Training in progress, epoch 1

.gitattributes

@@ -44,3 +44,4 @@ run-1/checkpoint-758/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 run-1/checkpoint-1516/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 run-1/checkpoint-2274/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 run-1/checkpoint-3032/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+run-2/checkpoint-3032/tokenizer.json filter=lfs diff=lfs merge=lfs -text

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c644fc0efa575ad88b314aaf6ad710652f9720f0ae7f704671b55356501e58a9
+oid sha256:f0aa0700582b596d98157b4d5babc7041eb824c1a55c6bbc40d579ddf0902195
 size 2239618672

run-2/checkpoint-3032/config.json

@@ -0,0 +1,35 @@
+{
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "not sexist",
+    "1": "sexist"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "not sexist": 0,
+    "sexist": 1
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

run-2/checkpoint-3032/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0aa0700582b596d98157b4d5babc7041eb824c1a55c6bbc40d579ddf0902195
+size 2239618672

run-2/checkpoint-3032/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1798364e42c3be0c502f8b4dd0fc20076bd9ff83ec4487c042d6b2836e6af1bf
+size 4352331

run-2/checkpoint-3032/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43573145e13dc140110e6eab09890508e8b3cb7b8e476824893201bf02519e7c
+size 14645

run-2/checkpoint-3032/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a44ba219ee25ba54906bbe6a19114994d3a1cfc53af7f0eae31be69ca15979e8
+size 1383

run-2/checkpoint-3032/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0828d5ca673fbcfe5d54f5e32b5d11098c5c279aba105c1509784b4a62077c50
+size 1465

run-2/checkpoint-3032/sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

run-2/checkpoint-3032/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

run-2/checkpoint-3032/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c7a0e0871aad3996728f46860ee352dd6ec57264dae6319c75acba465f93d55
+size 17082999

run-2/checkpoint-3032/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

run-2/checkpoint-3032/trainer_state.json

@@ -0,0 +1,64 @@
+{
+  "best_global_step": 3032,
+  "best_metric": 0.7971651410424061,
+  "best_model_checkpoint": "./xlm-all/run-2/checkpoint-3032",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 3032,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 50.056209564208984,
+      "learning_rate": 1.1826905051647535e-05,
+      "loss": 0.5622,
+      "step": 3032
+    },
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.7971651410424061,
+      "eval_loss": 0.6596376299858093,
+      "eval_runtime": 10.1654,
+      "eval_samples_per_second": 183.76,
+      "eval_steps_per_second": 45.94,
+      "step": 3032
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 39416,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 13,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4238423840415744.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.280931194228943e-05,
+    "num_train_epochs": 13,
+    "per_device_train_batch_size": 1,
+    "weight_decay": 0.030691968879613542
+  }
+}

run-2/checkpoint-3032/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1486e121a87d39c6b0d211fb29619fe748e6f680a201ea6351367d68cc086559
+size 5713

runs/May11_15-23-21_eagle-01/events.out.tfevents.1746981675.eagle-01.208775.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:683e3d82f4662e66701d71a20bdde4a25f34f8f34ed90d36b89c9f1fac5bbc37
+size 5663

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0dcb6ca3dfc9e19eadc05ab287eced197c177d9a914fa8da12a692ef22288be
+oid sha256:1486e121a87d39c6b0d211fb29619fe748e6f680a201ea6351367d68cc086559
 size 5713