Upload folder using huggingface_hub

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:677027e4409b490a593295b65f19efa300a5a1e9aba0cff392ca786175193366
+oid sha256:a914e52682550f8564955bcd75cde39fb1d446260e8c8c363d1a5c6a787b2423
 size 160069389

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a4c4dc4fc3b82c7e414e47ad4783fba119068cc7afd7fea70f21bd361051e0c
+oid sha256:91674d4a52910440bb5bb312e287f4513fc044ee6d514529f25330adf4e70a4b
 size 320193565

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d78143d9be5aecff6d15eb9fff604018f5c22d556656dce9ab94663022a8f0ae
+oid sha256:58fdbed67c3829622dfa48a2bbf084356503a2a890373c8bf0c98c2412e580c5
 size 14575

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c8c6aaf7abfed00c96e02dd330ed2bd374bffe362c92f8d5b77049e400c3168
+oid sha256:094fe83ba6b00779a606e1c315d5190ccde76611e3c53c464d9f758dd4968766
 size 627

trainer_state.json

@@ -1,289 +1,277 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.0,
+  "epoch": 2.9935483870967743,
   "eval_steps": 500,
-  "global_step": 91,
+  "global_step": 87,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.04,
-      "learning_rate": 2.857142857142857e-05,
-      "loss": 1.8496,
+      "epoch": 0.07,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 1.912,
       "step": 2
     },
     {
-      "epoch": 0.09,
-      "learning_rate": 5.714285714285714e-05,
-      "loss": 1.9673,
+      "epoch": 0.14,
+      "learning_rate": 8.888888888888889e-05,
+      "loss": 2.0591,
       "step": 4
     },
     {
-      "epoch": 0.13,
-      "learning_rate": 8.571428571428571e-05,
-      "loss": 1.8491,
+      "epoch": 0.21,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 1.9454,
       "step": 6
     },
     {
-      "epoch": 0.18,
-      "learning_rate": 0.00011428571428571428,
-      "loss": 1.9002,
+      "epoch": 0.28,
+      "learning_rate": 0.00017777777777777779,
+      "loss": 1.9692,
       "step": 8
     },
     {
-      "epoch": 0.22,
-      "learning_rate": 0.00014285714285714287,
-      "loss": 1.873,
+      "epoch": 0.34,
+      "learning_rate": 0.00019743589743589744,
+      "loss": 1.849,
       "step": 10
     },
     {
-      "epoch": 0.26,
-      "learning_rate": 0.00017142857142857143,
-      "loss": 1.9039,
+      "epoch": 0.41,
+      "learning_rate": 0.00019230769230769233,
+      "loss": 1.7833,
       "step": 12
     },
     {
-      "epoch": 0.31,
-      "learning_rate": 0.0002,
-      "loss": 1.8956,
+      "epoch": 0.48,
+      "learning_rate": 0.0001871794871794872,
+      "loss": 1.8451,
       "step": 14
     },
     {
-      "epoch": 0.35,
-      "learning_rate": 0.0001966942148760331,
-      "loss": 1.8618,
+      "epoch": 0.55,
+      "learning_rate": 0.00018205128205128207,
+      "loss": 1.8017,
       "step": 16
     },
     {
-      "epoch": 0.4,
-      "learning_rate": 0.0001933884297520661,
-      "loss": 1.7929,
+      "epoch": 0.62,
+      "learning_rate": 0.00017692307692307693,
+      "loss": 1.7176,
       "step": 18
     },
     {
-      "epoch": 0.44,
-      "learning_rate": 0.0001900826446280992,
-      "loss": 1.852,
+      "epoch": 0.69,
+      "learning_rate": 0.0001717948717948718,
+      "loss": 1.8041,
       "step": 20
     },
     {
-      "epoch": 0.48,
-      "learning_rate": 0.00018677685950413224,
-      "loss": 1.8218,
+      "epoch": 0.76,
+      "learning_rate": 0.0001666666666666667,
+      "loss": 1.6708,
       "step": 22
     },
     {
-      "epoch": 0.53,
-      "learning_rate": 0.00018347107438016532,
-      "loss": 1.8421,
+      "epoch": 0.83,
+      "learning_rate": 0.00016153846153846155,
+      "loss": 1.7398,
       "step": 24
     },
     {
-      "epoch": 0.57,
-      "learning_rate": 0.00018016528925619835,
-      "loss": 1.7531,
+      "epoch": 0.89,
+      "learning_rate": 0.00015641025641025642,
+      "loss": 1.7176,
       "step": 26
     },
     {
-      "epoch": 0.62,
-      "learning_rate": 0.00017685950413223143,
-      "loss": 1.7133,
+      "epoch": 0.96,
+      "learning_rate": 0.00015128205128205128,
+      "loss": 1.7141,
       "step": 28
     },
     {
-      "epoch": 0.66,
-      "learning_rate": 0.00017520661157024794,
-      "loss": 2.2706,
+      "epoch": 1.03,
+      "learning_rate": 0.00014615384615384615,
+      "loss": 1.7503,
       "step": 30
     },
     {
-      "epoch": 0.7,
-      "learning_rate": 0.00017190082644628102,
-      "loss": 1.7739,
+      "epoch": 1.1,
+      "learning_rate": 0.00014102564102564104,
+      "loss": 1.6686,
       "step": 32
     },
     {
-      "epoch": 0.75,
-      "learning_rate": 0.00016859504132231404,
-      "loss": 1.7082,
+      "epoch": 1.17,
+      "learning_rate": 0.0001358974358974359,
+      "loss": 1.723,
       "step": 34
     },
     {
-      "epoch": 0.79,
-      "learning_rate": 0.00016528925619834712,
-      "loss": 1.7831,
+      "epoch": 1.24,
+      "learning_rate": 0.00013076923076923077,
+      "loss": 1.7153,
       "step": 36
     },
     {
-      "epoch": 0.84,
-      "learning_rate": 0.00016198347107438017,
-      "loss": 1.778,
+      "epoch": 1.31,
+      "learning_rate": 0.00012564102564102564,
+      "loss": 1.6379,
       "step": 38
     },
     {
-      "epoch": 0.88,
-      "learning_rate": 0.00015867768595041322,
-      "loss": 1.7482,
+      "epoch": 1.38,
+      "learning_rate": 0.00012051282051282052,
+      "loss": 1.8047,
       "step": 40
     },
     {
-      "epoch": 0.92,
-      "learning_rate": 0.00015537190082644627,
-      "loss": 1.8466,
+      "epoch": 1.45,
+      "learning_rate": 0.00011538461538461538,
+      "loss": 1.719,
       "step": 42
     },
     {
-      "epoch": 0.97,
-      "learning_rate": 0.00015206611570247935,
-      "loss": 1.7918,
+      "epoch": 1.51,
+      "learning_rate": 0.00011025641025641027,
+      "loss": 1.6785,
       "step": 44
     },
     {
-      "epoch": 1.01,
-      "learning_rate": 0.0001487603305785124,
-      "loss": 1.7058,
+      "epoch": 1.58,
+      "learning_rate": 0.00010512820512820514,
+      "loss": 1.6407,
       "step": 46
     },
     {
-      "epoch": 1.05,
-      "learning_rate": 0.00014545454545454546,
-      "loss": 1.7294,
+      "epoch": 1.65,
+      "learning_rate": 0.0001,
+      "loss": 1.6414,
       "step": 48
     },
     {
-      "epoch": 1.1,
-      "learning_rate": 0.0001421487603305785,
-      "loss": 1.7285,
+      "epoch": 1.72,
+      "learning_rate": 9.487179487179487e-05,
+      "loss": 1.6422,
       "step": 50
     },
     {
-      "epoch": 1.14,
-      "learning_rate": 0.0001388429752066116,
-      "loss": 1.6392,
+      "epoch": 1.79,
+      "learning_rate": 8.974358974358975e-05,
+      "loss": 1.7277,
       "step": 52
     },
     {
-      "epoch": 1.19,
-      "learning_rate": 0.00013553719008264464,
-      "loss": 1.712,
+      "epoch": 1.86,
+      "learning_rate": 8.461538461538461e-05,
+      "loss": 1.6827,
       "step": 54
     },
     {
-      "epoch": 1.23,
-      "learning_rate": 0.0001322314049586777,
-      "loss": 1.6992,
+      "epoch": 1.93,
+      "learning_rate": 7.948717948717948e-05,
+      "loss": 1.721,
       "step": 56
     },
     {
-      "epoch": 1.27,
-      "learning_rate": 0.00012892561983471074,
-      "loss": 1.7677,
+      "epoch": 2.0,
+      "learning_rate": 7.435897435897436e-05,
+      "loss": 1.7153,
       "step": 58
     },
     {
-      "epoch": 1.32,
-      "learning_rate": 0.00012561983471074382,
-      "loss": 1.7096,
+      "epoch": 2.06,
+      "learning_rate": 6.923076923076924e-05,
+      "loss": 1.5865,
       "step": 60
     },
     {
-      "epoch": 1.36,
-      "learning_rate": 0.00012231404958677685,
-      "loss": 1.7602,
+      "epoch": 2.13,
+      "learning_rate": 6.410256410256412e-05,
+      "loss": 1.7077,
       "step": 62
     },
     {
-      "epoch": 1.41,
-      "learning_rate": 0.00011900826446280992,
-      "loss": 1.7128,
+      "epoch": 2.2,
+      "learning_rate": 5.897435897435898e-05,
+      "loss": 1.664,
       "step": 64
     },
     {
-      "epoch": 1.45,
-      "learning_rate": 0.00011570247933884298,
-      "loss": 1.6605,
+      "epoch": 2.27,
+      "learning_rate": 5.384615384615385e-05,
+      "loss": 1.7481,
       "step": 66
     },
     {
-      "epoch": 1.49,
-      "learning_rate": 0.00011239669421487604,
-      "loss": 1.6559,
+      "epoch": 2.34,
+      "learning_rate": 4.871794871794872e-05,
+      "loss": 1.7459,
       "step": 68
     },
     {
-      "epoch": 1.54,
-      "learning_rate": 0.00010909090909090909,
-      "loss": 1.6775,
+      "epoch": 2.41,
+      "learning_rate": 4.358974358974359e-05,
+      "loss": 1.7067,
       "step": 70
     },
     {
-      "epoch": 1.58,
-      "learning_rate": 0.00010578512396694216,
-      "loss": 1.8318,
+      "epoch": 2.48,
+      "learning_rate": 3.846153846153846e-05,
+      "loss": 1.6086,
       "step": 72
     },
     {
-      "epoch": 1.63,
-      "learning_rate": 0.00010247933884297521,
-      "loss": 1.7568,
+      "epoch": 2.55,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 1.5464,
       "step": 74
     },
     {
-      "epoch": 1.67,
-      "learning_rate": 9.917355371900827e-05,
-      "loss": 1.7349,
+      "epoch": 2.62,
+      "learning_rate": 2.8205128205128207e-05,
+      "loss": 1.5403,
       "step": 76
     },
     {
-      "epoch": 1.71,
-      "learning_rate": 9.586776859504133e-05,
-      "loss": 1.7956,
+      "epoch": 2.68,
+      "learning_rate": 2.307692307692308e-05,
+      "loss": 1.5363,
       "step": 78
     },
     {
-      "epoch": 1.76,
-      "learning_rate": 9.256198347107439e-05,
-      "loss": 1.684,
+      "epoch": 2.75,
+      "learning_rate": 1.794871794871795e-05,
+      "loss": 1.6695,
       "step": 80
     },
     {
-      "epoch": 1.8,
-      "learning_rate": 8.925619834710744e-05,
-      "loss": 1.6579,
+      "epoch": 2.82,
+      "learning_rate": 1.282051282051282e-05,
+      "loss": 1.5652,
       "step": 82
     },
     {
-      "epoch": 1.85,
-      "learning_rate": 8.595041322314051e-05,
-      "loss": 1.7188,
+      "epoch": 2.89,
+      "learning_rate": 7.692307692307694e-06,
+      "loss": 1.6139,
       "step": 84
     },
     {
-      "epoch": 1.89,
-      "learning_rate": 8.264462809917356e-05,
-      "loss": 1.6533,
+      "epoch": 2.96,
+      "learning_rate": 2.564102564102564e-06,
+      "loss": 1.6482,
       "step": 86
-    },
-    {
-      "epoch": 1.93,
-      "learning_rate": 8.099173553719009e-05,
-      "loss": 1.9246,
-      "step": 88
-    },
-    {
-      "epoch": 1.98,
-      "learning_rate": 7.768595041322314e-05,
-      "loss": 1.7969,
-      "step": 90
     }
   ],
   "logging_steps": 2,
-  "max_steps": 135,
+  "max_steps": 87,
   "num_train_epochs": 3,
   "save_steps": 500,
-  "total_flos": 5.946469637318246e+16,
+  "total_flos": 5.685086356557005e+16,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6660384e2521611c02ca201838bbcb32971b9104a07ca83aeebb90ae8d66cba1
+oid sha256:ec2cc6016d4f33d3436bd7d0abd53631d8fb77e5aa03ef5a3f588886acfcc626
 size 4027