Training in progress, step 1000

checkpoint-1000/config.json

@@ -0,0 +1,50 @@
+{
+  "_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-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d32e8828d1b1ae30530b7473d552ff9aa020e0b2f239c8b8134dfe979d15c0b
+size 267028677

checkpoint-1000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c366631ade427ba5a8dc8df9ca9f8d8f41caf8fad5eb2ca4c35c6fc3113ee13f
+size 133523761

checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46f76c8bed144eb0462eae7b352d4482d3ae98f3e4263329c2f739c21b5dd5ca
+size 14575

checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13828e1677406f24ffee2b52c5ac79b462a76afddafb014a11a21dd7429637dd
+size 627

checkpoint-1000/special_tokens_map.json

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

checkpoint-1000/tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "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-1000/trainer_state.json

@@ -0,0 +1,230 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "global_step": 1000,
+  "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
+    }
+  ],
+  "max_steps": 2500,
+  "num_train_epochs": 10,
+  "total_flos": 504019356005760.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1000/training_args.bin

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

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24a60923e118f86e3152bed751de29e981cde48e94fddec16dd1c7e9e4db929f
+oid sha256:c366631ade427ba5a8dc8df9ca9f8d8f41caf8fad5eb2ca4c35c6fc3113ee13f
 size 133523761

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 sha256:6a0105507a7dc18b7339a48cda035d074d7d3cf2e1c02937aa42eba5c5d8a377
-size 9265
+oid sha256:416334eba52c38503a50849c5e582537e15916e377fd8dfd037c12f9caaa7c8b
+size 13673