Upload 11 files

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2054b8a70f39f1311d58300ac2f9ff983723d88464d3e6c65098f7c9353cf782
+oid sha256:4d34ff14e4635049fc69270e532cc18dd05f28bd358833f0fcd8a5245a8ea695
 size 522284877

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c48312661d3c907412387b4da9b5dcb860f1b8d364f67ff8686ec114f338b08
+oid sha256:5c8d7a519c6145532b7b330e12787e047b51ab6b02fe38e6ba666b0d8e3c87ab
 size 1044539909

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58e2e1749611406923859c3ac550e806510c13fbc51536779fc8dd16b1beca83
+oid sha256:32a88e3b78c5281b945c1930b107415bc3c89413ca4dd9b4b5721d237c955737
 size 14575

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 512,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {

trainer_state.json

@@ -1,316 +1,316 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8123476848090982,
+  "epoch": 0.08574858514834505,
   "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.02,
+      "epoch": 0.0,
       "learning_rate": 0.0002,
-      "loss": 1.3234,
+      "loss": 2.6881,
       "step": 10
     },
     {
-      "epoch": 0.03,
+      "epoch": 0.0,
       "learning_rate": 0.0002,
-      "loss": 1.3389,
+      "loss": 2.5965,
       "step": 20
     },
     {
-      "epoch": 0.05,
+      "epoch": 0.01,
       "learning_rate": 0.0002,
-      "loss": 1.3999,
+      "loss": 2.5403,
       "step": 30
     },
     {
-      "epoch": 0.06,
+      "epoch": 0.01,
       "learning_rate": 0.0002,
-      "loss": 1.6548,
+      "loss": 2.488,
       "step": 40
     },
     {
-      "epoch": 0.08,
+      "epoch": 0.01,
       "learning_rate": 0.0002,
-      "loss": 1.8545,
+      "loss": 2.4193,
       "step": 50
     },
     {
-      "epoch": 0.1,
+      "epoch": 0.01,
       "learning_rate": 0.0002,
-      "loss": 1.2073,
+      "loss": 2.5918,
       "step": 60
     },
     {
-      "epoch": 0.11,
+      "epoch": 0.01,
       "learning_rate": 0.0002,
-      "loss": 1.2975,
+      "loss": 2.4684,
       "step": 70
     },
     {
-      "epoch": 0.13,
+      "epoch": 0.01,
       "learning_rate": 0.0002,
-      "loss": 1.3666,
+      "loss": 2.5298,
       "step": 80
     },
     {
-      "epoch": 0.15,
+      "epoch": 0.02,
       "learning_rate": 0.0002,
-      "loss": 1.5847,
+      "loss": 2.4885,
       "step": 90
     },
     {
-      "epoch": 0.16,
+      "epoch": 0.02,
       "learning_rate": 0.0002,
-      "loss": 1.787,
+      "loss": 2.3809,
       "step": 100
     },
     {
-      "epoch": 0.18,
+      "epoch": 0.02,
       "learning_rate": 0.0002,
-      "loss": 1.1914,
+      "loss": 2.534,
       "step": 110
     },
     {
-      "epoch": 0.19,
+      "epoch": 0.02,
       "learning_rate": 0.0002,
-      "loss": 1.2603,
+      "loss": 2.4542,
       "step": 120
     },
     {
-      "epoch": 0.21,
+      "epoch": 0.02,
       "learning_rate": 0.0002,
-      "loss": 1.3678,
+      "loss": 2.4874,
       "step": 130
     },
     {
-      "epoch": 0.23,
+      "epoch": 0.02,
       "learning_rate": 0.0002,
-      "loss": 1.4669,
+      "loss": 2.4379,
       "step": 140
     },
     {
-      "epoch": 0.24,
+      "epoch": 0.03,
       "learning_rate": 0.0002,
-      "loss": 1.8138,
+      "loss": 2.2407,
       "step": 150
     },
     {
-      "epoch": 0.26,
+      "epoch": 0.03,
       "learning_rate": 0.0002,
-      "loss": 1.209,
+      "loss": 2.5581,
       "step": 160
     },
     {
-      "epoch": 0.28,
+      "epoch": 0.03,
       "learning_rate": 0.0002,
-      "loss": 1.219,
+      "loss": 2.4943,
       "step": 170
     },
     {
-      "epoch": 0.29,
+      "epoch": 0.03,
       "learning_rate": 0.0002,
-      "loss": 1.2781,
+      "loss": 2.4102,
       "step": 180
     },
     {
-      "epoch": 0.31,
+      "epoch": 0.03,
       "learning_rate": 0.0002,
-      "loss": 1.5252,
+      "loss": 2.4299,
       "step": 190
     },
     {
-      "epoch": 0.32,
+      "epoch": 0.03,
       "learning_rate": 0.0002,
-      "loss": 1.8084,
+      "loss": 2.2748,
       "step": 200
     },
     {
-      "epoch": 0.34,
+      "epoch": 0.04,
       "learning_rate": 0.0002,
-      "loss": 1.1805,
+      "loss": 2.5647,
       "step": 210
     },
     {
-      "epoch": 0.36,
+      "epoch": 0.04,
       "learning_rate": 0.0002,
-      "loss": 1.2208,
+      "loss": 2.4367,
       "step": 220
     },
     {
-      "epoch": 0.37,
+      "epoch": 0.04,
       "learning_rate": 0.0002,
-      "loss": 1.3424,
+      "loss": 2.4337,
       "step": 230
     },
     {
-      "epoch": 0.39,
+      "epoch": 0.04,
       "learning_rate": 0.0002,
-      "loss": 1.5527,
+      "loss": 2.3807,
       "step": 240
     },
     {
-      "epoch": 0.41,
+      "epoch": 0.04,
       "learning_rate": 0.0002,
-      "loss": 1.7663,
+      "loss": 2.2684,
       "step": 250
     },
     {
-      "epoch": 0.42,
+      "epoch": 0.04,
       "learning_rate": 0.0002,
-      "loss": 1.2059,
+      "loss": 2.5007,
       "step": 260
     },
     {
-      "epoch": 0.44,
+      "epoch": 0.05,
       "learning_rate": 0.0002,
-      "loss": 1.2285,
+      "loss": 2.3955,
       "step": 270
     },
     {
-      "epoch": 0.45,
+      "epoch": 0.05,
       "learning_rate": 0.0002,
-      "loss": 1.3103,
+      "loss": 2.3898,
       "step": 280
     },
     {
-      "epoch": 0.47,
+      "epoch": 0.05,
       "learning_rate": 0.0002,
-      "loss": 1.5495,
+      "loss": 2.4153,
       "step": 290
     },
     {
-      "epoch": 0.49,
+      "epoch": 0.05,
       "learning_rate": 0.0002,
-      "loss": 1.7774,
+      "loss": 2.1962,
       "step": 300
     },
     {
-      "epoch": 0.5,
+      "epoch": 0.05,
       "learning_rate": 0.0002,
-      "loss": 1.205,
+      "loss": 2.4459,
       "step": 310
     },
     {
-      "epoch": 0.52,
+      "epoch": 0.05,
       "learning_rate": 0.0002,
-      "loss": 1.1946,
+      "loss": 2.3572,
       "step": 320
     },
     {
-      "epoch": 0.54,
+      "epoch": 0.06,
       "learning_rate": 0.0002,
-      "loss": 1.2776,
+      "loss": 2.4047,
       "step": 330
     },
     {
-      "epoch": 0.55,
+      "epoch": 0.06,
       "learning_rate": 0.0002,
-      "loss": 1.5044,
+      "loss": 2.3468,
       "step": 340
     },
     {
-      "epoch": 0.57,
+      "epoch": 0.06,
       "learning_rate": 0.0002,
-      "loss": 1.674,
+      "loss": 2.2472,
       "step": 350
     },
     {
-      "epoch": 0.58,
+      "epoch": 0.06,
       "learning_rate": 0.0002,
-      "loss": 1.1901,
+      "loss": 2.4912,
       "step": 360
     },
     {
-      "epoch": 0.6,
+      "epoch": 0.06,
       "learning_rate": 0.0002,
-      "loss": 1.2326,
+      "loss": 2.3635,
       "step": 370
     },
     {
-      "epoch": 0.62,
+      "epoch": 0.07,
       "learning_rate": 0.0002,
-      "loss": 1.3597,
+      "loss": 2.3732,
       "step": 380
     },
     {
-      "epoch": 0.63,
+      "epoch": 0.07,
       "learning_rate": 0.0002,
-      "loss": 1.5719,
+      "loss": 2.3813,
       "step": 390
     },
     {
-      "epoch": 0.65,
+      "epoch": 0.07,
       "learning_rate": 0.0002,
-      "loss": 1.727,
+      "loss": 2.0932,
       "step": 400
     },
     {
-      "epoch": 0.67,
+      "epoch": 0.07,
       "learning_rate": 0.0002,
-      "loss": 1.1642,
+      "loss": 2.5275,
       "step": 410
     },
     {
-      "epoch": 0.68,
+      "epoch": 0.07,
       "learning_rate": 0.0002,
-      "loss": 1.2354,
+      "loss": 2.3711,
       "step": 420
     },
     {
-      "epoch": 0.7,
+      "epoch": 0.07,
       "learning_rate": 0.0002,
-      "loss": 1.3189,
+      "loss": 2.364,
       "step": 430
     },
     {
-      "epoch": 0.71,
+      "epoch": 0.08,
       "learning_rate": 0.0002,
-      "loss": 1.5433,
+      "loss": 2.3475,
       "step": 440
     },
     {
-      "epoch": 0.73,
+      "epoch": 0.08,
       "learning_rate": 0.0002,
-      "loss": 1.8169,
+      "loss": 2.2098,
       "step": 450
     },
     {
-      "epoch": 0.75,
+      "epoch": 0.08,
       "learning_rate": 0.0002,
-      "loss": 1.1461,
+      "loss": 2.4563,
       "step": 460
     },
     {
-      "epoch": 0.76,
+      "epoch": 0.08,
       "learning_rate": 0.0002,
-      "loss": 1.2557,
+      "loss": 2.385,
       "step": 470
     },
     {
-      "epoch": 0.78,
+      "epoch": 0.08,
       "learning_rate": 0.0002,
-      "loss": 1.3328,
+      "loss": 2.3669,
       "step": 480
     },
     {
-      "epoch": 0.8,
+      "epoch": 0.08,
       "learning_rate": 0.0002,
-      "loss": 1.6532,
+      "loss": 2.41,
       "step": 490
     },
     {
-      "epoch": 0.81,
+      "epoch": 0.09,
       "learning_rate": 0.0002,
-      "loss": 1.7721,
+      "loss": 2.1759,
       "step": 500
     }
   ],
   "max_steps": 500,
   "num_train_epochs": 1,
-  "total_flos": 5.531824689009562e+16,
+  "total_flos": 3.806741872341811e+16,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00dd95671ba3e81fb44880e9a3d3ceee276294302e82002a2ade3eb27e6f042c
+oid sha256:f3d4f38ea2ce564961f05463e079bab73584cf1f2f14c1ee0013c0984507b263
 size 3963