End of training

checkpoint-2000/config.json

@@ -1,50 +0,0 @@
-{
-  "_name_or_path": "microsoft/MiniLM-L12-H384-uncased",
-  "architectures": [
-    "BertForSequenceClassification"
-  ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 384,
-  "id2label": {
-    "0": "Society & Culture",
-    "1": "Science & Mathematics",
-    "2": "Health",
-    "3": "Education & Reference",
-    "4": "Computers & Internet",
-    "5": "Sports",
-    "6": "Business & Finance",
-    "7": "Entertainment & Music",
-    "8": "Family & Relationships",
-    "9": "Politics & Government"
-  },
-  "initializer_range": 0.02,
-  "intermediate_size": 1536,
-  "label2id": {
-    "Business & Finance": 6,
-    "Computers & Internet": 4,
-    "Education & Reference": 3,
-    "Entertainment & Music": 7,
-    "Family & Relationships": 8,
-    "Health": 2,
-    "Politics & Government": 9,
-    "Science & Mathematics": 1,
-    "Society & Culture": 0,
-    "Sports": 5
-  },
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
-  "pad_token_id": 0,
-  "position_embedding_type": "absolute",
-  "problem_type": "single_label_classification",
-  "torch_dtype": "float32",
-  "transformers_version": "4.31.0",
-  "type_vocab_size": 2,
-  "use_cache": true,
-  "vocab_size": 30522
-}

checkpoint-2000/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:09552910dd7d5ed2eb865c6b30253726e3dcd7aed3588cc97c4702b013630f01
-size 267028677

checkpoint-2000/pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:294d34cfcdd9a17427a0a09cdf19e071c82e8ce59c34f4fe159d3c5118d1082d
-size 133523761

checkpoint-2000/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4f48f6150f5133b116ca71b75680965f3b45ab43582cfcc6566086e18896784f
-size 14575

checkpoint-2000/special_tokens_map.json

@@ -1,7 +0,0 @@
-{
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
-}

checkpoint-2000/tokenizer_config.json

@@ -1,15 +0,0 @@
-{
-  "clean_up_tokenization_spaces": true,
-  "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
-  "do_lower_case": true,
-  "mask_token": "[MASK]",
-  "model_max_length": 1000000000000000019884624838656,
-  "never_split": null,
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
-  "unk_token": "[UNK]"
-}

checkpoint-2000/trainer_state.json

@@ -1,438 +0,0 @@
-{
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 8.0,
-  "global_step": 2000,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.0,
-      "learning_rate": 1.9992e-05,
-      "loss": 2.3035,
-      "step": 1
-    },
-    {
-      "epoch": 0.5,
-      "learning_rate": 1.9e-05,
-      "loss": 2.1461,
-      "step": 125
-    },
-    {
-      "epoch": 0.5,
-      "eval_accuracy": 0.5465,
-      "eval_disk_space_total": 78.1898422241211,
-      "eval_disk_space_used": 24.584102630615234,
-      "eval_f1": 0.4711252488920671,
-      "eval_gpu_ram_allocated": 0.3996291160583496,
-      "eval_gpu_ram_cached": 12.9296875,
-      "eval_gpu_ram_total": 39.56402587890625,
-      "eval_gpu_utilization": 28,
-      "eval_loss": 1.8486889600753784,
-      "eval_precision": 0.5180898369172832,
-      "eval_recall": 0.5465,
-      "eval_runtime": 1.5234,
-      "eval_samples_per_second": 1312.845,
-      "eval_steps_per_second": 41.355,
-      "eval_system_ram_total": 83.48074722290039,
-      "eval_system_ram_used": 3.8797760009765625,
-      "step": 125
-    },
-    {
-      "epoch": 1.0,
-      "learning_rate": 1.8e-05,
-      "loss": 1.6793,
-      "step": 250
-    },
-    {
-      "epoch": 1.0,
-      "eval_accuracy": 0.615,
-      "eval_disk_space_total": 78.1898422241211,
-      "eval_disk_space_used": 24.584190368652344,
-      "eval_f1": 0.5799151958404197,
-      "eval_gpu_ram_allocated": 0.3996119499206543,
-      "eval_gpu_ram_cached": 12.9296875,
-      "eval_gpu_ram_total": 39.56402587890625,
-      "eval_gpu_utilization": 28,
-      "eval_loss": 1.5279773473739624,
-      "eval_precision": 0.6206909881233017,
-      "eval_recall": 0.615,
-      "eval_runtime": 1.5357,
-      "eval_samples_per_second": 1302.337,
-      "eval_steps_per_second": 41.024,
-      "eval_system_ram_total": 83.48074722290039,
-      "eval_system_ram_used": 3.8827476501464844,
-      "step": 250
-    },
-    {
-      "epoch": 1.5,
-      "learning_rate": 1.7e-05,
-      "loss": 1.4163,
-      "step": 375
-    },
-    {
-      "epoch": 1.5,
-      "eval_accuracy": 0.6675,
-      "eval_disk_space_total": 78.1898422241211,
-      "eval_disk_space_used": 24.584190368652344,
-      "eval_f1": 0.6507803054121275,
-      "eval_gpu_ram_allocated": 0.3996291160583496,
-      "eval_gpu_ram_cached": 12.9296875,
-      "eval_gpu_ram_total": 39.56402587890625,
-      "eval_gpu_utilization": 28,
-      "eval_loss": 1.3395830392837524,
-      "eval_precision": 0.6690538200035159,
-      "eval_recall": 0.6675,
-      "eval_runtime": 1.5175,
-      "eval_samples_per_second": 1317.927,
-      "eval_steps_per_second": 41.515,
-      "eval_system_ram_total": 83.48074722290039,
-      "eval_system_ram_used": 3.883075714111328,
-      "step": 375
-    },
-    {
-      "epoch": 2.0,
-      "learning_rate": 1.6000000000000003e-05,
-      "loss": 1.2855,
-      "step": 500
-    },
-    {
-      "epoch": 2.0,
-      "eval_accuracy": 0.6745,
-      "eval_disk_space_total": 78.1898422241211,
-      "eval_disk_space_used": 24.584270477294922,
-      "eval_f1": 0.6633189544214071,
-      "eval_gpu_ram_allocated": 0.3995933532714844,
-      "eval_gpu_ram_cached": 12.9296875,
-      "eval_gpu_ram_total": 39.56402587890625,
-      "eval_gpu_utilization": 30,
-      "eval_loss": 1.2413243055343628,
-      "eval_precision": 0.6741774761001332,
-      "eval_recall": 0.6745,
-      "eval_runtime": 1.5166,
-      "eval_samples_per_second": 1318.761,
-      "eval_steps_per_second": 41.541,
-      "eval_system_ram_total": 83.48074722290039,
-      "eval_system_ram_used": 3.897541046142578,
-      "step": 500
-    },
-    {
-      "epoch": 2.5,
-      "learning_rate": 1.5000000000000002e-05,
-      "loss": 1.1364,
-      "step": 625
-    },
-    {
-      "epoch": 2.5,
-      "eval_accuracy": 0.6725,
-      "eval_disk_space_total": 78.1898422241211,
-      "eval_disk_space_used": 25.457107543945312,
-      "eval_f1": 0.665830199533775,
-      "eval_gpu_ram_allocated": 0.3995990753173828,
-      "eval_gpu_ram_cached": 12.9296875,
-      "eval_gpu_ram_total": 39.56402587890625,
-      "eval_gpu_utilization": 31,
-      "eval_loss": 1.1794828176498413,
-      "eval_precision": 0.6758089281502129,
-      "eval_recall": 0.6725,
-      "eval_runtime": 1.5306,
-      "eval_samples_per_second": 1306.704,
-      "eval_steps_per_second": 41.161,
-      "eval_system_ram_total": 83.48074722290039,
-      "eval_system_ram_used": 4.096714019775391,
-      "step": 625
-    },
-    {
-      "epoch": 3.0,
-      "learning_rate": 1.4e-05,
-      "loss": 1.0569,
-      "step": 750
-    },
-    {
-      "epoch": 3.0,
-      "eval_accuracy": 0.6845,
-      "eval_disk_space_total": 78.1898422241211,
-      "eval_disk_space_used": 25.457260131835938,
-      "eval_f1": 0.6785417667541389,
-      "eval_gpu_ram_allocated": 0.3996105194091797,
-      "eval_gpu_ram_cached": 12.9296875,
-      "eval_gpu_ram_total": 39.56402587890625,
-      "eval_gpu_utilization": 29,
-      "eval_loss": 1.1167317628860474,
-      "eval_precision": 0.6841220967269329,
-      "eval_recall": 0.6845,
-      "eval_runtime": 1.5379,
-      "eval_samples_per_second": 1300.49,
-      "eval_steps_per_second": 40.965,
-      "eval_system_ram_total": 83.48074722290039,
-      "eval_system_ram_used": 4.092338562011719,
-      "step": 750
-    },
-    {
-      "epoch": 3.5,
-      "learning_rate": 1.3000000000000001e-05,
-      "loss": 0.9596,
-      "step": 875
-    },
-    {
-      "epoch": 3.5,
-      "eval_accuracy": 0.698,
-      "eval_disk_space_total": 78.1898422241211,
-      "eval_disk_space_used": 25.457298278808594,
-      "eval_f1": 0.6882774085430846,
-      "eval_gpu_ram_allocated": 0.3996591567993164,
-      "eval_gpu_ram_cached": 12.9296875,
-      "eval_gpu_ram_total": 39.56402587890625,
-      "eval_gpu_utilization": 29,
-      "eval_loss": 1.0866354703903198,
-      "eval_precision": 0.692037318372609,
-      "eval_recall": 0.698,
-      "eval_runtime": 1.5638,
-      "eval_samples_per_second": 1278.976,
-      "eval_steps_per_second": 40.288,
-      "eval_system_ram_total": 83.48074722290039,
-      "eval_system_ram_used": 3.876514434814453,
-      "step": 875
-    },
-    {
-      "epoch": 4.0,
-      "learning_rate": 1.2e-05,
-      "loss": 0.917,
-      "step": 1000
-    },
-    {
-      "epoch": 4.0,
-      "eval_accuracy": 0.6875,
-      "eval_disk_space_total": 78.1898422241211,
-      "eval_disk_space_used": 25.45730209350586,
-      "eval_f1": 0.6796355379748251,
-      "eval_gpu_ram_allocated": 0.3995933532714844,
-      "eval_gpu_ram_cached": 12.9296875,
-      "eval_gpu_ram_total": 39.56402587890625,
-      "eval_gpu_utilization": 29,
-      "eval_loss": 1.0703401565551758,
-      "eval_precision": 0.6840559389245768,
-      "eval_recall": 0.6875,
-      "eval_runtime": 1.5204,
-      "eval_samples_per_second": 1315.473,
-      "eval_steps_per_second": 41.437,
-      "eval_system_ram_total": 83.48074722290039,
-      "eval_system_ram_used": 3.8976211547851562,
-      "step": 1000
-    },
-    {
-      "epoch": 4.5,
-      "learning_rate": 1.1008e-05,
-      "loss": 0.8512,
-      "step": 1125
-    },
-    {
-      "epoch": 4.5,
-      "eval_accuracy": 0.6915,
-      "eval_disk_space_total": 78.1898422241211,
-      "eval_disk_space_used": 25.830577850341797,
-      "eval_f1": 0.6913447845710189,
-      "eval_gpu_ram_allocated": 0.3996849060058594,
-      "eval_gpu_ram_cached": 12.9296875,
-      "eval_gpu_ram_total": 39.56402587890625,
-      "eval_gpu_utilization": 28,
-      "eval_loss": 1.0628596544265747,
-      "eval_precision": 0.6944500140220231,
-      "eval_recall": 0.6915,
-      "eval_runtime": 1.5986,
-      "eval_samples_per_second": 1251.121,
-      "eval_steps_per_second": 39.41,
-      "eval_system_ram_total": 83.48074722290039,
-      "eval_system_ram_used": 4.0599517822265625,
-      "step": 1125
-    },
-    {
-      "epoch": 5.0,
-      "learning_rate": 1.0008e-05,
-      "loss": 0.8121,
-      "step": 1250
-    },
-    {
-      "epoch": 5.0,
-      "eval_accuracy": 0.691,
-      "eval_disk_space_total": 78.1898422241211,
-      "eval_disk_space_used": 25.830596923828125,
-      "eval_f1": 0.6838005278906992,
-      "eval_gpu_ram_allocated": 0.39963626861572266,
-      "eval_gpu_ram_cached": 12.9296875,
-      "eval_gpu_ram_total": 39.56402587890625,
-      "eval_gpu_utilization": 31,
-      "eval_loss": 1.0575964450836182,
-      "eval_precision": 0.6905089592227732,
-      "eval_recall": 0.691,
-      "eval_runtime": 1.5391,
-      "eval_samples_per_second": 1299.447,
-      "eval_steps_per_second": 40.933,
-      "eval_system_ram_total": 83.48074722290039,
-      "eval_system_ram_used": 4.043186187744141,
-      "step": 1250
-    },
-    {
-      "epoch": 5.5,
-      "learning_rate": 9.008e-06,
-      "loss": 0.7733,
-      "step": 1375
-    },
-    {
-      "epoch": 5.5,
-      "eval_accuracy": 0.6805,
-      "eval_disk_space_total": 78.1898422241211,
-      "eval_disk_space_used": 25.83068084716797,
-      "eval_f1": 0.6773653982197514,
-      "eval_gpu_ram_allocated": 0.3996090888977051,
-      "eval_gpu_ram_cached": 12.9296875,
-      "eval_gpu_ram_total": 39.56402587890625,
-      "eval_gpu_utilization": 28,
-      "eval_loss": 1.0597690343856812,
-      "eval_precision": 0.683800229871734,
-      "eval_recall": 0.6805,
-      "eval_runtime": 1.5511,
-      "eval_samples_per_second": 1289.373,
-      "eval_steps_per_second": 40.615,
-      "eval_system_ram_total": 83.48074722290039,
-      "eval_system_ram_used": 3.837909698486328,
-      "step": 1375
-    },
-    {
-      "epoch": 6.0,
-      "learning_rate": 8.008e-06,
-      "loss": 0.7431,
-      "step": 1500
-    },
-    {
-      "epoch": 6.0,
-      "eval_accuracy": 0.702,
-      "eval_disk_space_total": 78.1898422241211,
-      "eval_disk_space_used": 25.830699920654297,
-      "eval_f1": 0.6973584149072398,
-      "eval_gpu_ram_allocated": 0.39962053298950195,
-      "eval_gpu_ram_cached": 12.9296875,
-      "eval_gpu_ram_total": 39.56402587890625,
-      "eval_gpu_utilization": 31,
-      "eval_loss": 1.0375711917877197,
-      "eval_precision": 0.6975777506719404,
-      "eval_recall": 0.702,
-      "eval_runtime": 1.5383,
-      "eval_samples_per_second": 1300.155,
-      "eval_steps_per_second": 40.955,
-      "eval_system_ram_total": 83.48074722290039,
-      "eval_system_ram_used": 3.8545989990234375,
-      "step": 1500
-    },
-    {
-      "epoch": 6.5,
-      "learning_rate": 7.0080000000000005e-06,
-      "loss": 0.7065,
-      "step": 1625
-    },
-    {
-      "epoch": 6.5,
-      "eval_accuracy": 0.6995,
-      "eval_disk_space_total": 78.1898422241211,
-      "eval_disk_space_used": 26.203968048095703,
-      "eval_f1": 0.6990180197515704,
-      "eval_gpu_ram_allocated": 0.39959049224853516,
-      "eval_gpu_ram_cached": 12.9296875,
-      "eval_gpu_ram_total": 39.56402587890625,
-      "eval_gpu_utilization": 28,
-      "eval_loss": 1.0457407236099243,
-      "eval_precision": 0.701399008937391,
-      "eval_recall": 0.6995,
-      "eval_runtime": 1.5796,
-      "eval_samples_per_second": 1266.127,
-      "eval_steps_per_second": 39.883,
-      "eval_system_ram_total": 83.48074722290039,
-      "eval_system_ram_used": 4.033943176269531,
-      "step": 1625
-    },
-    {
-      "epoch": 7.0,
-      "learning_rate": 6.008000000000001e-06,
-      "loss": 0.671,
-      "step": 1750
-    },
-    {
-      "epoch": 7.0,
-      "eval_accuracy": 0.698,
-      "eval_disk_space_total": 78.1898422241211,
-      "eval_disk_space_used": 26.203968048095703,
-      "eval_f1": 0.6956310421863513,
-      "eval_gpu_ram_allocated": 0.39962339401245117,
-      "eval_gpu_ram_cached": 12.9296875,
-      "eval_gpu_ram_total": 39.56402587890625,
-      "eval_gpu_utilization": 28,
-      "eval_loss": 1.039590835571289,
-      "eval_precision": 0.696566876815876,
-      "eval_recall": 0.698,
-      "eval_runtime": 1.5301,
-      "eval_samples_per_second": 1307.136,
-      "eval_steps_per_second": 41.175,
-      "eval_system_ram_total": 83.48074722290039,
-      "eval_system_ram_used": 4.038356781005859,
-      "step": 1750
-    },
-    {
-      "epoch": 7.5,
-      "learning_rate": 5.008000000000001e-06,
-      "loss": 0.6438,
-      "step": 1875
-    },
-    {
-      "epoch": 7.5,
-      "eval_accuracy": 0.6925,
-      "eval_disk_space_total": 78.1898422241211,
-      "eval_disk_space_used": 26.203964233398438,
-      "eval_f1": 0.6886960392924729,
-      "eval_gpu_ram_allocated": 0.3995976448059082,
-      "eval_gpu_ram_cached": 12.9296875,
-      "eval_gpu_ram_total": 39.56402587890625,
-      "eval_gpu_utilization": 28,
-      "eval_loss": 1.0473765134811401,
-      "eval_precision": 0.6906747949914751,
-      "eval_recall": 0.6925,
-      "eval_runtime": 1.5569,
-      "eval_samples_per_second": 1284.611,
-      "eval_steps_per_second": 40.465,
-      "eval_system_ram_total": 83.48074722290039,
-      "eval_system_ram_used": 3.827362060546875,
-      "step": 1875
-    },
-    {
-      "epoch": 8.0,
-      "learning_rate": 4.008e-06,
-      "loss": 0.6326,
-      "step": 2000
-    },
-    {
-      "epoch": 8.0,
-      "eval_accuracy": 0.698,
-      "eval_disk_space_total": 78.1898422241211,
-      "eval_disk_space_used": 26.204063415527344,
-      "eval_f1": 0.6972467602684949,
-      "eval_gpu_ram_allocated": 0.39958906173706055,
-      "eval_gpu_ram_cached": 12.9296875,
-      "eval_gpu_ram_total": 39.56402587890625,
-      "eval_gpu_utilization": 34,
-      "eval_loss": 1.03837251663208,
-      "eval_precision": 0.6982790583069545,
-      "eval_recall": 0.698,
-      "eval_runtime": 1.5106,
-      "eval_samples_per_second": 1323.952,
-      "eval_steps_per_second": 41.704,
-      "eval_system_ram_total": 83.48074722290039,
-      "eval_system_ram_used": 3.8401947021484375,
-      "step": 2000
-    }
-  ],
-  "max_steps": 2500,
-  "num_train_epochs": 10,
-  "total_flos": 1010109883418496.0,
-  "trial_name": null,
-  "trial_params": null
-}

checkpoint-2000/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b163d01ba6550b4d0ea94aab97f417a764349c69c3237b0edc7b5507f1235fe6
-size 4091

runs/Jul23_00-54-01_c587bebf8fcc/events.out.tfevents.1690073651.c587bebf8fcc.2239.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbecb5c809c6be6c8afb303e013916d04358d96b487dee4dec559b0dcf5d3a75
-size 26897
+oid sha256:923bfa4184be2ac7c1ae1dfa982802a88f61003483e02ccb0e3223406b74d6d2
+size 27251

checkpoint-2000/scheduler.pt → runs/Jul23_00-54-01_c587bebf8fcc/events.out.tfevents.1690073907.c587bebf8fcc.2239.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ad0c62478b179935d131a5f36054eef5c951ef7612bbd788e7a63be9d94d8ef
-size 627
+oid sha256:4718c55f24759e71c5aa9bbe1950c8cce6ea2f7597149730814404da616703cd
+size 1033