Training in progress, epoch 4

.gitattributes

@@ -43,3 +43,4 @@ run-0/checkpoint-12128/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 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

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0e079f4660aae0516d14478dcb614b0c4e7db2dcde831afdbdb37b65b064e43
+oid sha256:c644fc0efa575ad88b314aaf6ad710652f9720f0ae7f704671b55356501e58a9
 size 2239618672

run-1/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-1/checkpoint-3032/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c644fc0efa575ad88b314aaf6ad710652f9720f0ae7f704671b55356501e58a9
+size 2239618672

run-1/checkpoint-3032/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b61928e431dcbf68d4cd3753c11a1abb8d29ca9aa7d49020fa9e1e97528f0cae
+size 4352331

run-1/checkpoint-3032/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f13227a94b24a788ae7f6f64c75c86d8c50c141b0569ec7859b811f4d573808
+size 14645

run-1/checkpoint-3032/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df486430e5f6f2444e9f5f7125cab63edb49f10745482319c16898f92b300e84
+size 1383

run-1/checkpoint-3032/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b33058117bd759dd013f2b53ed4a66d19b2d03702e78eb4bc92c6836ea597ad0
+size 1465

run-1/checkpoint-3032/sentencepiece.bpe.model

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

run-1/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-1/checkpoint-3032/tokenizer.json

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

run-1/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-1/checkpoint-3032/trainer_state.json

@@ -0,0 +1,112 @@
+{
+  "best_global_step": 2274,
+  "best_metric": 0.8549574327845205,
+  "best_model_checkpoint": "./xlm-all/run-1/checkpoint-2274",
+  "epoch": 4.0,
+  "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": 12.377753257751465,
+      "learning_rate": 1.751793956823625e-05,
+      "loss": 0.5073,
+      "step": 758
+    },
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.815612225938313,
+      "eval_loss": 0.513485848903656,
+      "eval_runtime": 10.3605,
+      "eval_samples_per_second": 180.3,
+      "eval_steps_per_second": 45.075,
+      "step": 758
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 8.5549898147583,
+      "learning_rate": 1.1696546235170456e-05,
+      "loss": 0.3585,
+      "step": 1516
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.8423910984685427,
+      "eval_loss": 0.48785603046417236,
+      "eval_runtime": 10.3617,
+      "eval_samples_per_second": 180.28,
+      "eval_steps_per_second": 45.07,
+      "step": 1516
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 50.38733673095703,
+      "learning_rate": 5.875152902104661e-06,
+      "loss": 0.2723,
+      "step": 2274
+    },
+    {
+      "epoch": 3.0,
+      "eval_f1": 0.8549574327845205,
+      "eval_loss": 0.5350980758666992,
+      "eval_runtime": 10.3575,
+      "eval_samples_per_second": 180.352,
+      "eval_steps_per_second": 45.088,
+      "step": 2274
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.187727689743042,
+      "learning_rate": 6.143950747298992e-08,
+      "loss": 0.2343,
+      "step": 3032
+    },
+    {
+      "epoch": 4.0,
+      "eval_f1": 0.8463623176902699,
+      "eval_loss": 0.583969235420227,
+      "eval_runtime": 10.3308,
+      "eval_samples_per_second": 180.818,
+      "eval_steps_per_second": 45.205,
+      "step": 3032
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3032,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 1
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.6953695361662976e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.328557333226318e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 4,
+    "weight_decay": 0.09896896704069603
+  }
+}

run-1/checkpoint-3032/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0dcb6ca3dfc9e19eadc05ab287eced197c177d9a914fa8da12a692ef22288be
+size 5713

runs/May11_15-23-21_eagle-01/events.out.tfevents.1746979630.eagle-01.208775.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bea5c281503115e3700c9a76dc8d190c36781ebb8cded3d09868d52ba8f7a13
-size 6717
+oid sha256:2f9b22fe446ba2abd84dc410b168a2c95afc618ed55fa8236c46f3f0f91b52fe
+size 7599