capmix single-domain code_cap_b4000_s0 (marin-8b-base)

.gitattributes

@@ -33,3 +33,5 @@ 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
+checkpoint-63/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

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_b4000_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_b4000_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-code__mix_code_cap_b4000_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: 1
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 5.7.0
+- Pytorch 2.13.0+cu130
+- Datasets 4.0.0
+- Tokenizers 0.22.2

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 2295712972800.0,
+    "train_loss": 0.2977916778080047,
+    "train_runtime": 2018.1852,
+    "train_samples_per_second": 1.982,
+    "train_steps_per_second": 0.031
+}

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 %}

checkpoint-63/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 %}

checkpoint-63/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
+}

checkpoint-63/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
+}

checkpoint-63/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0aaa2276192b5b03d71917041b3d154e59c16c6ff1a24e5f64aa3920833c3f99
+size 16060556616

checkpoint-63/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920

checkpoint-63/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"
+}

checkpoint-63/trainer_state.json

@@ -0,0 +1,41 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 63,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.5070397515220946,
+      "learning_rate": 1.2443403456474017e-06,
+      "loss": 0.30378759384155274,
+      "step": 50
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 63,
+  "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": 2295712972800.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-63/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da25d45395525d55c46a7dd6872e546185bf25e986085e3239afb4ae3cc1ad11
+size 7761

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
+}

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
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0aaa2276192b5b03d71917041b3d154e59c16c6ff1a24e5f64aa3920833c3f99
+size 16060556616

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920

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"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 2295712972800.0,
+    "train_loss": 0.2977916778080047,
+    "train_runtime": 2018.1852,
+    "train_samples_per_second": 1.982,
+    "train_steps_per_second": 0.031
+}

trainer_log.jsonl

@@ -0,0 +1,2 @@
+{"current_steps": 50, "total_steps": 63, "loss": 0.30378759384155274, "lr": 1.2443403456474017e-06, "epoch": 0.8, "percentage": 79.37, "elapsed_time": "0:26:47", "remaining_time": "0:06:57"}
+{"current_steps": 63, "total_steps": 63, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:33:38", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,50 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 63,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.5070397515220946,
+      "learning_rate": 1.2443403456474017e-06,
+      "loss": 0.30378759384155274,
+      "step": 50
+    },
+    {
+      "epoch": 1.0,
+      "step": 63,
+      "total_flos": 2295712972800.0,
+      "train_loss": 0.2977916778080047,
+      "train_runtime": 2018.1852,
+      "train_samples_per_second": 1.982,
+      "train_steps_per_second": 0.031
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 63,
+  "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": 2295712972800.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da25d45395525d55c46a7dd6872e546185bf25e986085e3239afb4ae3cc1ad11
+size 7761