Training in progress, epoch 1

logs/events.out.tfevents.1709617120.404ecd1cf399.26000.6

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:867d4df4afa577a7699f1894ea4d21d63c35643ed60ab229af9b7d8e95672906
-size 5998
+oid sha256:5bb824cb4d211fe32cb1bc5972113e26da6061b5dd3ff4e68074a48975c026f7
+size 9767

logs/events.out.tfevents.1709617962.404ecd1cf399.26000.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb506f97de355e1cb7a1f8f560a2a98891680271b7610b718622d438315d9c36
+size 5315

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d18302f45f2738bee84402d3149338ce771af8b090150e2415fd4658f8b35097
+oid sha256:3eb8876585d4fdb886e817abd3e35044d9b68fb1b7d8d76911fabe58f9f805d6
 size 17549312

run-0/checkpoint-576/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-576/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4779ddd752d6806e02c8ef27c36779f88177d02efc230bb359722ee2e9bb3b42
+size 17549312

run-0/checkpoint-576/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6a6063018a8db267a1e4d35b8d01d6066645909ef307ba9b19e260e769b4a5b
+size 35122746

run-0/checkpoint-576/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d4ad45514321df5f64172bb2de61ac319a093d9f31cf01031977fb88be20551
+size 14054

run-0/checkpoint-576/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31ce8ebda13eb9d943e5ff0b10e5de301e1d45e261b316128872c7139d9db919
+size 1064

run-0/checkpoint-576/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-576/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-576/trainer_state.json

@@ -0,0 +1,140 @@
+{
+  "best_metric": 0.8356164383561644,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/checkpoint-576",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 576,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.648221731185913,
+      "learning_rate": 0.0001778537404863438,
+      "loss": 0.5789,
+      "step": 96
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7700587084148728,
+      "eval_f1": 0.8049792531120332,
+      "eval_loss": 0.47850364446640015,
+      "eval_precision": 0.6988472622478387,
+      "eval_recall": 0.949119373776908,
+      "eval_runtime": 31.8773,
+      "eval_samples_per_second": 32.06,
+      "eval_steps_per_second": 1.004,
+      "step": 96
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 4.695119857788086,
+      "learning_rate": 0.0001482114504052865,
+      "loss": 0.4663,
+      "step": 192
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8131115459882583,
+      "eval_f1": 0.8323090430201932,
+      "eval_loss": 0.42822203040122986,
+      "eval_precision": 0.7547770700636943,
+      "eval_recall": 0.9275929549902152,
+      "eval_runtime": 31.0929,
+      "eval_samples_per_second": 32.869,
+      "eval_steps_per_second": 1.029,
+      "step": 192
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 4.924405097961426,
+      "learning_rate": 0.0001185691603242292,
+      "loss": 0.4316,
+      "step": 288
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8228962818003914,
+      "eval_f1": 0.8331797235023042,
+      "eval_loss": 0.4343426525592804,
+      "eval_precision": 0.7874564459930313,
+      "eval_recall": 0.8845401174168297,
+      "eval_runtime": 31.8005,
+      "eval_samples_per_second": 32.138,
+      "eval_steps_per_second": 1.006,
+      "step": 288
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 6.703495979309082,
+      "learning_rate": 8.89268702431719e-05,
+      "loss": 0.414,
+      "step": 384
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8180039138943248,
+      "eval_f1": 0.8245283018867925,
+      "eval_loss": 0.41725680232048035,
+      "eval_precision": 0.7959927140255009,
+      "eval_recall": 0.8551859099804305,
+      "eval_runtime": 32.0071,
+      "eval_samples_per_second": 31.93,
+      "eval_steps_per_second": 1.0,
+      "step": 384
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 2.176375150680542,
+      "learning_rate": 5.92845801621146e-05,
+      "loss": 0.4042,
+      "step": 480
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8336594911937377,
+      "eval_f1": 0.8473967684021544,
+      "eval_loss": 0.4033981263637543,
+      "eval_precision": 0.7827529021558872,
+      "eval_recall": 0.923679060665362,
+      "eval_runtime": 31.1502,
+      "eval_samples_per_second": 32.809,
+      "eval_steps_per_second": 1.027,
+      "step": 480
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 4.6770453453063965,
+      "learning_rate": 2.96422900810573e-05,
+      "loss": 0.3947,
+      "step": 576
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8356164383561644,
+      "eval_f1": 0.8497316636851521,
+      "eval_loss": 0.4074985384941101,
+      "eval_precision": 0.7825370675453048,
+      "eval_recall": 0.9295499021526419,
+      "eval_runtime": 31.7728,
+      "eval_samples_per_second": 32.166,
+      "eval_steps_per_second": 1.007,
+      "step": 576
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 672,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "total_flos": 1414171183680.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9489576625421504,
+    "learning_rate": 0.00020749603056740112,
+    "num_train_epochs": 7,
+    "temperature": 28
+  }
+}

run-0/checkpoint-576/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8331ea07c172c96760b5e5803c65d803e6e6da860ef2aeb4c9d1e33d878a2a66
+size 4920

run-0/checkpoint-672/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-672/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abb8cc016ca85373195e5f362f9ad258fd306ec80390fb47e4141542f3a6c3cd
+size 17549312

run-0/checkpoint-672/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b818cf779478eac84c48f1c52ea3279d8d5a192fb0e1f3cd949953dc2cc5c86f
+size 35122746

run-0/checkpoint-672/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a39c6918f3fd24e7a04a4220bba5fcc478d9db2386daee293756dba26ecf21ac
+size 14054

run-0/checkpoint-672/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:438a1b8a92d849f5ac9ab23a02158bb4bfdc470b0d7e0897b41fed2417ad839e
+size 1064

run-0/checkpoint-672/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-672/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-672/trainer_state.json

@@ -0,0 +1,159 @@
+{
+  "best_metric": 0.8356164383561644,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/checkpoint-576",
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 672,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.648221731185913,
+      "learning_rate": 0.0001778537404863438,
+      "loss": 0.5789,
+      "step": 96
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7700587084148728,
+      "eval_f1": 0.8049792531120332,
+      "eval_loss": 0.47850364446640015,
+      "eval_precision": 0.6988472622478387,
+      "eval_recall": 0.949119373776908,
+      "eval_runtime": 31.8773,
+      "eval_samples_per_second": 32.06,
+      "eval_steps_per_second": 1.004,
+      "step": 96
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 4.695119857788086,
+      "learning_rate": 0.0001482114504052865,
+      "loss": 0.4663,
+      "step": 192
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8131115459882583,
+      "eval_f1": 0.8323090430201932,
+      "eval_loss": 0.42822203040122986,
+      "eval_precision": 0.7547770700636943,
+      "eval_recall": 0.9275929549902152,
+      "eval_runtime": 31.0929,
+      "eval_samples_per_second": 32.869,
+      "eval_steps_per_second": 1.029,
+      "step": 192
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 4.924405097961426,
+      "learning_rate": 0.0001185691603242292,
+      "loss": 0.4316,
+      "step": 288
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8228962818003914,
+      "eval_f1": 0.8331797235023042,
+      "eval_loss": 0.4343426525592804,
+      "eval_precision": 0.7874564459930313,
+      "eval_recall": 0.8845401174168297,
+      "eval_runtime": 31.8005,
+      "eval_samples_per_second": 32.138,
+      "eval_steps_per_second": 1.006,
+      "step": 288
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 6.703495979309082,
+      "learning_rate": 8.89268702431719e-05,
+      "loss": 0.414,
+      "step": 384
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8180039138943248,
+      "eval_f1": 0.8245283018867925,
+      "eval_loss": 0.41725680232048035,
+      "eval_precision": 0.7959927140255009,
+      "eval_recall": 0.8551859099804305,
+      "eval_runtime": 32.0071,
+      "eval_samples_per_second": 31.93,
+      "eval_steps_per_second": 1.0,
+      "step": 384
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 2.176375150680542,
+      "learning_rate": 5.92845801621146e-05,
+      "loss": 0.4042,
+      "step": 480
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8336594911937377,
+      "eval_f1": 0.8473967684021544,
+      "eval_loss": 0.4033981263637543,
+      "eval_precision": 0.7827529021558872,
+      "eval_recall": 0.923679060665362,
+      "eval_runtime": 31.1502,
+      "eval_samples_per_second": 32.809,
+      "eval_steps_per_second": 1.027,
+      "step": 480
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 4.6770453453063965,
+      "learning_rate": 2.96422900810573e-05,
+      "loss": 0.3947,
+      "step": 576
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8356164383561644,
+      "eval_f1": 0.8497316636851521,
+      "eval_loss": 0.4074985384941101,
+      "eval_precision": 0.7825370675453048,
+      "eval_recall": 0.9295499021526419,
+      "eval_runtime": 31.7728,
+      "eval_samples_per_second": 32.166,
+      "eval_steps_per_second": 1.007,
+      "step": 576
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 3.172855854034424,
+      "learning_rate": 0.0,
+      "loss": 0.3887,
+      "step": 672
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8356164383561644,
+      "eval_f1": 0.8467153284671534,
+      "eval_loss": 0.4036194682121277,
+      "eval_precision": 0.7931623931623931,
+      "eval_recall": 0.9080234833659491,
+      "eval_runtime": 32.108,
+      "eval_samples_per_second": 31.83,
+      "eval_steps_per_second": 0.997,
+      "step": 672
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 672,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "total_flos": 1649866380960.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9489576625421504,
+    "learning_rate": 0.00020749603056740112,
+    "num_train_epochs": 7,
+    "temperature": 28
+  }
+}

run-0/checkpoint-672/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8331ea07c172c96760b5e5803c65d803e6e6da860ef2aeb4c9d1e33d878a2a66
+size 4920

run-1/checkpoint-96/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-1/checkpoint-96/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3eb8876585d4fdb886e817abd3e35044d9b68fb1b7d8d76911fabe58f9f805d6
+size 17549312

run-1/checkpoint-96/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93ffb05974d21c274d2e8e93abf4dbb0cb083ae6447a156be16ba97bde6f701c
+size 35122746

run-1/checkpoint-96/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24aa86019b8aea1c551cc1adaf38c4db2fc01de75a22af312230f6b592e0fd81
+size 14054

run-1/checkpoint-96/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e62093bac88d33754205092ea3cdb062efeb0addb4275fda5cfa6489c8a3e16
+size 1064

run-1/checkpoint-96/special_tokens_map.json

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

run-1/checkpoint-96/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-1/checkpoint-96/trainer_state.json

@@ -0,0 +1,45 @@
+{
+  "best_metric": 0.7651663405088063,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-1/checkpoint-96",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 96,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.4932310581207275,
+      "learning_rate": 0.00022974033046670533,
+      "loss": 0.4667,
+      "step": 96
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7651663405088063,
+      "eval_f1": 0.7701149425287357,
+      "eval_loss": 0.4088786244392395,
+      "eval_precision": 0.7542213883677298,
+      "eval_recall": 0.786692759295499,
+      "eval_runtime": 30.971,
+      "eval_samples_per_second": 32.999,
+      "eval_steps_per_second": 1.033,
+      "step": 96
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 480,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 235695197280.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.6818846524061118,
+    "learning_rate": 0.00028717541308338166,
+    "num_train_epochs": 5,
+    "temperature": 29
+  }
+}

run-1/checkpoint-96/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:793b34e056c09ac6895e4854810a5a38ad5f7e4ea7bfcdaf2571ad59272936ff
+size 4920

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8331ea07c172c96760b5e5803c65d803e6e6da860ef2aeb4c9d1e33d878a2a66
+oid sha256:793b34e056c09ac6895e4854810a5a38ad5f7e4ea7bfcdaf2571ad59272936ff
 size 4920