Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:593ae89289d9d92e361ca2ceb9582a6f6b4c7fc7b4c7b9ae371f5bb3b67a40e1
+oid sha256:6a33f6af52515c9b232db426ae70cd0781e64260d8aa0084cc4eb33d3f812202
 size 437958648

run-6/checkpoint-16838/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.4,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.4,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "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-6/checkpoint-16838/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a33f6af52515c9b232db426ae70cd0781e64260d8aa0084cc4eb33d3f812202
+size 437958648

run-6/checkpoint-16838/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45656ec8e114749940ad11aaa284ac02f7be27ef0636bf510e998170610978e6
+size 876038394

run-6/checkpoint-16838/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9af226e732c97fde89f01fd2c516fa16b929601d73614f43176d1e07edfd7dd
+size 14308

run-6/checkpoint-16838/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b192d5274273f9f59eb18098ddbbb9e9b28a9ea3974e9eafed09a363051170e7
+size 1064

run-6/checkpoint-16838/special_tokens_map.json

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

run-6/checkpoint-16838/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": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-6/checkpoint-16838/trainer_state.json

@@ -0,0 +1,73 @@
+{
+  "best_metric": 0.9139908256880734,
+  "best_model_checkpoint": "Tech-oriented/best_model_bert_uncasedbert-base-uncased-finetuned-sst2/run-6/checkpoint-8419",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 16838,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5,
+      "grad_norm": 35.4764289855957,
+      "learning_rate": 1.4625672140464685e-05,
+      "loss": 0.452,
+      "step": 4209
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.615936040878296,
+      "learning_rate": 1.2536574029383954e-05,
+      "loss": 0.354,
+      "step": 8418
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9139908256880734,
+      "eval_loss": 0.36559009552001953,
+      "eval_runtime": 2.4317,
+      "eval_samples_per_second": 358.596,
+      "eval_steps_per_second": 22.618,
+      "step": 8419
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 1.231093406677246,
+      "learning_rate": 1.0447475918303226e-05,
+      "loss": 0.3236,
+      "step": 12627
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 66.64139556884766,
+      "learning_rate": 8.358377807222495e-06,
+      "loss": 0.303,
+      "step": 16836
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9025229357798165,
+      "eval_loss": 0.4449034631252289,
+      "eval_runtime": 2.4314,
+      "eval_samples_per_second": 358.637,
+      "eval_steps_per_second": 22.62,
+      "step": 16838
+    }
+  ],
+  "logging_steps": 4209,
+  "max_steps": 33676,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 3441334840253340.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.6714770251545413e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 8,
+    "seed": 32,
+    "weight_decay": 0.41710891288145024
+  }
+}

run-6/checkpoint-16838/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f473f968b7e87229e13a2aa91b256ae59a2f8fb544c7ea1c0d31b1fdaca756e5
+size 4984

runs/Mar06_18-14-36_e017d622c671/events.out.tfevents.1709764768.e017d622c671.539.6

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29e4b8170ff8208713642b930ac173476c12df8574fdc997ce0161b4d8c77647
-size 5496
+oid sha256:1e60fe196a10bba79322e4dd4bbd7a7c7a17e362ee82d11e3a137e17e7b35770
+size 6251