Model save

README.md

@@ -0,0 +1,65 @@
+---
+license: apache-2.0
+base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
+tags:
+- trl
+- sft
+- generated_from_trainer
+model-index:
+- name: tinyllama-sft-vicuna-10k-small-user-length
+  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. -->
+
+# tinyllama-sft-vicuna-10k-small-user-length
+
+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 an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8264
+
+## 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: 2e-05
+- train_batch_size: 16
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 128
+- total_eval_batch_size: 32
+- 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 |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.8347        | 0.9936 | 78   | 0.8264          |
+
+
+### Framework versions
+
+- Transformers 4.40.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 32000
+}

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9936305732484076,
+    "total_flos": 11234023833600.0,
+    "train_loss": 0.8476498554914426,
+    "train_runtime": 656.6949,
+    "train_samples": 10000,
+    "train_samples_per_second": 15.228,
+    "train_steps_per_second": 0.119
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
+  "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,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 22,
+  "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": "4.40.2",
+  "use_cache": false,
+  "vocab_size": 32001
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 2048,
+  "pad_token_id": 0,
+  "transformers_version": "4.40.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f43ccf03d5013b94b83dea058bd3c3a7578cdb6711521e86b611a8a881b3e6b
+size 2200128056

runs/May29_09-36-59_illidan.cs.ucla.edu/events.out.tfevents.1717000695.illidan.cs.ucla.edu.1433104.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80522fc4109cf7c7c607c8cd510cf28fd201db9fa77228769fc1ab38df8a2951
+size 8936

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": "[PAD]",
+    "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 +1,50 @@
+{
+  "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
+    },
+    "32000": {
+      "content": "[PAD]",
+      "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": "[PAD]",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9936305732484076,
+    "total_flos": 11234023833600.0,
+    "train_loss": 0.8476498554914426,
+    "train_runtime": 656.6949,
+    "train_samples": 10000,
+    "train_samples_per_second": 15.228,
+    "train_steps_per_second": 0.119
+}

trainer_state.json

@@ -0,0 +1,150 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9936305732484076,
+  "eval_steps": 500,
+  "global_step": 78,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.012738853503184714,
+      "grad_norm": 9.419306860000189,
+      "learning_rate": 2.5e-06,
+      "loss": 1.2082,
+      "step": 1
+    },
+    {
+      "epoch": 0.06369426751592357,
+      "grad_norm": 11.154561988265748,
+      "learning_rate": 1.25e-05,
+      "loss": 1.1572,
+      "step": 5
+    },
+    {
+      "epoch": 0.12738853503184713,
+      "grad_norm": 0.9580718367338527,
+      "learning_rate": 1.9959742939952393e-05,
+      "loss": 0.926,
+      "step": 10
+    },
+    {
+      "epoch": 0.1910828025477707,
+      "grad_norm": 0.6962618582606526,
+      "learning_rate": 1.9510565162951538e-05,
+      "loss": 0.8462,
+      "step": 15
+    },
+    {
+      "epoch": 0.25477707006369427,
+      "grad_norm": 0.652360226118771,
+      "learning_rate": 1.8584487936018663e-05,
+      "loss": 0.8207,
+      "step": 20
+    },
+    {
+      "epoch": 0.3184713375796178,
+      "grad_norm": 0.6036498850889884,
+      "learning_rate": 1.7227948638273918e-05,
+      "loss": 0.8328,
+      "step": 25
+    },
+    {
+      "epoch": 0.3821656050955414,
+      "grad_norm": 0.6106437850436714,
+      "learning_rate": 1.5508969814521026e-05,
+      "loss": 0.8184,
+      "step": 30
+    },
+    {
+      "epoch": 0.445859872611465,
+      "grad_norm": 0.6112027883233256,
+      "learning_rate": 1.3513748240813429e-05,
+      "loss": 0.829,
+      "step": 35
+    },
+    {
+      "epoch": 0.5095541401273885,
+      "grad_norm": 0.5896867860825263,
+      "learning_rate": 1.1342332658176556e-05,
+      "loss": 0.8223,
+      "step": 40
+    },
+    {
+      "epoch": 0.5732484076433121,
+      "grad_norm": 0.6019677830367037,
+      "learning_rate": 9.103606910965666e-06,
+      "loss": 0.7841,
+      "step": 45
+    },
+    {
+      "epoch": 0.6369426751592356,
+      "grad_norm": 0.5830221008800777,
+      "learning_rate": 6.909830056250527e-06,
+      "loss": 0.8322,
+      "step": 50
+    },
+    {
+      "epoch": 0.7006369426751592,
+      "grad_norm": 0.5839501242867685,
+      "learning_rate": 4.87100722594094e-06,
+      "loss": 0.8069,
+      "step": 55
+    },
+    {
+      "epoch": 0.7643312101910829,
+      "grad_norm": 0.5957554055545055,
+      "learning_rate": 3.089373510131354e-06,
+      "loss": 0.7856,
+      "step": 60
+    },
+    {
+      "epoch": 0.8280254777070064,
+      "grad_norm": 0.5870067617046513,
+      "learning_rate": 1.6542674627869738e-06,
+      "loss": 0.8141,
+      "step": 65
+    },
+    {
+      "epoch": 0.89171974522293,
+      "grad_norm": 0.557541376858347,
+      "learning_rate": 6.37651293602628e-07,
+      "loss": 0.7947,
+      "step": 70
+    },
+    {
+      "epoch": 0.9554140127388535,
+      "grad_norm": 0.5998913867246424,
+      "learning_rate": 9.0502382320653e-08,
+      "loss": 0.8347,
+      "step": 75
+    },
+    {
+      "epoch": 0.9936305732484076,
+      "eval_loss": 0.8263773322105408,
+      "eval_runtime": 9.6507,
+      "eval_samples_per_second": 51.81,
+      "eval_steps_per_second": 1.658,
+      "step": 78
+    },
+    {
+      "epoch": 0.9936305732484076,
+      "step": 78,
+      "total_flos": 11234023833600.0,
+      "train_loss": 0.8476498554914426,
+      "train_runtime": 656.6949,
+      "train_samples_per_second": 15.228,
+      "train_steps_per_second": 0.119
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 78,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "total_flos": 11234023833600.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d9329c075b7a238a0dc7df679763c512d2341681088017ea10a86cdb2be6632
+size 6328