Training in progress, epoch 4

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:252b0645497e59d11ebf0827d3b5651082677f43cc2b34ce52b847fa8a3b37f4
+oid sha256:792c1e28ef0895b481cbc5a84ce9da554b3b84f7fa42de1ba24c6a764bcefca1
 size 267832560

run-9/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": "4.36.2",
+  "vocab_size": 30522
+}

run-9/checkpoint-8552/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:792c1e28ef0895b481cbc5a84ce9da554b3b84f7fa42de1ba24c6a764bcefca1
+size 267832560

run-9/checkpoint-8552/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55c5c5d7f8f96a3777df7481a020a5dda77c73b9113d5c8f602f7e55399a5595
+size 535727290

run-9/checkpoint-8552/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e045e82e93d9055d857764b5860c82d59187eb9b8d62c054e239387a096e84d
+size 14308

run-9/checkpoint-8552/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c01f24a355884731885349d22707381654702930b4202fb497b4b3db211e4e5e
+size 1064

run-9/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-9/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-9/checkpoint-8552/trainer_state.json

@@ -0,0 +1,164 @@
+{
+  "best_metric": 0.5085739436587455,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-9/checkpoint-6414",
+  "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": 0.23,
+      "learning_rate": 2.4756314159255174e-05,
+      "loss": 0.6193,
+      "step": 500
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 2.3219036826961632e-05,
+      "loss": 0.5585,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 2.1681759494668092e-05,
+      "loss": 0.5666,
+      "step": 1500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.0144482162374553e-05,
+      "loss": 0.5675,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6569426655769348,
+      "eval_matthews_correlation": 0.4227320658781353,
+      "eval_runtime": 0.7268,
+      "eval_samples_per_second": 1435.065,
+      "eval_steps_per_second": 90.81,
+      "step": 2138
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.8607204830081014e-05,
+      "loss": 0.4882,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.706992749778747e-05,
+      "loss": 0.4369,
+      "step": 3000
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 1.5532650165493932e-05,
+      "loss": 0.4617,
+      "step": 3500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.399537283320039e-05,
+      "loss": 0.4431,
+      "step": 4000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.8103704452514648,
+      "eval_matthews_correlation": 0.47958645804826155,
+      "eval_runtime": 0.7309,
+      "eval_samples_per_second": 1427.024,
+      "eval_steps_per_second": 90.301,
+      "step": 4276
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 1.245809550090685e-05,
+      "loss": 0.3617,
+      "step": 4500
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 1.092081816861331e-05,
+      "loss": 0.273,
+      "step": 5000
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 9.38354083631977e-06,
+      "loss": 0.3113,
+      "step": 5500
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 7.846263504026229e-06,
+      "loss": 0.2781,
+      "step": 6000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.0193597078323364,
+      "eval_matthews_correlation": 0.5085739436587455,
+      "eval_runtime": 0.7288,
+      "eval_samples_per_second": 1431.152,
+      "eval_steps_per_second": 90.562,
+      "step": 6414
+    },
+    {
+      "epoch": 3.04,
+      "learning_rate": 6.308986171732689e-06,
+      "loss": 0.2536,
+      "step": 6500
+    },
+    {
+      "epoch": 3.27,
+      "learning_rate": 4.771708839439149e-06,
+      "loss": 0.1707,
+      "step": 7000
+    },
+    {
+      "epoch": 3.51,
+      "learning_rate": 3.2344315071456087e-06,
+      "loss": 0.1652,
+      "step": 7500
+    },
+    {
+      "epoch": 3.74,
+      "learning_rate": 1.6971541748520686e-06,
+      "loss": 0.1255,
+      "step": 8000
+    },
+    {
+      "epoch": 3.98,
+      "learning_rate": 1.5987684255852818e-07,
+      "loss": 0.1883,
+      "step": 8500
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.2180700302124023,
+      "eval_matthews_correlation": 0.507418402843566,
+      "eval_runtime": 0.7358,
+      "eval_samples_per_second": 1417.466,
+      "eval_steps_per_second": 89.696,
+      "step": 8552
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 8552,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 138798926351136.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.6293591491548714e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 4,
+    "seed": 37
+  }
+}

run-9/checkpoint-8552/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d7f90b376166285bdadbbcc6bcdd97137714d15514517ba081d36c394405082
+size 4792

runs/Dec23_02-11-14_9e1ba8448b92/events.out.tfevents.1703298721.9e1ba8448b92.4051.11

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e665945000a6e065eec8b111cf63acb532ae7d48763248c0c7750427641efa6
-size 7704
+oid sha256:e18c3de8895aeb0843955ce7370b228aa2b97b5726067f1039996d1ab957f005
+size 8707