Model save

README.md

@@ -0,0 +1,67 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- trl
+- sft
+- generated_from_trainer
+base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
+model-index:
+- name: tiny-llama-20p
+  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. -->
+
+# tiny-llama-20p
+
+This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: nan
+
+## 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: 14
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 224
+- total_eval_batch_size: 4
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.0275        | 0.99  | 96   | nan             |
+
+
+### Framework versions
+
+- PEFT 0.7.1
+- Transformers 4.39.0.dev0
+- Pytorch 2.2.2+cu121
+- Datasets 2.14.6
+- Tokenizers 0.15.2

adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "q_proj",
+    "down_proj",
+    "v_proj",
+    "o_proj",
+    "k_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0665f8405a2c0e46f09ae327e51110211a09e75e81a3fb24e66c0fbc5223084b
+size 25272360

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.99,
+    "train_loss": 1.0698106847703457,
+    "train_runtime": 2647.5008,
+    "train_samples": 21594,
+    "train_samples_per_second": 8.156,
+    "train_steps_per_second": 0.036
+}

runs/Apr30_03-33-37_ip-172-31-69-60.ec2.internal/events.out.tfevents.1714448127.ip-172-31-69-60.ec2.internal.18260.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65fcffe30297aad68c13d6766805736cf4c6938c633ffb9aba1f7550c71341b2
+size 4946

runs/Apr30_03-37-35_ip-172-31-69-60.ec2.internal/events.out.tfevents.1714448265.ip-172-31-69-60.ec2.internal.20637.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54463644680f37661e1c263aa663608be8489dd1f485a077624990e3cc8a3677
+size 4738

runs/Apr30_03-38-29_ip-172-31-69-60.ec2.internal/events.out.tfevents.1714448315.ip-172-31-69-60.ec2.internal.21254.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:563803193818dd679c56a22761f528a780ecf5a5c5d0719ebd9b73b8cd0a2d94
+size 5359

runs/Apr30_03-40-35_ip-172-31-69-60.ec2.internal/events.out.tfevents.1714448440.ip-172-31-69-60.ec2.internal.22451.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06b62054282b7bce4fe11e67f7f45b3b8305332d5644e48da62fdbc5ae1497cc
+size 5152

runs/Apr30_03-41-46_ip-172-31-69-60.ec2.internal/events.out.tfevents.1714448511.ip-172-31-69-60.ec2.internal.23313.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf96b20f7c179c0b2a127e64fe37989b648c7056c01d605db5c6d964d678e4ef
+size 4945

runs/Apr30_03-42-46_ip-172-31-69-60.ec2.internal/events.out.tfevents.1714448572.ip-172-31-69-60.ec2.internal.24076.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f99fc04ede88bae4ed8eba4420425c6f6175c010897ce4ff8180391976fa22cf
+size 4945

runs/Apr30_03-44-15_ip-172-31-69-60.ec2.internal/events.out.tfevents.1714448661.ip-172-31-69-60.ec2.internal.25121.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8bed6476f979bb42e126e641a36bddae61482795de45ccbeab286de5a821045
+size 4945

runs/Apr30_03-45-03_ip-172-31-69-60.ec2.internal/events.out.tfevents.1714448708.ip-172-31-69-60.ec2.internal.25755.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf43a13e0f5e2871edd767d3841c672487ac88b973920c55457be74968d02eda
+size 4946

runs/Apr30_03-46-24_ip-172-31-69-60.ec2.internal/events.out.tfevents.1714448790.ip-172-31-69-60.ec2.internal.26784.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee4451fa9a22e0277980eb8adce23474827ed8a0602a2b108344a0a174c47a21
+size 9492

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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": "</s>",
+  "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 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.99,
+    "train_loss": 1.0698106847703457,
+    "train_runtime": 2647.5008,
+    "train_samples": 21594,
+    "train_samples_per_second": 8.156,
+    "train_steps_per_second": 0.036
+}

trainer_state.json

@@ -0,0 +1,178 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9948186528497409,
+  "eval_steps": 500,
+  "global_step": 96,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "grad_norm": 0.407313588435244,
+      "learning_rate": 2e-05,
+      "loss": 1.4393,
+      "step": 1
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.44021568832651153,
+      "learning_rate": 0.0001,
+      "loss": 1.4151,
+      "step": 5
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.4536750312789675,
+      "learning_rate": 0.0002,
+      "loss": 1.3352,
+      "step": 10
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.18522669739061845,
+      "learning_rate": 0.00019833656768294662,
+      "loss": 1.1436,
+      "step": 15
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.11940000702730413,
+      "learning_rate": 0.0001934016108732548,
+      "loss": 1.0861,
+      "step": 20
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.11067706553060182,
+      "learning_rate": 0.00018535930890373466,
+      "loss": 1.0546,
+      "step": 25
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.08326696985890841,
+      "learning_rate": 0.0001744772182743782,
+      "loss": 1.0452,
+      "step": 30
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.07551662936007832,
+      "learning_rate": 0.00016111737140978494,
+      "loss": 1.0374,
+      "step": 35
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.06940303607219772,
+      "learning_rate": 0.00014572423233046386,
+      "loss": 1.0203,
+      "step": 40
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.0646380507229549,
+      "learning_rate": 0.00012880990993652377,
+      "loss": 1.0025,
+      "step": 45
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.06370005100951007,
+      "learning_rate": 0.00011093712083778746,
+      "loss": 1.0186,
+      "step": 50
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.06034880535670624,
+      "learning_rate": 9.270046853390925e-05,
+      "loss": 1.0299,
+      "step": 55
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.06311665876872108,
+      "learning_rate": 7.470666176083192e-05,
+      "loss": 1.0156,
+      "step": 60
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.06131237795687744,
+      "learning_rate": 5.755433011241851e-05,
+      "loss": 1.0074,
+      "step": 65
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.06522472527006118,
+      "learning_rate": 4.181410844420474e-05,
+      "loss": 1.0452,
+      "step": 70
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.06426335241789467,
+      "learning_rate": 2.800965262420043e-05,
+      "loss": 1.0238,
+      "step": 75
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.06843282189243624,
+      "learning_rate": 1.660021821101222e-05,
+      "loss": 1.0167,
+      "step": 80
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.06475830798907048,
+      "learning_rate": 7.96538164308407e-06,
+      "loss": 1.0045,
+      "step": 85
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.06274448627075681,
+      "learning_rate": 2.392412244407294e-06,
+      "loss": 1.0133,
+      "step": 90
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.06343293325060437,
+      "learning_rate": 6.671516297606095e-08,
+      "loss": 1.0275,
+      "step": 95
+    },
+    {
+      "epoch": 0.99,
+      "eval_loss": NaN,
+      "eval_runtime": 238.4177,
+      "eval_samples_per_second": 9.689,
+      "eval_steps_per_second": 2.424,
+      "step": 96
+    },
+    {
+      "epoch": 0.99,
+      "step": 96,
+      "total_flos": 3308484214915072.0,
+      "train_loss": 1.0698106847703457,
+      "train_runtime": 2647.5008,
+      "train_samples_per_second": 8.156,
+      "train_steps_per_second": 0.036
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 96,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "total_flos": 3308484214915072.0,
+  "train_batch_size": 14,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92f31cebd24882b84aa4fdbdf0cf64186ae6aa3917df1d5758d5063b6fbbc7fc
+size 6072