初始化项目，由ModelHub XC社区提供模型

Model: Michnik/jarvis-1b-trained
Source: Original Platform

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

EMERGENCY/config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 5,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 32,
+  "pad_token_id": 3,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.7.0",
+  "use_cache": false,
+  "vocab_size": 9800
+}

EMERGENCY/generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 5,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 3,
+  "transformers_version": "5.7.0",
+  "use_cache": true
+}

EMERGENCY/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1dd929a5ccd0a1e1038e0ecaa548957afe64ee2ef4fb0eb08657eb1d66d6598
+size 2341218896

EMERGENCY/tokenizer_config.json

@@ -0,0 +1,8 @@
+{
+  "backend": "tokenizers",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "tokenizer_class": "TokenizersBackend"
+}

EMERGENCY/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af668a2ff3a854e7dc3f5cfb9a3243871d71d51ba0d8fcbfc9ac136005b4a10f
+size 4856

README.md

@@ -0,0 +1,57 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+model-index:
+- name: jarvis-1b-trained
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# jarvis-1b-trained
+
+This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- eval_loss: 7.0674
+- eval_runtime: 117.7328
+- eval_samples_per_second: 84.938
+- eval_steps_per_second: 10.617
+- epoch: 0.0003
+- step: 100
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0002
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 1
+
+### Framework versions
+
+- Transformers 5.7.0
+- Pytorch 2.4.1+cu124
+- Datasets 4.8.5
+- Tokenizers 0.22.2

config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 5,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 32,
+  "pad_token_id": 3,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.7.0",
+  "use_cache": false,
+  "vocab_size": 9800
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 5,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 3,
+  "transformers_version": "5.7.0",
+  "use_cache": true
+}

last-checkpoint/config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 5,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 32,
+  "pad_token_id": 3,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.7.0",
+  "use_cache": false,
+  "vocab_size": 9800
+}

last-checkpoint/generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 5,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 3,
+  "transformers_version": "5.7.0",
+  "use_cache": true
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f141eb84ec115751ee6a89897b08a199139d279b06418891e22419e294212b68
+size 2341218896

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0be457241ce63f8827efc7665288f543918f89be9524bfeb905f0d21d222c282
+size 4682561734

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ff264f99d31b522cc7e2a4eac9d38606d0c58a34c0adc74d71e0ca8b371dc36
+size 14244

last-checkpoint/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c178d88dd64302d0da55c078b7a67c25e5a7c7b6abe69bb648b63b0b5924756a
+size 1383

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e0bfbbe2be6a1399a4c175bf33e1a680e875704102055b2bbfcb74670a4c677
+size 1064

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,8 @@
+{
+  "backend": "tokenizers",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "tokenizer_class": "TokenizersBackend"
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,112 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.0002653961269416215,
+  "eval_steps": 100,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.6539612694162147e-05,
+      "grad_norm": 11.25,
+      "learning_rate": 1.8e-05,
+      "loss": 9.487161254882812,
+      "step": 10
+    },
+    {
+      "epoch": 5.3079225388324294e-05,
+      "grad_norm": 9.3125,
+      "learning_rate": 3.8e-05,
+      "loss": 9.404236602783204,
+      "step": 20
+    },
+    {
+      "epoch": 7.961883808248645e-05,
+      "grad_norm": 9.5625,
+      "learning_rate": 5.8e-05,
+      "loss": 9.108424377441406,
+      "step": 30
+    },
+    {
+      "epoch": 0.00010615845077664859,
+      "grad_norm": 2.484375,
+      "learning_rate": 7.800000000000001e-05,
+      "loss": 7.820616912841797,
+      "step": 40
+    },
+    {
+      "epoch": 0.00013269806347081074,
+      "grad_norm": 2.546875,
+      "learning_rate": 9.8e-05,
+      "loss": 7.00987548828125,
+      "step": 50
+    },
+    {
+      "epoch": 0.0001592376761649729,
+      "grad_norm": 5.34375,
+      "learning_rate": 0.000118,
+      "loss": 6.811207580566406,
+      "step": 60
+    },
+    {
+      "epoch": 0.00018577728885913502,
+      "grad_norm": 1.75,
+      "learning_rate": 0.000138,
+      "loss": 6.862815093994141,
+      "step": 70
+    },
+    {
+      "epoch": 0.00021231690155329718,
+      "grad_norm": 2.578125,
+      "learning_rate": 0.00015800000000000002,
+      "loss": 6.837502288818359,
+      "step": 80
+    },
+    {
+      "epoch": 0.00023885651424745933,
+      "grad_norm": 2.359375,
+      "learning_rate": 0.00017800000000000002,
+      "loss": 6.851012420654297,
+      "step": 90
+    },
+    {
+      "epoch": 0.0002653961269416215,
+      "grad_norm": 1.875,
+      "learning_rate": 0.00019800000000000002,
+      "loss": 6.771617126464844,
+      "step": 100
+    },
+    {
+      "epoch": 0.0002653961269416215,
+      "eval_loss": 7.0674147605896,
+      "eval_runtime": 117.7328,
+      "eval_samples_per_second": 84.938,
+      "eval_steps_per_second": 10.617,
+      "step": 100
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 376796,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2242948735746048.0,
+  "train_batch_size": 4,
+  "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:af668a2ff3a854e7dc3f5cfb9a3243871d71d51ba0d8fcbfc9ac136005b4a10f
+size 4856

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1dd929a5ccd0a1e1038e0ecaa548957afe64ee2ef4fb0eb08657eb1d66d6598
+size 2341218896

tokenizer_config.json

@@ -0,0 +1,8 @@
+{
+  "backend": "tokenizers",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "tokenizer_class": "TokenizersBackend"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af668a2ff3a854e7dc3f5cfb9a3243871d71d51ba0d8fcbfc9ac136005b4a10f
+size 4856