Training in progress, step 20

README.md

@@ -0,0 +1,86 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- generator
+base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
+model-index:
+- name: Tukan-1.1B-Chat-v0.1
+  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. -->
+
+# Tukan-1.1B-Chat-v0.1
+
+This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0546
+
+## 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: 4e-05
+- train_batch_size: 6
+- eval_batch_size: 4
+- seed: 42
+- distributed_type: multi-GPU
+- gradient_accumulation_steps: 36
+- total_train_batch_size: 216
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.1912        | 0.28  | 10   | 1.1099          |
+| 1.1238        | 0.55  | 20   | 1.0655          |
+| 1.1258        | 0.83  | 30   | 1.0550          |
+
+
+### Framework versions
+
+- Transformers 4.36.2
+- Pytorch 2.2.0a0+gitd925d94
+- Datasets 2.14.6
+- Tokenizers 0.15.0
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float16
+
+### Framework versions
+
+
+- PEFT 0.6.1

adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "./data/Tukan-1.1B-Chat_merged",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "down_proj",
+    "gate_proj",
+    "lm_head",
+    "k_proj",
+    "q_proj",
+    "up_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c56144c85bc25b19ca10ca1f4480428776f64332bf7454d9887c134827154827
+size 26362152

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 1.0545984506607056,
+    "eval_runtime": 9.2861,
+    "eval_samples": 130,
+    "eval_samples_per_second": 5.061,
+    "eval_steps_per_second": 1.292,
+    "train_loss": 1.1544433269235823,
+    "train_runtime": 5078.5964,
+    "train_samples": 29726,
+    "train_samples_per_second": 1.537,
+    "train_steps_per_second": 0.007
+}

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
+  "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,
+  "quantization_config": {
+    "bnb_4bit_compute_dtype": "float16",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": false,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.36.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 1.0545984506607056,
+    "eval_runtime": 9.2861,
+    "eval_samples": 130,
+    "eval_samples_per_second": 5.061,
+    "eval_steps_per_second": 1.292
+}

runs/Jan12_21-18-43_98f107f1aa39/events.out.tfevents.1705094369.98f107f1aa39.690151.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:994170c0508a41ba5a33c1c454f77c84946d403bed37d8b9c11bac41b3d8d894
+size 4454

runs/Jan13_19-02-46_98f107f1aa39/events.out.tfevents.1705172710.98f107f1aa39.129514.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2deb67ebf2196af0e275c3db1fea6dd00bbb8a3aec437dbf96cc46fbcb318147
+size 4857

runs/Jan13_19-08-57_98f107f1aa39/events.out.tfevents.1705173116.98f107f1aa39.135205.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0418aaf4f4e34c5e8a7f4d7195be546ab8734fd13518daf5b21a9c369929b03e
+size 4857

runs/Jan13_19-15-57_98f107f1aa39/events.out.tfevents.1705173410.98f107f1aa39.140623.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e01f832704f0ed5f0d028b93878374f48bde7b61f67ae7019e2583d7afc535e
+size 5011

runs/Jan13_19-23-25_98f107f1aa39/events.out.tfevents.1705173982.98f107f1aa39.146842.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:826fc611d1288bf9146d9d14259f2ca0fc64fa6389bdca206612579e5e4089cd
+size 4857

runs/Jan13_19-27-51_98f107f1aa39/events.out.tfevents.1705174126.98f107f1aa39.150537.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24ec04663f35abe7f8249c5873aeac32e488d2fb900c9186f40492bf9a269f4a
+size 4857

runs/Jan13_19-31-59_98f107f1aa39/events.out.tfevents.1705174497.98f107f1aa39.154347.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19b23ffb1193103c8874ec5d6b80f396589fdaf1ea2fab93a29bb79b481a657f
+size 7235

runs/Jan13_19-31-59_98f107f1aa39/events.out.tfevents.1705179585.98f107f1aa39.154347.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:771da7e33030b7c506cff2ebedb68fd5813ed7af9fee67bbca483a22096bc161
+size 354

runs/Jan13_21-58-38_98f107f1aa39/events.out.tfevents.1705183294.98f107f1aa39.242277.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a28a9d3f0da08da4b1b876b1492bbd7d6affd9449a13c1543e6047e2e9802d5
+size 6154

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 +1,43 @@
+{
+  "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": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 1.1544433269235823,
+    "train_runtime": 5078.5964,
+    "train_samples": 29726,
+    "train_samples_per_second": 1.537,
+    "train_steps_per_second": 0.007
+}

trainer_state.json

@@ -0,0 +1,102 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9961568024596464,
+  "eval_steps": 10,
+  "global_step": 36,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 3.9923893961834914e-05,
+      "loss": 1.3268,
+      "step": 1
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 3.812615574073301e-05,
+      "loss": 1.2548,
+      "step": 5
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 3.285575219373079e-05,
+      "loss": 1.1912,
+      "step": 10
+    },
+    {
+      "epoch": 0.28,
+      "eval_loss": 1.109934687614441,
+      "eval_runtime": 9.2946,
+      "eval_samples_per_second": 5.057,
+      "eval_steps_per_second": 1.291,
+      "step": 10
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 2.5176380902050418e-05,
+      "loss": 1.1433,
+      "step": 15
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.6527036446661396e-05,
+      "loss": 1.1238,
+      "step": 20
+    },
+    {
+      "epoch": 0.55,
+      "eval_loss": 1.065536379814148,
+      "eval_runtime": 9.2887,
+      "eval_samples_per_second": 5.06,
+      "eval_steps_per_second": 1.292,
+      "step": 20
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 8.528471272979083e-06,
+      "loss": 1.1102,
+      "step": 25
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 2.679491924311226e-06,
+      "loss": 1.1258,
+      "step": 30
+    },
+    {
+      "epoch": 0.83,
+      "eval_loss": 1.055001974105835,
+      "eval_runtime": 9.2909,
+      "eval_samples_per_second": 5.059,
+      "eval_steps_per_second": 1.292,
+      "step": 30
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 7.61060381650891e-08,
+      "loss": 1.1272,
+      "step": 35
+    },
+    {
+      "epoch": 1.0,
+      "step": 36,
+      "total_flos": 1.0010669722946765e+17,
+      "train_loss": 1.1544433269235823,
+      "train_runtime": 5078.5964,
+      "train_samples_per_second": 1.537,
+      "train_steps_per_second": 0.007
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 36,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 20,
+  "total_flos": 1.0010669722946765e+17,
+  "train_batch_size": 6,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69c81ac88e2869ccda740542c6596332cca7e1d65acbd50f130aca7858c31f79
+size 4728