Training in progress, epoch 7

logs/events.out.tfevents.1701758098.joseph_legion.10272.12

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22160d1aca7aee03709102d413d10aaf2af6e47f030999d9871c59b31f00b010
-size 7175
+oid sha256:5c741ac53ca2de150bd4798507ef297ab6cb36c9d6452fc407af7862fad5c63a
+size 7655

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f30e2b3e5a2e0c9efb0884c8595d4fb34d22a048b55d3915232e1be859dbb63
+oid sha256:05b396dccc58ff8c3bfd319a0a4b49922e224fb5a937067f51698ba4c64590f1
 size 17549312

run-11/checkpoint-3689/config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 128,
+  "id2label": {
+    "0": "negative",
+    "1": "positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "label2id": {
+    "negative": "0",
+    "positive": "1"
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 2,
+  "num_hidden_layers": 2,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-11/checkpoint-3689/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05b396dccc58ff8c3bfd319a0a4b49922e224fb5a937067f51698ba4c64590f1
+size 17549312

run-11/checkpoint-3689/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9fe83695748331365ff060d6bbead5b49fe81d4209e4b320d3670f45d9088c5
+size 35123898

run-11/checkpoint-3689/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc20784aa2bd9699f06a4a044cc4eca9a0a372503deca38139c95e84a56ccd04
+size 14308

run-11/checkpoint-3689/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04f5e4d9f82b179c452d1c3622d120aa1010c9d7be74a6dada0255da973c6f5c
+size 1064

run-11/checkpoint-3689/special_tokens_map.json

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

run-11/checkpoint-3689/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-11/checkpoint-3689/trainer_state.json

@@ -0,0 +1,129 @@
+{
+  "best_metric": 0.8302752293577982,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled\\run-11\\checkpoint-1054",
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 3689,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00018146994805344583,
+      "loss": 0.5299,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8188073394495413,
+      "eval_loss": 0.5735568404197693,
+      "eval_runtime": 1.6581,
+      "eval_samples_per_second": 525.898,
+      "eval_steps_per_second": 4.222,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0001555456697600964,
+      "loss": 0.2972,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8302752293577982,
+      "eval_loss": 0.6297323703765869,
+      "eval_runtime": 1.6463,
+      "eval_samples_per_second": 529.683,
+      "eval_steps_per_second": 4.252,
+      "step": 1054
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.000129621391466747,
+      "loss": 0.2227,
+      "step": 1581
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8119266055045872,
+      "eval_loss": 0.7183768153190613,
+      "eval_runtime": 1.7083,
+      "eval_samples_per_second": 510.435,
+      "eval_steps_per_second": 4.098,
+      "step": 1581
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.00010369711317339761,
+      "loss": 0.1776,
+      "step": 2108
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8142201834862385,
+      "eval_loss": 0.8192135691642761,
+      "eval_runtime": 1.629,
+      "eval_samples_per_second": 535.299,
+      "eval_steps_per_second": 4.297,
+      "step": 2108
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 7.77728348800482e-05,
+      "loss": 0.1505,
+      "step": 2635
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8222477064220184,
+      "eval_loss": 0.8350348472595215,
+      "eval_runtime": 1.629,
+      "eval_samples_per_second": 535.303,
+      "eval_steps_per_second": 4.297,
+      "step": 2635
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 5.1848556586698804e-05,
+      "loss": 0.1312,
+      "step": 3162
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8222477064220184,
+      "eval_loss": 0.8590517640113831,
+      "eval_runtime": 1.6215,
+      "eval_samples_per_second": 537.769,
+      "eval_steps_per_second": 4.317,
+      "step": 3162
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 2.5924278293349402e-05,
+      "loss": 0.1163,
+      "step": 3689
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8176605504587156,
+      "eval_loss": 0.910841166973114,
+      "eval_runtime": 1.6831,
+      "eval_samples_per_second": 518.077,
+      "eval_steps_per_second": 4.159,
+      "step": 3689
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4216,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "total_flos": 56626835675700.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.7309291121922327,
+    "learning_rate": 0.00020739422634679522,
+    "num_train_epochs": 8,
+    "temperature": 2
+  }
+}

run-11/checkpoint-3689/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:145839f54a5a626f3e4088fabae28ecd1671f8911e84c67f5728017d401bb3fe
+size 4664