracy": 0.5434782608695652,
-      "eval_loss": 1.3849265575408936,
-      "eval_runtime": 0.6417,
-      "eval_samples_per_second": 71.69,
-      "eval_steps_per_second": 4.675,
+      "eval_accuracy": 0.6521739130434783,
+      "eval_loss": 1.168088436126709,
+      "eval_runtime": 0.6072,
+      "eval_samples_per_second": 75.764,
+      "eval_steps_per_second": 4.941,
       "step": 10
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.6086956521739131,
-      "eval_loss": 1.383913516998291,
-      "eval_runtime": 0.6412,
-      "eval_samples_per_second": 71.74,
-      "eval_steps_per_second": 4.679,
+      "eval_accuracy": 0.5652173913043478,
+      "eval_loss": 1.044042944908142,
+      "eval_runtime": 0.6302,
+      "eval_samples_per_second": 72.998,
+      "eval_steps_per_second": 4.761,
       "step": 14
     },
     {
       "epoch": 4.86,
-      "eval_accuracy": 0.6086956521739131,
-      "eval_loss": 1.3834460973739624,
-      "eval_runtime": 0.5931,
-      "eval_samples_per_second": 77.552,
-      "eval_steps_per_second": 5.058,
+      "eval_accuracy": 0.6304347826086957,
+      "eval_loss": 1.0461686849594116,
+      "eval_runtime": 0.6512,
+      "eval_samples_per_second": 70.643,
+      "eval_steps_per_second": 4.607,
       "step": 17
     },
     {
       "epoch": 5.71,
-      "learning_rate": 1.2711864406779661e-05,
-      "loss": 1.3844,
+      "learning_rate": 0.001388888888888889,
+      "loss": 1.0903,
       "step": 20
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.6086956521739131,
-      "eval_loss": 1.3825335502624512,
-      "eval_runtime": 0.6087,
-      "eval_samples_per_second": 75.569,
-      "eval_steps_per_second": 4.928,
+      "eval_accuracy": 0.5869565217391305,
+      "eval_loss": 0.9293990731239319,
+      "eval_runtime": 0.6116,
+      "eval_samples_per_second": 75.207,
+      "eval_steps_per_second": 4.905,
       "step": 21
     },
     {
       "epoch": 6.86,
-      "eval_accuracy": 0.5869565217391305,
-      "eval_loss": 1.3820101022720337,
-      "eval_runtime": 0.6081,
-      "eval_samples_per_second": 75.639,
-      "eval_steps_per_second": 4.933,
+      "eval_accuracy": 0.6521739130434783,
+      "eval_loss": 0.9571677446365356,
+      "eval_runtime": 0.6031,
+      "eval_samples_per_second": 76.268,
+      "eval_steps_per_second": 4.974,
       "step": 24
     },
     {
       "epoch": 8.0,
-      "eval_accuracy": 0.5869565217391305,
-      "eval_loss": 1.3811701536178589,
-      "eval_runtime": 0.6908,
-      "eval_samples_per_second": 66.594,
-      "eval_steps_per_second": 4.343,
+      "eval_accuracy": 0.6739130434782609,
+      "eval_loss": 0.9286340475082397,
+      "eval_runtime": 0.6212,
+      "eval_samples_per_second": 74.056,
+      "eval_steps_per_second": 4.83,
       "step": 28
     },
     {
       "epoch": 8.57,
-      "learning_rate": 1.1440677966101694e-05,
-      "loss": 1.3831,
+      "learning_rate": 0.00125,
+      "loss": 1.0969,
       "step": 30
     },
     {
       "epoch": 8.86,
       "eval_accuracy": 0.6304347826086957,
-      "eval_loss": 1.3803642988204956,
-      "eval_runtime": 0.6012,
-      "eval_samples_per_second": 76.518,
-      "eval_steps_per_second": 4.99,
+      "eval_loss": 0.9229152798652649,
+      "eval_runtime": 0.6537,
+      "eval_samples_per_second": 70.374,
+      "eval_steps_per_second": 4.59,
       "step": 31
     },
     {
       "epoch": 10.0,
-      "eval_accuracy": 0.6086956521739131,
-      "eval_loss": 1.3793443441390991,
-      "eval_runtime": 0.6652,
-      "eval_samples_per_second": 69.156,
-      "eval_steps_per_second": 4.51,
+      "eval_accuracy": 0.6521739130434783,
+      "eval_loss": 0.9061374664306641,
+      "eval_runtime": 0.6311,
+      "eval_samples_per_second": 72.884,
+      "eval_steps_per_second": 4.753,
       "step": 35
     },
     {
       "epoch": 10.86,
-      "eval_accuracy": 0.6086956521739131,
-      "eval_loss": 1.3787044286727905,
-      "eval_runtime": 0.6567,
-      "eval_samples_per_second": 70.052,
-      "eval_steps_per_second": 4.569,
+      "eval_accuracy": 0.6739130434782609,
+      "eval_loss": 0.8341346383094788,
+      "eval_runtime": 0.6232,
+      "eval_samples_per_second": 73.818,
+      "eval_steps_per_second": 4.814,
       "step": 38
     },
     {
       "epoch": 11.43,
-      "learning_rate": 1.016949152542373e-05,
-      "loss": 1.3815,
+      "learning_rate": 0.0011111111111111111,
+      "loss": 0.8923,
       "step": 40
     },
     {
       "epoch": 12.0,
-      "eval_accuracy": 0.6086956521739131,
-      "eval_loss": 1.377792477607727,
-      "eval_runtime": 0.5967,
-      "eval_samples_per_second": 77.096,
-      "eval_steps_per_second": 5.028,
+      "eval_accuracy": 0.6739130434782609,
+      "eval_loss": 0.878592848777771,
+      "eval_runtime": 0.6071,
+      "eval_samples_per_second": 75.766,
+      "eval_steps_per_second": 4.941,
       "step": 42
     },
     {
       "epoch": 12.86,
-      "eval_accuracy": 0.6086956521739131,
-      "eval_loss": 1.3767056465148926,
-      "eval_runtime": 0.6238,
-      "eval_samples_per_second": 73.738,
-      "eval_steps_per_second": 4.809,
+      "eval_accuracy": 0.7391304347826086,
+      "eval_loss": 0.8596428632736206,
+      "eval_runtime": 0.6192,
+      "eval_samples_per_second": 74.295,
+      "eval_steps_per_second": 4.845,
       "step": 45
     },
     {
       "epoch": 14.0,
-      "eval_accuracy": 0.6086956521739131,
-      "eval_loss": 1.375701904296875,
-      "eval_runtime": 0.6527,
-      "eval_samples_per_second": 70.481,
-      "eval_steps_per_second": 4.597,
+      "eval_accuracy": 0.717391304347826,
+      "eval_loss": 0.8902113437652588,
+      "eval_runtime": 0.6051,
+      "eval_samples_per_second": 76.016,
+      "eval_steps_per_second": 4.958,
       "step": 49
     },
     {
       "epoch": 14.29,
-      "learning_rate": 8.898305084745763e-06,
-      "loss": 1.3794,
+      "learning_rate": 0.0009722222222222222,
+      "loss": 0.7289,
       "step": 50
     },
     {
       "epoch": 14.86,
-      "eval_accuracy": 0.6086956521739131,
-      "eval_loss": 1.3748270273208618,
-      "eval_runtime": 0.6441,
-      "eval_samples_per_second": 71.412,
-      "eval_steps_per_second": 4.657,
+      "eval_accuracy": 0.6739130434782609,
+      "eval_loss": 0.8024305105209351,
+      "eval_runtime": 0.6026,
+      "eval_samples_per_second": 76.33,
+      "eval_steps_per_second": 4.978,
       "step": 52
     },
     {
       "epoch": 16.0,
-      "eval_accuracy": 0.6304347826086957,
-      "eval_loss": 1.3738356828689575,
-      "eval_runtime": 0.6412,
-      "eval_samples_per_second": 71.742,
-      "eval_steps_per_second": 4.679,
+      "eval_accuracy": 0.717391304347826,
+      "eval_loss": 0.9340682625770569,
+      "eval_runtime": 0.6272,
+      "eval_samples_per_second": 73.347,
+      "eval_steps_per_second": 4.783,
       "step": 56
     },
     {
       "epoch": 16.86,
-      "eval_accuracy": 0.6086956521739131,
-      "eval_loss": 1.3729946613311768,
-      "eval_runtime": 0.6357,
-      "eval_samples_per_second": 72.367,
-      "eval_steps_per_second": 4.72,
+      "eval_accuracy": 0.717391304347826,
+      "eval_loss": 1.0463521480560303,
+      "eval_runtime": 0.6191,
+      "eval_samples_per_second": 74.297,
+      "eval_steps_per_second": 4.845,
       "step": 59
     },
     {
       "epoch": 17.14,
-      "learning_rate": 7.627118644067796e-06,
-      "loss": 1.3766,
+      "learning_rate": 0.0008333333333333334,
+      "loss": 0.6609,
       "step": 60
     },
     {
       "epoch": 18.0,
-      "eval_accuracy": 0.6521739130434783,
-      "eval_loss": 1.3718501329421997,
-      "eval_runtime": 0.6097,
-      "eval_samples_per_second": 75.453,
-      "eval_steps_per_second": 4.921,
+      "eval_accuracy": 0.6086956521739131,
+      "eval_loss": 0.9922565817832947,
+      "eval_runtime": 0.5991,
+      "eval_samples_per_second": 76.776,
+      "eval_steps_per_second": 5.007,
       "step": 63
     },
     {
       "epoch": 18.86,
-      "eval_accuracy": 0.6086956521739131,
-      "eval_loss": 1.3708202838897705,
-      "eval_runtime": 0.6567,
-      "eval_samples_per_second": 70.052,
-      "eval_steps_per_second": 4.569,
+      "eval_accuracy": 0.717391304347826,
+      "eval_loss": 0.8224782347679138,
+      "eval_runtime": 0.6182,
+      "eval_samples_per_second": 74.415,
+      "eval_steps_per_second": 4.853,
       "step": 66
     },
     {
       "epoch": 20.0,
-      "learning_rate": 6.3559322033898304e-06,
-      "loss": 1.3748,
+      "learning_rate": 0.0006944444444444445,
+      "loss": 0.6527,
       "step": 70
     },
     {
       "epoch": 20.0,
-      "eval_accuracy": 0.6304347826086957,
-      "eval_loss": 1.369877815246582,
-      "eval_runtime": 0.6577,
-      "eval_samples_per_second": 69.945,
-      "eval_steps_per_second": 4.562,
+      "eval_accuracy": 0.6956521739130435,
+      "eval_loss": 0.874836802482605,
+      "eval_runtime": 0.6096,
+      "eval_samples_per_second": 75.454,
+      "eval_steps_per_second": 4.921,
       "step": 70
     },
     {
       "epoch": 20.86,
-      "eval_accuracy": 0.6304347826086957,
-      "eval_loss": 1.3687235116958618,
-      "eval_runtime": 0.6742,
-      "eval_samples_per_second": 68.23,
-      "eval_steps_per_second": 4.45,
+      "eval_accuracy": 0.6739130434782609,
+      "eval_loss": 0.8051551580429077,
+      "eval_runtime": 0.5866,
+      "eval_samples_per_second": 78.412,
+      "eval_steps_per_second": 5.114,
       "step": 73
     },
     {
       "epoch": 22.0,
-      "eval_accuracy": 0.5869565217391305,
-      "eval_loss": 1.3677372932434082,
-      "eval_runtime": 0.6257,
-      "eval_samples_per_second": 73.523,
-      "eval_steps_per_second": 4.795,
+      "eval_accuracy": 0.6956521739130435,
+      "eval_loss": 0.8861276507377625,
+      "eval_runtime": 0.6181,
+      "eval_samples_per_second": 74.417,
+      "eval_steps_per_second": 4.853,
       "step": 77
     },
     {
       "epoch": 22.86,
-      "learning_rate": 5.084745762711865e-06,
-      "loss": 1.372,
+      "learning_rate": 0.0005555555555555556,
+      "loss": 0.493,
       "step": 80
     },
     {
       "epoch": 22.86,
-      "eval_accuracy": 0.6304347826086957,
-      "eval_loss": 1.3664358854293823,
-      "eval_runtime": 0.6397,
-      "eval_samples_per_second": 71.912,
-      "eval_steps_per_second": 4.69,
+      "eval_accuracy": 0.6956521739130435,
+      "eval_loss": 0.9554585218429565,
+      "eval_runtime": 0.6196,
+      "eval_samples_per_second": 74.236,
+      "eval_steps_per_second": 4.841,
       "step": 80
     },
     {
       "epoch": 24.0,
-      "eval_accuracy": 0.5869565217391305,
-      "eval_loss": 1.3654985427856445,
-      "eval_runtime": 0.6582,
-      "eval_samples_per_second": 69.892,
-      "eval_steps_per_second": 4.558,
+      "eval_accuracy": 0.6739130434782609,
+      "eval_loss": 1.0335818529129028,
+      "eval_runtime": 0.6146,
+      "eval_samples_per_second": 74.84,
+      "eval_steps_per_second": 4.881,
       "step": 84
     },
     {
       "epoch": 24.86,
-      "eval_accuracy": 0.6304347826086957,
-      "eval_loss": 1.364823579788208,
-      "eval_runtime": 0.6532,
-      "eval_samples_per_second": 70.424,
-      "eval_steps_per_second": 4.593,
+      "eval_accuracy": 0.6956521739130435,
+      "eval_loss": 0.9960870146751404,
+      "eval_runtime": 0.6046,
+      "eval_samples_per_second": 76.078,
+      "eval_steps_per_second": 4.962,
       "step": 87
     },
     {
       "epoch": 25.71,
-      "learning_rate": 3.813559322033898e-06,
-      "loss": 1.3693,
+      "learning_rate": 0.0004166666666666667,
+      "loss": 0.4088,
       "step": 90
     },
     {
       "epoch": 26.0,
-      "eval_accuracy": 0.6086956521739131,
-      "eval_loss": 1.3639944791793823,
-      "eval_runtime": 0.6257,
-      "eval_samples_per_second": 73.522,
-      "eval_steps_per_second": 4.795,
+      "eval_accuracy": 0.6956521739130435,
+      "eval_loss": 1.0399607419967651,
+      "eval_runtime": 0.6222,
+      "eval_samples_per_second": 73.937,
+      "eval_steps_per_second": 4.822,
       "step": 91
     },
     {
       "epoch": 26.86,
-      "eval_accuracy": 0.6086956521739131,
-      "eval_loss": 1.3637075424194336,
-      "eval_runtime": 0.6681,
-      "eval_samples_per_second": 68.847,
-      "eval_steps_per_second": 4.49,
+      "eval_accuracy": 0.6956521739130435,
+      "eval_loss": 1.053550362586975,
+      "eval_runtime": 0.6206,
+      "eval_samples_per_second": 74.116,
+      "eval_steps_per_second": 4.834,
       "step": 94
     },
     {
       "epoch": 28.0,
-      "eval_accuracy": 0.6304347826086957,
-      "eval_loss": 1.3627293109893799,
-      "eval_runtime": 0.6542,
-      "eval_samples_per_second": 70.316,
-      "eval_steps_per_second": 4.586,
+      "eval_accuracy": 0.6739130434782609,
+      "eval_loss": 1.1388055086135864,
+      "eval_runtime": 0.6152,
+      "eval_samples_per_second": 74.778,
+      "eval_steps_per_second": 4.877,
       "step": 98
     },
     {
       "epoch": 28.57,
-      "learning_rate": 2.5423728813559323e-06,
-      "loss": 1.3685,
+      "learning_rate": 0.0002777777777777778,
+      "loss": 0.4047,
       "step": 100
     },
     {
       "epoch": 28.86,
-      "eval_accuracy": 0.5869565217391305,
-      "eval_loss": 1.3624422550201416,
-      "eval_runtime": 0.616,
-      "eval_samples_per_second": 74.674,
-      "eval_steps_per_second": 4.87,
+      "eval_accuracy": 0.6521739130434783,
+      "eval_loss": 1.2294652462005615,
+      "eval_runtime": 0.6572,
+      "eval_samples_per_second": 69.998,
+      "eval_steps_per_second": 4.565,
       "step": 101
     },
     {
       "epoch": 30.0,
-      "eval_accuracy": 0.6086956521739131,
-      "eval_loss": 1.362162709236145,
-      "eval_runtime": 0.6333,
-      "eval_samples_per_second": 72.635,
-      "eval_steps_per_second": 4.737,
+      "eval_accuracy": 0.6521739130434783,
+      "eval_loss": 1.2627309560775757,
+      "eval_runtime": 0.6271,
+      "eval_samples_per_second": 73.349,
+      "eval_steps_per_second": 4.784,
       "step": 105
     },
     {
       "epoch": 30.86,
-      "eval_accuracy": 0.6086956521739131,
-      "eval_loss": 1.3610258102416992,
-      "eval_runtime": 0.6252,
-      "eval_samples_per_second": 73.574,
-      "eval_steps_per_second": 4.798,
+      "eval_accuracy": 0.6739130434782609,
+      "eval_loss": 1.2371925115585327,
+      "eval_runtime": 0.6617,
+      "eval_samples_per_second": 69.522,
+      "eval_steps_per_second": 4.534,
       "step": 108
     },
     {
       "epoch": 31.43,
-      "learning_rate": 1.2711864406779662e-06,
-      "loss": 1.3675,
+      "learning_rate": 0.0001388888888888889,
+      "loss": 0.3681,
       "step": 110
     },
     {
       "epoch": 32.0,
-      "eval_accuracy": 0.6086956521739131,
-      "eval_loss": 1.3605388402938843,
-      "eval_runtime": 0.6262,
-      "eval_samples_per_second": 73.462,
-      "eval_steps_per_second": 4.791,
+      "eval_accuracy": 0.6521739130434783,
+      "eval_loss": 1.2918990850448608,
+      "eval_runtime": 0.6482,
+      "eval_samples_per_second": 70.97,
+      "eval_steps_per_second": 4.628,
       "step": 112
     },
     {
       "epoch": 32.86,
-      "eval_accuracy": 0.6086956521739131,
-      "eval_loss": 1.3605269193649292,
-      "eval_runtime": 0.6382,
-      "eval_samples_per_second": 72.082,
-      "eval_steps_per_second": 4.701,
+      "eval_accuracy": 0.6521739130434783,
+      "eval_loss": 1.2453422546386719,
+      "eval_runtime": 0.6331,
+      "eval_samples_per_second": 72.653,
+      "eval_steps_per_second": 4.738,
       "step": 115
     },
     {
       "epoch": 34.0,
-      "eval_accuracy": 0.5869565217391305,
-      "eval_loss": 1.3611313104629517,
-      "eval_runtime": 0.6139,
-      "eval_samples_per_second": 74.93,
-      "eval_steps_per_second": 4.887,
+      "eval_accuracy": 0.6739130434782609,
+      "eval_loss": 1.2612279653549194,
+      "eval_runtime": 0.6181,
+      "eval_samples_per_second": 74.417,
+      "eval_steps_per_second": 4.853,
       "step": 119
     },
     {
       "epoch": 34.29,
       "learning_rate": 0.0,
-      "loss": 1.3663,
+      "loss": 0.353,
       "step": 120
     },
     {
       "epoch": 34.29,
-      "eval_accuracy": 0.6086956521739131,
-      "eval_loss": 1.3607913255691528,
-      "eval_runtime": 0.6386,
-      "eval_samples_per_second": 72.027,
-      "eval_steps_per_second": 4.697,
+      "eval_accuracy": 0.6956521739130435,
+      "eval_loss": 1.2610585689544678,
+      "eval_runtime": 0.6256,
+      "eval_samples_per_second": 73.524,
+      "eval_steps_per_second": 4.795,
       "step": 120
     },
     {
       "epoch": 34.29,
       "step": 120,
       "total_flos": 2.0027429927092224e+16,
-      "train_loss": 1.3757717927296957,
-      "train_runtime": 134.1596,
-      "train_samples_per_second": 63.506,
-      "train_steps_per_second": 0.894
+      "train_loss": 0.7088598291079203,
+      "train_runtime": 131.3917,
+      "train_samples_per_second": 64.844,
+      "train_steps_per_second": 0.913
     }
   ],
   "logging_steps": 10,