Training in progress, epoch 1

logs/events.out.tfevents.1709451254.49ae8f4e8e7b.1647.12

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e91defae41c4e624bcb2825dccfcff76609a50bf5c7a693fe529c108fc5bb7d
-size 5714
+oid sha256:5d751bf5d083746845f861f65576e0dcc761e4ca7d5850a31916b6866d6ee5ad
+size 9272

logs/events.out.tfevents.1709452881.49ae8f4e8e7b.1647.13

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4665f040725e08eab659a6bd6d283345d2ada1d498c336b4628bece4fd373de
+size 5180

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2145780c2f807d77d392bcbcd34ab93dffc279e27dc4d907625b698a4fccf557
+oid sha256:58562c272084a4b8f6957555e86ce8f953b5118bc25da5d4789dd034665a27c0
 size 17549312

run-11/checkpoint-4216/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-11/checkpoint-4216/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca138ce3eadcb6e215a53f1d9460285c060a3f5dfef13e75baab36972f24a145
+size 17549312

run-11/checkpoint-4216/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9021b2611227b5acdfec9975fcdb3db2ef4464887148d78e20feb21c4a9e9f8
+size 35123898

run-11/checkpoint-4216/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a2719006b61f28d7e37d68afe179a1c4b2eedc673365947492e106cb79f976c
+size 14308

run-11/checkpoint-4216/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf851309c6ecb8454c2c981595a25ea140bde4a96304b285691cec772717501a
+size 1064

run-11/checkpoint-4216/special_tokens_map.json

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

run-11/checkpoint-4216/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-11/checkpoint-4216/trainer_state.json

@@ -0,0 +1,154 @@
+{
+  "best_metric": 0.8256880733944955,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-11/checkpoint-527",
+  "epoch": 8.0,
+  "eval_steps": 500,
+  "global_step": 4216,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 6.5331573486328125,
+      "learning_rate": 0.00014562243502675204,
+      "loss": 0.547,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8256880733944955,
+      "eval_loss": 0.5717546343803406,
+      "eval_runtime": 2.8071,
+      "eval_samples_per_second": 310.639,
+      "eval_steps_per_second": 2.494,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 4.755884647369385,
+      "learning_rate": 0.0001248192300229303,
+      "loss": 0.3165,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.823394495412844,
+      "eval_loss": 0.6189394593238831,
+      "eval_runtime": 2.8231,
+      "eval_samples_per_second": 308.882,
+      "eval_steps_per_second": 2.48,
+      "step": 1054
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 13.318252563476562,
+      "learning_rate": 0.0001040160250191086,
+      "loss": 0.2438,
+      "step": 1581
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8256880733944955,
+      "eval_loss": 0.6849867701530457,
+      "eval_runtime": 2.8211,
+      "eval_samples_per_second": 309.105,
+      "eval_steps_per_second": 2.481,
+      "step": 1581
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 6.025650501251221,
+      "learning_rate": 8.321282001528688e-05,
+      "loss": 0.2015,
+      "step": 2108
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8256880733944955,
+      "eval_loss": 0.7157025337219238,
+      "eval_runtime": 2.8159,
+      "eval_samples_per_second": 309.671,
+      "eval_steps_per_second": 2.486,
+      "step": 2108
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 6.3858113288879395,
+      "learning_rate": 6.240961501146515e-05,
+      "loss": 0.1725,
+      "step": 2635
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8153669724770642,
+      "eval_loss": 0.7607192397117615,
+      "eval_runtime": 2.8278,
+      "eval_samples_per_second": 308.365,
+      "eval_steps_per_second": 2.475,
+      "step": 2635
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 12.167182922363281,
+      "learning_rate": 4.160641000764344e-05,
+      "loss": 0.1517,
+      "step": 3162
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8119266055045872,
+      "eval_loss": 0.8524329662322998,
+      "eval_runtime": 2.8071,
+      "eval_samples_per_second": 310.643,
+      "eval_steps_per_second": 2.494,
+      "step": 3162
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 6.675292015075684,
+      "learning_rate": 2.080320500382172e-05,
+      "loss": 0.1413,
+      "step": 3689
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8107798165137615,
+      "eval_loss": 0.862307608127594,
+      "eval_runtime": 2.8162,
+      "eval_samples_per_second": 309.641,
+      "eval_steps_per_second": 2.486,
+      "step": 3689
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 2.5445616245269775,
+      "learning_rate": 0.0,
+      "loss": 0.1299,
+      "step": 4216
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8107798165137615,
+      "eval_loss": 0.8725943565368652,
+      "eval_runtime": 2.8212,
+      "eval_samples_per_second": 309.086,
+      "eval_steps_per_second": 2.481,
+      "step": 4216
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4216,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "total_flos": 64687167744780.0,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9318516048675823,
+    "learning_rate": 0.00016642564003057375,
+    "num_train_epochs": 8,
+    "temperature": 23
+  }
+}

run-11/checkpoint-4216/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02ab451f50de4ed3d9e5dd09fa9222aca4567e2ff71c45b746c8f3a6f98f8b58
+size 4984

run-12/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-12/checkpoint-527/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58562c272084a4b8f6957555e86ce8f953b5118bc25da5d4789dd034665a27c0
+size 17549312

run-12/checkpoint-527/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6afb90d2e574345e25961f45467dd7680b86458a177ac3e465a0fd3a4e4d681
+size 35123898

run-12/checkpoint-527/rng_state.pth

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

run-12/checkpoint-527/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61856e660e737eccfc463fc9145b4ab8fba3e64cfdc5ee9c8fd21e059684f19a
+size 1064

run-12/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-12/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-12/checkpoint-527/trainer_state.json

@@ -0,0 +1,42 @@
+{
+  "best_metric": 0.8302752293577982,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-12/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": 9.690923690795898,
+      "learning_rate": 0.0003321213172401304,
+      "loss": 1.3202,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8302752293577982,
+      "eval_loss": 1.4912840127944946,
+      "eval_runtime": 2.8077,
+      "eval_samples_per_second": 310.575,
+      "eval_steps_per_second": 2.493,
+      "step": 527
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3689,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "total_flos": 8057768762220.0,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.3539642822905392,
+    "learning_rate": 0.00038747487011348545,
+    "num_train_epochs": 7,
+    "temperature": 26
+  }
+}

run-12/checkpoint-527/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3d08ae6ec02ad42dc32a924bc963a5ff21294f9231ad7a8fa48dbfc06efc1fd
+size 4984

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02ab451f50de4ed3d9e5dd09fa9222aca4567e2ff71c45b746c8f3a6f98f8b58
+oid sha256:d3d08ae6ec02ad42dc32a924bc963a5ff21294f9231ad7a8fa48dbfc06efc1fd
 size 4984