Training in progress, epoch 4

.gitattributes

@@ -39,3 +39,4 @@ run-2/checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text
 run-0/checkpoint-6064/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 run-0/checkpoint-9096/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+run-0/checkpoint-12128/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:f9e54d201f86481592538d3113b2e1c5e91d7c2db2320312c3918c1bae4e210c
+oid sha256:918ab0923dcea12c60a688a0c7df586e057be95ca2d8333be73c0ba693af7683
 size 2239618672

run-0/checkpoint-12128/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-0/checkpoint-12128/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:918ab0923dcea12c60a688a0c7df586e057be95ca2d8333be73c0ba693af7683
+size 2239618672

run-0/checkpoint-12128/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05205199940a2f2c21ecd2c286dc17a1b1541675b123f1b967a96a2aa11e0227
+size 4352331

run-0/checkpoint-12128/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b605e536f3476b011f115e7f54d84d305b690890f776c16bfd7f409e432f2544
+size 14645

run-0/checkpoint-12128/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cde8cf7e3e503791b1c804a89a7d0a2244ae27d5fa3235305c0e76709ffd0ba
+size 1383

run-0/checkpoint-12128/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd61d3f2cca6aa528b09762abcf9cc9d1891f1c026dcb8bb7f273c19a5f0823a
+size 1465

run-0/checkpoint-12128/sentencepiece.bpe.model

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

run-0/checkpoint-12128/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-0/checkpoint-12128/tokenizer.json

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

run-0/checkpoint-12128/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-0/checkpoint-12128/trainer_state.json

@@ -0,0 +1,112 @@
+{
+  "best_global_step": 3032,
+  "best_metric": 0.33899504600141545,
+  "best_model_checkpoint": "./xlm-all/run-0/checkpoint-3032",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 12128,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 9.779642105102539,
+      "learning_rate": 1.8643519897391662e-05,
+      "loss": 0.7018,
+      "step": 3032
+    },
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.33899504600141545,
+      "eval_loss": 0.7100579142570496,
+      "eval_runtime": 10.182,
+      "eval_samples_per_second": 183.46,
+      "eval_steps_per_second": 45.865,
+      "step": 3032
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 9.73989486694336,
+      "learning_rate": 1.5981790796638288e-05,
+      "loss": 0.6994,
+      "step": 6064
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.33899504600141545,
+      "eval_loss": 0.6966525912284851,
+      "eval_runtime": 10.1265,
+      "eval_samples_per_second": 184.467,
+      "eval_steps_per_second": 46.117,
+      "step": 6064
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 9.934926986694336,
+      "learning_rate": 1.331918352726045e-05,
+      "loss": 0.697,
+      "step": 9096
+    },
+    {
+      "epoch": 3.0,
+      "eval_f1": 0.33899504600141545,
+      "eval_loss": 0.7028103470802307,
+      "eval_runtime": 10.1164,
+      "eval_samples_per_second": 184.65,
+      "eval_steps_per_second": 46.163,
+      "step": 9096
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.8155622482299805,
+      "learning_rate": 1.0656576257882611e-05,
+      "loss": 0.6947,
+      "step": 12128
+    },
+    {
+      "epoch": 4.0,
+      "eval_f1": 0.33899504600141545,
+      "eval_loss": 0.7009352445602417,
+      "eval_runtime": 10.1141,
+      "eval_samples_per_second": 184.693,
+      "eval_steps_per_second": 46.173,
+      "step": 12128
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 24256,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 3
+      }
+    },
+    "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": 1,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.1300858155022713e-05,
+    "num_train_epochs": 8,
+    "per_device_train_batch_size": 1,
+    "weight_decay": 0.01912682401845879
+  }
+}

run-0/checkpoint-12128/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:363fa8cab07af263bfe2ce4fc5547f865fc88e22d75a7d7f77858446d6d2fdb9
+size 5713

runs/May11_15-23-21_eagle-01/events.out.tfevents.1746973423.eagle-01.208775.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62a5f1e279314aa18362ff5d4c62242851305ea5ac2f4bcc13da4637e472b4a0
-size 6718
+oid sha256:4f09ec0fc56f78a53e8a55a18db17b635512e90ebc7cb1e0e907d9abe01c128d
+size 7600