Training in progress, epoch 5

logs/events.out.tfevents.1706249191.A-FVFFG2C4Q05P.18450.19

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8e9193e605eef0fb5bd220ade658b78f062ba5fc8ea0e20ca53918eb38d1998
-size 5396
+oid sha256:9fd4c98722af83f9cd7065f3fd5cfcacdfcac48df3dc0e783e0ec52fb1acd051
+size 6836

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f7361cc641172e4d433d9122fa85e9b1eda716c64127b2b928ad93b520ec046
+oid sha256:c45e54c68134b07329ebc8d713846f3b955a30406885d185b73d22e069d4130d
 size 17549312

run-18/checkpoint-2108/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": "4.37.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-18/checkpoint-2108/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1af77ba935a895946c7413e68123d724463167b1d8cab54a51a1938cd1d8275
+size 17549312

run-18/checkpoint-2108/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b374cda362edf3ef6ef2ad8a71da5fada2b9dbc79b55b8cbe3d180ae9ae9e0e
+size 35122373

run-18/checkpoint-2108/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2aae3bffb74208d13dfae4d8b66eb00427742bd84752ee081ae0f135d90f179b
+size 13617

run-18/checkpoint-2108/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:199b222943ea355e8cafed84e05820110c7943d51c8a92d8ad2d53d7783aa249
+size 627

run-18/checkpoint-2108/special_tokens_map.json

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

run-18/checkpoint-2108/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-18/checkpoint-2108/trainer_state.json

@@ -0,0 +1,86 @@
+{
+  "best_metric": 0.8337155963302753,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-18/checkpoint-2108",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 2108,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00014893639687145338,
+      "loss": 0.8667,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8165137614678899,
+      "eval_loss": 0.8296506404876709,
+      "eval_runtime": 6.9326,
+      "eval_samples_per_second": 125.782,
+      "eval_steps_per_second": 1.01,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.00013031934726252174,
+      "loss": 0.4473,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8256880733944955,
+      "eval_loss": 0.9700397849082947,
+      "eval_runtime": 7.0917,
+      "eval_samples_per_second": 122.961,
+      "eval_steps_per_second": 0.987,
+      "step": 1054
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.00011170229765359004,
+      "loss": 0.3367,
+      "step": 1581
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8302752293577982,
+      "eval_loss": 0.971959114074707,
+      "eval_runtime": 7.4513,
+      "eval_samples_per_second": 117.027,
+      "eval_steps_per_second": 0.939,
+      "step": 1581
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 9.308524804465839e-05,
+      "loss": 0.2772,
+      "step": 2108
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8337155963302753,
+      "eval_loss": 0.9656078219413757,
+      "eval_runtime": 7.1382,
+      "eval_samples_per_second": 122.16,
+      "eval_steps_per_second": 0.981,
+      "step": 2108
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4743,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9,
+  "save_steps": 500,
+  "total_flos": 32344049138640.0,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.7585638468345914,
+    "learning_rate": 0.00016755344648038508,
+    "num_train_epochs": 9,
+    "temperature": 8
+  }
+}

run-18/checkpoint-2108/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dbd4682b40d5fae102c1795c728b50c70c76c7e268fdc70a102dfd6332bccba
+size 4283

run-18/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": "4.37.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-18/checkpoint-2635/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c45e54c68134b07329ebc8d713846f3b955a30406885d185b73d22e069d4130d
+size 17549312

run-18/checkpoint-2635/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed9d8d145917530460df842078e296324d7056d863275e76b72cc8d7d574a51c
+size 35122373

run-18/checkpoint-2635/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb154c82007a8758ab9f9ae31d1389cae06c1f2182ea0779f330182347f52f96
+size 13617

run-18/checkpoint-2635/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06432a37d8846c85eb0f37038d370f3493d35c0c9f1c259eb1d33bcc490cf4b6
+size 627

run-18/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-18/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-18/checkpoint-2635/trainer_state.json

@@ -0,0 +1,101 @@
+{
+  "best_metric": 0.8337155963302753,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-18/checkpoint-2108",
+  "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": 0.00014893639687145338,
+      "loss": 0.8667,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8165137614678899,
+      "eval_loss": 0.8296506404876709,
+      "eval_runtime": 6.9326,
+      "eval_samples_per_second": 125.782,
+      "eval_steps_per_second": 1.01,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.00013031934726252174,
+      "loss": 0.4473,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8256880733944955,
+      "eval_loss": 0.9700397849082947,
+      "eval_runtime": 7.0917,
+      "eval_samples_per_second": 122.961,
+      "eval_steps_per_second": 0.987,
+      "step": 1054
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.00011170229765359004,
+      "loss": 0.3367,
+      "step": 1581
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8302752293577982,
+      "eval_loss": 0.971959114074707,
+      "eval_runtime": 7.4513,
+      "eval_samples_per_second": 117.027,
+      "eval_steps_per_second": 0.939,
+      "step": 1581
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 9.308524804465839e-05,
+      "loss": 0.2772,
+      "step": 2108
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8337155963302753,
+      "eval_loss": 0.9656078219413757,
+      "eval_runtime": 7.1382,
+      "eval_samples_per_second": 122.16,
+      "eval_steps_per_second": 0.981,
+      "step": 2108
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 7.446819843572669e-05,
+      "loss": 0.2345,
+      "step": 2635
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.823394495412844,
+      "eval_loss": 1.0300672054290771,
+      "eval_runtime": 7.485,
+      "eval_samples_per_second": 116.5,
+      "eval_steps_per_second": 0.935,
+      "step": 2635
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4743,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9,
+  "save_steps": 500,
+  "total_flos": 40436714110320.0,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.7585638468345914,
+    "learning_rate": 0.00016755344648038508,
+    "num_train_epochs": 9,
+    "temperature": 8
+  }
+}

run-18/checkpoint-2635/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dbd4682b40d5fae102c1795c728b50c70c76c7e268fdc70a102dfd6332bccba
+size 4283