Training in progress, epoch 1

logs/events.out.tfevents.1709846785.013ec1551212.75384.16

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f97c0f7a0fb6806b2c75765b0e787e6cdf1620fb43be1ad1482533e01ae78fb8
-size 6009
+oid sha256:58fbcc3dafd3e33edd1dff30ed24a532a4e29b7e9c44d9af372e86a79d285c3b
+size 8412

logs/events.out.tfevents.1709849643.013ec1551212.75384.17

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14b447eea03993a0585661eb745906cb939f9f22005d4886ea7d82b432a0d1c7
+size 5325

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38c20500096d5a8be6899ca8cd8410bf3637e1b33603715423575954df395111
+oid sha256:4e5d57ff5ae43a3d0b1dfaae8e9453ed6cb041150db29097ddd1b9fda34b374e
 size 17549312

run-16/checkpoint-3064/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": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-16/checkpoint-3064/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25270cb1c1fb015d27ec5d24a5fbf7b45a3b7f70eba9dbe32310ffa6dfda5bf5
+size 17549312

run-16/checkpoint-3064/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84008cacaa5ec3f4bd084c4f8ec8728b5211f312e5788dbb2d12f225a91773d6
+size 35122746

run-16/checkpoint-3064/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:292ad54a0d62461febd393d8e26ded58c99675978b26670e37515848b048d88a
+size 14054

run-16/checkpoint-3064/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba0259bd18c8ad3ae4c8708e724078c6e8d41610dec40df3d15c9118a84f6ff9
+size 1064

run-16/checkpoint-3064/special_tokens_map.json

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

run-16/checkpoint-3064/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-16/checkpoint-3064/trainer_state.json

@@ -0,0 +1,102 @@
+{
+  "best_metric": 0.815068493150685,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-16/checkpoint-3064",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 3064,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.586636066436768,
+      "learning_rate": 0.0002815362185318002,
+      "loss": 0.5012,
+      "step": 766
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7847358121330724,
+      "eval_f1": 0.8090277777777778,
+      "eval_loss": 0.4424646198749542,
+      "eval_precision": 0.7269890795631825,
+      "eval_recall": 0.9119373776908023,
+      "eval_runtime": 131.6873,
+      "eval_samples_per_second": 7.761,
+      "eval_steps_per_second": 1.944,
+      "step": 766
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 4.197028160095215,
+      "learning_rate": 0.00021115216389885013,
+      "loss": 0.4492,
+      "step": 1532
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.799412915851272,
+      "eval_f1": 0.8064211520302172,
+      "eval_loss": 0.440277099609375,
+      "eval_precision": 0.7791970802919708,
+      "eval_recall": 0.8356164383561644,
+      "eval_runtime": 131.1398,
+      "eval_samples_per_second": 7.793,
+      "eval_steps_per_second": 1.952,
+      "step": 1532
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.803006172180176,
+      "learning_rate": 0.0001407681092659001,
+      "loss": 0.4291,
+      "step": 2298
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.812133072407045,
+      "eval_f1": 0.8218923933209648,
+      "eval_loss": 0.4386424720287323,
+      "eval_precision": 0.781305114638448,
+      "eval_recall": 0.8669275929549902,
+      "eval_runtime": 130.5843,
+      "eval_samples_per_second": 7.826,
+      "eval_steps_per_second": 1.96,
+      "step": 2298
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.590163230895996,
+      "learning_rate": 7.038405463295006e-05,
+      "loss": 0.4241,
+      "step": 3064
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.815068493150685,
+      "eval_f1": 0.8177434908389585,
+      "eval_loss": 0.4371667206287384,
+      "eval_precision": 0.8060836501901141,
+      "eval_recall": 0.8297455968688845,
+      "eval_runtime": 130.7093,
+      "eval_samples_per_second": 7.819,
+      "eval_steps_per_second": 1.959,
+      "step": 3064
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3830,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 942780789120.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.7716344444380391,
+    "learning_rate": 0.00035192027316475024,
+    "num_train_epochs": 5,
+    "temperature": 10
+  }
+}

run-16/checkpoint-3064/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:447fc90b16b64e1ad048ef36b5e745ecb1f888d7304a1aea1048d24a1dc2951f
+size 4920

run-16/checkpoint-3830/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": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-16/checkpoint-3830/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04d2827610aea73d53704d3a6dfdef64fa880640020d5d111fa716f0bb582ec1
+size 17549312

run-16/checkpoint-3830/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2258844243891348c6131b6d923b86a0aaec8ae08ab5ed60e9d7ef40f5d0aa8b
+size 35122746

run-16/checkpoint-3830/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11f0f7f8253cabe8457ea3e8be3f556fa57dd5de6a14e336e6ae5d5e2e50d1cf
+size 14054

run-16/checkpoint-3830/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f337dd5dd70944bd15d9a3991a0fd4dfe7aebb972a119fea790819723872419a
+size 1064

run-16/checkpoint-3830/special_tokens_map.json

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

run-16/checkpoint-3830/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-16/checkpoint-3830/trainer_state.json

@@ -0,0 +1,121 @@
+{
+  "best_metric": 0.8189823874755382,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-16/checkpoint-3830",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 3830,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.586636066436768,
+      "learning_rate": 0.0002815362185318002,
+      "loss": 0.5012,
+      "step": 766
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7847358121330724,
+      "eval_f1": 0.8090277777777778,
+      "eval_loss": 0.4424646198749542,
+      "eval_precision": 0.7269890795631825,
+      "eval_recall": 0.9119373776908023,
+      "eval_runtime": 131.6873,
+      "eval_samples_per_second": 7.761,
+      "eval_steps_per_second": 1.944,
+      "step": 766
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 4.197028160095215,
+      "learning_rate": 0.00021115216389885013,
+      "loss": 0.4492,
+      "step": 1532
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.799412915851272,
+      "eval_f1": 0.8064211520302172,
+      "eval_loss": 0.440277099609375,
+      "eval_precision": 0.7791970802919708,
+      "eval_recall": 0.8356164383561644,
+      "eval_runtime": 131.1398,
+      "eval_samples_per_second": 7.793,
+      "eval_steps_per_second": 1.952,
+      "step": 1532
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.803006172180176,
+      "learning_rate": 0.0001407681092659001,
+      "loss": 0.4291,
+      "step": 2298
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.812133072407045,
+      "eval_f1": 0.8218923933209648,
+      "eval_loss": 0.4386424720287323,
+      "eval_precision": 0.781305114638448,
+      "eval_recall": 0.8669275929549902,
+      "eval_runtime": 130.5843,
+      "eval_samples_per_second": 7.826,
+      "eval_steps_per_second": 1.96,
+      "step": 2298
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.590163230895996,
+      "learning_rate": 7.038405463295006e-05,
+      "loss": 0.4241,
+      "step": 3064
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.815068493150685,
+      "eval_f1": 0.8177434908389585,
+      "eval_loss": 0.4371667206287384,
+      "eval_precision": 0.8060836501901141,
+      "eval_recall": 0.8297455968688845,
+      "eval_runtime": 130.7093,
+      "eval_samples_per_second": 7.819,
+      "eval_steps_per_second": 1.959,
+      "step": 3064
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 17.153400421142578,
+      "learning_rate": 0.0,
+      "loss": 0.4008,
+      "step": 3830
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8189823874755382,
+      "eval_f1": 0.8310502283105022,
+      "eval_loss": 0.4148101210594177,
+      "eval_precision": 0.7791095890410958,
+      "eval_recall": 0.8904109589041096,
+      "eval_runtime": 131.3758,
+      "eval_samples_per_second": 7.779,
+      "eval_steps_per_second": 1.949,
+      "step": 3830
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3830,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 1178475986400.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.7716344444380391,
+    "learning_rate": 0.00035192027316475024,
+    "num_train_epochs": 5,
+    "temperature": 10
+  }
+}

run-16/checkpoint-3830/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:447fc90b16b64e1ad048ef36b5e745ecb1f888d7304a1aea1048d24a1dc2951f
+size 4920

run-17/checkpoint-766/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": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-17/checkpoint-766/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e5d57ff5ae43a3d0b1dfaae8e9453ed6cb041150db29097ddd1b9fda34b374e
+size 17549312

run-17/checkpoint-766/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3ec0198db8d9115b4f2dc5f7eeed277be169a782545d440445e9e5b8225edb6
+size 35122746

run-17/checkpoint-766/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a29b5a9fab412f426bae759e459d7d9236aab6602ae439ea13f5bd437e1b98a4
+size 14054

run-17/checkpoint-766/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5dca096fea9455a00631a83752035008e7914ede393b7d8e3ee818212dad7b2
+size 1064

run-17/checkpoint-766/special_tokens_map.json

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

run-17/checkpoint-766/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-17/checkpoint-766/trainer_state.json

@@ -0,0 +1,45 @@
+{
+  "best_metric": 0.7876712328767124,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-17/checkpoint-766",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 766,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 3.036878824234009,
+      "learning_rate": 6.985166134218099e-05,
+      "loss": 0.5738,
+      "step": 766
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7876712328767124,
+      "eval_f1": 0.8121212121212121,
+      "eval_loss": 0.4637316167354584,
+      "eval_precision": 0.7282608695652174,
+      "eval_recall": 0.9178082191780822,
+      "eval_runtime": 132.0721,
+      "eval_samples_per_second": 7.738,
+      "eval_steps_per_second": 1.938,
+      "step": 766
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5362,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "total_flos": 235695197280.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9998794266799103,
+    "learning_rate": 8.149360489921117e-05,
+    "num_train_epochs": 7,
+    "temperature": 5
+  }
+}

run-17/checkpoint-766/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc7cb385fe32ff8bcfa8aa15978ddd1e9f86bac01019408664394fdf5d59d66e
+size 4920

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:447fc90b16b64e1ad048ef36b5e745ecb1f888d7304a1aea1048d24a1dc2951f
+oid sha256:bc7cb385fe32ff8bcfa8aa15978ddd1e9f86bac01019408664394fdf5d59d66e
 size 4920