Upload 10 files

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1",
+  "architectures": [
+    "Qwen2ForSequenceClassification"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "max_position_embeddings": 131072,
+  "max_window_layers": 24,
+  "model_type": "qwen2",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float16",
+  "transformers_version": "4.44.2",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e56c619cbe49de5517fab6b8c458971daa6444115538f63c2fbf973ed607808
+size 988099416

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "auto_map": {
+    "AutoTokenizer": [
+      "HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1--tokenization_qwen.Qwen2Tokenizer",
+      "HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1--tokenization_qwen.Qwen2TokenizerFast"
+    ]
+  },
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "max_length": 512,
+  "model_max_length": 32768,
+  "pad_to_multiple_of": null,
+  "pad_token": "<|endoftext|>",
+  "pad_token_type_id": 0,
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "stride": 0,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,82 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 3733,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1339405304045004,
+      "grad_norm": 20.019311904907227,
+      "learning_rate": 1.925573087228342e-05,
+      "loss": 0.6476,
+      "step": 500
+    },
+    {
+      "epoch": 0.2678810608090008,
+      "grad_norm": 15.345267295837402,
+      "learning_rate": 1.627865436141709e-05,
+      "loss": 0.4459,
+      "step": 1000
+    },
+    {
+      "epoch": 0.4018215912135012,
+      "grad_norm": 10.613130569458008,
+      "learning_rate": 1.330157785055076e-05,
+      "loss": 0.3806,
+      "step": 1500
+    },
+    {
+      "epoch": 0.5357621216180016,
+      "grad_norm": 6.42950439453125,
+      "learning_rate": 1.0324501339684432e-05,
+      "loss": 0.356,
+      "step": 2000
+    },
+    {
+      "epoch": 0.669702652022502,
+      "grad_norm": 11.147576332092285,
+      "learning_rate": 7.347424828818102e-06,
+      "loss": 0.3135,
+      "step": 2500
+    },
+    {
+      "epoch": 0.8036431824270024,
+      "grad_norm": 6.7693047523498535,
+      "learning_rate": 4.370348317951772e-06,
+      "loss": 0.304,
+      "step": 3000
+    },
+    {
+      "epoch": 0.9375837128315028,
+      "grad_norm": 8.816291809082031,
+      "learning_rate": 1.3932718070854423e-06,
+      "loss": 0.2765,
+      "step": 3500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3733,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "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": 0.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:644341618422331205081ed36797f91eec27f9651203e76ad37f736da419b59f
+size 6776