Upload folder using huggingface_hub

README.md

@@ -0,0 +1,131 @@
+---
+license: apache-2.0
+base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
+tags:
+- generated_from_trainer
+model-index:
+- name: TinyLlama-PsychiatryCaseNotes-epochs-1-lr-0002
+  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. -->
+
+[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.4.0`
+```yaml
+adapter: null
+base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
+bf16: auto
+dataset_prepared_path: last_run_prepared
+datasets:
+- path: utrgvseniorproject/Tinybook
+  type: completion
+debug: null
+deepspeed: null
+early_stopping_patience: null
+eval_sample_packing: false
+eval_table_size: null
+evals_per_epoch: 4
+flash_attention: true
+flash_attn_cross_entropy: false
+flash_attn_fuse_mlp: true
+flash_attn_fuse_qkv: false
+flash_attn_rms_norm: true
+fp16: null
+fsdp: null
+fsdp_config: null
+gradient_accumulation_steps: 1
+gradient_checkpointing: true
+group_by_length: false
+learning_rate: 0.0002
+load_in_4bit: false
+load_in_8bit: false
+local_rank: null
+logging_steps: 1
+lora_alpha: null
+lora_dropout: null
+lora_fan_in_fan_out: null
+lora_model_dir: null
+lora_r: null
+lora_target_linear: null
+lr_scheduler: cosine
+micro_batch_size: 1
+model_type: LlamaForCausalLM
+num_epochs: 1
+optimizer: adamw_bnb_8bit
+output_dir: ./TinyLlama-PsychiatryCaseNotes-epochs-1-lr-0002
+pad_to_sequence_len: true
+resume_from_checkpoint: null
+sample_packing: true
+saves_per_epoch: 1
+sequence_len: 2048
+special_tokens: null
+strict: false
+tf32: false
+tokenizer_type: LlamaTokenizer
+train_on_inputs: false
+val_set_size: 0.05
+wandb_entity: utrgvmedai
+wandb_log_model: null
+wandb_name: tinyLama_colab_test_2
+wandb_project: TinyLlama-PsychiatryCaseNotes-epochs-1-lr-0002
+wandb_watch: null
+warmup_steps: 100
+weight_decay: 0.1
+xformers_attention: null
+
+```
+
+</details><br>
+
+# TinyLlama-PsychiatryCaseNotes-epochs-1-lr-0002
+
+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: 1.8020
+
+## 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: 1
+- eval_batch_size: 1
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.7259        | 0.04  | 1    | 1.9138          |
+| 1.8148        | 0.26  | 6    | 1.9011          |
+| 1.8631        | 0.52  | 12   | 1.8659          |
+| 1.8768        | 0.78  | 18   | 1.8020          |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.1.2+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.0

checkpoint-23/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": "4.38.2",
+  "use_cache": false,
+  "vocab_size": 32000
+}

checkpoint-23/generation_config.json

@@ -0,0 +1,8 @@
+{
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "max_length": 2048,
+  "pad_token_id": 0,
+  "transformers_version": "4.38.2"
+}

checkpoint-23/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba30f671d999fe633d081c0421918318256694dc5e34fc9716fe553a3c955ed1
+size 2200117448

checkpoint-23/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4ea382251858d90b652feb78299e4cfd871c4e0f5cc4ff0b8545c47c81d6669
+size 2205132090

checkpoint-23/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b3ee827a7a00012c0a116546df467feee35e70376d81a7a85b1a70eb90414d3
+size 14244

checkpoint-23/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d628143488a87bbd00a601b9e0c49fc74e98baeb714f6509744eab74f54d1813
+size 1064

checkpoint-23/trainer_state.json

@@ -0,0 +1,214 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 6,
+  "global_step": 23,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04,
+      "grad_norm": 6.0,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.7259,
+      "step": 1
+    },
+    {
+      "epoch": 0.04,
+      "eval_loss": 1.913841724395752,
+      "eval_runtime": 0.1057,
+      "eval_samples_per_second": 18.922,
+      "eval_steps_per_second": 18.922,
+      "step": 1
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 7.0,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.8344,
+      "step": 2
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 6.1875,
+      "learning_rate": 6e-06,
+      "loss": 1.8468,
+      "step": 3
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 6.3125,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 1.7955,
+      "step": 4
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 6.0625,
+      "learning_rate": 1e-05,
+      "loss": 1.8767,
+      "step": 5
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 6.6875,
+      "learning_rate": 1.2e-05,
+      "loss": 1.8148,
+      "step": 6
+    },
+    {
+      "epoch": 0.26,
+      "eval_loss": 1.901075005531311,
+      "eval_runtime": 0.1023,
+      "eval_samples_per_second": 19.547,
+      "eval_steps_per_second": 19.547,
+      "step": 6
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 6.9375,
+      "learning_rate": 1.4000000000000001e-05,
+      "loss": 1.9312,
+      "step": 7
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 6.25,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 1.832,
+      "step": 8
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 6.375,
+      "learning_rate": 1.8e-05,
+      "loss": 1.8511,
+      "step": 9
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 6.5625,
+      "learning_rate": 2e-05,
+      "loss": 1.9536,
+      "step": 10
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 6.3125,
+      "learning_rate": 2.2000000000000003e-05,
+      "loss": 1.9282,
+      "step": 11
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 6.125,
+      "learning_rate": 2.4e-05,
+      "loss": 1.8631,
+      "step": 12
+    },
+    {
+      "epoch": 0.52,
+      "eval_loss": 1.8658802509307861,
+      "eval_runtime": 0.1025,
+      "eval_samples_per_second": 19.508,
+      "eval_steps_per_second": 19.508,
+      "step": 12
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 6.15625,
+      "learning_rate": 2.6000000000000002e-05,
+      "loss": 1.8138,
+      "step": 13
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 6.5625,
+      "learning_rate": 2.8000000000000003e-05,
+      "loss": 1.7873,
+      "step": 14
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 12.875,
+      "learning_rate": 3e-05,
+      "loss": 1.9504,
+      "step": 15
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 6.53125,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 1.7767,
+      "step": 16
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 7.09375,
+      "learning_rate": 3.4000000000000007e-05,
+      "loss": 1.9669,
+      "step": 17
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 6.96875,
+      "learning_rate": 3.6e-05,
+      "loss": 1.8768,
+      "step": 18
+    },
+    {
+      "epoch": 0.78,
+      "eval_loss": 1.8019580841064453,
+      "eval_runtime": 0.1033,
+      "eval_samples_per_second": 19.362,
+      "eval_steps_per_second": 19.362,
+      "step": 18
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 6.5625,
+      "learning_rate": 3.8e-05,
+      "loss": 1.6976,
+      "step": 19
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 5.90625,
+      "learning_rate": 4e-05,
+      "loss": 1.7206,
+      "step": 20
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 6.5,
+      "learning_rate": 4.2e-05,
+      "loss": 1.884,
+      "step": 21
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 6.53125,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 2.005,
+      "step": 22
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 6.09375,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 1.7929,
+      "step": 23
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 23,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 292378028015616.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-23/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d9c490b52d0079996aa8fe2e1d328e7be40b73d158b23ea0b114134e1124760
+size 5688

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": "4.38.2",
+  "use_cache": false,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "max_length": 2048,
+  "pad_token_id": 0,
+  "transformers_version": "4.38.2"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67e8b25ed3014fa68dcc813285269f1b7af8cb41c3fc9fa1bdaeba70e2a85863
+size 2200160278

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 +1,44 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "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>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}