Model save

README.md

@@ -0,0 +1,66 @@
+---
+license: apache-2.0
+library_name: peft
+tags:
+- trl
+- sft
+- generated_from_trainer
+base_model: mistralai/Mistral-7B-Instruct-v0.1
+datasets:
+- generator
+model-index:
+- name: mistral-7b-sft-lora-tom-baseline
+  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. -->
+
+# mistral-7b-sft-lora-tom-baseline
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.4316
+
+## 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: 1
+- eval_batch_size: 1
+- seed: 42
+- gradient_accumulation_steps: 128
+- total_train_batch_size: 128
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 2
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| No log        | 1.0   | 1    | 1.4419          |
+| No log        | 2.0   | 2    | 1.4316          |
+
+
+### Framework versions
+
+- PEFT 0.10.1.dev0
+- Transformers 4.41.0.dev0
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.1",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "o_proj",
+    "v_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0beb6ddd773d95dac144b7617d2d2981ee4ceb36e1ea93686c309a8595f370d
+size 218138576

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.0,
+    "total_flos": 176091612315648.0,
+    "train_loss": 0.011341426521539688,
+    "train_runtime": 28.129,
+    "train_samples": 15,
+    "train_samples_per_second": 0.071,
+    "train_steps_per_second": 0.071
+}

runs/Apr18_22-58-46_ip-10-192-12-209/events.out.tfevents.1713481152.ip-10-192-12-209.2364.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e397ecc226a5d8ba85d3088ab7015de2a76c8936ee116fc4db95e52a5b6b5ad1
+size 5314

runs/Apr18_23-04-50_ip-10-192-12-209/events.out.tfevents.1713481505.ip-10-192-12-209.12403.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9a1a9766bcf05727ec981f19866307feb5a838ca25e675a1c276f29fde505eb
+size 5315

runs/Apr18_23-05-57_ip-10-192-12-209/events.out.tfevents.1713481568.ip-10-192-12-209.12403.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a78c72418abd70bc64e50c946b12097d73470c19438cba846c920c0fbbd6705
+size 5315

runs/Apr18_23-07-36_ip-10-192-12-209/events.out.tfevents.1713481664.ip-10-192-12-209.12403.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:971ee0c5cf46bcaf1228c14da77a6c78429163c35bb5a5e6de39deb261fd78d6
+size 5314

runs/Apr18_23-08-44_ip-10-192-12-209/events.out.tfevents.1713481737.ip-10-192-12-209.12403.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0db501944aba43c4a35ef416d472c65de9401ce6d5b8a6eb9301093d1186a702
+size 5315

runs/Apr18_23-10-03_ip-10-192-12-209/events.out.tfevents.1713481818.ip-10-192-12-209.12403.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4a44241b2e6f34a3ea84fcd15e18c28dfa63073ff8cc4289fd1365b38c7097c
+size 5315

runs/Apr18_23-15-04_ip-10-192-12-209/events.out.tfevents.1713482107.ip-10-192-12-209.27070.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41bca768cdc66d82d0bd4e96d9748716635f9daf0cfb7276ff52cd487590cd2a
+size 5929

runs/Apr19_07-15-52_ip-10-192-11-238/events.out.tfevents.1713510964.ip-10-192-11-238.2860.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c458a09f4f69ccaf3aabc3e7c380939dfa89f5735055b05ae67f42015dd35c9a
+size 5335

runs/Apr19_07-18-35_ip-10-192-11-238/events.out.tfevents.1713511165.ip-10-192-11-238.7026.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc34c92a7146d284d498ce1f22b7e4f1de1be74e72f27cc664509043feab63f9
+size 5335

runs/Apr19_07-33-41_ip-10-192-11-238/events.out.tfevents.1713512025.ip-10-192-11-238.7026.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a73df649dfb66864558c458c5b8cf650d4485788d2213228ca2952c62bec07eb
+size 6224

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_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
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token + ' ' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.0,
+    "total_flos": 176091612315648.0,
+    "train_loss": 0.011341426521539688,
+    "train_runtime": 28.129,
+    "train_samples": 15,
+    "train_samples_per_second": 0.071,
+    "train_steps_per_second": 0.071
+}

trainer_state.json

@@ -0,0 +1,46 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 2,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.441920280456543,
+      "eval_runtime": 3.7457,
+      "eval_samples_per_second": 0.267,
+      "eval_steps_per_second": 0.267,
+      "step": 1
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.4315892457962036,
+      "eval_runtime": 3.7937,
+      "eval_samples_per_second": 0.264,
+      "eval_steps_per_second": 0.264,
+      "step": 2
+    },
+    {
+      "epoch": 2.0,
+      "step": 2,
+      "total_flos": 176091612315648.0,
+      "train_loss": 0.011341426521539688,
+      "train_runtime": 28.129,
+      "train_samples_per_second": 0.071,
+      "train_steps_per_second": 0.071
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 2,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 176091612315648.0,
+  "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 sha256:9213336a2a272123f85149eb3c38922441610712326e372deb245e9b8de0bd86
+size 5176