Training in progress, epoch 4

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:451d26bbe7d0ff1f4e00e63c1a95a00a0aad9724be00ae320a1896212da604d7
+oid sha256:40ace6b7f68e491503f3f0453773bb707b735093040bcbc0a9ee9ea5f06153ff
 size 267835644

run-0/checkpoint-296/config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "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": "4.38.1",
+  "vocab_size": 30522
+}

run-0/checkpoint-296/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40ace6b7f68e491503f3f0453773bb707b735093040bcbc0a9ee9ea5f06153ff
+size 267835644

run-0/checkpoint-296/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f979655b9c06786e2ca1b8e8f80bb3624b7f7a9e0719e8f93b20ed0bc9c52c5
+size 535733434

run-0/checkpoint-296/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f019ca6cf7f48fb4b2b4a97bbde52c9be07a4f10c3cc609d858414efae321e29
+size 14244

run-0/checkpoint-296/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c264c3b44f569149068f5ecad3a7a1a95f6f0b0ebdbf3d0b0db176c235bb01ea
+size 1064

run-0/checkpoint-296/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-296/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-296/trainer_state.json

@@ -0,0 +1,62 @@
+{
+  "best_metric": 0.6318493150684932,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-SA/run-0/checkpoint-296",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 296,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.547945205479452,
+      "eval_loss": 0.9810061454772949,
+      "eval_runtime": 3.373,
+      "eval_samples_per_second": 173.142,
+      "eval_steps_per_second": 10.97,
+      "step": 74
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6061643835616438,
+      "eval_loss": 0.9076536893844604,
+      "eval_runtime": 3.3848,
+      "eval_samples_per_second": 172.534,
+      "eval_steps_per_second": 10.931,
+      "step": 148
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6181506849315068,
+      "eval_loss": 0.8786949515342712,
+      "eval_runtime": 3.355,
+      "eval_samples_per_second": 174.07,
+      "eval_steps_per_second": 11.028,
+      "step": 222
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6318493150684932,
+      "eval_loss": 0.8698766827583313,
+      "eval_runtime": 3.3557,
+      "eval_samples_per_second": 174.033,
+      "eval_steps_per_second": 11.026,
+      "step": 296
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 296,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.1624173301056434e-06,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 64,
+    "seed": 2
+  }
+}

run-0/checkpoint-296/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdece1721090c1972a91e9dd9fe47f1498680c26311f0caf5e2ae7f7706cee28
+size 4984

runs/Apr02_02-49-58_ef019a3ab26d/events.out.tfevents.1712026422.ef019a3ab26d.26.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61087b982e2bcac503cb7afb5da566e1f5bc6dfbdf751c5b79bac80dd16df702
-size 5654
+oid sha256:bc6d42df58e015563fc153643e654d3579112094b98f9a10573686404cd133ba
+size 6331