Upload 15 files

README.md

@@ -0,0 +1,59 @@
+---
+license: other
+base_model: models/tinyllama-rubra-2
+tags:
+- llama-factory
+- freeze
+- generated_from_trainer
+model-index:
+- name: sft
+  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. -->
+
+# sft
+
+This model is a fine-tuned version of [models/tinyllama-rubra-2](https://huggingface.co/models/tinyllama-rubra-2) on the test_data2 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6112
+
+## 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: 0.0001
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 10.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.43.4
+- Pytorch 2.4.0+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 9.887640449438202,
+    "eval_loss": 0.6112431287765503,
+    "eval_runtime": 0.0915,
+    "eval_samples_per_second": 109.273,
+    "eval_steps_per_second": 109.273,
+    "total_flos": 580815710552064.0,
+    "train_loss": 0.4857807181098244,
+    "train_runtime": 12.3878,
+    "train_samples_per_second": 71.845,
+    "train_steps_per_second": 8.88
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "models/tinyllama-rubra-2",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "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": 23,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.43.4",
+  "use_cache": false,
+  "vocab_size": 32000
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 9.887640449438202,
+    "eval_loss": 0.6112431287765503,
+    "eval_runtime": 0.0915,
+    "eval_samples_per_second": 109.273,
+    "eval_steps_per_second": 109.273
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.43.4"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e84091e2472826cf6642e7809952120e258033842aedb4d1d79e741deef6d227
+size 2376298056

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% set system_message = 'You are Zephyr, a helpful assistant.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|system|>\n' + system_message + '</s>' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|user|>\n' + content + '</s>' + '<|assistant|>\n' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 9.887640449438202,
+    "total_flos": 580815710552064.0,
+    "train_loss": 0.4857807181098244,
+    "train_runtime": 12.3878,
+    "train_samples_per_second": 71.845,
+    "train_steps_per_second": 8.88
+}

trainer_log.jsonl

@@ -0,0 +1,12 @@
+{"current_steps": 10, "total_steps": 110, "loss": 1.8614, "learning_rate": 9.090909090909092e-05, "epoch": 0.898876404494382, "percentage": 9.09, "elapsed_time": "0:00:01", "remaining_time": "0:00:13", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 20, "total_steps": 110, "loss": 0.9497, "learning_rate": 9.797464868072488e-05, "epoch": 1.797752808988764, "percentage": 18.18, "elapsed_time": "0:00:02", "remaining_time": "0:00:10", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 30, "total_steps": 110, "loss": 0.6147, "learning_rate": 9.118382907149165e-05, "epoch": 2.696629213483146, "percentage": 27.27, "elapsed_time": "0:00:03", "remaining_time": "0:00:08", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 40, "total_steps": 110, "loss": 0.4921, "learning_rate": 8.028048435688333e-05, "epoch": 3.595505617977528, "percentage": 36.36, "elapsed_time": "0:00:04", "remaining_time": "0:00:07", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 50, "total_steps": 110, "loss": 0.3398, "learning_rate": 6.635339816587109e-05, "epoch": 4.49438202247191, "percentage": 45.45, "elapsed_time": "0:00:05", "remaining_time": "0:00:06", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 60, "total_steps": 110, "loss": 0.2866, "learning_rate": 5.0793298191740404e-05, "epoch": 5.393258426966292, "percentage": 54.55, "elapsed_time": "0:00:06", "remaining_time": "0:00:05", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 70, "total_steps": 110, "loss": 0.2223, "learning_rate": 3.515398123358627e-05, "epoch": 6.292134831460674, "percentage": 63.64, "elapsed_time": "0:00:07", "remaining_time": "0:00:04", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 80, "total_steps": 110, "loss": 0.1728, "learning_rate": 2.09971545214401e-05, "epoch": 7.191011235955056, "percentage": 72.73, "elapsed_time": "0:00:07", "remaining_time": "0:00:02", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 90, "total_steps": 110, "loss": 0.1539, "learning_rate": 9.73648712344707e-06, "epoch": 8.089887640449438, "percentage": 81.82, "elapsed_time": "0:00:08", "remaining_time": "0:00:01", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 100, "total_steps": 110, "loss": 0.1284, "learning_rate": 2.496444112952734e-06, "epoch": 8.98876404494382, "percentage": 90.91, "elapsed_time": "0:00:09", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 110, "total_steps": 110, "loss": 0.1219, "learning_rate": 0.0, "epoch": 9.887640449438202, "percentage": 100.0, "elapsed_time": "0:00:10", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 110, "total_steps": 110, "epoch": 9.887640449438202, "percentage": 100.0, "elapsed_time": "0:00:12", "remaining_time": "0:00:00", "throughput": "0.00", "total_tokens": 0}

trainer_state.json

@@ -0,0 +1,119 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.887640449438202,
+  "eval_steps": 500,
+  "global_step": 110,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.898876404494382,
+      "grad_norm": 4.312319755554199,
+      "learning_rate": 9.090909090909092e-05,
+      "loss": 1.8614,
+      "step": 10
+    },
+    {
+      "epoch": 1.797752808988764,
+      "grad_norm": 1.8239428997039795,
+      "learning_rate": 9.797464868072488e-05,
+      "loss": 0.9497,
+      "step": 20
+    },
+    {
+      "epoch": 2.696629213483146,
+      "grad_norm": 2.482679843902588,
+      "learning_rate": 9.118382907149165e-05,
+      "loss": 0.6147,
+      "step": 30
+    },
+    {
+      "epoch": 3.595505617977528,
+      "grad_norm": 1.4796712398529053,
+      "learning_rate": 8.028048435688333e-05,
+      "loss": 0.4921,
+      "step": 40
+    },
+    {
+      "epoch": 4.49438202247191,
+      "grad_norm": 1.1127064228057861,
+      "learning_rate": 6.635339816587109e-05,
+      "loss": 0.3398,
+      "step": 50
+    },
+    {
+      "epoch": 5.393258426966292,
+      "grad_norm": 1.4359052181243896,
+      "learning_rate": 5.0793298191740404e-05,
+      "loss": 0.2866,
+      "step": 60
+    },
+    {
+      "epoch": 6.292134831460674,
+      "grad_norm": 1.3968243598937988,
+      "learning_rate": 3.515398123358627e-05,
+      "loss": 0.2223,
+      "step": 70
+    },
+    {
+      "epoch": 7.191011235955056,
+      "grad_norm": 1.2981433868408203,
+      "learning_rate": 2.09971545214401e-05,
+      "loss": 0.1728,
+      "step": 80
+    },
+    {
+      "epoch": 8.089887640449438,
+      "grad_norm": 0.8524450063705444,
+      "learning_rate": 9.73648712344707e-06,
+      "loss": 0.1539,
+      "step": 90
+    },
+    {
+      "epoch": 8.98876404494382,
+      "grad_norm": 1.1347664594650269,
+      "learning_rate": 2.496444112952734e-06,
+      "loss": 0.1284,
+      "step": 100
+    },
+    {
+      "epoch": 9.887640449438202,
+      "grad_norm": 0.8518253564834595,
+      "learning_rate": 0.0,
+      "loss": 0.1219,
+      "step": 110
+    },
+    {
+      "epoch": 9.887640449438202,
+      "step": 110,
+      "total_flos": 580815710552064.0,
+      "train_loss": 0.4857807181098244,
+      "train_runtime": 12.3878,
+      "train_samples_per_second": 71.845,
+      "train_steps_per_second": 8.88
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 110,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "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": 580815710552064.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c3bf01f4ef562949b3684316964295ce8dcd0d6b14d3eb2c5ddb08319ea9f4e
+size 5368