Training in progress, epoch 4

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0002ebee0bd754647b0905f16600e79d1f9860257fe829262f4b9e7204565a5
+oid sha256:c533140593174e95e64ef0a64025c6f2370e91c930140ea074dc5d8f7b570259
 size 267832560

run-3/checkpoint-8552/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "vocab_size": 30522
+}

run-3/checkpoint-8552/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c533140593174e95e64ef0a64025c6f2370e91c930140ea074dc5d8f7b570259
+size 267832560

run-3/checkpoint-8552/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f923959f43833e596af836a40a4176855bc96b31e04db2f18fb8a7106c669a43
+size 535727290

run-3/checkpoint-8552/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09a69cc9c8417161a72d6296931407c41855d5e8e03476149541fce72fa9ad9c
+size 14244

run-3/checkpoint-8552/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83355240f67c42e0f017cfeb3e6c978fbc0c50b6911dc224db7a3a4823c9193e
+size 1064

run-3/checkpoint-8552/special_tokens_map.json

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

run-3/checkpoint-8552/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-3/checkpoint-8552/trainer_state.json

@@ -0,0 +1,193 @@
+{
+  "best_metric": 0.44602012183933715,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-8552",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 8552,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23386342376052385,
+      "grad_norm": 5.5802998542785645,
+      "learning_rate": 3.2594792755956787e-05,
+      "loss": 0.6107,
+      "step": 500
+    },
+    {
+      "epoch": 0.4677268475210477,
+      "grad_norm": 9.347123146057129,
+      "learning_rate": 3.0570774328488035e-05,
+      "loss": 0.6033,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7015902712815716,
+      "grad_norm": 8.453703880310059,
+      "learning_rate": 2.8546755901019283e-05,
+      "loss": 0.5638,
+      "step": 1500
+    },
+    {
+      "epoch": 0.9354536950420954,
+      "grad_norm": 22.564891815185547,
+      "learning_rate": 2.652273747355053e-05,
+      "loss": 0.5621,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6280548572540283,
+      "eval_matthews_correlation": 0.40366439212980376,
+      "eval_runtime": 0.746,
+      "eval_samples_per_second": 1398.063,
+      "eval_steps_per_second": 88.468,
+      "step": 2138
+    },
+    {
+      "epoch": 1.1693171188026192,
+      "grad_norm": 32.08448791503906,
+      "learning_rate": 2.449871904608178e-05,
+      "loss": 0.4895,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4031805425631432,
+      "grad_norm": 142.33758544921875,
+      "learning_rate": 2.2474700618613024e-05,
+      "loss": 0.4803,
+      "step": 3000
+    },
+    {
+      "epoch": 1.637043966323667,
+      "grad_norm": 0.26033705472946167,
+      "learning_rate": 2.0450682191144272e-05,
+      "loss": 0.496,
+      "step": 3500
+    },
+    {
+      "epoch": 1.8709073900841908,
+      "grad_norm": 0.21774961054325104,
+      "learning_rate": 1.842666376367552e-05,
+      "loss": 0.4973,
+      "step": 4000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.7891594171524048,
+      "eval_matthews_correlation": 0.4205775146937564,
+      "eval_runtime": 0.7577,
+      "eval_samples_per_second": 1376.591,
+      "eval_steps_per_second": 87.109,
+      "step": 4276
+    },
+    {
+      "epoch": 2.1047708138447145,
+      "grad_norm": 153.6420135498047,
+      "learning_rate": 1.6402645336206768e-05,
+      "loss": 0.3969,
+      "step": 4500
+    },
+    {
+      "epoch": 2.3386342376052385,
+      "grad_norm": 6.752998352050781,
+      "learning_rate": 1.4378626908738016e-05,
+      "loss": 0.3002,
+      "step": 5000
+    },
+    {
+      "epoch": 2.5724976613657624,
+      "grad_norm": 0.23360666632652283,
+      "learning_rate": 1.2354608481269264e-05,
+      "loss": 0.3187,
+      "step": 5500
+    },
+    {
+      "epoch": 2.8063610851262863,
+      "grad_norm": 0.040108609944581985,
+      "learning_rate": 1.033059005380051e-05,
+      "loss": 0.2948,
+      "step": 6000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.0743186473846436,
+      "eval_matthews_correlation": 0.43324727666295126,
+      "eval_runtime": 0.8224,
+      "eval_samples_per_second": 1268.249,
+      "eval_steps_per_second": 80.254,
+      "step": 6414
+    },
+    {
+      "epoch": 3.0402245088868103,
+      "grad_norm": 28.617097854614258,
+      "learning_rate": 8.30657162633176e-06,
+      "loss": 0.3157,
+      "step": 6500
+    },
+    {
+      "epoch": 3.2740879326473338,
+      "grad_norm": 0.022375483065843582,
+      "learning_rate": 6.282553198863007e-06,
+      "loss": 0.1711,
+      "step": 7000
+    },
+    {
+      "epoch": 3.5079513564078577,
+      "grad_norm": 0.04736020788550377,
+      "learning_rate": 4.258534771394255e-06,
+      "loss": 0.183,
+      "step": 7500
+    },
+    {
+      "epoch": 3.7418147801683816,
+      "grad_norm": 0.016091570258140564,
+      "learning_rate": 2.2345163439255026e-06,
+      "loss": 0.1847,
+      "step": 8000
+    },
+    {
+      "epoch": 3.9756782039289056,
+      "grad_norm": 0.029599422588944435,
+      "learning_rate": 2.1049791645675023e-07,
+      "loss": 0.2136,
+      "step": 8500
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.2531371116638184,
+      "eval_matthews_correlation": 0.44602012183933715,
+      "eval_runtime": 0.8826,
+      "eval_samples_per_second": 1181.734,
+      "eval_steps_per_second": 74.779,
+      "step": 8552
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 8552,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 138709407366888.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.461881118342554e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 4,
+    "seed": 15
+  }
+}

run-3/checkpoint-8552/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07dab171a7cb748251ce8519a5f38719459c9164b11e2b6b4c6cf96155df3e53
+size 5176

runs/Aug28_15-48-15_c15c80b486ff/events.out.tfevents.1724861243.c15c80b486ff.424.5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd6becbf6ced829c7a6dcfe3ce2f78c26ce63f3c78bfbda070717ef77eef2cbe
-size 8772
+oid sha256:837ff923bd9a0d641fb71c05d1f70ef990d1064970771b6e22008478264dc6fa
+size 10094