初始化项目，由ModelHub XC社区提供模型

Model: Yousefbahr/Turjman-Cold-Start
Source: Original Platform

last-checkpoint/chat_template.jinja

@@ -0,0 +1 @@
+{{ bos_token }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% elif false == true %}{% set loop_messages = messages %}{% set system_message = 'You are Aya, a brilliant, sophisticated, multilingual AI-assistant trained to assist human users by providing thorough responses. You are able to interact and respond to questions in 23 languages and you are powered by a multilingual model built by Cohere For AI.' %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% if system_message != false %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' + system_message + '<|END_OF_TURN_TOKEN|>' }}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|START_OF_TURN_TOKEN|><|USER_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% elif message['role'] == 'assistant' %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>'  + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>' }}{% endif %}

last-checkpoint/config.json

@@ -0,0 +1,31 @@
+{
+  "architectures": [
+    "CohereForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 5,
+  "dtype": "bfloat16",
+  "eos_token_id": 255001,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "layer_norm_eps": 1e-05,
+  "logit_scale": 0.125,
+  "max_position_embeddings": 8192,
+  "model_type": "cohere",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "rope_parameters": {
+    "rope_theta": 10000,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.2.0",
+  "use_cache": false,
+  "use_qk_norm": false,
+  "vocab_size": 256000
+}

last-checkpoint/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 5,
+  "eos_token_id": [
+    255001
+  ],
+  "pad_token_id": 0,
+  "transformers_version": "5.2.0"
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71d874b039ecc399abb9bd66ffe499e41dc0d648bc19f5df44b3f5872071a74c
+size 16056096184

last-checkpoint/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d72cb57ce120d4797ec0a544cee3792f228c9dca4cb1863e11cb341f0ec3e576
+size 20124086

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,22 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<BOS_TOKEN>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<CLS>",
+  "eos_token": "<|END_OF_TURN_TOKEN|>",
+  "errors": "replace",
+  "is_local": true,
+  "legacy": true,
+  "mask_token": "<MASK_TOKEN>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<PAD>",
+  "padding_side": "right",
+  "sep_token": "<SEP>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "CohereTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,209 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.6724949562878278,
+  "eval_steps": 500,
+  "global_step": 250,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.026899798251513115,
+      "grad_norm": 0.9497337273894788,
+      "learning_rate": 9.879032258064517e-06,
+      "loss": 0.21184968948364258,
+      "step": 10
+    },
+    {
+      "epoch": 0.05379959650302623,
+      "grad_norm": 0.954080750401948,
+      "learning_rate": 9.744623655913979e-06,
+      "loss": 0.21339879035949708,
+      "step": 20
+    },
+    {
+      "epoch": 0.08069939475453934,
+      "grad_norm": 0.9097806480768484,
+      "learning_rate": 9.610215053763442e-06,
+      "loss": 0.2068164110183716,
+      "step": 30
+    },
+    {
+      "epoch": 0.10759919300605246,
+      "grad_norm": 1.0018783014353256,
+      "learning_rate": 9.475806451612905e-06,
+      "loss": 0.2059403896331787,
+      "step": 40
+    },
+    {
+      "epoch": 0.13449899125756556,
+      "grad_norm": 0.9372500482771303,
+      "learning_rate": 9.341397849462367e-06,
+      "loss": 0.19799630641937255,
+      "step": 50
+    },
+    {
+      "epoch": 0.16139878950907868,
+      "grad_norm": 0.9509184109653567,
+      "learning_rate": 9.206989247311828e-06,
+      "loss": 0.2008678436279297,
+      "step": 60
+    },
+    {
+      "epoch": 0.1882985877605918,
+      "grad_norm": 1.1134282940647546,
+      "learning_rate": 9.072580645161291e-06,
+      "loss": 0.20529050827026368,
+      "step": 70
+    },
+    {
+      "epoch": 0.21519838601210492,
+      "grad_norm": 0.9233328708641031,
+      "learning_rate": 8.938172043010753e-06,
+      "loss": 0.2078157901763916,
+      "step": 80
+    },
+    {
+      "epoch": 0.242098184263618,
+      "grad_norm": 1.0158369506432157,
+      "learning_rate": 8.803763440860216e-06,
+      "loss": 0.2069852113723755,
+      "step": 90
+    },
+    {
+      "epoch": 0.26899798251513113,
+      "grad_norm": 0.9962467911152623,
+      "learning_rate": 8.669354838709677e-06,
+      "loss": 0.19123213291168212,
+      "step": 100
+    },
+    {
+      "epoch": 0.29589778076664425,
+      "grad_norm": 0.9050182554717234,
+      "learning_rate": 8.53494623655914e-06,
+      "loss": 0.1998592734336853,
+      "step": 110
+    },
+    {
+      "epoch": 0.32279757901815737,
+      "grad_norm": 1.16989042706525,
+      "learning_rate": 8.400537634408604e-06,
+      "loss": 0.19017333984375,
+      "step": 120
+    },
+    {
+      "epoch": 0.3496973772696705,
+      "grad_norm": 0.9202065176879053,
+      "learning_rate": 8.266129032258065e-06,
+      "loss": 0.1971895694732666,
+      "step": 130
+    },
+    {
+      "epoch": 0.3765971755211836,
+      "grad_norm": 0.9882788749577818,
+      "learning_rate": 8.131720430107529e-06,
+      "loss": 0.20348339080810546,
+      "step": 140
+    },
+    {
+      "epoch": 0.4034969737726967,
+      "grad_norm": 0.9666836025801647,
+      "learning_rate": 7.99731182795699e-06,
+      "loss": 0.18486206531524657,
+      "step": 150
+    },
+    {
+      "epoch": 0.43039677202420984,
+      "grad_norm": 0.8578034645388888,
+      "learning_rate": 7.862903225806451e-06,
+      "loss": 0.19098201990127564,
+      "step": 160
+    },
+    {
+      "epoch": 0.45729657027572296,
+      "grad_norm": 0.9758615729928365,
+      "learning_rate": 7.728494623655915e-06,
+      "loss": 0.18409807682037355,
+      "step": 170
+    },
+    {
+      "epoch": 0.484196368527236,
+      "grad_norm": 0.9564910398607444,
+      "learning_rate": 7.594086021505377e-06,
+      "loss": 0.20637857913970947,
+      "step": 180
+    },
+    {
+      "epoch": 0.5110961667787491,
+      "grad_norm": 1.09919047792078,
+      "learning_rate": 7.459677419354839e-06,
+      "loss": 0.1931600570678711,
+      "step": 190
+    },
+    {
+      "epoch": 0.5379959650302623,
+      "grad_norm": 1.0745145882317149,
+      "learning_rate": 7.325268817204302e-06,
+      "loss": 0.19824893474578859,
+      "step": 200
+    },
+    {
+      "epoch": 0.5648957632817754,
+      "grad_norm": 0.9633608114145525,
+      "learning_rate": 7.190860215053764e-06,
+      "loss": 0.2040123701095581,
+      "step": 210
+    },
+    {
+      "epoch": 0.5917955615332885,
+      "grad_norm": 1.0540947069171986,
+      "learning_rate": 7.056451612903227e-06,
+      "loss": 0.200044584274292,
+      "step": 220
+    },
+    {
+      "epoch": 0.6186953597848016,
+      "grad_norm": 0.9784264211901752,
+      "learning_rate": 6.9220430107526895e-06,
+      "loss": 0.2000995397567749,
+      "step": 230
+    },
+    {
+      "epoch": 0.6455951580363147,
+      "grad_norm": 1.1286177734944867,
+      "learning_rate": 6.787634408602151e-06,
+      "loss": 0.1975030779838562,
+      "step": 240
+    },
+    {
+      "epoch": 0.6724949562878278,
+      "grad_norm": 1.0140389237975715,
+      "learning_rate": 6.653225806451613e-06,
+      "loss": 0.1995392322540283,
+      "step": 250
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 744,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 250,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2257087168512.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7f60116ab3a4196b53fe018135cc3143df6799b220c9919983aefb8dfae4e1a
+size 6904