Training in progress, epoch 5

logs/events.out.tfevents.1701759678.joseph_legion.10272.16

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30e45a247480ebc96f209baecd56acbc5368dad6e274a3e9595cb141e93c2059
-size 6215
+oid sha256:c872767754a2941acb5d0a162a9149f168b14506eb41b68f6af621917fcfd7fd
+size 7049

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4cc67758e9a4f5985c447e41bf77d5dd887aedb083af407a31e26afd6302ab9
+oid sha256:751fa74d94e8c9417596246797ac66a254e9e1b6d447d9255a355106566f42e7
 size 17549312

run-15/checkpoint-2635/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-15/checkpoint-2635/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:751fa74d94e8c9417596246797ac66a254e9e1b6d447d9255a355106566f42e7
+size 17549312

run-15/checkpoint-2635/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af2c39dd4e3d0c451cc19dfa0e3ad96ca6f399feb2b0fd722653b656df052308
+size 35123898

run-15/checkpoint-2635/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dede22851852362c4610a33dd1fe1d0ae7402b3b76398a9832f493ea9fb1aa9
+size 14308

run-15/checkpoint-2635/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:045ccf44220c41ad80db37f6c0ec208ddaaea3098027bb5a4944bac72918bbe4
+size 1064

run-15/checkpoint-2635/special_tokens_map.json

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

run-15/checkpoint-2635/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-15/checkpoint-2635/trainer_state.json

@@ -0,0 +1,99 @@
+{
+  "best_metric": 0.8314220183486238,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled\\run-15\\checkpoint-527",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 2635,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00025200338594854476,
+      "loss": 0.9759,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8314220183486238,
+      "eval_loss": 1.0490596294403076,
+      "eval_runtime": 1.7959,
+      "eval_samples_per_second": 485.544,
+      "eval_steps_per_second": 3.898,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.00018900253946140859,
+      "loss": 0.4734,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.823394495412844,
+      "eval_loss": 1.201561450958252,
+      "eval_runtime": 1.7799,
+      "eval_samples_per_second": 489.914,
+      "eval_steps_per_second": 3.933,
+      "step": 1054
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.00012600169297427238,
+      "loss": 0.3336,
+      "step": 1581
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8188073394495413,
+      "eval_loss": 1.2774909734725952,
+      "eval_runtime": 1.7767,
+      "eval_samples_per_second": 490.805,
+      "eval_steps_per_second": 3.94,
+      "step": 1581
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 6.300084648713619e-05,
+      "loss": 0.2564,
+      "step": 2108
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8176605504587156,
+      "eval_loss": 1.3708006143569946,
+      "eval_runtime": 1.8028,
+      "eval_samples_per_second": 483.681,
+      "eval_steps_per_second": 3.883,
+      "step": 2108
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.0,
+      "loss": 0.2168,
+      "step": 2635
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8188073394495413,
+      "eval_loss": 1.375797152519226,
+      "eval_runtime": 1.8489,
+      "eval_samples_per_second": 471.625,
+      "eval_steps_per_second": 3.786,
+      "step": 2635
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2635,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 40452267650880.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.6153233971144083,
+    "learning_rate": 0.00031500423243568097,
+    "num_train_epochs": 5,
+    "temperature": 14
+  }
+}

run-15/checkpoint-2635/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fd5459235a8577a6454d836553135f3519b14545a636877d353491a383dc742
+size 4664