Training in progress, epoch 1

logs/events.out.tfevents.1711282685.73e3a81c01ef.4225.12

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6416e9d93272fee8ea5a186d9f36296f2750b88eb753c3f78f341a09c3a9d02
-size 6137
+oid sha256:c0cb6f44033edbda4bbee3cf57ceb7123955381b894a3ab6928f3be1bfad6f42
+size 10141

logs/events.out.tfevents.1711284651.73e3a81c01ef.4225.13

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:284c4b74ef7bf035b31a429961c7bddce0b7ef0a8df4f35e90778131500f74e1
+size 5406

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b660c3145a24c104b2234fb16de7ef451eb254eeb869faf043b2b340f3b84acc
+oid sha256:a6d4a7a835de9ad3ca145c3316bf66668b0f1f3a97275581ed4d381186446959
 size 17549312

run-12/checkpoint-1344/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": "4.39.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-12/checkpoint-1344/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b039ac14eadbb072e671bb56cd16e0e8df739611bd4dda196e61b9b85e1a7a30
+size 17549312

run-12/checkpoint-1344/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84cb521edc445c3765c05cc1aff2694d6caa5d045930cce1a1066837d0c90659
+size 35122746

run-12/checkpoint-1344/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5daa194f252973a6e638902bc960b7e07ea23884d291e0a3c2a48ccf865c60f8
+size 14054

run-12/checkpoint-1344/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1f69d45c03f178f9486b4a1583ea92d9ed490b542ba8a75029af2dbf6a14ee8
+size 1064

run-12/checkpoint-1344/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-1344/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-1344/trainer_state.json

@@ -0,0 +1,167 @@
+{
+  "best_metric": 0.8209393346379648,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-12/checkpoint-768",
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 1344,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.9969735741615295,
+      "learning_rate": 0.0003519988357465585,
+      "loss": 0.4838,
+      "step": 192
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7915851272015656,
+      "eval_f1": 0.8149435273675064,
+      "eval_loss": 0.4351368844509125,
+      "eval_mcc": 0.6026908465743466,
+      "eval_precision": 0.7328125,
+      "eval_recall": 0.9178082191780822,
+      "eval_runtime": 66.7179,
+      "eval_samples_per_second": 15.318,
+      "eval_steps_per_second": 0.48,
+      "step": 192
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 9.071135520935059,
+      "learning_rate": 0.0002933323631221321,
+      "loss": 0.435,
+      "step": 384
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7954990215264188,
+      "eval_f1": 0.7956989247311829,
+      "eval_loss": 0.42000794410705566,
+      "eval_mcc": 0.5909991747116098,
+      "eval_precision": 0.794921875,
+      "eval_recall": 0.7964774951076321,
+      "eval_runtime": 66.4436,
+      "eval_samples_per_second": 15.381,
+      "eval_steps_per_second": 0.482,
+      "step": 384
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 3.5558242797851562,
+      "learning_rate": 0.00023466589049770566,
+      "loss": 0.4107,
+      "step": 576
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8101761252446184,
+      "eval_f1": 0.8255395683453237,
+      "eval_loss": 0.4215203523635864,
+      "eval_mcc": 0.6302037430382941,
+      "eval_precision": 0.7637271214642263,
+      "eval_recall": 0.898238747553816,
+      "eval_runtime": 66.249,
+      "eval_samples_per_second": 15.427,
+      "eval_steps_per_second": 0.483,
+      "step": 576
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 3.956291437149048,
+      "learning_rate": 0.00017599941787327925,
+      "loss": 0.4095,
+      "step": 768
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8209393346379648,
+      "eval_f1": 0.8271954674220963,
+      "eval_loss": 0.4081785976886749,
+      "eval_mcc": 0.6435679288765915,
+      "eval_precision": 0.7992700729927007,
+      "eval_recall": 0.8571428571428571,
+      "eval_runtime": 66.2882,
+      "eval_samples_per_second": 15.418,
+      "eval_steps_per_second": 0.483,
+      "step": 768
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 5.7001824378967285,
+      "learning_rate": 0.00011733294524885283,
+      "loss": 0.3959,
+      "step": 960
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8170254403131115,
+      "eval_f1": 0.826046511627907,
+      "eval_loss": 0.41252297163009644,
+      "eval_mcc": 0.6374890350533482,
+      "eval_precision": 0.7872340425531915,
+      "eval_recall": 0.8688845401174168,
+      "eval_runtime": 66.4475,
+      "eval_samples_per_second": 15.381,
+      "eval_steps_per_second": 0.482,
+      "step": 960
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 1.9468530416488647,
+      "learning_rate": 5.8666472624426415e-05,
+      "loss": 0.3889,
+      "step": 1152
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8160469667318982,
+      "eval_f1": 0.8324420677361855,
+      "eval_loss": 0.40997278690338135,
+      "eval_mcc": 0.6445565206113043,
+      "eval_precision": 0.7643207855973814,
+      "eval_recall": 0.913894324853229,
+      "eval_runtime": 66.9893,
+      "eval_samples_per_second": 15.256,
+      "eval_steps_per_second": 0.478,
+      "step": 1152
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 1.8196734189987183,
+      "learning_rate": 0.0,
+      "loss": 0.3804,
+      "step": 1344
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8209393346379648,
+      "eval_f1": 0.8297674418604651,
+      "eval_loss": 0.405351847410202,
+      "eval_mcc": 0.6453592700540068,
+      "eval_precision": 0.7907801418439716,
+      "eval_recall": 0.87279843444227,
+      "eval_runtime": 66.7109,
+      "eval_samples_per_second": 15.32,
+      "eval_steps_per_second": 0.48,
+      "step": 1344
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1344,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "total_flos": 1649866380960.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.7654129557516562,
+    "learning_rate": 0.00041066530837098494,
+    "num_train_epochs": 7,
+    "per_device_train_batch_size": 16,
+    "temperature": 40
+  }
+}

run-12/checkpoint-1344/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d85b6e817a8acea631d86d5c2c6470764f0dfa446cf60f01180ee7e29f4e646c
+size 4984

run-12/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": "4.39.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-12/checkpoint-768/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ba355a9ef5e2ecf5c10dd2eacc55b84160bc53df00036ef8e6cdd59b52bffe5
+size 17549312

run-12/checkpoint-768/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de2b9bd53924add6a7cb5c791645bdc2bd8923a81c576e279eab182ff0305851
+size 35122746

run-12/checkpoint-768/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ed72394efd052c27a025cbbb902950bb9336778a32545e8b891d3c9c80c35d9
+size 14054

run-12/checkpoint-768/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b32e52327f61d33ad8b0b078ac5fa542177730eaa0a4d09322d2f83092c50bae
+size 1064

run-12/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-12/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-12/checkpoint-768/trainer_state.json

@@ -0,0 +1,107 @@
+{
+  "best_metric": 0.8209393346379648,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-12/checkpoint-768",
+  "epoch": 4.0,
+  "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": 0.9969735741615295,
+      "learning_rate": 0.0003519988357465585,
+      "loss": 0.4838,
+      "step": 192
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7915851272015656,
+      "eval_f1": 0.8149435273675064,
+      "eval_loss": 0.4351368844509125,
+      "eval_mcc": 0.6026908465743466,
+      "eval_precision": 0.7328125,
+      "eval_recall": 0.9178082191780822,
+      "eval_runtime": 66.7179,
+      "eval_samples_per_second": 15.318,
+      "eval_steps_per_second": 0.48,
+      "step": 192
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 9.071135520935059,
+      "learning_rate": 0.0002933323631221321,
+      "loss": 0.435,
+      "step": 384
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7954990215264188,
+      "eval_f1": 0.7956989247311829,
+      "eval_loss": 0.42000794410705566,
+      "eval_mcc": 0.5909991747116098,
+      "eval_precision": 0.794921875,
+      "eval_recall": 0.7964774951076321,
+      "eval_runtime": 66.4436,
+      "eval_samples_per_second": 15.381,
+      "eval_steps_per_second": 0.482,
+      "step": 384
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 3.5558242797851562,
+      "learning_rate": 0.00023466589049770566,
+      "loss": 0.4107,
+      "step": 576
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8101761252446184,
+      "eval_f1": 0.8255395683453237,
+      "eval_loss": 0.4215203523635864,
+      "eval_mcc": 0.6302037430382941,
+      "eval_precision": 0.7637271214642263,
+      "eval_recall": 0.898238747553816,
+      "eval_runtime": 66.249,
+      "eval_samples_per_second": 15.427,
+      "eval_steps_per_second": 0.483,
+      "step": 576
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 3.956291437149048,
+      "learning_rate": 0.00017599941787327925,
+      "loss": 0.4095,
+      "step": 768
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8209393346379648,
+      "eval_f1": 0.8271954674220963,
+      "eval_loss": 0.4081785976886749,
+      "eval_mcc": 0.6435679288765915,
+      "eval_precision": 0.7992700729927007,
+      "eval_recall": 0.8571428571428571,
+      "eval_runtime": 66.2882,
+      "eval_samples_per_second": 15.418,
+      "eval_steps_per_second": 0.483,
+      "step": 768
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1344,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "total_flos": 942780789120.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.7654129557516562,
+    "learning_rate": 0.00041066530837098494,
+    "num_train_epochs": 7,
+    "per_device_train_batch_size": 16,
+    "temperature": 40
+  }
+}

run-12/checkpoint-768/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d85b6e817a8acea631d86d5c2c6470764f0dfa446cf60f01180ee7e29f4e646c
+size 4984

run-13/checkpoint-192/config.json

@@ -27,7 +27,7 @@
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
   "torch_dtype": "float32",
-  "transformers_version": "4.38.2",
+  "transformers_version": "4.39.1",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 30522

run-13/checkpoint-192/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec936bdbd05fce36e04feb9175016a668f2656862e3ebe1e41b08d9b168c218e
+oid sha256:a6d4a7a835de9ad3ca145c3316bf66668b0f1f3a97275581ed4d381186446959
 size 17549312

run-13/checkpoint-192/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62d7a984e692c1ceefc8287215564d0a0f0933154db48c4b07e90b01eec7f910
+oid sha256:8430bb3982d5333762da6c451b24a06a006891d84a9ea8dbbf0a139587d29f51
 size 35122746

run-13/checkpoint-192/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d267b33c0df8c744bb62ca8fc0e243d0ddded8c46ea62639c56f51d1dc7a548
+oid sha256:ee09ea0d216727b799a80771850b95d7d61b646360702c64b2ec889cdc725399
 size 14054

run-13/checkpoint-192/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25ebf2e2a39f7392b671af90dbfc3dcf5c6d20071895936fbcc160751e900b77
+oid sha256:6ddce8a986910e81370dbd5660d956251d083d802e55f85598ff417f12caec60
 size 1064

run-13/checkpoint-192/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_metric": 0.8160469667318982,
+  "best_metric": 0.7152641878669276,
   "best_model_checkpoint": "tiny-bert-sst2-distilled/run-13/checkpoint-192",
-  "epoch": 4.0,
+  "epoch": 1.0,
   "eval_steps": 500,
   "global_step": 192,
   "is_hyper_param_search": true,
@@ -10,93 +10,38 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 1.1932880878448486,
-      "learning_rate": 0.00031905315423317427,
-      "loss": 0.5324,
-      "step": 48
-    },
-    {
-      "epoch": 1.0,
-      "eval_accuracy": 0.7514677103718199,
-      "eval_f1": 0.7897350993377483,
-      "eval_loss": 0.4841874837875366,
-      "eval_precision": 0.6843615494978479,
-      "eval_recall": 0.9334637964774951,
-      "eval_runtime": 27.3845,
-      "eval_samples_per_second": 37.32,
-      "eval_steps_per_second": 0.584,
-      "step": 48
-    },
-    {
-      "epoch": 2.0,
-      "grad_norm": 5.759732723236084,
-      "learning_rate": 0.0002552425233865394,
-      "loss": 0.4624,
-      "step": 96
-    },
-    {
-      "epoch": 2.0,
-      "eval_accuracy": 0.7720156555772995,
-      "eval_f1": 0.762487257900102,
-      "eval_loss": 0.43731480836868286,
-      "eval_precision": 0.7957446808510639,
-      "eval_recall": 0.7318982387475538,
-      "eval_runtime": 27.3758,
-      "eval_samples_per_second": 37.332,
-      "eval_steps_per_second": 0.584,
-      "step": 96
-    },
-    {
-      "epoch": 3.0,
-      "grad_norm": 1.5165303945541382,
-      "learning_rate": 0.00019143189253990455,
-      "loss": 0.4346,
-      "step": 144
-    },
-    {
-      "epoch": 3.0,
-      "eval_accuracy": 0.8091976516634051,
-      "eval_f1": 0.8133971291866028,
-      "eval_loss": 0.4113065004348755,
-      "eval_precision": 0.795880149812734,
-      "eval_recall": 0.8317025440313112,
-      "eval_runtime": 26.8327,
-      "eval_samples_per_second": 38.088,
-      "eval_steps_per_second": 0.596,
-      "step": 144
-    },
-    {
-      "epoch": 4.0,
-      "grad_norm": 2.3469491004943848,
-      "learning_rate": 0.0001276212616932697,
-      "loss": 0.4143,
+      "grad_norm": 1.2103345394134521,
+      "learning_rate": 0.0007303245817667495,
+      "loss": 0.5045,
       "step": 192
     },
     {
-      "epoch": 4.0,
-      "eval_accuracy": 0.8160469667318982,
-      "eval_f1": 0.821969696969697,
-      "eval_loss": 0.39889204502105713,
-      "eval_precision": 0.7963302752293578,
-      "eval_recall": 0.8493150684931506,
-      "eval_runtime": 27.0864,
-      "eval_samples_per_second": 37.731,
-      "eval_steps_per_second": 0.591,
+      "epoch": 1.0,
+      "eval_accuracy": 0.7152641878669276,
+      "eval_f1": 0.7390134529147983,
+      "eval_loss": 0.4673319160938263,
+      "eval_mcc": 0.43784064067818973,
+      "eval_precision": 0.6821192052980133,
+      "eval_recall": 0.8062622309197651,
+      "eval_runtime": 66.234,
+      "eval_samples_per_second": 15.43,
+      "eval_steps_per_second": 0.483,
       "step": 192
     }
   ],
   "logging_steps": 500,
-  "max_steps": 288,
+  "max_steps": 768,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 6,
+  "num_train_epochs": 4,
   "save_steps": 500,
-  "total_flos": 942780789120.0,
-  "train_batch_size": 64,
+  "total_flos": 235695197280.0,
+  "train_batch_size": 16,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.804266474524187,
-    "learning_rate": 0.0003828637850798091,
-    "num_train_epochs": 6,
-    "temperature": 12
+    "alpha": 0.7599505594326271,
+    "learning_rate": 0.0009737661090223328,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 16,
+    "temperature": 27
   }
 }

run-13/checkpoint-192/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f002440cabbefeb4455cfed69099363d2aa36dc476d0817c5f461e40a0d9c304
-size 4920
+oid sha256:52d46ee5b8882f3f740b90052dba90a4aa730ef1bbac5b08a1bf876e2216e432
+size 4984

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d85b6e817a8acea631d86d5c2c6470764f0dfa446cf60f01180ee7e29f4e646c
+oid sha256:52d46ee5b8882f3f740b90052dba90a4aa730ef1bbac5b08a1bf876e2216e432
 size 4984