Training in progress, epoch 1

logs/events.out.tfevents.1709739452.1dcff7455174.7719.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:825e449f3fd585e5ac831d9f7aad593c683436f477d712a70fceb001ddd14b2c
-size 5998
+oid sha256:f6a01dcec98287f4f06e2a5428b1b4d944acd7e05b1ceb1513f4ad865485b278
+size 11816

logs/events.out.tfevents.1709740464.1dcff7455174.7719.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bb1a8699986bd484846055993ca21ab5dabbfde4653e2c99f556f07be25df55
+size 5315

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:deb960f86bbce7f1a97643d0b15f883fecda364eb8de95e7626d45f3ec4fd61f
+oid sha256:ab948656a8f3a068c475bd4f8ea69d4442a86b38d858b54c66838470d5bc791d
 size 17549312

run-4/checkpoint-864/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-4/checkpoint-864/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd776eee58e7a327b5c1150dd898089963d59b4786017aa0c65743ee1e4a8345
+size 17549312

run-4/checkpoint-864/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3e1bf5bb4b06cfd382febd2debb51dab61b1d5492011a69934277fe5ebbfecf
+size 35122746

run-4/checkpoint-864/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97d9a51ee84ffde410aa6ee4faf7cd8373bce5e285d974fd9648694f2208055b
+size 14054

run-4/checkpoint-864/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a91b25eef2becc640caf961fbc576d107039ef54a8c7dc8d7f9ecfdbd3024e27
+size 1064

run-4/checkpoint-864/special_tokens_map.json

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

run-4/checkpoint-864/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-4/checkpoint-864/trainer_state.json

@@ -0,0 +1,197 @@
+{
+  "best_metric": 0.8238747553816047,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-4/checkpoint-768",
+  "epoch": 9.0,
+  "eval_steps": 500,
+  "global_step": 864,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.90240478515625,
+      "learning_rate": 0.0008040462940429662,
+      "loss": 0.4563,
+      "step": 96
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7446183953033269,
+      "eval_f1": 0.7473378509196515,
+      "eval_loss": 0.415781170129776,
+      "eval_precision": 0.7394636015325671,
+      "eval_recall": 0.7553816046966731,
+      "eval_runtime": 25.3619,
+      "eval_samples_per_second": 40.297,
+      "eval_steps_per_second": 1.262,
+      "step": 96
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.7548394799232483,
+      "learning_rate": 0.0007147078169270811,
+      "loss": 0.4243,
+      "step": 192
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7896281800391389,
+      "eval_f1": 0.7969782813975448,
+      "eval_loss": 0.39640527963638306,
+      "eval_precision": 0.7700729927007299,
+      "eval_recall": 0.8258317025440313,
+      "eval_runtime": 25.8877,
+      "eval_samples_per_second": 39.478,
+      "eval_steps_per_second": 1.236,
+      "step": 192
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.091404914855957,
+      "learning_rate": 0.0006253693398111959,
+      "loss": 0.4007,
+      "step": 288
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8052837573385518,
+      "eval_f1": 0.8240495137046862,
+      "eval_loss": 0.39981088042259216,
+      "eval_precision": 0.7516129032258064,
+      "eval_recall": 0.9119373776908023,
+      "eval_runtime": 25.886,
+      "eval_samples_per_second": 39.481,
+      "eval_steps_per_second": 1.236,
+      "step": 288
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.994834542274475,
+      "learning_rate": 0.0005360308626953108,
+      "loss": 0.3871,
+      "step": 384
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8082191780821918,
+      "eval_f1": 0.8175046554934823,
+      "eval_loss": 0.38285842537879944,
+      "eval_precision": 0.7797513321492007,
+      "eval_recall": 0.8590998043052838,
+      "eval_runtime": 25.8573,
+      "eval_samples_per_second": 39.525,
+      "eval_steps_per_second": 1.238,
+      "step": 384
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.7219040393829346,
+      "learning_rate": 0.00044669238557942565,
+      "loss": 0.378,
+      "step": 480
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.773972602739726,
+      "eval_f1": 0.7640449438202248,
+      "eval_loss": 0.39512935280799866,
+      "eval_precision": 0.7991452991452992,
+      "eval_recall": 0.7318982387475538,
+      "eval_runtime": 25.8711,
+      "eval_samples_per_second": 39.503,
+      "eval_steps_per_second": 1.237,
+      "step": 480
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 1.2725290060043335,
+      "learning_rate": 0.00035735390846354054,
+      "loss": 0.3759,
+      "step": 576
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.815068493150685,
+      "eval_f1": 0.8270814272644098,
+      "eval_loss": 0.3832918703556061,
+      "eval_precision": 0.7766323024054983,
+      "eval_recall": 0.8845401174168297,
+      "eval_runtime": 26.2709,
+      "eval_samples_per_second": 38.902,
+      "eval_steps_per_second": 1.218,
+      "step": 576
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.7257367968559265,
+      "learning_rate": 0.0002680154313476554,
+      "loss": 0.3679,
+      "step": 672
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.815068493150685,
+      "eval_f1": 0.8280254777070064,
+      "eval_loss": 0.37927353382110596,
+      "eval_precision": 0.7738095238095238,
+      "eval_recall": 0.8904109589041096,
+      "eval_runtime": 25.5612,
+      "eval_samples_per_second": 39.982,
+      "eval_steps_per_second": 1.252,
+      "step": 672
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 1.1571022272109985,
+      "learning_rate": 0.00017867695423177027,
+      "loss": 0.3609,
+      "step": 768
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8238747553816047,
+      "eval_f1": 0.832089552238806,
+      "eval_loss": 0.37364885210990906,
+      "eval_precision": 0.7950089126559715,
+      "eval_recall": 0.87279843444227,
+      "eval_runtime": 25.5421,
+      "eval_samples_per_second": 40.012,
+      "eval_steps_per_second": 1.253,
+      "step": 768
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 0.6674935817718506,
+      "learning_rate": 8.933847711588513e-05,
+      "loss": 0.3556,
+      "step": 864
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.8238747553816047,
+      "eval_f1": 0.8314606741573034,
+      "eval_loss": 0.3790241479873657,
+      "eval_precision": 0.7971274685816876,
+      "eval_recall": 0.8688845401174168,
+      "eval_runtime": 26.0614,
+      "eval_samples_per_second": 39.215,
+      "eval_steps_per_second": 1.228,
+      "step": 864
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 960,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 2121256775520.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.6601531096042508,
+    "learning_rate": 0.0008933847711588513,
+    "num_train_epochs": 10,
+    "temperature": 4
+  }
+}

run-4/checkpoint-864/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05a27237c59bc1684c5bc675b662fc3c971fc4d8663bd9fafef0f646ea921a93
+size 4920

run-4/checkpoint-960/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-4/checkpoint-960/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9cb480c01b2955ab4659777f56d6468bbadc585e4291f6207b02514eb20e61e
+size 17549312

run-4/checkpoint-960/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da3592e83ad14aebe9c980b18c0dc1ac9c15623e49972208fc3fb854289268a0
+size 35122746

run-4/checkpoint-960/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bc70fadfc325a9e3454d9d9f633805a30a7b6edb6e2dafe2e6da349874f75d0
+size 14054

run-4/checkpoint-960/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:377fe6940de29d4b1b362bdb64bc5a7963c0c1099ce7d7c87c76a44e0533c320
+size 1064

run-4/checkpoint-960/special_tokens_map.json

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

run-4/checkpoint-960/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-4/checkpoint-960/trainer_state.json

@@ -0,0 +1,216 @@
+{
+  "best_metric": 0.8258317025440313,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-4/checkpoint-960",
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 960,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.90240478515625,
+      "learning_rate": 0.0008040462940429662,
+      "loss": 0.4563,
+      "step": 96
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7446183953033269,
+      "eval_f1": 0.7473378509196515,
+      "eval_loss": 0.415781170129776,
+      "eval_precision": 0.7394636015325671,
+      "eval_recall": 0.7553816046966731,
+      "eval_runtime": 25.3619,
+      "eval_samples_per_second": 40.297,
+      "eval_steps_per_second": 1.262,
+      "step": 96
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.7548394799232483,
+      "learning_rate": 0.0007147078169270811,
+      "loss": 0.4243,
+      "step": 192
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7896281800391389,
+      "eval_f1": 0.7969782813975448,
+      "eval_loss": 0.39640527963638306,
+      "eval_precision": 0.7700729927007299,
+      "eval_recall": 0.8258317025440313,
+      "eval_runtime": 25.8877,
+      "eval_samples_per_second": 39.478,
+      "eval_steps_per_second": 1.236,
+      "step": 192
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.091404914855957,
+      "learning_rate": 0.0006253693398111959,
+      "loss": 0.4007,
+      "step": 288
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8052837573385518,
+      "eval_f1": 0.8240495137046862,
+      "eval_loss": 0.39981088042259216,
+      "eval_precision": 0.7516129032258064,
+      "eval_recall": 0.9119373776908023,
+      "eval_runtime": 25.886,
+      "eval_samples_per_second": 39.481,
+      "eval_steps_per_second": 1.236,
+      "step": 288
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.994834542274475,
+      "learning_rate": 0.0005360308626953108,
+      "loss": 0.3871,
+      "step": 384
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8082191780821918,
+      "eval_f1": 0.8175046554934823,
+      "eval_loss": 0.38285842537879944,
+      "eval_precision": 0.7797513321492007,
+      "eval_recall": 0.8590998043052838,
+      "eval_runtime": 25.8573,
+      "eval_samples_per_second": 39.525,
+      "eval_steps_per_second": 1.238,
+      "step": 384
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.7219040393829346,
+      "learning_rate": 0.00044669238557942565,
+      "loss": 0.378,
+      "step": 480
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.773972602739726,
+      "eval_f1": 0.7640449438202248,
+      "eval_loss": 0.39512935280799866,
+      "eval_precision": 0.7991452991452992,
+      "eval_recall": 0.7318982387475538,
+      "eval_runtime": 25.8711,
+      "eval_samples_per_second": 39.503,
+      "eval_steps_per_second": 1.237,
+      "step": 480
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 1.2725290060043335,
+      "learning_rate": 0.00035735390846354054,
+      "loss": 0.3759,
+      "step": 576
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.815068493150685,
+      "eval_f1": 0.8270814272644098,
+      "eval_loss": 0.3832918703556061,
+      "eval_precision": 0.7766323024054983,
+      "eval_recall": 0.8845401174168297,
+      "eval_runtime": 26.2709,
+      "eval_samples_per_second": 38.902,
+      "eval_steps_per_second": 1.218,
+      "step": 576
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.7257367968559265,
+      "learning_rate": 0.0002680154313476554,
+      "loss": 0.3679,
+      "step": 672
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.815068493150685,
+      "eval_f1": 0.8280254777070064,
+      "eval_loss": 0.37927353382110596,
+      "eval_precision": 0.7738095238095238,
+      "eval_recall": 0.8904109589041096,
+      "eval_runtime": 25.5612,
+      "eval_samples_per_second": 39.982,
+      "eval_steps_per_second": 1.252,
+      "step": 672
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 1.1571022272109985,
+      "learning_rate": 0.00017867695423177027,
+      "loss": 0.3609,
+      "step": 768
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8238747553816047,
+      "eval_f1": 0.832089552238806,
+      "eval_loss": 0.37364885210990906,
+      "eval_precision": 0.7950089126559715,
+      "eval_recall": 0.87279843444227,
+      "eval_runtime": 25.5421,
+      "eval_samples_per_second": 40.012,
+      "eval_steps_per_second": 1.253,
+      "step": 768
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 0.6674935817718506,
+      "learning_rate": 8.933847711588513e-05,
+      "loss": 0.3556,
+      "step": 864
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.8238747553816047,
+      "eval_f1": 0.8314606741573034,
+      "eval_loss": 0.3790241479873657,
+      "eval_precision": 0.7971274685816876,
+      "eval_recall": 0.8688845401174168,
+      "eval_runtime": 26.0614,
+      "eval_samples_per_second": 39.215,
+      "eval_steps_per_second": 1.228,
+      "step": 864
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 1.1517527103424072,
+      "learning_rate": 0.0,
+      "loss": 0.3558,
+      "step": 960
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.8258317025440313,
+      "eval_f1": 0.8327067669172932,
+      "eval_loss": 0.3765825033187866,
+      "eval_precision": 0.8010849909584087,
+      "eval_recall": 0.8669275929549902,
+      "eval_runtime": 25.5387,
+      "eval_samples_per_second": 40.018,
+      "eval_steps_per_second": 1.253,
+      "step": 960
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 960,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 2356951972800.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.6601531096042508,
+    "learning_rate": 0.0008933847711588513,
+    "num_train_epochs": 10,
+    "temperature": 4
+  }
+}

run-4/checkpoint-960/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05a27237c59bc1684c5bc675b662fc3c971fc4d8663bd9fafef0f646ea921a93
+size 4920

run-5/checkpoint-96/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccbc2692ffb008c33546615e958ce626fe5509ebd029a94df4bf890a08b8c299
+oid sha256:ab948656a8f3a068c475bd4f8ea69d4442a86b38d858b54c66838470d5bc791d
 size 17549312

run-5/checkpoint-96/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e602e47b7704ae34c8e851b7b565b29fd3b1cd6bef7e3ca692ee28e130f92b7
+oid sha256:789a53ef9e5c4daac0ab858396795e61203c98fbd2ae96b471d91e28ad70018e
 size 35122746

run-5/checkpoint-96/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3928d055d8b075b2b37b65175c5c6ddee065149b7092644ef1614d0079a2abad
+oid sha256:d29be6a38b7f249657264e2a9093d3d5bceb88084b4985ceabe7d5be446796ea
 size 1064

run-5/checkpoint-96/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.5,
+  "best_metric": 0.7485322896281801,
   "best_model_checkpoint": "tiny-bert-sst2-distilled/run-5/checkpoint-96",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -10,36 +10,36 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 0.3559625446796417,
-      "learning_rate": 1.0630037292458489e-05,
-      "loss": 0.1611,
+      "grad_norm": 4.850555896759033,
+      "learning_rate": 0.00013535007385325417,
+      "loss": 0.604,
       "step": 96
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.5,
-      "eval_f1": 0.0,
-      "eval_loss": 0.08401502668857574,
-      "eval_precision": 0.0,
-      "eval_recall": 0.0,
-      "eval_runtime": 29.4435,
-      "eval_samples_per_second": 34.711,
-      "eval_steps_per_second": 1.087,
+      "eval_accuracy": 0.7485322896281801,
+      "eval_f1": 0.7925746569814367,
+      "eval_loss": 0.5116264820098877,
+      "eval_precision": 0.6744505494505495,
+      "eval_recall": 0.9608610567514677,
+      "eval_runtime": 25.4927,
+      "eval_samples_per_second": 40.09,
+      "eval_steps_per_second": 1.255,
       "step": 96
     }
   ],
   "logging_steps": 500,
-  "max_steps": 576,
+  "max_steps": 864,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 6,
+  "num_train_epochs": 9,
   "save_steps": 500,
   "total_flos": 235695197280.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.052099509776179165,
-    "learning_rate": 1.2756044750950187e-05,
-    "num_train_epochs": 6,
-    "temperature": 24
+    "alpha": 0.9725110110091697,
+    "learning_rate": 0.00015226883308491095,
+    "num_train_epochs": 9,
+    "temperature": 30
   }
 }

run-5/checkpoint-96/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfbbf54cec56060e2edd3d1a453b0c70fd065bc032e57f0724da791ee79740dc
+oid sha256:e928ace2435c5cf3b335e3ecdb8105916df767a328988fcbdd90881ae94c09c4
 size 4920

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b1e78ebe59ee96c303be832e031d6c088100762ee5b36fd3c45156a45542056
+oid sha256:e928ace2435c5cf3b335e3ecdb8105916df767a328988fcbdd90881ae94c09c4
 size 4920