Training in progress, step 500

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "prajjwal1/bert-mini",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 256,
+  "id2label": {
+    "0": 0,
+    "1": 1
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "label2id": {
+    "0": 0,
+    "1": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 4,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

last-checkpoint/config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "prajjwal1/bert-mini",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 256,
+  "id2label": {
+    "0": 0,
+    "1": 1
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "label2id": {
+    "0": 0,
+    "1": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 4,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0efa6bdaa130143505fe541f1a423271362235e155e1283cec21b7458cb2e20
+size 88883845

last-checkpoint/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dbf84df44938b4c7f472e1c14c8f156cfb95726eafc3a9d7fc2fbc34a649b0c
+size 44449417

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1509ee85fa64f545e114cdaeb719c65524c2eabebb894701e5ac95a4915d5a78
+size 14575

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a7964cc59dbcd4cafe1ff58736b1a37cf044babc53007397f39ade5c8183aa6
+size 627

last-checkpoint/trainer_state.json

@@ -0,0 +1,34 @@
+{
+  "best_metric": 0.47408804297447205,
+  "best_model_checkpoint": "./test-small-bert-with-loss-weight/checkpoint-500",
+  "epoch": 0.4921259842519685,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.49,
+      "learning_rate": 4.1797900262467194e-05,
+      "loss": 0.5221,
+      "step": 500
+    },
+    {
+      "epoch": 0.49,
+      "eval_accuracy": 0.7981369412985216,
+      "eval_f1": 0.559788090457472,
+      "eval_loss": 0.47408804297447205,
+      "eval_precision": 0.4648381238649884,
+      "eval_recall": 0.7034852038761343,
+      "eval_runtime": 9.072,
+      "eval_samples_per_second": 1084.879,
+      "eval_steps_per_second": 4.299,
+      "step": 500
+    }
+  ],
+  "max_steps": 3048,
+  "num_train_epochs": 3,
+  "total_flos": 155323564032000.0,
+  "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:d7f78e51cdb55988f80e94c328e516b8025aedbf34269355824347fae368c890
+size 3515

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dbf84df44938b4c7f472e1c14c8f156cfb95726eafc3a9d7fc2fbc34a649b0c
+size 44449417

runs/Feb06_09-41-46_fadceb92582a/1675676530.2681575/events.out.tfevents.1675676530.fadceb92582a.597.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ecfacab3fbf276c27cbd2dd0e5c4995398c88e07ed193bd284b412fbb091ce8
+size 5734

runs/Feb06_09-41-46_fadceb92582a/events.out.tfevents.1675676530.fadceb92582a.597.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14024d31ce988ab997b3a13c355c4f578c1d057441c624ae069eb9ef1805e8c9
+size 4508

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7f78e51cdb55988f80e94c328e516b8025aedbf34269355824347fae368c890
+size 3515