Upload 12 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "<|...|>": 250005,
+  "<|assistant|>": 250004,
+  "<|system|>": 250002,
+  "<|user|>": 250003
+}

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.9152704643370033,
+    "eval_loss": 0.26646581292152405,
+    "eval_runtime": 1.1405,
+    "eval_samples": 2089,
+    "eval_samples_per_second": 1831.598,
+    "eval_steps_per_second": 229.717,
+    "num_input_tokens_seen": 5347200,
+    "total_flos": 687958325107200.0,
+    "train_loss": 0.17576850672087602,
+    "train_runtime": 152.9681,
+    "train_samples": 8355,
+    "train_samples_per_second": 273.096,
+    "train_steps_per_second": 34.157
+}

config.json

@@ -0,0 +1,37 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "finetuning_task": "text-classification",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "id2label": {
+    "0": "Non-refusal",
+    "1": "Refusal"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "label2id": {
+    "Non-refusal": 0,
+    "Refusal": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "transformers_version": "5.0.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": false,
+  "vocab_size": 250006
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.9152704643370033,
+    "eval_loss": 0.26646581292152405,
+    "eval_runtime": 1.1405,
+    "eval_samples": 2089,
+    "eval_samples_per_second": 1831.598,
+    "eval_steps_per_second": 229.717,
+    "num_input_tokens_seen": 5347200
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bd23b6798039c679834ceb778e9cccac84ca26557d7970c4fe21c121a72f6aa
+size 470594048

sentencepiece.bpe.model

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

special_tokens_map.json

@@ -0,0 +1,57 @@
+{
+  "additional_special_tokens": [
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|...|>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eafa6ff176beee152d4d70e1e309fa313e903994e046875cda0e7b6f763c8a04
+size 17083811

tokenizer_config.json

@@ -0,0 +1,101 @@
+{
+  "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": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250002": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250003": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250004": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250005": {
+      "content": "<|...|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|...|>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "stride": 0,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}

train_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 5.0,
+    "num_input_tokens_seen": 5347200,
+    "total_flos": 687958325107200.0,
+    "train_loss": 0.17576850672087602,
+    "train_runtime": 152.9681,
+    "train_samples": 8355,
+    "train_samples_per_second": 273.096,
+    "train_steps_per_second": 34.157
+}

trainer_state.json

@@ -0,0 +1,194 @@
+{
+  "best_global_step": 2090,
+  "best_metric": 0.26646581292152405,
+  "best_model_checkpoint": "/media/user/Expansion1/multilingual-e5-small-aligned-v2-conversation-refusal/checkpoint-2090",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 5225,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.4784688995215311,
+      "grad_norm": 14.723045349121094,
+      "learning_rate": 4.522488038277512e-05,
+      "loss": 0.3758,
+      "num_input_tokens_seen": 512000,
+      "step": 500,
+      "train_runtime": 13.5893,
+      "train_tokens_per_second": 37676.655
+    },
+    {
+      "epoch": 0.9569377990430622,
+      "grad_norm": 1.9174224138259888,
+      "learning_rate": 4.044019138755981e-05,
+      "loss": 0.308,
+      "num_input_tokens_seen": 1024000,
+      "step": 1000,
+      "train_runtime": 26.8861,
+      "train_tokens_per_second": 38086.661
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9023456199138343,
+      "eval_loss": 0.29579150676727295,
+      "eval_runtime": 1.1525,
+      "eval_samples_per_second": 1812.63,
+      "eval_steps_per_second": 227.338,
+      "num_input_tokens_seen": 1069440,
+      "step": 1045
+    },
+    {
+      "epoch": 1.4354066985645932,
+      "grad_norm": 12.026004791259766,
+      "learning_rate": 3.56555023923445e-05,
+      "loss": 0.2384,
+      "num_input_tokens_seen": 1535360,
+      "step": 1500,
+      "train_runtime": 42.6862,
+      "train_tokens_per_second": 35968.498
+    },
+    {
+      "epoch": 1.9138755980861244,
+      "grad_norm": 3.3293282985687256,
+      "learning_rate": 3.0870813397129186e-05,
+      "loss": 0.2253,
+      "num_input_tokens_seen": 2047360,
+      "step": 2000,
+      "train_runtime": 56.0083,
+      "train_tokens_per_second": 36554.566
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9152704643370033,
+      "eval_loss": 0.26646581292152405,
+      "eval_runtime": 1.1367,
+      "eval_samples_per_second": 1837.79,
+      "eval_steps_per_second": 230.493,
+      "num_input_tokens_seen": 2138880,
+      "step": 2090
+    },
+    {
+      "epoch": 2.3923444976076556,
+      "grad_norm": 1.1071521043777466,
+      "learning_rate": 2.6086124401913874e-05,
+      "loss": 0.159,
+      "num_input_tokens_seen": 2558720,
+      "step": 2500,
+      "train_runtime": 71.8393,
+      "train_tokens_per_second": 35617.282
+    },
+    {
+      "epoch": 2.8708133971291865,
+      "grad_norm": 2.7163774967193604,
+      "learning_rate": 2.1301435406698568e-05,
+      "loss": 0.1607,
+      "num_input_tokens_seen": 3070720,
+      "step": 3000,
+      "train_runtime": 85.1841,
+      "train_tokens_per_second": 36048.061
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9128769746290091,
+      "eval_loss": 0.3344113528728485,
+      "eval_runtime": 1.1569,
+      "eval_samples_per_second": 1805.706,
+      "eval_steps_per_second": 226.47,
+      "num_input_tokens_seen": 3208320,
+      "step": 3135
+    },
+    {
+      "epoch": 3.349282296650718,
+      "grad_norm": 0.12201690673828125,
+      "learning_rate": 1.6516746411483256e-05,
+      "loss": 0.1179,
+      "num_input_tokens_seen": 3582080,
+      "step": 3500,
+      "train_runtime": 101.233,
+      "train_tokens_per_second": 35384.512
+    },
+    {
+      "epoch": 3.827751196172249,
+      "grad_norm": 0.03180946409702301,
+      "learning_rate": 1.1732057416267943e-05,
+      "loss": 0.1058,
+      "num_input_tokens_seen": 4094080,
+      "step": 4000,
+      "train_runtime": 114.5749,
+      "train_tokens_per_second": 35732.797
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9009095260890378,
+      "eval_loss": 0.4442259669303894,
+      "eval_runtime": 1.1377,
+      "eval_samples_per_second": 1836.223,
+      "eval_steps_per_second": 230.297,
+      "num_input_tokens_seen": 4277760,
+      "step": 4180
+    },
+    {
+      "epoch": 4.30622009569378,
+      "grad_norm": 0.1291642189025879,
+      "learning_rate": 6.9473684210526315e-06,
+      "loss": 0.0685,
+      "num_input_tokens_seen": 4605440,
+      "step": 4500,
+      "train_runtime": 130.6244,
+      "train_tokens_per_second": 35257.12
+    },
+    {
+      "epoch": 4.784688995215311,
+      "grad_norm": 0.04361966624855995,
+      "learning_rate": 2.1626794258373207e-06,
+      "loss": 0.0575,
+      "num_input_tokens_seen": 5117440,
+      "step": 5000,
+      "train_runtime": 143.9296,
+      "train_tokens_per_second": 35555.165
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8985160363810436,
+      "eval_loss": 0.5183091163635254,
+      "eval_runtime": 1.1353,
+      "eval_samples_per_second": 1840.123,
+      "eval_steps_per_second": 230.786,
+      "num_input_tokens_seen": 5347200,
+      "step": 5225
+    },
+    {
+      "epoch": 5.0,
+      "num_input_tokens_seen": 5347200,
+      "step": 5225,
+      "total_flos": 687958325107200.0,
+      "train_loss": 0.17576850672087602,
+      "train_runtime": 152.9681,
+      "train_samples_per_second": 273.096,
+      "train_steps_per_second": 34.157
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5225,
+  "num_input_tokens_seen": 5347200,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 687958325107200.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd94a90af606746a139fe17cccd04636a5451d129ba9813cbafa73d3eb0781b2
+size 5265