Training in progress, epoch 1, checkpoint

last-checkpoint/config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "distilbert-base-cased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "anger",
+    "1": "joy",
+    "2": "optimism",
+    "3": "sadness"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "anger": 0,
+    "joy": 1,
+    "optimism": 2,
+    "sadness": 3
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "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": "4.35.2",
+  "vocab_size": 28996
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e68fd628f2354a6a657de268a85d88023f92d72b0575f8b18769ddf9cc28a15
+size 263150840

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c50dc24e634ed44e89d3f9744310f42352dc1a84846d6360a2351aceafe8904
+size 526363834

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b90df5d61f2cf16876715eb8ad68783d2e9241e7463932793f4e217a880ced5
+size 14244

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96687253d7e86f86cc3b4cffb7369957dc7f9fcfeaff891e76a1d2e7e9f579ae
+size 1064

last-checkpoint/special_tokens_map.json

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

last-checkpoint/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": false,
+  "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]"
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,36 @@
+{
+  "best_metric": 0.7061901924276679,
+  "best_model_checkpoint": "bert-emotion/checkpoint-815",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 815,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.8416,
+      "step": 815
+    },
+    {
+      "epoch": 1.0,
+      "eval_fscore": 0.7061901924276679,
+      "eval_loss": 0.7683064937591553,
+      "eval_precision": 0.7000145689951174,
+      "eval_recall": 0.7141334228293426,
+      "eval_runtime": 0.8695,
+      "eval_samples_per_second": 430.12,
+      "eval_steps_per_second": 108.105,
+      "step": 815
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2445,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 31692920583072.0,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2294a0df7e2df7fd066300ebcd07ab493a37e08d865146532978b0b09b32751a
+size 4536