Training in progress, epoch 1

logs/events.out.tfevents.1709706236.a2333cf40ebd.21010.38

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f048fba88c39fae7f3c05051a9e6ab54dc7d386a089ef9c1f3d141ebc0b671a7
-size 5998
+oid sha256:1c6c20c442afa63f5bc1ddf3c5e36749080a36e5d527a320d69778ad1244d91e
+size 11133

logs/events.out.tfevents.1709707289.a2333cf40ebd.21010.39

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:332c6bf58d1d74f79ed8c099b721c3ec9ec049277746e10ae3ea75896da5d74e
+size 5314

logs/events.out.tfevents.1709707402.a2333cf40ebd.21010.40

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb432dbcdfd98db5e5bc4facfaa749f97c717c2c6e05683c5a29ef6dd060905e
+size 5315

logs/events.out.tfevents.1709707514.a2333cf40ebd.21010.41

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfa8c1498e201bd3a30de466fb607872f802977cdaa65610c8ff3d9ec4a3316c
+size 5314

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7013e4613787fffb2187f1262a3607aff9a475fd1154360bfd1efeb805ed4a0
+oid sha256:09ba047a380994384e599e41981d871ceaba0d611aa17668901a037a269e6885
 size 17549312

run-38/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-38/checkpoint-768/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7c075f9376838dd854bad9b663d212f18c2fa695b9b07ad77aa39f337417ff6
+size 17549312

run-38/checkpoint-768/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cfc29054deb2252a2b2b07a8d316b54cc2a7ce77f35631c2ac3203b82bf288e
+size 35122746

run-38/checkpoint-768/rng_state.pth

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

run-38/checkpoint-768/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33b9cdc2824d0195ea494e67364be656fbf077e4d0f425d30170195948542637
+size 1064

run-38/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-38/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-38/checkpoint-768/trainer_state.json

@@ -0,0 +1,178 @@
+{
+  "best_metric": 0.8307240704500979,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-38/checkpoint-672",
+  "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": 1.8633686304092407,
+      "learning_rate": 0.00011164310281576651,
+      "loss": 0.584,
+      "step": 96
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7690802348336595,
+      "eval_f1": 0.7993197278911565,
+      "eval_loss": 0.48832422494888306,
+      "eval_precision": 0.706766917293233,
+      "eval_recall": 0.9197651663405088,
+      "eval_runtime": 28.3969,
+      "eval_samples_per_second": 35.99,
+      "eval_steps_per_second": 1.127,
+      "step": 96
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.9557557106018066,
+      "learning_rate": 9.76877149637957e-05,
+      "loss": 0.4827,
+      "step": 192
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8003913894324853,
+      "eval_f1": 0.8222996515679443,
+      "eval_loss": 0.44451940059661865,
+      "eval_precision": 0.7409733124018838,
+      "eval_recall": 0.923679060665362,
+      "eval_runtime": 28.5294,
+      "eval_samples_per_second": 35.823,
+      "eval_steps_per_second": 1.122,
+      "step": 192
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 3.0629470348358154,
+      "learning_rate": 8.373232711182488e-05,
+      "loss": 0.448,
+      "step": 288
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.824853228962818,
+      "eval_f1": 0.8353265869365226,
+      "eval_loss": 0.4216720759868622,
+      "eval_precision": 0.7881944444444444,
+      "eval_recall": 0.8884540117416829,
+      "eval_runtime": 28.7944,
+      "eval_samples_per_second": 35.493,
+      "eval_steps_per_second": 1.111,
+      "step": 288
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 5.688210964202881,
+      "learning_rate": 6.977693925985407e-05,
+      "loss": 0.4341,
+      "step": 384
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8209393346379648,
+      "eval_f1": 0.825214899713467,
+      "eval_loss": 0.42298367619514465,
+      "eval_precision": 0.8059701492537313,
+      "eval_recall": 0.8454011741682974,
+      "eval_runtime": 28.2399,
+      "eval_samples_per_second": 36.19,
+      "eval_steps_per_second": 1.133,
+      "step": 384
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 2.334526300430298,
+      "learning_rate": 5.5821551407883254e-05,
+      "loss": 0.4202,
+      "step": 480
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8287671232876712,
+      "eval_f1": 0.8436103663985702,
+      "eval_loss": 0.4076910614967346,
+      "eval_precision": 0.7763157894736842,
+      "eval_recall": 0.923679060665362,
+      "eval_runtime": 28.534,
+      "eval_samples_per_second": 35.817,
+      "eval_steps_per_second": 1.121,
+      "step": 480
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 4.195997714996338,
+      "learning_rate": 4.186616355591244e-05,
+      "loss": 0.4109,
+      "step": 576
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8258317025440313,
+      "eval_f1": 0.842756183745583,
+      "eval_loss": 0.4115942418575287,
+      "eval_precision": 0.7681159420289855,
+      "eval_recall": 0.9334637964774951,
+      "eval_runtime": 28.3073,
+      "eval_samples_per_second": 36.104,
+      "eval_steps_per_second": 1.13,
+      "step": 576
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 2.727288007736206,
+      "learning_rate": 2.7910775703941627e-05,
+      "loss": 0.4017,
+      "step": 672
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8307240704500979,
+      "eval_f1": 0.8467670504871568,
+      "eval_loss": 0.41019657254219055,
+      "eval_precision": 0.7734627831715211,
+      "eval_recall": 0.9354207436399217,
+      "eval_runtime": 28.5087,
+      "eval_samples_per_second": 35.849,
+      "eval_steps_per_second": 1.122,
+      "step": 672
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 3.721353530883789,
+      "learning_rate": 1.3955387851970814e-05,
+      "loss": 0.4014,
+      "step": 768
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8258317025440313,
+      "eval_f1": 0.8405017921146953,
+      "eval_loss": 0.40405774116516113,
+      "eval_precision": 0.775206611570248,
+      "eval_recall": 0.9178082191780822,
+      "eval_runtime": 28.5925,
+      "eval_samples_per_second": 35.744,
+      "eval_steps_per_second": 1.119,
+      "step": 768
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 864,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9,
+  "save_steps": 500,
+  "total_flos": 1885561578240.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.8898885181069172,
+    "learning_rate": 0.00012559849066773733,
+    "num_train_epochs": 9,
+    "temperature": 3
+  }
+}

run-38/checkpoint-768/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b78761570f9c0a3dc21081804a93e4de0e1f3e64d53a0de9de90979115cf843
+size 4920

run-38/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-38/checkpoint-864/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43db1fd5d3f19d7b8fcda0786a447b68edfe4423b6f57f36894a2441888274d4
+size 17549312

run-38/checkpoint-864/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32dc1db2518031f32f191e060de1dcf3534a7ef5e1dc09e2ef3d815ccd734f31
+size 35122746

run-38/checkpoint-864/rng_state.pth

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

run-38/checkpoint-864/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1c767b67be61953b062a731e55c384231b3fc13be9849b3f5ac623b9b0f7464
+size 1064

run-38/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-38/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-38/checkpoint-864/trainer_state.json

@@ -0,0 +1,197 @@
+{
+  "best_metric": 0.8346379647749511,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-38/checkpoint-864",
+  "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": 1.8633686304092407,
+      "learning_rate": 0.00011164310281576651,
+      "loss": 0.584,
+      "step": 96
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7690802348336595,
+      "eval_f1": 0.7993197278911565,
+      "eval_loss": 0.48832422494888306,
+      "eval_precision": 0.706766917293233,
+      "eval_recall": 0.9197651663405088,
+      "eval_runtime": 28.3969,
+      "eval_samples_per_second": 35.99,
+      "eval_steps_per_second": 1.127,
+      "step": 96
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.9557557106018066,
+      "learning_rate": 9.76877149637957e-05,
+      "loss": 0.4827,
+      "step": 192
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8003913894324853,
+      "eval_f1": 0.8222996515679443,
+      "eval_loss": 0.44451940059661865,
+      "eval_precision": 0.7409733124018838,
+      "eval_recall": 0.923679060665362,
+      "eval_runtime": 28.5294,
+      "eval_samples_per_second": 35.823,
+      "eval_steps_per_second": 1.122,
+      "step": 192
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 3.0629470348358154,
+      "learning_rate": 8.373232711182488e-05,
+      "loss": 0.448,
+      "step": 288
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.824853228962818,
+      "eval_f1": 0.8353265869365226,
+      "eval_loss": 0.4216720759868622,
+      "eval_precision": 0.7881944444444444,
+      "eval_recall": 0.8884540117416829,
+      "eval_runtime": 28.7944,
+      "eval_samples_per_second": 35.493,
+      "eval_steps_per_second": 1.111,
+      "step": 288
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 5.688210964202881,
+      "learning_rate": 6.977693925985407e-05,
+      "loss": 0.4341,
+      "step": 384
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8209393346379648,
+      "eval_f1": 0.825214899713467,
+      "eval_loss": 0.42298367619514465,
+      "eval_precision": 0.8059701492537313,
+      "eval_recall": 0.8454011741682974,
+      "eval_runtime": 28.2399,
+      "eval_samples_per_second": 36.19,
+      "eval_steps_per_second": 1.133,
+      "step": 384
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 2.334526300430298,
+      "learning_rate": 5.5821551407883254e-05,
+      "loss": 0.4202,
+      "step": 480
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8287671232876712,
+      "eval_f1": 0.8436103663985702,
+      "eval_loss": 0.4076910614967346,
+      "eval_precision": 0.7763157894736842,
+      "eval_recall": 0.923679060665362,
+      "eval_runtime": 28.534,
+      "eval_samples_per_second": 35.817,
+      "eval_steps_per_second": 1.121,
+      "step": 480
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 4.195997714996338,
+      "learning_rate": 4.186616355591244e-05,
+      "loss": 0.4109,
+      "step": 576
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8258317025440313,
+      "eval_f1": 0.842756183745583,
+      "eval_loss": 0.4115942418575287,
+      "eval_precision": 0.7681159420289855,
+      "eval_recall": 0.9334637964774951,
+      "eval_runtime": 28.3073,
+      "eval_samples_per_second": 36.104,
+      "eval_steps_per_second": 1.13,
+      "step": 576
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 2.727288007736206,
+      "learning_rate": 2.7910775703941627e-05,
+      "loss": 0.4017,
+      "step": 672
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8307240704500979,
+      "eval_f1": 0.8467670504871568,
+      "eval_loss": 0.41019657254219055,
+      "eval_precision": 0.7734627831715211,
+      "eval_recall": 0.9354207436399217,
+      "eval_runtime": 28.5087,
+      "eval_samples_per_second": 35.849,
+      "eval_steps_per_second": 1.122,
+      "step": 672
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 3.721353530883789,
+      "learning_rate": 1.3955387851970814e-05,
+      "loss": 0.4014,
+      "step": 768
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8258317025440313,
+      "eval_f1": 0.8405017921146953,
+      "eval_loss": 0.40405774116516113,
+      "eval_precision": 0.775206611570248,
+      "eval_recall": 0.9178082191780822,
+      "eval_runtime": 28.5925,
+      "eval_samples_per_second": 35.744,
+      "eval_steps_per_second": 1.119,
+      "step": 768
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 2.3781871795654297,
+      "learning_rate": 0.0,
+      "loss": 0.3968,
+      "step": 864
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.8346379647749511,
+      "eval_f1": 0.8456621004566209,
+      "eval_loss": 0.4000749886035919,
+      "eval_precision": 0.7928082191780822,
+      "eval_recall": 0.9060665362035225,
+      "eval_runtime": 28.358,
+      "eval_samples_per_second": 36.039,
+      "eval_steps_per_second": 1.128,
+      "step": 864
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 864,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9,
+  "save_steps": 500,
+  "total_flos": 2121256775520.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.8898885181069172,
+    "learning_rate": 0.00012559849066773733,
+    "num_train_epochs": 9,
+    "temperature": 3
+  }
+}

run-38/checkpoint-864/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b78761570f9c0a3dc21081804a93e4de0e1f3e64d53a0de9de90979115cf843
+size 4920

run-41/checkpoint-96/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b45d5e15ea63304f1b5fcbf01b2f45b2628b1f0e85dedeebe8454ec1d471b9f4
+oid sha256:09ba047a380994384e599e41981d871ceaba0d611aa17668901a037a269e6885
 size 17549312

run-41/checkpoint-96/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:340328c24ba37b28a47af5dc4e7dac1bd6b82c120cc4818db1651822495770c3
+oid sha256:214c709048272cfa3ebfb6cf6d7c2a73cfae93d61a479d9bf9ef5c6f6948e1ac
 size 35122746

run-41/checkpoint-96/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9a1b9148001cd085549296a686e20fca05f21d76cbf29f2d694685ea3c0e90b
+oid sha256:4b75872ca4c3159c14e7c8d1b1d44dfee8a49c76e9913a14bfb4e11f84941d28
 size 1064

run-41/checkpoint-96/trainer_state.json

@@ -10,36 +10,36 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 2.904797315597534,
-      "learning_rate": 0.0001800620290766639,
-      "loss": 0.5678,
+      "grad_norm": 1.4870496988296509,
+      "learning_rate": 0.00011097537892965708,
+      "loss": 0.5464,
       "step": 96
     },
     {
       "epoch": 1.0,
       "eval_accuracy": 0.7749510763209393,
-      "eval_f1": 0.8060708263069141,
-      "eval_loss": 0.47195959091186523,
-      "eval_precision": 0.7081481481481482,
-      "eval_recall": 0.9354207436399217,
-      "eval_runtime": 32.7213,
-      "eval_samples_per_second": 31.233,
-      "eval_steps_per_second": 0.978,
+      "eval_f1": 0.8017241379310346,
+      "eval_loss": 0.4673503041267395,
+      "eval_precision": 0.7164869029275809,
+      "eval_recall": 0.9099804305283757,
+      "eval_runtime": 28.2108,
+      "eval_samples_per_second": 36.227,
+      "eval_steps_per_second": 1.134,
       "step": 96
     }
   ],
   "logging_steps": 500,
-  "max_steps": 288,
+  "max_steps": 864,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
+  "num_train_epochs": 9,
   "save_steps": 500,
   "total_flos": 235695197280.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.9482965338753422,
-    "learning_rate": 0.0002700930436149959,
-    "num_train_epochs": 3,
-    "temperature": 9
+    "alpha": 0.8078288065121237,
+    "learning_rate": 0.0001248473012958642,
+    "num_train_epochs": 9,
+    "temperature": 4
   }
 }

run-41/checkpoint-96/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a79ffddd3dbb36d7991e9db486bb85c65a0c011c05a4c2d55c9d8aaeca1b28f2
+oid sha256:9599a9eb05fb1abdd888ed4c4bfde1c3333a817ee2a411e437b9a1cf607a92ec
 size 4920

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b78761570f9c0a3dc21081804a93e4de0e1f3e64d53a0de9de90979115cf843
+oid sha256:9599a9eb05fb1abdd888ed4c4bfde1c3333a817ee2a411e437b9a1cf607a92ec
 size 4920