Upload folder using huggingface_hub

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.8965769723595094
+      value: 0.8879736408566722
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/opt-350m](https://huggingface.co/facebook/opt-350m) on the GLUE QNLI dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8084
-- Accuracy: 0.8966
+- Loss: 0.9154
+- Accuracy: 0.8880
 
 ## Model description
 
@@ -53,7 +53,7 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 32
+- train_batch_size: 16
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08

all_results.json

@@ -1,14 +1,14 @@
 {
     "epoch": 5.0,
-    "eval_accuracy": 0.8965769723595094,
-    "eval_loss": 0.808398425579071,
-    "eval_runtime": 31.8395,
+    "eval_accuracy": 0.8879736408566722,
+    "eval_loss": 0.9153996109962463,
+    "eval_runtime": 14.2073,
     "eval_samples": 5463,
-    "eval_samples_per_second": 171.58,
-    "eval_steps_per_second": 21.451,
-    "train_loss": 0.14827317719643043,
-    "train_runtime": 8514.0774,
+    "eval_samples_per_second": 384.52,
+    "eval_steps_per_second": 48.074,
+    "train_loss": 0.18100789875515877,
+    "train_runtime": 2992.4891,
     "train_samples": 104743,
-    "train_samples_per_second": 61.512,
-    "train_steps_per_second": 1.923
+    "train_samples_per_second": 175.01,
+    "train_steps_per_second": 10.939
 }

eval_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 5.0,
-    "eval_accuracy": 0.8965769723595094,
-    "eval_loss": 0.808398425579071,
-    "eval_runtime": 31.8395,
+    "eval_accuracy": 0.8879736408566722,
+    "eval_loss": 0.9153996109962463,
+    "eval_runtime": 14.2073,
     "eval_samples": 5463,
-    "eval_samples_per_second": 171.58,
-    "eval_steps_per_second": 21.451
+    "eval_samples_per_second": 384.52,
+    "eval_steps_per_second": 48.074
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb4b1a44b30ec881324caea0c9774b1727b9f81d8c4cc470bbab58e92e3672e7
+oid sha256:aa23862730d443972a24c0f53f1b0d94066a7f8e583086587fd54f9c64efe073
 size 1324921569

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 5.0,
-    "train_loss": 0.14827317719643043,
-    "train_runtime": 8514.0774,
+    "train_loss": 0.18100789875515877,
+    "train_runtime": 2992.4891,
     "train_samples": 104743,
-    "train_samples_per_second": 61.512,
-    "train_steps_per_second": 1.923
+    "train_samples_per_second": 175.01,
+    "train_steps_per_second": 10.939
 }

trainer_state.json

@@ -2,214 +2,412 @@
   "best_metric": null,
   "best_model_checkpoint": null,
   "epoch": 5.0,
-  "global_step": 16370,
+  "global_step": 32735,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.15,
-      "learning_rate": 1.938912645082468e-05,
-      "loss": 0.5176,
+      "epoch": 0.08,
+      "learning_rate": 1.9696960439896138e-05,
+      "loss": 0.5866,
       "step": 500
     },
     {
-      "epoch": 0.31,
-      "learning_rate": 1.8778252901649362e-05,
-      "loss": 0.4025,
+      "epoch": 0.15,
+      "learning_rate": 1.939147701237208e-05,
+      "loss": 0.4699,
       "step": 1000
     },
     {
-      "epoch": 0.46,
-      "learning_rate": 1.816737935247404e-05,
-      "loss": 0.3706,
+      "epoch": 0.23,
+      "learning_rate": 1.9085993584848024e-05,
+      "loss": 0.4424,
       "step": 1500
     },
     {
-      "epoch": 0.61,
-      "learning_rate": 1.755650580329872e-05,
-      "loss": 0.3541,
+      "epoch": 0.31,
+      "learning_rate": 1.8780510157323964e-05,
+      "loss": 0.4243,
       "step": 2000
     },
     {
-      "epoch": 0.76,
-      "learning_rate": 1.69456322541234e-05,
-      "loss": 0.3371,
+      "epoch": 0.38,
+      "learning_rate": 1.847502672979991e-05,
+      "loss": 0.4041,
       "step": 2500
     },
     {
-      "epoch": 0.92,
-      "learning_rate": 1.6334758704948076e-05,
-      "loss": 0.3221,
+      "epoch": 0.46,
+      "learning_rate": 1.8169543302275854e-05,
+      "loss": 0.4013,
       "step": 3000
     },
     {
-      "epoch": 1.07,
-      "learning_rate": 1.5723885155772757e-05,
-      "loss": 0.2637,
+      "epoch": 0.53,
+      "learning_rate": 1.7864059874751797e-05,
+      "loss": 0.3895,
       "step": 3500
     },
     {
-      "epoch": 1.22,
-      "learning_rate": 1.5113011606597437e-05,
-      "loss": 0.201,
+      "epoch": 0.61,
+      "learning_rate": 1.755857644722774e-05,
+      "loss": 0.3854,
       "step": 4000
     },
     {
-      "epoch": 1.37,
-      "learning_rate": 1.4502138057422115e-05,
-      "loss": 0.1971,
+      "epoch": 0.69,
+      "learning_rate": 1.725309301970368e-05,
+      "loss": 0.3613,
       "step": 4500
     },
     {
-      "epoch": 1.53,
-      "learning_rate": 1.3891264508246794e-05,
-      "loss": 0.2067,
+      "epoch": 0.76,
+      "learning_rate": 1.6947609592179627e-05,
+      "loss": 0.3674,
       "step": 5000
     },
     {
-      "epoch": 1.68,
-      "learning_rate": 1.3280390959071474e-05,
-      "loss": 0.2032,
+      "epoch": 0.84,
+      "learning_rate": 1.664212616465557e-05,
+      "loss": 0.3519,
       "step": 5500
     },
     {
-      "epoch": 1.83,
-      "learning_rate": 1.2669517409896153e-05,
-      "loss": 0.1971,
+      "epoch": 0.92,
+      "learning_rate": 1.633664273713151e-05,
+      "loss": 0.3376,
       "step": 6000
     },
     {
-      "epoch": 1.99,
-      "learning_rate": 1.2058643860720831e-05,
-      "loss": 0.2034,
+      "epoch": 0.99,
+      "learning_rate": 1.6031770276462503e-05,
+      "loss": 0.3444,
       "step": 6500
     },
     {
-      "epoch": 2.14,
-      "learning_rate": 1.1447770311545512e-05,
-      "loss": 0.104,
+      "epoch": 1.07,
+      "learning_rate": 1.5726286848938447e-05,
+      "loss": 0.2444,
       "step": 7000
     },
     {
-      "epoch": 2.29,
-      "learning_rate": 1.083689676237019e-05,
-      "loss": 0.0962,
+      "epoch": 1.15,
+      "learning_rate": 1.542080342141439e-05,
+      "loss": 0.2328,
       "step": 7500
     },
     {
-      "epoch": 2.44,
-      "learning_rate": 1.0226023213194869e-05,
-      "loss": 0.1046,
+      "epoch": 1.22,
+      "learning_rate": 1.5115319993890332e-05,
+      "loss": 0.2461,
       "step": 8000
     },
     {
-      "epoch": 2.6,
-      "learning_rate": 9.615149664019549e-06,
-      "loss": 0.1022,
+      "epoch": 1.3,
+      "learning_rate": 1.4809836566366276e-05,
+      "loss": 0.2425,
       "step": 8500
     },
     {
-      "epoch": 2.75,
-      "learning_rate": 9.004276114844227e-06,
-      "loss": 0.0951,
+      "epoch": 1.37,
+      "learning_rate": 1.450435313884222e-05,
+      "loss": 0.2503,
       "step": 9000
     },
     {
-      "epoch": 2.9,
-      "learning_rate": 8.393402565668908e-06,
-      "loss": 0.1011,
+      "epoch": 1.45,
+      "learning_rate": 1.419948067817321e-05,
+      "loss": 0.2383,
       "step": 9500
     },
     {
-      "epoch": 3.05,
-      "learning_rate": 7.782529016493586e-06,
-      "loss": 0.0793,
+      "epoch": 1.53,
+      "learning_rate": 1.3893997250649154e-05,
+      "loss": 0.243,
       "step": 10000
     },
     {
-      "epoch": 3.21,
-      "learning_rate": 7.171655467318266e-06,
-      "loss": 0.0385,
+      "epoch": 1.6,
+      "learning_rate": 1.3588513823125096e-05,
+      "loss": 0.2406,
       "step": 10500
     },
     {
-      "epoch": 3.36,
-      "learning_rate": 6.560781918142944e-06,
-      "loss": 0.0487,
+      "epoch": 1.68,
+      "learning_rate": 1.328303039560104e-05,
+      "loss": 0.2529,
       "step": 11000
     },
     {
-      "epoch": 3.51,
-      "learning_rate": 5.949908368967624e-06,
-      "loss": 0.0526,
+      "epoch": 1.76,
+      "learning_rate": 1.2977546968076984e-05,
+      "loss": 0.2371,
       "step": 11500
     },
     {
-      "epoch": 3.67,
-      "learning_rate": 5.339034819792304e-06,
-      "loss": 0.0515,
+      "epoch": 1.83,
+      "learning_rate": 1.2672063540552926e-05,
+      "loss": 0.2456,
       "step": 12000
     },
     {
-      "epoch": 3.82,
-      "learning_rate": 4.728161270616982e-06,
-      "loss": 0.0455,
+      "epoch": 1.91,
+      "learning_rate": 1.2366580113028869e-05,
+      "loss": 0.2424,
       "step": 12500
     },
     {
-      "epoch": 3.97,
-      "learning_rate": 4.117287721441662e-06,
-      "loss": 0.0481,
+      "epoch": 1.99,
+      "learning_rate": 1.2061096685504812e-05,
+      "loss": 0.2501,
       "step": 13000
     },
     {
-      "epoch": 4.12,
-      "learning_rate": 3.506414172266341e-06,
-      "loss": 0.021,
+      "epoch": 2.06,
+      "learning_rate": 1.1756835191690852e-05,
+      "loss": 0.1505,
       "step": 13500
     },
     {
-      "epoch": 4.28,
-      "learning_rate": 2.8955406230910206e-06,
-      "loss": 0.017,
+      "epoch": 2.14,
+      "learning_rate": 1.1451351764166795e-05,
+      "loss": 0.1296,
       "step": 14000
     },
     {
-      "epoch": 4.43,
-      "learning_rate": 2.2846670739156996e-06,
-      "loss": 0.0143,
+      "epoch": 2.21,
+      "learning_rate": 1.1147090270352833e-05,
+      "loss": 0.1561,
       "step": 14500
     },
     {
-      "epoch": 4.58,
-      "learning_rate": 1.6737935247403788e-06,
-      "loss": 0.0165,
+      "epoch": 2.29,
+      "learning_rate": 1.0841606842828778e-05,
+      "loss": 0.1607,
       "step": 15000
     },
     {
-      "epoch": 4.73,
-      "learning_rate": 1.0629199755650582e-06,
-      "loss": 0.0167,
+      "epoch": 2.37,
+      "learning_rate": 1.053612341530472e-05,
+      "loss": 0.1479,
       "step": 15500
     },
     {
-      "epoch": 4.89,
-      "learning_rate": 4.5204642638973736e-07,
-      "loss": 0.015,
+      "epoch": 2.44,
+      "learning_rate": 1.0230639987780663e-05,
+      "loss": 0.1608,
       "step": 16000
     },
+    {
+      "epoch": 2.52,
+      "learning_rate": 9.925156560256606e-06,
+      "loss": 0.171,
+      "step": 16500
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 9.61967313273255e-06,
+      "loss": 0.1508,
+      "step": 17000
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 9.314189705208493e-06,
+      "loss": 0.1575,
+      "step": 17500
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 9.008706277684436e-06,
+      "loss": 0.1776,
+      "step": 18000
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 8.703833817015428e-06,
+      "loss": 0.1484,
+      "step": 18500
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 8.398350389491371e-06,
+      "loss": 0.1454,
+      "step": 19000
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 8.092866961967314e-06,
+      "loss": 0.1672,
+      "step": 19500
+    },
+    {
+      "epoch": 3.05,
+      "learning_rate": 7.787383534443257e-06,
+      "loss": 0.1022,
+      "step": 20000
+    },
+    {
+      "epoch": 3.13,
+      "learning_rate": 7.482511073774248e-06,
+      "loss": 0.0724,
+      "step": 20500
+    },
+    {
+      "epoch": 3.21,
+      "learning_rate": 7.17763861310524e-06,
+      "loss": 0.0652,
+      "step": 21000
+    },
+    {
+      "epoch": 3.28,
+      "learning_rate": 6.872155185581183e-06,
+      "loss": 0.0802,
+      "step": 21500
+    },
+    {
+      "epoch": 3.36,
+      "learning_rate": 6.566671758057126e-06,
+      "loss": 0.0787,
+      "step": 22000
+    },
+    {
+      "epoch": 3.44,
+      "learning_rate": 6.261188330533069e-06,
+      "loss": 0.0767,
+      "step": 22500
+    },
+    {
+      "epoch": 3.51,
+      "learning_rate": 5.955704903009012e-06,
+      "loss": 0.0846,
+      "step": 23000
+    },
+    {
+      "epoch": 3.59,
+      "learning_rate": 5.650221475484955e-06,
+      "loss": 0.0742,
+      "step": 23500
+    },
+    {
+      "epoch": 3.67,
+      "learning_rate": 5.344738047960899e-06,
+      "loss": 0.0903,
+      "step": 24000
+    },
+    {
+      "epoch": 3.74,
+      "learning_rate": 5.039254620436842e-06,
+      "loss": 0.0816,
+      "step": 24500
+    },
+    {
+      "epoch": 3.82,
+      "learning_rate": 4.733771192912785e-06,
+      "loss": 0.0732,
+      "step": 25000
+    },
+    {
+      "epoch": 3.89,
+      "learning_rate": 4.428898732243776e-06,
+      "loss": 0.0779,
+      "step": 25500
+    },
+    {
+      "epoch": 3.97,
+      "learning_rate": 4.1234153047197195e-06,
+      "loss": 0.0778,
+      "step": 26000
+    },
+    {
+      "epoch": 4.05,
+      "learning_rate": 3.817931877195663e-06,
+      "loss": 0.0441,
+      "step": 26500
+    },
+    {
+      "epoch": 4.12,
+      "learning_rate": 3.5124484496716056e-06,
+      "loss": 0.0271,
+      "step": 27000
+    },
+    {
+      "epoch": 4.2,
+      "learning_rate": 3.207575989002597e-06,
+      "loss": 0.0299,
+      "step": 27500
+    },
+    {
+      "epoch": 4.28,
+      "learning_rate": 2.90209256147854e-06,
+      "loss": 0.0308,
+      "step": 28000
+    },
+    {
+      "epoch": 4.35,
+      "learning_rate": 2.597220100809531e-06,
+      "loss": 0.0268,
+      "step": 28500
+    },
+    {
+      "epoch": 4.43,
+      "learning_rate": 2.2917366732854746e-06,
+      "loss": 0.0251,
+      "step": 29000
+    },
+    {
+      "epoch": 4.51,
+      "learning_rate": 1.9862532457614175e-06,
+      "loss": 0.0225,
+      "step": 29500
+    },
+    {
+      "epoch": 4.58,
+      "learning_rate": 1.6807698182373607e-06,
+      "loss": 0.0259,
+      "step": 30000
+    },
+    {
+      "epoch": 4.66,
+      "learning_rate": 1.375897357568352e-06,
+      "loss": 0.0321,
+      "step": 30500
+    },
+    {
+      "epoch": 4.73,
+      "learning_rate": 1.0704139300442952e-06,
+      "loss": 0.0234,
+      "step": 31000
+    },
+    {
+      "epoch": 4.81,
+      "learning_rate": 7.649305025202383e-07,
+      "loss": 0.0262,
+      "step": 31500
+    },
+    {
+      "epoch": 4.89,
+      "learning_rate": 4.594470749961815e-07,
+      "loss": 0.0239,
+      "step": 32000
+    },
+    {
+      "epoch": 4.96,
+      "learning_rate": 1.5396364747212466e-07,
+      "loss": 0.0129,
+      "step": 32500
+    },
     {
       "epoch": 5.0,
-      "step": 16370,
+      "step": 32735,
       "total_flos": 1.2201496021696512e+17,
-      "train_loss": 0.14827317719643043,
-      "train_runtime": 8514.0774,
-      "train_samples_per_second": 61.512,
-      "train_steps_per_second": 1.923
+      "train_loss": 0.18100789875515877,
+      "train_runtime": 2992.4891,
+      "train_samples_per_second": 175.01,
+      "train_steps_per_second": 10.939
     }
   ],
-  "max_steps": 16370,
+  "max_steps": 32735,
   "num_train_epochs": 5,
   "total_flos": 1.2201496021696512e+17,
   "trial_name": null,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5bdd037aab1677ff45ae16a921f301d377c09978b0d47309412766022bea09a
+oid sha256:29bbf7bc47277e201d10f33a64a17c3ce9afab415ea9c2fe0579645e7de94bc4
 size 3963