Training in progress, epoch 1

logs/events.out.tfevents.1709454712.49ae8f4e8e7b.1647.16

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53c74418c9707e8418397edf7577013390aa23b5405c08221864bdb568d33015
-size 5713
+oid sha256:53b17ec747dfd991ee5dfa6edd3f7d19b05c4e6da48a39ccf1be24522b4de170
+size 8737

logs/events.out.tfevents.1709456138.49ae8f4e8e7b.1647.17

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a22fa903660fdc625d8c0757f138805831987136b8c10552223d5687d850cdb
+size 5180

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3271379bef6bd1cb0c8ff7b46a6e514101d27032eb3d739e7a1d5b12d9fb4e2
+oid sha256:42fd1789b8f66804806aaf7e8c89d46f34b6bda9937d7312b10257634acdab74
 size 17549312

run-15/checkpoint-3689/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-15/checkpoint-3689/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfe7e812105eeb912a310a6c177936f8f0567a86e64464312cf0680b07f69e55
+size 17549312

run-15/checkpoint-3689/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b87ffae6ce9517aff0c883a0a51763d841b7ccd111b00dafcccd49bdfbe6f9f
+size 35123898

run-15/checkpoint-3689/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d13a9fca2ec73f276977f9543d3bb73304bb3a986bf0809d2c7305e26c18047
+size 14308

run-15/checkpoint-3689/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3717b64225b9ac5366ce29fc2204aed91335169d7284bbd3af7a41ad1181611
+size 1064

run-15/checkpoint-3689/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-3689/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-3689/trainer_state.json

@@ -0,0 +1,138 @@
+{
+  "best_metric": 0.8371559633027523,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-15/checkpoint-527",
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 3689,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 20.894563674926758,
+      "learning_rate": 0.00025961167449966676,
+      "loss": 1.6678,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8371559633027523,
+      "eval_loss": 1.635141134262085,
+      "eval_runtime": 2.8174,
+      "eval_samples_per_second": 309.502,
+      "eval_steps_per_second": 2.485,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 7.817446708679199,
+      "learning_rate": 0.00021634306208305565,
+      "loss": 0.738,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8188073394495413,
+      "eval_loss": 1.8634682893753052,
+      "eval_runtime": 2.8123,
+      "eval_samples_per_second": 310.062,
+      "eval_steps_per_second": 2.489,
+      "step": 1054
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": NaN,
+      "learning_rate": 0.00017315655329531854,
+      "loss": 0.5214,
+      "step": 1581
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8222477064220184,
+      "eval_loss": 1.81102454662323,
+      "eval_runtime": 2.8135,
+      "eval_samples_per_second": 309.932,
+      "eval_steps_per_second": 2.488,
+      "step": 1581
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 6.225761890411377,
+      "learning_rate": 0.0001298879408787074,
+      "loss": 0.4003,
+      "step": 2108
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8302752293577982,
+      "eval_loss": 1.878706932067871,
+      "eval_runtime": 2.8102,
+      "eval_samples_per_second": 310.296,
+      "eval_steps_per_second": 2.491,
+      "step": 2108
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 12.372098922729492,
+      "learning_rate": 8.661932846209629e-05,
+      "loss": 0.32,
+      "step": 2635
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8256880733944955,
+      "eval_loss": 1.8621728420257568,
+      "eval_runtime": 2.8187,
+      "eval_samples_per_second": 309.357,
+      "eval_steps_per_second": 2.483,
+      "step": 2635
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 20.063739776611328,
+      "learning_rate": 4.3350716045485156e-05,
+      "loss": 0.2702,
+      "step": 3162
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.823394495412844,
+      "eval_loss": 1.8646079301834106,
+      "eval_runtime": 2.813,
+      "eval_samples_per_second": 309.994,
+      "eval_steps_per_second": 2.488,
+      "step": 3162
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 8.405074119567871,
+      "learning_rate": 8.21036288740249e-08,
+      "loss": 0.2411,
+      "step": 3689
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8268348623853211,
+      "eval_loss": 1.880131483078003,
+      "eval_runtime": 2.8069,
+      "eval_samples_per_second": 310.665,
+      "eval_steps_per_second": 2.494,
+      "step": 3689
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3689,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "total_flos": 56628612372420.0,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.18003409042088625,
+    "learning_rate": 0.0003028802869162779,
+    "num_train_epochs": 7,
+    "temperature": 27
+  }
+}

run-15/checkpoint-3689/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:889ffd888c436e4a2c1590b654c7f117214f9b89b552e368e672dcc2f8c386b1
+size 4984

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

run-16/checkpoint-527/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42fd1789b8f66804806aaf7e8c89d46f34b6bda9937d7312b10257634acdab74
+size 17549312

run-16/checkpoint-527/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd099a3ee4c240e7435f50863251f4c4e9106d5863dcf9ba4fe172281eecd8b1
+size 35123898

run-16/checkpoint-527/rng_state.pth

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

run-16/checkpoint-527/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f71ca46f1a079db224802435549531dad123205b651040ce288be4747a7bdbe7
+size 1064

run-16/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-16/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-16/checkpoint-527/trainer_state.json

@@ -0,0 +1,42 @@
+{
+  "best_metric": 0.8256880733944955,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-16/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": 15.605107307434082,
+      "learning_rate": 0.00011351736809377586,
+      "loss": 1.2624,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8256880733944955,
+      "eval_loss": 1.1314730644226074,
+      "eval_runtime": 2.8139,
+      "eval_samples_per_second": 309.89,
+      "eval_steps_per_second": 2.488,
+      "step": 527
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2108,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 8057768762220.0,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.5930583577377427,
+    "learning_rate": 0.00015135649079170115,
+    "num_train_epochs": 4,
+    "temperature": 20
+  }
+}

run-16/checkpoint-527/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a57fdeab65524293cd0d615294bcf49a03ea5ac5a67936255d0dead2ac2a4c51
+size 4984

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:889ffd888c436e4a2c1590b654c7f117214f9b89b552e368e672dcc2f8c386b1
+oid sha256:a57fdeab65524293cd0d615294bcf49a03ea5ac5a67936255d0dead2ac2a4c51
 size 4984