Training in progress, epoch 3

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b87e447afcc6450cb13ca14e3644e9d76788c936457f95dbb88373e764323c93
+oid sha256:097d83f7abfa7a086e971f1afb84acad12e5398bd9ed1ad294d5e26101fbdfaf
 size 437958648

run-1/checkpoint-1263/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "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-1/checkpoint-1263/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:097d83f7abfa7a086e971f1afb84acad12e5398bd9ed1ad294d5e26101fbdfaf
+size 437958648

run-1/checkpoint-1263/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a408b7eae7383e242fdf8c02049a4bcfc26bb23f4e9639ede84e3c8d8bd98fa
+size 876038394

run-1/checkpoint-1263/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:063ad9cbd28f3bc1c439727a778daf76083fbe7f187e4f5bd94f52e025dd74e3
+size 14244

run-1/checkpoint-1263/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6e623ec2092cf7d7cc03acd5da06e04c15dfda0a47f5c6f0292fe35df8ca2f9
+size 1064

run-1/checkpoint-1263/special_tokens_map.json

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

run-1/checkpoint-1263/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-1/checkpoint-1263/trainer_state.json

@@ -0,0 +1,67 @@
+{
+  "best_metric": 0.9231651376146789,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-sst2/run-1/checkpoint-421",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1263,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9231651376146789,
+      "eval_loss": 0.24830688536167145,
+      "eval_runtime": 2.2848,
+      "eval_samples_per_second": 381.657,
+      "eval_steps_per_second": 24.072,
+      "step": 421
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 1.174437165260315,
+      "learning_rate": 3.136892070081642e-05,
+      "loss": 0.3128,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9139908256880734,
+      "eval_loss": 0.3306081295013428,
+      "eval_runtime": 2.3075,
+      "eval_samples_per_second": 377.901,
+      "eval_steps_per_second": 23.835,
+      "step": 842
+    },
+    {
+      "epoch": 2.38,
+      "grad_norm": 14.713961601257324,
+      "learning_rate": 1.0812616178656248e-05,
+      "loss": 0.1105,
+      "step": 1000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9139908256880734,
+      "eval_loss": 0.4116528332233429,
+      "eval_runtime": 2.3531,
+      "eval_samples_per_second": 370.572,
+      "eval_steps_per_second": 23.373,
+      "step": 1263
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1263,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 291460243797480.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 5.192522522297658e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 16,
+    "seed": 6
+  }
+}

run-1/checkpoint-1263/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a42951e65bb3aa1e125b1b27e2a27b66ec94bb48bc4ff40d24214557a0e4b15
+size 4920

run-1/checkpoint-842/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da03c42f7d21e72fcf2e35495731396193ad69891d1c94620346f9ea1b114f41
+oid sha256:9854b3a5c1cd9a5d9c6ed2826e77d6a076648a46ca110e6211ee7cd8cdb15a73
 size 437958648

run-1/checkpoint-842/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ade1da78eee8738ba225255d5a5a3fdc8e2966a8198c67ef2833fd0d0fd3992b
+oid sha256:7c79fd1d85362acbc5103ae59788f6de68b11f471e6767d9cea573d5ce3cd535
 size 876038394

run-1/checkpoint-842/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3a63861dc396620edd4b11db54d670765bc44b1d879bdac9cfa099d89602994
-size 14308
+oid sha256:505ff0daefb21a6c8c2324f62a92aad54c4bd1f2e84dbebb3c66afe6327a77a4
+size 14244

run-1/checkpoint-842/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bc52c61ce135ad5f61822f7d16ad67b3c031cd6aaa19cb7701ac4ec162df4c8
+oid sha256:f8b0ffe5f3238e7c27281c5885b3b317a2efe6ef72456a7b36dc568271172ebb
 size 1064

run-1/checkpoint-842/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d58728a4c98462c056199818a16dc9ffabb0131d677c081afc7148b4da7bd4e
+oid sha256:5a42951e65bb3aa1e125b1b27e2a27b66ec94bb48bc4ff40d24214557a0e4b15
 size 4920

runs/Mar03_17-42-01_90708aaa767a/events.out.tfevents.1709497614.90708aaa767a.21824.19

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1778f90d52d065d9300ccfe56cd2b6065e60d4ee8042afbb97744bb1516d48d
-size 5691
+oid sha256:01786409408c8f3f5900035146b4ab90d5fc801a535c92cecf92af785616fb34
+size 6368