Training in progress, epoch 1

logs/events.out.tfevents.1709701849.adc675a344d5.5455.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:390f1a682c8c6754679f33a5b08baf722a2030d7fa0526e591a80b7ca2d7519a
-size 5998
+oid sha256:3cc08e103cee2f47a1aea9677e79a0e9d02441251d519213cb8d9ca0690b2079
+size 11816

logs/events.out.tfevents.1709703029.adc675a344d5.5455.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15d21e2ea51e168f1ee72eb0b17139fc3af6168bb5edd0528c764eb32895e7f9
+size 5314

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:194b75112269fc06e88a80b35841cbdf88acba5ee067538c1a1c095a9e141232
+oid sha256:d88b78d29ffacae504916ff9826e9a4fd404d9cb381fd25e2e8cc7e7ac3a360b
 size 17549312

run-0/checkpoint-768/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-0/checkpoint-768/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8999c0a2601a95f76a1f6cfd71237bd1561d6c2699a3ec424a192b88c0ef7ec6
+size 17549312

run-0/checkpoint-768/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0212a03868ee7df77f715497eb28dd8123426d540c6ea0304f45051d1cc0a4e9
+size 35122746

run-0/checkpoint-768/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33d55a7a7e131cd196205e2fe9c7e3f3a3d61ed6d79c468c68d4163c6b46138d
+size 14054

run-0/checkpoint-768/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64c4bb5a1127d358b3bd8745d71f76f7cf7ad37c71bb568c0b584fc6dda7795c
+size 1064

run-0/checkpoint-768/special_tokens_map.json

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

run-0/checkpoint-768/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-0/checkpoint-768/trainer_state.json

@@ -0,0 +1,178 @@
+{
+  "best_metric": 0.8228962818003914,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/checkpoint-768",
+  "epoch": 8.0,
+  "eval_steps": 500,
+  "global_step": 768,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.8004393577575684,
+      "learning_rate": 0.0007697157586205755,
+      "loss": 0.4935,
+      "step": 96
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7436399217221135,
+      "eval_f1": 0.7689594356261024,
+      "eval_loss": 0.448881596326828,
+      "eval_precision": 0.6998394863563403,
+      "eval_recall": 0.8532289628180039,
+      "eval_runtime": 28.6476,
+      "eval_samples_per_second": 35.675,
+      "eval_steps_per_second": 1.117,
+      "step": 96
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 4.9879961013793945,
+      "learning_rate": 0.0006841917854405115,
+      "loss": 0.4571,
+      "step": 192
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7896281800391389,
+      "eval_f1": 0.8057813911472448,
+      "eval_loss": 0.42557916045188904,
+      "eval_precision": 0.7483221476510067,
+      "eval_recall": 0.87279843444227,
+      "eval_runtime": 28.772,
+      "eval_samples_per_second": 35.521,
+      "eval_steps_per_second": 1.112,
+      "step": 192
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 3.279979705810547,
+      "learning_rate": 0.0005986678122604475,
+      "loss": 0.4337,
+      "step": 288
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7945205479452054,
+      "eval_f1": 0.8059149722735675,
+      "eval_loss": 0.4328659176826477,
+      "eval_precision": 0.7635726795096323,
+      "eval_recall": 0.8532289628180039,
+      "eval_runtime": 28.2776,
+      "eval_samples_per_second": 36.142,
+      "eval_steps_per_second": 1.132,
+      "step": 288
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.231189727783203,
+      "learning_rate": 0.0005131438390803836,
+      "loss": 0.4235,
+      "step": 384
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7690802348336595,
+      "eval_f1": 0.7704280155642023,
+      "eval_loss": 0.45082738995552063,
+      "eval_precision": 0.7659574468085106,
+      "eval_recall": 0.7749510763209393,
+      "eval_runtime": 29.4798,
+      "eval_samples_per_second": 34.668,
+      "eval_steps_per_second": 1.085,
+      "step": 384
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.6898621320724487,
+      "learning_rate": 0.00042761986590031967,
+      "loss": 0.4136,
+      "step": 480
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8033268101761253,
+      "eval_f1": 0.814404432132964,
+      "eval_loss": 0.41852009296417236,
+      "eval_precision": 0.7709790209790209,
+      "eval_recall": 0.863013698630137,
+      "eval_runtime": 29.6952,
+      "eval_samples_per_second": 34.416,
+      "eval_steps_per_second": 1.078,
+      "step": 480
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 1.360769510269165,
+      "learning_rate": 0.00034209589272025573,
+      "loss": 0.405,
+      "step": 576
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8043052837573386,
+      "eval_f1": 0.8204667863554758,
+      "eval_loss": 0.4140284061431885,
+      "eval_precision": 0.75787728026534,
+      "eval_recall": 0.8943248532289628,
+      "eval_runtime": 28.8106,
+      "eval_samples_per_second": 35.473,
+      "eval_steps_per_second": 1.111,
+      "step": 576
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 1.9378271102905273,
+      "learning_rate": 0.0002565719195401918,
+      "loss": 0.3961,
+      "step": 672
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.815068493150685,
+      "eval_f1": 0.8301886792452831,
+      "eval_loss": 0.4103885591030121,
+      "eval_precision": 0.7674418604651163,
+      "eval_recall": 0.9041095890410958,
+      "eval_runtime": 29.2823,
+      "eval_samples_per_second": 34.902,
+      "eval_steps_per_second": 1.093,
+      "step": 672
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 1.5738866329193115,
+      "learning_rate": 0.00017104794636012787,
+      "loss": 0.3931,
+      "step": 768
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8228962818003914,
+      "eval_f1": 0.8340971585701191,
+      "eval_loss": 0.39944925904273987,
+      "eval_precision": 0.7844827586206896,
+      "eval_recall": 0.8904109589041096,
+      "eval_runtime": 29.1614,
+      "eval_samples_per_second": 35.046,
+      "eval_steps_per_second": 1.097,
+      "step": 768
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 960,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1885561578240.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.735211359802956,
+    "learning_rate": 0.0008552397318006393,
+    "num_train_epochs": 10,
+    "temperature": 25
+  }
+}

run-0/checkpoint-768/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23804eaaa0feed30486319d2982557f65dce708f7d788864c811c20b2e8c33b4
+size 4920

run-0/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-0/checkpoint-960/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba4a7003755b10592915508f55852913e649127e5440c66527724e592cc2c7b9
+size 17549312

run-0/checkpoint-960/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af588371549f4acb73612d2ad9cd55882aa5fd9f7a0e04c941b81fe140e8d522
+size 35122746

run-0/checkpoint-960/rng_state.pth

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

run-0/checkpoint-960/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e74635b58993a273a88d047851a4965dd0f1dab13efd68e1f5c9a3b33d5098c1
+size 1064

run-0/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-0/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-0/checkpoint-960/trainer_state.json

@@ -0,0 +1,216 @@
+{
+  "best_metric": 0.8228962818003914,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/checkpoint-768",
+  "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": 1.8004393577575684,
+      "learning_rate": 0.0007697157586205755,
+      "loss": 0.4935,
+      "step": 96
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7436399217221135,
+      "eval_f1": 0.7689594356261024,
+      "eval_loss": 0.448881596326828,
+      "eval_precision": 0.6998394863563403,
+      "eval_recall": 0.8532289628180039,
+      "eval_runtime": 28.6476,
+      "eval_samples_per_second": 35.675,
+      "eval_steps_per_second": 1.117,
+      "step": 96
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 4.9879961013793945,
+      "learning_rate": 0.0006841917854405115,
+      "loss": 0.4571,
+      "step": 192
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7896281800391389,
+      "eval_f1": 0.8057813911472448,
+      "eval_loss": 0.42557916045188904,
+      "eval_precision": 0.7483221476510067,
+      "eval_recall": 0.87279843444227,
+      "eval_runtime": 28.772,
+      "eval_samples_per_second": 35.521,
+      "eval_steps_per_second": 1.112,
+      "step": 192
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 3.279979705810547,
+      "learning_rate": 0.0005986678122604475,
+      "loss": 0.4337,
+      "step": 288
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7945205479452054,
+      "eval_f1": 0.8059149722735675,
+      "eval_loss": 0.4328659176826477,
+      "eval_precision": 0.7635726795096323,
+      "eval_recall": 0.8532289628180039,
+      "eval_runtime": 28.2776,
+      "eval_samples_per_second": 36.142,
+      "eval_steps_per_second": 1.132,
+      "step": 288
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.231189727783203,
+      "learning_rate": 0.0005131438390803836,
+      "loss": 0.4235,
+      "step": 384
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7690802348336595,
+      "eval_f1": 0.7704280155642023,
+      "eval_loss": 0.45082738995552063,
+      "eval_precision": 0.7659574468085106,
+      "eval_recall": 0.7749510763209393,
+      "eval_runtime": 29.4798,
+      "eval_samples_per_second": 34.668,
+      "eval_steps_per_second": 1.085,
+      "step": 384
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.6898621320724487,
+      "learning_rate": 0.00042761986590031967,
+      "loss": 0.4136,
+      "step": 480
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8033268101761253,
+      "eval_f1": 0.814404432132964,
+      "eval_loss": 0.41852009296417236,
+      "eval_precision": 0.7709790209790209,
+      "eval_recall": 0.863013698630137,
+      "eval_runtime": 29.6952,
+      "eval_samples_per_second": 34.416,
+      "eval_steps_per_second": 1.078,
+      "step": 480
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 1.360769510269165,
+      "learning_rate": 0.00034209589272025573,
+      "loss": 0.405,
+      "step": 576
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8043052837573386,
+      "eval_f1": 0.8204667863554758,
+      "eval_loss": 0.4140284061431885,
+      "eval_precision": 0.75787728026534,
+      "eval_recall": 0.8943248532289628,
+      "eval_runtime": 28.8106,
+      "eval_samples_per_second": 35.473,
+      "eval_steps_per_second": 1.111,
+      "step": 576
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 1.9378271102905273,
+      "learning_rate": 0.0002565719195401918,
+      "loss": 0.3961,
+      "step": 672
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.815068493150685,
+      "eval_f1": 0.8301886792452831,
+      "eval_loss": 0.4103885591030121,
+      "eval_precision": 0.7674418604651163,
+      "eval_recall": 0.9041095890410958,
+      "eval_runtime": 29.2823,
+      "eval_samples_per_second": 34.902,
+      "eval_steps_per_second": 1.093,
+      "step": 672
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 1.5738866329193115,
+      "learning_rate": 0.00017104794636012787,
+      "loss": 0.3931,
+      "step": 768
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8228962818003914,
+      "eval_f1": 0.8340971585701191,
+      "eval_loss": 0.39944925904273987,
+      "eval_precision": 0.7844827586206896,
+      "eval_recall": 0.8904109589041096,
+      "eval_runtime": 29.1614,
+      "eval_samples_per_second": 35.046,
+      "eval_steps_per_second": 1.097,
+      "step": 768
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 0.702528178691864,
+      "learning_rate": 8.552397318006393e-05,
+      "loss": 0.3891,
+      "step": 864
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.8180039138943248,
+      "eval_f1": 0.8287292817679558,
+      "eval_loss": 0.39775392413139343,
+      "eval_precision": 0.782608695652174,
+      "eval_recall": 0.8806262230919765,
+      "eval_runtime": 29.1415,
+      "eval_samples_per_second": 35.07,
+      "eval_steps_per_second": 1.098,
+      "step": 864
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 2.4524667263031006,
+      "learning_rate": 0.0,
+      "loss": 0.3819,
+      "step": 960
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.8209393346379648,
+      "eval_f1": 0.8288119738072964,
+      "eval_loss": 0.3977544605731964,
+      "eval_precision": 0.7939068100358423,
+      "eval_recall": 0.8669275929549902,
+      "eval_runtime": 30.4608,
+      "eval_samples_per_second": 33.551,
+      "eval_steps_per_second": 1.051,
+      "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": 0.735211359802956,
+    "learning_rate": 0.0008552397318006393,
+    "num_train_epochs": 10,
+    "temperature": 25
+  }
+}

run-0/checkpoint-960/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23804eaaa0feed30486319d2982557f65dce708f7d788864c811c20b2e8c33b4
+size 4920

run-1/checkpoint-96/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65f3dae738929185d1e20f41e7bcf6ea1a73d176be72cfab23bb6503fcf370a1
+oid sha256:d88b78d29ffacae504916ff9826e9a4fd404d9cb381fd25e2e8cc7e7ac3a360b
 size 17549312

run-1/checkpoint-96/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5326787fcf5c172156d5e04cae26b95cb125ac94f1539f5594be70c38588eb7d
+oid sha256:a71f0829ccad1e615e8dc9739e8dd9ab2f6416a41935856d3df570f98d5f2dfe
 size 35122746

run-1/checkpoint-96/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:034a02c034574a59465ffaa25a28c8e0454ff7549227e81b8c6665e0b383867a
+oid sha256:bb304cd08666fb88677de9b419b0e96e439e7a92921a497fac84001d1c921c20
 size 1064

run-1/checkpoint-96/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.5,
+  "best_metric": 0.7661448140900196,
   "best_model_checkpoint": "tiny-bert-sst2-distilled/run-1/checkpoint-96",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -10,36 +10,36 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 0.4667714238166809,
-      "learning_rate": 7.759069356217338e-06,
-      "loss": 0.317,
+      "grad_norm": 2.6617980003356934,
+      "learning_rate": 0.0006635023570917325,
+      "loss": 0.5037,
       "step": 96
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.5,
-      "eval_f1": 0.0,
-      "eval_loss": 0.26975956559181213,
-      "eval_precision": 0.0,
-      "eval_recall": 0.0,
-      "eval_runtime": 28.3197,
-      "eval_samples_per_second": 36.088,
-      "eval_steps_per_second": 1.13,
+      "eval_accuracy": 0.7661448140900196,
+      "eval_f1": 0.792714657415438,
+      "eval_loss": 0.4430159628391266,
+      "eval_precision": 0.7118380062305296,
+      "eval_recall": 0.8943248532289628,
+      "eval_runtime": 28.6854,
+      "eval_samples_per_second": 35.628,
+      "eval_steps_per_second": 1.116,
       "step": 96
     }
   ],
   "logging_steps": 500,
-  "max_steps": 384,
+  "max_steps": 480,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 4,
+  "num_train_epochs": 5,
   "save_steps": 500,
   "total_flos": 235695197280.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.2995113868248127,
-    "learning_rate": 1.0345425808289785e-05,
-    "num_train_epochs": 4,
-    "temperature": 18
+    "alpha": 0.7818460169984094,
+    "learning_rate": 0.0008293779463646656,
+    "num_train_epochs": 5,
+    "temperature": 3
   }
 }

run-1/checkpoint-96/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f7a7027861ec8f0a120b010edf2e889059268bbeac3a62f529a79661a3cf64f
+oid sha256:1ab2cfe4c2ab241510bc23e9ec5727876e620ab477a4e5ad72a937b25e09df23
 size 4920

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99da68eb3e23d3e605d1e77f3904ae2ee7244687e6e5e8018e151049999ab73d
+oid sha256:1ab2cfe4c2ab241510bc23e9ec5727876e620ab477a4e5ad72a937b25e09df23
 size 4920