Training in progress, step 500, checkpoint

last-checkpoint/adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": null,
+  "base_model_name_or_path": "moussaKam/AraBART",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -16,9 +16,9 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "q_proj",
     "k_proj",
-    "v_proj",
-    "q_proj"
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7935188532ca057c97e35d2ac25f19e5fae4cf310316411033753c2aedac4f4f
-size 2671008
+oid sha256:06a00240c5d34a9ff7edd4dd5a3e092a2a18c12ba3bd2b86f429da7a7b14e38e
+size 2669168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:466f7b6852211bc4dc3e6a84306a602d73d2cbae547dc06726b7afc040129e28
+oid sha256:d6861692a197e3d3172244c88b75085295c5d68e644c6e610f8fd0d1cb88cdb8
 size 5399290

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44d78c7a5b58042ac25fc7da4ea65482e30dd6f8da26fca722f9c52e7f8076c1
+oid sha256:a2d2b8552fa83772d62927b9906f821a2ecef0bd6edbcaab4a1c02dfdd6b1cee
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a9689c060fa18f4a65213217a79366f663c930ab5ba6ad66745c2e7b18c5a2f
+oid sha256:6c82bedf0a611f290596df2fde142fbda2afa059d93dc846b92ee4f876380a79
 size 1064

last-checkpoint/trainer_state.json

@@ -1,1429 +1,359 @@
 {
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 1.0,
-  "eval_steps": 30,
-  "global_step": 1635,
+  "best_metric": 0.5440758466720581,
+  "best_model_checkpoint": "bart_lora_outputs\\checkpoint-500",
+  "epoch": 0.8156606851549756,
+  "eval_steps": 100,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.01,
+      "epoch": 0.02,
       "learning_rate": 2e-05,
-      "loss": 2.9348,
+      "loss": 2.9197,
       "step": 10
     },
     {
-      "epoch": 0.01,
+      "epoch": 0.03,
       "learning_rate": 4e-05,
-      "loss": 2.993,
+      "loss": 2.872,
       "step": 20
     },
     {
-      "epoch": 0.02,
+      "epoch": 0.05,
       "learning_rate": 6e-05,
-      "loss": 2.6684,
-      "step": 30
-    },
-    {
-      "epoch": 0.02,
-      "eval_loss": 2.1267645359039307,
-      "eval_runtime": 14.5639,
-      "eval_samples_per_second": 80.404,
-      "eval_steps_per_second": 6.729,
+      "loss": 2.6183,
       "step": 30
     },
     {
-      "epoch": 0.02,
+      "epoch": 0.07,
       "learning_rate": 8e-05,
-      "loss": 2.493,
+      "loss": 2.4094,
       "step": 40
     },
     {
-      "epoch": 0.03,
+      "epoch": 0.08,
       "learning_rate": 0.0001,
-      "loss": 2.1131,
+      "loss": 2.15,
       "step": 50
     },
     {
-      "epoch": 0.04,
+      "epoch": 0.1,
       "learning_rate": 0.00012,
-      "loss": 1.7994,
-      "step": 60
-    },
-    {
-      "epoch": 0.04,
-      "eval_loss": 1.461239218711853,
-      "eval_runtime": 15.3978,
-      "eval_samples_per_second": 76.05,
-      "eval_steps_per_second": 6.365,
+      "loss": 1.7088,
       "step": 60
     },
     {
-      "epoch": 0.04,
+      "epoch": 0.11,
       "learning_rate": 0.00014000000000000001,
-      "loss": 1.3698,
+      "loss": 1.413,
       "step": 70
     },
     {
-      "epoch": 0.05,
+      "epoch": 0.13,
       "learning_rate": 0.00016,
-      "loss": 1.205,
+      "loss": 1.2326,
       "step": 80
     },
     {
-      "epoch": 0.06,
+      "epoch": 0.15,
       "learning_rate": 0.00017999999999999998,
-      "loss": 1.1072,
+      "loss": 1.1108,
       "step": 90
     },
     {
-      "epoch": 0.06,
-      "eval_loss": 0.979037344455719,
-      "eval_runtime": 15.999,
-      "eval_samples_per_second": 73.192,
-      "eval_steps_per_second": 6.125,
-      "step": 90
+      "epoch": 0.16,
+      "learning_rate": 0.0002,
+      "loss": 1.0331,
+      "step": 100
     },
     {
-      "epoch": 0.06,
-      "learning_rate": 0.0002,
-      "loss": 1.154,
+      "epoch": 0.16,
+      "eval_loss": 0.8141101598739624,
+      "eval_runtime": 5.616,
+      "eval_samples_per_second": 208.511,
+      "eval_steps_per_second": 13.177,
       "step": 100
     },
     {
-      "epoch": 0.07,
+      "epoch": 0.18,
       "learning_rate": 0.00022,
-      "loss": 0.9462,
+      "loss": 0.9807,
       "step": 110
     },
     {
-      "epoch": 0.07,
+      "epoch": 0.2,
       "learning_rate": 0.00024,
-      "loss": 1.052,
-      "step": 120
-    },
-    {
-      "epoch": 0.07,
-      "eval_loss": 0.8346178531646729,
-      "eval_runtime": 15.0815,
-      "eval_samples_per_second": 77.645,
-      "eval_steps_per_second": 6.498,
+      "loss": 0.9853,
       "step": 120
     },
     {
-      "epoch": 0.08,
+      "epoch": 0.21,
       "learning_rate": 0.00026000000000000003,
-      "loss": 1.0541,
+      "loss": 0.9411,
       "step": 130
     },
     {
-      "epoch": 0.09,
+      "epoch": 0.23,
       "learning_rate": 0.00028000000000000003,
-      "loss": 0.9987,
+      "loss": 0.8733,
       "step": 140
     },
     {
-      "epoch": 0.09,
+      "epoch": 0.24,
       "learning_rate": 0.0003,
-      "loss": 0.9079,
-      "step": 150
-    },
-    {
-      "epoch": 0.09,
-      "eval_loss": 0.8187346458435059,
-      "eval_runtime": 15.0493,
-      "eval_samples_per_second": 77.811,
-      "eval_steps_per_second": 6.512,
+      "loss": 0.8347,
       "step": 150
     },
     {
-      "epoch": 0.1,
+      "epoch": 0.26,
       "learning_rate": 0.00032,
-      "loss": 0.9271,
+      "loss": 0.8786,
       "step": 160
     },
     {
-      "epoch": 0.1,
+      "epoch": 0.28,
       "learning_rate": 0.00034,
-      "loss": 0.9079,
+      "loss": 0.7676,
       "step": 170
     },
     {
-      "epoch": 0.11,
+      "epoch": 0.29,
       "learning_rate": 0.00035999999999999997,
-      "loss": 0.8843,
-      "step": 180
-    },
-    {
-      "epoch": 0.11,
-      "eval_loss": 0.7424212694168091,
-      "eval_runtime": 15.4048,
-      "eval_samples_per_second": 76.016,
-      "eval_steps_per_second": 6.362,
+      "loss": 0.8399,
       "step": 180
     },
     {
-      "epoch": 0.12,
+      "epoch": 0.31,
       "learning_rate": 0.00038,
-      "loss": 0.818,
+      "loss": 0.838,
       "step": 190
     },
     {
-      "epoch": 0.12,
+      "epoch": 0.33,
       "learning_rate": 0.0004,
-      "loss": 0.8288,
+      "loss": 0.7888,
       "step": 200
     },
     {
-      "epoch": 0.13,
-      "learning_rate": 0.00042,
-      "loss": 0.9119,
-      "step": 210
+      "epoch": 0.33,
+      "eval_loss": 0.6890668869018555,
+      "eval_runtime": 5.748,
+      "eval_samples_per_second": 203.722,
+      "eval_steps_per_second": 12.874,
+      "step": 200
     },
     {
-      "epoch": 0.13,
-      "eval_loss": 0.7072588205337524,
-      "eval_runtime": 15.4947,
-      "eval_samples_per_second": 75.574,
-      "eval_steps_per_second": 6.325,
+      "epoch": 0.34,
+      "learning_rate": 0.00042,
+      "loss": 0.7596,
       "step": 210
     },
     {
-      "epoch": 0.13,
+      "epoch": 0.36,
       "learning_rate": 0.00044,
-      "loss": 0.8642,
+      "loss": 0.7959,
       "step": 220
     },
     {
-      "epoch": 0.14,
+      "epoch": 0.38,
       "learning_rate": 0.00046,
-      "loss": 0.7842,
+      "loss": 0.7637,
       "step": 230
     },
     {
-      "epoch": 0.15,
+      "epoch": 0.39,
       "learning_rate": 0.00048,
-      "loss": 0.8218,
-      "step": 240
-    },
-    {
-      "epoch": 0.15,
-      "eval_loss": 0.6722940802574158,
-      "eval_runtime": 15.2385,
-      "eval_samples_per_second": 76.845,
-      "eval_steps_per_second": 6.431,
+      "loss": 0.7413,
       "step": 240
     },
     {
-      "epoch": 0.15,
+      "epoch": 0.41,
       "learning_rate": 0.0005,
-      "loss": 0.8302,
+      "loss": 0.7559,
       "step": 250
     },
     {
-      "epoch": 0.16,
+      "epoch": 0.42,
       "learning_rate": 0.0005200000000000001,
-      "loss": 0.81,
+      "loss": 0.7465,
       "step": 260
     },
     {
-      "epoch": 0.17,
+      "epoch": 0.44,
       "learning_rate": 0.00054,
-      "loss": 0.7181,
-      "step": 270
-    },
-    {
-      "epoch": 0.17,
-      "eval_loss": 0.6630179286003113,
-      "eval_runtime": 15.2349,
-      "eval_samples_per_second": 76.863,
-      "eval_steps_per_second": 6.433,
+      "loss": 0.7311,
       "step": 270
     },
     {
-      "epoch": 0.17,
+      "epoch": 0.46,
       "learning_rate": 0.0005600000000000001,
-      "loss": 0.7874,
+      "loss": 0.7031,
       "step": 280
     },
     {
-      "epoch": 0.18,
+      "epoch": 0.47,
       "learning_rate": 0.00058,
-      "loss": 0.7636,
+      "loss": 0.7565,
       "step": 290
     },
     {
-      "epoch": 0.18,
+      "epoch": 0.49,
       "learning_rate": 0.0006,
-      "loss": 0.7933,
+      "loss": 0.6811,
       "step": 300
     },
     {
-      "epoch": 0.18,
-      "eval_loss": 0.648048460483551,
-      "eval_runtime": 15.3271,
-      "eval_samples_per_second": 76.401,
-      "eval_steps_per_second": 6.394,
+      "epoch": 0.49,
+      "eval_loss": 0.6422508955001831,
+      "eval_runtime": 5.623,
+      "eval_samples_per_second": 208.251,
+      "eval_steps_per_second": 13.16,
       "step": 300
     },
     {
-      "epoch": 0.19,
+      "epoch": 0.51,
       "learning_rate": 0.00062,
-      "loss": 0.806,
+      "loss": 0.7063,
       "step": 310
     },
     {
-      "epoch": 0.2,
+      "epoch": 0.52,
       "learning_rate": 0.00064,
-      "loss": 0.8229,
+      "loss": 0.727,
       "step": 320
     },
     {
-      "epoch": 0.2,
+      "epoch": 0.54,
       "learning_rate": 0.00066,
-      "loss": 0.7979,
-      "step": 330
-    },
-    {
-      "epoch": 0.2,
-      "eval_loss": 0.6749615669250488,
-      "eval_runtime": 15.4179,
-      "eval_samples_per_second": 75.951,
-      "eval_steps_per_second": 6.356,
+      "loss": 0.6678,
       "step": 330
     },
     {
-      "epoch": 0.21,
+      "epoch": 0.55,
       "learning_rate": 0.00068,
-      "loss": 0.7493,
+      "loss": 0.6465,
       "step": 340
     },
     {
-      "epoch": 0.21,
+      "epoch": 0.57,
       "learning_rate": 0.0007,
-      "loss": 0.8082,
+      "loss": 0.6647,
       "step": 350
     },
     {
-      "epoch": 0.22,
+      "epoch": 0.59,
       "learning_rate": 0.0007199999999999999,
-      "loss": 0.7077,
-      "step": 360
-    },
-    {
-      "epoch": 0.22,
-      "eval_loss": 0.6362787485122681,
-      "eval_runtime": 15.3758,
-      "eval_samples_per_second": 76.159,
-      "eval_steps_per_second": 6.374,
+      "loss": 0.6754,
       "step": 360
     },
     {
-      "epoch": 0.23,
+      "epoch": 0.6,
       "learning_rate": 0.00074,
-      "loss": 0.7082,
+      "loss": 0.6419,
       "step": 370
     },
     {
-      "epoch": 0.23,
+      "epoch": 0.62,
       "learning_rate": 0.00076,
-      "loss": 0.7552,
+      "loss": 0.6746,
       "step": 380
     },
     {
-      "epoch": 0.24,
+      "epoch": 0.64,
       "learning_rate": 0.0007800000000000001,
-      "loss": 0.7012,
+      "loss": 0.6279,
       "step": 390
     },
     {
-      "epoch": 0.24,
-      "eval_loss": 0.6303613781929016,
-      "eval_runtime": 15.3461,
-      "eval_samples_per_second": 76.306,
-      "eval_steps_per_second": 6.386,
-      "step": 390
+      "epoch": 0.65,
+      "learning_rate": 0.0008,
+      "loss": 0.7124,
+      "step": 400
     },
     {
-      "epoch": 0.24,
-      "learning_rate": 0.0008,
-      "loss": 0.6524,
+      "epoch": 0.65,
+      "eval_loss": 0.5565645098686218,
+      "eval_runtime": 5.756,
+      "eval_samples_per_second": 203.439,
+      "eval_steps_per_second": 12.856,
       "step": 400
     },
     {
-      "epoch": 0.25,
+      "epoch": 0.67,
       "learning_rate": 0.00082,
-      "loss": 0.7403,
+      "loss": 0.6656,
       "step": 410
     },
     {
-      "epoch": 0.26,
+      "epoch": 0.69,
       "learning_rate": 0.00084,
-      "loss": 0.7808,
-      "step": 420
-    },
-    {
-      "epoch": 0.26,
-      "eval_loss": 0.6001694798469543,
-      "eval_runtime": 15.2815,
-      "eval_samples_per_second": 76.629,
-      "eval_steps_per_second": 6.413,
+      "loss": 0.6298,
       "step": 420
     },
     {
-      "epoch": 0.26,
+      "epoch": 0.7,
       "learning_rate": 0.00086,
-      "loss": 0.6942,
+      "loss": 0.6795,
       "step": 430
     },
     {
-      "epoch": 0.27,
+      "epoch": 0.72,
       "learning_rate": 0.00088,
-      "loss": 0.6691,
+      "loss": 0.6279,
       "step": 440
     },
     {
-      "epoch": 0.28,
+      "epoch": 0.73,
       "learning_rate": 0.0009000000000000001,
-      "loss": 0.613,
+      "loss": 0.6663,
       "step": 450
     },
     {
-      "epoch": 0.28,
-      "eval_loss": 0.6457517743110657,
-      "eval_runtime": 15.2997,
-      "eval_samples_per_second": 76.537,
-      "eval_steps_per_second": 6.405,
-      "step": 450
-    },
-    {
-      "epoch": 0.28,
+      "epoch": 0.75,
       "learning_rate": 0.00092,
-      "loss": 0.7459,
+      "loss": 0.662,
       "step": 460
     },
     {
-      "epoch": 0.29,
+      "epoch": 0.77,
       "learning_rate": 0.00094,
-      "loss": 0.7077,
+      "loss": 0.6339,
       "step": 470
     },
     {
-      "epoch": 0.29,
+      "epoch": 0.78,
       "learning_rate": 0.00096,
-      "loss": 0.6939,
-      "step": 480
-    },
-    {
-      "epoch": 0.29,
-      "eval_loss": 0.6020320057868958,
-      "eval_runtime": 15.2909,
-      "eval_samples_per_second": 76.581,
-      "eval_steps_per_second": 6.409,
+      "loss": 0.6099,
       "step": 480
     },
     {
-      "epoch": 0.3,
+      "epoch": 0.8,
       "learning_rate": 0.00098,
-      "loss": 0.7313,
+      "loss": 0.6465,
       "step": 490
     },
     {
-      "epoch": 0.31,
+      "epoch": 0.82,
       "learning_rate": 0.001,
-      "loss": 0.6848,
+      "loss": 0.615,
       "step": 500
     },
-    {
-      "epoch": 0.31,
-      "learning_rate": 0.0009993690851735015,
-      "loss": 0.7805,
-      "step": 510
-    },
-    {
-      "epoch": 0.31,
-      "eval_loss": 0.5767749547958374,
-      "eval_runtime": 15.3007,
-      "eval_samples_per_second": 76.532,
-      "eval_steps_per_second": 6.405,
-      "step": 510
-    },
-    {
-      "epoch": 0.32,
-      "learning_rate": 0.0009987381703470033,
-      "loss": 0.6732,
-      "step": 520
-    },
-    {
-      "epoch": 0.32,
-      "learning_rate": 0.0009981072555205047,
-      "loss": 0.6052,
-      "step": 530
-    },
-    {
-      "epoch": 0.33,
-      "learning_rate": 0.0009974763406940062,
-      "loss": 0.664,
-      "step": 540
-    },
-    {
-      "epoch": 0.33,
-      "eval_loss": 0.5918195843696594,
-      "eval_runtime": 15.2896,
-      "eval_samples_per_second": 76.588,
-      "eval_steps_per_second": 6.41,
-      "step": 540
-    },
-    {
-      "epoch": 0.34,
-      "learning_rate": 0.000996845425867508,
-      "loss": 0.657,
-      "step": 550
-    },
-    {
-      "epoch": 0.34,
-      "learning_rate": 0.0009962145110410095,
-      "loss": 0.6524,
-      "step": 560
-    },
-    {
-      "epoch": 0.35,
-      "learning_rate": 0.0009955835962145111,
-      "loss": 0.7756,
-      "step": 570
-    },
-    {
-      "epoch": 0.35,
-      "eval_loss": 0.5548932552337646,
-      "eval_runtime": 15.3185,
-      "eval_samples_per_second": 76.443,
-      "eval_steps_per_second": 6.397,
-      "step": 570
-    },
-    {
-      "epoch": 0.35,
-      "learning_rate": 0.0009949526813880128,
-      "loss": 0.6771,
-      "step": 580
-    },
-    {
-      "epoch": 0.36,
-      "learning_rate": 0.0009943217665615142,
-      "loss": 0.6054,
-      "step": 590
-    },
-    {
-      "epoch": 0.37,
-      "learning_rate": 0.0009936908517350158,
-      "loss": 0.6582,
-      "step": 600
-    },
-    {
-      "epoch": 0.37,
-      "eval_loss": 0.5589831471443176,
-      "eval_runtime": 15.3491,
-      "eval_samples_per_second": 76.291,
-      "eval_steps_per_second": 6.385,
-      "step": 600
-    },
-    {
-      "epoch": 0.37,
-      "learning_rate": 0.0009930599369085175,
-      "loss": 0.6386,
-      "step": 610
-    },
-    {
-      "epoch": 0.38,
-      "learning_rate": 0.000992429022082019,
-      "loss": 0.6355,
-      "step": 620
-    },
-    {
-      "epoch": 0.39,
-      "learning_rate": 0.0009917981072555206,
-      "loss": 0.6883,
-      "step": 630
-    },
-    {
-      "epoch": 0.39,
-      "eval_loss": 0.5954719185829163,
-      "eval_runtime": 15.317,
-      "eval_samples_per_second": 76.451,
-      "eval_steps_per_second": 6.398,
-      "step": 630
-    },
-    {
-      "epoch": 0.39,
-      "learning_rate": 0.0009911671924290222,
-      "loss": 0.6283,
-      "step": 640
-    },
-    {
-      "epoch": 0.4,
-      "learning_rate": 0.0009905362776025236,
-      "loss": 0.6973,
-      "step": 650
-    },
-    {
-      "epoch": 0.4,
-      "learning_rate": 0.0009899053627760253,
-      "loss": 0.6252,
-      "step": 660
-    },
-    {
-      "epoch": 0.4,
-      "eval_loss": 0.5695869326591492,
-      "eval_runtime": 15.3301,
-      "eval_samples_per_second": 76.386,
-      "eval_steps_per_second": 6.393,
-      "step": 660
-    },
-    {
-      "epoch": 0.41,
-      "learning_rate": 0.000989274447949527,
-      "loss": 0.6971,
-      "step": 670
-    },
-    {
-      "epoch": 0.42,
-      "learning_rate": 0.0009886435331230286,
-      "loss": 0.6276,
-      "step": 680
-    },
-    {
-      "epoch": 0.42,
-      "learning_rate": 0.00098801261829653,
-      "loss": 0.6776,
-      "step": 690
-    },
-    {
-      "epoch": 0.42,
-      "eval_loss": 0.5438072085380554,
-      "eval_runtime": 15.2869,
-      "eval_samples_per_second": 76.602,
-      "eval_steps_per_second": 6.411,
-      "step": 690
-    },
-    {
-      "epoch": 0.43,
-      "learning_rate": 0.0009873817034700316,
-      "loss": 0.5928,
-      "step": 700
-    },
-    {
-      "epoch": 0.43,
-      "learning_rate": 0.0009867507886435333,
-      "loss": 0.6095,
-      "step": 710
-    },
-    {
-      "epoch": 0.44,
-      "learning_rate": 0.0009861198738170347,
-      "loss": 0.6427,
-      "step": 720
-    },
-    {
-      "epoch": 0.44,
-      "eval_loss": 0.5402929186820984,
-      "eval_runtime": 15.332,
-      "eval_samples_per_second": 76.376,
-      "eval_steps_per_second": 6.392,
-      "step": 720
-    },
-    {
-      "epoch": 0.45,
-      "learning_rate": 0.0009854889589905364,
-      "loss": 0.5991,
-      "step": 730
-    },
-    {
-      "epoch": 0.45,
-      "learning_rate": 0.000984858044164038,
-      "loss": 0.6153,
-      "step": 740
-    },
-    {
-      "epoch": 0.46,
-      "learning_rate": 0.0009842271293375394,
-      "loss": 0.6422,
-      "step": 750
-    },
-    {
-      "epoch": 0.46,
-      "eval_loss": 0.55536949634552,
-      "eval_runtime": 15.315,
-      "eval_samples_per_second": 76.461,
-      "eval_steps_per_second": 6.399,
-      "step": 750
-    },
-    {
-      "epoch": 0.46,
-      "learning_rate": 0.000983596214511041,
-      "loss": 0.6874,
-      "step": 760
-    },
-    {
-      "epoch": 0.47,
-      "learning_rate": 0.0009829652996845427,
-      "loss": 0.6588,
-      "step": 770
-    },
-    {
-      "epoch": 0.48,
-      "learning_rate": 0.0009823343848580442,
-      "loss": 0.5467,
-      "step": 780
-    },
-    {
-      "epoch": 0.48,
-      "eval_loss": 0.5687702298164368,
-      "eval_runtime": 15.3018,
-      "eval_samples_per_second": 76.527,
-      "eval_steps_per_second": 6.404,
-      "step": 780
-    },
-    {
-      "epoch": 0.48,
-      "learning_rate": 0.0009817034700315458,
-      "loss": 0.5929,
-      "step": 790
-    },
-    {
-      "epoch": 0.49,
-      "learning_rate": 0.0009810725552050475,
-      "loss": 0.6407,
-      "step": 800
-    },
-    {
-      "epoch": 0.5,
-      "learning_rate": 0.0009804416403785489,
-      "loss": 0.621,
-      "step": 810
-    },
-    {
-      "epoch": 0.5,
-      "eval_loss": 0.5593787431716919,
-      "eval_runtime": 15.32,
-      "eval_samples_per_second": 76.436,
-      "eval_steps_per_second": 6.397,
-      "step": 810
-    },
-    {
-      "epoch": 0.5,
-      "learning_rate": 0.0009798107255520505,
-      "loss": 0.6191,
-      "step": 820
-    },
-    {
-      "epoch": 0.51,
-      "learning_rate": 0.0009791798107255522,
-      "loss": 0.6468,
-      "step": 830
-    },
-    {
-      "epoch": 0.51,
-      "learning_rate": 0.0009785488958990536,
-      "loss": 0.6486,
-      "step": 840
-    },
-    {
-      "epoch": 0.51,
-      "eval_loss": 0.542827308177948,
-      "eval_runtime": 15.3141,
-      "eval_samples_per_second": 76.466,
-      "eval_steps_per_second": 6.399,
-      "step": 840
-    },
-    {
-      "epoch": 0.52,
-      "learning_rate": 0.0009779179810725552,
-      "loss": 0.6503,
-      "step": 850
-    },
-    {
-      "epoch": 0.53,
-      "learning_rate": 0.000977287066246057,
-      "loss": 0.5697,
-      "step": 860
-    },
-    {
-      "epoch": 0.53,
-      "learning_rate": 0.0009766561514195583,
-      "loss": 0.5993,
-      "step": 870
-    },
-    {
-      "epoch": 0.53,
-      "eval_loss": 0.5758046507835388,
-      "eval_runtime": 15.2882,
-      "eval_samples_per_second": 76.595,
-      "eval_steps_per_second": 6.41,
-      "step": 870
-    },
-    {
-      "epoch": 0.54,
-      "learning_rate": 0.00097602523659306,
-      "loss": 0.6151,
-      "step": 880
-    },
-    {
-      "epoch": 0.54,
-      "learning_rate": 0.0009753943217665615,
-      "loss": 0.5733,
-      "step": 890
-    },
-    {
-      "epoch": 0.55,
-      "learning_rate": 0.0009747634069400632,
-      "loss": 0.5637,
-      "step": 900
-    },
-    {
-      "epoch": 0.55,
-      "eval_loss": 0.5380309224128723,
-      "eval_runtime": 15.3344,
-      "eval_samples_per_second": 76.364,
-      "eval_steps_per_second": 6.391,
-      "step": 900
-    },
-    {
-      "epoch": 0.56,
-      "learning_rate": 0.0009741324921135647,
-      "loss": 0.5768,
-      "step": 910
-    },
-    {
-      "epoch": 0.56,
-      "learning_rate": 0.0009735015772870662,
-      "loss": 0.5445,
-      "step": 920
-    },
-    {
-      "epoch": 0.57,
-      "learning_rate": 0.0009728706624605679,
-      "loss": 0.627,
-      "step": 930
-    },
-    {
-      "epoch": 0.57,
-      "eval_loss": 0.5249527096748352,
-      "eval_runtime": 15.3162,
-      "eval_samples_per_second": 76.455,
-      "eval_steps_per_second": 6.398,
-      "step": 930
-    },
-    {
-      "epoch": 0.57,
-      "learning_rate": 0.0009722397476340694,
-      "loss": 0.5396,
-      "step": 940
-    },
-    {
-      "epoch": 0.58,
-      "learning_rate": 0.000971608832807571,
-      "loss": 0.6558,
-      "step": 950
-    },
-    {
-      "epoch": 0.59,
-      "learning_rate": 0.0009709779179810726,
-      "loss": 0.5876,
-      "step": 960
-    },
-    {
-      "epoch": 0.59,
-      "eval_loss": 0.5324742197990417,
-      "eval_runtime": 15.3008,
-      "eval_samples_per_second": 76.532,
-      "eval_steps_per_second": 6.405,
-      "step": 960
-    },
-    {
-      "epoch": 0.59,
-      "learning_rate": 0.0009703470031545741,
-      "loss": 0.581,
-      "step": 970
-    },
-    {
-      "epoch": 0.6,
-      "learning_rate": 0.0009697160883280758,
-      "loss": 0.5938,
-      "step": 980
-    },
-    {
-      "epoch": 0.61,
-      "learning_rate": 0.0009690851735015773,
-      "loss": 0.5539,
-      "step": 990
-    },
-    {
-      "epoch": 0.61,
-      "eval_loss": 0.5384231209754944,
-      "eval_runtime": 15.3241,
-      "eval_samples_per_second": 76.416,
-      "eval_steps_per_second": 6.395,
-      "step": 990
-    },
-    {
-      "epoch": 0.61,
-      "learning_rate": 0.0009684542586750789,
-      "loss": 0.6287,
-      "step": 1000
-    },
-    {
-      "epoch": 0.62,
-      "learning_rate": 0.0009678233438485805,
-      "loss": 0.6094,
-      "step": 1010
-    },
-    {
-      "epoch": 0.62,
-      "learning_rate": 0.000967192429022082,
-      "loss": 0.5671,
-      "step": 1020
-    },
-    {
-      "epoch": 0.62,
-      "eval_loss": 0.5662776827812195,
-      "eval_runtime": 15.3105,
-      "eval_samples_per_second": 76.483,
-      "eval_steps_per_second": 6.401,
-      "step": 1020
-    },
-    {
-      "epoch": 0.63,
-      "learning_rate": 0.0009665615141955836,
-      "loss": 0.5863,
-      "step": 1030
-    },
-    {
-      "epoch": 0.64,
-      "learning_rate": 0.0009659305993690852,
-      "loss": 0.5675,
-      "step": 1040
-    },
-    {
-      "epoch": 0.64,
-      "learning_rate": 0.0009652996845425868,
-      "loss": 0.714,
-      "step": 1050
-    },
-    {
-      "epoch": 0.64,
-      "eval_loss": 0.5345898270606995,
-      "eval_runtime": 15.3604,
-      "eval_samples_per_second": 76.235,
-      "eval_steps_per_second": 6.38,
-      "step": 1050
-    },
-    {
-      "epoch": 0.65,
-      "learning_rate": 0.0009646687697160883,
-      "loss": 0.6364,
-      "step": 1060
-    },
-    {
-      "epoch": 0.65,
-      "learning_rate": 0.0009640378548895899,
-      "loss": 0.5733,
-      "step": 1070
-    },
-    {
-      "epoch": 0.66,
-      "learning_rate": 0.0009634069400630915,
-      "loss": 0.6243,
-      "step": 1080
-    },
-    {
-      "epoch": 0.66,
-      "eval_loss": 0.5188413858413696,
-      "eval_runtime": 15.3443,
-      "eval_samples_per_second": 76.315,
-      "eval_steps_per_second": 6.387,
-      "step": 1080
-    },
-    {
-      "epoch": 0.67,
-      "learning_rate": 0.0009627760252365931,
-      "loss": 0.5955,
-      "step": 1090
-    },
-    {
-      "epoch": 0.67,
-      "learning_rate": 0.0009621451104100947,
-      "loss": 0.5949,
-      "step": 1100
-    },
-    {
-      "epoch": 0.68,
-      "learning_rate": 0.0009615141955835962,
-      "loss": 0.5342,
-      "step": 1110
-    },
-    {
-      "epoch": 0.68,
-      "eval_loss": 0.5572788119316101,
-      "eval_runtime": 15.4088,
-      "eval_samples_per_second": 75.996,
-      "eval_steps_per_second": 6.36,
-      "step": 1110
-    },
-    {
-      "epoch": 0.69,
-      "learning_rate": 0.0009608832807570978,
-      "loss": 0.5371,
-      "step": 1120
-    },
-    {
-      "epoch": 0.69,
-      "learning_rate": 0.0009602523659305994,
-      "loss": 0.6767,
-      "step": 1130
-    },
-    {
-      "epoch": 0.7,
-      "learning_rate": 0.0009596214511041009,
-      "loss": 0.589,
-      "step": 1140
-    },
-    {
-      "epoch": 0.7,
-      "eval_loss": 0.5333449840545654,
-      "eval_runtime": 15.3542,
-      "eval_samples_per_second": 76.266,
-      "eval_steps_per_second": 6.383,
-      "step": 1140
-    },
-    {
-      "epoch": 0.7,
-      "learning_rate": 0.0009589905362776026,
-      "loss": 0.5914,
-      "step": 1150
-    },
-    {
-      "epoch": 0.71,
-      "learning_rate": 0.0009583596214511041,
-      "loss": 0.547,
-      "step": 1160
-    },
-    {
-      "epoch": 0.72,
-      "learning_rate": 0.0009577287066246056,
-      "loss": 0.577,
-      "step": 1170
-    },
-    {
-      "epoch": 0.72,
-      "eval_loss": 0.520677924156189,
-      "eval_runtime": 15.3767,
-      "eval_samples_per_second": 76.154,
-      "eval_steps_per_second": 6.373,
-      "step": 1170
-    },
-    {
-      "epoch": 0.72,
-      "learning_rate": 0.0009570977917981073,
-      "loss": 0.6002,
-      "step": 1180
-    },
-    {
-      "epoch": 0.73,
-      "learning_rate": 0.0009564668769716088,
-      "loss": 0.6236,
-      "step": 1190
-    },
-    {
-      "epoch": 0.73,
-      "learning_rate": 0.0009558359621451105,
-      "loss": 0.5757,
-      "step": 1200
-    },
-    {
-      "epoch": 0.73,
-      "eval_loss": 0.5401705503463745,
-      "eval_runtime": 15.3622,
-      "eval_samples_per_second": 76.226,
-      "eval_steps_per_second": 6.379,
-      "step": 1200
-    },
-    {
-      "epoch": 0.74,
-      "learning_rate": 0.000955205047318612,
-      "loss": 0.681,
-      "step": 1210
-    },
-    {
-      "epoch": 0.75,
-      "learning_rate": 0.0009545741324921136,
-      "loss": 0.5508,
-      "step": 1220
-    },
-    {
-      "epoch": 0.75,
-      "learning_rate": 0.0009539432176656152,
-      "loss": 0.5726,
-      "step": 1230
-    },
-    {
-      "epoch": 0.75,
-      "eval_loss": 0.5101749897003174,
-      "eval_runtime": 15.3465,
-      "eval_samples_per_second": 76.304,
-      "eval_steps_per_second": 6.386,
-      "step": 1230
-    },
-    {
-      "epoch": 0.76,
-      "learning_rate": 0.0009533123028391167,
-      "loss": 0.5528,
-      "step": 1240
-    },
-    {
-      "epoch": 0.76,
-      "learning_rate": 0.0009526813880126183,
-      "loss": 0.6107,
-      "step": 1250
-    },
-    {
-      "epoch": 0.77,
-      "learning_rate": 0.0009520504731861199,
-      "loss": 0.5675,
-      "step": 1260
-    },
-    {
-      "epoch": 0.77,
-      "eval_loss": 0.5156053900718689,
-      "eval_runtime": 15.3646,
-      "eval_samples_per_second": 76.214,
-      "eval_steps_per_second": 6.378,
-      "step": 1260
-    },
-    {
-      "epoch": 0.78,
-      "learning_rate": 0.0009514195583596215,
-      "loss": 0.5795,
-      "step": 1270
-    },
-    {
-      "epoch": 0.78,
-      "learning_rate": 0.000950788643533123,
-      "loss": 0.5489,
-      "step": 1280
-    },
-    {
-      "epoch": 0.79,
-      "learning_rate": 0.0009501577287066246,
-      "loss": 0.5931,
-      "step": 1290
-    },
-    {
-      "epoch": 0.79,
-      "eval_loss": 0.5232254266738892,
-      "eval_runtime": 15.3627,
-      "eval_samples_per_second": 76.224,
-      "eval_steps_per_second": 6.379,
-      "step": 1290
-    },
-    {
-      "epoch": 0.8,
-      "learning_rate": 0.0009495268138801262,
-      "loss": 0.6082,
-      "step": 1300
-    },
-    {
-      "epoch": 0.8,
-      "learning_rate": 0.0009488958990536278,
-      "loss": 0.6085,
-      "step": 1310
-    },
-    {
-      "epoch": 0.81,
-      "learning_rate": 0.0009482649842271294,
-      "loss": 0.5727,
-      "step": 1320
-    },
-    {
-      "epoch": 0.81,
-      "eval_loss": 0.5149978399276733,
-      "eval_runtime": 15.3731,
-      "eval_samples_per_second": 76.172,
-      "eval_steps_per_second": 6.375,
-      "step": 1320
-    },
-    {
-      "epoch": 0.81,
-      "learning_rate": 0.0009476340694006309,
-      "loss": 0.5912,
-      "step": 1330
-    },
     {
       "epoch": 0.82,
-      "learning_rate": 0.0009470031545741325,
-      "loss": 0.6397,
-      "step": 1340
-    },
-    {
-      "epoch": 0.83,
-      "learning_rate": 0.0009463722397476341,
-      "loss": 0.6233,
-      "step": 1350
-    },
-    {
-      "epoch": 0.83,
-      "eval_loss": 0.5305810570716858,
-      "eval_runtime": 15.3303,
-      "eval_samples_per_second": 76.385,
-      "eval_steps_per_second": 6.393,
-      "step": 1350
-    },
-    {
-      "epoch": 0.83,
-      "learning_rate": 0.0009457413249211356,
-      "loss": 0.54,
-      "step": 1360
-    },
-    {
-      "epoch": 0.84,
-      "learning_rate": 0.0009451104100946373,
-      "loss": 0.6118,
-      "step": 1370
-    },
-    {
-      "epoch": 0.84,
-      "learning_rate": 0.0009444794952681388,
-      "loss": 0.5661,
-      "step": 1380
-    },
-    {
-      "epoch": 0.84,
-      "eval_loss": 0.5178245306015015,
-      "eval_runtime": 15.3439,
-      "eval_samples_per_second": 76.317,
-      "eval_steps_per_second": 6.387,
-      "step": 1380
-    },
-    {
-      "epoch": 0.85,
-      "learning_rate": 0.0009438485804416403,
-      "loss": 0.6365,
-      "step": 1390
-    },
-    {
-      "epoch": 0.86,
-      "learning_rate": 0.000943217665615142,
-      "loss": 0.5635,
-      "step": 1400
-    },
-    {
-      "epoch": 0.86,
-      "learning_rate": 0.0009425867507886435,
-      "loss": 0.5993,
-      "step": 1410
-    },
-    {
-      "epoch": 0.86,
-      "eval_loss": 0.5094326734542847,
-      "eval_runtime": 15.3033,
-      "eval_samples_per_second": 76.519,
-      "eval_steps_per_second": 6.404,
-      "step": 1410
-    },
-    {
-      "epoch": 0.87,
-      "learning_rate": 0.0009419558359621452,
-      "loss": 0.5921,
-      "step": 1420
-    },
-    {
-      "epoch": 0.87,
-      "learning_rate": 0.0009413249211356467,
-      "loss": 0.5571,
-      "step": 1430
-    },
-    {
-      "epoch": 0.88,
-      "learning_rate": 0.0009406940063091482,
-      "loss": 0.5359,
-      "step": 1440
-    },
-    {
-      "epoch": 0.88,
-      "eval_loss": 0.5110692977905273,
-      "eval_runtime": 15.3327,
-      "eval_samples_per_second": 76.373,
-      "eval_steps_per_second": 6.392,
-      "step": 1440
-    },
-    {
-      "epoch": 0.89,
-      "learning_rate": 0.0009400630914826499,
-      "loss": 0.5363,
-      "step": 1450
-    },
-    {
-      "epoch": 0.89,
-      "learning_rate": 0.0009394321766561514,
-      "loss": 0.5619,
-      "step": 1460
-    },
-    {
-      "epoch": 0.9,
-      "learning_rate": 0.000938801261829653,
-      "loss": 0.5925,
-      "step": 1470
-    },
-    {
-      "epoch": 0.9,
-      "eval_loss": 0.5252500176429749,
-      "eval_runtime": 15.3611,
-      "eval_samples_per_second": 76.231,
-      "eval_steps_per_second": 6.38,
-      "step": 1470
-    },
-    {
-      "epoch": 0.91,
-      "learning_rate": 0.0009381703470031546,
-      "loss": 0.611,
-      "step": 1480
-    },
-    {
-      "epoch": 0.91,
-      "learning_rate": 0.0009375394321766562,
-      "loss": 0.581,
-      "step": 1490
-    },
-    {
-      "epoch": 0.92,
-      "learning_rate": 0.0009369085173501577,
-      "loss": 0.4984,
-      "step": 1500
-    },
-    {
-      "epoch": 0.92,
-      "eval_loss": 0.5312231779098511,
-      "eval_runtime": 15.5553,
-      "eval_samples_per_second": 75.28,
-      "eval_steps_per_second": 6.3,
-      "step": 1500
-    },
-    {
-      "epoch": 0.92,
-      "learning_rate": 0.0009362776025236593,
-      "loss": 0.5921,
-      "step": 1510
-    },
-    {
-      "epoch": 0.93,
-      "learning_rate": 0.0009356466876971609,
-      "loss": 0.5776,
-      "step": 1520
-    },
-    {
-      "epoch": 0.94,
-      "learning_rate": 0.0009350157728706625,
-      "loss": 0.5551,
-      "step": 1530
-    },
-    {
-      "epoch": 0.94,
-      "eval_loss": 0.515774130821228,
-      "eval_runtime": 15.3618,
-      "eval_samples_per_second": 76.228,
-      "eval_steps_per_second": 6.379,
-      "step": 1530
-    },
-    {
-      "epoch": 0.94,
-      "learning_rate": 0.0009343848580441641,
-      "loss": 0.5832,
-      "step": 1540
-    },
-    {
-      "epoch": 0.95,
-      "learning_rate": 0.0009337539432176656,
-      "loss": 0.5673,
-      "step": 1550
-    },
-    {
-      "epoch": 0.95,
-      "learning_rate": 0.0009331230283911672,
-      "loss": 0.6288,
-      "step": 1560
-    },
-    {
-      "epoch": 0.95,
-      "eval_loss": 0.4972882866859436,
-      "eval_runtime": 15.359,
-      "eval_samples_per_second": 76.242,
-      "eval_steps_per_second": 6.381,
-      "step": 1560
-    },
-    {
-      "epoch": 0.96,
-      "learning_rate": 0.0009324921135646688,
-      "loss": 0.555,
-      "step": 1570
-    },
-    {
-      "epoch": 0.97,
-      "learning_rate": 0.0009318611987381703,
-      "loss": 0.5405,
-      "step": 1580
-    },
-    {
-      "epoch": 0.97,
-      "learning_rate": 0.000931230283911672,
-      "loss": 0.6164,
-      "step": 1590
-    },
-    {
-      "epoch": 0.97,
-      "eval_loss": 0.5089274644851685,
-      "eval_runtime": 15.3184,
-      "eval_samples_per_second": 76.444,
-      "eval_steps_per_second": 6.398,
-      "step": 1590
-    },
-    {
-      "epoch": 0.98,
-      "learning_rate": 0.0009305993690851735,
-      "loss": 0.5609,
-      "step": 1600
-    },
-    {
-      "epoch": 0.98,
-      "learning_rate": 0.000929968454258675,
-      "loss": 0.6188,
-      "step": 1610
-    },
-    {
-      "epoch": 0.99,
-      "learning_rate": 0.0009293375394321767,
-      "loss": 0.5423,
-      "step": 1620
-    },
-    {
-      "epoch": 0.99,
-      "eval_loss": 0.5065773129463196,
-      "eval_runtime": 15.2816,
-      "eval_samples_per_second": 76.628,
-      "eval_steps_per_second": 6.413,
-      "step": 1620
-    },
-    {
-      "epoch": 1.0,
-      "learning_rate": 0.0009287066246056782,
-      "loss": 0.5393,
-      "step": 1630
+      "eval_loss": 0.5440758466720581,
+      "eval_runtime": 5.541,
+      "eval_samples_per_second": 211.333,
+      "eval_steps_per_second": 13.355,
+      "step": 500
     }
   ],
   "logging_steps": 10,
-  "max_steps": 16350,
+  "max_steps": 6130,
   "num_train_epochs": 10,
   "save_steps": 500,
-  "total_flos": 1250508061458432.0,
+  "total_flos": 1077083681587200.0,
   "trial_name": null,
   "trial_params": null
 }

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed73ee57056e6e53e9f323b135ace6c4a0b4f7e29df3c6690c9977fa6847b593
+oid sha256:ef926b73ee7f8ea582bb0c8e88b44eeac71091525992f56ddfde5d64524b7acf
 size 4600