Training in progress, epoch 1

logs/events.out.tfevents.1713972412.a9ae8da52b57.4950.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b550970794dfbbec66fe297a660858b7e7e7497a6d704c2f6d40d6f140518d05
-size 5821
+oid sha256:5ced07f22216594a2799dfe425f0633a8560e7c2c584148f170b1366f83f609c
+size 7777

logs/events.out.tfevents.1713973393.a9ae8da52b57.4950.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:043f2b99889f42f4851dbfa4e8bf62400278810451fd3ebad96ccf5046fcdeea
+size 5289

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04718424263f1daeb934702fa9ed577b5f83d2953bd0c1ad552cadff85fb1fca
+oid sha256:d1e6cde987af6bff15d28e5d15ae9235f31b2f971522928ad2570f4843b1b6be
 size 17549312

run-1/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": "4.40.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-1/checkpoint-2635/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5339b0c6bc3d4ef7ca075671cb2c928b02bd773e24d9101798cab7494a35d853
+size 17549312

run-1/checkpoint-2635/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3335cf3a3d11748630f1e261895f2c8b03250623980594db6717b342834e141f
+size 35123898

run-1/checkpoint-2635/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bd37da819cfe1c92aea202c8f190c02a65fdc71a17fd2af0ed4760f9222ae02
+size 14308

run-1/checkpoint-2635/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ace847735e0948f99e6590d0e4a9b38efc4ac38c63ee656797b97ea52fc78ce
+size 1064

run-1/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-1/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-1/checkpoint-2635/trainer_state.json

@@ -0,0 +1,106 @@
+{
+  "best_metric": 0.8360091743119266,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-1/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,
+      "grad_norm": 22.49123764038086,
+      "learning_rate": 0.0002780733463240362,
+      "loss": 1.7444,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8360091743119266,
+      "eval_loss": 1.752740740776062,
+      "eval_runtime": 2.7351,
+      "eval_samples_per_second": 318.815,
+      "eval_steps_per_second": 2.559,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 10.574456214904785,
+      "learning_rate": 0.00020855500974302718,
+      "loss": 0.7696,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8142201834862385,
+      "eval_loss": 1.9697859287261963,
+      "eval_runtime": 2.6884,
+      "eval_samples_per_second": 324.355,
+      "eval_steps_per_second": 2.604,
+      "step": 1054
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013916858651416426,
+      "loss": 0.5359,
+      "step": 1581
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8222477064220184,
+      "eval_loss": 1.9042038917541504,
+      "eval_runtime": 2.7045,
+      "eval_samples_per_second": 322.427,
+      "eval_steps_per_second": 2.588,
+      "step": 1581
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 9.347850799560547,
+      "learning_rate": 6.965024993315518e-05,
+      "loss": 0.4078,
+      "step": 2108
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8222477064220184,
+      "eval_loss": 2.049978017807007,
+      "eval_runtime": 2.713,
+      "eval_samples_per_second": 321.42,
+      "eval_steps_per_second": 2.58,
+      "step": 2108
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 14.40003490447998,
+      "learning_rate": 1.3191335214612724e-07,
+      "loss": 0.329,
+      "step": 2635
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8279816513761468,
+      "eval_loss": 2.0179200172424316,
+      "eval_runtime": 2.6918,
+      "eval_samples_per_second": 323.947,
+      "eval_steps_per_second": 2.6,
+      "step": 2635
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2635,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 40447180739880.0,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.08970692378937972,
+    "learning_rate": 0.0003475916829050453,
+    "num_train_epochs": 5,
+    "temperature": 30
+  }
+}

run-1/checkpoint-2635/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2608572d74b285a65dbc7ad54bc17bf582a54f334d1b1780f3914acbfa4a4cbe
+size 5048

run-2/checkpoint-527/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": "4.40.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-2/checkpoint-527/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1e6cde987af6bff15d28e5d15ae9235f31b2f971522928ad2570f4843b1b6be
+size 17549312

run-2/checkpoint-527/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a4319eef3c7a41744ca793a40daa8d781b9b889506c8b431bcad7bd334a18d5
+size 35123898

run-2/checkpoint-527/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a32291cb0c1329fbb9596dcc47c5d9b0d1f71ecc09dad1791e0b193314659e4
+size 14308

run-2/checkpoint-527/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83be7bab6121a8f653f97f0e2a64d3880bdce736b2af814ef757f43d35e49cf7
+size 1064

run-2/checkpoint-527/special_tokens_map.json

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

run-2/checkpoint-527/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-2/checkpoint-527/trainer_state.json

@@ -0,0 +1,42 @@
+{
+  "best_metric": 0.7821100917431193,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-2/checkpoint-527",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 527,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 3.8070333003997803,
+      "learning_rate": 3.0759690838398e-05,
+      "loss": 0.8585,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7821100917431193,
+      "eval_loss": 0.7264055609703064,
+      "eval_runtime": 2.6688,
+      "eval_samples_per_second": 326.736,
+      "eval_steps_per_second": 2.623,
+      "step": 527
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5270,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 8057768762220.0,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9025220801031371,
+    "learning_rate": 3.4177434264886666e-05,
+    "num_train_epochs": 10,
+    "temperature": 12
+  }
+}

run-2/checkpoint-527/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a0beebefb12d041f1dcf06515119df79f0753e043a91d5e458722b2ea9abc44
+size 5048

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2608572d74b285a65dbc7ad54bc17bf582a54f334d1b1780f3914acbfa4a4cbe
+oid sha256:5a0beebefb12d041f1dcf06515119df79f0753e043a91d5e458722b2ea9abc44
 size 5048