fix: Uploading summarizer

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "t5-small",
+  "_name_or_path": "TusharJoshi89/medical-research-title-generator",
   "architectures": [
     "T5ForConditionalGeneration"
   ],

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f84b3cc9fb8e9717544736645adf6cd4b86a75e35e579416077c9d1743ce9e41
-size 484130565
+oid sha256:8138409839f3271d64fddaf61d9388d19eff4847f49244d6598d22c1be08f7f4
+size 484130629

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa51035225c92add97277af43f4abfa1b8e0fff2b471b95315e9d09dba25e46e
+oid sha256:45d9f210a59994931e6bebed8d928bb7b91b9d0221c0ae617e0e3d7da0795431
 size 242071641

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ff6959ed8d1291fd55400668e43aee7512eb604c51c6ffc6749f160bd1ff3d1
+oid sha256:601c80416e72a4a9ad433190bad47bcabb8046f27bc84cb9117568b6f3fb9f9e
 size 14575

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:daaedac35250ef1ced3437442c43e80298f6c3c1a8e743335e3ed835bcb73680
+oid sha256:2b3b2a129639e4a3c47b487288feb3a58ca2794ba7ae74d20499bbe0637078b4
 size 627

trainer_state.json

@@ -1,467 +1,403 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 19.653179190751445,
-  "global_step": 17000,
+  "epoch": 3.9332700393327005,
+  "global_step": 29000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.58,
-      "learning_rate": 1.15606936416185e-05,
-      "loss": 4.1602,
+      "epoch": 0.07,
+      "learning_rate": 8.440677966101696e-05,
+      "loss": 2.551,
       "step": 500
     },
     {
-      "epoch": 1.0,
-      "eval_gen_len": 15.5003,
-      "eval_loss": 2.8024423122406006,
-      "eval_rouge1": 0.2552,
-      "eval_rouge2": 0.1019,
-      "eval_rougeL": 0.2331,
-      "eval_rougeLsum": 0.2332,
-      "eval_runtime": 184.148,
-      "eval_samples_per_second": 18.778,
-      "eval_steps_per_second": 1.178,
-      "step": 865
-    },
-    {
-      "epoch": 1.16,
-      "learning_rate": 1.9835716458777003e-05,
-      "loss": 3.1173,
+      "epoch": 0.14,
+      "learning_rate": 0.00016915254237288136,
+      "loss": 2.541,
       "step": 1000
     },
     {
-      "epoch": 1.73,
-      "learning_rate": 1.922725889869182e-05,
-      "loss": 2.9624,
+      "epoch": 0.2,
+      "learning_rate": 0.0002538983050847458,
+      "loss": 2.5194,
       "step": 1500
     },
     {
-      "epoch": 2.0,
-      "eval_gen_len": 15.8271,
-      "eval_loss": 2.6451988220214844,
-      "eval_rouge1": 0.2882,
-      "eval_rouge2": 0.1183,
-      "eval_rougeL": 0.2626,
-      "eval_rougeLsum": 0.2626,
-      "eval_runtime": 182.4271,
-      "eval_samples_per_second": 18.956,
-      "eval_steps_per_second": 1.19,
-      "step": 1730
-    },
-    {
-      "epoch": 2.31,
-      "learning_rate": 1.8618801338606633e-05,
-      "loss": 2.8766,
+      "epoch": 0.27,
+      "learning_rate": 0.00033864406779661016,
+      "loss": 2.4769,
       "step": 2000
     },
     {
-      "epoch": 2.89,
-      "learning_rate": 1.801034377852145e-05,
-      "loss": 2.8206,
+      "epoch": 0.34,
+      "learning_rate": 0.0004233898305084746,
+      "loss": 2.46,
       "step": 2500
     },
     {
-      "epoch": 3.0,
-      "eval_gen_len": 16.2183,
-      "eval_loss": 2.5787582397460938,
-      "eval_rouge1": 0.2952,
-      "eval_rouge2": 0.1218,
-      "eval_rougeL": 0.2684,
-      "eval_rougeLsum": 0.2685,
-      "eval_runtime": 182.2993,
-      "eval_samples_per_second": 18.969,
-      "eval_steps_per_second": 1.19,
-      "step": 2595
-    },
-    {
-      "epoch": 3.47,
-      "learning_rate": 1.7401886218436267e-05,
-      "loss": 2.7764,
+      "epoch": 0.41,
+      "learning_rate": 0.0004990957727375481,
+      "loss": 2.403,
       "step": 3000
     },
     {
-      "epoch": 4.0,
-      "eval_gen_len": 16.3418,
-      "eval_loss": 2.5332629680633545,
-      "eval_rouge1": 0.3029,
-      "eval_rouge2": 0.1258,
-      "eval_rougeL": 0.2755,
-      "eval_rougeLsum": 0.2754,
-      "eval_runtime": 181.4496,
-      "eval_samples_per_second": 19.058,
-      "eval_steps_per_second": 1.196,
-      "step": 3460
-    },
-    {
-      "epoch": 4.05,
-      "learning_rate": 1.679342865835108e-05,
-      "loss": 2.7414,
+      "epoch": 0.47,
+      "learning_rate": 0.0004897144148896089,
+      "loss": 2.3829,
       "step": 3500
     },
     {
-      "epoch": 4.62,
-      "learning_rate": 1.6184971098265897e-05,
-      "loss": 2.6997,
+      "epoch": 0.54,
+      "learning_rate": 0.0004802953809057343,
+      "loss": 2.3175,
       "step": 4000
     },
     {
-      "epoch": 5.0,
-      "eval_gen_len": 16.4101,
-      "eval_loss": 2.504000186920166,
-      "eval_rouge1": 0.3046,
-      "eval_rouge2": 0.1273,
-      "eval_rougeL": 0.2773,
-      "eval_rougeLsum": 0.2771,
-      "eval_runtime": 181.6751,
-      "eval_samples_per_second": 19.034,
-      "eval_steps_per_second": 1.194,
-      "step": 4325
-    },
-    {
-      "epoch": 5.2,
-      "learning_rate": 1.5576513538180714e-05,
-      "loss": 2.6795,
+      "epoch": 0.61,
+      "learning_rate": 0.0004708763469218597,
+      "loss": 2.3087,
       "step": 4500
     },
     {
-      "epoch": 5.78,
-      "learning_rate": 1.4968055978095528e-05,
-      "loss": 2.6647,
+      "epoch": 0.68,
+      "learning_rate": 0.0004614573129379851,
+      "loss": 2.2763,
       "step": 5000
     },
     {
-      "epoch": 6.0,
-      "eval_gen_len": 16.354,
-      "eval_loss": 2.4734175205230713,
-      "eval_rouge1": 0.3069,
-      "eval_rouge2": 0.1298,
-      "eval_rougeL": 0.2802,
-      "eval_rougeLsum": 0.2801,
-      "eval_runtime": 181.0262,
-      "eval_samples_per_second": 19.102,
-      "eval_steps_per_second": 1.199,
-      "step": 5190
-    },
-    {
-      "epoch": 6.36,
-      "learning_rate": 1.4359598418010346e-05,
-      "loss": 2.6287,
+      "epoch": 0.75,
+      "learning_rate": 0.0004520382789541105,
+      "loss": 2.2438,
       "step": 5500
     },
     {
-      "epoch": 6.94,
-      "learning_rate": 1.375114085792516e-05,
-      "loss": 2.6196,
+      "epoch": 0.81,
+      "learning_rate": 0.0004426192449702359,
+      "loss": 2.2358,
       "step": 6000
     },
     {
-      "epoch": 7.0,
-      "eval_gen_len": 16.526,
-      "eval_loss": 2.4547228813171387,
-      "eval_rouge1": 0.3077,
-      "eval_rouge2": 0.131,
-      "eval_rougeL": 0.2804,
-      "eval_rougeLsum": 0.2804,
-      "eval_runtime": 182.5951,
-      "eval_samples_per_second": 18.938,
-      "eval_steps_per_second": 1.188,
-      "step": 6055
+      "epoch": 0.88,
+      "learning_rate": 0.000433219049054329,
+      "loss": 2.194,
+      "step": 6500
     },
     {
-      "epoch": 7.51,
-      "learning_rate": 1.3142683297839978e-05,
-      "loss": 2.5916,
-      "step": 6500
+      "epoch": 0.95,
+      "learning_rate": 0.0004238000150704544,
+      "loss": 2.1761,
+      "step": 7000
     },
     {
-      "epoch": 8.0,
-      "eval_gen_len": 16.4419,
-      "eval_loss": 2.435168504714966,
-      "eval_rouge1": 0.3107,
-      "eval_rouge2": 0.1332,
-      "eval_rougeL": 0.2833,
-      "eval_rougeLsum": 0.2834,
-      "eval_runtime": 181.1692,
-      "eval_samples_per_second": 19.087,
-      "eval_steps_per_second": 1.198,
-      "step": 6920
+      "epoch": 1.0,
+      "eval_gen_len": 16.7426,
+      "eval_loss": 2.006333589553833,
+      "eval_rouge1": 0.3422,
+      "eval_rouge2": 0.1605,
+      "eval_rougeL": 0.3139,
+      "eval_rougeLsum": 0.314,
+      "eval_runtime": 782.1975,
+      "eval_samples_per_second": 16.757,
+      "eval_steps_per_second": 2.095,
+      "step": 7373
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.0004143809810865798,
+      "loss": 2.1455,
+      "step": 7500
     },
     {
-      "epoch": 8.09,
-      "learning_rate": 1.2534225737754793e-05,
-      "loss": 2.5986,
-      "step": 7000
+      "epoch": 1.09,
+      "learning_rate": 0.0004049619471027052,
+      "loss": 2.0777,
+      "step": 8000
     },
     {
-      "epoch": 8.67,
-      "learning_rate": 1.1925768177669607e-05,
-      "loss": 2.5716,
-      "step": 7500
+      "epoch": 1.15,
+      "learning_rate": 0.0003955429131188306,
+      "loss": 2.0945,
+      "step": 8500
     },
     {
-      "epoch": 9.0,
-      "eval_gen_len": 16.4023,
-      "eval_loss": 2.4196717739105225,
-      "eval_rouge1": 0.3092,
-      "eval_rouge2": 0.132,
-      "eval_rougeL": 0.2819,
-      "eval_rougeLsum": 0.2817,
-      "eval_runtime": 181.3331,
-      "eval_samples_per_second": 19.07,
-      "eval_steps_per_second": 1.197,
-      "step": 7785
+      "epoch": 1.22,
+      "learning_rate": 0.00038612387913495596,
+      "loss": 2.0485,
+      "step": 9000
     },
     {
-      "epoch": 9.25,
-      "learning_rate": 1.1317310617584426e-05,
-      "loss": 2.5347,
-      "step": 8000
+      "epoch": 1.29,
+      "learning_rate": 0.00037670484515108134,
+      "loss": 2.054,
+      "step": 9500
     },
     {
-      "epoch": 9.83,
-      "learning_rate": 1.070885305749924e-05,
-      "loss": 2.548,
-      "step": 8500
+      "epoch": 1.36,
+      "learning_rate": 0.0003672858111672067,
+      "loss": 2.073,
+      "step": 10000
     },
     {
-      "epoch": 10.0,
-      "eval_gen_len": 16.3256,
-      "eval_loss": 2.4123945236206055,
-      "eval_rouge1": 0.3094,
-      "eval_rouge2": 0.1329,
-      "eval_rougeL": 0.2822,
-      "eval_rougeLsum": 0.2823,
-      "eval_runtime": 181.1565,
-      "eval_samples_per_second": 19.088,
-      "eval_steps_per_second": 1.198,
-      "step": 8650
+      "epoch": 1.42,
+      "learning_rate": 0.0003578667771833321,
+      "loss": 2.0396,
+      "step": 10500
     },
     {
-      "epoch": 10.4,
-      "learning_rate": 1.0100395497414058e-05,
-      "loss": 2.5237,
-      "step": 9000
+      "epoch": 1.49,
+      "learning_rate": 0.0003484665812674252,
+      "loss": 2.0387,
+      "step": 11000
     },
     {
-      "epoch": 10.98,
-      "learning_rate": 9.491937937328873e-06,
-      "loss": 2.5352,
-      "step": 9500
+      "epoch": 1.56,
+      "learning_rate": 0.0003390475472835506,
+      "loss": 2.0198,
+      "step": 11500
     },
     {
-      "epoch": 11.0,
-      "eval_gen_len": 16.3774,
-      "eval_loss": 2.402285575866699,
-      "eval_rouge1": 0.3096,
-      "eval_rouge2": 0.1323,
-      "eval_rougeL": 0.2821,
-      "eval_rougeLsum": 0.282,
-      "eval_runtime": 181.4776,
-      "eval_samples_per_second": 19.055,
-      "eval_steps_per_second": 1.196,
-      "step": 9515
+      "epoch": 1.63,
+      "learning_rate": 0.000329628513299676,
+      "loss": 2.0144,
+      "step": 12000
     },
     {
-      "epoch": 11.56,
-      "learning_rate": 8.883480377243688e-06,
-      "loss": 2.5087,
-      "step": 10000
+      "epoch": 1.7,
+      "learning_rate": 0.00032020947931580136,
+      "loss": 2.0256,
+      "step": 12500
     },
     {
-      "epoch": 12.0,
-      "eval_gen_len": 16.4592,
-      "eval_loss": 2.39676570892334,
-      "eval_rouge1": 0.3107,
-      "eval_rouge2": 0.1326,
-      "eval_rougeL": 0.2831,
-      "eval_rougeLsum": 0.2832,
-      "eval_runtime": 182.2228,
-      "eval_samples_per_second": 18.977,
-      "eval_steps_per_second": 1.191,
-      "step": 10380
+      "epoch": 1.76,
+      "learning_rate": 0.0003108092833998945,
+      "loss": 2.0027,
+      "step": 13000
     },
     {
-      "epoch": 12.14,
-      "learning_rate": 8.275022817158503e-06,
-      "loss": 2.514,
-      "step": 10500
+      "epoch": 1.83,
+      "learning_rate": 0.0003013902494160199,
+      "loss": 2.0005,
+      "step": 13500
     },
     {
-      "epoch": 12.72,
-      "learning_rate": 7.66656525707332e-06,
-      "loss": 2.4865,
-      "step": 11000
+      "epoch": 1.9,
+      "learning_rate": 0.0002919712154321453,
+      "loss": 1.9977,
+      "step": 14000
     },
     {
-      "epoch": 13.0,
-      "eval_gen_len": 16.4586,
-      "eval_loss": 2.38985013961792,
-      "eval_rouge1": 0.3117,
-      "eval_rouge2": 0.1339,
-      "eval_rougeL": 0.2841,
-      "eval_rougeLsum": 0.2842,
-      "eval_runtime": 181.3381,
-      "eval_samples_per_second": 19.069,
-      "eval_steps_per_second": 1.197,
-      "step": 11245
+      "epoch": 1.97,
+      "learning_rate": 0.0002825521814482707,
+      "loss": 1.9967,
+      "step": 14500
     },
     {
-      "epoch": 13.29,
-      "learning_rate": 7.058107696988135e-06,
-      "loss": 2.4861,
-      "step": 11500
+      "epoch": 2.0,
+      "eval_gen_len": 16.758,
+      "eval_loss": 1.8912419080734253,
+      "eval_rouge1": 0.3607,
+      "eval_rouge2": 0.1759,
+      "eval_rougeL": 0.3322,
+      "eval_rougeLsum": 0.3321,
+      "eval_runtime": 782.0201,
+      "eval_samples_per_second": 16.76,
+      "eval_steps_per_second": 2.096,
+      "step": 14746
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 0.0002731519855323638,
+      "loss": 1.9494,
+      "step": 15000
     },
     {
-      "epoch": 13.87,
-      "learning_rate": 6.449650136902952e-06,
-      "loss": 2.5081,
-      "step": 12000
+      "epoch": 2.1,
+      "learning_rate": 0.0002637329515484892,
+      "loss": 1.8612,
+      "step": 15500
     },
     {
-      "epoch": 14.0,
-      "eval_gen_len": 16.4072,
-      "eval_loss": 2.3885083198547363,
-      "eval_rouge1": 0.3124,
-      "eval_rouge2": 0.1337,
-      "eval_rougeL": 0.2845,
-      "eval_rougeLsum": 0.2845,
-      "eval_runtime": 181.2166,
-      "eval_samples_per_second": 19.082,
-      "eval_steps_per_second": 1.197,
-      "step": 12110
+      "epoch": 2.17,
+      "learning_rate": 0.0002543139175646146,
+      "loss": 1.9076,
+      "step": 16000
     },
     {
-      "epoch": 14.45,
-      "learning_rate": 5.841192576817768e-06,
-      "loss": 2.4748,
-      "step": 12500
+      "epoch": 2.24,
+      "learning_rate": 0.00024489488358074,
+      "loss": 1.8987,
+      "step": 16500
     },
     {
-      "epoch": 15.0,
-      "eval_gen_len": 16.4572,
-      "eval_loss": 2.3791513442993164,
-      "eval_rouge1": 0.3131,
-      "eval_rouge2": 0.134,
-      "eval_rougeL": 0.285,
-      "eval_rougeLsum": 0.2849,
-      "eval_runtime": 181.192,
-      "eval_samples_per_second": 19.085,
-      "eval_steps_per_second": 1.198,
-      "step": 12975
+      "epoch": 2.31,
+      "learning_rate": 0.00023547584959686534,
+      "loss": 1.8882,
+      "step": 17000
     },
     {
-      "epoch": 15.03,
-      "learning_rate": 5.232735016732583e-06,
-      "loss": 2.4641,
-      "step": 13000
+      "epoch": 2.37,
+      "learning_rate": 0.00022605681561299075,
+      "loss": 1.9032,
+      "step": 17500
     },
     {
-      "epoch": 15.61,
-      "learning_rate": 4.6242774566473994e-06,
-      "loss": 2.469,
-      "step": 13500
+      "epoch": 2.44,
+      "learning_rate": 0.00021663778162911613,
+      "loss": 1.8853,
+      "step": 18000
     },
     {
-      "epoch": 16.0,
-      "eval_gen_len": 16.3907,
-      "eval_loss": 2.3784728050231934,
-      "eval_rouge1": 0.3119,
-      "eval_rouge2": 0.1333,
-      "eval_rougeL": 0.2841,
-      "eval_rougeLsum": 0.284,
-      "eval_runtime": 180.9918,
-      "eval_samples_per_second": 19.106,
-      "eval_steps_per_second": 1.199,
-      "step": 13840
+      "epoch": 2.51,
+      "learning_rate": 0.00020721874764524151,
+      "loss": 1.8841,
+      "step": 18500
     },
     {
-      "epoch": 16.18,
-      "learning_rate": 4.0158198965622155e-06,
-      "loss": 2.4771,
-      "step": 14000
+      "epoch": 2.58,
+      "learning_rate": 0.00019781855172933463,
+      "loss": 1.8747,
+      "step": 19000
     },
     {
-      "epoch": 16.76,
-      "learning_rate": 3.4073623364770307e-06,
-      "loss": 2.4587,
-      "step": 14500
+      "epoch": 2.64,
+      "learning_rate": 0.00018841835581342778,
+      "loss": 1.8842,
+      "step": 19500
     },
     {
-      "epoch": 17.0,
-      "eval_gen_len": 16.4488,
-      "eval_loss": 2.3765616416931152,
-      "eval_rouge1": 0.3115,
-      "eval_rouge2": 0.1334,
-      "eval_rougeL": 0.2835,
-      "eval_rougeLsum": 0.2834,
-      "eval_runtime": 181.9602,
-      "eval_samples_per_second": 19.004,
-      "eval_steps_per_second": 1.193,
-      "step": 14705
+      "epoch": 2.71,
+      "learning_rate": 0.00017899932182955316,
+      "loss": 1.8856,
+      "step": 20000
     },
     {
-      "epoch": 17.34,
-      "learning_rate": 2.798904776391847e-06,
-      "loss": 2.4679,
-      "step": 15000
+      "epoch": 2.78,
+      "learning_rate": 0.00016958028784567857,
+      "loss": 1.8751,
+      "step": 20500
     },
     {
-      "epoch": 17.92,
-      "learning_rate": 2.1904472163066628e-06,
-      "loss": 2.4428,
-      "step": 15500
+      "epoch": 2.85,
+      "learning_rate": 0.00016016125386180395,
+      "loss": 1.8806,
+      "step": 21000
     },
     {
-      "epoch": 18.0,
-      "eval_gen_len": 16.4141,
-      "eval_loss": 2.375408411026001,
-      "eval_rouge1": 0.3137,
-      "eval_rouge2": 0.1346,
-      "eval_rougeL": 0.2854,
-      "eval_rougeLsum": 0.2854,
-      "eval_runtime": 181.1095,
-      "eval_samples_per_second": 19.093,
-      "eval_steps_per_second": 1.198,
-      "step": 15570
+      "epoch": 2.92,
+      "learning_rate": 0.00015074221987792933,
+      "loss": 1.8519,
+      "step": 21500
     },
     {
-      "epoch": 18.5,
-      "learning_rate": 1.5819896562214788e-06,
-      "loss": 2.4548,
-      "step": 16000
+      "epoch": 2.98,
+      "learning_rate": 0.00014134202396202245,
+      "loss": 1.8716,
+      "step": 22000
+    },
+    {
+      "epoch": 3.0,
+      "eval_gen_len": 16.6685,
+      "eval_loss": 1.8340635299682617,
+      "eval_rouge1": 0.3656,
+      "eval_rouge2": 0.1782,
+      "eval_rougeL": 0.3354,
+      "eval_rougeLsum": 0.3355,
+      "eval_runtime": 781.3209,
+      "eval_samples_per_second": 16.775,
+      "eval_steps_per_second": 2.098,
+      "step": 22119
     },
     {
-      "epoch": 19.0,
-      "eval_gen_len": 16.4451,
-      "eval_loss": 2.3725531101226807,
-      "eval_rouge1": 0.3129,
-      "eval_rouge2": 0.1341,
-      "eval_rougeL": 0.2849,
-      "eval_rougeLsum": 0.285,
-      "eval_runtime": 180.98,
-      "eval_samples_per_second": 19.107,
-      "eval_steps_per_second": 1.199,
-      "step": 16435
+      "epoch": 3.05,
+      "learning_rate": 0.00013192298997814783,
+      "loss": 1.8213,
+      "step": 22500
     },
     {
-      "epoch": 19.08,
-      "learning_rate": 9.735320961362946e-07,
-      "loss": 2.4426,
-      "step": 16500
+      "epoch": 3.12,
+      "learning_rate": 0.00012250395599427324,
+      "loss": 1.78,
+      "step": 23000
     },
     {
-      "epoch": 19.65,
-      "learning_rate": 3.650745360511105e-07,
-      "loss": 2.4389,
-      "step": 17000
+      "epoch": 3.19,
+      "learning_rate": 0.00011308492201039862,
+      "loss": 1.7891,
+      "step": 23500
+    },
+    {
+      "epoch": 3.26,
+      "learning_rate": 0.00010366588802652401,
+      "loss": 1.7992,
+      "step": 24000
+    },
+    {
+      "epoch": 3.32,
+      "learning_rate": 9.424685404264939e-05,
+      "loss": 1.8033,
+      "step": 24500
+    },
+    {
+      "epoch": 3.39,
+      "learning_rate": 8.482782005877477e-05,
+      "loss": 1.8072,
+      "step": 25000
+    },
+    {
+      "epoch": 3.46,
+      "learning_rate": 7.540878607490017e-05,
+      "loss": 1.7981,
+      "step": 25500
+    },
+    {
+      "epoch": 3.53,
+      "learning_rate": 6.60085901589933e-05,
+      "loss": 1.7978,
+      "step": 26000
+    },
+    {
+      "epoch": 3.59,
+      "learning_rate": 5.6589556175118686e-05,
+      "loss": 1.7927,
+      "step": 26500
+    },
+    {
+      "epoch": 3.66,
+      "learning_rate": 4.7170522191244066e-05,
+      "loss": 1.7735,
+      "step": 27000
+    },
+    {
+      "epoch": 3.73,
+      "learning_rate": 3.7751488207369454e-05,
+      "loss": 1.7863,
+      "step": 27500
+    },
+    {
+      "epoch": 3.8,
+      "learning_rate": 2.8332454223494838e-05,
+      "loss": 1.7965,
+      "step": 28000
+    },
+    {
+      "epoch": 3.87,
+      "learning_rate": 1.8932258307587973e-05,
+      "loss": 1.7722,
+      "step": 28500
+    },
+    {
+      "epoch": 3.93,
+      "learning_rate": 9.513224323713361e-06,
+      "loss": 1.7679,
+      "step": 29000
     }
   ],
-  "max_steps": 17300,
-  "num_train_epochs": 20,
-  "total_flos": 6.944051276532941e+16,
+  "max_steps": 29492,
+  "num_train_epochs": 4,
+  "total_flos": 1.1856217832207155e+17,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:037777afe7f6a0e02734b8f27ee76168428c6a68b7c2296930ac277edcf3ea7b
+oid sha256:9327d8e3421496510caca2bb5661ec80a69fff8151109ade379e3c1754ab335d
 size 4091