Training in progress, epoch 1

logs/events.out.tfevents.1713970842.a9ae8da52b57.4950.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25a958b71d2d16cc3e78da2740a530a4024544c100a928b553545c73c24c56cf
-size 5822
+oid sha256:83f00e3dd4cab71124258bb32f5c87e7e538adbedc60a1d7d676e1e3d7a3ad67
+size 9380

logs/events.out.tfevents.1713972412.a9ae8da52b57.4950.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:515aaa5d5b808698e8d7f876d48e5bf223cc149fdc0d63f24cefa9d7006364f8
+size 5287

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef8a53367281448355780b7b0fdefb481ca9d156d7d13aa415fe1c61860e1f26
+oid sha256:cc24eccafea43a9890bdd4d965b6c0abc379519d1f79ffdc746d7439ac8fb2fc
 size 17549312

run-0/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": "4.40.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-0/checkpoint-3689/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b9991c8318e0500e923ff73ab15d77890f81ce9a1c8a5155bef2b550cc5c7b8
+size 17549312

run-0/checkpoint-3689/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c19a443faed29e9f7c624c2ad9ff4db2dda5dd8ba4b1231aa360ccf3d87dd45
+size 35123898

run-0/checkpoint-3689/rng_state.pth

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

run-0/checkpoint-3689/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edbb3dac49bfeec292c5bd637c4453b104a115375c5a01b41b9b1e66caafb239
+size 1064

run-0/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-0/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-0/checkpoint-3689/trainer_state.json

@@ -0,0 +1,138 @@
+{
+  "best_metric": 0.7844036697247706,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/checkpoint-2635",
+  "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": 17.1326904296875,
+      "learning_rate": 9.513173921403958e-06,
+      "loss": 3.6378,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6915137614678899,
+      "eval_loss": 3.044344902038574,
+      "eval_runtime": 2.6844,
+      "eval_samples_per_second": 324.846,
+      "eval_steps_per_second": 2.608,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": Infinity,
+      "learning_rate": 8.156727870263139e-06,
+      "loss": 2.9201,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7763761467889908,
+      "eval_loss": 2.3391239643096924,
+      "eval_runtime": 2.6931,
+      "eval_samples_per_second": 323.787,
+      "eval_steps_per_second": 2.599,
+      "step": 1054
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 45.30732345581055,
+      "learning_rate": 6.797703024348287e-06,
+      "loss": 2.3619,
+      "step": 1581
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7752293577981652,
+      "eval_loss": 2.095879554748535,
+      "eval_runtime": 2.7528,
+      "eval_samples_per_second": 316.768,
+      "eval_steps_per_second": 2.543,
+      "step": 1581
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 42.87710952758789,
+      "learning_rate": 5.4386781784334364e-06,
+      "loss": 2.0658,
+      "step": 2108
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7798165137614679,
+      "eval_loss": 1.9894497394561768,
+      "eval_runtime": 2.6956,
+      "eval_samples_per_second": 323.487,
+      "eval_steps_per_second": 2.597,
+      "step": 2108
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 24.316022872924805,
+      "learning_rate": 4.0796533325185855e-06,
+      "loss": 1.9068,
+      "step": 2635
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7844036697247706,
+      "eval_loss": 1.9175504446029663,
+      "eval_runtime": 2.6587,
+      "eval_samples_per_second": 327.984,
+      "eval_steps_per_second": 2.633,
+      "step": 2635
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 22.026918411254883,
+      "learning_rate": 2.723207281377766e-06,
+      "loss": 1.7844,
+      "step": 3162
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7844036697247706,
+      "eval_loss": 1.8753291368484497,
+      "eval_runtime": 2.7064,
+      "eval_samples_per_second": 322.195,
+      "eval_steps_per_second": 2.586,
+      "step": 3162
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 28.347148895263672,
+      "learning_rate": 1.3641824354629153e-06,
+      "loss": 1.7245,
+      "step": 3689
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.7844036697247706,
+      "eval_loss": 1.8515244722366333,
+      "eval_runtime": 2.7066,
+      "eval_samples_per_second": 322.171,
+      "eval_steps_per_second": 2.586,
+      "step": 3689
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4216,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "total_flos": 56628612372420.0,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.283430275721788,
+    "learning_rate": 1.0872198767318809e-05,
+    "num_train_epochs": 8,
+    "temperature": 13
+  }
+}

run-0/checkpoint-3689/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:685c5ca76e50efcbdad73bed43aea4bc7cc0fe066757f948d6ec7618865f3672
+size 5048

run-0/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": "4.40.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-0/checkpoint-4216/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c4f11014b1492f4244c5b7ad50dd95e62e9d03f68be73bfd5adb5311ce44534
+size 17549312

run-0/checkpoint-4216/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b517a3a8eb743a1e2217af964879dc99acd7c4e2c85599e63b232c715cf9fca
+size 35123898

run-0/checkpoint-4216/rng_state.pth

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

run-0/checkpoint-4216/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c45d3a74cd3e8c2ba393c07a93b0979e460b8019a3592fab539522d72eb31561
+size 1064

run-0/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-0/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-0/checkpoint-4216/trainer_state.json

@@ -0,0 +1,154 @@
+{
+  "best_metric": 0.7878440366972477,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/checkpoint-4216",
+  "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": 17.1326904296875,
+      "learning_rate": 9.513173921403958e-06,
+      "loss": 3.6378,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6915137614678899,
+      "eval_loss": 3.044344902038574,
+      "eval_runtime": 2.6844,
+      "eval_samples_per_second": 324.846,
+      "eval_steps_per_second": 2.608,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": Infinity,
+      "learning_rate": 8.156727870263139e-06,
+      "loss": 2.9201,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7763761467889908,
+      "eval_loss": 2.3391239643096924,
+      "eval_runtime": 2.6931,
+      "eval_samples_per_second": 323.787,
+      "eval_steps_per_second": 2.599,
+      "step": 1054
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 45.30732345581055,
+      "learning_rate": 6.797703024348287e-06,
+      "loss": 2.3619,
+      "step": 1581
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7752293577981652,
+      "eval_loss": 2.095879554748535,
+      "eval_runtime": 2.7528,
+      "eval_samples_per_second": 316.768,
+      "eval_steps_per_second": 2.543,
+      "step": 1581
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 42.87710952758789,
+      "learning_rate": 5.4386781784334364e-06,
+      "loss": 2.0658,
+      "step": 2108
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7798165137614679,
+      "eval_loss": 1.9894497394561768,
+      "eval_runtime": 2.6956,
+      "eval_samples_per_second": 323.487,
+      "eval_steps_per_second": 2.597,
+      "step": 2108
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 24.316022872924805,
+      "learning_rate": 4.0796533325185855e-06,
+      "loss": 1.9068,
+      "step": 2635
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7844036697247706,
+      "eval_loss": 1.9175504446029663,
+      "eval_runtime": 2.6587,
+      "eval_samples_per_second": 327.984,
+      "eval_steps_per_second": 2.633,
+      "step": 2635
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 22.026918411254883,
+      "learning_rate": 2.723207281377766e-06,
+      "loss": 1.7844,
+      "step": 3162
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7844036697247706,
+      "eval_loss": 1.8753291368484497,
+      "eval_runtime": 2.7064,
+      "eval_samples_per_second": 322.195,
+      "eval_steps_per_second": 2.586,
+      "step": 3162
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 28.347148895263672,
+      "learning_rate": 1.3641824354629153e-06,
+      "loss": 1.7245,
+      "step": 3689
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.7844036697247706,
+      "eval_loss": 1.8515244722366333,
+      "eval_runtime": 2.7066,
+      "eval_samples_per_second": 322.171,
+      "eval_steps_per_second": 2.586,
+      "step": 3689
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": Infinity,
+      "learning_rate": 7.736384322095927e-09,
+      "loss": 1.705,
+      "step": 4216
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.7878440366972477,
+      "eval_loss": 1.8409373760223389,
+      "eval_runtime": 2.6794,
+      "eval_samples_per_second": 325.446,
+      "eval_steps_per_second": 2.613,
+      "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": 0.283430275721788,
+    "learning_rate": 1.0872198767318809e-05,
+    "num_train_epochs": 8,
+    "temperature": 13
+  }
+}

run-0/checkpoint-4216/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:685c5ca76e50efcbdad73bed43aea4bc7cc0fe066757f948d6ec7618865f3672
+size 5048

run-1/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": "4.40.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-1/checkpoint-527/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc24eccafea43a9890bdd4d965b6c0abc379519d1f79ffdc746d7439ac8fb2fc
+size 17549312

run-1/checkpoint-527/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d384bbf3d41f0e47458ba9f69d17326e12d83103bd9281bee133584b1779283
+size 35123898

run-1/checkpoint-527/rng_state.pth

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

run-1/checkpoint-527/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12a6f3dd92736c7f9195c374b40969f60dded8b46a5e2be99124f35680f33a73
+size 1064

run-1/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-1/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-1/checkpoint-527/trainer_state.json

@@ -0,0 +1,42 @@
+{
+  "best_metric": 0.8360091743119266,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-1/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": 22.49123764038086,
+      "learning_rate": 0.0002780733463240362,
+      "loss": 1.7444,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8360091743119266,
+      "eval_loss": 1.752740740776062,
+      "eval_runtime": 2.7351,
+      "eval_samples_per_second": 318.815,
+      "eval_steps_per_second": 2.559,
+      "step": 527
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2635,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 8057768762220.0,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.08970692378937972,
+    "learning_rate": 0.0003475916829050453,
+    "num_train_epochs": 5,
+    "temperature": 30
+  }
+}

run-1/checkpoint-527/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2608572d74b285a65dbc7ad54bc17bf582a54f334d1b1780f3914acbfa4a4cbe
+size 5048

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:685c5ca76e50efcbdad73bed43aea4bc7cc0fe066757f948d6ec7618865f3672
+oid sha256:2608572d74b285a65dbc7ad54bc17bf582a54f334d1b1780f3914acbfa4a4cbe
 size 5048