Upload folder using huggingface_hub

adapter_config.json

@@ -1,6 +1,6 @@
 {
   "auto_mapping": null,
-  "base_model_name_or_path": "TinyPixel/redpajama-3b",
+  "base_model_name_or_path": "TinyPixel/redpajama-3b-mix",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbef5f96cf940de9a96f60aaf5e997b148c50544a173ff917f2d39888d8d6e5c
+oid sha256:99890e1b7d1dc1174851137240bfee24d2d89ec420c0b5e67fd8af1fa9e43acf
 size 335638221

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f00c9e6c87631b0314d9c05c2e6c0d71dac4d8f668210d71cc941aaa9db0d69
+oid sha256:525293280f0c9a7e7a8e31bdf604ae44c8ce7e05dd2df0c272aecc21e687c526
 size 671246597

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f00f0e2936c92ab5d78c64078e35cfdbd86fe6aa63462c19e3470a1b5a840f3
+oid sha256:189d8d49096dee46b93ff504831fbfbe872d5c824dbf02779b4528dce980eca7
 size 14575

trainer_state.json

@@ -1,616 +1,616 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.1067961165048543,
+  "epoch": 0.03071636318259918,
   "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.03,
+      "epoch": 0.0,
       "learning_rate": 2e-05,
-      "loss": 2.0808,
+      "loss": 1.084,
       "step": 2
     },
     {
-      "epoch": 0.06,
+      "epoch": 0.0,
       "learning_rate": 2e-05,
-      "loss": 2.2803,
+      "loss": 1.1252,
       "step": 4
     },
     {
-      "epoch": 0.09,
+      "epoch": 0.0,
       "learning_rate": 2e-05,
-      "loss": 2.2346,
+      "loss": 1.2937,
       "step": 6
     },
     {
-      "epoch": 0.12,
+      "epoch": 0.0,
       "learning_rate": 2e-05,
-      "loss": 2.3889,
+      "loss": 1.2343,
       "step": 8
     },
     {
-      "epoch": 0.16,
+      "epoch": 0.0,
       "learning_rate": 2e-05,
-      "loss": 2.3853,
+      "loss": 1.2752,
       "step": 10
     },
     {
-      "epoch": 0.19,
+      "epoch": 0.0,
       "learning_rate": 2e-05,
-      "loss": 2.4811,
+      "loss": 1.2433,
       "step": 12
     },
     {
-      "epoch": 0.22,
+      "epoch": 0.0,
       "learning_rate": 2e-05,
-      "loss": 2.4258,
+      "loss": 1.3077,
       "step": 14
     },
     {
-      "epoch": 0.25,
+      "epoch": 0.0,
       "learning_rate": 2e-05,
-      "loss": 2.604,
+      "loss": 1.2717,
       "step": 16
     },
     {
-      "epoch": 0.28,
+      "epoch": 0.0,
       "learning_rate": 2e-05,
-      "loss": 2.0606,
+      "loss": 1.3482,
       "step": 18
     },
     {
-      "epoch": 0.31,
+      "epoch": 0.0,
       "learning_rate": 2e-05,
-      "loss": 2.0915,
+      "loss": 1.3193,
       "step": 20
     },
     {
-      "epoch": 0.34,
+      "epoch": 0.0,
       "learning_rate": 2e-05,
-      "loss": 2.1706,
+      "loss": 1.3002,
       "step": 22
     },
     {
-      "epoch": 0.37,
+      "epoch": 0.0,
       "learning_rate": 2e-05,
-      "loss": 2.3519,
+      "loss": 1.3096,
       "step": 24
     },
     {
-      "epoch": 0.4,
+      "epoch": 0.0,
       "learning_rate": 2e-05,
-      "loss": 2.3622,
+      "loss": 1.2693,
       "step": 26
     },
     {
-      "epoch": 0.43,
+      "epoch": 0.0,
       "learning_rate": 2e-05,
-      "loss": 2.4284,
+      "loss": 1.3124,
       "step": 28
     },
     {
-      "epoch": 0.47,
+      "epoch": 0.0,
       "learning_rate": 2e-05,
-      "loss": 2.3514,
+      "loss": 1.2432,
       "step": 30
     },
     {
-      "epoch": 0.5,
+      "epoch": 0.0,
       "learning_rate": 2e-05,
-      "loss": 2.4474,
+      "loss": 1.2651,
       "step": 32
     },
     {
-      "epoch": 0.53,
+      "epoch": 0.01,
       "learning_rate": 2e-05,
-      "loss": 2.0205,
+      "loss": 1.3088,
       "step": 34
     },
     {
-      "epoch": 0.56,
+      "epoch": 0.01,
       "learning_rate": 2e-05,
-      "loss": 2.2274,
+      "loss": 1.2831,
       "step": 36
     },
     {
-      "epoch": 0.59,
+      "epoch": 0.01,
       "learning_rate": 2e-05,
-      "loss": 2.2873,
+      "loss": 1.3152,
       "step": 38
     },
     {
-      "epoch": 0.62,
+      "epoch": 0.01,
       "learning_rate": 2e-05,
-      "loss": 2.2911,
+      "loss": 1.2468,
       "step": 40
     },
     {
-      "epoch": 0.65,
+      "epoch": 0.01,
       "learning_rate": 2e-05,
-      "loss": 2.3293,
+      "loss": 1.2408,
       "step": 42
     },
     {
-      "epoch": 0.68,
+      "epoch": 0.01,
       "learning_rate": 2e-05,
-      "loss": 2.2486,
+      "loss": 1.3324,
       "step": 44
     },
     {
-      "epoch": 0.71,
+      "epoch": 0.01,
       "learning_rate": 2e-05,
-      "loss": 2.2288,
+      "loss": 1.2572,
       "step": 46
     },
     {
-      "epoch": 0.75,
+      "epoch": 0.01,
       "learning_rate": 2e-05,
-      "loss": 2.0851,
+      "loss": 1.1837,
       "step": 48
     },
     {
-      "epoch": 0.78,
+      "epoch": 0.01,
       "learning_rate": 2e-05,
-      "loss": 2.0276,
+      "loss": 0.9402,
       "step": 50
     },
     {
-      "epoch": 0.81,
+      "epoch": 0.01,
       "learning_rate": 2e-05,
-      "loss": 2.1148,
+      "loss": 1.116,
       "step": 52
     },
     {
-      "epoch": 0.84,
+      "epoch": 0.01,
       "learning_rate": 2e-05,
-      "loss": 2.2354,
+      "loss": 1.0173,
       "step": 54
     },
     {
-      "epoch": 0.87,
+      "epoch": 0.01,
       "learning_rate": 2e-05,
-      "loss": 2.202,
+      "loss": 1.11,
       "step": 56
     },
     {
-      "epoch": 0.9,
+      "epoch": 0.01,
       "learning_rate": 2e-05,
-      "loss": 2.2542,
+      "loss": 1.0466,
       "step": 58
     },
     {
-      "epoch": 0.93,
+      "epoch": 0.01,
       "learning_rate": 2e-05,
-      "loss": 2.1504,
+      "loss": 1.0767,
       "step": 60
     },
     {
-      "epoch": 0.96,
+      "epoch": 0.01,
       "learning_rate": 2e-05,
-      "loss": 2.164,
+      "loss": 1.1989,
       "step": 62
     },
     {
-      "epoch": 0.99,
+      "epoch": 0.01,
       "learning_rate": 2e-05,
-      "loss": 1.8191,
+      "loss": 1.0991,
       "step": 64
     },
     {
-      "epoch": 1.03,
+      "epoch": 0.01,
       "learning_rate": 2e-05,
-      "loss": 2.0248,
+      "loss": 1.16,
       "step": 66
     },
     {
-      "epoch": 1.06,
+      "epoch": 0.01,
       "learning_rate": 2e-05,
-      "loss": 2.0377,
+      "loss": 1.1241,
       "step": 68
     },
     {
-      "epoch": 1.09,
+      "epoch": 0.01,
       "learning_rate": 2e-05,
-      "loss": 2.0993,
+      "loss": 1.1576,
       "step": 70
     },
     {
-      "epoch": 1.12,
+      "epoch": 0.01,
       "learning_rate": 2e-05,
-      "loss": 2.1726,
+      "loss": 1.0886,
       "step": 72
     },
     {
-      "epoch": 1.15,
+      "epoch": 0.01,
       "learning_rate": 2e-05,
-      "loss": 2.2722,
+      "loss": 1.0697,
       "step": 74
     },
     {
-      "epoch": 1.18,
+      "epoch": 0.01,
       "learning_rate": 2e-05,
-      "loss": 2.0678,
+      "loss": 1.0236,
       "step": 76
     },
     {
-      "epoch": 1.21,
+      "epoch": 0.01,
       "learning_rate": 2e-05,
-      "loss": 2.1441,
+      "loss": 1.0654,
       "step": 78
     },
     {
-      "epoch": 1.24,
+      "epoch": 0.01,
       "learning_rate": 2e-05,
-      "loss": 1.7498,
+      "loss": 1.0331,
       "step": 80
     },
     {
-      "epoch": 1.27,
+      "epoch": 0.01,
       "learning_rate": 2e-05,
-      "loss": 1.795,
+      "loss": 1.0305,
       "step": 82
     },
     {
-      "epoch": 1.3,
+      "epoch": 0.01,
       "learning_rate": 2e-05,
-      "loss": 1.9947,
+      "loss": 1.037,
       "step": 84
     },
     {
-      "epoch": 1.34,
+      "epoch": 0.01,
       "learning_rate": 2e-05,
-      "loss": 2.1502,
+      "loss": 1.0694,
       "step": 86
     },
     {
-      "epoch": 1.37,
+      "epoch": 0.01,
       "learning_rate": 2e-05,
-      "loss": 2.1128,
+      "loss": 1.0142,
       "step": 88
     },
     {
-      "epoch": 1.4,
+      "epoch": 0.01,
       "learning_rate": 2e-05,
-      "loss": 2.1395,
+      "loss": 1.0003,
       "step": 90
     },
     {
-      "epoch": 1.43,
+      "epoch": 0.01,
       "learning_rate": 2e-05,
-      "loss": 2.1278,
+      "loss": 0.9496,
       "step": 92
     },
     {
-      "epoch": 1.46,
+      "epoch": 0.01,
       "learning_rate": 2e-05,
-      "loss": 2.0642,
+      "loss": 0.9599,
       "step": 94
     },
     {
-      "epoch": 1.49,
+      "epoch": 0.01,
       "learning_rate": 2e-05,
-      "loss": 1.9564,
+      "loss": 0.868,
       "step": 96
     },
     {
-      "epoch": 1.52,
+      "epoch": 0.02,
       "learning_rate": 2e-05,
-      "loss": 1.9769,
+      "loss": 0.7543,
       "step": 98
     },
     {
-      "epoch": 1.55,
+      "epoch": 0.02,
       "learning_rate": 2e-05,
-      "loss": 1.944,
+      "loss": 0.6971,
       "step": 100
     },
     {
-      "epoch": 1.58,
+      "epoch": 0.02,
       "learning_rate": 2e-05,
-      "loss": 2.1057,
+      "loss": 0.9862,
       "step": 102
     },
     {
-      "epoch": 1.62,
+      "epoch": 0.02,
       "learning_rate": 2e-05,
-      "loss": 2.1769,
+      "loss": 0.9372,
       "step": 104
     },
     {
-      "epoch": 1.65,
+      "epoch": 0.02,
       "learning_rate": 2e-05,
-      "loss": 2.2026,
+      "loss": 1.0577,
       "step": 106
     },
     {
-      "epoch": 1.68,
+      "epoch": 0.02,
       "learning_rate": 2e-05,
-      "loss": 2.2704,
+      "loss": 1.0922,
       "step": 108
     },
     {
-      "epoch": 1.71,
+      "epoch": 0.02,
       "learning_rate": 2e-05,
-      "loss": 2.1163,
+      "loss": 1.0425,
       "step": 110
     },
     {
-      "epoch": 1.74,
+      "epoch": 0.02,
       "learning_rate": 2e-05,
-      "loss": 1.8605,
+      "loss": 0.9818,
       "step": 112
     },
     {
-      "epoch": 1.77,
+      "epoch": 0.02,
       "learning_rate": 2e-05,
-      "loss": 1.9346,
+      "loss": 1.0309,
       "step": 114
     },
     {
-      "epoch": 1.8,
+      "epoch": 0.02,
       "learning_rate": 2e-05,
-      "loss": 2.1167,
+      "loss": 1.03,
       "step": 116
     },
     {
-      "epoch": 1.83,
+      "epoch": 0.02,
       "learning_rate": 2e-05,
-      "loss": 2.1707,
+      "loss": 0.9641,
       "step": 118
     },
     {
-      "epoch": 1.86,
+      "epoch": 0.02,
       "learning_rate": 2e-05,
-      "loss": 2.2284,
+      "loss": 1.008,
       "step": 120
     },
     {
-      "epoch": 1.9,
+      "epoch": 0.02,
       "learning_rate": 2e-05,
-      "loss": 2.1376,
+      "loss": 0.9725,
       "step": 122
     },
     {
-      "epoch": 1.93,
+      "epoch": 0.02,
       "learning_rate": 2e-05,
-      "loss": 2.0558,
+      "loss": 0.8816,
       "step": 124
     },
     {
-      "epoch": 1.96,
+      "epoch": 0.02,
       "learning_rate": 2e-05,
-      "loss": 2.1332,
+      "loss": 0.9917,
       "step": 126
     },
     {
-      "epoch": 1.99,
+      "epoch": 0.02,
       "learning_rate": 2e-05,
-      "loss": 1.9035,
+      "loss": 0.9134,
       "step": 128
     },
     {
-      "epoch": 2.02,
+      "epoch": 0.02,
       "learning_rate": 2e-05,
-      "loss": 1.8632,
+      "loss": 0.9148,
       "step": 130
     },
     {
-      "epoch": 2.05,
+      "epoch": 0.02,
       "learning_rate": 2e-05,
-      "loss": 2.0288,
+      "loss": 0.9404,
       "step": 132
     },
     {
-      "epoch": 2.08,
+      "epoch": 0.02,
       "learning_rate": 2e-05,
-      "loss": 2.1937,
+      "loss": 0.8703,
       "step": 134
     },
     {
-      "epoch": 2.11,
+      "epoch": 0.02,
       "learning_rate": 2e-05,
-      "loss": 2.1676,
+      "loss": 0.8983,
       "step": 136
     },
     {
-      "epoch": 2.14,
+      "epoch": 0.02,
       "learning_rate": 2e-05,
-      "loss": 2.1686,
+      "loss": 0.8411,
       "step": 138
     },
     {
-      "epoch": 2.17,
+      "epoch": 0.02,
       "learning_rate": 2e-05,
-      "loss": 2.2143,
+      "loss": 0.9116,
       "step": 140
     },
     {
-      "epoch": 2.21,
+      "epoch": 0.02,
       "learning_rate": 2e-05,
-      "loss": 2.1759,
+      "loss": 0.8977,
       "step": 142
     },
     {
-      "epoch": 2.24,
+      "epoch": 0.02,
       "learning_rate": 2e-05,
-      "loss": 2.0273,
+      "loss": 0.779,
       "step": 144
     },
     {
-      "epoch": 2.27,
+      "epoch": 0.02,
       "learning_rate": 2e-05,
-      "loss": 1.7455,
+      "loss": 0.6799,
       "step": 146
     },
     {
-      "epoch": 2.3,
+      "epoch": 0.02,
       "learning_rate": 2e-05,
-      "loss": 1.9342,
+      "loss": 0.6409,
       "step": 148
     },
     {
-      "epoch": 2.33,
+      "epoch": 0.02,
       "learning_rate": 2e-05,
-      "loss": 2.2147,
+      "loss": 0.5788,
       "step": 150
     },
     {
-      "epoch": 2.36,
+      "epoch": 0.02,
       "learning_rate": 2e-05,
-      "loss": 2.1071,
+      "loss": 0.9028,
       "step": 152
     },
     {
-      "epoch": 2.39,
+      "epoch": 0.02,
       "learning_rate": 2e-05,
-      "loss": 2.0393,
+      "loss": 0.9255,
       "step": 154
     },
     {
-      "epoch": 2.42,
+      "epoch": 0.02,
       "learning_rate": 2e-05,
-      "loss": 2.0794,
+      "loss": 1.0516,
       "step": 156
     },
     {
-      "epoch": 2.45,
+      "epoch": 0.02,
       "learning_rate": 2e-05,
-      "loss": 2.1025,
+      "loss": 0.9669,
       "step": 158
     },
     {
-      "epoch": 2.49,
+      "epoch": 0.02,
       "learning_rate": 2e-05,
-      "loss": 1.8357,
+      "loss": 0.9713,
       "step": 160
     },
     {
-      "epoch": 2.52,
+      "epoch": 0.02,
       "learning_rate": 2e-05,
-      "loss": 1.8036,
+      "loss": 0.9672,
       "step": 162
     },
     {
-      "epoch": 2.55,
+      "epoch": 0.03,
       "learning_rate": 2e-05,
-      "loss": 2.047,
+      "loss": 0.9257,
       "step": 164
     },
     {
-      "epoch": 2.58,
+      "epoch": 0.03,
       "learning_rate": 2e-05,
-      "loss": 2.1332,
+      "loss": 0.9292,
       "step": 166
     },
     {
-      "epoch": 2.61,
+      "epoch": 0.03,
       "learning_rate": 2e-05,
-      "loss": 1.957,
+      "loss": 0.9572,
       "step": 168
     },
     {
-      "epoch": 2.64,
+      "epoch": 0.03,
       "learning_rate": 2e-05,
-      "loss": 2.3205,
+      "loss": 0.9309,
       "step": 170
     },
     {
-      "epoch": 2.67,
+      "epoch": 0.03,
       "learning_rate": 2e-05,
-      "loss": 2.1057,
+      "loss": 0.867,
       "step": 172
     },
     {
-      "epoch": 2.7,
+      "epoch": 0.03,
       "learning_rate": 2e-05,
-      "loss": 2.0754,
+      "loss": 0.9095,
       "step": 174
     },
     {
-      "epoch": 2.73,
+      "epoch": 0.03,
       "learning_rate": 2e-05,
-      "loss": 2.0535,
+      "loss": 0.9037,
       "step": 176
     },
     {
-      "epoch": 2.77,
+      "epoch": 0.03,
       "learning_rate": 2e-05,
-      "loss": 1.7939,
+      "loss": 0.8635,
       "step": 178
     },
     {
-      "epoch": 2.8,
+      "epoch": 0.03,
       "learning_rate": 2e-05,
-      "loss": 1.9192,
+      "loss": 0.867,
       "step": 180
     },
     {
-      "epoch": 2.83,
+      "epoch": 0.03,
       "learning_rate": 2e-05,
-      "loss": 2.0407,
+      "loss": 0.8901,
       "step": 182
     },
     {
-      "epoch": 2.86,
+      "epoch": 0.03,
       "learning_rate": 2e-05,
-      "loss": 2.1022,
+      "loss": 0.856,
       "step": 184
     },
     {
-      "epoch": 2.89,
+      "epoch": 0.03,
       "learning_rate": 2e-05,
-      "loss": 2.2867,
+      "loss": 0.9077,
       "step": 186
     },
     {
-      "epoch": 2.92,
+      "epoch": 0.03,
       "learning_rate": 2e-05,
-      "loss": 2.0103,
+      "loss": 0.9208,
       "step": 188
     },
     {
-      "epoch": 2.95,
+      "epoch": 0.03,
       "learning_rate": 2e-05,
-      "loss": 1.873,
+      "loss": 0.8073,
       "step": 190
     },
     {
-      "epoch": 2.98,
+      "epoch": 0.03,
       "learning_rate": 2e-05,
-      "loss": 1.8587,
+      "loss": 0.7951,
       "step": 192
     },
     {
-      "epoch": 3.01,
+      "epoch": 0.03,
       "learning_rate": 2e-05,
-      "loss": 1.847,
+      "loss": 0.7404,
       "step": 194
     },
     {
-      "epoch": 3.04,
+      "epoch": 0.03,
       "learning_rate": 2e-05,
-      "loss": 2.0433,
+      "loss": 0.66,
       "step": 196
     },
     {
-      "epoch": 3.08,
+      "epoch": 0.03,
       "learning_rate": 2e-05,
-      "loss": 2.2823,
+      "loss": 0.6155,
       "step": 198
     },
     {
-      "epoch": 3.11,
+      "epoch": 0.03,
       "learning_rate": 2e-05,
-      "loss": 1.9667,
+      "loss": 0.6461,
       "step": 200
     }
   ],
   "max_steps": 1000,
-  "num_train_epochs": 16,
-  "total_flos": 1.573580218235904e+16,
+  "num_train_epochs": 1,
+  "total_flos": 1.163602858478592e+16,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb02852352c319fcdcce66dee1ea6a482a061a0edf06650010d4fe6f3094fd92
+oid sha256:67f158d96c01bfbe3f71419f77423d0d31181700ff7fbfbc6f03d73832dbc65b
 size 3963