Upload folder using huggingface_hub

checkpoint-125/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe1c3929b91273974f32cd39c1d15a78948f9d8313a49a10f9557ad0ebbe9c96
+size 569086987

checkpoint-125/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:997f51d5cfc41a3cb8be45b551c8a04fe3b4f2e93af07f1bb6d1e5db6bc3d245
+size 284546819

checkpoint-125/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bfe1981024ef92f2da08a90c72c7c793d1cc9de1547abd2556c968be70232eb
+size 16389

checkpoint-125/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a35b845d476d830805793c3dcf8ac2daad87fec289bff3f7eda9e72fc374eda1
+size 16389

checkpoint-125/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03e9880996b01262a807d1ec3ebd91eee540e08130a14a45a4648731fd0d48a9
+size 16389

checkpoint-125/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee25c237d6fe62ec76adcf7daf899d7ed32eab5d1a5b447b911f4451c9a1b258
+size 16389

checkpoint-125/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a6b31133f29a8fc0cb538aa807d6a403bd51939336bfd425cd3d122d8c5595c
+size 16389

checkpoint-125/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a26c55b5c7fa0522b1d27b2c00a7ea77ad010f19a1321991165c5c972b8fa97a
+size 16389

checkpoint-125/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a1a3cf85626196804f25a8293e22dc561bba068a70fb123e04afe4896c33972
+size 16389

checkpoint-125/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28f87c1ee5f5db346c7b913137cbccd196eaf8ec5a4cf9f192418a3069269b49
+size 16389

checkpoint-125/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e98e16a4c39959c94df5622ca50d71f139e63895a4fb83574000eefef3834325
+size 1465

checkpoint-125/special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-125/tokenizer_config.json

@@ -0,0 +1,53 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "[UNK]"
+}

checkpoint-125/trainer_state.json

@@ -0,0 +1,537 @@
+{
+  "best_global_step": 125,
+  "best_metric": 15.553059577941895,
+  "best_model_checkpoint": "/gpfs/scratch/guoh/DNAFM/output/gencode_human_12.8k_12800/Gencode-BPE/checkpoint-125",
+  "epoch": 0.03546099290780142,
+  "eval_steps": 125,
+  "global_step": 125,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0005673758865248227,
+      "grad_norm": 1275.0146484375,
+      "loss": 281.4781,
+      "lr": 2e-06,
+      "step": 2,
+      "tokens_trained": 0.000192256
+    },
+    {
+      "epoch": 0.0011347517730496454,
+      "grad_norm": 1437.579833984375,
+      "loss": 267.2211,
+      "lr": 6e-06,
+      "step": 4,
+      "tokens_trained": 0.000382024
+    },
+    {
+      "epoch": 0.001702127659574468,
+      "grad_norm": 1719.271484375,
+      "loss": 219.3822,
+      "lr": 1e-05,
+      "step": 6,
+      "tokens_trained": 0.00057072
+    },
+    {
+      "epoch": 0.0022695035460992908,
+      "grad_norm": 1444.94970703125,
+      "loss": 133.8172,
+      "lr": 1.4e-05,
+      "step": 8,
+      "tokens_trained": 0.000761336
+    },
+    {
+      "epoch": 0.0028368794326241137,
+      "grad_norm": 238.9689178466797,
+      "loss": 90.8177,
+      "lr": 1.8e-05,
+      "step": 10,
+      "tokens_trained": 0.000953248
+    },
+    {
+      "epoch": 0.003404255319148936,
+      "grad_norm": 158.53497314453125,
+      "loss": 84.6922,
+      "lr": 2.2e-05,
+      "step": 12,
+      "tokens_trained": 0.00114424
+    },
+    {
+      "epoch": 0.003971631205673759,
+      "grad_norm": 146.10595703125,
+      "loss": 76.7055,
+      "lr": 2.6e-05,
+      "step": 14,
+      "tokens_trained": 0.001334104
+    },
+    {
+      "epoch": 0.0045390070921985815,
+      "grad_norm": 140.69964599609375,
+      "loss": 67.9952,
+      "lr": 3e-05,
+      "step": 16,
+      "tokens_trained": 0.00152392
+    },
+    {
+      "epoch": 0.005106382978723404,
+      "grad_norm": 108.80303192138672,
+      "loss": 57.8088,
+      "lr": 3.4000000000000007e-05,
+      "step": 18,
+      "tokens_trained": 0.001713872
+    },
+    {
+      "epoch": 0.005673758865248227,
+      "grad_norm": 106.82334899902344,
+      "loss": 48.6585,
+      "lr": 3.8e-05,
+      "step": 20,
+      "tokens_trained": 0.001903976
+    },
+    {
+      "epoch": 0.00624113475177305,
+      "grad_norm": 93.58769989013672,
+      "loss": 41.7984,
+      "lr": 4.2000000000000004e-05,
+      "step": 22,
+      "tokens_trained": 0.002094288
+    },
+    {
+      "epoch": 0.006808510638297872,
+      "grad_norm": 87.5854721069336,
+      "loss": 37.6201,
+      "lr": 4.6e-05,
+      "step": 24,
+      "tokens_trained": 0.002282496
+    },
+    {
+      "epoch": 0.007375886524822695,
+      "grad_norm": 84.12794494628906,
+      "loss": 35.0091,
+      "lr": 5e-05,
+      "step": 26,
+      "tokens_trained": 0.00247068
+    },
+    {
+      "epoch": 0.007943262411347518,
+      "grad_norm": 79.77535247802734,
+      "loss": 33.2253,
+      "lr": 5.4e-05,
+      "step": 28,
+      "tokens_trained": 0.002662888
+    },
+    {
+      "epoch": 0.00851063829787234,
+      "grad_norm": 66.42157745361328,
+      "loss": 32.0682,
+      "lr": 5.800000000000001e-05,
+      "step": 30,
+      "tokens_trained": 0.002851968
+    },
+    {
+      "epoch": 0.009078014184397163,
+      "grad_norm": 87.52485656738281,
+      "loss": 30.893,
+      "lr": 6.2e-05,
+      "step": 32,
+      "tokens_trained": 0.003041384
+    },
+    {
+      "epoch": 0.009645390070921986,
+      "grad_norm": 58.33614730834961,
+      "loss": 30.0513,
+      "lr": 6.6e-05,
+      "step": 34,
+      "tokens_trained": 0.003232872
+    },
+    {
+      "epoch": 0.010212765957446808,
+      "grad_norm": 54.629329681396484,
+      "loss": 29.0115,
+      "lr": 7.000000000000001e-05,
+      "step": 36,
+      "tokens_trained": 0.003423824
+    },
+    {
+      "epoch": 0.01078014184397163,
+      "grad_norm": 52.79097366333008,
+      "loss": 28.2084,
+      "lr": 7.4e-05,
+      "step": 38,
+      "tokens_trained": 0.003613232
+    },
+    {
+      "epoch": 0.011347517730496455,
+      "grad_norm": 54.481224060058594,
+      "loss": 27.4345,
+      "lr": 7.8e-05,
+      "step": 40,
+      "tokens_trained": 0.003800952
+    },
+    {
+      "epoch": 0.011914893617021277,
+      "grad_norm": 58.7069091796875,
+      "loss": 26.5936,
+      "lr": 8.2e-05,
+      "step": 42,
+      "tokens_trained": 0.003991512
+    },
+    {
+      "epoch": 0.0124822695035461,
+      "grad_norm": 49.30760955810547,
+      "loss": 26.0608,
+      "lr": 8.599999999999999e-05,
+      "step": 44,
+      "tokens_trained": 0.004180648
+    },
+    {
+      "epoch": 0.013049645390070922,
+      "grad_norm": 61.902587890625,
+      "loss": 25.5363,
+      "lr": 8.999999999999999e-05,
+      "step": 46,
+      "tokens_trained": 0.00437148
+    },
+    {
+      "epoch": 0.013617021276595745,
+      "grad_norm": 46.76111602783203,
+      "loss": 24.9599,
+      "lr": 9.400000000000001e-05,
+      "step": 48,
+      "tokens_trained": 0.004559344
+    },
+    {
+      "epoch": 0.014184397163120567,
+      "grad_norm": 57.06416702270508,
+      "loss": 24.4087,
+      "lr": 9.800000000000001e-05,
+      "step": 50,
+      "tokens_trained": 0.004749256
+    },
+    {
+      "epoch": 0.01475177304964539,
+      "grad_norm": 44.798736572265625,
+      "loss": 24.1444,
+      "lr": 0.000102,
+      "step": 52,
+      "tokens_trained": 0.004940192
+    },
+    {
+      "epoch": 0.015319148936170212,
+      "grad_norm": 40.29296875,
+      "loss": 23.6011,
+      "lr": 0.000106,
+      "step": 54,
+      "tokens_trained": 0.005130304
+    },
+    {
+      "epoch": 0.015886524822695036,
+      "grad_norm": 38.75099563598633,
+      "loss": 23.1781,
+      "lr": 0.00011,
+      "step": 56,
+      "tokens_trained": 0.005322864
+    },
+    {
+      "epoch": 0.016453900709219857,
+      "grad_norm": 37.470706939697266,
+      "loss": 22.9136,
+      "lr": 0.000114,
+      "step": 58,
+      "tokens_trained": 0.00551392
+    },
+    {
+      "epoch": 0.01702127659574468,
+      "grad_norm": 35.1894645690918,
+      "loss": 22.6336,
+      "lr": 0.000118,
+      "step": 60,
+      "tokens_trained": 0.005703096
+    },
+    {
+      "epoch": 0.017588652482269502,
+      "grad_norm": 35.136573791503906,
+      "loss": 22.2998,
+      "lr": 0.000122,
+      "step": 62,
+      "tokens_trained": 0.005892448
+    },
+    {
+      "epoch": 0.018156028368794326,
+      "grad_norm": 38.05111312866211,
+      "loss": 21.9401,
+      "lr": 0.000126,
+      "step": 64,
+      "tokens_trained": 0.006081656
+    },
+    {
+      "epoch": 0.01872340425531915,
+      "grad_norm": 35.63850021362305,
+      "loss": 21.7206,
+      "lr": 0.00013000000000000002,
+      "step": 66,
+      "tokens_trained": 0.006273032
+    },
+    {
+      "epoch": 0.01929078014184397,
+      "grad_norm": 34.327667236328125,
+      "loss": 21.4051,
+      "lr": 0.000134,
+      "step": 68,
+      "tokens_trained": 0.00646304
+    },
+    {
+      "epoch": 0.019858156028368795,
+      "grad_norm": 31.457059860229492,
+      "loss": 21.0774,
+      "lr": 0.00013800000000000002,
+      "step": 70,
+      "tokens_trained": 0.006652832
+    },
+    {
+      "epoch": 0.020425531914893616,
+      "grad_norm": 34.91672897338867,
+      "loss": 20.8718,
+      "lr": 0.00014199999999999998,
+      "step": 72,
+      "tokens_trained": 0.006843512
+    },
+    {
+      "epoch": 0.02099290780141844,
+      "grad_norm": 27.959579467773438,
+      "loss": 20.6932,
+      "lr": 0.000146,
+      "step": 74,
+      "tokens_trained": 0.007033584
+    },
+    {
+      "epoch": 0.02156028368794326,
+      "grad_norm": 26.569866180419922,
+      "loss": 20.4072,
+      "lr": 0.00015,
+      "step": 76,
+      "tokens_trained": 0.007224032
+    },
+    {
+      "epoch": 0.022127659574468085,
+      "grad_norm": 28.009904861450195,
+      "loss": 20.2229,
+      "lr": 0.000154,
+      "step": 78,
+      "tokens_trained": 0.00741368
+    },
+    {
+      "epoch": 0.02269503546099291,
+      "grad_norm": 28.892959594726562,
+      "loss": 20.0528,
+      "lr": 0.000158,
+      "step": 80,
+      "tokens_trained": 0.00760416
+    },
+    {
+      "epoch": 0.02326241134751773,
+      "grad_norm": 31.58131980895996,
+      "loss": 19.8016,
+      "lr": 0.000162,
+      "step": 82,
+      "tokens_trained": 0.007793952
+    },
+    {
+      "epoch": 0.023829787234042554,
+      "grad_norm": 31.01254653930664,
+      "loss": 19.634,
+      "lr": 0.00016600000000000002,
+      "step": 84,
+      "tokens_trained": 0.007980792
+    },
+    {
+      "epoch": 0.024397163120567375,
+      "grad_norm": 28.732515335083008,
+      "loss": 19.3777,
+      "lr": 0.00017,
+      "step": 86,
+      "tokens_trained": 0.008171968
+    },
+    {
+      "epoch": 0.0249645390070922,
+      "grad_norm": 24.31264877319336,
+      "loss": 19.1346,
+      "lr": 0.000174,
+      "step": 88,
+      "tokens_trained": 0.008361632
+    },
+    {
+      "epoch": 0.02553191489361702,
+      "grad_norm": 26.557010650634766,
+      "loss": 19.0014,
+      "lr": 0.000178,
+      "step": 90,
+      "tokens_trained": 0.008552328
+    },
+    {
+      "epoch": 0.026099290780141844,
+      "grad_norm": 21.156103134155273,
+      "loss": 18.7032,
+      "lr": 0.000182,
+      "step": 92,
+      "tokens_trained": 0.008743136
+    },
+    {
+      "epoch": 0.02666666666666667,
+      "grad_norm": 25.7484188079834,
+      "loss": 18.4836,
+      "lr": 0.000186,
+      "step": 94,
+      "tokens_trained": 0.008932056
+    },
+    {
+      "epoch": 0.02723404255319149,
+      "grad_norm": 22.27949333190918,
+      "loss": 18.2233,
+      "lr": 0.00019,
+      "step": 96,
+      "tokens_trained": 0.009121608
+    },
+    {
+      "epoch": 0.027801418439716313,
+      "grad_norm": 24.9247989654541,
+      "loss": 17.9867,
+      "lr": 0.000194,
+      "step": 98,
+      "tokens_trained": 0.009311008
+    },
+    {
+      "epoch": 0.028368794326241134,
+      "grad_norm": 24.302066802978516,
+      "loss": 17.8016,
+      "lr": 0.00019800000000000002,
+      "step": 100,
+      "tokens_trained": 0.009501456
+    },
+    {
+      "epoch": 0.02893617021276596,
+      "grad_norm": 23.458459854125977,
+      "loss": 17.6295,
+      "lr": 0.000202,
+      "step": 102,
+      "tokens_trained": 0.009693952
+    },
+    {
+      "epoch": 0.02950354609929078,
+      "grad_norm": 24.092350006103516,
+      "loss": 17.4593,
+      "lr": 0.000206,
+      "step": 104,
+      "tokens_trained": 0.009883328
+    },
+    {
+      "epoch": 0.030070921985815603,
+      "grad_norm": 22.54726219177246,
+      "loss": 17.2141,
+      "lr": 0.00021,
+      "step": 106,
+      "tokens_trained": 0.01007316
+    },
+    {
+      "epoch": 0.030638297872340424,
+      "grad_norm": 21.334760665893555,
+      "loss": 17.044,
+      "lr": 0.000214,
+      "step": 108,
+      "tokens_trained": 0.010266504
+    },
+    {
+      "epoch": 0.031205673758865248,
+      "grad_norm": 20.584287643432617,
+      "loss": 16.8919,
+      "lr": 0.000218,
+      "step": 110,
+      "tokens_trained": 0.010455736
+    },
+    {
+      "epoch": 0.03177304964539007,
+      "grad_norm": 23.51676368713379,
+      "loss": 16.751,
+      "lr": 0.000222,
+      "step": 112,
+      "tokens_trained": 0.010645208
+    },
+    {
+      "epoch": 0.03234042553191489,
+      "grad_norm": 23.278276443481445,
+      "loss": 16.5997,
+      "lr": 0.00022600000000000002,
+      "step": 114,
+      "tokens_trained": 0.010838928
+    },
+    {
+      "epoch": 0.032907801418439714,
+      "grad_norm": 25.4830265045166,
+      "loss": 16.3416,
+      "lr": 0.00023,
+      "step": 116,
+      "tokens_trained": 0.011027792
+    },
+    {
+      "epoch": 0.03347517730496454,
+      "grad_norm": 29.442413330078125,
+      "loss": 16.24,
+      "lr": 0.00023400000000000002,
+      "step": 118,
+      "tokens_trained": 0.011217456
+    },
+    {
+      "epoch": 0.03404255319148936,
+      "grad_norm": 21.77578353881836,
+      "loss": 16.1922,
+      "lr": 0.00023799999999999998,
+      "step": 120,
+      "tokens_trained": 0.01140804
+    },
+    {
+      "epoch": 0.03460992907801418,
+      "grad_norm": 27.040719985961914,
+      "loss": 15.9059,
+      "lr": 0.000242,
+      "step": 122,
+      "tokens_trained": 0.011597816
+    },
+    {
+      "epoch": 0.035177304964539004,
+      "grad_norm": 24.74480628967285,
+      "loss": 15.7818,
+      "lr": 0.000246,
+      "step": 124,
+      "tokens_trained": 0.011785624
+    },
+    {
+      "epoch": 0.03546099290780142,
+      "eval_loss": 15.553059577941895,
+      "eval_runtime": 23.5485,
+      "step": 125,
+      "tokens_trained": 0.011880832
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 7650,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 125,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-125/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c9833ede7e0bc4a67116e2be49e665ef793dc257b8d78c77b367cb70647f355
+size 5969