Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eea5952683a4ccb8880831fd725cd0e1f4f7aab43e8da88bd66f0eef2b323306
+oid sha256:975253fc09918f473d63640e6b9a8ab53313c2f9d0e21d4f3fbab597786edba0
 size 267832560

run-0/checkpoint-268/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": "4.37.1",
+  "vocab_size": 30522
+}

run-0/checkpoint-268/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd87231dbdc2c18bf8611263cc5eecffc0d6c98c76b2a33ebc297876f4c51908
+size 267832560

run-0/checkpoint-268/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e354662c86b2a9a74866e910dc0ab776450c73dc31c368e23dbfd97c2516eafa
+size 535724410

run-0/checkpoint-268/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b4a577f9ff5c852a71d75ef2b039448ccd86e2f1f1e9946d82af7208afe9e24
+size 13990

run-0/checkpoint-268/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6a488cadf606fae9c058d6b628840d7cccda3610f1afa38a7f38cd091b9c8ab
+size 1064

run-0/checkpoint-268/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-268/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-0/checkpoint-268/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": 0.42386559425174,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-268",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 268,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.4662749767303467,
+      "eval_matthews_correlation": 0.42386559425174,
+      "eval_runtime": 30.5523,
+      "eval_samples_per_second": 34.138,
+      "eval_steps_per_second": 2.16,
+      "step": 268
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1072,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 7.330569795718295e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 32,
+    "seed": 19
+  }
+}

run-0/checkpoint-268/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d72f1b39c9effe99043a3e407e4dedd56e0eb00ce40829698b7ced9fd0a7ccf6
+size 4792

run-0/checkpoint-536/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": "4.37.1",
+  "vocab_size": 30522
+}

run-0/checkpoint-536/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:975253fc09918f473d63640e6b9a8ab53313c2f9d0e21d4f3fbab597786edba0
+size 267832560

run-0/checkpoint-536/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b269af20a228ed2acbcd932b190a84c1e1b205796fd12120a15e95835cbae46f
+size 535724410

run-0/checkpoint-536/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b7294d4941e3c560da9921cdd5858526b0dc22ba83174f054cd12e766ac4225
+size 13990

run-0/checkpoint-536/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc2beb8ed7f51ccd5867b9f21d1a3a06667fd18ba25ebc78ff63d4daf9f6c02e
+size 1064

run-0/checkpoint-536/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-536/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-0/checkpoint-536/trainer_state.json

@@ -0,0 +1,50 @@
+{
+  "best_metric": 0.48074996963903815,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-536",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 536,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.4662749767303467,
+      "eval_matthews_correlation": 0.42386559425174,
+      "eval_runtime": 30.5523,
+      "eval_samples_per_second": 34.138,
+      "eval_steps_per_second": 2.16,
+      "step": 268
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 3.9114607492078965e-05,
+      "loss": 0.425,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5247857570648193,
+      "eval_matthews_correlation": 0.48074996963903815,
+      "eval_runtime": 31.3458,
+      "eval_samples_per_second": 33.274,
+      "eval_steps_per_second": 2.106,
+      "step": 536
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1072,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 95542370006028.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 7.330569795718295e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 32,
+    "seed": 19
+  }
+}

run-0/checkpoint-536/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d72f1b39c9effe99043a3e407e4dedd56e0eb00ce40829698b7ced9fd0a7ccf6
+size 4792

runs/Jan26_08-04-50_7ac5f092fd85/events.out.tfevents.1706278490.7ac5f092fd85.1710.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:413278b464b8739b3765d4b0ddab93b913a1340411c535e089b229d00e271ce5
+size 5158

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63d852579470f5dd2639f004403d5670c16390b00a25f9b8179c7d252c76a607
+oid sha256:d72f1b39c9effe99043a3e407e4dedd56e0eb00ce40829698b7ced9fd0a7ccf6
 size 4792