Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f84014248274b80667fce8855d133b87c51c89eee525604a55f8598228b768d
+oid sha256:dc6628694c950dd5fbe46f68ce2987c750081a50bc283657d3212f07f03f972f
 size 267832560

tmp-checkpoint-350/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
+}

tmp-checkpoint-350/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc6628694c950dd5fbe46f68ce2987c750081a50bc283657d3212f07f03f972f
+size 267832560

tmp-checkpoint-350/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5877be18420a112359a1a007e8e3b106c6f005a1f1e9c87fd1b5df566d875441
+size 535727290

tmp-checkpoint-350/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe0e7135622ace68d7968efe929220efcc643079f367f734515eda6abfb77956
+size 14244

tmp-checkpoint-350/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:962767c052121cc97a86e61e22f918f67e3a261cb52213471bfe6b643edaffb8
+size 1064

tmp-checkpoint-350/special_tokens_map.json

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

tmp-checkpoint-350/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]"
+}

tmp-checkpoint-350/trainer_state.json

@@ -0,0 +1,83 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 350,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 0.5477,
+      "step": 50
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.5383,
+      "step": 100
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 3e-06,
+      "loss": 0.5464,
+      "step": 150
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7685714285714286,
+      "eval_f1": 0.8691437802907915,
+      "eval_loss": 0.5194858312606812,
+      "eval_runtime": 10.6792,
+      "eval_samples_per_second": 65.548,
+      "eval_steps_per_second": 4.12,
+      "step": 175
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.5248,
+      "step": 200
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 5e-06,
+      "loss": 0.5475,
+      "step": 250
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 6e-06,
+      "loss": 0.5114,
+      "step": 300
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 7e-06,
+      "loss": 0.5552,
+      "step": 350
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7685714285714286,
+      "eval_f1": 0.8691437802907915,
+      "eval_loss": 0.525272011756897,
+      "eval_runtime": 15.9825,
+      "eval_samples_per_second": 43.798,
+      "eval_steps_per_second": 2.753,
+      "step": 350
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 525,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 826596567613440.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

tmp-checkpoint-350/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17e386d1c2fffd73ff73abe40645453eee911a33dcdd7656050f585848ce23d5
+size 4664