初始化项目，由ModelHub XC社区提供模型

Model: AmberYifan/capsd-final-retrain-marin-8b-base-code_cap_b8000_s0 Source: Original Platform
2026-10-10 02:03:19 +08:00
commit aec7b54db1
37 changed files with 912 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,39 @@
+*.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
+checkpoint-125/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-250/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-375/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
--- a/README.md
+++ b/README.md
@@ -0,0 +1,61 @@
+---
+library_name: transformers
+license: other
+base_model: marin-community/marin-8b-base
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: marin-8b-base_code_cap_b8000_s0
+  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. -->
+
+# marin-8b-base_code_cap_b8000_s0
+
+This model is a fine-tuned version of [marin-community/marin-8b-base](https://huggingface.co/marin-community/marin-8b-base) on the capsd_marin-8b-base-n80000-opc__mix_code_cap_b8000_s0 dataset.
+
+## 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: 1e-05
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 0
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 64
+- total_eval_batch_size: 32
+- 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: 0.03
+- num_epochs: 3
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 5.7.0
+- Pytorch 2.13.0+cu130
+- Datasets 4.0.0
+- Tokenizers 0.22.2
--- a/all_results.json
+++ b/all_results.json
@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 7801590251520.0,
+    "train_loss": 0.21588493855794272,
+    "train_runtime": 11728.7173,
+    "train_samples_per_second": 2.046,
+    "train_steps_per_second": 0.032
+}
--- a/chat_template.jinja
+++ b/chat_template.jinja
@@ -0,0 +1,7 @@
+{{ '<|begin_of_text|>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|start_header_id|>system<|end_header_id|>
+
+' + system_message + '<|eot_id|>' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|start_header_id|>user<|end_header_id|>
+
+' + content + '<|eot_id|><|start_header_id|>assistant<|end_header_id|>
+
+' }}{% elif message['role'] == 'assistant' %}{{ content + '<|eot_id|>' }}{% endif %}{% endfor %}
--- a/checkpoint-125/chat_template.jinja
+++ b/checkpoint-125/chat_template.jinja
@@ -0,0 +1,7 @@
+{{ '<|begin_of_text|>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|start_header_id|>system<|end_header_id|>
+
+' + system_message + '<|eot_id|>' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|start_header_id|>user<|end_header_id|>
+
+' + content + '<|eot_id|><|start_header_id|>assistant<|end_header_id|>
+
+' }}{% elif message['role'] == 'assistant' %}{{ content + '<|eot_id|>' }}{% endif %}{% endfor %}
--- a/checkpoint-125/config.json
+++ b/checkpoint-125/config.json
@@ -0,0 +1,51 @@
+{
+  "_attn_implementation_autoset": false,
+  "add_cross_attention": false,
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "cross_attention_hidden_size": null,
+  "decoder_start_token_id": 128000,
+  "dtype": "bfloat16",
+  "eos_token_id": 128009,
+  "finetuning_task": null,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "is_decoder": false,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 128009,
+  "prefix": null,
+  "pretraining_tp": 1,
+  "pruned_heads": {},
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_theta": 500000,
+    "rope_type": "llama3"
+  },
+  "sep_token_id": null,
+  "task_specific_params": null,
+  "tf_legacy_loss": false,
+  "tie_encoder_decoder": false,
+  "tie_word_embeddings": false,
+  "tokenizer_class": null,
+  "torchscript": false,
+  "transformers_version": "5.7.0",
+  "use_bfloat16": false,
+  "use_cache": false,
+  "vocab_size": 128256
+}
--- a/checkpoint-125/generation_config.json
+++ b/checkpoint-125/generation_config.json
@@ -0,0 +1,37 @@
+{
+  "_from_model_config": true,
+  "begin_suppress_tokens": [
+    128000,
+    128001
+  ],
+  "bos_token_id": 128000,
+  "decoder_start_token_id": 128000,
+  "diversity_penalty": 0.0,
+  "do_sample": false,
+  "early_stopping": false,
+  "encoder_no_repeat_ngram_size": 0,
+  "eos_token_id": [
+    128009,
+    128001
+  ],
+  "length_penalty": 1.0,
+  "max_length": 20,
+  "min_length": 0,
+  "no_repeat_ngram_size": 0,
+  "num_beam_groups": 1,
+  "num_beams": 1,
+  "num_return_sequences": 1,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "output_scores": false,
+  "pad_token_id": 128009,
+  "remove_invalid_values": false,
+  "repetition_penalty": 1.0,
+  "return_dict_in_generate": false,
+  "temperature": 1.0,
+  "top_k": 50,
+  "top_p": 1.0,
+  "transformers_version": "5.7.0",
+  "typical_p": 1.0,
+  "use_cache": true
+}
--- a/checkpoint-125/model.safetensors
+++ b/checkpoint-125/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c62df6fb72dd12a9e9271297b004dad1ebf2701d81a0ce3790c491ab74eb84b8
+size 16060556616
--- a/checkpoint-125/tokenizer.json
+++ b/checkpoint-125/tokenizer.json
--- a/checkpoint-125/tokenizer_config.json
+++ b/checkpoint-125/tokenizer_config.json
@@ -0,0 +1,20 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "extra_special_tokens": [
+    "<|eom_id|>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|eot_id|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend"
+}
--- a/checkpoint-125/trainer_state.json
+++ b/checkpoint-125/trainer_state.json
@@ -0,0 +1,48 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 125,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.7079986148748518,
+      "learning_rate": 9.745834992450688e-06,
+      "loss": 0.3882425308227539,
+      "step": 50
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.6250265786305943,
+      "learning_rate": 8.64839582897015e-06,
+      "loss": 0.2884632110595703,
+      "step": 100
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 375,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2603673845760.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}
--- a/checkpoint-125/training_args.bin
+++ b/checkpoint-125/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c526375ec0015c66f3d30a2a29d46038359e1094e1eb4f00ba80454852d3c48
+size 7761
--- a/checkpoint-250/chat_template.jinja
+++ b/checkpoint-250/chat_template.jinja
@@ -0,0 +1,7 @@
+{{ '<|begin_of_text|>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|start_header_id|>system<|end_header_id|>
+
+' + system_message + '<|eot_id|>' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|start_header_id|>user<|end_header_id|>
+
+' + content + '<|eot_id|><|start_header_id|>assistant<|end_header_id|>
+
+' }}{% elif message['role'] == 'assistant' %}{{ content + '<|eot_id|>' }}{% endif %}{% endfor %}
--- a/checkpoint-250/config.json
+++ b/checkpoint-250/config.json
@@ -0,0 +1,51 @@
+{
+  "_attn_implementation_autoset": false,
+  "add_cross_attention": false,
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "cross_attention_hidden_size": null,
+  "decoder_start_token_id": 128000,
+  "dtype": "bfloat16",
+  "eos_token_id": 128009,
+  "finetuning_task": null,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "is_decoder": false,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 128009,
+  "prefix": null,
+  "pretraining_tp": 1,
+  "pruned_heads": {},
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_theta": 500000,
+    "rope_type": "llama3"
+  },
+  "sep_token_id": null,
+  "task_specific_params": null,
+  "tf_legacy_loss": false,
+  "tie_encoder_decoder": false,
+  "tie_word_embeddings": false,
+  "tokenizer_class": null,
+  "torchscript": false,
+  "transformers_version": "5.7.0",
+  "use_bfloat16": false,
+  "use_cache": false,
+  "vocab_size": 128256
+}
--- a/checkpoint-250/generation_config.json
+++ b/checkpoint-250/generation_config.json
@@ -0,0 +1,37 @@
+{
+  "_from_model_config": true,
+  "begin_suppress_tokens": [
+    128000,
+    128001
+  ],
+  "bos_token_id": 128000,
+  "decoder_start_token_id": 128000,
+  "diversity_penalty": 0.0,
+  "do_sample": false,
+  "early_stopping": false,
+  "encoder_no_repeat_ngram_size": 0,
+  "eos_token_id": [
+    128009,
+    128001
+  ],
+  "length_penalty": 1.0,
+  "max_length": 20,
+  "min_length": 0,
+  "no_repeat_ngram_size": 0,
+  "num_beam_groups": 1,
+  "num_beams": 1,
+  "num_return_sequences": 1,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "output_scores": false,
+  "pad_token_id": 128009,
+  "remove_invalid_values": false,
+  "repetition_penalty": 1.0,
+  "return_dict_in_generate": false,
+  "temperature": 1.0,
+  "top_k": 50,
+  "top_p": 1.0,
+  "transformers_version": "5.7.0",
+  "typical_p": 1.0,
+  "use_cache": true
+}
--- a/checkpoint-250/model.safetensors
+++ b/checkpoint-250/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8aed159dcfce3eb5fe23dffb1ae0c8ac97a6a7f1de95a7ad3c02203d2af8e4ae
+size 16060556616
--- a/checkpoint-250/tokenizer.json
+++ b/checkpoint-250/tokenizer.json
--- a/checkpoint-250/tokenizer_config.json
+++ b/checkpoint-250/tokenizer_config.json
@@ -0,0 +1,20 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "extra_special_tokens": [
+    "<|eom_id|>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|eot_id|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend"
+}
--- a/checkpoint-250/trainer_state.json
+++ b/checkpoint-250/trainer_state.json
@@ -0,0 +1,69 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 250,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.7079986148748518,
+      "learning_rate": 9.745834992450688e-06,
+      "loss": 0.3882425308227539,
+      "step": 50
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.6250265786305943,
+      "learning_rate": 8.64839582897015e-06,
+      "loss": 0.2884632110595703,
+      "step": 100
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.7014561886986339,
+      "learning_rate": 6.878381276221777e-06,
+      "loss": 0.24055294036865235,
+      "step": 150
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.6683347354350464,
+      "learning_rate": 4.762090420881289e-06,
+      "loss": 0.1965186309814453,
+      "step": 200
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.7284867299833838,
+      "learning_rate": 2.689657780298019e-06,
+      "loss": 0.19071041107177733,
+      "step": 250
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 375,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5203207127040.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}
--- a/checkpoint-250/training_args.bin
+++ b/checkpoint-250/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c526375ec0015c66f3d30a2a29d46038359e1094e1eb4f00ba80454852d3c48
+size 7761
--- a/checkpoint-375/chat_template.jinja
+++ b/checkpoint-375/chat_template.jinja
@@ -0,0 +1,7 @@
+{{ '<|begin_of_text|>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|start_header_id|>system<|end_header_id|>
+
+' + system_message + '<|eot_id|>' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|start_header_id|>user<|end_header_id|>
+
+' + content + '<|eot_id|><|start_header_id|>assistant<|end_header_id|>
+
+' }}{% elif message['role'] == 'assistant' %}{{ content + '<|eot_id|>' }}{% endif %}{% endfor %}
--- a/checkpoint-375/config.json
+++ b/checkpoint-375/config.json
@@ -0,0 +1,51 @@
+{
+  "_attn_implementation_autoset": false,
+  "add_cross_attention": false,
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "cross_attention_hidden_size": null,
+  "decoder_start_token_id": 128000,
+  "dtype": "bfloat16",
+  "eos_token_id": 128009,
+  "finetuning_task": null,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "is_decoder": false,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 128009,
+  "prefix": null,
+  "pretraining_tp": 1,
+  "pruned_heads": {},
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_theta": 500000,
+    "rope_type": "llama3"
+  },
+  "sep_token_id": null,
+  "task_specific_params": null,
+  "tf_legacy_loss": false,
+  "tie_encoder_decoder": false,
+  "tie_word_embeddings": false,
+  "tokenizer_class": null,
+  "torchscript": false,
+  "transformers_version": "5.7.0",
+  "use_bfloat16": false,
+  "use_cache": false,
+  "vocab_size": 128256
+}
--- a/checkpoint-375/generation_config.json
+++ b/checkpoint-375/generation_config.json
@@ -0,0 +1,37 @@
+{
+  "_from_model_config": true,
+  "begin_suppress_tokens": [
+    128000,
+    128001
+  ],
+  "bos_token_id": 128000,
+  "decoder_start_token_id": 128000,
+  "diversity_penalty": 0.0,
+  "do_sample": false,
+  "early_stopping": false,
+  "encoder_no_repeat_ngram_size": 0,
+  "eos_token_id": [
+    128009,
+    128001
+  ],
+  "length_penalty": 1.0,
+  "max_length": 20,
+  "min_length": 0,
+  "no_repeat_ngram_size": 0,
+  "num_beam_groups": 1,
+  "num_beams": 1,
+  "num_return_sequences": 1,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "output_scores": false,
+  "pad_token_id": 128009,
+  "remove_invalid_values": false,
+  "repetition_penalty": 1.0,
+  "return_dict_in_generate": false,
+  "temperature": 1.0,
+  "top_k": 50,
+  "top_p": 1.0,
+  "transformers_version": "5.7.0",
+  "typical_p": 1.0,
+  "use_cache": true
+}
--- a/checkpoint-375/model.safetensors
+++ b/checkpoint-375/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:208b87368ea03c736f7e59cec1ccaecd14b4dcd81abd1caafbd4aa9bf9ceccbe
+size 16060556616
--- a/checkpoint-375/tokenizer.json
+++ b/checkpoint-375/tokenizer.json
--- a/checkpoint-375/tokenizer_config.json
+++ b/checkpoint-375/tokenizer_config.json
@@ -0,0 +1,20 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "extra_special_tokens": [
+    "<|eom_id|>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|eot_id|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend"
+}
--- a/checkpoint-375/trainer_state.json
+++ b/checkpoint-375/trainer_state.json
@@ -0,0 +1,83 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 375,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.7079986148748518,
+      "learning_rate": 9.745834992450688e-06,
+      "loss": 0.3882425308227539,
+      "step": 50
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.6250265786305943,
+      "learning_rate": 8.64839582897015e-06,
+      "loss": 0.2884632110595703,
+      "step": 100
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.7014561886986339,
+      "learning_rate": 6.878381276221777e-06,
+      "loss": 0.24055294036865235,
+      "step": 150
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.6683347354350464,
+      "learning_rate": 4.762090420881289e-06,
+      "loss": 0.1965186309814453,
+      "step": 200
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.7284867299833838,
+      "learning_rate": 2.689657780298019e-06,
+      "loss": 0.19071041107177733,
+      "step": 250
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.8642127471212965,
+      "learning_rate": 1.0431326866479457e-06,
+      "loss": 0.12675453186035157,
+      "step": 300
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.71206320276362,
+      "learning_rate": 1.2604916083075236e-07,
+      "loss": 0.12834136962890624,
+      "step": 350
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 375,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 7801590251520.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}
--- a/checkpoint-375/training_args.bin
+++ b/checkpoint-375/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c526375ec0015c66f3d30a2a29d46038359e1094e1eb4f00ba80454852d3c48
+size 7761
--- a/config.json
+++ b/config.json
@@ -0,0 +1,51 @@
+{
+  "_attn_implementation_autoset": false,
+  "add_cross_attention": false,
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "cross_attention_hidden_size": null,
+  "decoder_start_token_id": 128000,
+  "dtype": "bfloat16",
+  "eos_token_id": 128009,
+  "finetuning_task": null,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "is_decoder": false,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 128009,
+  "prefix": null,
+  "pretraining_tp": 1,
+  "pruned_heads": {},
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_theta": 500000,
+    "rope_type": "llama3"
+  },
+  "sep_token_id": null,
+  "task_specific_params": null,
+  "tf_legacy_loss": false,
+  "tie_encoder_decoder": false,
+  "tie_word_embeddings": false,
+  "tokenizer_class": null,
+  "torchscript": false,
+  "transformers_version": "5.7.0",
+  "use_bfloat16": false,
+  "use_cache": false,
+  "vocab_size": 128256
+}
--- a/generation_config.json
+++ b/generation_config.json
@@ -0,0 +1,37 @@
+{
+  "_from_model_config": true,
+  "begin_suppress_tokens": [
+    128000,
+    128001
+  ],
+  "bos_token_id": 128000,
+  "decoder_start_token_id": 128000,
+  "diversity_penalty": 0.0,
+  "do_sample": false,
+  "early_stopping": false,
+  "encoder_no_repeat_ngram_size": 0,
+  "eos_token_id": [
+    128009,
+    128001
+  ],
+  "length_penalty": 1.0,
+  "max_length": 20,
+  "min_length": 0,
+  "no_repeat_ngram_size": 0,
+  "num_beam_groups": 1,
+  "num_beams": 1,
+  "num_return_sequences": 1,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "output_scores": false,
+  "pad_token_id": 128009,
+  "remove_invalid_values": false,
+  "repetition_penalty": 1.0,
+  "return_dict_in_generate": false,
+  "temperature": 1.0,
+  "top_k": 50,
+  "top_p": 1.0,
+  "transformers_version": "5.7.0",
+  "typical_p": 1.0,
+  "use_cache": true
+}
--- a/model.safetensors
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:208b87368ea03c736f7e59cec1ccaecd14b4dcd81abd1caafbd4aa9bf9ceccbe
+size 16060556616
--- a/tokenizer.json
+++ b/tokenizer.json
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,20 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "extra_special_tokens": [
+    "<|eom_id|>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|eot_id|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend"
+}
--- a/train_results.json
+++ b/train_results.json
@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 7801590251520.0,
+    "train_loss": 0.21588493855794272,
+    "train_runtime": 11728.7173,
+    "train_samples_per_second": 2.046,
+    "train_steps_per_second": 0.032
+}
--- a/trainer_log.jsonl
+++ b/trainer_log.jsonl
@@ -0,0 +1,8 @@
+{"current_steps": 50, "total_steps": 375, "loss": 0.3882425308227539, "lr": 9.745834992450688e-06, "epoch": 0.4, "percentage": 13.33, "elapsed_time": "0:26:00", "remaining_time": "2:49:03"}
+{"current_steps": 100, "total_steps": 375, "loss": 0.2884632110595703, "lr": 8.64839582897015e-06, "epoch": 0.8, "percentage": 26.67, "elapsed_time": "0:51:59", "remaining_time": "2:22:57"}
+{"current_steps": 150, "total_steps": 375, "loss": 0.24055294036865235, "lr": 6.878381276221777e-06, "epoch": 1.2, "percentage": 40.0, "elapsed_time": "1:18:12", "remaining_time": "1:57:18"}
+{"current_steps": 200, "total_steps": 375, "loss": 0.1965186309814453, "lr": 4.762090420881289e-06, "epoch": 1.6, "percentage": 53.33, "elapsed_time": "1:44:09", "remaining_time": "1:31:08"}
+{"current_steps": 250, "total_steps": 375, "loss": 0.19071041107177733, "lr": 2.689657780298019e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "2:10:05", "remaining_time": "1:05:02"}
+{"current_steps": 300, "total_steps": 375, "loss": 0.12675453186035157, "lr": 1.0431326866479457e-06, "epoch": 2.4, "percentage": 80.0, "elapsed_time": "2:36:18", "remaining_time": "0:39:04"}
+{"current_steps": 350, "total_steps": 375, "loss": 0.12834136962890624, "lr": 1.2604916083075236e-07, "epoch": 2.8, "percentage": 93.33, "elapsed_time": "3:02:15", "remaining_time": "0:13:01"}
+{"current_steps": 375, "total_steps": 375, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "3:15:28", "remaining_time": "0:00:00"}
--- a/trainer_state.json
+++ b/trainer_state.json
@@ -0,0 +1,92 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 375,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.7079986148748518,
+      "learning_rate": 9.745834992450688e-06,
+      "loss": 0.3882425308227539,
+      "step": 50
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.6250265786305943,
+      "learning_rate": 8.64839582897015e-06,
+      "loss": 0.2884632110595703,
+      "step": 100
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.7014561886986339,
+      "learning_rate": 6.878381276221777e-06,
+      "loss": 0.24055294036865235,
+      "step": 150
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.6683347354350464,
+      "learning_rate": 4.762090420881289e-06,
+      "loss": 0.1965186309814453,
+      "step": 200
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.7284867299833838,
+      "learning_rate": 2.689657780298019e-06,
+      "loss": 0.19071041107177733,
+      "step": 250
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.8642127471212965,
+      "learning_rate": 1.0431326866479457e-06,
+      "loss": 0.12675453186035157,
+      "step": 300
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.71206320276362,
+      "learning_rate": 1.2604916083075236e-07,
+      "loss": 0.12834136962890624,
+      "step": 350
+    },
+    {
+      "epoch": 3.0,
+      "step": 375,
+      "total_flos": 7801590251520.0,
+      "train_loss": 0.21588493855794272,
+      "train_runtime": 11728.7173,
+      "train_samples_per_second": 2.046,
+      "train_steps_per_second": 0.032
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 375,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 7801590251520.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}
--- a/training_args.bin
+++ b/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c526375ec0015c66f3d30a2a29d46038359e1094e1eb4f00ba80454852d3c48
+size 7761