Training in progress, epoch 1

logs/events.out.tfevents.1702277265.joseph_legion.22340.18

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:617af0d0886d3afd4ff3cd38b1b6fffa6a90d9121388c9f65939a469babf63cd
-size 7326
+oid sha256:84137f79fed20b031041dcd9ebb7b7bdb937a8ab33c669a520b5f92471aeeb63
+size 7806

logs/events.out.tfevents.1702280530.joseph_legion.22340.19

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:094429f2fb6546a60be731f7960f31d9d202dec31eabca9b10cf940af19d4e96
+size 4926

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c263ed7680053b0c6647f5947ff43e2263f33c30e7eaea33b614362bff78d60f
+oid sha256:fdf633a0181d211cb748e18f69c462c45119815d3f6af546ab8dcb0712a96e71
 size 44692608

run-6/checkpoint-197/config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "google/bert_uncased_L-4_H-256_A-4",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 256,
+  "id2label": {
+    "0": 0,
+    "1": 1
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "label2id": {
+    "0": 0,
+    "1": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 4,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-6/checkpoint-197/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdf633a0181d211cb748e18f69c462c45119815d3f6af546ab8dcb0712a96e71
+size 44692608

run-6/checkpoint-197/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6be57f413280070766754dfc8cb49b126c424614ae272f6a13681fb8f1530b1
+size 89430010

run-6/checkpoint-197/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfce427b13a79881b8dd7c1ca79db1eca136c641f9f35f4f0773c5f01a793672
+size 14308

run-6/checkpoint-197/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c8c9507b786e342fe342627cbebb3356874b502deed953225c033e1ae4865cf
+size 1064

run-6/checkpoint-197/special_tokens_map.json

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

run-6/checkpoint-197/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-6/checkpoint-197/trainer_state.json

@@ -0,0 +1,40 @@
+{
+  "best_metric": 0.7536131183991106,
+  "best_model_checkpoint": "tinybert-TG-HS-HX-parentpretrained\\run-6\\checkpoint-197",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 197,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.0611700032566007e-05,
+      "loss": 0.1259,
+      "step": 197
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7536131183991106,
+      "eval_loss": 0.12161022424697876,
+      "eval_runtime": 125.6824,
+      "eval_samples_per_second": 57.255,
+      "eval_steps_per_second": 0.454,
+      "step": 197
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1576,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "total_flos": 44298765947484.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.18717092492624732,
+    "learning_rate": 1.2127657180075437e-05,
+    "num_train_epochs": 8,
+    "temperature": 5
+  }
+}

run-6/checkpoint-197/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40dcaec467c321bbd4ff99afc7a2ae4bf90159a9a099a7339cfff83b49ccfbc6
+size 4792

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28cc7611006f792e9dd8ff296313a535b356cc6a1bb6db2c1180dd69535d0c93
+oid sha256:40dcaec467c321bbd4ff99afc7a2ae4bf90159a9a099a7339cfff83b49ccfbc6
 size 4792